diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/args.yaml b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/args.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7a1d3d1449c2645008bc100372450b579797d2a7 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/args.yaml @@ -0,0 +1,162 @@ +aa: rand-m9-mstd0.5-inc1 +act_fun: QGateGrad +adam_epoch: 1000 +adaptation_info: false +adaptive_node: false +alpha: 0.8 +amp: false +apex_amp: false +audio_path: /mnt/home/hexiang/datasets/CREMA-D/AudioWAV/ +aug_splits: 0 +batch_size: 32 +bn_eps: null +bn_momentum: null +bn_tf: false +channels_last: false +clip_grad: null +color_jitter: 0.4 +conf_mat: false +conv_type: normal +cooldown_epochs: 10 +critical_loss: false +crop_pct: null +cut_mix: false +cutmix: 0.0 +cutmix_beta: 2.0 +cutmix_minmax: null +cutmix_noise: 0.0 +cutmix_num: 1 +cutmix_prob: 0.5 +dataset: KineticSound +decay_epochs: 70 +decay_rate: 0.1 +device: 0 +dist_bn: '' +drop: 0.0 +drop_block: null +drop_connect: null +drop_path: 0.1 +encode: direct +epochs: 100 +eval: false +eval_checkpoint: '' +eval_metric: top1 +event_mix: false +event_size: 48 +fps: 1 +fusion_method: concat +gaussian_n: 3 +gp: null +hflip: 0.5 +img_size: 224 +initial_checkpoint: '' +interpolation: '' +inverse: false +inverse_ends: 100 +inverse_starts: 0 +jsd: false +kernel_method: cuda +layer_by_layer: false +local_rank: 0 +log_interval: 50 +loss_fn: ce +lr: 0.005 +lr_cycle_limit: 1 +lr_cycle_mul: 1.0 +lr_noise: null +lr_noise_pct: 0.67 +lr_noise_std: 1.0 +mean: null +mem_dist: false +meta_ratio: -1.0 +min_lr: 1.0e-05 +mix_up: false +mixup: 0.0 +mixup_mode: batch +mixup_off_epoch: 0 +mixup_prob: 0.0 +mixup_switch_prob: 0.5 +modality: audio-visual +model: AVresnet18 +model_ema: false +model_ema_decay: 0.99996 +model_ema_force_cpu: false +modulation: Normal +modulation_ends: 50 +modulation_starts: 0 +momentum: 0.9 +n_encode_type: linear +n_groups: 1 +n_preact: false +native_amp: false +newton_maxiter: 20 +no_aug: false +no_prefetcher: false +no_resume_opt: false +node_resume: '' +node_type: LIFNode +noisy_grad: 0.0 +num_classes: 31 +num_gpu: 1 +opt: sgd +opt_betas: null +opt_eps: 1.0e-08 +output: ./exp_results +patience_epochs: 10 +pin_mem: false +power: 1 +pretrained: false +psai: 1.0 +rand_aug: false +rand_step: false +randaug_m: 15 +randaug_n: 3 +ratio: +- 0.75 +- 1.3333333333333333 +recount: 1 +recovery_interval: 0 +remode: pixel +reprob: 0.25 +requires_thres_grad: false +reset_drop: false +resplit: false +resume: '' +save_images: false +scale: +- 0.08 +- 1.0 +sched: step +seed: 2025 +sew_cnf: ADD +sigmoid_thres: false +smoothing: 0.1 +snr: -100 +snrModality: null +spike_output: false +spike_rate: false +split_bn: false +start_epoch: null +std: null +step: 4 +suffix: '' +sync_bn: false +tau: 2.0 +temporal_flatten: false +tensorboard_dir: ./exp_results +tet_loss: false +threshold: 0.5 +train_interpolation: random +train_portion: 0.9 +tsne: false +tta: 0 +use_multi_epochs_loader: false +use_video_frames: 3 +validation_batch_size_multiplier: 1 +vflip: 0.0 +visual_path: /mnt/home/hexiang/datasets/CREMA-D/ +visualize: false +warmup_epochs: 0 +warmup_lr: 1.0e-06 +weight_decay: 0.0005 +workers: 8 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-18.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-18.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..cfebeea6a4d83b1416464a359a2a6a6513c6b05f --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-18.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725a2ecb9fbf7fe1401787f341a2c5634359273ed94e8e79027b54d10685ace4 +size 179373193 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/events.out.tfevents.1745049404.af1fd63cd999.1304305.0 b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/events.out.tfevents.1745049404.af1fd63cd999.1304305.0 new file mode 100644 index 0000000000000000000000000000000000000000..97b4015c9a388f2eeda3ec52b198e73ca2f20b5b --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/events.out.tfevents.1745049404.af1fd63cd999.1304305.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449918997efa67e11a0332b2d92578c97f8db82b1e24be00ea74eb4537163319 +size 12954544 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/last.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/last.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..7fb37c0b7c827cd77c1a35ebe04dde29d4c8d59a --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/last.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46acbe5047813ca9be0c7cc0b68fba0fefd1850ce945611d4f22f493cd2221e6 +size 179373193 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/log.txt b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..3c69f001e71a945edd786459f9907c641858e0b9 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/log.txt @@ -0,0 +1,1443 @@ +2025-04-19 07:56:44,447 - train: [ INFO] - Training with a single process on 1 GPUs. +2025-04-19 07:56:49,403 - train: [ INFO] - AMP not enabled. Training in float32. +2025-04-19 07:56:49,406 - train: [ INFO] - Scheduled epochs: 100 +2025-04-19 07:57:04,139 - train: [ INFO] - Train: 0 [ 0/461 ( 0%)] Loss: 3.647504 (3.6475) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 3.1250 ( 3.1250) Acc@5: 18.7500 (18.7500) Time: 14.716s, 2.17/s (14.716s, 2.17/s) LR: 5.000e-03 Data: 7.456 (7.456) +2025-04-19 07:57:22,679 - train: [ INFO] - Train: 0 [ 50/461 ( 11%)] Loss: 3.413835 (3.5307) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 18.7500 (10.9375) Acc@5: 28.1250 (23.4375) Time: 0.322s, 99.23/s (0.650s, 49.24/s) LR: 5.000e-03 Data: 0.000 (0.147) +2025-04-19 07:57:40,733 - train: [ INFO] - Train: 0 [ 100/461 ( 22%)] Loss: 2.888637 (3.3167) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 15.6250 (12.5000) Acc@5: 59.3750 (35.4167) Time: 0.319s, 100.39/s (0.505s, 63.32/s) LR: 5.000e-03 Data: 0.000 (0.075) +2025-04-19 07:57:59,847 - train: [ INFO] - Train: 0 [ 150/461 ( 33%)] Loss: 2.783587 (3.1834) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 21.8750 (14.8438) Acc@5: 59.3750 (41.4062) Time: 0.341s, 93.85/s (0.463s, 69.09/s) LR: 5.000e-03 Data: 0.000 (0.050) +2025-04-19 07:58:17,588 - train: [ INFO] - Train: 0 [ 200/461 ( 43%)] Loss: 2.395114 (3.0257) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (21.8750) Acc@5: 75.0000 (48.1250) Time: 0.356s, 89.79/s (0.436s, 73.42/s) LR: 5.000e-03 Data: 0.001 (0.038) +2025-04-19 07:58:35,794 - train: [ INFO] - Train: 0 [ 250/461 ( 54%)] Loss: 2.719778 (2.9747) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (23.9583) Acc@5: 62.5000 (50.5208) Time: 0.341s, 93.95/s (0.421s, 76.00/s) LR: 5.000e-03 Data: 0.005 (0.031) +2025-04-19 07:58:53,518 - train: [ INFO] - Train: 0 [ 300/461 ( 65%)] Loss: 2.599177 (2.9211) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 25.0000 (24.1071) Acc@5: 65.6250 (52.6786) Time: 0.333s, 96.10/s (0.409s, 78.17/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 07:59:12,264 - train: [ INFO] - Train: 0 [ 350/461 ( 76%)] Loss: 2.752683 (2.9000) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 21.8750 (23.8281) Acc@5: 65.6250 (54.2969) Time: 0.420s, 76.22/s (0.404s, 79.24/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 07:59:30,715 - train: [ INFO] - Train: 0 [ 400/461 ( 87%)] Loss: 2.840736 (2.8935) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 28.1250 (24.3056) Acc@5: 53.1250 (54.1667) Time: 0.324s, 98.89/s (0.399s, 80.19/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 07:59:48,417 - train: [ INFO] - Train: 0 [ 450/461 ( 98%)] Loss: 2.608861 (2.8650) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 28.1250 (24.6875) Acc@5: 65.6250 (55.3125) Time: 0.338s, 94.76/s (0.394s, 81.24/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 07:59:52,088 - train: [ INFO] - Train: 0 [ 460/461 (100%)] Loss: 2.617963 (2.8425) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (26.1364) Acc@5: 75.0000 (57.1023) Time: 0.319s, 100.33/s (0.393s, 81.36/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 08:00:00,283 - train: [ INFO] - Eval : 0 Time: 8.034 (8.034) Loss: 2.2243 (2.2243) Acc@1: 37.5000 (37.5000)Acc@5: 65.6250 (65.6250) +2025-04-19 08:00:16,440 - train: [ INFO] - Eval : 0 Time: 0.205 (0.474) Loss: 2.5174 (2.4231) Acc@1: 34.3750 (31.5564)Acc@5: 56.2500 (66.2990) +2025-04-19 08:00:23,599 - train: [ INFO] - Eval : 0 Time: 0.055 (0.382) Loss: 4.9932 (2.4138) Acc@1: 0.0000 (32.1511)Acc@5: 0.0000 (66.5767) +2025-04-19 08:00:34,364 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-0.pth.tar', 32.15111796453354) + +2025-04-19 08:00:38,443 - train: [ INFO] - Train: 1 [ 0/461 ( 0%)] Loss: 2.412565 (2.4126) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (40.6250) Acc@5: 68.7500 (68.7500) Time: 4.071s, 7.86/s (4.071s, 7.86/s) LR: 5.000e-03 Data: 3.568 (3.568) +2025-04-19 08:00:58,483 - train: [ INFO] - Train: 1 [ 50/461 ( 11%)] Loss: 2.757709 (2.5851) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (37.5000) Acc@5: 56.2500 (62.5000) Time: 0.416s, 76.95/s (0.468s, 68.42/s) LR: 5.000e-03 Data: 0.000 (0.071) +2025-04-19 08:01:16,318 - train: [ INFO] - Train: 1 [ 100/461 ( 22%)] Loss: 2.358969 (2.5097) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (37.5000) Acc@5: 75.0000 (66.6667) Time: 0.435s, 73.62/s (0.412s, 77.72/s) LR: 5.000e-03 Data: 0.006 (0.036) +2025-04-19 08:01:34,560 - train: [ INFO] - Train: 1 [ 150/461 ( 33%)] Loss: 2.160999 (2.4226) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (40.6250) Acc@5: 71.8750 (67.9688) Time: 0.335s, 95.51/s (0.395s, 80.99/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-19 08:01:52,861 - train: [ INFO] - Train: 1 [ 200/461 ( 43%)] Loss: 2.092480 (2.3565) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (42.5000) Acc@5: 84.3750 (71.2500) Time: 0.376s, 85.04/s (0.387s, 82.66/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 08:02:10,922 - train: [ INFO] - Train: 1 [ 250/461 ( 54%)] Loss: 2.444506 (2.3712) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 31.2500 (40.6250) Acc@5: 81.2500 (72.9167) Time: 0.336s, 95.34/s (0.381s, 83.94/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 08:02:29,295 - train: [ INFO] - Train: 1 [ 300/461 ( 65%)] Loss: 2.478326 (2.3865) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 28.1250 (38.8393) Acc@5: 71.8750 (72.7679) Time: 0.417s, 76.68/s (0.378s, 84.62/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 08:02:47,704 - train: [ INFO] - Train: 1 [ 350/461 ( 76%)] Loss: 2.429953 (2.3919) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (39.4531) Acc@5: 75.0000 (73.0469) Time: 0.495s, 64.67/s (0.376s, 84.99/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 08:03:05,553 - train: [ INFO] - Train: 1 [ 400/461 ( 87%)] Loss: 2.444465 (2.3978) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (39.5833) Acc@5: 62.5000 (71.8750) Time: 0.395s, 80.98/s (0.374s, 85.64/s) LR: 5.000e-03 Data: 0.001 (0.010) +2025-04-19 08:03:23,501 - train: [ INFO] - Train: 1 [ 450/461 ( 98%)] Loss: 2.390430 (2.3970) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 28.1250 (38.4375) Acc@5: 78.1250 (72.5000) Time: 0.310s, 103.19/s (0.372s, 86.07/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 08:03:26,995 - train: [ INFO] - Train: 1 [ 460/461 (100%)] Loss: 2.168202 (2.3762) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (39.2045) Acc@5: 75.0000 (72.7273) Time: 0.311s, 102.84/s (0.371s, 86.18/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 08:03:31,699 - train: [ INFO] - Eval : 1 Time: 4.354 (4.354) Loss: 2.3732 (2.3732) Acc@1: 31.2500 (31.2500)Acc@5: 71.8750 (71.8750) +2025-04-19 08:03:42,055 - train: [ INFO] - Eval : 1 Time: 0.196 (0.288) Loss: 2.4730 (2.2645) Acc@1: 37.5000 (35.7843)Acc@5: 59.3750 (70.3431) +2025-04-19 08:03:47,572 - train: [ INFO] - Eval : 1 Time: 0.050 (0.247) Loss: 4.9664 (2.2628) Acc@1: 0.0000 (35.5050)Acc@5: 0.0000 (70.1234) +2025-04-19 08:03:53,164 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-1.pth.tar', 35.50501156515035) + +2025-04-19 08:03:56,667 - train: [ INFO] - Train: 2 [ 0/461 ( 0%)] Loss: 1.951293 (1.9513) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (56.2500) Acc@5: 84.3750 (84.3750) Time: 3.466s, 9.23/s (3.466s, 9.23/s) LR: 5.000e-03 Data: 3.035 (3.035) +2025-04-19 08:04:16,334 - train: [ INFO] - Train: 2 [ 50/461 ( 11%)] Loss: 2.346133 (2.1487) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (48.4375) Acc@5: 75.0000 (79.6875) Time: 0.359s, 89.23/s (0.445s, 71.86/s) LR: 5.000e-03 Data: 0.000 (0.081) +2025-04-19 08:04:34,081 - train: [ INFO] - Train: 2 [ 100/461 ( 22%)] Loss: 2.116186 (2.1379) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (46.8750) Acc@5: 81.2500 (80.2083) Time: 0.323s, 99.20/s (0.399s, 80.26/s) LR: 5.000e-03 Data: 0.001 (0.041) +2025-04-19 08:04:52,573 - train: [ INFO] - Train: 2 [ 150/461 ( 33%)] Loss: 2.044540 (2.1145) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (47.6562) Acc@5: 81.2500 (80.4688) Time: 0.365s, 87.79/s (0.389s, 82.29/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-19 08:05:10,388 - train: [ INFO] - Train: 2 [ 200/461 ( 43%)] Loss: 2.091113 (2.1099) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (48.1250) Acc@5: 81.2500 (80.6250) Time: 0.391s, 81.75/s (0.380s, 84.10/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 08:05:29,205 - train: [ INFO] - Train: 2 [ 250/461 ( 54%)] Loss: 2.199543 (2.1248) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (46.3542) Acc@5: 81.2500 (80.7292) Time: 0.318s, 100.73/s (0.379s, 84.33/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 08:05:47,492 - train: [ INFO] - Train: 2 [ 300/461 ( 65%)] Loss: 2.375466 (2.1606) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (46.4286) Acc@5: 75.0000 (79.9107) Time: 0.363s, 88.14/s (0.377s, 84.87/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 08:06:06,181 - train: [ INFO] - Train: 2 [ 350/461 ( 76%)] Loss: 2.252375 (2.1721) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (45.7031) Acc@5: 75.0000 (79.2969) Time: 0.433s, 73.86/s (0.376s, 85.03/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 08:06:24,708 - train: [ INFO] - Train: 2 [ 400/461 ( 87%)] Loss: 2.063056 (2.1600) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (46.1806) Acc@5: 78.1250 (79.1667) Time: 0.335s, 95.52/s (0.375s, 85.22/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 08:06:42,225 - train: [ INFO] - Train: 2 [ 450/461 ( 98%)] Loss: 2.143361 (2.1583) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (46.8750) Acc@5: 87.5000 (80.0000) Time: 0.335s, 95.66/s (0.373s, 85.89/s) LR: 5.000e-03 Data: 0.001 (0.010) +2025-04-19 08:06:45,577 - train: [ INFO] - Train: 2 [ 460/461 (100%)] Loss: 2.361338 (2.1768) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (46.3068) Acc@5: 81.2500 (80.1136) Time: 0.384s, 83.37/s (0.372s, 86.08/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 08:06:50,486 - train: [ INFO] - Eval : 2 Time: 4.651 (4.651) Loss: 1.7513 (1.7513) Acc@1: 43.7500 (43.7500)Acc@5: 84.3750 (84.3750) +2025-04-19 08:07:00,826 - train: [ INFO] - Eval : 2 Time: 0.205 (0.294) Loss: 2.2371 (1.9379) Acc@1: 46.8750 (44.3627)Acc@5: 71.8750 (78.3088) +2025-04-19 08:07:06,303 - train: [ INFO] - Eval : 2 Time: 0.050 (0.250) Loss: 4.3726 (1.9477) Acc@1: 0.0000 (43.7934)Acc@5: 0.0000 (77.3323) +2025-04-19 08:07:11,007 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-2.pth.tar', 43.79336931380108) + +2025-04-19 08:07:15,524 - train: [ INFO] - Train: 3 [ 0/461 ( 0%)] Loss: 2.039525 (2.0395) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (46.8750) Acc@5: 84.3750 (84.3750) Time: 4.481s, 7.14/s (4.481s, 7.14/s) LR: 5.000e-03 Data: 3.874 (3.874) +2025-04-19 08:07:34,253 - train: [ INFO] - Train: 3 [ 50/461 ( 11%)] Loss: 1.808847 (1.9242) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (50.0000) Acc@5: 84.3750 (84.3750) Time: 0.346s, 92.49/s (0.451s, 70.89/s) LR: 5.000e-03 Data: 0.001 (0.077) +2025-04-19 08:07:52,880 - train: [ INFO] - Train: 3 [ 100/461 ( 22%)] Loss: 2.143408 (1.9973) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (52.0833) Acc@5: 81.2500 (83.3333) Time: 0.340s, 94.04/s (0.412s, 77.76/s) LR: 5.000e-03 Data: 0.001 (0.039) +2025-04-19 08:08:10,822 - train: [ INFO] - Train: 3 [ 150/461 ( 33%)] Loss: 2.057928 (2.0124) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (51.5625) Acc@5: 81.2500 (82.8125) Time: 0.379s, 84.35/s (0.392s, 81.55/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 08:08:29,439 - train: [ INFO] - Train: 3 [ 200/461 ( 43%)] Loss: 2.203670 (2.0507) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (51.2500) Acc@5: 71.8750 (80.6250) Time: 0.346s, 92.36/s (0.386s, 82.87/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 08:08:46,454 - train: [ INFO] - Train: 3 [ 250/461 ( 54%)] Loss: 1.817641 (2.0118) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (52.0833) Acc@5: 87.5000 (81.7708) Time: 0.377s, 84.90/s (0.377s, 84.92/s) LR: 5.000e-03 Data: 0.002 (0.016) +2025-04-19 08:09:04,932 - train: [ INFO] - Train: 3 [ 300/461 ( 65%)] Loss: 1.824198 (1.9850) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (53.1250) Acc@5: 87.5000 (82.5893) Time: 0.332s, 96.50/s (0.375s, 85.24/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 08:09:23,678 - train: [ INFO] - Train: 3 [ 350/461 ( 76%)] Loss: 1.661079 (1.9445) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (54.2969) Acc@5: 96.8750 (84.3750) Time: 0.337s, 95.00/s (0.375s, 85.35/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 08:09:41,645 - train: [ INFO] - Train: 3 [ 400/461 ( 87%)] Loss: 1.808321 (1.9294) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (55.9028) Acc@5: 81.2500 (84.0278) Time: 0.332s, 96.44/s (0.373s, 85.85/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 08:09:59,567 - train: [ INFO] - Train: 3 [ 450/461 ( 98%)] Loss: 2.139235 (1.9504) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (54.6875) Acc@5: 81.2500 (83.7500) Time: 0.326s, 98.17/s (0.371s, 86.28/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 08:10:03,202 - train: [ INFO] - Train: 3 [ 460/461 (100%)] Loss: 1.951486 (1.9505) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (54.5455) Acc@5: 81.2500 (83.5227) Time: 0.336s, 95.14/s (0.371s, 86.32/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 08:10:08,323 - train: [ INFO] - Eval : 3 Time: 4.836 (4.836) Loss: 1.9201 (1.9201) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-19 08:10:17,605 - train: [ INFO] - Eval : 3 Time: 0.162 (0.276) Loss: 1.8403 (1.9208) Acc@1: 53.1250 (44.9142)Acc@5: 71.8750 (77.9412) +2025-04-19 08:10:23,159 - train: [ INFO] - Eval : 3 Time: 0.051 (0.240) Loss: 3.2532 (1.9157) Acc@1: 0.0000 (44.4102)Acc@5: 50.0000 (77.9877) +2025-04-19 08:10:26,513 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-3.pth.tar', 44.41017733230532) + +2025-04-19 08:10:31,551 - train: [ INFO] - Train: 4 [ 0/461 ( 0%)] Loss: 1.581327 (1.5813) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (78.1250) Acc@5: 90.6250 (90.6250) Time: 4.979s, 6.43/s (4.979s, 6.43/s) LR: 5.000e-03 Data: 4.562 (4.562) +2025-04-19 08:10:50,085 - train: [ INFO] - Train: 4 [ 50/461 ( 11%)] Loss: 1.888843 (1.7351) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (68.7500) Acc@5: 84.3750 (87.5000) Time: 0.368s, 86.91/s (0.459s, 69.71/s) LR: 5.000e-03 Data: 0.001 (0.090) +2025-04-19 08:11:07,521 - train: [ INFO] - Train: 4 [ 100/461 ( 22%)] Loss: 1.861609 (1.7773) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (65.6250) Acc@5: 87.5000 (87.5000) Time: 0.347s, 92.22/s (0.403s, 79.46/s) LR: 5.000e-03 Data: 0.006 (0.046) +2025-04-19 08:11:25,231 - train: [ INFO] - Train: 4 [ 150/461 ( 33%)] Loss: 2.161565 (1.8733) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (58.5938) Acc@5: 81.2500 (85.9375) Time: 0.326s, 98.09/s (0.386s, 82.93/s) LR: 5.000e-03 Data: 0.001 (0.031) +2025-04-19 08:11:42,392 - train: [ INFO] - Train: 4 [ 200/461 ( 43%)] Loss: 2.301229 (1.9589) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (55.6250) Acc@5: 75.0000 (83.7500) Time: 0.371s, 86.36/s (0.375s, 85.43/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-19 08:11:59,581 - train: [ INFO] - Train: 4 [ 250/461 ( 54%)] Loss: 2.105668 (1.9834) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (55.7292) Acc@5: 78.1250 (82.8125) Time: 0.329s, 97.34/s (0.368s, 86.95/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 08:12:17,197 - train: [ INFO] - Train: 4 [ 300/461 ( 65%)] Loss: 1.916134 (1.9738) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (55.8036) Acc@5: 84.3750 (83.0357) Time: 0.334s, 95.86/s (0.365s, 87.65/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 08:12:35,287 - train: [ INFO] - Train: 4 [ 350/461 ( 76%)] Loss: 2.049760 (1.9833) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (54.6875) Acc@5: 81.2500 (82.8125) Time: 0.341s, 93.92/s (0.364s, 87.82/s) LR: 5.000e-03 Data: 0.002 (0.014) +2025-04-19 08:12:53,253 - train: [ INFO] - Train: 4 [ 400/461 ( 87%)] Loss: 1.914432 (1.9756) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (55.9028) Acc@5: 78.1250 (82.2917) Time: 0.410s, 77.97/s (0.363s, 88.03/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 08:13:10,508 - train: [ INFO] - Train: 4 [ 450/461 ( 98%)] Loss: 2.041384 (1.9822) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (56.2500) Acc@5: 81.2500 (82.1875) Time: 0.320s, 99.91/s (0.361s, 88.57/s) LR: 5.000e-03 Data: 0.003 (0.011) +2025-04-19 08:13:14,110 - train: [ INFO] - Train: 4 [ 460/461 (100%)] Loss: 1.709906 (1.9574) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (56.5341) Acc@5: 93.7500 (83.2386) Time: 0.330s, 96.98/s (0.361s, 88.58/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 08:13:18,517 - train: [ INFO] - Eval : 4 Time: 4.144 (4.144) Loss: 1.7737 (1.7737) Acc@1: 43.7500 (43.7500)Acc@5: 81.2500 (81.2500) +2025-04-19 08:15:08,477 - train: [ INFO] - Eval : 4 Time: 0.227 (2.237) Loss: 2.0883 (1.9309) Acc@1: 43.7500 (44.3015)Acc@5: 68.7500 (79.6569) +2025-04-19 08:15:13,419 - train: [ INFO] - Eval : 4 Time: 0.048 (1.452) Loss: 4.4816 (1.9151) Acc@1: 0.0000 (44.7571)Acc@5: 0.0000 (78.9900) +2025-04-19 08:15:16,635 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-4.pth.tar', 44.75713184271395) + +2025-04-19 08:15:21,369 - train: [ INFO] - Train: 5 [ 0/461 ( 0%)] Loss: 2.013274 (2.0133) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (56.2500) Acc@5: 81.2500 (81.2500) Time: 4.656s, 6.87/s (4.656s, 6.87/s) LR: 5.000e-03 Data: 4.147 (4.147) +2025-04-19 08:15:40,008 - train: [ INFO] - Train: 5 [ 50/461 ( 11%)] Loss: 1.945831 (1.9796) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (54.6875) Acc@5: 84.3750 (82.8125) Time: 0.328s, 97.42/s (0.448s, 71.49/s) LR: 5.000e-03 Data: 0.001 (0.083) +2025-04-19 08:15:58,000 - train: [ INFO] - Train: 5 [ 100/461 ( 22%)] Loss: 1.816027 (1.9250) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (59.3750) Acc@5: 87.5000 (84.3750) Time: 0.354s, 90.45/s (0.404s, 79.31/s) LR: 5.000e-03 Data: 0.001 (0.042) +2025-04-19 08:16:16,483 - train: [ INFO] - Train: 5 [ 150/461 ( 33%)] Loss: 1.558127 (1.8333) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (61.7188) Acc@5: 93.7500 (86.7188) Time: 0.399s, 80.29/s (0.392s, 81.69/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 08:16:34,023 - train: [ INFO] - Train: 5 [ 200/461 ( 43%)] Loss: 1.925553 (1.8518) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (60.6250) Acc@5: 87.5000 (86.8750) Time: 0.355s, 90.08/s (0.381s, 83.93/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-19 08:16:51,957 - train: [ INFO] - Train: 5 [ 250/461 ( 54%)] Loss: 1.911036 (1.8616) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (60.4167) Acc@5: 84.3750 (86.4583) Time: 0.340s, 94.20/s (0.377s, 84.96/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 08:17:10,665 - train: [ INFO] - Train: 5 [ 300/461 ( 65%)] Loss: 1.959947 (1.8757) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (59.3750) Acc@5: 84.3750 (86.1607) Time: 0.360s, 88.89/s (0.376s, 85.12/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 08:17:28,162 - train: [ INFO] - Train: 5 [ 350/461 ( 76%)] Loss: 1.775784 (1.8632) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (60.5469) Acc@5: 87.5000 (86.3281) Time: 0.325s, 98.39/s (0.372s, 86.00/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 08:17:46,410 - train: [ INFO] - Train: 5 [ 400/461 ( 87%)] Loss: 1.964544 (1.8745) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (59.7222) Acc@5: 87.5000 (86.4583) Time: 0.317s, 100.80/s (0.371s, 86.27/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 08:18:03,586 - train: [ INFO] - Train: 5 [ 450/461 ( 98%)] Loss: 1.964908 (1.8835) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (59.6875) Acc@5: 78.1250 (85.6250) Time: 0.398s, 80.42/s (0.368s, 87.04/s) LR: 5.000e-03 Data: 0.001 (0.010) +2025-04-19 08:18:06,968 - train: [ INFO] - Train: 5 [ 460/461 (100%)] Loss: 2.024040 (1.8963) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (57.9545) Acc@5: 87.5000 (85.7955) Time: 0.330s, 97.04/s (0.367s, 87.20/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 08:18:11,725 - train: [ INFO] - Eval : 5 Time: 4.483 (4.483) Loss: 1.9211 (1.9211) Acc@1: 40.6250 (40.6250)Acc@5: 81.2500 (81.2500) +2025-04-19 08:18:22,113 - train: [ INFO] - Eval : 5 Time: 0.162 (0.292) Loss: 1.9084 (1.8444) Acc@1: 56.2500 (46.8137)Acc@5: 75.0000 (78.9216) +2025-04-19 08:18:27,290 - train: [ INFO] - Eval : 5 Time: 0.149 (0.244) Loss: 3.8340 (1.8586) Acc@1: 0.0000 (46.8774)Acc@5: 0.0000 (78.2190) +2025-04-19 08:18:30,351 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-5.pth.tar', 46.87740940632228) + +2025-04-19 08:18:34,976 - train: [ INFO] - Train: 6 [ 0/461 ( 0%)] Loss: 1.995944 (1.9959) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (53.1250) Acc@5: 84.3750 (84.3750) Time: 4.597s, 6.96/s (4.597s, 6.96/s) LR: 5.000e-03 Data: 4.166 (4.166) +2025-04-19 08:18:52,815 - train: [ INFO] - Train: 6 [ 50/461 ( 11%)] Loss: 2.381546 (2.1887) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (46.8750) Acc@5: 65.6250 (75.0000) Time: 0.358s, 89.34/s (0.438s, 73.08/s) LR: 5.000e-03 Data: 0.001 (0.083) +2025-04-19 08:19:10,839 - train: [ INFO] - Train: 6 [ 100/461 ( 22%)] Loss: 1.456588 (1.9447) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (56.2500) Acc@5: 96.8750 (82.2917) Time: 0.386s, 82.83/s (0.398s, 80.32/s) LR: 5.000e-03 Data: 0.000 (0.042) +2025-04-19 08:19:28,157 - train: [ INFO] - Train: 6 [ 150/461 ( 33%)] Loss: 1.738267 (1.8931) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (59.3750) Acc@5: 87.5000 (83.5938) Time: 0.351s, 91.12/s (0.381s, 84.04/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-19 08:19:46,026 - train: [ INFO] - Train: 6 [ 200/461 ( 43%)] Loss: 2.105789 (1.9356) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (56.2500) Acc@5: 78.1250 (82.5000) Time: 0.349s, 91.60/s (0.375s, 85.43/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 08:20:03,405 - train: [ INFO] - Train: 6 [ 250/461 ( 54%)] Loss: 1.648073 (1.8877) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (57.8125) Acc@5: 87.5000 (83.3333) Time: 0.457s, 70.08/s (0.369s, 86.72/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 08:20:21,319 - train: [ INFO] - Train: 6 [ 300/461 ( 65%)] Loss: 2.245464 (1.9388) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (56.6964) Acc@5: 78.1250 (82.5893) Time: 0.328s, 97.71/s (0.367s, 87.19/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 08:20:45,107 - train: [ INFO] - Train: 6 [ 350/461 ( 76%)] Loss: 1.882363 (1.9318) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (57.4219) Acc@5: 87.5000 (83.2031) Time: 0.622s, 51.48/s (0.382s, 83.69/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 08:21:14,108 - train: [ INFO] - Train: 6 [ 400/461 ( 87%)] Loss: 1.445504 (1.8777) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (58.3333) Acc@5: 96.8750 (84.7222) Time: 0.609s, 52.51/s (0.407s, 78.65/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 08:21:43,550 - train: [ INFO] - Train: 6 [ 450/461 ( 98%)] Loss: 1.896851 (1.8796) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (58.7500) Acc@5: 84.3750 (84.6875) Time: 0.516s, 62.01/s (0.427s, 74.97/s) LR: 5.000e-03 Data: 0.001 (0.010) +2025-04-19 08:21:49,371 - train: [ INFO] - Train: 6 [ 460/461 (100%)] Loss: 1.678254 (1.8613) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (59.3750) Acc@5: 93.7500 (85.5114) Time: 0.536s, 59.71/s (0.430s, 74.40/s) LR: 5.000e-03 Data: 0.001 (0.010) +2025-04-19 08:21:54,873 - train: [ INFO] - Eval : 6 Time: 5.172 (5.172) Loss: 1.7319 (1.7319) Acc@1: 40.6250 (40.6250)Acc@5: 84.3750 (84.3750) +2025-04-19 08:22:07,715 - train: [ INFO] - Eval : 6 Time: 0.356 (0.353) Loss: 2.0826 (1.8335) Acc@1: 50.0000 (48.3456)Acc@5: 75.0000 (80.5760) +2025-04-19 08:22:15,180 - train: [ INFO] - Eval : 6 Time: 0.056 (0.311) Loss: 4.4038 (1.8515) Acc@1: 0.0000 (47.8412)Acc@5: 0.0000 (79.0671) +2025-04-19 08:22:19,084 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-6.pth.tar', 47.84117193523516) + +2025-04-19 08:22:25,271 - train: [ INFO] - Train: 7 [ 0/461 ( 0%)] Loss: 1.707847 (1.7078) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (59.3750) Acc@5: 90.6250 (90.6250) Time: 6.104s, 5.24/s (6.104s, 5.24/s) LR: 5.000e-03 Data: 5.503 (5.503) +2025-04-19 08:22:54,652 - train: [ INFO] - Train: 7 [ 50/461 ( 11%)] Loss: 1.702836 (1.7053) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (59.3750) Acc@5: 90.6250 (90.6250) Time: 0.692s, 46.24/s (0.693s, 46.17/s) LR: 5.000e-03 Data: 0.008 (0.110) +2025-04-19 08:23:21,589 - train: [ INFO] - Train: 7 [ 100/461 ( 22%)] Loss: 1.597865 (1.6695) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (65.6250) Acc@5: 90.6250 (90.6250) Time: 0.381s, 83.91/s (0.614s, 52.08/s) LR: 5.000e-03 Data: 0.001 (0.056) +2025-04-19 08:23:39,773 - train: [ INFO] - Train: 7 [ 150/461 ( 33%)] Loss: 1.869722 (1.7196) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (62.5000) Acc@5: 84.3750 (89.0625) Time: 0.393s, 81.37/s (0.531s, 60.27/s) LR: 5.000e-03 Data: 0.001 (0.037) +2025-04-19 08:23:58,910 - train: [ INFO] - Train: 7 [ 200/461 ( 43%)] Loss: 1.601442 (1.6959) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (63.1250) Acc@5: 93.7500 (90.0000) Time: 0.420s, 76.13/s (0.494s, 64.83/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-19 08:24:17,487 - train: [ INFO] - Train: 7 [ 250/461 ( 54%)] Loss: 1.458447 (1.6564) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (64.0625) Acc@5: 93.7500 (90.6250) Time: 0.336s, 95.26/s (0.469s, 68.23/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-19 08:24:35,923 - train: [ INFO] - Train: 7 [ 300/461 ( 65%)] Loss: 1.579475 (1.6454) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (64.7321) Acc@5: 93.7500 (91.0714) Time: 0.309s, 103.46/s (0.452s, 70.81/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 08:25:00,869 - train: [ INFO] - Train: 7 [ 350/461 ( 76%)] Loss: 1.789437 (1.6634) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (65.6250) Acc@5: 87.5000 (90.6250) Time: 0.758s, 42.24/s (0.458s, 69.81/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 08:25:34,221 - train: [ INFO] - Train: 7 [ 400/461 ( 87%)] Loss: 1.416244 (1.6359) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (66.6667) Acc@5: 100.0000 (91.6667) Time: 0.584s, 54.77/s (0.484s, 66.09/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 08:26:06,209 - train: [ INFO] - Train: 7 [ 450/461 ( 98%)] Loss: 1.586299 (1.6310) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (67.1875) Acc@5: 87.5000 (91.2500) Time: 0.604s, 53.01/s (0.501s, 63.84/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 08:26:13,053 - train: [ INFO] - Train: 7 [ 460/461 (100%)] Loss: 1.664175 (1.6340) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (67.3295) Acc@5: 87.5000 (90.9091) Time: 0.676s, 47.34/s (0.505s, 63.35/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 08:26:18,321 - train: [ INFO] - Eval : 7 Time: 4.686 (4.686) Loss: 1.7429 (1.7429) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-19 08:26:30,561 - train: [ INFO] - Eval : 7 Time: 0.242 (0.332) Loss: 2.1466 (1.8063) Acc@1: 53.1250 (49.7549)Acc@5: 71.8750 (79.5956) +2025-04-19 08:26:37,597 - train: [ INFO] - Eval : 7 Time: 0.058 (0.292) Loss: 4.0775 (1.8127) Acc@1: 0.0000 (49.3832)Acc@5: 0.0000 (79.7995) +2025-04-19 08:26:40,698 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-7.pth.tar', 49.38319198149576) + +2025-04-19 08:26:48,028 - train: [ INFO] - Train: 8 [ 0/461 ( 0%)] Loss: 1.473817 (1.4738) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (75.0000) Acc@5: 96.8750 (96.8750) Time: 7.280s, 4.40/s (7.280s, 4.40/s) LR: 5.000e-03 Data: 6.477 (6.477) +2025-04-19 08:27:20,741 - train: [ INFO] - Train: 8 [ 50/461 ( 11%)] Loss: 1.658552 (1.5662) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (73.4375) Acc@5: 81.2500 (89.0625) Time: 0.605s, 52.87/s (0.783s, 40.89/s) LR: 5.000e-03 Data: 0.001 (0.128) +2025-04-19 08:27:52,439 - train: [ INFO] - Train: 8 [ 100/461 ( 22%)] Loss: 1.332620 (1.4883) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (76.0417) Acc@5: 96.8750 (91.6667) Time: 0.772s, 41.43/s (0.708s, 45.21/s) LR: 5.000e-03 Data: 0.001 (0.065) +2025-04-19 08:28:24,649 - train: [ INFO] - Train: 8 [ 150/461 ( 33%)] Loss: 1.682060 (1.5368) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (73.4375) Acc@5: 90.6250 (91.4062) Time: 0.657s, 48.72/s (0.686s, 46.64/s) LR: 5.000e-03 Data: 0.000 (0.044) +2025-04-19 08:28:56,961 - train: [ INFO] - Train: 8 [ 200/461 ( 43%)] Loss: 1.806731 (1.5908) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (70.6250) Acc@5: 87.5000 (90.6250) Time: 0.568s, 56.38/s (0.675s, 47.39/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 08:29:31,001 - train: [ INFO] - Train: 8 [ 250/461 ( 54%)] Loss: 1.836716 (1.6317) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (67.7083) Acc@5: 81.2500 (89.0625) Time: 0.675s, 47.37/s (0.676s, 47.33/s) LR: 5.000e-03 Data: 0.001 (0.027) +2025-04-19 08:30:11,424 - train: [ INFO] - Train: 8 [ 300/461 ( 65%)] Loss: 1.683152 (1.6391) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (66.5179) Acc@5: 93.7500 (89.7321) Time: 0.907s, 35.27/s (0.697s, 45.88/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-19 08:30:46,622 - train: [ INFO] - Train: 8 [ 350/461 ( 76%)] Loss: 1.632022 (1.6382) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (65.6250) Acc@5: 90.6250 (89.8438) Time: 0.690s, 46.40/s (0.698s, 45.84/s) LR: 5.000e-03 Data: 0.001 (0.020) +2025-04-19 08:31:18,366 - train: [ INFO] - Train: 8 [ 400/461 ( 87%)] Loss: 1.951305 (1.6730) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (64.9306) Acc@5: 81.2500 (88.8889) Time: 0.731s, 43.76/s (0.690s, 46.37/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 08:31:54,741 - train: [ INFO] - Train: 8 [ 450/461 ( 98%)] Loss: 2.012124 (1.7069) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (63.7500) Acc@5: 78.1250 (87.8125) Time: 0.713s, 44.87/s (0.694s, 46.11/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 08:32:02,022 - train: [ INFO] - Train: 8 [ 460/461 (100%)] Loss: 1.690975 (1.7055) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (64.4886) Acc@5: 87.5000 (87.7841) Time: 0.848s, 37.71/s (0.695s, 46.07/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 08:32:07,143 - train: [ INFO] - Eval : 8 Time: 4.728 (4.728) Loss: 2.0319 (2.0319) Acc@1: 37.5000 (37.5000)Acc@5: 75.0000 (75.0000) +2025-04-19 08:32:20,551 - train: [ INFO] - Eval : 8 Time: 0.225 (0.356) Loss: 2.3896 (1.8151) Acc@1: 53.1250 (50.3064)Acc@5: 71.8750 (79.5343) +2025-04-19 08:32:28,123 - train: [ INFO] - Eval : 8 Time: 0.068 (0.314) Loss: 4.2015 (1.7927) Acc@1: 0.0000 (49.8072)Acc@5: 0.0000 (79.9152) +2025-04-19 08:32:31,648 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-8.pth.tar', 49.80724749421743) + +2025-04-19 08:32:36,897 - train: [ INFO] - Train: 9 [ 0/461 ( 0%)] Loss: 1.653752 (1.6538) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (71.8750) Acc@5: 90.6250 (90.6250) Time: 5.184s, 6.17/s (5.184s, 6.17/s) LR: 5.000e-03 Data: 4.404 (4.404) +2025-04-19 08:33:11,874 - train: [ INFO] - Train: 9 [ 50/461 ( 11%)] Loss: 1.448025 (1.5509) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (75.0000) Acc@5: 90.6250 (90.6250) Time: 0.637s, 50.20/s (0.784s, 40.82/s) LR: 5.000e-03 Data: 0.001 (0.087) +2025-04-19 08:33:46,098 - train: [ INFO] - Train: 9 [ 100/461 ( 22%)] Loss: 1.451768 (1.5178) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (76.0417) Acc@5: 84.3750 (88.5417) Time: 0.820s, 39.01/s (0.733s, 43.63/s) LR: 5.000e-03 Data: 0.001 (0.045) +2025-04-19 08:34:18,578 - train: [ INFO] - Train: 9 [ 150/461 ( 33%)] Loss: 1.481930 (1.5089) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (75.0000) Acc@5: 96.8750 (90.6250) Time: 0.747s, 42.85/s (0.705s, 45.40/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-19 08:34:53,901 - train: [ INFO] - Train: 9 [ 200/461 ( 43%)] Loss: 1.284744 (1.4640) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (75.0000) Acc@5: 100.0000 (92.5000) Time: 0.793s, 40.37/s (0.705s, 45.41/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-19 08:35:28,464 - train: [ INFO] - Train: 9 [ 250/461 ( 54%)] Loss: 1.420024 (1.4567) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (75.0000) Acc@5: 93.7500 (92.7083) Time: 0.583s, 54.88/s (0.702s, 45.62/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 08:36:03,364 - train: [ INFO] - Train: 9 [ 300/461 ( 65%)] Loss: 1.757256 (1.4996) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (71.8750) Acc@5: 93.7500 (92.8571) Time: 0.861s, 37.17/s (0.701s, 45.67/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 08:36:38,823 - train: [ INFO] - Train: 9 [ 350/461 ( 76%)] Loss: 1.417003 (1.4893) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (73.0469) Acc@5: 93.7500 (92.9688) Time: 0.620s, 51.61/s (0.702s, 45.62/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 08:37:13,726 - train: [ INFO] - Train: 9 [ 400/461 ( 87%)] Loss: 1.690322 (1.5116) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (71.8750) Acc@5: 87.5000 (92.3611) Time: 0.787s, 40.69/s (0.701s, 45.66/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:37:51,004 - train: [ INFO] - Train: 9 [ 450/461 ( 98%)] Loss: 1.721497 (1.5326) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (70.6250) Acc@5: 81.2500 (91.2500) Time: 0.805s, 39.74/s (0.705s, 45.36/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 08:37:58,766 - train: [ INFO] - Train: 9 [ 460/461 (100%)] Loss: 1.761967 (1.5535) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (69.8864) Acc@5: 93.7500 (91.4773) Time: 0.603s, 53.08/s (0.707s, 45.27/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 08:38:09,992 - train: [ INFO] - Eval : 9 Time: 10.845 (10.845) Loss: 1.8968 (1.8968) Acc@1: 56.2500 (56.2500)Acc@5: 78.1250 (78.1250) +2025-04-19 08:38:34,303 - train: [ INFO] - Eval : 9 Time: 0.307 (0.689) Loss: 1.8888 (1.8074) Acc@1: 56.2500 (50.6740)Acc@5: 81.2500 (80.0858) +2025-04-19 08:38:45,868 - train: [ INFO] - Eval : 9 Time: 0.071 (0.570) Loss: 4.6034 (1.8292) Acc@1: 0.0000 (49.8843)Acc@5: 50.0000 (79.4526) +2025-04-19 08:38:52,186 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-9.pth.tar', 49.88434849653046) + +2025-04-19 08:39:04,604 - train: [ INFO] - Train: 10 [ 0/461 ( 0%)] Loss: 1.620006 (1.6200) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (68.7500) Acc@5: 93.7500 (93.7500) Time: 12.258s, 2.61/s (12.258s, 2.61/s) LR: 5.000e-03 Data: 11.411 (11.411) +2025-04-19 08:39:40,879 - train: [ INFO] - Train: 10 [ 50/461 ( 11%)] Loss: 1.561257 (1.5906) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (70.3125) Acc@5: 90.6250 (92.1875) Time: 0.801s, 39.95/s (0.949s, 33.72/s) LR: 5.000e-03 Data: 0.004 (0.226) +2025-04-19 08:40:16,744 - train: [ INFO] - Train: 10 [ 100/461 ( 22%)] Loss: 1.328741 (1.5033) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (73.9583) Acc@5: 96.8750 (93.7500) Time: 0.676s, 47.35/s (0.832s, 38.44/s) LR: 5.000e-03 Data: 0.000 (0.114) +2025-04-19 08:40:50,890 - train: [ INFO] - Train: 10 [ 150/461 ( 33%)] Loss: 1.461713 (1.4929) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (73.4375) Acc@5: 96.8750 (94.5312) Time: 0.816s, 39.20/s (0.782s, 40.91/s) LR: 5.000e-03 Data: 0.006 (0.077) +2025-04-19 08:41:27,180 - train: [ INFO] - Train: 10 [ 200/461 ( 43%)] Loss: 1.705794 (1.5355) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (71.2500) Acc@5: 87.5000 (93.1250) Time: 0.778s, 41.13/s (0.768s, 41.67/s) LR: 5.000e-03 Data: 0.000 (0.058) +2025-04-19 08:42:04,657 - train: [ INFO] - Train: 10 [ 250/461 ( 54%)] Loss: 1.236509 (1.4857) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (73.9583) Acc@5: 100.0000 (94.2708) Time: 0.543s, 58.92/s (0.764s, 41.89/s) LR: 5.000e-03 Data: 0.006 (0.047) +2025-04-19 08:42:42,500 - train: [ INFO] - Train: 10 [ 300/461 ( 65%)] Loss: 1.605048 (1.5027) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (71.4286) Acc@5: 96.8750 (94.6429) Time: 0.820s, 39.00/s (0.762s, 41.98/s) LR: 5.000e-03 Data: 0.001 (0.039) +2025-04-19 08:43:22,860 - train: [ INFO] - Train: 10 [ 350/461 ( 76%)] Loss: 1.671406 (1.5238) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (70.7031) Acc@5: 93.7500 (94.5312) Time: 0.601s, 53.23/s (0.769s, 41.64/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 08:43:59,642 - train: [ INFO] - Train: 10 [ 400/461 ( 87%)] Loss: 1.266522 (1.4952) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (71.5278) Acc@5: 96.8750 (94.7917) Time: 0.947s, 33.79/s (0.764s, 41.87/s) LR: 5.000e-03 Data: 0.001 (0.030) +2025-04-19 08:44:38,364 - train: [ INFO] - Train: 10 [ 450/461 ( 98%)] Loss: 1.726229 (1.5183) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (71.5625) Acc@5: 84.3750 (93.7500) Time: 0.628s, 50.93/s (0.765s, 41.82/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 08:44:46,310 - train: [ INFO] - Train: 10 [ 460/461 (100%)] Loss: 1.503048 (1.5169) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (71.3068) Acc@5: 93.7500 (93.7500) Time: 0.766s, 41.77/s (0.766s, 41.79/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 08:44:52,072 - train: [ INFO] - Eval : 10 Time: 5.141 (5.141) Loss: 2.0580 (2.0580) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-19 08:45:05,542 - train: [ INFO] - Eval : 10 Time: 0.335 (0.365) Loss: 1.7310 (1.8675) Acc@1: 56.2500 (48.4681)Acc@5: 71.8750 (79.5956) +2025-04-19 08:45:13,191 - train: [ INFO] - Eval : 10 Time: 0.067 (0.320) Loss: 4.0338 (1.8784) Acc@1: 0.0000 (48.5736)Acc@5: 50.0000 (79.1056) +2025-04-19 08:45:23,004 - train: [ INFO] - Train: 11 [ 0/461 ( 0%)] Loss: 1.435956 (1.4360) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (65.6250) Acc@5: 96.8750 (96.8750) Time: 5.924s, 5.40/s (5.924s, 5.40/s) LR: 5.000e-03 Data: 5.090 (5.090) +2025-04-19 08:45:56,343 - train: [ INFO] - Train: 11 [ 50/461 ( 11%)] Loss: 1.377995 (1.4070) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (70.3125) Acc@5: 96.8750 (96.8750) Time: 0.622s, 51.44/s (0.766s, 41.79/s) LR: 5.000e-03 Data: 0.001 (0.101) +2025-04-19 08:46:29,600 - train: [ INFO] - Train: 11 [ 100/461 ( 22%)] Loss: 1.333508 (1.3825) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (72.9167) Acc@5: 96.8750 (96.8750) Time: 0.546s, 58.59/s (0.715s, 44.79/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-19 08:47:01,240 - train: [ INFO] - Train: 11 [ 150/461 ( 33%)] Loss: 1.296457 (1.3610) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (75.0000) Acc@5: 96.8750 (96.8750) Time: 0.688s, 46.54/s (0.687s, 46.59/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-19 08:47:31,768 - train: [ INFO] - Train: 11 [ 200/461 ( 43%)] Loss: 1.507900 (1.3904) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (75.0000) Acc@5: 90.6250 (95.6250) Time: 0.625s, 51.16/s (0.667s, 47.96/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 08:48:04,612 - train: [ INFO] - Train: 11 [ 250/461 ( 54%)] Loss: 1.371486 (1.3872) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (75.5208) Acc@5: 96.8750 (95.8333) Time: 0.683s, 46.82/s (0.665s, 48.13/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 08:48:37,357 - train: [ INFO] - Train: 11 [ 300/461 ( 65%)] Loss: 1.264547 (1.3697) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (76.7857) Acc@5: 96.8750 (95.9821) Time: 0.416s, 76.84/s (0.663s, 48.28/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 08:49:09,357 - train: [ INFO] - Train: 11 [ 350/461 ( 76%)] Loss: 1.387026 (1.3719) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (77.3438) Acc@5: 96.8750 (96.0938) Time: 0.711s, 45.00/s (0.659s, 48.54/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 08:49:43,240 - train: [ INFO] - Train: 11 [ 400/461 ( 87%)] Loss: 1.685846 (1.4067) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (75.6944) Acc@5: 93.7500 (95.8333) Time: 0.599s, 53.45/s (0.661s, 48.38/s) LR: 5.000e-03 Data: 0.009 (0.014) +2025-04-19 08:50:16,624 - train: [ INFO] - Train: 11 [ 450/461 ( 98%)] Loss: 1.339486 (1.4000) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (76.5625) Acc@5: 96.8750 (95.9375) Time: 0.638s, 50.13/s (0.662s, 48.34/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 08:50:23,665 - train: [ INFO] - Train: 11 [ 460/461 (100%)] Loss: 1.754754 (1.4323) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (75.0000) Acc@5: 87.5000 (95.1705) Time: 0.502s, 63.78/s (0.663s, 48.28/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:50:30,048 - train: [ INFO] - Eval : 11 Time: 6.041 (6.041) Loss: 1.9729 (1.9729) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-19 08:50:43,773 - train: [ INFO] - Eval : 11 Time: 0.240 (0.388) Loss: 2.0170 (1.8239) Acc@1: 53.1250 (49.9387)Acc@5: 78.1250 (80.8824) +2025-04-19 08:50:51,210 - train: [ INFO] - Eval : 11 Time: 0.079 (0.332) Loss: 4.7269 (1.8312) Acc@1: 0.0000 (49.6145)Acc@5: 0.0000 (80.6476) +2025-04-19 08:51:00,426 - train: [ INFO] - Train: 12 [ 0/461 ( 0%)] Loss: 1.135657 (1.1357) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (87.5000) Acc@5: 96.8750 (96.8750) Time: 5.337s, 6.00/s (5.337s, 6.00/s) LR: 5.000e-03 Data: 4.742 (4.742) +2025-04-19 08:51:39,233 - train: [ INFO] - Train: 12 [ 50/461 ( 11%)] Loss: 0.998443 (1.0670) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (93.7500) Acc@5: 100.0000 (98.4375) Time: 0.832s, 38.47/s (0.864s, 37.05/s) LR: 5.000e-03 Data: 0.000 (0.094) +2025-04-19 08:52:15,859 - train: [ INFO] - Train: 12 [ 100/461 ( 22%)] Loss: 1.181053 (1.1051) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (92.7083) Acc@5: 96.8750 (97.9167) Time: 0.833s, 38.39/s (0.798s, 40.11/s) LR: 5.000e-03 Data: 0.001 (0.048) +2025-04-19 08:52:51,685 - train: [ INFO] - Train: 12 [ 150/461 ( 33%)] Loss: 1.081942 (1.0993) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (92.1875) Acc@5: 100.0000 (98.4375) Time: 0.661s, 48.40/s (0.770s, 41.54/s) LR: 5.000e-03 Data: 0.002 (0.032) +2025-04-19 08:53:28,674 - train: [ INFO] - Train: 12 [ 200/461 ( 43%)] Loss: 1.048223 (1.0891) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (91.8750) Acc@5: 100.0000 (98.7500) Time: 0.663s, 48.29/s (0.762s, 41.98/s) LR: 5.000e-03 Data: 0.001 (0.025) +2025-04-19 08:54:00,576 - train: [ INFO] - Train: 12 [ 250/461 ( 54%)] Loss: 1.250603 (1.1160) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (89.0625) Acc@5: 96.8750 (98.4375) Time: 0.571s, 56.00/s (0.737s, 43.41/s) LR: 5.000e-03 Data: 0.001 (0.020) +2025-04-19 08:54:32,388 - train: [ INFO] - Train: 12 [ 300/461 ( 65%)] Loss: 1.104433 (1.1143) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (89.7321) Acc@5: 100.0000 (98.6607) Time: 0.506s, 63.28/s (0.720s, 44.46/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 08:55:06,050 - train: [ INFO] - Train: 12 [ 350/461 ( 76%)] Loss: 1.027213 (1.1034) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (90.6250) Acc@5: 100.0000 (98.8281) Time: 0.653s, 48.98/s (0.713s, 44.89/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 08:55:40,272 - train: [ INFO] - Train: 12 [ 400/461 ( 87%)] Loss: 1.233819 (1.1179) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (89.9306) Acc@5: 100.0000 (98.9583) Time: 0.725s, 44.13/s (0.709s, 45.14/s) LR: 5.000e-03 Data: 0.006 (0.013) +2025-04-19 08:56:13,101 - train: [ INFO] - Train: 12 [ 450/461 ( 98%)] Loss: 1.466507 (1.1528) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (87.8125) Acc@5: 93.7500 (98.4375) Time: 0.724s, 44.22/s (0.703s, 45.53/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:56:19,278 - train: [ INFO] - Train: 12 [ 460/461 (100%)] Loss: 1.228713 (1.1597) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (87.2159) Acc@5: 100.0000 (98.5795) Time: 0.598s, 53.53/s (0.701s, 45.65/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 08:56:25,629 - train: [ INFO] - Eval : 12 Time: 5.952 (5.952) Loss: 2.0329 (2.0329) Acc@1: 53.1250 (53.1250)Acc@5: 71.8750 (71.8750) +2025-04-19 08:56:39,070 - train: [ INFO] - Eval : 12 Time: 0.320 (0.380) Loss: 1.9418 (1.8684) Acc@1: 59.3750 (49.0809)Acc@5: 75.0000 (78.7377) +2025-04-19 08:56:46,278 - train: [ INFO] - Eval : 12 Time: 0.064 (0.324) Loss: 4.2518 (1.8691) Acc@1: 0.0000 (49.1519)Acc@5: 0.0000 (78.2190) +2025-04-19 08:56:56,640 - train: [ INFO] - Train: 13 [ 0/461 ( 0%)] Loss: 1.016780 (1.0168) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (93.7500) Acc@5: 100.0000 (100.0000) Time: 6.350s, 5.04/s (6.350s, 5.04/s) LR: 5.000e-03 Data: 5.512 (5.512) +2025-04-19 08:57:30,983 - train: [ INFO] - Train: 13 [ 50/461 ( 11%)] Loss: 1.065371 (1.0411) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (92.1875) Acc@5: 96.8750 (98.4375) Time: 0.588s, 54.45/s (0.795s, 40.24/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-19 08:58:02,867 - train: [ INFO] - Train: 13 [ 100/461 ( 22%)] Loss: 1.106071 (1.0627) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (90.6250) Acc@5: 100.0000 (98.9583) Time: 0.862s, 37.14/s (0.716s, 44.72/s) LR: 5.000e-03 Data: 0.001 (0.056) +2025-04-19 08:58:35,175 - train: [ INFO] - Train: 13 [ 150/461 ( 33%)] Loss: 1.006661 (1.0487) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (89.8438) Acc@5: 100.0000 (99.2188) Time: 0.760s, 42.09/s (0.692s, 46.23/s) LR: 5.000e-03 Data: 0.001 (0.037) +2025-04-19 08:59:06,473 - train: [ INFO] - Train: 13 [ 200/461 ( 43%)] Loss: 1.030937 (1.0452) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (90.6250) Acc@5: 100.0000 (99.3750) Time: 0.755s, 42.38/s (0.675s, 47.40/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-19 08:59:40,385 - train: [ INFO] - Train: 13 [ 250/461 ( 54%)] Loss: 1.131392 (1.0595) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (90.6250) Acc@5: 96.8750 (98.9583) Time: 0.669s, 47.81/s (0.675s, 47.37/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-19 09:00:11,906 - train: [ INFO] - Train: 13 [ 300/461 ( 65%)] Loss: 1.071671 (1.0613) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (90.6250) Acc@5: 100.0000 (99.1071) Time: 0.716s, 44.66/s (0.668s, 47.93/s) LR: 5.000e-03 Data: 0.010 (0.019) +2025-04-19 09:00:45,504 - train: [ INFO] - Train: 13 [ 350/461 ( 76%)] Loss: 1.210230 (1.0799) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (89.8438) Acc@5: 100.0000 (99.2188) Time: 0.570s, 56.16/s (0.668s, 47.90/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 09:01:18,463 - train: [ INFO] - Train: 13 [ 400/461 ( 87%)] Loss: 0.963612 (1.0670) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (90.2778) Acc@5: 100.0000 (99.3056) Time: 0.613s, 52.23/s (0.667s, 48.00/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 09:01:52,560 - train: [ INFO] - Train: 13 [ 450/461 ( 98%)] Loss: 1.037895 (1.0641) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (90.6250) Acc@5: 100.0000 (99.3750) Time: 0.586s, 54.59/s (0.668s, 47.90/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:01:58,455 - train: [ INFO] - Train: 13 [ 460/461 (100%)] Loss: 1.241471 (1.0802) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (90.0568) Acc@5: 93.7500 (98.8636) Time: 0.596s, 53.71/s (0.666s, 48.02/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:02:03,793 - train: [ INFO] - Eval : 13 Time: 4.974 (4.974) Loss: 2.0288 (2.0288) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-19 09:02:17,013 - train: [ INFO] - Eval : 13 Time: 0.277 (0.357) Loss: 1.9688 (1.9165) Acc@1: 53.1250 (48.7132)Acc@5: 75.0000 (78.0025) +2025-04-19 09:02:24,238 - train: [ INFO] - Eval : 13 Time: 0.063 (0.310) Loss: 4.4464 (1.9097) Acc@1: 0.0000 (49.0362)Acc@5: 0.0000 (77.4094) +2025-04-19 09:02:33,669 - train: [ INFO] - Train: 14 [ 0/461 ( 0%)] Loss: 0.967454 (0.9675) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (93.7500) Acc@5: 100.0000 (100.0000) Time: 5.864s, 5.46/s (5.864s, 5.46/s) LR: 5.000e-03 Data: 5.173 (5.173) +2025-04-19 09:03:07,377 - train: [ INFO] - Train: 14 [ 50/461 ( 11%)] Loss: 0.858681 (0.9131) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (96.8750) Acc@5: 100.0000 (100.0000) Time: 0.725s, 44.16/s (0.773s, 41.39/s) LR: 5.000e-03 Data: 0.001 (0.102) +2025-04-19 09:03:39,194 - train: [ INFO] - Train: 14 [ 100/461 ( 22%)] Loss: 1.075486 (0.9672) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (95.8333) Acc@5: 93.7500 (97.9167) Time: 0.602s, 53.15/s (0.704s, 45.42/s) LR: 5.000e-03 Data: 0.000 (0.052) +2025-04-19 09:04:11,669 - train: [ INFO] - Train: 14 [ 150/461 ( 33%)] Loss: 1.094930 (0.9991) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (93.7500) Acc@5: 100.0000 (98.4375) Time: 0.795s, 40.25/s (0.686s, 46.66/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-19 09:04:38,252 - train: [ INFO] - Train: 14 [ 200/461 ( 43%)] Loss: 0.919474 (0.9832) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (94.3750) Acc@5: 100.0000 (98.7500) Time: 0.678s, 47.21/s (0.646s, 49.51/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 09:05:09,810 - train: [ INFO] - Train: 14 [ 250/461 ( 54%)] Loss: 1.052528 (0.9948) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (92.7083) Acc@5: 100.0000 (98.9583) Time: 0.621s, 51.53/s (0.643s, 49.78/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 09:05:40,341 - train: [ INFO] - Train: 14 [ 300/461 ( 65%)] Loss: 0.881322 (0.9786) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (93.3036) Acc@5: 100.0000 (99.1071) Time: 0.705s, 45.38/s (0.637s, 50.23/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 09:06:12,899 - train: [ INFO] - Train: 14 [ 350/461 ( 76%)] Loss: 1.106079 (0.9945) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (92.5781) Acc@5: 96.8750 (98.8281) Time: 0.806s, 39.70/s (0.639s, 50.09/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 09:06:45,676 - train: [ INFO] - Train: 14 [ 400/461 ( 87%)] Loss: 0.978395 (0.9927) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (92.7083) Acc@5: 100.0000 (98.9583) Time: 0.736s, 43.50/s (0.641s, 49.94/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 09:07:15,804 - train: [ INFO] - Train: 14 [ 450/461 ( 98%)] Loss: 0.960631 (0.9895) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (92.8125) Acc@5: 100.0000 (99.0625) Time: 0.784s, 40.84/s (0.636s, 50.29/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:07:21,936 - train: [ INFO] - Train: 14 [ 460/461 (100%)] Loss: 0.898407 (0.9812) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (93.4659) Acc@5: 100.0000 (99.1477) Time: 0.602s, 53.14/s (0.636s, 50.33/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 09:07:29,446 - train: [ INFO] - Eval : 14 Time: 6.874 (6.874) Loss: 1.7127 (1.7127) Acc@1: 56.2500 (56.2500)Acc@5: 81.2500 (81.2500) +2025-04-19 09:07:42,834 - train: [ INFO] - Eval : 14 Time: 0.322 (0.397) Loss: 1.9411 (1.8448) Acc@1: 53.1250 (49.7549)Acc@5: 84.3750 (78.9828) +2025-04-19 09:07:50,308 - train: [ INFO] - Eval : 14 Time: 0.063 (0.338) Loss: 4.3189 (1.8703) Acc@1: 0.0000 (50.0771)Acc@5: 0.0000 (78.8743) +2025-04-19 09:07:54,840 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-14.pth.tar', 50.07710100231303) + +2025-04-19 09:08:00,272 - train: [ INFO] - Train: 15 [ 0/461 ( 0%)] Loss: 0.884849 (0.8848) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (93.7500) Acc@5: 100.0000 (100.0000) Time: 5.338s, 5.99/s (5.338s, 5.99/s) LR: 5.000e-03 Data: 4.640 (4.640) +2025-04-19 09:08:33,252 - train: [ INFO] - Train: 15 [ 50/461 ( 11%)] Loss: 0.864870 (0.8749) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (96.8750) Acc@5: 100.0000 (100.0000) Time: 0.584s, 54.80/s (0.749s, 42.70/s) LR: 5.000e-03 Data: 0.001 (0.092) +2025-04-19 09:09:04,360 - train: [ INFO] - Train: 15 [ 100/461 ( 22%)] Loss: 0.922638 (0.8908) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (95.8333) Acc@5: 100.0000 (100.0000) Time: 0.645s, 49.63/s (0.685s, 46.73/s) LR: 5.000e-03 Data: 0.000 (0.047) +2025-04-19 09:09:36,553 - train: [ INFO] - Train: 15 [ 150/461 ( 33%)] Loss: 0.893969 (0.8916) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.0938) Acc@5: 100.0000 (100.0000) Time: 0.575s, 55.66/s (0.670s, 47.73/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-19 09:10:06,223 - train: [ INFO] - Train: 15 [ 200/461 ( 43%)] Loss: 0.895574 (0.8924) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.2500) Acc@5: 96.8750 (99.3750) Time: 0.415s, 77.04/s (0.651s, 49.17/s) LR: 5.000e-03 Data: 0.028 (0.024) +2025-04-19 09:10:38,484 - train: [ INFO] - Train: 15 [ 250/461 ( 54%)] Loss: 0.839773 (0.8836) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (96.8750) Acc@5: 100.0000 (99.4792) Time: 0.682s, 46.92/s (0.649s, 49.28/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 09:11:10,113 - train: [ INFO] - Train: 15 [ 300/461 ( 65%)] Loss: 0.883958 (0.8837) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (97.3214) Acc@5: 100.0000 (99.5536) Time: 0.728s, 43.98/s (0.646s, 49.52/s) LR: 5.000e-03 Data: 0.003 (0.017) +2025-04-19 09:11:44,647 - train: [ INFO] - Train: 15 [ 350/461 ( 76%)] Loss: 0.970694 (0.8945) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (96.4844) Acc@5: 100.0000 (99.6094) Time: 0.458s, 69.89/s (0.652s, 49.08/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 09:12:14,901 - train: [ INFO] - Train: 15 [ 400/461 ( 87%)] Loss: 0.918233 (0.8972) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.5278) Acc@5: 96.8750 (99.3056) Time: 0.560s, 57.16/s (0.646s, 49.55/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 09:12:44,460 - train: [ INFO] - Train: 15 [ 450/461 ( 98%)] Loss: 0.838712 (0.8913) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (96.8750) Acc@5: 100.0000 (99.3750) Time: 0.594s, 53.90/s (0.640s, 50.03/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 09:12:50,934 - train: [ INFO] - Train: 15 [ 460/461 (100%)] Loss: 0.954139 (0.8970) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (99.4318) Time: 0.458s, 69.94/s (0.640s, 50.02/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:12:57,290 - train: [ INFO] - Eval : 15 Time: 5.897 (5.897) Loss: 2.0328 (2.0328) Acc@1: 40.6250 (40.6250)Acc@5: 71.8750 (71.8750) +2025-04-19 09:13:10,935 - train: [ INFO] - Eval : 15 Time: 0.274 (0.383) Loss: 1.7692 (1.8938) Acc@1: 56.2500 (49.0809)Acc@5: 78.1250 (77.3897) +2025-04-19 09:13:18,182 - train: [ INFO] - Eval : 15 Time: 0.077 (0.327) Loss: 3.2880 (1.8975) Acc@1: 0.0000 (48.9206)Acc@5: 50.0000 (77.7564) +2025-04-19 09:13:27,769 - train: [ INFO] - Train: 16 [ 0/461 ( 0%)] Loss: 0.798619 (0.7986) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.899s, 5.42/s (5.899s, 5.42/s) LR: 5.000e-03 Data: 5.180 (5.180) +2025-04-19 09:13:57,192 - train: [ INFO] - Train: 16 [ 50/461 ( 11%)] Loss: 0.820803 (0.8097) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.588s, 54.46/s (0.691s, 46.31/s) LR: 5.000e-03 Data: 0.005 (0.103) +2025-04-19 09:14:27,187 - train: [ INFO] - Train: 16 [ 100/461 ( 22%)] Loss: 0.819665 (0.8130) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.542s, 58.99/s (0.645s, 49.60/s) LR: 5.000e-03 Data: 0.001 (0.053) +2025-04-19 09:14:59,559 - train: [ INFO] - Train: 16 [ 150/461 ( 33%)] Loss: 0.846326 (0.8214) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.644s, 49.69/s (0.645s, 49.60/s) LR: 5.000e-03 Data: 0.000 (0.036) +2025-04-19 09:15:29,191 - train: [ INFO] - Train: 16 [ 200/461 ( 43%)] Loss: 0.837123 (0.8245) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.391s, 81.88/s (0.632s, 50.66/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 09:16:01,210 - train: [ INFO] - Train: 16 [ 250/461 ( 54%)] Loss: 0.848800 (0.8286) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.588s, 54.38/s (0.633s, 50.55/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 09:16:33,533 - train: [ INFO] - Train: 16 [ 300/461 ( 65%)] Loss: 0.951908 (0.8462) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (98.6607) Acc@5: 100.0000 (100.0000) Time: 0.864s, 37.03/s (0.635s, 50.40/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 09:17:03,642 - train: [ INFO] - Train: 16 [ 350/461 ( 76%)] Loss: 0.797869 (0.8401) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8281) Acc@5: 100.0000 (100.0000) Time: 0.568s, 56.38/s (0.630s, 50.79/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 09:17:35,586 - train: [ INFO] - Train: 16 [ 400/461 ( 87%)] Loss: 0.839297 (0.8400) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.641s, 49.91/s (0.631s, 50.73/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 09:18:03,404 - train: [ INFO] - Train: 16 [ 450/461 ( 98%)] Loss: 0.809857 (0.8370) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (100.0000) Time: 0.636s, 50.33/s (0.622s, 51.42/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:18:09,421 - train: [ INFO] - Train: 16 [ 460/461 (100%)] Loss: 0.954356 (0.8477) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (98.2955) Acc@5: 96.8750 (99.7159) Time: 0.560s, 57.12/s (0.622s, 51.46/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:18:14,809 - train: [ INFO] - Eval : 16 Time: 5.002 (5.002) Loss: 2.0130 (2.0130) Acc@1: 40.6250 (40.6250)Acc@5: 68.7500 (68.7500) +2025-04-19 09:18:25,706 - train: [ INFO] - Eval : 16 Time: 0.162 (0.312) Loss: 2.0594 (1.8710) Acc@1: 50.0000 (49.6324)Acc@5: 75.0000 (77.5123) +2025-04-19 09:18:32,337 - train: [ INFO] - Eval : 16 Time: 0.066 (0.275) Loss: 2.1531 (1.8760) Acc@1: 50.0000 (49.7687)Acc@5: 100.0000 (77.8720) +2025-04-19 09:18:40,740 - train: [ INFO] - Train: 17 [ 0/461 ( 0%)] Loss: 0.783196 (0.7832) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.027s, 6.37/s (5.027s, 6.37/s) LR: 5.000e-03 Data: 4.379 (4.379) +2025-04-19 09:19:11,328 - train: [ INFO] - Train: 17 [ 50/461 ( 11%)] Loss: 0.750299 (0.7667) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.531s, 60.23/s (0.695s, 46.05/s) LR: 5.000e-03 Data: 0.000 (0.087) +2025-04-19 09:19:40,341 - train: [ INFO] - Train: 17 [ 100/461 ( 22%)] Loss: 0.783538 (0.7723) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.636s, 50.30/s (0.637s, 50.25/s) LR: 5.000e-03 Data: 0.000 (0.045) +2025-04-19 09:20:11,851 - train: [ INFO] - Train: 17 [ 150/461 ( 33%)] Loss: 0.808805 (0.7815) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.488s, 65.56/s (0.634s, 50.48/s) LR: 5.000e-03 Data: 0.001 (0.030) +2025-04-19 09:20:41,862 - train: [ INFO] - Train: 17 [ 200/461 ( 43%)] Loss: 0.808077 (0.7868) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.491s, 65.15/s (0.625s, 51.19/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-19 09:21:13,194 - train: [ INFO] - Train: 17 [ 250/461 ( 54%)] Loss: 0.809702 (0.7906) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.709s, 45.12/s (0.625s, 51.19/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 09:21:45,493 - train: [ INFO] - Train: 17 [ 300/461 ( 65%)] Loss: 0.763733 (0.7868) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.692s, 46.21/s (0.628s, 50.94/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 09:22:16,400 - train: [ INFO] - Train: 17 [ 350/461 ( 76%)] Loss: 0.851158 (0.7948) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.485s, 66.03/s (0.627s, 51.08/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 09:22:46,237 - train: [ INFO] - Train: 17 [ 400/461 ( 87%)] Loss: 0.792304 (0.7945) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.623s, 51.33/s (0.623s, 51.40/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 09:23:17,425 - train: [ INFO] - Train: 17 [ 450/461 ( 98%)] Loss: 0.818417 (0.7969) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 100.0000 (100.0000) Time: 0.715s, 44.77/s (0.623s, 51.40/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:23:23,441 - train: [ INFO] - Train: 17 [ 460/461 (100%)] Loss: 0.802764 (0.7975) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8636) Acc@5: 100.0000 (100.0000) Time: 0.590s, 54.26/s (0.622s, 51.45/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:23:29,937 - train: [ INFO] - Eval : 17 Time: 6.078 (6.078) Loss: 1.8699 (1.8699) Acc@1: 53.1250 (53.1250)Acc@5: 78.1250 (78.1250) +2025-04-19 09:23:43,305 - train: [ INFO] - Eval : 17 Time: 0.259 (0.381) Loss: 1.8769 (1.8183) Acc@1: 50.0000 (51.5319)Acc@5: 81.2500 (78.6152) +2025-04-19 09:23:50,295 - train: [ INFO] - Eval : 17 Time: 0.067 (0.322) Loss: 3.2260 (1.8158) Acc@1: 0.0000 (51.5420)Acc@5: 50.0000 (78.7587) +2025-04-19 09:23:54,639 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-17.pth.tar', 51.5420200462606) + +2025-04-19 09:23:59,668 - train: [ INFO] - Train: 18 [ 0/461 ( 0%)] Loss: 0.754900 (0.7549) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.969s, 6.44/s (4.969s, 6.44/s) LR: 5.000e-03 Data: 4.254 (4.254) +2025-04-19 09:24:30,808 - train: [ INFO] - Train: 18 [ 50/461 ( 11%)] Loss: 0.779104 (0.7670) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.536s, 59.66/s (0.705s, 45.39/s) LR: 5.000e-03 Data: 0.000 (0.084) +2025-04-19 09:25:03,543 - train: [ INFO] - Train: 18 [ 100/461 ( 22%)] Loss: 0.894584 (0.8095) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.378s, 84.67/s (0.679s, 47.15/s) LR: 5.000e-03 Data: 0.002 (0.044) +2025-04-19 09:25:33,111 - train: [ INFO] - Train: 18 [ 150/461 ( 33%)] Loss: 0.788056 (0.8042) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.761s, 42.05/s (0.649s, 49.30/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 09:26:05,786 - train: [ INFO] - Train: 18 [ 200/461 ( 43%)] Loss: 0.740761 (0.7915) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.557s, 57.44/s (0.649s, 49.28/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-19 09:26:36,778 - train: [ INFO] - Train: 18 [ 250/461 ( 54%)] Loss: 0.821656 (0.7965) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.645s, 49.61/s (0.643s, 49.78/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 09:27:09,985 - train: [ INFO] - Train: 18 [ 300/461 ( 65%)] Loss: 0.994121 (0.8247) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (97.7679) Acc@5: 93.7500 (98.6607) Time: 0.540s, 59.30/s (0.646s, 49.52/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 09:27:42,539 - train: [ INFO] - Train: 18 [ 350/461 ( 76%)] Loss: 0.769551 (0.8178) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.0469) Acc@5: 100.0000 (98.8281) Time: 0.634s, 50.48/s (0.646s, 49.50/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:28:13,996 - train: [ INFO] - Train: 18 [ 400/461 ( 87%)] Loss: 0.782333 (0.8139) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.9167) Acc@5: 100.0000 (98.9583) Time: 0.584s, 54.84/s (0.644s, 49.69/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 09:28:45,017 - train: [ INFO] - Train: 18 [ 450/461 ( 98%)] Loss: 0.756771 (0.8082) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.1250) Acc@5: 100.0000 (99.0625) Time: 0.437s, 73.26/s (0.641s, 49.90/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:28:51,332 - train: [ INFO] - Train: 18 [ 460/461 (100%)] Loss: 0.751822 (0.8031) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.2955) Acc@5: 100.0000 (99.1477) Time: 0.577s, 55.50/s (0.641s, 49.93/s) LR: 5.000e-03 Data: 0.001 (0.010) +2025-04-19 09:28:56,720 - train: [ INFO] - Eval : 18 Time: 5.025 (5.025) Loss: 1.7016 (1.7016) Acc@1: 53.1250 (53.1250)Acc@5: 84.3750 (84.3750) +2025-04-19 09:29:09,608 - train: [ INFO] - Eval : 18 Time: 0.272 (0.351) Loss: 1.8127 (1.7805) Acc@1: 59.3750 (53.0637)Acc@5: 81.2500 (78.9828) +2025-04-19 09:29:16,683 - train: [ INFO] - Eval : 18 Time: 0.067 (0.305) Loss: 2.6059 (1.7803) Acc@1: 0.0000 (52.8527)Acc@5: 100.0000 (79.2213) +2025-04-19 09:29:20,180 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-18.pth.tar', 52.85273708558211) + +2025-04-19 09:29:26,311 - train: [ INFO] - Train: 19 [ 0/461 ( 0%)] Loss: 0.756193 (0.7562) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.030s, 5.31/s (6.030s, 5.31/s) LR: 5.000e-03 Data: 5.185 (5.185) +2025-04-19 09:29:57,884 - train: [ INFO] - Train: 19 [ 50/461 ( 11%)] Loss: 0.717715 (0.7370) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.657s, 48.73/s (0.734s, 43.60/s) LR: 5.000e-03 Data: 0.000 (0.104) +2025-04-19 09:30:30,779 - train: [ INFO] - Train: 19 [ 100/461 ( 22%)] Loss: 0.736008 (0.7366) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.661s, 48.39/s (0.695s, 46.02/s) LR: 5.000e-03 Data: 0.000 (0.053) +2025-04-19 09:30:59,046 - train: [ INFO] - Train: 19 [ 150/461 ( 33%)] Loss: 0.753918 (0.7410) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.476s, 67.22/s (0.652s, 49.09/s) LR: 5.000e-03 Data: 0.001 (0.036) +2025-04-19 09:31:30,486 - train: [ INFO] - Train: 19 [ 200/461 ( 43%)] Loss: 0.739303 (0.7406) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.472s, 67.73/s (0.646s, 49.56/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 09:31:57,936 - train: [ INFO] - Train: 19 [ 250/461 ( 54%)] Loss: 0.754063 (0.7429) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.735s, 43.56/s (0.626s, 51.13/s) LR: 5.000e-03 Data: 0.039 (0.022) +2025-04-19 09:32:28,848 - train: [ INFO] - Train: 19 [ 300/461 ( 65%)] Loss: 0.729276 (0.7409) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.646s, 49.52/s (0.624s, 51.29/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 09:33:02,078 - train: [ INFO] - Train: 19 [ 350/461 ( 76%)] Loss: 0.739905 (0.7408) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.807s, 39.67/s (0.629s, 50.85/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 09:33:33,413 - train: [ INFO] - Train: 19 [ 400/461 ( 87%)] Loss: 0.767221 (0.7437) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.555s, 57.69/s (0.629s, 50.89/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 09:34:03,274 - train: [ INFO] - Train: 19 [ 450/461 ( 98%)] Loss: 0.759234 (0.7453) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.389s, 82.31/s (0.625s, 51.19/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:34:09,449 - train: [ INFO] - Train: 19 [ 460/461 (100%)] Loss: 0.761785 (0.7468) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.635s, 50.40/s (0.625s, 51.21/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:34:16,545 - train: [ INFO] - Eval : 19 Time: 6.728 (6.728) Loss: 1.6481 (1.6481) Acc@1: 59.3750 (59.3750)Acc@5: 75.0000 (75.0000) +2025-04-19 09:34:30,067 - train: [ INFO] - Eval : 19 Time: 0.334 (0.397) Loss: 1.7376 (1.8448) Acc@1: 50.0000 (50.9191)Acc@5: 84.3750 (76.7770) +2025-04-19 09:34:37,718 - train: [ INFO] - Eval : 19 Time: 0.058 (0.340) Loss: 3.0346 (1.8264) Acc@1: 0.0000 (51.5035)Acc@5: 50.0000 (77.5251) +2025-04-19 09:34:46,993 - train: [ INFO] - Train: 20 [ 0/461 ( 0%)] Loss: 0.798992 (0.7990) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.472s, 5.85/s (5.472s, 5.85/s) LR: 5.000e-03 Data: 4.914 (4.914) +2025-04-19 09:35:19,604 - train: [ INFO] - Train: 20 [ 50/461 ( 11%)] Loss: 0.744958 (0.7720) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.743s, 43.09/s (0.743s, 43.06/s) LR: 5.000e-03 Data: 0.000 (0.098) +2025-04-19 09:35:52,304 - train: [ INFO] - Train: 20 [ 100/461 ( 22%)] Loss: 0.744549 (0.7628) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.835s, 38.33/s (0.697s, 45.91/s) LR: 5.000e-03 Data: 0.000 (0.050) +2025-04-19 09:36:19,548 - train: [ INFO] - Train: 20 [ 150/461 ( 33%)] Loss: 0.847722 (0.7841) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (99.2188) Time: 0.789s, 40.55/s (0.646s, 49.54/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 09:36:53,680 - train: [ INFO] - Train: 20 [ 200/461 ( 43%)] Loss: 0.725523 (0.7723) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.767s, 41.70/s (0.654s, 48.90/s) LR: 5.000e-03 Data: 0.001 (0.026) +2025-04-19 09:37:24,236 - train: [ INFO] - Train: 20 [ 250/461 ( 54%)] Loss: 0.772203 (0.7723) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.4792) Time: 0.754s, 42.42/s (0.646s, 49.57/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 09:37:56,094 - train: [ INFO] - Train: 20 [ 300/461 ( 65%)] Loss: 0.732616 (0.7667) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6607) Acc@5: 100.0000 (99.5536) Time: 0.599s, 53.41/s (0.644s, 49.71/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 09:38:28,177 - train: [ INFO] - Train: 20 [ 350/461 ( 76%)] Loss: 0.725162 (0.7615) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8281) Acc@5: 100.0000 (99.6094) Time: 0.777s, 41.18/s (0.643s, 49.76/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 09:39:00,859 - train: [ INFO] - Train: 20 [ 400/461 ( 87%)] Loss: 0.747913 (0.7600) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.6528) Time: 0.628s, 50.92/s (0.644s, 49.68/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:39:33,977 - train: [ INFO] - Train: 20 [ 450/461 ( 98%)] Loss: 0.736651 (0.7576) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.6875) Time: 0.519s, 61.62/s (0.646s, 49.55/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 09:39:41,779 - train: [ INFO] - Train: 20 [ 460/461 (100%)] Loss: 0.738633 (0.7559) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.7159) Time: 0.562s, 56.94/s (0.649s, 49.33/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 09:39:47,753 - train: [ INFO] - Eval : 20 Time: 5.260 (5.260) Loss: 1.6940 (1.6940) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 09:40:01,478 - train: [ INFO] - Eval : 20 Time: 0.320 (0.372) Loss: 1.6968 (1.8313) Acc@1: 59.3750 (50.4902)Acc@5: 81.2500 (78.7377) +2025-04-19 09:40:08,642 - train: [ INFO] - Eval : 20 Time: 0.056 (0.319) Loss: 3.2561 (1.8338) Acc@1: 0.0000 (50.3855)Acc@5: 50.0000 (78.7587) +2025-04-19 09:40:19,636 - train: [ INFO] - Train: 21 [ 0/461 ( 0%)] Loss: 0.763765 (0.7638) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.900s, 5.42/s (5.900s, 5.42/s) LR: 5.000e-03 Data: 5.069 (5.069) +2025-04-19 09:40:53,609 - train: [ INFO] - Train: 21 [ 50/461 ( 11%)] Loss: 0.744252 (0.7540) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.833s, 38.42/s (0.779s, 41.08/s) LR: 5.000e-03 Data: 0.000 (0.101) +2025-04-19 09:41:22,926 - train: [ INFO] - Train: 21 [ 100/461 ( 22%)] Loss: 0.725754 (0.7446) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.391s, 81.94/s (0.682s, 46.89/s) LR: 5.000e-03 Data: 0.001 (0.051) +2025-04-19 09:41:50,918 - train: [ INFO] - Train: 21 [ 150/461 ( 33%)] Loss: 0.755337 (0.7473) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.728s, 43.97/s (0.641s, 49.91/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-19 09:42:17,812 - train: [ INFO] - Train: 21 [ 200/461 ( 43%)] Loss: 0.718780 (0.7416) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.653s, 49.04/s (0.615s, 52.05/s) LR: 5.000e-03 Data: 0.003 (0.026) +2025-04-19 09:42:48,212 - train: [ INFO] - Train: 21 [ 250/461 ( 54%)] Loss: 0.733827 (0.7403) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.771s, 41.51/s (0.613s, 52.19/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 09:43:19,254 - train: [ INFO] - Train: 21 [ 300/461 ( 65%)] Loss: 0.738026 (0.7400) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.762s, 42.00/s (0.614s, 52.11/s) LR: 5.000e-03 Data: 0.002 (0.018) +2025-04-19 09:43:51,518 - train: [ INFO] - Train: 21 [ 350/461 ( 76%)] Loss: 0.737908 (0.7397) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.622s, 51.42/s (0.618s, 51.77/s) LR: 5.000e-03 Data: 0.010 (0.016) +2025-04-19 09:44:22,230 - train: [ INFO] - Train: 21 [ 400/461 ( 87%)] Loss: 0.812958 (0.7478) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.648s, 49.37/s (0.617s, 51.83/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 09:44:56,074 - train: [ INFO] - Train: 21 [ 450/461 ( 98%)] Loss: 0.787329 (0.7518) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.764s, 41.87/s (0.624s, 51.32/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 09:45:03,026 - train: [ INFO] - Train: 21 [ 460/461 (100%)] Loss: 0.718354 (0.7488) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.727s, 44.02/s (0.625s, 51.20/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 09:45:09,692 - train: [ INFO] - Eval : 21 Time: 6.226 (6.226) Loss: 1.7818 (1.7818) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-19 09:45:22,784 - train: [ INFO] - Eval : 21 Time: 0.175 (0.379) Loss: 1.7946 (1.8193) Acc@1: 53.1250 (51.5931)Acc@5: 81.2500 (78.0637) +2025-04-19 09:45:30,083 - train: [ INFO] - Eval : 21 Time: 0.053 (0.325) Loss: 2.6631 (1.8161) Acc@1: 0.0000 (51.4649)Acc@5: 100.0000 (78.5274) +2025-04-19 09:45:41,149 - train: [ INFO] - Train: 22 [ 0/461 ( 0%)] Loss: 0.724546 (0.7245) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.283s, 4.39/s (7.283s, 4.39/s) LR: 5.000e-03 Data: 6.621 (6.621) +2025-04-19 09:46:14,418 - train: [ INFO] - Train: 22 [ 50/461 ( 11%)] Loss: 0.741148 (0.7328) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.784s, 40.84/s (0.792s, 40.41/s) LR: 5.000e-03 Data: 0.000 (0.131) +2025-04-19 09:46:47,204 - train: [ INFO] - Train: 22 [ 100/461 ( 22%)] Loss: 0.724096 (0.7299) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.656s, 48.75/s (0.723s, 44.25/s) LR: 5.000e-03 Data: 0.001 (0.067) +2025-04-19 09:47:18,824 - train: [ INFO] - Train: 22 [ 150/461 ( 33%)] Loss: 0.721073 (0.7277) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.876s, 36.53/s (0.692s, 46.23/s) LR: 5.000e-03 Data: 0.000 (0.045) +2025-04-19 09:47:49,251 - train: [ INFO] - Train: 22 [ 200/461 ( 43%)] Loss: 0.785096 (0.7392) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.406s, 78.81/s (0.671s, 47.72/s) LR: 5.000e-03 Data: 0.001 (0.034) +2025-04-19 09:48:23,814 - train: [ INFO] - Train: 22 [ 250/461 ( 54%)] Loss: 0.729822 (0.7376) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.730s, 43.82/s (0.674s, 47.48/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 09:48:55,982 - train: [ INFO] - Train: 22 [ 300/461 ( 65%)] Loss: 0.720839 (0.7352) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.592s, 54.08/s (0.669s, 47.86/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-19 09:49:26,961 - train: [ INFO] - Train: 22 [ 350/461 ( 76%)] Loss: 0.833847 (0.7476) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.6094) Time: 0.465s, 68.84/s (0.661s, 48.38/s) LR: 5.000e-03 Data: 0.007 (0.020) +2025-04-19 09:49:59,919 - train: [ INFO] - Train: 22 [ 400/461 ( 87%)] Loss: 0.715514 (0.7440) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.656s, 48.82/s (0.661s, 48.41/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 09:50:32,092 - train: [ INFO] - Train: 22 [ 450/461 ( 98%)] Loss: 0.723037 (0.7419) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.588s, 54.40/s (0.659s, 48.57/s) LR: 5.000e-03 Data: 0.004 (0.016) +2025-04-19 09:50:38,346 - train: [ INFO] - Train: 22 [ 460/461 (100%)] Loss: 0.866528 (0.7532) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (98.8636) Acc@5: 100.0000 (99.7159) Time: 0.614s, 52.08/s (0.658s, 48.63/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 09:50:44,287 - train: [ INFO] - Eval : 22 Time: 5.588 (5.588) Loss: 1.9357 (1.9357) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-19 09:50:58,027 - train: [ INFO] - Eval : 22 Time: 0.202 (0.379) Loss: 1.6278 (1.8372) Acc@1: 59.3750 (52.6961)Acc@5: 84.3750 (78.4314) +2025-04-19 09:51:05,054 - train: [ INFO] - Eval : 22 Time: 0.059 (0.321) Loss: 3.2291 (1.8189) Acc@1: 0.0000 (52.5829)Acc@5: 0.0000 (79.0285) +2025-04-19 09:51:15,574 - train: [ INFO] - Train: 23 [ 0/461 ( 0%)] Loss: 0.745521 (0.7455) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.778s, 4.72/s (6.778s, 4.72/s) LR: 5.000e-03 Data: 5.968 (5.968) +2025-04-19 09:51:49,072 - train: [ INFO] - Train: 23 [ 50/461 ( 11%)] Loss: 0.725193 (0.7354) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.536s, 59.73/s (0.788s, 40.63/s) LR: 5.000e-03 Data: 0.000 (0.119) +2025-04-19 09:52:24,260 - train: [ INFO] - Train: 23 [ 100/461 ( 22%)] Loss: 0.731829 (0.7342) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.940s, 34.05/s (0.744s, 43.03/s) LR: 5.000e-03 Data: 0.000 (0.061) +2025-04-19 09:53:00,864 - train: [ INFO] - Train: 23 [ 150/461 ( 33%)] Loss: 0.751277 (0.7385) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.825s, 38.80/s (0.739s, 43.30/s) LR: 5.000e-03 Data: 0.000 (0.041) +2025-04-19 09:53:34,713 - train: [ INFO] - Train: 23 [ 200/461 ( 43%)] Loss: 0.732014 (0.7372) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.850s, 37.65/s (0.723s, 44.27/s) LR: 5.000e-03 Data: 0.001 (0.031) +2025-04-19 09:54:07,796 - train: [ INFO] - Train: 23 [ 250/461 ( 54%)] Loss: 0.733468 (0.7366) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.570s, 56.14/s (0.710s, 45.06/s) LR: 5.000e-03 Data: 0.001 (0.025) +2025-04-19 09:54:40,598 - train: [ INFO] - Train: 23 [ 300/461 ( 65%)] Loss: 0.755013 (0.7392) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.622s, 51.45/s (0.701s, 45.66/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 09:55:15,605 - train: [ INFO] - Train: 23 [ 350/461 ( 76%)] Loss: 0.809190 (0.7479) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.609s, 52.57/s (0.700s, 45.70/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 09:55:48,833 - train: [ INFO] - Train: 23 [ 400/461 ( 87%)] Loss: 0.733596 (0.7463) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.668s, 47.93/s (0.696s, 46.01/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 09:56:20,592 - train: [ INFO] - Train: 23 [ 450/461 ( 98%)] Loss: 0.715122 (0.7432) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.469s, 68.21/s (0.689s, 46.47/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 09:56:26,351 - train: [ INFO] - Train: 23 [ 460/461 (100%)] Loss: 0.751326 (0.7440) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.378s, 84.70/s (0.686s, 46.64/s) LR: 5.000e-03 Data: 0.008 (0.014) +2025-04-19 09:56:31,591 - train: [ INFO] - Eval : 23 Time: 4.913 (4.913) Loss: 1.8655 (1.8655) Acc@1: 53.1250 (53.1250)Acc@5: 78.1250 (78.1250) +2025-04-19 09:56:45,622 - train: [ INFO] - Eval : 23 Time: 0.242 (0.371) Loss: 1.7859 (1.8215) Acc@1: 53.1250 (51.6544)Acc@5: 78.1250 (79.0441) +2025-04-19 09:56:52,698 - train: [ INFO] - Eval : 23 Time: 0.067 (0.317) Loss: 2.9536 (1.8134) Acc@1: 0.0000 (51.6191)Acc@5: 50.0000 (79.1827) +2025-04-19 09:57:02,704 - train: [ INFO] - Train: 24 [ 0/461 ( 0%)] Loss: 0.730451 (0.7305) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.969s, 5.36/s (5.969s, 5.36/s) LR: 5.000e-03 Data: 5.416 (5.416) +2025-04-19 09:57:31,601 - train: [ INFO] - Train: 24 [ 50/461 ( 11%)] Loss: 0.710253 (0.7204) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.500s, 63.95/s (0.680s, 47.05/s) LR: 5.000e-03 Data: 0.001 (0.107) +2025-04-19 09:58:04,744 - train: [ INFO] - Train: 24 [ 100/461 ( 22%)] Loss: 0.733874 (0.7249) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.543s, 58.94/s (0.670s, 47.78/s) LR: 5.000e-03 Data: 0.000 (0.056) +2025-04-19 09:58:39,064 - train: [ INFO] - Train: 24 [ 150/461 ( 33%)] Loss: 0.719519 (0.7235) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.533s, 60.05/s (0.674s, 47.48/s) LR: 5.000e-03 Data: 0.001 (0.037) +2025-04-19 09:59:15,976 - train: [ INFO] - Train: 24 [ 200/461 ( 43%)] Loss: 0.724178 (0.7237) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.586s, 54.65/s (0.689s, 46.43/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 09:59:49,369 - train: [ INFO] - Train: 24 [ 250/461 ( 54%)] Loss: 0.711542 (0.7216) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.613s, 52.24/s (0.685s, 46.74/s) LR: 5.000e-03 Data: 0.003 (0.023) +2025-04-19 10:00:22,567 - train: [ INFO] - Train: 24 [ 300/461 ( 65%)] Loss: 0.734515 (0.7235) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.696s, 45.98/s (0.681s, 47.00/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 10:00:58,709 - train: [ INFO] - Train: 24 [ 350/461 ( 76%)] Loss: 0.715792 (0.7225) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.834s, 38.35/s (0.687s, 46.60/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 10:01:34,748 - train: [ INFO] - Train: 24 [ 400/461 ( 87%)] Loss: 0.777284 (0.7286) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.656s, 48.78/s (0.691s, 46.34/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 10:02:08,612 - train: [ INFO] - Train: 24 [ 450/461 ( 98%)] Loss: 0.718596 (0.7276) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.804s, 39.82/s (0.689s, 46.45/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 10:02:15,821 - train: [ INFO] - Train: 24 [ 460/461 (100%)] Loss: 0.717731 (0.7267) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.729s, 43.92/s (0.690s, 46.41/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 10:02:22,403 - train: [ INFO] - Eval : 24 Time: 6.078 (6.078) Loss: 1.7887 (1.7887) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-19 10:02:36,343 - train: [ INFO] - Eval : 24 Time: 0.264 (0.393) Loss: 1.7436 (1.8638) Acc@1: 53.1250 (51.2868)Acc@5: 84.3750 (76.9608) +2025-04-19 10:02:43,689 - train: [ INFO] - Eval : 24 Time: 0.057 (0.334) Loss: 3.4465 (1.8581) Acc@1: 0.0000 (51.1565)Acc@5: 50.0000 (77.4480) +2025-04-19 10:02:54,080 - train: [ INFO] - Train: 25 [ 0/461 ( 0%)] Loss: 0.782711 (0.7827) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.377s, 5.02/s (6.377s, 5.02/s) LR: 5.000e-03 Data: 5.541 (5.541) +2025-04-19 10:03:29,260 - train: [ INFO] - Train: 25 [ 50/461 ( 11%)] Loss: 0.707191 (0.7450) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.944s, 33.91/s (0.812s, 39.41/s) LR: 5.000e-03 Data: 0.001 (0.110) +2025-04-19 10:04:01,057 - train: [ INFO] - Train: 25 [ 100/461 ( 22%)] Loss: 0.708662 (0.7329) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.512s, 62.53/s (0.724s, 44.23/s) LR: 5.000e-03 Data: 0.007 (0.056) +2025-04-19 10:04:38,283 - train: [ INFO] - Train: 25 [ 150/461 ( 33%)] Loss: 0.727365 (0.7315) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.724s, 44.23/s (0.730s, 43.84/s) LR: 5.000e-03 Data: 0.001 (0.038) +2025-04-19 10:05:12,078 - train: [ INFO] - Train: 25 [ 200/461 ( 43%)] Loss: 0.711345 (0.7275) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.836s, 38.26/s (0.716s, 44.71/s) LR: 5.000e-03 Data: 0.001 (0.029) +2025-04-19 10:05:46,374 - train: [ INFO] - Train: 25 [ 250/461 ( 54%)] Loss: 0.807772 (0.7408) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.893s, 35.83/s (0.709s, 45.11/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 10:06:18,418 - train: [ INFO] - Train: 25 [ 300/461 ( 65%)] Loss: 0.725398 (0.7386) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.718s, 44.56/s (0.698s, 45.88/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 10:06:56,753 - train: [ INFO] - Train: 25 [ 350/461 ( 76%)] Loss: 0.755769 (0.7408) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.688s, 46.48/s (0.707s, 45.26/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 10:07:34,104 - train: [ INFO] - Train: 25 [ 400/461 ( 87%)] Loss: 0.712386 (0.7376) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.764s, 41.90/s (0.712s, 44.97/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 10:08:14,222 - train: [ INFO] - Train: 25 [ 450/461 ( 98%)] Loss: 0.720990 (0.7360) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.833s, 38.41/s (0.721s, 44.35/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:08:22,242 - train: [ INFO] - Train: 25 [ 460/461 (100%)] Loss: 0.716614 (0.7342) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.866s, 36.96/s (0.723s, 44.25/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:08:27,985 - train: [ INFO] - Eval : 25 Time: 5.370 (5.370) Loss: 1.8005 (1.8005) Acc@1: 53.1250 (53.1250)Acc@5: 81.2500 (81.2500) +2025-04-19 10:08:43,411 - train: [ INFO] - Eval : 25 Time: 0.402 (0.408) Loss: 1.6568 (1.8536) Acc@1: 59.3750 (51.3480)Acc@5: 81.2500 (77.8186) +2025-04-19 10:08:51,812 - train: [ INFO] - Eval : 25 Time: 0.063 (0.356) Loss: 2.9463 (1.8453) Acc@1: 0.0000 (50.8867)Acc@5: 50.0000 (78.2190) +2025-04-19 10:09:01,472 - train: [ INFO] - Train: 26 [ 0/461 ( 0%)] Loss: 0.791753 (0.7918) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 5.804s, 5.51/s (5.804s, 5.51/s) LR: 5.000e-03 Data: 4.964 (4.964) +2025-04-19 10:09:39,684 - train: [ INFO] - Train: 26 [ 50/461 ( 11%)] Loss: 0.696889 (0.7443) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.856s, 37.37/s (0.861s, 37.17/s) LR: 5.000e-03 Data: 0.000 (0.098) +2025-04-19 10:10:15,034 - train: [ INFO] - Train: 26 [ 100/461 ( 22%)] Loss: 0.720154 (0.7363) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.611s, 52.40/s (0.784s, 40.84/s) LR: 5.000e-03 Data: 0.001 (0.050) +2025-04-19 10:10:43,900 - train: [ INFO] - Train: 26 [ 150/461 ( 33%)] Loss: 0.708661 (0.7294) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.477s, 67.04/s (0.715s, 44.77/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-19 10:11:17,204 - train: [ INFO] - Train: 26 [ 200/461 ( 43%)] Loss: 0.709509 (0.7254) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.705s, 45.38/s (0.702s, 45.60/s) LR: 5.000e-03 Data: 0.001 (0.026) +2025-04-19 10:11:50,557 - train: [ INFO] - Train: 26 [ 250/461 ( 54%)] Loss: 0.723247 (0.7250) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 1.014s, 31.56/s (0.695s, 46.07/s) LR: 5.000e-03 Data: 0.006 (0.021) +2025-04-19 10:12:27,803 - train: [ INFO] - Train: 26 [ 300/461 ( 65%)] Loss: 0.736655 (0.7267) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.711s, 44.99/s (0.703s, 45.54/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 10:13:04,465 - train: [ INFO] - Train: 26 [ 350/461 ( 76%)] Loss: 0.708027 (0.7244) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.696s, 45.97/s (0.707s, 45.27/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 10:13:42,540 - train: [ INFO] - Train: 26 [ 400/461 ( 87%)] Loss: 0.732052 (0.7252) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.719s, 44.53/s (0.713s, 44.86/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 10:14:19,597 - train: [ INFO] - Train: 26 [ 450/461 ( 98%)] Loss: 0.701796 (0.7229) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.769s, 41.60/s (0.716s, 44.68/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:14:25,873 - train: [ INFO] - Train: 26 [ 460/461 (100%)] Loss: 0.702193 (0.7210) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.569s, 56.27/s (0.714s, 44.80/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:14:31,480 - train: [ INFO] - Eval : 26 Time: 5.242 (5.242) Loss: 1.7864 (1.7864) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-19 10:14:45,196 - train: [ INFO] - Eval : 26 Time: 0.146 (0.372) Loss: 1.8202 (1.8717) Acc@1: 56.2500 (50.9804)Acc@5: 81.2500 (77.7574) +2025-04-19 10:14:53,301 - train: [ INFO] - Eval : 26 Time: 0.058 (0.330) Loss: 3.0869 (1.8723) Acc@1: 0.0000 (50.0000)Acc@5: 50.0000 (78.2961) +2025-04-19 10:15:03,604 - train: [ INFO] - Train: 27 [ 0/461 ( 0%)] Loss: 0.707383 (0.7074) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.439s, 4.97/s (6.439s, 4.97/s) LR: 5.000e-03 Data: 5.794 (5.794) +2025-04-19 10:15:38,362 - train: [ INFO] - Train: 27 [ 50/461 ( 11%)] Loss: 0.714553 (0.7110) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.692s, 46.25/s (0.806s, 39.71/s) LR: 5.000e-03 Data: 0.000 (0.115) +2025-04-19 10:16:14,297 - train: [ INFO] - Train: 27 [ 100/461 ( 22%)] Loss: 0.701183 (0.7077) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.486s, 65.85/s (0.762s, 41.99/s) LR: 5.000e-03 Data: 0.000 (0.059) +2025-04-19 10:16:48,832 - train: [ INFO] - Train: 27 [ 150/461 ( 33%)] Loss: 0.752827 (0.7190) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.907s, 35.29/s (0.737s, 43.42/s) LR: 5.000e-03 Data: 0.000 (0.040) +2025-04-19 10:17:26,818 - train: [ INFO] - Train: 27 [ 200/461 ( 43%)] Loss: 0.704840 (0.7162) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.888s, 36.04/s (0.742s, 43.13/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-19 10:17:59,000 - train: [ INFO] - Train: 27 [ 250/461 ( 54%)] Loss: 0.729070 (0.7183) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.731s, 43.78/s (0.722s, 44.32/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 10:18:33,825 - train: [ INFO] - Train: 27 [ 300/461 ( 65%)] Loss: 0.708990 (0.7170) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.823s, 38.90/s (0.717s, 44.60/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 10:19:12,707 - train: [ INFO] - Train: 27 [ 350/461 ( 76%)] Loss: 0.728776 (0.7185) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.597s, 53.57/s (0.726s, 44.09/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 10:19:54,135 - train: [ INFO] - Train: 27 [ 400/461 ( 87%)] Loss: 0.737322 (0.7205) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.949s, 33.73/s (0.738s, 43.34/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 10:20:35,377 - train: [ INFO] - Train: 27 [ 450/461 ( 98%)] Loss: 0.736792 (0.7222) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.047s, 30.57/s (0.748s, 42.79/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 10:20:42,568 - train: [ INFO] - Train: 27 [ 460/461 (100%)] Loss: 0.715042 (0.7215) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.604s, 52.96/s (0.747s, 42.83/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 10:20:48,075 - train: [ INFO] - Eval : 27 Time: 5.137 (5.137) Loss: 1.8612 (1.8612) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-19 10:21:02,082 - train: [ INFO] - Eval : 27 Time: 0.297 (0.375) Loss: 1.7143 (1.8459) Acc@1: 56.2500 (51.7770)Acc@5: 87.5000 (78.6152) +2025-04-19 10:21:09,915 - train: [ INFO] - Eval : 27 Time: 0.061 (0.329) Loss: 3.0674 (1.8431) Acc@1: 0.0000 (50.9638)Acc@5: 50.0000 (78.7201) +2025-04-19 10:21:19,013 - train: [ INFO] - Train: 28 [ 0/461 ( 0%)] Loss: 0.709559 (0.7096) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.465s, 5.86/s (5.465s, 5.86/s) LR: 5.000e-03 Data: 4.836 (4.836) +2025-04-19 10:22:00,855 - train: [ INFO] - Train: 28 [ 50/461 ( 11%)] Loss: 0.769976 (0.7398) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.46/s (0.926s, 34.55/s) LR: 5.000e-03 Data: 0.001 (0.096) +2025-04-19 10:22:39,704 - train: [ INFO] - Train: 28 [ 100/461 ( 22%)] Loss: 0.759692 (0.7464) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.9167) Acc@5: 100.0000 (100.0000) Time: 0.960s, 33.35/s (0.851s, 37.60/s) LR: 5.000e-03 Data: 0.000 (0.049) +2025-04-19 10:23:17,411 - train: [ INFO] - Train: 28 [ 150/461 ( 33%)] Loss: 0.704951 (0.7360) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.917s, 34.88/s (0.818s, 39.10/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-19 10:23:51,799 - train: [ INFO] - Train: 28 [ 200/461 ( 43%)] Loss: 0.736234 (0.7361) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.769s, 41.64/s (0.785s, 40.74/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 10:24:30,264 - train: [ INFO] - Train: 28 [ 250/461 ( 54%)] Loss: 0.705544 (0.7310) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.916s, 34.92/s (0.782s, 40.94/s) LR: 5.000e-03 Data: 0.001 (0.020) +2025-04-19 10:25:05,112 - train: [ INFO] - Train: 28 [ 300/461 ( 65%)] Loss: 0.751213 (0.7339) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.489s, 65.50/s (0.767s, 41.70/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 10:25:40,652 - train: [ INFO] - Train: 28 [ 350/461 ( 76%)] Loss: 0.695323 (0.7291) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.381s, 83.88/s (0.759s, 42.16/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 10:26:18,910 - train: [ INFO] - Train: 28 [ 400/461 ( 87%)] Loss: 0.688469 (0.7246) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 1.000s, 31.99/s (0.760s, 42.13/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:26:56,739 - train: [ INFO] - Train: 28 [ 450/461 ( 98%)] Loss: 0.734365 (0.7255) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.622s, 51.44/s (0.759s, 42.16/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:27:04,044 - train: [ INFO] - Train: 28 [ 460/461 (100%)] Loss: 0.723141 (0.7253) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.587s, 54.48/s (0.758s, 42.20/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 10:27:10,035 - train: [ INFO] - Eval : 28 Time: 5.635 (5.635) Loss: 1.8369 (1.8369) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 10:27:24,263 - train: [ INFO] - Eval : 28 Time: 0.255 (0.389) Loss: 1.7166 (1.8555) Acc@1: 62.5000 (50.7966)Acc@5: 75.0000 (78.0025) +2025-04-19 10:27:31,949 - train: [ INFO] - Eval : 28 Time: 0.084 (0.336) Loss: 2.7729 (1.8472) Acc@1: 0.0000 (51.0794)Acc@5: 50.0000 (77.6793) +2025-04-19 10:27:42,569 - train: [ INFO] - Train: 29 [ 0/461 ( 0%)] Loss: 0.704899 (0.7049) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.698s, 5.62/s (5.698s, 5.62/s) LR: 5.000e-03 Data: 4.753 (4.753) +2025-04-19 10:28:16,584 - train: [ INFO] - Train: 29 [ 50/461 ( 11%)] Loss: 0.698656 (0.7018) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.607s, 52.68/s (0.777s, 41.18/s) LR: 5.000e-03 Data: 0.000 (0.094) +2025-04-19 10:28:53,338 - train: [ INFO] - Train: 29 [ 100/461 ( 22%)] Loss: 0.819960 (0.7412) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.821s, 38.99/s (0.756s, 42.35/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-19 10:29:33,113 - train: [ INFO] - Train: 29 [ 150/461 ( 33%)] Loss: 0.730377 (0.7385) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.740s, 43.23/s (0.768s, 41.66/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-19 10:30:14,242 - train: [ INFO] - Train: 29 [ 200/461 ( 43%)] Loss: 0.712532 (0.7333) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.929s, 34.46/s (0.781s, 40.96/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 10:30:54,713 - train: [ INFO] - Train: 29 [ 250/461 ( 54%)] Loss: 0.798189 (0.7441) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.814s, 39.30/s (0.786s, 40.69/s) LR: 5.000e-03 Data: 0.003 (0.020) +2025-04-19 10:31:34,510 - train: [ INFO] - Train: 29 [ 300/461 ( 65%)] Loss: 0.715931 (0.7401) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.1071) Time: 0.683s, 46.83/s (0.788s, 40.63/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 10:32:12,504 - train: [ INFO] - Train: 29 [ 350/461 ( 76%)] Loss: 0.774487 (0.7444) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8281) Acc@5: 100.0000 (99.2188) Time: 0.815s, 39.25/s (0.783s, 40.85/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 10:32:50,712 - train: [ INFO] - Train: 29 [ 400/461 ( 87%)] Loss: 0.702113 (0.7397) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.3056) Time: 0.687s, 46.59/s (0.781s, 40.99/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:33:30,203 - train: [ INFO] - Train: 29 [ 450/461 ( 98%)] Loss: 0.713045 (0.7370) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.3750) Time: 0.654s, 48.91/s (0.782s, 40.95/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:33:38,353 - train: [ INFO] - Train: 29 [ 460/461 (100%)] Loss: 0.707027 (0.7343) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.4318) Time: 0.637s, 50.26/s (0.782s, 40.91/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 10:33:43,868 - train: [ INFO] - Eval : 29 Time: 5.147 (5.147) Loss: 1.9824 (1.9824) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-19 10:33:57,896 - train: [ INFO] - Eval : 29 Time: 0.209 (0.376) Loss: 1.6283 (1.8774) Acc@1: 59.3750 (50.3676)Acc@5: 84.3750 (76.5931) +2025-04-19 10:34:05,373 - train: [ INFO] - Eval : 29 Time: 0.066 (0.325) Loss: 2.7955 (1.8728) Acc@1: 0.0000 (50.4241)Acc@5: 50.0000 (77.3709) +2025-04-19 10:34:16,026 - train: [ INFO] - Train: 30 [ 0/461 ( 0%)] Loss: 0.704316 (0.7043) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.251s, 5.12/s (6.251s, 5.12/s) LR: 5.000e-03 Data: 5.351 (5.351) +2025-04-19 10:34:54,527 - train: [ INFO] - Train: 30 [ 50/461 ( 11%)] Loss: 0.714871 (0.7096) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.803s, 39.84/s (0.876s, 36.54/s) LR: 5.000e-03 Data: 0.008 (0.106) +2025-04-19 10:35:35,128 - train: [ INFO] - Train: 30 [ 100/461 ( 22%)] Loss: 0.695625 (0.7049) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.859s, 37.24/s (0.843s, 37.96/s) LR: 5.000e-03 Data: 0.000 (0.054) +2025-04-19 10:36:08,792 - train: [ INFO] - Train: 30 [ 150/461 ( 33%)] Loss: 0.703511 (0.7046) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.779s, 41.07/s (0.786s, 40.71/s) LR: 5.000e-03 Data: 0.000 (0.037) +2025-04-19 10:36:49,091 - train: [ INFO] - Train: 30 [ 200/461 ( 43%)] Loss: 0.702459 (0.7042) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.909s, 35.20/s (0.790s, 40.49/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-19 10:37:29,692 - train: [ INFO] - Train: 30 [ 250/461 ( 54%)] Loss: 0.748106 (0.7115) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.755s, 42.41/s (0.794s, 40.28/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-19 10:38:07,022 - train: [ INFO] - Train: 30 [ 300/461 ( 65%)] Loss: 0.756558 (0.7179) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.606s, 52.85/s (0.786s, 40.70/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 10:38:47,029 - train: [ INFO] - Train: 30 [ 350/461 ( 76%)] Loss: 0.718600 (0.7180) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.720s, 44.42/s (0.788s, 40.62/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 10:39:27,492 - train: [ INFO] - Train: 30 [ 400/461 ( 87%)] Loss: 0.728726 (0.7192) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.672s, 47.65/s (0.790s, 40.49/s) LR: 5.000e-03 Data: 0.004 (0.015) +2025-04-19 10:40:05,669 - train: [ INFO] - Train: 30 [ 450/461 ( 98%)] Loss: 0.710387 (0.7183) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.830s, 38.55/s (0.787s, 40.65/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:40:13,685 - train: [ INFO] - Train: 30 [ 460/461 (100%)] Loss: 0.830243 (0.7285) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.634s, 50.49/s (0.787s, 40.64/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:40:19,425 - train: [ INFO] - Eval : 30 Time: 5.397 (5.397) Loss: 1.8864 (1.8864) Acc@1: 50.0000 (50.0000)Acc@5: 84.3750 (84.3750) +2025-04-19 10:40:32,819 - train: [ INFO] - Eval : 30 Time: 0.206 (0.368) Loss: 1.6526 (1.8677) Acc@1: 53.1250 (50.3676)Acc@5: 84.3750 (77.3897) +2025-04-19 10:40:40,328 - train: [ INFO] - Eval : 30 Time: 0.091 (0.321) Loss: 3.1623 (1.8630) Acc@1: 0.0000 (51.1565)Acc@5: 50.0000 (77.4094) +2025-04-19 10:40:49,637 - train: [ INFO] - Train: 31 [ 0/461 ( 0%)] Loss: 0.700037 (0.7000) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.890s, 6.54/s (4.890s, 6.54/s) LR: 5.000e-03 Data: 4.054 (4.054) +2025-04-19 10:41:28,751 - train: [ INFO] - Train: 31 [ 50/461 ( 11%)] Loss: 0.691958 (0.6960) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.794s, 40.28/s (0.861s, 37.16/s) LR: 5.000e-03 Data: 0.002 (0.090) +2025-04-19 10:42:07,586 - train: [ INFO] - Train: 31 [ 100/461 ( 22%)] Loss: 0.735190 (0.7091) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.856s, 37.38/s (0.819s, 39.09/s) LR: 5.000e-03 Data: 0.000 (0.046) +2025-04-19 10:42:47,080 - train: [ INFO] - Train: 31 [ 150/461 ( 33%)] Loss: 0.733495 (0.7152) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.867s, 36.91/s (0.808s, 39.58/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 10:43:25,814 - train: [ INFO] - Train: 31 [ 200/461 ( 43%)] Loss: 0.701221 (0.7124) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.722s, 44.33/s (0.800s, 40.02/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-19 10:44:02,526 - train: [ INFO] - Train: 31 [ 250/461 ( 54%)] Loss: 0.713578 (0.7126) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.663s, 48.24/s (0.786s, 40.71/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 10:44:43,683 - train: [ INFO] - Train: 31 [ 300/461 ( 65%)] Loss: 0.733931 (0.7156) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.710s, 45.10/s (0.792s, 40.40/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 10:45:23,766 - train: [ INFO] - Train: 31 [ 350/461 ( 76%)] Loss: 0.695900 (0.7132) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.765s, 41.83/s (0.793s, 40.34/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 10:46:02,754 - train: [ INFO] - Train: 31 [ 400/461 ( 87%)] Loss: 0.733394 (0.7154) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.609s, 52.51/s (0.791s, 40.44/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:46:44,700 - train: [ INFO] - Train: 31 [ 450/461 ( 98%)] Loss: 0.694066 (0.7133) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.898s, 35.64/s (0.796s, 40.18/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 10:46:53,319 - train: [ INFO] - Train: 31 [ 460/461 (100%)] Loss: 0.700697 (0.7121) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.744s, 43.03/s (0.798s, 40.11/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 10:46:58,782 - train: [ INFO] - Eval : 31 Time: 5.111 (5.111) Loss: 1.9227 (1.9227) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-19 10:47:13,006 - train: [ INFO] - Eval : 31 Time: 0.267 (0.379) Loss: 1.8250 (1.8931) Acc@1: 50.0000 (50.4289)Acc@5: 78.1250 (76.8995) +2025-04-19 10:47:21,039 - train: [ INFO] - Eval : 31 Time: 0.078 (0.334) Loss: 2.8383 (1.8922) Acc@1: 0.0000 (50.2699)Acc@5: 50.0000 (77.0239) +2025-04-19 10:47:31,659 - train: [ INFO] - Train: 32 [ 0/461 ( 0%)] Loss: 0.710773 (0.7108) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.292s, 5.09/s (6.292s, 5.09/s) LR: 5.000e-03 Data: 5.499 (5.499) +2025-04-19 10:48:09,823 - train: [ INFO] - Train: 32 [ 50/461 ( 11%)] Loss: 0.702951 (0.7069) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.815s, 39.26/s (0.869s, 36.81/s) LR: 5.000e-03 Data: 0.000 (0.108) +2025-04-19 10:48:48,710 - train: [ INFO] - Train: 32 [ 100/461 ( 22%)] Loss: 0.705402 (0.7064) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.603s, 53.09/s (0.823s, 38.87/s) LR: 5.000e-03 Data: 0.000 (0.055) +2025-04-19 10:49:26,784 - train: [ INFO] - Train: 32 [ 150/461 ( 33%)] Loss: 0.702599 (0.7054) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.782s, 40.93/s (0.802s, 39.90/s) LR: 5.000e-03 Data: 0.000 (0.038) +2025-04-19 10:50:06,518 - train: [ INFO] - Train: 32 [ 200/461 ( 43%)] Loss: 0.711195 (0.7066) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.914s, 35.02/s (0.800s, 40.02/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-19 10:50:42,531 - train: [ INFO] - Train: 32 [ 250/461 ( 54%)] Loss: 0.737097 (0.7117) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.756s, 42.33/s (0.784s, 40.84/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 10:51:24,680 - train: [ INFO] - Train: 32 [ 300/461 ( 65%)] Loss: 0.728194 (0.7140) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.846s, 37.84/s (0.793s, 40.35/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 10:52:04,396 - train: [ INFO] - Train: 32 [ 350/461 ( 76%)] Loss: 0.700221 (0.7123) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.807s, 39.63/s (0.793s, 40.35/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 10:52:42,601 - train: [ INFO] - Train: 32 [ 400/461 ( 87%)] Loss: 0.704880 (0.7115) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.033s, 30.99/s (0.789s, 40.55/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 10:53:21,661 - train: [ INFO] - Train: 32 [ 450/461 ( 98%)] Loss: 0.691069 (0.7094) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.788s, 40.59/s (0.788s, 40.60/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:53:29,617 - train: [ INFO] - Train: 32 [ 460/461 (100%)] Loss: 0.749768 (0.7131) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.808s, 39.59/s (0.788s, 40.60/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:53:35,190 - train: [ INFO] - Eval : 32 Time: 5.186 (5.186) Loss: 1.8846 (1.8846) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-19 10:53:49,097 - train: [ INFO] - Eval : 32 Time: 0.338 (0.374) Loss: 1.7330 (1.8654) Acc@1: 56.2500 (51.3480)Acc@5: 81.2500 (77.3284) +2025-04-19 10:53:57,113 - train: [ INFO] - Eval : 32 Time: 0.070 (0.331) Loss: 2.9488 (1.8636) Acc@1: 0.0000 (51.3493)Acc@5: 50.0000 (77.3709) +2025-04-19 10:54:06,877 - train: [ INFO] - Train: 33 [ 0/461 ( 0%)] Loss: 0.746729 (0.7467) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.588s, 5.73/s (5.588s, 5.73/s) LR: 5.000e-03 Data: 4.689 (4.689) +2025-04-19 10:54:42,864 - train: [ INFO] - Train: 33 [ 50/461 ( 11%)] Loss: 0.748605 (0.7477) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.542s, 59.05/s (0.813s, 39.36/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-19 10:55:20,972 - train: [ INFO] - Train: 33 [ 100/461 ( 22%)] Loss: 0.771001 (0.7554) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.767s, 41.71/s (0.787s, 40.66/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-19 10:56:01,241 - train: [ INFO] - Train: 33 [ 150/461 ( 33%)] Loss: 0.722810 (0.7473) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 1.001s, 31.95/s (0.792s, 40.38/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-19 10:56:40,099 - train: [ INFO] - Train: 33 [ 200/461 ( 43%)] Loss: 0.692317 (0.7363) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.703s, 45.50/s (0.788s, 40.60/s) LR: 5.000e-03 Data: 0.004 (0.025) +2025-04-19 10:57:19,900 - train: [ INFO] - Train: 33 [ 250/461 ( 54%)] Loss: 0.703676 (0.7309) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.706s, 45.31/s (0.789s, 40.54/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 10:57:57,640 - train: [ INFO] - Train: 33 [ 300/461 ( 65%)] Loss: 0.720538 (0.7294) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.594s, 53.87/s (0.783s, 40.85/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 10:58:34,725 - train: [ INFO] - Train: 33 [ 350/461 ( 76%)] Loss: 0.714644 (0.7275) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.526s, 60.78/s (0.777s, 41.18/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 10:59:12,285 - train: [ INFO] - Train: 33 [ 400/461 ( 87%)] Loss: 0.690296 (0.7234) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.575s, 55.65/s (0.774s, 41.37/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:59:48,268 - train: [ INFO] - Train: 33 [ 450/461 ( 98%)] Loss: 0.714200 (0.7225) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.729s, 43.92/s (0.767s, 41.71/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 10:59:55,729 - train: [ INFO] - Train: 33 [ 460/461 (100%)] Loss: 0.707393 (0.7211) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.608s, 52.63/s (0.767s, 41.73/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 11:00:01,264 - train: [ INFO] - Eval : 33 Time: 5.181 (5.181) Loss: 1.9445 (1.9445) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-19 11:00:14,732 - train: [ INFO] - Eval : 33 Time: 0.175 (0.366) Loss: 1.7222 (1.9125) Acc@1: 59.3750 (50.1225)Acc@5: 84.3750 (76.0417) +2025-04-19 11:00:22,283 - train: [ INFO] - Eval : 33 Time: 0.076 (0.320) Loss: 3.3608 (1.9082) Acc@1: 0.0000 (50.6168)Acc@5: 50.0000 (76.3685) +2025-04-19 11:00:31,699 - train: [ INFO] - Train: 34 [ 0/461 ( 0%)] Loss: 0.695018 (0.6950) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.284s, 6.06/s (5.284s, 6.06/s) LR: 5.000e-03 Data: 4.238 (4.238) +2025-04-19 11:01:12,938 - train: [ INFO] - Train: 34 [ 50/461 ( 11%)] Loss: 0.695897 (0.6955) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.934s, 34.26/s (0.910s, 35.17/s) LR: 5.000e-03 Data: 0.000 (0.087) +2025-04-19 11:01:51,147 - train: [ INFO] - Train: 34 [ 100/461 ( 22%)] Loss: 0.718879 (0.7033) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.817s, 39.17/s (0.836s, 38.26/s) LR: 5.000e-03 Data: 0.001 (0.044) +2025-04-19 11:02:27,910 - train: [ INFO] - Train: 34 [ 150/461 ( 33%)] Loss: 0.705495 (0.7038) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.837s, 38.24/s (0.802s, 39.89/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-19 11:03:09,159 - train: [ INFO] - Train: 34 [ 200/461 ( 43%)] Loss: 0.762191 (0.7155) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.778s, 41.12/s (0.808s, 39.63/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 11:03:47,111 - train: [ INFO] - Train: 34 [ 250/461 ( 54%)] Loss: 0.688625 (0.7110) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.518s, 61.83/s (0.797s, 40.13/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 11:04:25,362 - train: [ INFO] - Train: 34 [ 300/461 ( 65%)] Loss: 0.706433 (0.7104) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.597s, 53.64/s (0.792s, 40.41/s) LR: 5.000e-03 Data: 0.002 (0.016) +2025-04-19 11:05:02,456 - train: [ INFO] - Train: 34 [ 350/461 ( 76%)] Loss: 0.699755 (0.7090) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.635s, 50.42/s (0.784s, 40.80/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:05:40,490 - train: [ INFO] - Train: 34 [ 400/461 ( 87%)] Loss: 0.707749 (0.7089) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.705s, 45.39/s (0.781s, 40.97/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 11:06:17,060 - train: [ INFO] - Train: 34 [ 450/461 ( 98%)] Loss: 0.690835 (0.7071) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.662s, 48.35/s (0.775s, 41.27/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 11:06:25,219 - train: [ INFO] - Train: 34 [ 460/461 (100%)] Loss: 0.697294 (0.7062) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.956s, 33.48/s (0.776s, 41.23/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 11:06:32,194 - train: [ INFO] - Eval : 34 Time: 6.592 (6.592) Loss: 1.9240 (1.9240) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-19 11:06:45,312 - train: [ INFO] - Eval : 34 Time: 0.220 (0.386) Loss: 1.6351 (1.8790) Acc@1: 62.5000 (51.6544)Acc@5: 84.3750 (76.5319) +2025-04-19 11:06:53,036 - train: [ INFO] - Eval : 34 Time: 0.092 (0.335) Loss: 3.2480 (1.8797) Acc@1: 0.0000 (51.2336)Acc@5: 50.0000 (76.7926) +2025-04-19 11:07:04,275 - train: [ INFO] - Train: 35 [ 0/461 ( 0%)] Loss: 0.702121 (0.7021) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.583s, 4.86/s (6.583s, 4.86/s) LR: 5.000e-03 Data: 5.581 (5.581) +2025-04-19 11:07:41,960 - train: [ INFO] - Train: 35 [ 50/461 ( 11%)] Loss: 0.734059 (0.7181) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.886s, 36.10/s (0.866s, 36.93/s) LR: 5.000e-03 Data: 0.001 (0.110) +2025-04-19 11:08:20,203 - train: [ INFO] - Train: 35 [ 100/461 ( 22%)] Loss: 0.712775 (0.7163) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.811s, 39.45/s (0.815s, 39.26/s) LR: 5.000e-03 Data: 0.000 (0.056) +2025-04-19 11:08:56,126 - train: [ INFO] - Train: 35 [ 150/461 ( 33%)] Loss: 0.702720 (0.7129) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.980s, 32.67/s (0.783s, 40.89/s) LR: 5.000e-03 Data: 0.000 (0.038) +2025-04-19 11:09:36,697 - train: [ INFO] - Train: 35 [ 200/461 ( 43%)] Loss: 0.706638 (0.7117) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.889s, 36.00/s (0.789s, 40.54/s) LR: 5.000e-03 Data: 0.002 (0.029) +2025-04-19 11:10:14,280 - train: [ INFO] - Train: 35 [ 250/461 ( 54%)] Loss: 0.696299 (0.7091) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.720s, 44.42/s (0.782s, 40.94/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 11:10:52,140 - train: [ INFO] - Train: 35 [ 300/461 ( 65%)] Loss: 0.695602 (0.7072) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.969s, 33.03/s (0.777s, 41.17/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 11:11:27,406 - train: [ INFO] - Train: 35 [ 350/461 ( 76%)] Loss: 0.715146 (0.7082) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.642s, 49.82/s (0.767s, 41.73/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 11:12:06,130 - train: [ INFO] - Train: 35 [ 400/461 ( 87%)] Loss: 0.766988 (0.7147) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.825s, 38.77/s (0.768s, 41.69/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 11:12:46,498 - train: [ INFO] - Train: 35 [ 450/461 ( 98%)] Loss: 0.719586 (0.7152) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.863s, 37.06/s (0.772s, 41.46/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:12:55,364 - train: [ INFO] - Train: 35 [ 460/461 (100%)] Loss: 0.708286 (0.7146) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.839s, 38.13/s (0.774s, 41.33/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:13:00,783 - train: [ INFO] - Eval : 35 Time: 4.992 (4.992) Loss: 1.9960 (1.9960) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-19 11:13:15,866 - train: [ INFO] - Eval : 35 Time: 0.270 (0.394) Loss: 1.6436 (1.9085) Acc@1: 53.1250 (50.5515)Acc@5: 84.3750 (76.4706) +2025-04-19 11:13:23,814 - train: [ INFO] - Eval : 35 Time: 0.077 (0.342) Loss: 3.3087 (1.9017) Acc@1: 0.0000 (50.2699)Acc@5: 0.0000 (77.2552) +2025-04-19 11:13:35,940 - train: [ INFO] - Train: 36 [ 0/461 ( 0%)] Loss: 0.771998 (0.7720) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 6.697s, 4.78/s (6.697s, 4.78/s) LR: 5.000e-03 Data: 5.907 (5.907) +2025-04-19 11:14:16,403 - train: [ INFO] - Train: 36 [ 50/461 ( 11%)] Loss: 0.685795 (0.7289) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 1.055s, 30.34/s (0.921s, 34.75/s) LR: 5.000e-03 Data: 0.000 (0.117) +2025-04-19 11:14:58,204 - train: [ INFO] - Train: 36 [ 100/461 ( 22%)] Loss: 0.691776 (0.7165) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.658s, 48.64/s (0.878s, 36.46/s) LR: 5.000e-03 Data: 0.001 (0.059) +2025-04-19 11:15:36,374 - train: [ INFO] - Train: 36 [ 150/461 ( 33%)] Loss: 0.719787 (0.7173) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.728s, 43.97/s (0.839s, 38.13/s) LR: 5.000e-03 Data: 0.000 (0.040) +2025-04-19 11:16:17,377 - train: [ INFO] - Train: 36 [ 200/461 ( 43%)] Loss: 0.744763 (0.7228) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.856s, 37.40/s (0.834s, 38.37/s) LR: 5.000e-03 Data: 0.001 (0.030) +2025-04-19 11:16:55,814 - train: [ INFO] - Train: 36 [ 250/461 ( 54%)] Loss: 0.694100 (0.7180) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.854s, 37.49/s (0.821s, 38.99/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 11:17:33,048 - train: [ INFO] - Train: 36 [ 300/461 ( 65%)] Loss: 0.685103 (0.7133) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.616s, 51.94/s (0.808s, 39.62/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 11:18:11,847 - train: [ INFO] - Train: 36 [ 350/461 ( 76%)] Loss: 0.692539 (0.7107) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.803s, 39.86/s (0.803s, 39.86/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 11:18:48,923 - train: [ INFO] - Train: 36 [ 400/461 ( 87%)] Loss: 0.698447 (0.7094) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.643s, 49.78/s (0.795s, 40.26/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 11:19:24,279 - train: [ INFO] - Train: 36 [ 450/461 ( 98%)] Loss: 0.742331 (0.7127) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.805s, 39.76/s (0.785s, 40.77/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 11:19:31,391 - train: [ INFO] - Train: 36 [ 460/461 (100%)] Loss: 0.709654 (0.7124) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.595s, 53.77/s (0.783s, 40.85/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 11:19:37,349 - train: [ INFO] - Eval : 36 Time: 5.637 (5.637) Loss: 1.9697 (1.9697) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-19 11:19:51,277 - train: [ INFO] - Eval : 36 Time: 0.295 (0.384) Loss: 1.7137 (1.9059) Acc@1: 56.2500 (50.9804)Acc@5: 81.2500 (76.1029) +2025-04-19 11:19:58,855 - train: [ INFO] - Eval : 36 Time: 0.085 (0.331) Loss: 3.2619 (1.8909) Acc@1: 0.0000 (51.6191)Acc@5: 0.0000 (76.7155) +2025-04-19 11:20:08,348 - train: [ INFO] - Train: 37 [ 0/461 ( 0%)] Loss: 0.705762 (0.7058) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.129s, 6.24/s (5.129s, 6.24/s) LR: 5.000e-03 Data: 4.209 (4.209) +2025-04-19 11:20:42,774 - train: [ INFO] - Train: 37 [ 50/461 ( 11%)] Loss: 0.729797 (0.7178) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.721s, 44.41/s (0.773s, 41.38/s) LR: 5.000e-03 Data: 0.000 (0.084) +2025-04-19 11:21:21,061 - train: [ INFO] - Train: 37 [ 100/461 ( 22%)] Loss: 0.721004 (0.7189) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.917s, 34.91/s (0.769s, 41.62/s) LR: 5.000e-03 Data: 0.000 (0.043) +2025-04-19 11:22:00,590 - train: [ INFO] - Train: 37 [ 150/461 ( 33%)] Loss: 0.763404 (0.7300) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.817s, 39.16/s (0.775s, 41.27/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 11:22:38,772 - train: [ INFO] - Train: 37 [ 200/461 ( 43%)] Loss: 0.764092 (0.7368) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.771s, 41.52/s (0.772s, 41.45/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 11:23:16,521 - train: [ INFO] - Train: 37 [ 250/461 ( 54%)] Loss: 0.700078 (0.7307) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.838s, 38.19/s (0.768s, 41.66/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 11:23:56,939 - train: [ INFO] - Train: 37 [ 300/461 ( 65%)] Loss: 0.704601 (0.7270) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.805s, 39.74/s (0.775s, 41.31/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 11:24:38,491 - train: [ INFO] - Train: 37 [ 350/461 ( 76%)] Loss: 0.703593 (0.7240) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.797s, 40.17/s (0.782s, 40.90/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 11:25:15,872 - train: [ INFO] - Train: 37 [ 400/461 ( 87%)] Loss: 0.704355 (0.7219) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.789s, 40.55/s (0.778s, 41.14/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 11:25:53,632 - train: [ INFO] - Train: 37 [ 450/461 ( 98%)] Loss: 0.692374 (0.7189) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.696s, 45.94/s (0.775s, 41.28/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 11:26:00,832 - train: [ INFO] - Train: 37 [ 460/461 (100%)] Loss: 0.693582 (0.7166) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.936s, 34.20/s (0.774s, 41.35/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 11:26:06,013 - train: [ INFO] - Eval : 37 Time: 4.833 (4.833) Loss: 2.1224 (2.1224) Acc@1: 50.0000 (50.0000)Acc@5: 68.7500 (68.7500) +2025-04-19 11:26:18,350 - train: [ INFO] - Eval : 37 Time: 0.227 (0.337) Loss: 1.7692 (1.9392) Acc@1: 59.3750 (50.0613)Acc@5: 84.3750 (76.2868) +2025-04-19 11:26:24,578 - train: [ INFO] - Eval : 37 Time: 0.073 (0.285) Loss: 3.5366 (1.9243) Acc@1: 0.0000 (49.9614)Acc@5: 0.0000 (76.7155) +2025-04-19 11:26:34,509 - train: [ INFO] - Train: 38 [ 0/461 ( 0%)] Loss: 0.707387 (0.7074) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.658s, 5.66/s (5.658s, 5.66/s) LR: 5.000e-03 Data: 4.701 (4.701) +2025-04-19 11:27:16,158 - train: [ INFO] - Train: 38 [ 50/461 ( 11%)] Loss: 0.705538 (0.7065) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.032s, 31.01/s (0.925s, 34.60/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-19 11:27:55,307 - train: [ INFO] - Train: 38 [ 100/461 ( 22%)] Loss: 0.788494 (0.7338) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.479s, 66.79/s (0.854s, 37.48/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-19 11:28:33,024 - train: [ INFO] - Train: 38 [ 150/461 ( 33%)] Loss: 0.726333 (0.7319) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.827s, 38.67/s (0.820s, 39.01/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-19 11:29:09,837 - train: [ INFO] - Train: 38 [ 200/461 ( 43%)] Loss: 0.697010 (0.7250) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.471s, 67.99/s (0.799s, 40.06/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 11:29:45,152 - train: [ INFO] - Train: 38 [ 250/461 ( 54%)] Loss: 0.765923 (0.7318) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.897s, 35.69/s (0.780s, 41.03/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 11:30:22,003 - train: [ INFO] - Train: 38 [ 300/461 ( 65%)] Loss: 0.698920 (0.7271) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.807s, 39.67/s (0.772s, 41.43/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 11:30:58,239 - train: [ INFO] - Train: 38 [ 350/461 ( 76%)] Loss: 0.703303 (0.7241) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.713s, 44.87/s (0.765s, 41.81/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 11:31:34,384 - train: [ INFO] - Train: 38 [ 400/461 ( 87%)] Loss: 0.704138 (0.7219) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.645s, 49.58/s (0.760s, 42.11/s) LR: 5.000e-03 Data: 0.004 (0.013) +2025-04-19 11:32:11,340 - train: [ INFO] - Train: 38 [ 450/461 ( 98%)] Loss: 0.699189 (0.7196) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.814s, 39.33/s (0.757s, 42.26/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 11:32:19,374 - train: [ INFO] - Train: 38 [ 460/461 (100%)] Loss: 0.680264 (0.7160) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.870s, 36.80/s (0.758s, 42.21/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 11:32:25,244 - train: [ INFO] - Eval : 38 Time: 5.485 (5.485) Loss: 1.9310 (1.9310) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-19 11:32:40,145 - train: [ INFO] - Eval : 38 Time: 0.296 (0.400) Loss: 1.8890 (1.9289) Acc@1: 53.1250 (50.1838)Acc@5: 68.7500 (75.8578) +2025-04-19 11:32:47,571 - train: [ INFO] - Eval : 38 Time: 0.072 (0.339) Loss: 3.0323 (1.9210) Acc@1: 0.0000 (50.0771)Acc@5: 50.0000 (76.1372) +2025-04-19 11:32:57,762 - train: [ INFO] - Train: 39 [ 0/461 ( 0%)] Loss: 0.690804 (0.6908) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.604s, 5.71/s (5.604s, 5.71/s) LR: 5.000e-03 Data: 4.811 (4.811) +2025-04-19 11:33:38,344 - train: [ INFO] - Train: 39 [ 50/461 ( 11%)] Loss: 0.715716 (0.7033) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.615s, 52.03/s (0.902s, 35.46/s) LR: 5.000e-03 Data: 0.000 (0.095) +2025-04-19 11:34:14,677 - train: [ INFO] - Train: 39 [ 100/461 ( 22%)] Loss: 0.703387 (0.7033) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.600s, 53.33/s (0.815s, 39.28/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-19 11:34:53,103 - train: [ INFO] - Train: 39 [ 150/461 ( 33%)] Loss: 0.706419 (0.7041) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.855s, 37.43/s (0.799s, 40.06/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-19 11:35:33,532 - train: [ INFO] - Train: 39 [ 200/461 ( 43%)] Loss: 0.701746 (0.7036) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.983s, 32.56/s (0.801s, 39.97/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 11:36:10,560 - train: [ INFO] - Train: 39 [ 250/461 ( 54%)] Loss: 0.717706 (0.7060) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.775s, 41.29/s (0.788s, 40.59/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 11:36:47,689 - train: [ INFO] - Train: 39 [ 300/461 ( 65%)] Loss: 0.715972 (0.7074) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.833s, 38.41/s (0.780s, 41.00/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 11:37:28,538 - train: [ INFO] - Train: 39 [ 350/461 ( 76%)] Loss: 0.710664 (0.7078) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.729s, 43.92/s (0.785s, 40.74/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 11:38:06,562 - train: [ INFO] - Train: 39 [ 400/461 ( 87%)] Loss: 0.720300 (0.7092) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.506s, 63.22/s (0.782s, 40.92/s) LR: 5.000e-03 Data: 0.003 (0.013) +2025-04-19 11:38:42,617 - train: [ INFO] - Train: 39 [ 450/461 ( 98%)] Loss: 0.739606 (0.7122) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.018s, 31.45/s (0.775s, 41.28/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 11:38:50,888 - train: [ INFO] - Train: 39 [ 460/461 (100%)] Loss: 0.689661 (0.7102) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.788s, 40.59/s (0.776s, 41.22/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 11:38:56,968 - train: [ INFO] - Eval : 39 Time: 5.720 (5.720) Loss: 1.9867 (1.9867) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 11:39:10,802 - train: [ INFO] - Eval : 39 Time: 0.285 (0.383) Loss: 1.7222 (1.8941) Acc@1: 59.3750 (51.1029)Acc@5: 81.2500 (78.6152) +2025-04-19 11:39:18,625 - train: [ INFO] - Eval : 39 Time: 0.064 (0.334) Loss: 2.8237 (1.8869) Acc@1: 0.0000 (51.3493)Acc@5: 50.0000 (78.0648) +2025-04-19 11:39:27,432 - train: [ INFO] - Train: 40 [ 0/461 ( 0%)] Loss: 0.710748 (0.7107) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.663s, 6.86/s (4.663s, 6.86/s) LR: 5.000e-03 Data: 3.903 (3.903) +2025-04-19 11:40:07,255 - train: [ INFO] - Train: 40 [ 50/461 ( 11%)] Loss: 0.710112 (0.7104) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.751s, 42.60/s (0.870s, 36.77/s) LR: 5.000e-03 Data: 0.004 (0.078) +2025-04-19 11:40:43,095 - train: [ INFO] - Train: 40 [ 100/461 ( 22%)] Loss: 0.766669 (0.7292) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.740s, 43.23/s (0.793s, 40.35/s) LR: 5.000e-03 Data: 0.000 (0.040) +2025-04-19 11:41:19,526 - train: [ INFO] - Train: 40 [ 150/461 ( 33%)] Loss: 0.694605 (0.7205) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.692s, 46.22/s (0.771s, 41.49/s) LR: 5.000e-03 Data: 0.001 (0.027) +2025-04-19 11:42:00,106 - train: [ INFO] - Train: 40 [ 200/461 ( 43%)] Loss: 0.768129 (0.7301) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.729s, 43.89/s (0.781s, 41.00/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 11:42:38,416 - train: [ INFO] - Train: 40 [ 250/461 ( 54%)] Loss: 0.705146 (0.7259) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.620s, 51.63/s (0.777s, 41.17/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 11:43:16,360 - train: [ INFO] - Train: 40 [ 300/461 ( 65%)] Loss: 0.686624 (0.7203) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.537s, 59.57/s (0.774s, 41.35/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 11:43:55,096 - train: [ INFO] - Train: 40 [ 350/461 ( 76%)] Loss: 0.691611 (0.7167) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.539s, 59.32/s (0.774s, 41.37/s) LR: 5.000e-03 Data: 0.004 (0.012) +2025-04-19 11:44:31,161 - train: [ INFO] - Train: 40 [ 400/461 ( 87%)] Loss: 0.740772 (0.7194) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.761s, 42.05/s (0.767s, 41.73/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 11:45:09,500 - train: [ INFO] - Train: 40 [ 450/461 ( 98%)] Loss: 0.711423 (0.7186) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.627s, 51.03/s (0.767s, 41.74/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 11:45:17,420 - train: [ INFO] - Train: 40 [ 460/461 (100%)] Loss: 0.697984 (0.7167) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.738s, 43.35/s (0.767s, 41.71/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 11:45:23,404 - train: [ INFO] - Eval : 40 Time: 5.664 (5.664) Loss: 2.0281 (2.0281) Acc@1: 46.8750 (46.8750)Acc@5: 84.3750 (84.3750) +2025-04-19 11:45:37,526 - train: [ INFO] - Eval : 40 Time: 0.326 (0.388) Loss: 1.7576 (1.9670) Acc@1: 59.3750 (48.4069)Acc@5: 81.2500 (75.6127) +2025-04-19 11:45:45,338 - train: [ INFO] - Eval : 40 Time: 0.073 (0.337) Loss: 2.5833 (1.9453) Acc@1: 0.0000 (49.0748)Acc@5: 50.0000 (75.9445) +2025-04-19 11:45:54,624 - train: [ INFO] - Train: 41 [ 0/461 ( 0%)] Loss: 0.704133 (0.7041) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.508s, 5.81/s (5.508s, 5.81/s) LR: 5.000e-03 Data: 4.550 (4.550) +2025-04-19 11:46:34,474 - train: [ INFO] - Train: 41 [ 50/461 ( 11%)] Loss: 0.756929 (0.7305) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.714s, 44.83/s (0.884s, 36.20/s) LR: 5.000e-03 Data: 0.001 (0.091) +2025-04-19 11:47:16,338 - train: [ INFO] - Train: 41 [ 100/461 ( 22%)] Loss: 0.696227 (0.7191) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.987s, 32.43/s (0.860s, 37.22/s) LR: 5.000e-03 Data: 0.000 (0.046) +2025-04-19 11:47:54,257 - train: [ INFO] - Train: 41 [ 150/461 ( 33%)] Loss: 0.715786 (0.7183) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.838s, 38.17/s (0.825s, 38.79/s) LR: 5.000e-03 Data: 0.001 (0.031) +2025-04-19 11:48:31,054 - train: [ INFO] - Train: 41 [ 200/461 ( 43%)] Loss: 0.718246 (0.7183) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.727s, 44.00/s (0.802s, 39.89/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 11:49:08,442 - train: [ INFO] - Train: 41 [ 250/461 ( 54%)] Loss: 0.813481 (0.7341) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.567s, 56.47/s (0.791s, 40.46/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 11:49:43,520 - train: [ INFO] - Train: 41 [ 300/461 ( 65%)] Loss: 0.703265 (0.7297) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.625s, 51.24/s (0.776s, 41.25/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 11:50:20,861 - train: [ INFO] - Train: 41 [ 350/461 ( 76%)] Loss: 0.694609 (0.7253) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.823s, 38.89/s (0.771s, 41.48/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 11:51:00,869 - train: [ INFO] - Train: 41 [ 400/461 ( 87%)] Loss: 0.701674 (0.7227) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.908s, 35.26/s (0.775s, 41.31/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 11:51:41,403 - train: [ INFO] - Train: 41 [ 450/461 ( 98%)] Loss: 0.717775 (0.7222) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.487s, 65.74/s (0.778s, 41.11/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 11:51:49,350 - train: [ INFO] - Train: 41 [ 460/461 (100%)] Loss: 0.739096 (0.7237) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.040s, 30.76/s (0.779s, 41.09/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 11:51:55,156 - train: [ INFO] - Eval : 41 Time: 5.445 (5.445) Loss: 1.9178 (1.9178) Acc@1: 56.2500 (56.2500)Acc@5: 75.0000 (75.0000) +2025-04-19 11:52:08,536 - train: [ INFO] - Eval : 41 Time: 0.282 (0.369) Loss: 1.8462 (1.9430) Acc@1: 59.3750 (50.2451)Acc@5: 78.1250 (74.2647) +2025-04-19 11:52:15,220 - train: [ INFO] - Eval : 41 Time: 0.079 (0.311) Loss: 3.0961 (1.9286) Acc@1: 0.0000 (50.6168)Acc@5: 50.0000 (75.2120) +2025-04-19 11:52:24,524 - train: [ INFO] - Train: 42 [ 0/461 ( 0%)] Loss: 0.692987 (0.6930) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.078s, 6.30/s (5.078s, 6.30/s) LR: 5.000e-03 Data: 4.276 (4.276) +2025-04-19 11:53:03,345 - train: [ INFO] - Train: 42 [ 50/461 ( 11%)] Loss: 0.716015 (0.7045) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.759s, 42.15/s (0.859s, 37.25/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-19 11:53:35,508 - train: [ INFO] - Train: 42 [ 100/461 ( 22%)] Loss: 0.692091 (0.7004) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.496s, 64.47/s (0.751s, 42.58/s) LR: 5.000e-03 Data: 0.003 (0.048) +2025-04-19 11:54:11,684 - train: [ INFO] - Train: 42 [ 150/461 ( 33%)] Loss: 0.729624 (0.7077) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.748s, 42.76/s (0.741s, 43.17/s) LR: 5.000e-03 Data: 0.001 (0.033) +2025-04-19 11:54:52,064 - train: [ INFO] - Train: 42 [ 200/461 ( 43%)] Loss: 0.705755 (0.7073) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.926s, 34.56/s (0.757s, 42.26/s) LR: 5.000e-03 Data: 0.006 (0.025) +2025-04-19 11:55:32,037 - train: [ INFO] - Train: 42 [ 250/461 ( 54%)] Loss: 0.714267 (0.7085) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.988s, 32.39/s (0.765s, 41.82/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 11:56:13,353 - train: [ INFO] - Train: 42 [ 300/461 ( 65%)] Loss: 0.768642 (0.7171) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.906s, 35.33/s (0.775s, 41.30/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 11:56:49,953 - train: [ INFO] - Train: 42 [ 350/461 ( 76%)] Loss: 0.762258 (0.7227) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.733s, 43.67/s (0.769s, 41.64/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 11:57:29,674 - train: [ INFO] - Train: 42 [ 400/461 ( 87%)] Loss: 0.700185 (0.7202) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.824s, 38.83/s (0.771s, 41.48/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 11:58:07,791 - train: [ INFO] - Train: 42 [ 450/461 ( 98%)] Loss: 0.716852 (0.7199) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.802s, 39.88/s (0.770s, 41.55/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 11:58:14,272 - train: [ INFO] - Train: 42 [ 460/461 (100%)] Loss: 0.687321 (0.7169) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.582s, 54.96/s (0.768s, 41.69/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 11:58:20,361 - train: [ INFO] - Eval : 42 Time: 5.720 (5.720) Loss: 2.0962 (2.0962) Acc@1: 40.6250 (40.6250)Acc@5: 68.7500 (68.7500) +2025-04-19 11:58:33,497 - train: [ INFO] - Eval : 42 Time: 0.200 (0.370) Loss: 1.8744 (1.9366) Acc@1: 50.0000 (49.9387)Acc@5: 71.8750 (76.7157) +2025-04-19 11:58:40,759 - train: [ INFO] - Eval : 42 Time: 0.082 (0.319) Loss: 3.5331 (1.9345) Acc@1: 0.0000 (49.4988)Acc@5: 0.0000 (76.7155) +2025-04-19 11:58:48,939 - train: [ INFO] - Train: 43 [ 0/461 ( 0%)] Loss: 0.696149 (0.6961) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.380s, 7.31/s (4.380s, 7.31/s) LR: 5.000e-03 Data: 3.591 (3.591) +2025-04-19 11:59:26,200 - train: [ INFO] - Train: 43 [ 50/461 ( 11%)] Loss: 0.737693 (0.7169) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.740s, 43.27/s (0.814s, 39.30/s) LR: 5.000e-03 Data: 0.001 (0.075) +2025-04-19 12:00:01,845 - train: [ INFO] - Train: 43 [ 100/461 ( 22%)] Loss: 0.690062 (0.7080) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.738s, 43.37/s (0.763s, 41.93/s) LR: 5.000e-03 Data: 0.000 (0.038) +2025-04-19 12:00:39,521 - train: [ INFO] - Train: 43 [ 150/461 ( 33%)] Loss: 0.700062 (0.7060) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.839s, 38.13/s (0.759s, 42.15/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 12:01:14,884 - train: [ INFO] - Train: 43 [ 200/461 ( 43%)] Loss: 0.756949 (0.7162) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.631s, 50.71/s (0.746s, 42.91/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 12:01:57,791 - train: [ INFO] - Train: 43 [ 250/461 ( 54%)] Loss: 0.708505 (0.7149) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.992s, 32.26/s (0.768s, 41.67/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 12:02:38,147 - train: [ INFO] - Train: 43 [ 300/461 ( 65%)] Loss: 0.693655 (0.7119) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.714s, 44.80/s (0.774s, 41.34/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:03:18,741 - train: [ INFO] - Train: 43 [ 350/461 ( 76%)] Loss: 0.719131 (0.7128) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.907s, 35.26/s (0.779s, 41.07/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 12:03:58,727 - train: [ INFO] - Train: 43 [ 400/461 ( 87%)] Loss: 0.683338 (0.7095) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.492s, 65.07/s (0.781s, 40.95/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 12:04:36,803 - train: [ INFO] - Train: 43 [ 450/461 ( 98%)] Loss: 0.717452 (0.7103) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.882s, 36.28/s (0.779s, 41.08/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 12:04:43,625 - train: [ INFO] - Train: 43 [ 460/461 (100%)] Loss: 0.707581 (0.7101) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.583s, 54.90/s (0.777s, 41.19/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 12:04:48,741 - train: [ INFO] - Eval : 43 Time: 4.766 (4.766) Loss: 2.0421 (2.0421) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-19 12:05:02,406 - train: [ INFO] - Eval : 43 Time: 0.374 (0.361) Loss: 1.8013 (1.9266) Acc@1: 53.1250 (49.7549)Acc@5: 78.1250 (77.0221) +2025-04-19 12:05:09,864 - train: [ INFO] - Eval : 43 Time: 0.083 (0.316) Loss: 3.4665 (1.9232) Acc@1: 0.0000 (50.0771)Acc@5: 0.0000 (76.6769) +2025-04-19 12:05:19,678 - train: [ INFO] - Train: 44 [ 0/461 ( 0%)] Loss: 0.698822 (0.6988) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.756s, 5.56/s (5.756s, 5.56/s) LR: 5.000e-03 Data: 5.015 (5.015) +2025-04-19 12:05:55,741 - train: [ INFO] - Train: 44 [ 50/461 ( 11%)] Loss: 0.712772 (0.7058) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.823s, 38.89/s (0.818s, 39.11/s) LR: 5.000e-03 Data: 0.000 (0.100) +2025-04-19 12:06:33,729 - train: [ INFO] - Train: 44 [ 100/461 ( 22%)] Loss: 0.692582 (0.7014) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.723s, 44.27/s (0.788s, 40.60/s) LR: 5.000e-03 Data: 0.001 (0.051) +2025-04-19 12:07:12,297 - train: [ INFO] - Train: 44 [ 150/461 ( 33%)] Loss: 0.697877 (0.7005) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.924s, 34.63/s (0.782s, 40.93/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 12:07:48,080 - train: [ INFO] - Train: 44 [ 200/461 ( 43%)] Loss: 0.721140 (0.7046) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.608s, 52.62/s (0.765s, 41.84/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 12:08:23,448 - train: [ INFO] - Train: 44 [ 250/461 ( 54%)] Loss: 0.686704 (0.7016) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.961s, 33.28/s (0.753s, 42.49/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 12:08:59,957 - train: [ INFO] - Train: 44 [ 300/461 ( 65%)] Loss: 0.701250 (0.7016) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.615s, 52.01/s (0.749s, 42.72/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 12:09:38,769 - train: [ INFO] - Train: 44 [ 350/461 ( 76%)] Loss: 0.727730 (0.7049) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.594s, 53.89/s (0.753s, 42.52/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 12:10:13,906 - train: [ INFO] - Train: 44 [ 400/461 ( 87%)] Loss: 0.694224 (0.7037) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.626s, 51.12/s (0.746s, 42.88/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:10:52,591 - train: [ INFO] - Train: 44 [ 450/461 ( 98%)] Loss: 0.731378 (0.7064) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.762s, 41.97/s (0.749s, 42.72/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 12:11:00,074 - train: [ INFO] - Train: 44 [ 460/461 (100%)] Loss: 0.729547 (0.7085) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.794s, 40.29/s (0.749s, 42.73/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 12:11:06,181 - train: [ INFO] - Eval : 44 Time: 5.742 (5.742) Loss: 2.0439 (2.0439) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-19 12:11:20,177 - train: [ INFO] - Eval : 44 Time: 0.221 (0.387) Loss: 1.7577 (1.9684) Acc@1: 59.3750 (47.8554)Acc@5: 75.0000 (75.3064) +2025-04-19 12:11:28,085 - train: [ INFO] - Eval : 44 Time: 0.090 (0.337) Loss: 3.2402 (1.9689) Acc@1: 0.0000 (47.7641)Acc@5: 50.0000 (75.2506) +2025-04-19 12:11:37,932 - train: [ INFO] - Train: 45 [ 0/461 ( 0%)] Loss: 0.717236 (0.7172) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.254s, 6.09/s (5.254s, 6.09/s) LR: 5.000e-03 Data: 4.379 (4.379) +2025-04-19 12:12:14,696 - train: [ INFO] - Train: 45 [ 50/461 ( 11%)] Loss: 0.727510 (0.7224) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.598s, 53.55/s (0.821s, 38.97/s) LR: 5.000e-03 Data: 0.000 (0.087) +2025-04-19 12:12:50,954 - train: [ INFO] - Train: 45 [ 100/461 ( 22%)] Loss: 0.713372 (0.7194) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.593s, 53.97/s (0.772s, 41.43/s) LR: 5.000e-03 Data: 0.001 (0.045) +2025-04-19 12:13:26,587 - train: [ INFO] - Train: 45 [ 150/461 ( 33%)] Loss: 0.698562 (0.7142) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.743s, 43.08/s (0.752s, 42.56/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-19 12:14:02,537 - train: [ INFO] - Train: 45 [ 200/461 ( 43%)] Loss: 0.699226 (0.7112) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.537s, 59.62/s (0.743s, 43.05/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-19 12:14:39,367 - train: [ INFO] - Train: 45 [ 250/461 ( 54%)] Loss: 0.690605 (0.7078) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.970s, 33.01/s (0.742s, 43.15/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 12:15:19,115 - train: [ INFO] - Train: 45 [ 300/461 ( 65%)] Loss: 0.687833 (0.7049) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.954s, 33.53/s (0.750s, 42.66/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 12:15:57,895 - train: [ INFO] - Train: 45 [ 350/461 ( 76%)] Loss: 0.702945 (0.7047) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.668s, 47.88/s (0.754s, 42.47/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:16:34,420 - train: [ INFO] - Train: 45 [ 400/461 ( 87%)] Loss: 0.699277 (0.7041) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.683s, 46.84/s (0.750s, 42.64/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 12:17:10,420 - train: [ INFO] - Train: 45 [ 450/461 ( 98%)] Loss: 0.687450 (0.7024) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.755s, 42.39/s (0.747s, 42.84/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 12:17:17,859 - train: [ INFO] - Train: 45 [ 460/461 (100%)] Loss: 0.770488 (0.7086) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.743s, 43.07/s (0.747s, 42.85/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 12:17:24,581 - train: [ INFO] - Eval : 45 Time: 6.370 (6.370) Loss: 2.1208 (2.1208) Acc@1: 40.6250 (40.6250)Acc@5: 71.8750 (71.8750) +2025-04-19 12:17:38,421 - train: [ INFO] - Eval : 45 Time: 0.257 (0.396) Loss: 1.8222 (1.9328) Acc@1: 53.1250 (50.4902)Acc@5: 78.1250 (75.8578) +2025-04-19 12:17:46,250 - train: [ INFO] - Eval : 45 Time: 0.065 (0.342) Loss: 3.2003 (1.9245) Acc@1: 0.0000 (49.9229)Acc@5: 50.0000 (76.1372) +2025-04-19 12:17:55,828 - train: [ INFO] - Train: 46 [ 0/461 ( 0%)] Loss: 0.706505 (0.7065) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.509s, 5.81/s (5.509s, 5.81/s) LR: 5.000e-03 Data: 4.746 (4.746) +2025-04-19 12:18:36,169 - train: [ INFO] - Train: 46 [ 50/461 ( 11%)] Loss: 0.694038 (0.7003) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.955s, 33.51/s (0.896s, 35.70/s) LR: 5.000e-03 Data: 0.000 (0.094) +2025-04-19 12:19:16,413 - train: [ INFO] - Train: 46 [ 100/461 ( 22%)] Loss: 0.704493 (0.7017) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.757s, 42.30/s (0.850s, 37.64/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-19 12:19:58,158 - train: [ INFO] - Train: 46 [ 150/461 ( 33%)] Loss: 0.716734 (0.7054) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.911s, 35.14/s (0.844s, 37.90/s) LR: 5.000e-03 Data: 0.001 (0.032) +2025-04-19 12:20:36,826 - train: [ INFO] - Train: 46 [ 200/461 ( 43%)] Loss: 0.715934 (0.7075) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.728s, 43.94/s (0.826s, 38.74/s) LR: 5.000e-03 Data: 0.007 (0.025) +2025-04-19 12:21:17,410 - train: [ INFO] - Train: 46 [ 250/461 ( 54%)] Loss: 0.697553 (0.7059) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.722s, 44.34/s (0.823s, 38.89/s) LR: 5.000e-03 Data: 0.001 (0.020) +2025-04-19 12:21:55,098 - train: [ INFO] - Train: 46 [ 300/461 ( 65%)] Loss: 0.690913 (0.7037) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.774s, 41.34/s (0.811s, 39.46/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 12:22:33,471 - train: [ INFO] - Train: 46 [ 350/461 ( 76%)] Loss: 0.688484 (0.7018) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.823s, 38.88/s (0.804s, 39.78/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 12:23:14,191 - train: [ INFO] - Train: 46 [ 400/461 ( 87%)] Loss: 0.695524 (0.7011) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.690s, 46.38/s (0.805s, 39.73/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 12:23:55,410 - train: [ INFO] - Train: 46 [ 450/461 ( 98%)] Loss: 0.739648 (0.7050) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.826s, 38.72/s (0.807s, 39.64/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 12:24:02,639 - train: [ INFO] - Train: 46 [ 460/461 (100%)] Loss: 0.710742 (0.7055) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.986s, 32.44/s (0.805s, 39.73/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 12:24:08,929 - train: [ INFO] - Eval : 46 Time: 5.906 (5.906) Loss: 1.9904 (1.9904) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 12:24:22,756 - train: [ INFO] - Eval : 46 Time: 0.286 (0.387) Loss: 1.7776 (1.9324) Acc@1: 59.3750 (49.2034)Acc@5: 87.5000 (76.5931) +2025-04-19 12:24:30,058 - train: [ INFO] - Eval : 46 Time: 0.073 (0.330) Loss: 3.5457 (1.9364) Acc@1: 0.0000 (49.2290)Acc@5: 0.0000 (76.4071) +2025-04-19 12:24:40,715 - train: [ INFO] - Train: 47 [ 0/461 ( 0%)] Loss: 0.827199 (0.8272) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 6.385s, 5.01/s (6.385s, 5.01/s) LR: 5.000e-03 Data: 5.407 (5.407) +2025-04-19 12:25:23,666 - train: [ INFO] - Train: 47 [ 50/461 ( 11%)] Loss: 0.704336 (0.7658) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.944s, 33.90/s (0.965s, 33.16/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-19 12:26:00,932 - train: [ INFO] - Train: 47 [ 100/461 ( 22%)] Loss: 0.693330 (0.7416) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.961s, 33.28/s (0.855s, 37.42/s) LR: 5.000e-03 Data: 0.006 (0.054) +2025-04-19 12:26:36,306 - train: [ INFO] - Train: 47 [ 150/461 ( 33%)] Loss: 0.721479 (0.7366) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.605s, 52.86/s (0.805s, 39.73/s) LR: 5.000e-03 Data: 0.000 (0.037) +2025-04-19 12:27:14,368 - train: [ INFO] - Train: 47 [ 200/461 ( 43%)] Loss: 0.703637 (0.7300) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.818s, 39.11/s (0.794s, 40.31/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-19 12:27:50,880 - train: [ INFO] - Train: 47 [ 250/461 ( 54%)] Loss: 0.702385 (0.7254) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.588s, 54.46/s (0.781s, 40.99/s) LR: 5.000e-03 Data: 0.003 (0.022) +2025-04-19 12:28:27,570 - train: [ INFO] - Train: 47 [ 300/461 ( 65%)] Loss: 0.721002 (0.7248) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.774s, 41.34/s (0.773s, 41.42/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 12:29:08,022 - train: [ INFO] - Train: 47 [ 350/461 ( 76%)] Loss: 0.685984 (0.7199) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.854s, 37.49/s (0.778s, 41.16/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 12:29:49,612 - train: [ INFO] - Train: 47 [ 400/461 ( 87%)] Loss: 0.688985 (0.7165) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.839s, 38.12/s (0.784s, 40.81/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:30:31,579 - train: [ INFO] - Train: 47 [ 450/461 ( 98%)] Loss: 0.692946 (0.7141) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.752s, 42.54/s (0.790s, 40.51/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 12:30:40,106 - train: [ INFO] - Train: 47 [ 460/461 (100%)] Loss: 0.708459 (0.7136) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.956s, 33.46/s (0.791s, 40.44/s) LR: 5.000e-03 Data: 0.007 (0.013) +2025-04-19 12:30:44,730 - train: [ INFO] - Eval : 47 Time: 4.286 (4.286) Loss: 2.0306 (2.0306) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-19 12:30:58,265 - train: [ INFO] - Eval : 47 Time: 0.253 (0.349) Loss: 1.6834 (1.9150) Acc@1: 59.3750 (50.7353)Acc@5: 84.3750 (76.5931) +2025-04-19 12:31:05,940 - train: [ INFO] - Eval : 47 Time: 0.066 (0.311) Loss: 3.2478 (1.9175) Acc@1: 0.0000 (50.2313)Acc@5: 50.0000 (77.0239) +2025-04-19 12:31:16,862 - train: [ INFO] - Train: 48 [ 0/461 ( 0%)] Loss: 0.713324 (0.7133) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.309s, 5.07/s (6.309s, 5.07/s) LR: 5.000e-03 Data: 5.446 (5.446) +2025-04-19 12:31:57,909 - train: [ INFO] - Train: 48 [ 50/461 ( 11%)] Loss: 0.695907 (0.7046) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.693s, 46.16/s (0.927s, 34.53/s) LR: 5.000e-03 Data: 0.001 (0.107) +2025-04-19 12:32:39,588 - train: [ INFO] - Train: 48 [ 100/461 ( 22%)] Loss: 0.711560 (0.7069) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.811s, 39.45/s (0.880s, 36.38/s) LR: 5.000e-03 Data: 0.000 (0.055) +2025-04-19 12:33:21,041 - train: [ INFO] - Train: 48 [ 150/461 ( 33%)] Loss: 0.701087 (0.7055) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.742s, 43.15/s (0.862s, 37.11/s) LR: 5.000e-03 Data: 0.000 (0.037) +2025-04-19 12:34:01,819 - train: [ INFO] - Train: 48 [ 200/461 ( 43%)] Loss: 0.785625 (0.7215) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.670s, 47.78/s (0.850s, 37.64/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-19 12:34:41,926 - train: [ INFO] - Train: 48 [ 250/461 ( 54%)] Loss: 0.794790 (0.7337) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.722s, 44.31/s (0.840s, 38.09/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 12:35:23,191 - train: [ INFO] - Train: 48 [ 300/461 ( 65%)] Loss: 0.699338 (0.7288) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.749s, 42.73/s (0.837s, 38.22/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 12:36:03,465 - train: [ INFO] - Train: 48 [ 350/461 ( 76%)] Loss: 0.718078 (0.7275) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.902s, 35.50/s (0.832s, 38.44/s) LR: 5.000e-03 Data: 0.007 (0.016) +2025-04-19 12:36:39,470 - train: [ INFO] - Train: 48 [ 400/461 ( 87%)] Loss: 0.693277 (0.7237) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.977s, 32.76/s (0.818s, 39.11/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:37:18,546 - train: [ INFO] - Train: 48 [ 450/461 ( 98%)] Loss: 0.707977 (0.7221) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.878s, 36.46/s (0.814s, 39.32/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 12:37:25,491 - train: [ INFO] - Train: 48 [ 460/461 (100%)] Loss: 0.724913 (0.7224) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.732s, 43.72/s (0.811s, 39.44/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 12:37:31,556 - train: [ INFO] - Eval : 48 Time: 5.650 (5.650) Loss: 1.8747 (1.8747) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 12:37:44,915 - train: [ INFO] - Eval : 48 Time: 0.284 (0.373) Loss: 1.8024 (1.9313) Acc@1: 50.0000 (49.7549)Acc@5: 75.0000 (76.3480) +2025-04-19 12:37:52,690 - train: [ INFO] - Eval : 48 Time: 0.064 (0.327) Loss: 3.6392 (1.9193) Acc@1: 0.0000 (50.3084)Acc@5: 0.0000 (76.4071) +2025-04-19 12:38:02,956 - train: [ INFO] - Train: 49 [ 0/461 ( 0%)] Loss: 0.750153 (0.7502) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.878s, 5.44/s (5.878s, 5.44/s) LR: 5.000e-03 Data: 5.006 (5.006) +2025-04-19 12:38:43,609 - train: [ INFO] - Train: 49 [ 50/461 ( 11%)] Loss: 0.705993 (0.7281) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.840s, 38.12/s (0.910s, 35.18/s) LR: 5.000e-03 Data: 0.000 (0.099) +2025-04-19 12:39:19,217 - train: [ INFO] - Train: 49 [ 100/461 ( 22%)] Loss: 0.707208 (0.7211) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.602s, 53.19/s (0.811s, 39.46/s) LR: 5.000e-03 Data: 0.001 (0.051) +2025-04-19 12:39:54,535 - train: [ INFO] - Train: 49 [ 150/461 ( 33%)] Loss: 0.758194 (0.7304) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.589s, 54.34/s (0.776s, 41.25/s) LR: 5.000e-03 Data: 0.001 (0.034) +2025-04-19 12:40:34,363 - train: [ INFO] - Train: 49 [ 200/461 ( 43%)] Loss: 0.711321 (0.7266) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.844s, 37.91/s (0.780s, 41.00/s) LR: 5.000e-03 Data: 0.002 (0.026) +2025-04-19 12:41:10,952 - train: [ INFO] - Train: 49 [ 250/461 ( 54%)] Loss: 0.697723 (0.7218) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.773s, 41.38/s (0.770s, 41.53/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 12:41:50,338 - train: [ INFO] - Train: 49 [ 300/461 ( 65%)] Loss: 0.710699 (0.7202) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.807s, 39.64/s (0.773s, 41.39/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 12:42:26,338 - train: [ INFO] - Train: 49 [ 350/461 ( 76%)] Loss: 0.692055 (0.7167) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.548s, 58.37/s (0.765s, 41.82/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 12:43:07,847 - train: [ INFO] - Train: 49 [ 400/461 ( 87%)] Loss: 0.694383 (0.7142) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.819s, 39.05/s (0.773s, 41.40/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:43:49,600 - train: [ INFO] - Train: 49 [ 450/461 ( 98%)] Loss: 0.695797 (0.7124) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.908s, 35.26/s (0.780s, 41.04/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 12:43:56,829 - train: [ INFO] - Train: 49 [ 460/461 (100%)] Loss: 0.698407 (0.7111) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.467s, 68.51/s (0.778s, 41.11/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 12:44:02,287 - train: [ INFO] - Eval : 49 Time: 5.126 (5.126) Loss: 2.1149 (2.1149) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 12:44:15,952 - train: [ INFO] - Eval : 49 Time: 0.309 (0.368) Loss: 1.8517 (1.9641) Acc@1: 53.1250 (49.9387)Acc@5: 81.2500 (75.0613) +2025-04-19 12:44:23,848 - train: [ INFO] - Eval : 49 Time: 0.075 (0.325) Loss: 3.8075 (1.9485) Acc@1: 0.0000 (49.9614)Acc@5: 0.0000 (75.7517) +2025-04-19 12:44:33,567 - train: [ INFO] - Train: 50 [ 0/461 ( 0%)] Loss: 0.703528 (0.7035) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.413s, 5.91/s (5.413s, 5.91/s) LR: 5.000e-03 Data: 4.698 (4.698) +2025-04-19 12:45:11,933 - train: [ INFO] - Train: 50 [ 50/461 ( 11%)] Loss: 0.770388 (0.7370) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.947s, 33.79/s (0.857s, 37.35/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-19 12:45:50,786 - train: [ INFO] - Train: 50 [ 100/461 ( 22%)] Loss: 0.742961 (0.7390) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.621s, 51.51/s (0.817s, 39.18/s) LR: 5.000e-03 Data: 0.000 (0.047) +2025-04-19 12:46:31,130 - train: [ INFO] - Train: 50 [ 150/461 ( 33%)] Loss: 0.702801 (0.7299) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.744s, 43.02/s (0.813s, 39.37/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-19 12:47:10,596 - train: [ INFO] - Train: 50 [ 200/461 ( 43%)] Loss: 0.702589 (0.7245) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.612s, 52.32/s (0.807s, 39.67/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 12:47:49,832 - train: [ INFO] - Train: 50 [ 250/461 ( 54%)] Loss: 0.754496 (0.7295) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.886s, 36.11/s (0.802s, 39.90/s) LR: 5.000e-03 Data: 0.002 (0.020) +2025-04-19 12:48:26,860 - train: [ INFO] - Train: 50 [ 300/461 ( 65%)] Loss: 0.719904 (0.7281) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.938s, 34.12/s (0.791s, 40.43/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 12:49:07,612 - train: [ INFO] - Train: 50 [ 350/461 ( 76%)] Loss: 0.690206 (0.7234) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.904s, 35.38/s (0.795s, 40.27/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:49:46,420 - train: [ INFO] - Train: 50 [ 400/461 ( 87%)] Loss: 0.697650 (0.7205) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.642s, 49.81/s (0.792s, 40.40/s) LR: 5.000e-03 Data: 0.005 (0.013) +2025-04-19 12:50:25,272 - train: [ INFO] - Train: 50 [ 450/461 ( 98%)] Loss: 0.742455 (0.7227) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.777s, 41.18/s (0.790s, 40.50/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 12:50:32,248 - train: [ INFO] - Train: 50 [ 460/461 (100%)] Loss: 0.712170 (0.7217) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.784s, 40.81/s (0.788s, 40.61/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 12:50:37,849 - train: [ INFO] - Eval : 50 Time: 5.259 (5.259) Loss: 1.9977 (1.9977) Acc@1: 40.6250 (40.6250)Acc@5: 71.8750 (71.8750) +2025-04-19 12:50:51,167 - train: [ INFO] - Eval : 50 Time: 0.263 (0.364) Loss: 1.7551 (1.9538) Acc@1: 56.2500 (50.7353)Acc@5: 81.2500 (76.1642) +2025-04-19 12:50:58,553 - train: [ INFO] - Eval : 50 Time: 0.069 (0.317) Loss: 2.7743 (1.9434) Acc@1: 0.0000 (50.6168)Acc@5: 50.0000 (76.5613) +2025-04-19 12:51:07,668 - train: [ INFO] - Train: 51 [ 0/461 ( 0%)] Loss: 0.698156 (0.6982) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.074s, 6.31/s (5.074s, 6.31/s) LR: 5.000e-03 Data: 4.287 (4.287) +2025-04-19 12:51:45,638 - train: [ INFO] - Train: 51 [ 50/461 ( 11%)] Loss: 0.695037 (0.6966) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.669s, 47.85/s (0.843s, 37.98/s) LR: 5.000e-03 Data: 0.001 (0.086) +2025-04-19 12:52:18,474 - train: [ INFO] - Train: 51 [ 100/461 ( 22%)] Loss: 0.782748 (0.7253) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.761s, 42.02/s (0.749s, 42.70/s) LR: 5.000e-03 Data: 0.000 (0.044) +2025-04-19 12:52:57,801 - train: [ INFO] - Train: 51 [ 150/461 ( 33%)] Loss: 0.695102 (0.7178) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.838s, 38.18/s (0.761s, 42.04/s) LR: 5.000e-03 Data: 0.001 (0.030) +2025-04-19 12:53:36,465 - train: [ INFO] - Train: 51 [ 200/461 ( 43%)] Loss: 0.708037 (0.7158) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.692s, 46.25/s (0.764s, 41.90/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-19 12:54:11,822 - train: [ INFO] - Train: 51 [ 250/461 ( 54%)] Loss: 0.731989 (0.7185) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.648s, 49.41/s (0.752s, 42.55/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 12:54:53,318 - train: [ INFO] - Train: 51 [ 300/461 ( 65%)] Loss: 0.703779 (0.7164) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.626s, 51.15/s (0.765s, 41.85/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 12:55:34,113 - train: [ INFO] - Train: 51 [ 350/461 ( 76%)] Loss: 0.699992 (0.7144) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.834s, 38.37/s (0.772s, 41.47/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 12:56:13,745 - train: [ INFO] - Train: 51 [ 400/461 ( 87%)] Loss: 0.701076 (0.7129) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.942s, 33.96/s (0.774s, 41.34/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 12:56:47,174 - train: [ INFO] - Train: 51 [ 450/461 ( 98%)] Loss: 0.698222 (0.7114) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.498s, 64.25/s (0.762s, 41.99/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 12:56:52,905 - train: [ INFO] - Train: 51 [ 460/461 (100%)] Loss: 0.685109 (0.7090) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.853s, 37.53/s (0.758s, 42.22/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 12:56:59,043 - train: [ INFO] - Eval : 51 Time: 5.830 (5.830) Loss: 1.9866 (1.9866) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-19 12:57:12,831 - train: [ INFO] - Eval : 51 Time: 0.324 (0.385) Loss: 1.7395 (1.9619) Acc@1: 62.5000 (49.0196)Acc@5: 78.1250 (75.6127) +2025-04-19 12:57:20,908 - train: [ INFO] - Eval : 51 Time: 0.066 (0.338) Loss: 3.6769 (1.9511) Acc@1: 0.0000 (50.0771)Acc@5: 0.0000 (75.8674) +2025-04-19 12:57:33,103 - train: [ INFO] - Train: 52 [ 0/461 ( 0%)] Loss: 0.700211 (0.7002) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.679s, 4.17/s (7.679s, 4.17/s) LR: 5.000e-03 Data: 6.719 (6.719) +2025-04-19 12:58:12,593 - train: [ INFO] - Train: 52 [ 50/461 ( 11%)] Loss: 0.702336 (0.7013) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.715s, 44.75/s (0.923s, 34.67/s) LR: 5.000e-03 Data: 0.001 (0.133) +2025-04-19 12:58:50,539 - train: [ INFO] - Train: 52 [ 100/461 ( 22%)] Loss: 0.712128 (0.7049) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.847s, 37.76/s (0.841s, 38.05/s) LR: 5.000e-03 Data: 0.000 (0.068) +2025-04-19 12:59:30,728 - train: [ INFO] - Train: 52 [ 150/461 ( 33%)] Loss: 0.716440 (0.7078) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.888s, 36.02/s (0.828s, 38.64/s) LR: 5.000e-03 Data: 0.000 (0.045) +2025-04-19 13:00:12,209 - train: [ INFO] - Train: 52 [ 200/461 ( 43%)] Loss: 0.691308 (0.7045) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.695s, 46.04/s (0.828s, 38.67/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 13:00:52,093 - train: [ INFO] - Train: 52 [ 250/461 ( 54%)] Loss: 0.696121 (0.7031) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.868s, 36.88/s (0.821s, 38.96/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-19 13:01:32,670 - train: [ INFO] - Train: 52 [ 300/461 ( 65%)] Loss: 0.703751 (0.7032) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.878s, 36.44/s (0.819s, 39.06/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 13:02:10,556 - train: [ INFO] - Train: 52 [ 350/461 ( 76%)] Loss: 0.745404 (0.7085) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.868s, 36.86/s (0.810s, 39.50/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 13:02:51,961 - train: [ INFO] - Train: 52 [ 400/461 ( 87%)] Loss: 0.701231 (0.7077) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.728s, 43.96/s (0.812s, 39.40/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 13:03:31,952 - train: [ INFO] - Train: 52 [ 450/461 ( 98%)] Loss: 0.697544 (0.7066) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.825s, 38.81/s (0.811s, 39.48/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 13:03:39,607 - train: [ INFO] - Train: 52 [ 460/461 (100%)] Loss: 0.699955 (0.7060) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.733s, 43.63/s (0.809s, 39.53/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 13:03:45,520 - train: [ INFO] - Eval : 52 Time: 5.592 (5.592) Loss: 2.1186 (2.1186) Acc@1: 43.7500 (43.7500)Acc@5: 65.6250 (65.6250) +2025-04-19 13:03:58,884 - train: [ INFO] - Eval : 52 Time: 0.274 (0.372) Loss: 1.6485 (1.9424) Acc@1: 62.5000 (51.1029)Acc@5: 81.2500 (76.0417) +2025-04-19 13:04:06,337 - train: [ INFO] - Eval : 52 Time: 0.092 (0.322) Loss: 3.2244 (1.9396) Acc@1: 0.0000 (50.7710)Acc@5: 50.0000 (76.3685) +2025-04-19 13:04:15,719 - train: [ INFO] - Train: 53 [ 0/461 ( 0%)] Loss: 0.724699 (0.7247) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.080s, 6.30/s (5.080s, 6.30/s) LR: 5.000e-03 Data: 4.002 (4.002) +2025-04-19 13:04:54,767 - train: [ INFO] - Train: 53 [ 50/461 ( 11%)] Loss: 0.686262 (0.7055) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.47/s (0.864s, 37.06/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-19 13:05:32,720 - train: [ INFO] - Train: 53 [ 100/461 ( 22%)] Loss: 0.712983 (0.7080) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.587s, 54.56/s (0.811s, 39.47/s) LR: 5.000e-03 Data: 0.000 (0.041) +2025-04-19 13:06:09,881 - train: [ INFO] - Train: 53 [ 150/461 ( 33%)] Loss: 0.698826 (0.7057) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.534s, 59.92/s (0.788s, 40.62/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-19 13:06:50,309 - train: [ INFO] - Train: 53 [ 200/461 ( 43%)] Loss: 0.740504 (0.7127) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.775s, 41.29/s (0.793s, 40.37/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 13:07:27,068 - train: [ INFO] - Train: 53 [ 250/461 ( 54%)] Loss: 0.693041 (0.7094) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.788s, 40.59/s (0.781s, 40.99/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 13:08:05,150 - train: [ INFO] - Train: 53 [ 300/461 ( 65%)] Loss: 0.698936 (0.7079) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.965s, 33.16/s (0.777s, 41.17/s) LR: 5.000e-03 Data: 0.002 (0.015) +2025-04-19 13:08:45,407 - train: [ INFO] - Train: 53 [ 350/461 ( 76%)] Loss: 0.738291 (0.7117) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.786s, 40.70/s (0.781s, 40.98/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 13:09:28,855 - train: [ INFO] - Train: 53 [ 400/461 ( 87%)] Loss: 0.724586 (0.7131) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.846s, 37.83/s (0.792s, 40.42/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 13:10:08,913 - train: [ INFO] - Train: 53 [ 450/461 ( 98%)] Loss: 0.698672 (0.7117) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.876s, 36.52/s (0.793s, 40.38/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 13:10:16,480 - train: [ INFO] - Train: 53 [ 460/461 (100%)] Loss: 0.695876 (0.7102) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.739s, 43.32/s (0.792s, 40.42/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 13:10:21,861 - train: [ INFO] - Eval : 53 Time: 5.034 (5.034) Loss: 2.1559 (2.1559) Acc@1: 37.5000 (37.5000)Acc@5: 71.8750 (71.8750) +2025-04-19 13:10:36,372 - train: [ INFO] - Eval : 53 Time: 0.311 (0.383) Loss: 1.8131 (1.9276) Acc@1: 59.3750 (50.0613)Acc@5: 68.7500 (76.1029) +2025-04-19 13:10:43,831 - train: [ INFO] - Eval : 53 Time: 0.063 (0.329) Loss: 3.3158 (1.9259) Acc@1: 0.0000 (50.3855)Acc@5: 50.0000 (76.4842) +2025-04-19 13:10:54,177 - train: [ INFO] - Train: 54 [ 0/461 ( 0%)] Loss: 0.715954 (0.7160) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.223s, 5.14/s (6.223s, 5.14/s) LR: 5.000e-03 Data: 5.353 (5.353) +2025-04-19 13:11:36,169 - train: [ INFO] - Train: 54 [ 50/461 ( 11%)] Loss: 0.727952 (0.7220) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.869s, 36.81/s (0.943s, 33.92/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-19 13:12:16,940 - train: [ INFO] - Train: 54 [ 100/461 ( 22%)] Loss: 0.723118 (0.7223) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.851s, 37.61/s (0.879s, 36.41/s) LR: 5.000e-03 Data: 0.000 (0.055) +2025-04-19 13:12:54,924 - train: [ INFO] - Train: 54 [ 150/461 ( 33%)] Loss: 0.713863 (0.7202) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.833s, 38.43/s (0.839s, 38.14/s) LR: 5.000e-03 Data: 0.000 (0.037) +2025-04-19 13:13:31,567 - train: [ INFO] - Train: 54 [ 200/461 ( 43%)] Loss: 0.722172 (0.7206) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.814s, 39.33/s (0.812s, 39.40/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-19 13:14:12,260 - train: [ INFO] - Train: 54 [ 250/461 ( 54%)] Loss: 0.729966 (0.7222) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.860s, 37.20/s (0.812s, 39.40/s) LR: 5.000e-03 Data: 0.005 (0.023) +2025-04-19 13:14:51,980 - train: [ INFO] - Train: 54 [ 300/461 ( 65%)] Loss: 0.700043 (0.7190) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.788s, 40.61/s (0.809s, 39.56/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 13:15:30,682 - train: [ INFO] - Train: 54 [ 350/461 ( 76%)] Loss: 0.722168 (0.7194) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.825s, 38.77/s (0.804s, 39.82/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 13:16:10,734 - train: [ INFO] - Train: 54 [ 400/461 ( 87%)] Loss: 0.712034 (0.7186) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.981s, 32.61/s (0.803s, 39.84/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 13:16:48,270 - train: [ INFO] - Train: 54 [ 450/461 ( 98%)] Loss: 0.705301 (0.7173) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.614s, 52.10/s (0.797s, 40.14/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 13:16:55,862 - train: [ INFO] - Train: 54 [ 460/461 (100%)] Loss: 0.712874 (0.7169) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.883s, 36.24/s (0.796s, 40.19/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 13:17:01,429 - train: [ INFO] - Eval : 54 Time: 5.219 (5.219) Loss: 2.0520 (2.0520) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-19 13:17:15,484 - train: [ INFO] - Eval : 54 Time: 0.284 (0.378) Loss: 1.7032 (1.9414) Acc@1: 59.3750 (49.2034)Acc@5: 78.1250 (76.4093) +2025-04-19 13:17:23,376 - train: [ INFO] - Eval : 54 Time: 0.082 (0.331) Loss: 3.0652 (1.9363) Acc@1: 0.0000 (49.3832)Acc@5: 50.0000 (75.9830) +2025-04-19 13:17:33,350 - train: [ INFO] - Train: 55 [ 0/461 ( 0%)] Loss: 0.717567 (0.7176) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.046s, 5.29/s (6.046s, 5.29/s) LR: 5.000e-03 Data: 5.032 (5.032) +2025-04-19 13:18:11,719 - train: [ INFO] - Train: 55 [ 50/461 ( 11%)] Loss: 0.701635 (0.7096) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.597s, 53.63/s (0.869s, 36.81/s) LR: 5.000e-03 Data: 0.000 (0.100) +2025-04-19 13:18:50,456 - train: [ INFO] - Train: 55 [ 100/461 ( 22%)] Loss: 0.783084 (0.7341) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.820s, 39.04/s (0.822s, 38.94/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-19 13:19:30,519 - train: [ INFO] - Train: 55 [ 150/461 ( 33%)] Loss: 0.755409 (0.7394) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.806s, 39.68/s (0.814s, 39.29/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-19 13:20:09,495 - train: [ INFO] - Train: 55 [ 200/461 ( 43%)] Loss: 0.753948 (0.7423) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.627s, 51.03/s (0.805s, 39.74/s) LR: 5.000e-03 Data: 0.004 (0.026) +2025-04-19 13:20:47,672 - train: [ INFO] - Train: 55 [ 250/461 ( 54%)] Loss: 0.695542 (0.7345) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.881s, 36.33/s (0.797s, 40.17/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 13:21:24,607 - train: [ INFO] - Train: 55 [ 300/461 ( 65%)] Loss: 0.695556 (0.7290) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.441s, 72.55/s (0.787s, 40.68/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 13:22:02,175 - train: [ INFO] - Train: 55 [ 350/461 ( 76%)] Loss: 0.745973 (0.7311) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.662s, 48.35/s (0.781s, 40.96/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 13:22:41,275 - train: [ INFO] - Train: 55 [ 400/461 ( 87%)] Loss: 0.697271 (0.7273) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.769s, 41.59/s (0.781s, 40.96/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 13:23:15,797 - train: [ INFO] - Train: 55 [ 450/461 ( 98%)] Loss: 0.700830 (0.7247) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.808s, 39.62/s (0.771s, 41.51/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:23:22,218 - train: [ INFO] - Train: 55 [ 460/461 (100%)] Loss: 0.699196 (0.7224) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.577s, 55.42/s (0.768s, 41.66/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:23:27,909 - train: [ INFO] - Eval : 55 Time: 5.309 (5.309) Loss: 1.9452 (1.9452) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-19 13:23:40,711 - train: [ INFO] - Eval : 55 Time: 0.233 (0.355) Loss: 1.7846 (1.9667) Acc@1: 53.1250 (49.3260)Acc@5: 78.1250 (75.5515) +2025-04-19 13:23:48,550 - train: [ INFO] - Eval : 55 Time: 0.062 (0.316) Loss: 3.5870 (1.9537) Acc@1: 0.0000 (49.6145)Acc@5: 50.0000 (75.7517) +2025-04-19 13:23:58,138 - train: [ INFO] - Train: 56 [ 0/461 ( 0%)] Loss: 0.714640 (0.7146) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.462s, 5.86/s (5.462s, 5.86/s) LR: 5.000e-03 Data: 4.548 (4.548) +2025-04-19 13:24:35,516 - train: [ INFO] - Train: 56 [ 50/461 ( 11%)] Loss: 0.699924 (0.7073) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.838s, 38.19/s (0.838s, 38.19/s) LR: 5.000e-03 Data: 0.000 (0.090) +2025-04-19 13:25:15,338 - train: [ INFO] - Train: 56 [ 100/461 ( 22%)] Loss: 0.691285 (0.7019) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.44/s (0.816s, 39.20/s) LR: 5.000e-03 Data: 0.001 (0.046) +2025-04-19 13:25:55,371 - train: [ INFO] - Train: 56 [ 150/461 ( 33%)] Loss: 0.784165 (0.7225) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.688s, 46.55/s (0.810s, 39.48/s) LR: 5.000e-03 Data: 0.001 (0.031) +2025-04-19 13:26:39,058 - train: [ INFO] - Train: 56 [ 200/461 ( 43%)] Loss: 0.693717 (0.7167) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.886s, 36.11/s (0.826s, 38.75/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 13:27:18,885 - train: [ INFO] - Train: 56 [ 250/461 ( 54%)] Loss: 0.688998 (0.7121) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.776s, 41.22/s (0.820s, 39.04/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 13:27:54,808 - train: [ INFO] - Train: 56 [ 300/461 ( 65%)] Loss: 0.716599 (0.7128) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.559s, 57.28/s (0.802s, 39.88/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 13:28:32,651 - train: [ INFO] - Train: 56 [ 350/461 ( 76%)] Loss: 0.704670 (0.7117) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.671s, 47.72/s (0.796s, 40.21/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 13:29:08,762 - train: [ INFO] - Train: 56 [ 400/461 ( 87%)] Loss: 0.723641 (0.7131) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.714s, 44.80/s (0.786s, 40.69/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 13:29:47,692 - train: [ INFO] - Train: 56 [ 450/461 ( 98%)] Loss: 0.754320 (0.7172) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.850s, 37.66/s (0.785s, 40.75/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 13:29:55,030 - train: [ INFO] - Train: 56 [ 460/461 (100%)] Loss: 0.692507 (0.7150) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.766s, 41.78/s (0.784s, 40.81/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 13:29:59,893 - train: [ INFO] - Eval : 56 Time: 4.530 (4.530) Loss: 1.9351 (1.9351) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-19 13:30:12,858 - train: [ INFO] - Eval : 56 Time: 0.304 (0.343) Loss: 1.8488 (1.9445) Acc@1: 62.5000 (51.2255)Acc@5: 71.8750 (76.5931) +2025-04-19 13:30:20,034 - train: [ INFO] - Eval : 56 Time: 0.065 (0.301) Loss: 3.9545 (1.9377) Acc@1: 0.0000 (51.4264)Acc@5: 0.0000 (76.5613) +2025-04-19 13:30:29,358 - train: [ INFO] - Train: 57 [ 0/461 ( 0%)] Loss: 0.711326 (0.7113) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.395s, 5.93/s (5.395s, 5.93/s) LR: 5.000e-03 Data: 4.651 (4.651) +2025-04-19 13:31:09,616 - train: [ INFO] - Train: 57 [ 50/461 ( 11%)] Loss: 0.706249 (0.7088) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.943s, 33.92/s (0.894s, 35.81/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-19 13:31:45,730 - train: [ INFO] - Train: 57 [ 100/461 ( 22%)] Loss: 0.778188 (0.7319) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.862s, 37.12/s (0.808s, 39.60/s) LR: 5.000e-03 Data: 0.003 (0.048) +2025-04-19 13:32:19,997 - train: [ INFO] - Train: 57 [ 150/461 ( 33%)] Loss: 0.693737 (0.7224) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.439s, 72.91/s (0.767s, 41.73/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-19 13:32:56,849 - train: [ INFO] - Train: 57 [ 200/461 ( 43%)] Loss: 0.688771 (0.7157) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.921s, 34.75/s (0.759s, 42.17/s) LR: 5.000e-03 Data: 0.005 (0.024) +2025-04-19 13:33:34,171 - train: [ INFO] - Train: 57 [ 250/461 ( 54%)] Loss: 0.684803 (0.7105) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.688s, 46.52/s (0.756s, 42.33/s) LR: 5.000e-03 Data: 0.002 (0.020) +2025-04-19 13:34:13,711 - train: [ INFO] - Train: 57 [ 300/461 ( 65%)] Loss: 0.695630 (0.7084) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.576s, 55.51/s (0.761s, 42.02/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 13:34:52,259 - train: [ INFO] - Train: 57 [ 350/461 ( 76%)] Loss: 0.722326 (0.7101) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.948s, 33.76/s (0.763s, 41.97/s) LR: 5.000e-03 Data: 0.003 (0.014) +2025-04-19 13:35:30,811 - train: [ INFO] - Train: 57 [ 400/461 ( 87%)] Loss: 0.721934 (0.7114) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.725s, 44.11/s (0.763s, 41.93/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 13:36:10,889 - train: [ INFO] - Train: 57 [ 450/461 ( 98%)] Loss: 0.700830 (0.7104) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.849s, 37.71/s (0.767s, 41.71/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 13:36:19,392 - train: [ INFO] - Train: 57 [ 460/461 (100%)] Loss: 0.692115 (0.7087) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.805s, 39.74/s (0.769s, 41.61/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 13:36:25,709 - train: [ INFO] - Eval : 57 Time: 5.950 (5.950) Loss: 2.0846 (2.0846) Acc@1: 43.7500 (43.7500)Acc@5: 68.7500 (68.7500) +2025-04-19 13:36:37,941 - train: [ INFO] - Eval : 57 Time: 0.236 (0.357) Loss: 1.8049 (1.9650) Acc@1: 53.1250 (48.7132)Acc@5: 71.8750 (74.6936) +2025-04-19 13:36:45,329 - train: [ INFO] - Eval : 57 Time: 0.057 (0.312) Loss: 4.1353 (1.9575) Acc@1: 0.0000 (49.3061)Acc@5: 0.0000 (74.9807) +2025-04-19 13:36:54,922 - train: [ INFO] - Train: 58 [ 0/461 ( 0%)] Loss: 0.685979 (0.6860) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.507s, 5.81/s (5.507s, 5.81/s) LR: 5.000e-03 Data: 4.662 (4.662) +2025-04-19 13:37:31,028 - train: [ INFO] - Train: 58 [ 50/461 ( 11%)] Loss: 0.686797 (0.6864) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.837s, 38.24/s (0.815s, 39.29/s) LR: 5.000e-03 Data: 0.002 (0.093) +2025-04-19 13:38:08,691 - train: [ INFO] - Train: 58 [ 100/461 ( 22%)] Loss: 0.703413 (0.6921) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.730s, 43.84/s (0.783s, 40.87/s) LR: 5.000e-03 Data: 0.001 (0.047) +2025-04-19 13:38:46,316 - train: [ INFO] - Train: 58 [ 150/461 ( 33%)] Loss: 0.702871 (0.6948) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.735s, 43.52/s (0.772s, 41.44/s) LR: 5.000e-03 Data: 0.012 (0.032) +2025-04-19 13:39:25,026 - train: [ INFO] - Train: 58 [ 200/461 ( 43%)] Loss: 0.692757 (0.6944) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.800s, 39.99/s (0.772s, 41.45/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 13:40:03,232 - train: [ INFO] - Train: 58 [ 250/461 ( 54%)] Loss: 0.701222 (0.6955) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.882s, 36.28/s (0.770s, 41.55/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 13:40:42,097 - train: [ INFO] - Train: 58 [ 300/461 ( 65%)] Loss: 0.706564 (0.6971) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.548s, 58.43/s (0.771s, 41.50/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 13:41:17,695 - train: [ INFO] - Train: 58 [ 350/461 ( 76%)] Loss: 0.698265 (0.6972) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.557s, 57.46/s (0.762s, 41.97/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 13:41:53,856 - train: [ INFO] - Train: 58 [ 400/461 ( 87%)] Loss: 0.710417 (0.6987) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.813s, 39.35/s (0.757s, 42.26/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 13:42:29,703 - train: [ INFO] - Train: 58 [ 450/461 ( 98%)] Loss: 0.699624 (0.6988) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.577s, 55.45/s (0.753s, 42.52/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:42:37,434 - train: [ INFO] - Train: 58 [ 460/461 (100%)] Loss: 0.730867 (0.7017) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.019s, 31.40/s (0.753s, 42.50/s) LR: 5.000e-03 Data: 0.002 (0.012) +2025-04-19 13:42:43,085 - train: [ INFO] - Eval : 58 Time: 5.314 (5.314) Loss: 2.0753 (2.0753) Acc@1: 43.7500 (43.7500)Acc@5: 68.7500 (68.7500) +2025-04-19 13:42:56,247 - train: [ INFO] - Eval : 58 Time: 0.260 (0.362) Loss: 1.7233 (1.9632) Acc@1: 50.0000 (49.1422)Acc@5: 75.0000 (75.7353) +2025-04-19 13:43:04,128 - train: [ INFO] - Eval : 58 Time: 0.062 (0.321) Loss: 3.5827 (1.9589) Acc@1: 0.0000 (49.0748)Acc@5: 0.0000 (76.1758) +2025-04-19 13:43:12,632 - train: [ INFO] - Train: 59 [ 0/461 ( 0%)] Loss: 0.754808 (0.7548) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 4.514s, 7.09/s (4.514s, 7.09/s) LR: 5.000e-03 Data: 3.728 (3.728) +2025-04-19 13:43:50,793 - train: [ INFO] - Train: 59 [ 50/461 ( 11%)] Loss: 0.695324 (0.7251) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.940s, 34.05/s (0.835s, 38.32/s) LR: 5.000e-03 Data: 0.000 (0.074) +2025-04-19 13:44:28,865 - train: [ INFO] - Train: 59 [ 100/461 ( 22%)] Loss: 0.704261 (0.7181) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.835s, 38.33/s (0.798s, 40.12/s) LR: 5.000e-03 Data: 0.010 (0.038) +2025-04-19 13:45:06,928 - train: [ INFO] - Train: 59 [ 150/461 ( 33%)] Loss: 0.707728 (0.7155) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.547s, 58.55/s (0.785s, 40.77/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 13:45:42,306 - train: [ INFO] - Train: 59 [ 200/461 ( 43%)] Loss: 0.728953 (0.7182) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.921s, 34.73/s (0.765s, 41.81/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 13:46:21,497 - train: [ INFO] - Train: 59 [ 250/461 ( 54%)] Loss: 0.696367 (0.7146) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.959s, 33.37/s (0.769s, 41.63/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 13:46:58,760 - train: [ INFO] - Train: 59 [ 300/461 ( 65%)] Loss: 0.704764 (0.7132) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.855s, 37.43/s (0.764s, 41.86/s) LR: 5.000e-03 Data: 0.007 (0.014) +2025-04-19 13:47:36,407 - train: [ INFO] - Train: 59 [ 350/461 ( 76%)] Loss: 0.691516 (0.7105) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.751s, 42.59/s (0.763s, 41.96/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:48:14,858 - train: [ INFO] - Train: 59 [ 400/461 ( 87%)] Loss: 0.706689 (0.7100) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.835s, 38.31/s (0.763s, 41.93/s) LR: 5.000e-03 Data: 0.001 (0.010) +2025-04-19 13:48:53,035 - train: [ INFO] - Train: 59 [ 450/461 ( 98%)] Loss: 0.710665 (0.7101) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.978s, 32.72/s (0.763s, 41.94/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 13:49:00,621 - train: [ INFO] - Train: 59 [ 460/461 (100%)] Loss: 0.712747 (0.7103) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.607s, 52.71/s (0.763s, 41.95/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 13:49:06,653 - train: [ INFO] - Eval : 59 Time: 5.697 (5.697) Loss: 1.9842 (1.9842) Acc@1: 50.0000 (50.0000)Acc@5: 71.8750 (71.8750) +2025-04-19 13:49:21,082 - train: [ INFO] - Eval : 59 Time: 0.331 (0.395) Loss: 1.9485 (1.9785) Acc@1: 50.0000 (48.9583)Acc@5: 75.0000 (75.1225) +2025-04-19 13:49:28,912 - train: [ INFO] - Eval : 59 Time: 0.079 (0.341) Loss: 3.5174 (1.9767) Acc@1: 0.0000 (48.4965)Acc@5: 50.0000 (75.4433) +2025-04-19 13:49:38,709 - train: [ INFO] - Train: 60 [ 0/461 ( 0%)] Loss: 0.686395 (0.6864) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.834s, 5.48/s (5.834s, 5.48/s) LR: 5.000e-03 Data: 5.047 (5.047) +2025-04-19 13:50:16,730 - train: [ INFO] - Train: 60 [ 50/461 ( 11%)] Loss: 0.702620 (0.6945) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.864s, 37.05/s (0.857s, 37.33/s) LR: 5.000e-03 Data: 0.006 (0.101) +2025-04-19 13:50:52,820 - train: [ INFO] - Train: 60 [ 100/461 ( 22%)] Loss: 0.729834 (0.7063) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.961s, 33.29/s (0.789s, 40.55/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-19 13:51:33,008 - train: [ INFO] - Train: 60 [ 150/461 ( 33%)] Loss: 0.696497 (0.7038) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.872s, 36.69/s (0.793s, 40.33/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-19 13:52:14,147 - train: [ INFO] - Train: 60 [ 200/461 ( 43%)] Loss: 0.703526 (0.7038) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.988s, 32.39/s (0.800s, 39.99/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 13:52:54,133 - train: [ INFO] - Train: 60 [ 250/461 ( 54%)] Loss: 0.705313 (0.7040) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.826s, 38.76/s (0.800s, 40.01/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 13:53:31,639 - train: [ INFO] - Train: 60 [ 300/461 ( 65%)] Loss: 0.693722 (0.7026) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.812s, 39.42/s (0.791s, 40.44/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 13:54:11,932 - train: [ INFO] - Train: 60 [ 350/461 ( 76%)] Loss: 0.691757 (0.7012) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.713s, 44.85/s (0.793s, 40.34/s) LR: 5.000e-03 Data: 0.004 (0.016) +2025-04-19 13:54:45,468 - train: [ INFO] - Train: 60 [ 400/461 ( 87%)] Loss: 0.693158 (0.7003) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.323s, 98.96/s (0.778s, 41.14/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 13:55:10,776 - train: [ INFO] - Train: 60 [ 450/461 ( 98%)] Loss: 0.702187 (0.7005) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.574s, 55.70/s (0.747s, 42.81/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:55:16,579 - train: [ INFO] - Train: 60 [ 460/461 (100%)] Loss: 0.732646 (0.7034) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.611s, 52.34/s (0.744s, 43.03/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 13:55:22,452 - train: [ INFO] - Eval : 60 Time: 5.528 (5.528) Loss: 2.1612 (2.1612) Acc@1: 40.6250 (40.6250)Acc@5: 71.8750 (71.8750) +2025-04-19 13:55:36,193 - train: [ INFO] - Eval : 60 Time: 0.338 (0.378) Loss: 1.6622 (1.9483) Acc@1: 59.3750 (50.1225)Acc@5: 75.0000 (74.8162) +2025-04-19 13:55:43,864 - train: [ INFO] - Eval : 60 Time: 0.072 (0.329) Loss: 3.6929 (1.9398) Acc@1: 0.0000 (50.2313)Acc@5: 0.0000 (75.8288) +2025-04-19 13:55:53,313 - train: [ INFO] - Train: 61 [ 0/461 ( 0%)] Loss: 0.694631 (0.6946) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.306s, 6.03/s (5.306s, 6.03/s) LR: 5.000e-03 Data: 4.271 (4.271) +2025-04-19 13:56:32,059 - train: [ INFO] - Train: 61 [ 50/461 ( 11%)] Loss: 0.688020 (0.6913) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.706s, 45.36/s (0.862s, 37.14/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-19 13:57:09,417 - train: [ INFO] - Train: 61 [ 100/461 ( 22%)] Loss: 0.685632 (0.6894) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.630s, 50.78/s (0.804s, 39.81/s) LR: 5.000e-03 Data: 0.000 (0.043) +2025-04-19 13:57:47,028 - train: [ INFO] - Train: 61 [ 150/461 ( 33%)] Loss: 0.694831 (0.6908) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.846s, 37.80/s (0.786s, 40.70/s) LR: 5.000e-03 Data: 0.002 (0.029) +2025-04-19 13:58:26,205 - train: [ INFO] - Train: 61 [ 200/461 ( 43%)] Loss: 0.700567 (0.6927) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.766s, 41.76/s (0.785s, 40.77/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 13:59:06,506 - train: [ INFO] - Train: 61 [ 250/461 ( 54%)] Loss: 0.758186 (0.7036) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.826s, 38.72/s (0.789s, 40.57/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 13:59:44,652 - train: [ INFO] - Train: 61 [ 300/461 ( 65%)] Loss: 0.718795 (0.7058) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.680s, 47.08/s (0.784s, 40.81/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 14:00:20,777 - train: [ INFO] - Train: 61 [ 350/461 ( 76%)] Loss: 0.739088 (0.7100) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.430s, 74.43/s (0.775s, 41.29/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:00:59,045 - train: [ INFO] - Train: 61 [ 400/461 ( 87%)] Loss: 0.761426 (0.7157) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.010s, 31.67/s (0.774s, 41.37/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 14:01:40,824 - train: [ INFO] - Train: 61 [ 450/461 ( 98%)] Loss: 0.730482 (0.7172) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.785s, 40.76/s (0.780s, 41.01/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:01:48,356 - train: [ INFO] - Train: 61 [ 460/461 (100%)] Loss: 0.706884 (0.7162) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.810s, 39.50/s (0.780s, 41.05/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 14:01:53,684 - train: [ INFO] - Eval : 61 Time: 4.959 (4.959) Loss: 2.0157 (2.0157) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-19 14:02:07,642 - train: [ INFO] - Eval : 61 Time: 0.250 (0.371) Loss: 1.8194 (1.9448) Acc@1: 59.3750 (50.4289)Acc@5: 75.0000 (75.4902) +2025-04-19 14:02:15,501 - train: [ INFO] - Eval : 61 Time: 0.061 (0.327) Loss: 3.0082 (1.9330) Acc@1: 0.0000 (50.6554)Acc@5: 50.0000 (76.2143) +2025-04-19 14:02:24,597 - train: [ INFO] - Train: 62 [ 0/461 ( 0%)] Loss: 0.688300 (0.6883) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.850s, 6.60/s (4.850s, 6.60/s) LR: 5.000e-03 Data: 4.019 (4.019) +2025-04-19 14:03:02,930 - train: [ INFO] - Train: 62 [ 50/461 ( 11%)] Loss: 0.705183 (0.6967) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.907s, 35.30/s (0.845s, 37.87/s) LR: 5.000e-03 Data: 0.000 (0.081) +2025-04-19 14:03:41,623 - train: [ INFO] - Train: 62 [ 100/461 ( 22%)] Loss: 0.695992 (0.6965) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.993s, 32.23/s (0.809s, 39.56/s) LR: 5.000e-03 Data: 0.000 (0.042) +2025-04-19 14:04:22,487 - train: [ INFO] - Train: 62 [ 150/461 ( 33%)] Loss: 0.687219 (0.6942) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.592s, 54.05/s (0.811s, 39.45/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-19 14:04:58,165 - train: [ INFO] - Train: 62 [ 200/461 ( 43%)] Loss: 0.700054 (0.6953) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.844s, 37.93/s (0.787s, 40.68/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 14:05:38,177 - train: [ INFO] - Train: 62 [ 250/461 ( 54%)] Loss: 0.707599 (0.6974) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.791s, 40.46/s (0.789s, 40.56/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 14:06:15,069 - train: [ INFO] - Train: 62 [ 300/461 ( 65%)] Loss: 0.685085 (0.6956) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.813s, 39.34/s (0.780s, 41.01/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 14:06:55,399 - train: [ INFO] - Train: 62 [ 350/461 ( 76%)] Loss: 0.697448 (0.6959) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.831s, 38.51/s (0.784s, 40.83/s) LR: 5.000e-03 Data: 0.005 (0.013) +2025-04-19 14:07:34,309 - train: [ INFO] - Train: 62 [ 400/461 ( 87%)] Loss: 0.715676 (0.6981) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.694s, 46.10/s (0.783s, 40.88/s) LR: 5.000e-03 Data: 0.007 (0.011) +2025-04-19 14:08:11,147 - train: [ INFO] - Train: 62 [ 450/461 ( 98%)] Loss: 0.700338 (0.6983) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.591s, 54.13/s (0.778s, 41.15/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 14:08:18,073 - train: [ INFO] - Train: 62 [ 460/461 (100%)] Loss: 0.743451 (0.7024) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.569s, 56.28/s (0.776s, 41.25/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 14:08:23,454 - train: [ INFO] - Eval : 62 Time: 5.021 (5.021) Loss: 2.0600 (2.0600) Acc@1: 40.6250 (40.6250)Acc@5: 75.0000 (75.0000) +2025-04-19 14:08:37,606 - train: [ INFO] - Eval : 62 Time: 0.297 (0.376) Loss: 1.7690 (1.9749) Acc@1: 62.5000 (49.8775)Acc@5: 78.1250 (74.0809) +2025-04-19 14:08:44,944 - train: [ INFO] - Eval : 62 Time: 0.067 (0.323) Loss: 3.5399 (1.9760) Acc@1: 0.0000 (49.6916)Acc@5: 0.0000 (74.0555) +2025-04-19 14:08:55,782 - train: [ INFO] - Train: 63 [ 0/461 ( 0%)] Loss: 0.770234 (0.7702) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 6.192s, 5.17/s (6.192s, 5.17/s) LR: 5.000e-03 Data: 5.228 (5.228) +2025-04-19 14:09:33,988 - train: [ INFO] - Train: 63 [ 50/461 ( 11%)] Loss: 0.701421 (0.7358) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.813s, 39.35/s (0.868s, 36.86/s) LR: 5.000e-03 Data: 0.003 (0.104) +2025-04-19 14:10:12,328 - train: [ INFO] - Train: 63 [ 100/461 ( 22%)] Loss: 0.719765 (0.7305) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.748s, 42.80/s (0.816s, 39.19/s) LR: 5.000e-03 Data: 0.003 (0.053) +2025-04-19 14:10:51,768 - train: [ INFO] - Train: 63 [ 150/461 ( 33%)] Loss: 0.720873 (0.7281) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.927s, 34.52/s (0.807s, 39.67/s) LR: 5.000e-03 Data: 0.001 (0.036) +2025-04-19 14:11:29,088 - train: [ INFO] - Train: 63 [ 200/461 ( 43%)] Loss: 0.699759 (0.7224) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.721s, 44.37/s (0.791s, 40.44/s) LR: 5.000e-03 Data: 0.007 (0.027) +2025-04-19 14:12:10,765 - train: [ INFO] - Train: 63 [ 250/461 ( 54%)] Loss: 0.695380 (0.7179) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 1.015s, 31.53/s (0.799s, 40.04/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 14:12:51,839 - train: [ INFO] - Train: 63 [ 300/461 ( 65%)] Loss: 0.697522 (0.7150) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.716s, 44.72/s (0.803s, 39.87/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 14:13:31,976 - train: [ INFO] - Train: 63 [ 350/461 ( 76%)] Loss: 0.689557 (0.7118) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.783s, 40.88/s (0.802s, 39.88/s) LR: 5.000e-03 Data: 0.007 (0.016) +2025-04-19 14:14:11,425 - train: [ INFO] - Train: 63 [ 400/461 ( 87%)] Loss: 0.709614 (0.7116) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.738s, 43.37/s (0.801s, 39.97/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 14:14:51,454 - train: [ INFO] - Train: 63 [ 450/461 ( 98%)] Loss: 0.716101 (0.7120) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.841s, 38.05/s (0.800s, 39.98/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:14:58,107 - train: [ INFO] - Train: 63 [ 460/461 (100%)] Loss: 0.696347 (0.7106) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.679s, 47.15/s (0.797s, 40.13/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:15:03,487 - train: [ INFO] - Eval : 63 Time: 5.060 (5.060) Loss: 2.0252 (2.0252) Acc@1: 40.6250 (40.6250)Acc@5: 75.0000 (75.0000) +2025-04-19 14:15:17,068 - train: [ INFO] - Eval : 63 Time: 0.282 (0.365) Loss: 1.8852 (1.9832) Acc@1: 50.0000 (48.9583)Acc@5: 75.0000 (74.6936) +2025-04-19 14:15:24,559 - train: [ INFO] - Eval : 63 Time: 0.082 (0.319) Loss: 3.4539 (1.9782) Acc@1: 0.0000 (49.3061)Acc@5: 0.0000 (75.0193) +2025-04-19 14:15:35,223 - train: [ INFO] - Train: 64 [ 0/461 ( 0%)] Loss: 0.778862 (0.7789) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 6.244s, 5.12/s (6.244s, 5.12/s) LR: 5.000e-03 Data: 5.598 (5.598) +2025-04-19 14:16:13,479 - train: [ INFO] - Train: 64 [ 50/461 ( 11%)] Loss: 0.699141 (0.7390) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.839s, 38.16/s (0.872s, 36.71/s) LR: 5.000e-03 Data: 0.000 (0.111) +2025-04-19 14:16:52,530 - train: [ INFO] - Train: 64 [ 100/461 ( 22%)] Loss: 0.683891 (0.7206) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.883s, 36.24/s (0.826s, 38.73/s) LR: 5.000e-03 Data: 0.000 (0.056) +2025-04-19 14:17:28,085 - train: [ INFO] - Train: 64 [ 150/461 ( 33%)] Loss: 0.682358 (0.7111) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.732s, 43.70/s (0.787s, 40.64/s) LR: 5.000e-03 Data: 0.000 (0.038) +2025-04-19 14:18:06,930 - train: [ INFO] - Train: 64 [ 200/461 ( 43%)] Loss: 0.695498 (0.7079) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.953s, 33.59/s (0.784s, 40.80/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 14:18:44,573 - train: [ INFO] - Train: 64 [ 250/461 ( 54%)] Loss: 0.699354 (0.7065) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.871s, 36.74/s (0.778s, 41.15/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 14:19:25,502 - train: [ INFO] - Train: 64 [ 300/461 ( 65%)] Loss: 0.688148 (0.7039) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.800s, 39.98/s (0.784s, 40.81/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 14:20:09,073 - train: [ INFO] - Train: 64 [ 350/461 ( 76%)] Loss: 0.697647 (0.7031) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 1.023s, 31.27/s (0.796s, 40.19/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 14:20:50,999 - train: [ INFO] - Train: 64 [ 400/461 ( 87%)] Loss: 0.692356 (0.7019) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.969s, 33.04/s (0.801s, 39.94/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 14:21:30,629 - train: [ INFO] - Train: 64 [ 450/461 ( 98%)] Loss: 0.704277 (0.7022) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.709s, 45.13/s (0.800s, 40.00/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:21:37,314 - train: [ INFO] - Train: 64 [ 460/461 (100%)] Loss: 0.722249 (0.7040) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.724s, 44.21/s (0.797s, 40.15/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:21:43,194 - train: [ INFO] - Eval : 64 Time: 5.513 (5.513) Loss: 2.0023 (2.0023) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-19 14:21:57,475 - train: [ INFO] - Eval : 64 Time: 0.303 (0.388) Loss: 1.8060 (1.9863) Acc@1: 53.1250 (48.8971)Acc@5: 75.0000 (74.6936) +2025-04-19 14:22:05,744 - train: [ INFO] - Eval : 64 Time: 0.076 (0.342) Loss: 3.8560 (1.9892) Acc@1: 0.0000 (48.6122)Acc@5: 0.0000 (74.7109) +2025-04-19 14:22:15,563 - train: [ INFO] - Train: 65 [ 0/461 ( 0%)] Loss: 0.701755 (0.7018) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.449s, 5.87/s (5.449s, 5.87/s) LR: 5.000e-03 Data: 4.475 (4.475) +2025-04-19 14:22:52,881 - train: [ INFO] - Train: 65 [ 50/461 ( 11%)] Loss: 0.709101 (0.7054) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.968s, 33.05/s (0.837s, 38.22/s) LR: 5.000e-03 Data: 0.000 (0.089) +2025-04-19 14:23:31,412 - train: [ INFO] - Train: 65 [ 100/461 ( 22%)] Loss: 0.745004 (0.7186) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.697s, 45.91/s (0.803s, 39.83/s) LR: 5.000e-03 Data: 0.005 (0.045) +2025-04-19 14:24:11,567 - train: [ INFO] - Train: 65 [ 150/461 ( 33%)] Loss: 0.806715 (0.7406) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (99.2188) Time: 0.879s, 36.41/s (0.803s, 39.86/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 14:24:49,640 - train: [ INFO] - Train: 65 [ 200/461 ( 43%)] Loss: 0.695146 (0.7315) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.873s, 36.64/s (0.792s, 40.41/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 14:25:30,988 - train: [ INFO] - Train: 65 [ 250/461 ( 54%)] Loss: 0.692669 (0.7251) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.930s, 34.42/s (0.798s, 40.08/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 14:26:07,558 - train: [ INFO] - Train: 65 [ 300/461 ( 65%)] Loss: 0.696702 (0.7210) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.813s, 39.36/s (0.787s, 40.66/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 14:26:46,504 - train: [ INFO] - Train: 65 [ 350/461 ( 76%)] Loss: 0.696367 (0.7179) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.757s, 42.28/s (0.786s, 40.73/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 14:27:24,941 - train: [ INFO] - Train: 65 [ 400/461 ( 87%)] Loss: 0.695973 (0.7155) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.625s, 51.21/s (0.783s, 40.86/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 14:28:03,668 - train: [ INFO] - Train: 65 [ 450/461 ( 98%)] Loss: 0.687860 (0.7127) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.627s, 51.05/s (0.782s, 40.92/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 14:28:11,934 - train: [ INFO] - Train: 65 [ 460/461 (100%)] Loss: 0.718412 (0.7132) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.819s, 39.07/s (0.783s, 40.88/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:28:18,660 - train: [ INFO] - Eval : 65 Time: 6.381 (6.381) Loss: 2.1349 (2.1349) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 14:28:31,941 - train: [ INFO] - Eval : 65 Time: 0.246 (0.386) Loss: 1.7698 (2.0373) Acc@1: 56.2500 (47.4265)Acc@5: 75.0000 (73.6520) +2025-04-19 14:28:39,414 - train: [ INFO] - Eval : 65 Time: 0.074 (0.331) Loss: 3.1514 (2.0309) Acc@1: 0.0000 (47.3015)Acc@5: 0.0000 (73.6700) +2025-04-19 14:28:48,988 - train: [ INFO] - Train: 66 [ 0/461 ( 0%)] Loss: 0.705134 (0.7051) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.738s, 5.58/s (5.738s, 5.58/s) LR: 5.000e-03 Data: 4.995 (4.995) +2025-04-19 14:29:27,687 - train: [ INFO] - Train: 66 [ 50/461 ( 11%)] Loss: 0.709006 (0.7071) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.793s, 40.35/s (0.869s, 36.81/s) LR: 5.000e-03 Data: 0.001 (0.099) +2025-04-19 14:30:05,368 - train: [ INFO] - Train: 66 [ 100/461 ( 22%)] Loss: 0.688920 (0.7010) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.644s, 49.68/s (0.811s, 39.47/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-19 14:30:43,016 - train: [ INFO] - Train: 66 [ 150/461 ( 33%)] Loss: 0.685011 (0.6970) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.470s, 68.06/s (0.791s, 40.45/s) LR: 5.000e-03 Data: 0.001 (0.034) +2025-04-19 14:31:18,068 - train: [ INFO] - Train: 66 [ 200/461 ( 43%)] Loss: 0.696755 (0.6970) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.816s, 39.20/s (0.768s, 41.65/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 14:31:57,192 - train: [ INFO] - Train: 66 [ 250/461 ( 54%)] Loss: 0.713496 (0.6997) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.888s, 36.05/s (0.771s, 41.52/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 14:32:35,843 - train: [ INFO] - Train: 66 [ 300/461 ( 65%)] Loss: 0.711286 (0.7014) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.705s, 45.39/s (0.771s, 41.52/s) LR: 5.000e-03 Data: 0.002 (0.018) +2025-04-19 14:33:13,355 - train: [ INFO] - Train: 66 [ 350/461 ( 76%)] Loss: 0.725086 (0.7043) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.539s, 59.40/s (0.768s, 41.69/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 14:33:49,473 - train: [ INFO] - Train: 66 [ 400/461 ( 87%)] Loss: 0.691368 (0.7029) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.658s, 48.67/s (0.762s, 42.01/s) LR: 5.000e-03 Data: 0.007 (0.014) +2025-04-19 14:34:24,773 - train: [ INFO] - Train: 66 [ 450/461 ( 98%)] Loss: 0.744686 (0.7071) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.713s, 44.86/s (0.755s, 42.37/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 14:34:32,660 - train: [ INFO] - Train: 66 [ 460/461 (100%)] Loss: 0.695662 (0.7060) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.803s, 39.87/s (0.756s, 42.33/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 14:34:37,420 - train: [ INFO] - Eval : 66 Time: 4.423 (4.423) Loss: 2.1405 (2.1405) Acc@1: 37.5000 (37.5000)Acc@5: 71.8750 (71.8750) +2025-04-19 14:34:51,476 - train: [ INFO] - Eval : 66 Time: 0.313 (0.362) Loss: 1.7952 (1.9928) Acc@1: 56.2500 (48.0392)Acc@5: 71.8750 (74.6936) +2025-04-19 14:34:59,313 - train: [ INFO] - Eval : 66 Time: 0.054 (0.321) Loss: 3.5705 (1.9825) Acc@1: 0.0000 (48.1496)Acc@5: 0.0000 (75.5975) +2025-04-19 14:35:08,788 - train: [ INFO] - Train: 67 [ 0/461 ( 0%)] Loss: 0.700738 (0.7007) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.647s, 5.67/s (5.647s, 5.67/s) LR: 5.000e-03 Data: 4.744 (4.744) +2025-04-19 14:35:49,717 - train: [ INFO] - Train: 67 [ 50/461 ( 11%)] Loss: 0.699377 (0.7001) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.983s, 32.54/s (0.911s, 35.13/s) LR: 5.000e-03 Data: 0.001 (0.094) +2025-04-19 14:36:30,309 - train: [ INFO] - Train: 67 [ 100/461 ( 22%)] Loss: 0.697487 (0.6992) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.602s, 53.14/s (0.861s, 37.17/s) LR: 5.000e-03 Data: 0.001 (0.048) +2025-04-19 14:37:08,334 - train: [ INFO] - Train: 67 [ 150/461 ( 33%)] Loss: 0.700688 (0.6996) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.939s, 34.07/s (0.826s, 38.72/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-19 14:37:49,752 - train: [ INFO] - Train: 67 [ 200/461 ( 43%)] Loss: 0.710386 (0.7017) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.763s, 41.93/s (0.827s, 38.72/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 14:38:31,222 - train: [ INFO] - Train: 67 [ 250/461 ( 54%)] Loss: 0.709088 (0.7030) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.908s, 35.24/s (0.827s, 38.71/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 14:39:12,094 - train: [ INFO] - Train: 67 [ 300/461 ( 65%)] Loss: 0.752612 (0.7101) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.806s, 39.72/s (0.825s, 38.80/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 14:39:52,174 - train: [ INFO] - Train: 67 [ 350/461 ( 76%)] Loss: 0.698176 (0.7086) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.863s, 37.10/s (0.821s, 38.97/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 14:40:31,686 - train: [ INFO] - Train: 67 [ 400/461 ( 87%)] Loss: 0.791025 (0.7177) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.567s, 56.39/s (0.817s, 39.16/s) LR: 5.000e-03 Data: 0.002 (0.013) +2025-04-19 14:41:09,981 - train: [ INFO] - Train: 67 [ 450/461 ( 98%)] Loss: 0.692739 (0.7152) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.708s, 45.18/s (0.811s, 39.45/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 14:41:17,617 - train: [ INFO] - Train: 67 [ 460/461 (100%)] Loss: 0.719964 (0.7157) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.863s, 37.08/s (0.810s, 39.50/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:41:22,569 - train: [ INFO] - Eval : 67 Time: 4.620 (4.620) Loss: 2.0294 (2.0294) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-19 14:41:36,295 - train: [ INFO] - Eval : 67 Time: 0.250 (0.360) Loss: 1.7903 (1.9718) Acc@1: 56.2500 (48.8971)Acc@5: 78.1250 (74.5711) +2025-04-19 14:41:43,831 - train: [ INFO] - Eval : 67 Time: 0.058 (0.316) Loss: 3.7512 (1.9637) Acc@1: 0.0000 (49.0748)Acc@5: 0.0000 (74.9807) +2025-04-19 14:41:53,158 - train: [ INFO] - Train: 68 [ 0/461 ( 0%)] Loss: 0.687011 (0.6870) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.168s, 6.19/s (5.168s, 6.19/s) LR: 5.000e-03 Data: 4.483 (4.483) +2025-04-19 14:42:33,847 - train: [ INFO] - Train: 68 [ 50/461 ( 11%)] Loss: 0.693373 (0.6902) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.906s, 35.32/s (0.897s, 35.69/s) LR: 5.000e-03 Data: 0.001 (0.091) +2025-04-19 14:43:12,359 - train: [ INFO] - Train: 68 [ 100/461 ( 22%)] Loss: 0.693920 (0.6914) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.611s, 52.37/s (0.833s, 38.41/s) LR: 5.000e-03 Data: 0.002 (0.046) +2025-04-19 14:43:53,234 - train: [ INFO] - Train: 68 [ 150/461 ( 33%)] Loss: 0.697148 (0.6929) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.894s, 35.77/s (0.827s, 38.68/s) LR: 5.000e-03 Data: 0.004 (0.031) +2025-04-19 14:44:29,986 - train: [ INFO] - Train: 68 [ 200/461 ( 43%)] Loss: 0.729859 (0.7003) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.758s, 42.20/s (0.804s, 39.81/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 14:45:04,069 - train: [ INFO] - Train: 68 [ 250/461 ( 54%)] Loss: 0.684981 (0.6977) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.597s, 53.60/s (0.779s, 41.06/s) LR: 5.000e-03 Data: 0.003 (0.020) +2025-04-19 14:45:43,943 - train: [ INFO] - Train: 68 [ 300/461 ( 65%)] Loss: 0.700687 (0.6981) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.800s, 40.02/s (0.782s, 40.92/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 14:46:21,011 - train: [ INFO] - Train: 68 [ 350/461 ( 76%)] Loss: 0.725225 (0.7015) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.958s, 33.39/s (0.776s, 41.23/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 14:46:57,471 - train: [ INFO] - Train: 68 [ 400/461 ( 87%)] Loss: 0.705496 (0.7020) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.742s, 43.14/s (0.770s, 41.56/s) LR: 5.000e-03 Data: 0.007 (0.013) +2025-04-19 14:47:34,316 - train: [ INFO] - Train: 68 [ 450/461 ( 98%)] Loss: 0.693209 (0.7011) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.788s, 40.59/s (0.766s, 41.77/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 14:47:41,428 - train: [ INFO] - Train: 68 [ 460/461 (100%)] Loss: 0.687399 (0.6998) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.600s, 53.37/s (0.765s, 41.84/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:47:46,970 - train: [ INFO] - Eval : 68 Time: 5.231 (5.231) Loss: 2.0021 (2.0021) Acc@1: 56.2500 (56.2500)Acc@5: 75.0000 (75.0000) +2025-04-19 14:48:00,280 - train: [ INFO] - Eval : 68 Time: 0.295 (0.364) Loss: 1.6597 (1.9487) Acc@1: 59.3750 (49.2034)Acc@5: 84.3750 (75.6127) +2025-04-19 14:48:08,515 - train: [ INFO] - Eval : 68 Time: 0.063 (0.327) Loss: 4.2943 (1.9447) Acc@1: 0.0000 (49.6530)Acc@5: 0.0000 (75.9445) +2025-04-19 14:48:17,671 - train: [ INFO] - Train: 69 [ 0/461 ( 0%)] Loss: 0.685379 (0.6854) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.124s, 6.25/s (5.124s, 6.25/s) LR: 5.000e-03 Data: 4.184 (4.184) +2025-04-19 14:48:59,726 - train: [ INFO] - Train: 69 [ 50/461 ( 11%)] Loss: 0.700362 (0.6929) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.962s, 33.25/s (0.922s, 34.72/s) LR: 5.000e-03 Data: 0.001 (0.083) +2025-04-19 14:49:35,593 - train: [ INFO] - Train: 69 [ 100/461 ( 22%)] Loss: 0.713859 (0.6999) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.988s, 32.40/s (0.820s, 39.04/s) LR: 5.000e-03 Data: 0.000 (0.043) +2025-04-19 14:50:15,164 - train: [ INFO] - Train: 69 [ 150/461 ( 33%)] Loss: 0.692128 (0.6979) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.737s, 43.42/s (0.810s, 39.51/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 14:50:54,976 - train: [ INFO] - Train: 69 [ 200/461 ( 43%)] Loss: 0.686581 (0.6957) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.809s, 39.54/s (0.806s, 39.70/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-19 14:51:33,345 - train: [ INFO] - Train: 69 [ 250/461 ( 54%)] Loss: 0.713337 (0.6986) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.980s, 32.64/s (0.798s, 40.10/s) LR: 5.000e-03 Data: 0.003 (0.018) +2025-04-19 14:52:11,436 - train: [ INFO] - Train: 69 [ 300/461 ( 65%)] Loss: 0.706185 (0.6997) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.943s, 33.95/s (0.792s, 40.42/s) LR: 5.000e-03 Data: 0.002 (0.015) +2025-04-19 14:52:48,465 - train: [ INFO] - Train: 69 [ 350/461 ( 76%)] Loss: 0.703399 (0.7002) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.397s, 80.65/s (0.784s, 40.81/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:53:27,646 - train: [ INFO] - Train: 69 [ 400/461 ( 87%)] Loss: 0.694569 (0.6995) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.778s, 41.13/s (0.784s, 40.82/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 14:54:07,619 - train: [ INFO] - Train: 69 [ 450/461 ( 98%)] Loss: 0.726255 (0.7022) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.749s, 42.70/s (0.785s, 40.74/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:54:15,261 - train: [ INFO] - Train: 69 [ 460/461 (100%)] Loss: 0.709325 (0.7029) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.854s, 37.48/s (0.785s, 40.77/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 14:54:21,084 - train: [ INFO] - Eval : 69 Time: 5.472 (5.472) Loss: 2.0760 (2.0760) Acc@1: 43.7500 (43.7500)Acc@5: 65.6250 (65.6250) +2025-04-19 14:54:35,245 - train: [ INFO] - Eval : 69 Time: 0.289 (0.385) Loss: 1.9064 (2.0057) Acc@1: 46.8750 (47.5490)Acc@5: 84.3750 (74.2647) +2025-04-19 14:54:42,007 - train: [ INFO] - Eval : 69 Time: 0.080 (0.322) Loss: 3.8592 (2.0081) Acc@1: 0.0000 (48.1496)Acc@5: 0.0000 (73.5929) +2025-04-19 14:54:52,592 - train: [ INFO] - Train: 70 [ 0/461 ( 0%)] Loss: 0.717635 (0.7176) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.347s, 5.04/s (6.347s, 5.04/s) LR: 5.000e-04 Data: 5.471 (5.471) +2025-04-19 14:55:34,524 - train: [ INFO] - Train: 70 [ 50/461 ( 11%)] Loss: 0.686666 (0.7022) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.680s, 47.04/s (0.945s, 33.86/s) LR: 5.000e-04 Data: 0.001 (0.109) +2025-04-19 14:56:13,842 - train: [ INFO] - Train: 70 [ 100/461 ( 22%)] Loss: 0.714195 (0.7062) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.621s, 51.51/s (0.866s, 36.95/s) LR: 5.000e-04 Data: 0.000 (0.055) +2025-04-19 14:56:50,698 - train: [ INFO] - Train: 70 [ 150/461 ( 33%)] Loss: 0.684802 (0.7008) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.773s, 41.37/s (0.823s, 38.88/s) LR: 5.000e-04 Data: 0.000 (0.037) +2025-04-19 14:57:27,557 - train: [ INFO] - Train: 70 [ 200/461 ( 43%)] Loss: 0.688374 (0.6983) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.877s, 36.48/s (0.801s, 39.95/s) LR: 5.000e-04 Data: 0.001 (0.028) +2025-04-19 14:58:08,547 - train: [ INFO] - Train: 70 [ 250/461 ( 54%)] Loss: 0.696234 (0.6980) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.846s, 37.83/s (0.804s, 39.78/s) LR: 5.000e-04 Data: 0.002 (0.023) +2025-04-19 14:58:46,927 - train: [ INFO] - Train: 70 [ 300/461 ( 65%)] Loss: 0.688618 (0.6966) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.606s, 52.82/s (0.798s, 40.10/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 14:59:21,520 - train: [ INFO] - Train: 70 [ 350/461 ( 76%)] Loss: 0.680922 (0.6947) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.833s, 38.42/s (0.782s, 40.90/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 15:00:00,622 - train: [ INFO] - Train: 70 [ 400/461 ( 87%)] Loss: 0.689031 (0.6941) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.809s, 39.56/s (0.782s, 40.92/s) LR: 5.000e-04 Data: 0.004 (0.015) +2025-04-19 15:00:39,952 - train: [ INFO] - Train: 70 [ 450/461 ( 98%)] Loss: 0.693821 (0.6940) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.640s, 50.00/s (0.782s, 40.90/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:00:46,608 - train: [ INFO] - Train: 70 [ 460/461 (100%)] Loss: 0.701890 (0.6947) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.703s, 45.52/s (0.780s, 41.04/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:00:51,973 - train: [ INFO] - Eval : 70 Time: 5.069 (5.069) Loss: 2.0965 (2.0965) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 15:01:05,157 - train: [ INFO] - Eval : 70 Time: 0.201 (0.358) Loss: 1.7174 (1.9582) Acc@1: 56.2500 (49.3260)Acc@5: 81.2500 (75.7966) +2025-04-19 15:01:12,940 - train: [ INFO] - Eval : 70 Time: 0.079 (0.318) Loss: 3.6040 (1.9577) Acc@1: 0.0000 (50.1542)Acc@5: 0.0000 (75.5590) +2025-04-19 15:01:21,790 - train: [ INFO] - Train: 71 [ 0/461 ( 0%)] Loss: 0.684568 (0.6846) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.091s, 6.29/s (5.091s, 6.29/s) LR: 5.000e-04 Data: 4.231 (4.231) +2025-04-19 15:02:02,296 - train: [ INFO] - Train: 71 [ 50/461 ( 11%)] Loss: 0.702331 (0.6934) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.808s, 39.60/s (0.893s, 35.85/s) LR: 5.000e-04 Data: 0.001 (0.084) +2025-04-19 15:02:39,238 - train: [ INFO] - Train: 71 [ 100/461 ( 22%)] Loss: 0.683888 (0.6903) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.784s, 40.81/s (0.815s, 39.24/s) LR: 5.000e-04 Data: 0.000 (0.043) +2025-04-19 15:03:17,572 - train: [ INFO] - Train: 71 [ 150/461 ( 33%)] Loss: 0.689392 (0.6900) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.883s, 36.25/s (0.799s, 40.06/s) LR: 5.000e-04 Data: 0.001 (0.030) +2025-04-19 15:03:56,582 - train: [ INFO] - Train: 71 [ 200/461 ( 43%)] Loss: 0.672825 (0.6866) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.907s, 35.26/s (0.794s, 40.31/s) LR: 5.000e-04 Data: 0.001 (0.023) +2025-04-19 15:04:35,097 - train: [ INFO] - Train: 71 [ 250/461 ( 54%)] Loss: 0.712174 (0.6909) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.978s, 32.72/s (0.789s, 40.56/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-19 15:05:13,313 - train: [ INFO] - Train: 71 [ 300/461 ( 65%)] Loss: 0.683442 (0.6898) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.724s, 44.19/s (0.784s, 40.80/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 15:05:48,524 - train: [ INFO] - Train: 71 [ 350/461 ( 76%)] Loss: 0.675377 (0.6880) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.860s, 37.20/s (0.773s, 41.41/s) LR: 5.000e-04 Data: 0.013 (0.014) +2025-04-19 15:06:29,687 - train: [ INFO] - Train: 71 [ 400/461 ( 87%)] Loss: 0.734316 (0.6931) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.753s, 42.52/s (0.779s, 41.09/s) LR: 5.000e-04 Data: 0.001 (0.012) +2025-04-19 15:07:07,185 - train: [ INFO] - Train: 71 [ 450/461 ( 98%)] Loss: 0.673474 (0.6912) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.592s, 54.02/s (0.775s, 41.26/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:07:14,033 - train: [ INFO] - Train: 71 [ 460/461 (100%)] Loss: 0.676304 (0.6898) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.652s, 49.10/s (0.773s, 41.37/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:07:19,863 - train: [ INFO] - Eval : 71 Time: 5.514 (5.514) Loss: 2.0843 (2.0843) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-19 15:07:34,640 - train: [ INFO] - Eval : 71 Time: 0.278 (0.398) Loss: 1.7965 (1.9409) Acc@1: 56.2500 (50.6740)Acc@5: 78.1250 (77.0221) +2025-04-19 15:07:42,296 - train: [ INFO] - Eval : 71 Time: 0.069 (0.341) Loss: 3.3900 (1.9384) Acc@1: 0.0000 (51.0023)Acc@5: 50.0000 (77.2552) +2025-04-19 15:07:52,137 - train: [ INFO] - Train: 72 [ 0/461 ( 0%)] Loss: 0.685874 (0.6859) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.227s, 6.12/s (5.227s, 6.12/s) LR: 5.000e-04 Data: 4.495 (4.495) +2025-04-19 15:08:29,152 - train: [ INFO] - Train: 72 [ 50/461 ( 11%)] Loss: 0.678091 (0.6820) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.728s, 43.96/s (0.826s, 38.76/s) LR: 5.000e-04 Data: 0.000 (0.089) +2025-04-19 15:09:09,917 - train: [ INFO] - Train: 72 [ 100/461 ( 22%)] Loss: 0.680703 (0.6816) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.945s, 33.88/s (0.819s, 39.05/s) LR: 5.000e-04 Data: 0.000 (0.046) +2025-04-19 15:09:48,410 - train: [ INFO] - Train: 72 [ 150/461 ( 33%)] Loss: 0.718872 (0.6909) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.716s, 44.69/s (0.803s, 39.88/s) LR: 5.000e-04 Data: 0.000 (0.031) +2025-04-19 15:10:28,972 - train: [ INFO] - Train: 72 [ 200/461 ( 43%)] Loss: 0.705879 (0.6939) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.480s, 66.61/s (0.804s, 39.78/s) LR: 5.000e-04 Data: 0.000 (0.024) +2025-04-19 15:11:08,340 - train: [ INFO] - Train: 72 [ 250/461 ( 54%)] Loss: 0.706500 (0.6960) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.841s, 38.07/s (0.801s, 39.97/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-19 15:11:48,323 - train: [ INFO] - Train: 72 [ 300/461 ( 65%)] Loss: 0.669780 (0.6922) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.808s, 39.61/s (0.800s, 40.00/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 15:12:26,761 - train: [ INFO] - Train: 72 [ 350/461 ( 76%)] Loss: 0.672114 (0.6897) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.913s, 35.05/s (0.795s, 40.24/s) LR: 5.000e-04 Data: 0.005 (0.014) +2025-04-19 15:13:04,344 - train: [ INFO] - Train: 72 [ 400/461 ( 87%)] Loss: 0.687487 (0.6895) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.809s, 39.55/s (0.790s, 40.53/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 15:13:41,028 - train: [ INFO] - Train: 72 [ 450/461 ( 98%)] Loss: 0.677586 (0.6883) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.656s, 48.77/s (0.783s, 40.86/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:13:48,819 - train: [ INFO] - Train: 72 [ 460/461 (100%)] Loss: 0.673135 (0.6869) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.713s, 44.90/s (0.783s, 40.86/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:13:53,477 - train: [ INFO] - Eval : 72 Time: 4.318 (4.318) Loss: 2.1358 (2.1358) Acc@1: 46.8750 (46.8750)Acc@5: 65.6250 (65.6250) +2025-04-19 15:14:07,451 - train: [ INFO] - Eval : 72 Time: 0.328 (0.359) Loss: 1.8180 (1.9538) Acc@1: 50.0000 (51.1029)Acc@5: 78.1250 (76.0417) +2025-04-19 15:14:15,722 - train: [ INFO] - Eval : 72 Time: 0.082 (0.324) Loss: 3.2787 (1.9485) Acc@1: 0.0000 (51.1951)Acc@5: 50.0000 (76.2529) +2025-04-19 15:14:25,517 - train: [ INFO] - Train: 73 [ 0/461 ( 0%)] Loss: 0.683210 (0.6832) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.523s, 5.79/s (5.523s, 5.79/s) LR: 5.000e-04 Data: 4.707 (4.707) +2025-04-19 15:15:07,058 - train: [ INFO] - Train: 73 [ 50/461 ( 11%)] Loss: 0.674389 (0.6788) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.749s, 42.72/s (0.921s, 34.75/s) LR: 5.000e-04 Data: 0.000 (0.093) +2025-04-19 15:15:48,807 - train: [ INFO] - Train: 73 [ 100/461 ( 22%)] Loss: 0.671712 (0.6764) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.701s, 45.65/s (0.878s, 36.46/s) LR: 5.000e-04 Data: 0.000 (0.048) +2025-04-19 15:16:27,714 - train: [ INFO] - Train: 73 [ 150/461 ( 33%)] Loss: 0.673086 (0.6756) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.597s, 53.57/s (0.844s, 37.91/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-19 15:17:05,240 - train: [ INFO] - Train: 73 [ 200/461 ( 43%)] Loss: 0.771923 (0.6949) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.603s, 53.07/s (0.820s, 39.01/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-19 15:17:41,348 - train: [ INFO] - Train: 73 [ 250/461 ( 54%)] Loss: 0.695553 (0.6950) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.731s, 43.79/s (0.800s, 39.98/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 15:18:15,981 - train: [ INFO] - Train: 73 [ 300/461 ( 65%)] Loss: 0.672819 (0.6918) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.458s, 69.83/s (0.782s, 40.90/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 15:18:52,975 - train: [ INFO] - Train: 73 [ 350/461 ( 76%)] Loss: 0.670323 (0.6891) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 1.011s, 31.65/s (0.776s, 41.24/s) LR: 5.000e-04 Data: 0.005 (0.015) +2025-04-19 15:19:32,115 - train: [ INFO] - Train: 73 [ 400/461 ( 87%)] Loss: 0.671371 (0.6872) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.764s, 41.89/s (0.777s, 41.20/s) LR: 5.000e-04 Data: 0.004 (0.013) +2025-04-19 15:20:11,205 - train: [ INFO] - Train: 73 [ 450/461 ( 98%)] Loss: 0.722668 (0.6907) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.919s, 34.83/s (0.777s, 41.19/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 15:20:18,744 - train: [ INFO] - Train: 73 [ 460/461 (100%)] Loss: 0.702383 (0.6918) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.831s, 38.49/s (0.776s, 41.21/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 15:20:24,305 - train: [ INFO] - Eval : 73 Time: 5.197 (5.197) Loss: 2.0840 (2.0840) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-19 15:20:37,670 - train: [ INFO] - Eval : 73 Time: 0.269 (0.364) Loss: 1.7916 (1.9731) Acc@1: 56.2500 (50.6127)Acc@5: 75.0000 (76.2255) +2025-04-19 15:20:44,867 - train: [ INFO] - Eval : 73 Time: 0.060 (0.314) Loss: 3.3223 (1.9716) Acc@1: 0.0000 (50.8867)Acc@5: 50.0000 (76.0216) +2025-04-19 15:20:54,951 - train: [ INFO] - Train: 74 [ 0/461 ( 0%)] Loss: 0.670834 (0.6708) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.137s, 5.21/s (6.137s, 5.21/s) LR: 5.000e-04 Data: 5.206 (5.206) +2025-04-19 15:21:34,661 - train: [ INFO] - Train: 74 [ 50/461 ( 11%)] Loss: 0.680603 (0.6757) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.770s, 41.55/s (0.897s, 35.65/s) LR: 5.000e-04 Data: 0.000 (0.104) +2025-04-19 15:22:14,900 - train: [ INFO] - Train: 74 [ 100/461 ( 22%)] Loss: 0.673810 (0.6751) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.637s, 50.20/s (0.850s, 37.63/s) LR: 5.000e-04 Data: 0.000 (0.053) +2025-04-19 15:22:54,668 - train: [ INFO] - Train: 74 [ 150/461 ( 33%)] Loss: 0.679654 (0.6762) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.790s, 40.49/s (0.832s, 38.47/s) LR: 5.000e-04 Data: 0.003 (0.036) +2025-04-19 15:23:34,514 - train: [ INFO] - Train: 74 [ 200/461 ( 43%)] Loss: 0.667750 (0.6745) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.816s, 39.19/s (0.823s, 38.91/s) LR: 5.000e-04 Data: 0.001 (0.027) +2025-04-19 15:24:10,648 - train: [ INFO] - Train: 74 [ 250/461 ( 54%)] Loss: 0.675591 (0.6747) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.612s, 52.33/s (0.802s, 39.89/s) LR: 5.000e-04 Data: 0.000 (0.022) +2025-04-19 15:24:49,137 - train: [ INFO] - Train: 74 [ 300/461 ( 65%)] Loss: 0.666422 (0.6735) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.860s, 37.19/s (0.796s, 40.18/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-19 15:25:27,712 - train: [ INFO] - Train: 74 [ 350/461 ( 76%)] Loss: 0.671377 (0.6733) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.782s, 40.93/s (0.793s, 40.38/s) LR: 5.000e-04 Data: 0.007 (0.016) +2025-04-19 15:26:06,935 - train: [ INFO] - Train: 74 [ 400/461 ( 87%)] Loss: 0.696032 (0.6758) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.952s, 33.62/s (0.791s, 40.44/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-19 15:26:45,441 - train: [ INFO] - Train: 74 [ 450/461 ( 98%)] Loss: 0.700158 (0.6782) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.677s, 47.24/s (0.789s, 40.57/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:26:52,460 - train: [ INFO] - Train: 74 [ 460/461 (100%)] Loss: 0.675070 (0.6779) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.631s, 50.71/s (0.787s, 40.67/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:26:57,341 - train: [ INFO] - Eval : 74 Time: 4.546 (4.546) Loss: 2.1219 (2.1219) Acc@1: 50.0000 (50.0000)Acc@5: 71.8750 (71.8750) +2025-04-19 15:27:09,852 - train: [ INFO] - Eval : 74 Time: 0.195 (0.334) Loss: 1.8054 (1.9708) Acc@1: 56.2500 (50.4289)Acc@5: 78.1250 (76.2868) +2025-04-19 15:27:16,403 - train: [ INFO] - Eval : 74 Time: 0.095 (0.288) Loss: 3.5549 (1.9686) Acc@1: 0.0000 (51.0023)Acc@5: 0.0000 (76.0216) +2025-04-19 15:27:26,704 - train: [ INFO] - Train: 75 [ 0/461 ( 0%)] Loss: 0.672502 (0.6725) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.330s, 5.06/s (6.330s, 5.06/s) LR: 5.000e-04 Data: 5.436 (5.436) +2025-04-19 15:28:05,370 - train: [ INFO] - Train: 75 [ 50/461 ( 11%)] Loss: 0.695495 (0.6840) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.651s, 49.19/s (0.881s, 36.34/s) LR: 5.000e-04 Data: 0.001 (0.107) +2025-04-19 15:28:44,744 - train: [ INFO] - Train: 75 [ 100/461 ( 22%)] Loss: 0.669035 (0.6790) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.799s, 40.04/s (0.834s, 38.38/s) LR: 5.000e-04 Data: 0.000 (0.055) +2025-04-19 15:29:22,672 - train: [ INFO] - Train: 75 [ 150/461 ( 33%)] Loss: 0.691091 (0.6820) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.785s, 40.75/s (0.808s, 39.60/s) LR: 5.000e-04 Data: 0.000 (0.037) +2025-04-19 15:30:02,896 - train: [ INFO] - Train: 75 [ 200/461 ( 43%)] Loss: 0.670707 (0.6798) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.818s, 39.11/s (0.807s, 39.67/s) LR: 5.000e-04 Data: 0.000 (0.028) +2025-04-19 15:30:41,228 - train: [ INFO] - Train: 75 [ 250/461 ( 54%)] Loss: 0.677068 (0.6793) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.770s, 41.54/s (0.798s, 40.08/s) LR: 5.000e-04 Data: 0.005 (0.023) +2025-04-19 15:31:20,052 - train: [ INFO] - Train: 75 [ 300/461 ( 65%)] Loss: 0.674546 (0.6786) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.817s, 39.18/s (0.794s, 40.28/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-19 15:32:00,717 - train: [ INFO] - Train: 75 [ 350/461 ( 76%)] Loss: 0.671034 (0.6777) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.994s, 32.18/s (0.797s, 40.16/s) LR: 5.000e-04 Data: 0.001 (0.017) +2025-04-19 15:32:42,405 - train: [ INFO] - Train: 75 [ 400/461 ( 87%)] Loss: 0.699161 (0.6801) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.725s, 44.12/s (0.801s, 39.94/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 15:33:21,359 - train: [ INFO] - Train: 75 [ 450/461 ( 98%)] Loss: 0.672523 (0.6793) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.934s, 34.27/s (0.799s, 40.07/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:33:29,806 - train: [ INFO] - Train: 75 [ 460/461 (100%)] Loss: 0.690980 (0.6804) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.834s, 38.39/s (0.799s, 40.03/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:33:35,636 - train: [ INFO] - Eval : 75 Time: 5.450 (5.450) Loss: 2.1038 (2.1038) Acc@1: 40.6250 (40.6250)Acc@5: 75.0000 (75.0000) +2025-04-19 15:33:49,309 - train: [ INFO] - Eval : 75 Time: 0.211 (0.375) Loss: 1.8293 (1.9811) Acc@1: 53.1250 (50.0613)Acc@5: 75.0000 (76.4706) +2025-04-19 15:33:57,396 - train: [ INFO] - Eval : 75 Time: 0.090 (0.332) Loss: 3.4171 (1.9766) Acc@1: 0.0000 (50.0771)Acc@5: 0.0000 (76.4071) +2025-04-19 15:34:08,049 - train: [ INFO] - Train: 76 [ 0/461 ( 0%)] Loss: 0.669513 (0.6695) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.973s, 5.36/s (5.973s, 5.36/s) LR: 5.000e-04 Data: 5.121 (5.121) +2025-04-19 15:34:44,595 - train: [ INFO] - Train: 76 [ 50/461 ( 11%)] Loss: 0.687396 (0.6785) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.687s, 46.56/s (0.831s, 38.51/s) LR: 5.000e-04 Data: 0.000 (0.101) +2025-04-19 15:35:19,871 - train: [ INFO] - Train: 76 [ 100/461 ( 22%)] Loss: 0.717082 (0.6913) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.750s, 42.67/s (0.768s, 41.66/s) LR: 5.000e-04 Data: 0.000 (0.052) +2025-04-19 15:35:56,606 - train: [ INFO] - Train: 76 [ 150/461 ( 33%)] Loss: 0.667318 (0.6853) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.841s, 38.04/s (0.756s, 42.31/s) LR: 5.000e-04 Data: 0.000 (0.035) +2025-04-19 15:36:36,751 - train: [ INFO] - Train: 76 [ 200/461 ( 43%)] Loss: 0.664050 (0.6811) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.700s, 45.69/s (0.767s, 41.72/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-19 15:37:15,917 - train: [ INFO] - Train: 76 [ 250/461 ( 54%)] Loss: 0.721257 (0.6878) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.682s, 46.93/s (0.770s, 41.58/s) LR: 5.000e-04 Data: 0.013 (0.022) +2025-04-19 15:37:57,137 - train: [ INFO] - Train: 76 [ 300/461 ( 65%)] Loss: 0.673691 (0.6858) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.854s, 37.47/s (0.778s, 41.12/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-19 15:38:36,069 - train: [ INFO] - Train: 76 [ 350/461 ( 76%)] Loss: 0.677004 (0.6847) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.767s, 41.70/s (0.778s, 41.13/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 15:39:14,332 - train: [ INFO] - Train: 76 [ 400/461 ( 87%)] Loss: 0.668181 (0.6828) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.933s, 34.29/s (0.776s, 41.23/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 15:39:50,839 - train: [ INFO] - Train: 76 [ 450/461 ( 98%)] Loss: 0.673942 (0.6819) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.979s, 32.69/s (0.771s, 41.52/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 15:39:58,205 - train: [ INFO] - Train: 76 [ 460/461 (100%)] Loss: 0.705071 (0.6840) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.778s, 41.16/s (0.770s, 41.56/s) LR: 5.000e-04 Data: 0.007 (0.012) +2025-04-19 15:40:04,293 - train: [ INFO] - Eval : 76 Time: 5.752 (5.752) Loss: 2.0884 (2.0884) Acc@1: 50.0000 (50.0000)Acc@5: 71.8750 (71.8750) +2025-04-19 15:40:18,016 - train: [ INFO] - Eval : 76 Time: 0.235 (0.382) Loss: 1.8066 (1.9763) Acc@1: 56.2500 (50.5515)Acc@5: 75.0000 (76.2255) +2025-04-19 15:40:26,061 - train: [ INFO] - Eval : 76 Time: 0.054 (0.336) Loss: 3.5158 (1.9753) Acc@1: 0.0000 (50.8096)Acc@5: 0.0000 (75.7132) +2025-04-19 15:40:36,205 - train: [ INFO] - Train: 77 [ 0/461 ( 0%)] Loss: 0.671218 (0.6712) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.900s, 5.42/s (5.900s, 5.42/s) LR: 5.000e-04 Data: 5.100 (5.100) +2025-04-19 15:41:14,232 - train: [ INFO] - Train: 77 [ 50/461 ( 11%)] Loss: 0.689576 (0.6804) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.722s, 44.30/s (0.859s, 37.27/s) LR: 5.000e-04 Data: 0.000 (0.101) +2025-04-19 15:41:54,368 - train: [ INFO] - Train: 77 [ 100/461 ( 22%)] Loss: 0.672132 (0.6776) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.953s, 33.57/s (0.830s, 38.57/s) LR: 5.000e-04 Data: 0.000 (0.052) +2025-04-19 15:42:36,206 - train: [ INFO] - Train: 77 [ 150/461 ( 33%)] Loss: 0.667325 (0.6751) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.865s, 37.00/s (0.831s, 38.49/s) LR: 5.000e-04 Data: 0.000 (0.035) +2025-04-19 15:43:15,259 - train: [ INFO] - Train: 77 [ 200/461 ( 43%)] Loss: 0.672461 (0.6745) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.640s, 49.98/s (0.819s, 39.09/s) LR: 5.000e-04 Data: 0.001 (0.026) +2025-04-19 15:43:54,982 - train: [ INFO] - Train: 77 [ 250/461 ( 54%)] Loss: 0.673503 (0.6744) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.476s, 67.29/s (0.813s, 39.35/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 15:44:34,514 - train: [ INFO] - Train: 77 [ 300/461 ( 65%)] Loss: 0.670106 (0.6738) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.785s, 40.75/s (0.809s, 39.55/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 15:45:14,293 - train: [ INFO] - Train: 77 [ 350/461 ( 76%)] Loss: 0.679131 (0.6744) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.673s, 47.57/s (0.807s, 39.66/s) LR: 5.000e-04 Data: 0.005 (0.016) +2025-04-19 15:45:52,367 - train: [ INFO] - Train: 77 [ 400/461 ( 87%)] Loss: 0.669109 (0.6738) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.663s, 48.28/s (0.801s, 39.95/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 15:46:31,029 - train: [ INFO] - Train: 77 [ 450/461 ( 98%)] Loss: 0.669588 (0.6734) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.939s, 34.07/s (0.798s, 40.12/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 15:46:38,911 - train: [ INFO] - Train: 77 [ 460/461 (100%)] Loss: 0.668878 (0.6730) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.679s, 47.10/s (0.797s, 40.13/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 15:46:44,766 - train: [ INFO] - Eval : 77 Time: 5.500 (5.500) Loss: 2.0972 (2.0972) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-19 15:46:58,476 - train: [ INFO] - Eval : 77 Time: 0.296 (0.377) Loss: 1.8340 (1.9786) Acc@1: 46.8750 (50.6740)Acc@5: 75.0000 (76.3480) +2025-04-19 15:47:06,264 - train: [ INFO] - Eval : 77 Time: 0.063 (0.329) Loss: 3.1829 (1.9756) Acc@1: 0.0000 (50.8481)Acc@5: 50.0000 (76.2914) +2025-04-19 15:47:16,210 - train: [ INFO] - Train: 78 [ 0/461 ( 0%)] Loss: 0.689769 (0.6898) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.664s, 5.65/s (5.664s, 5.65/s) LR: 5.000e-04 Data: 4.754 (4.754) +2025-04-19 15:47:59,124 - train: [ INFO] - Train: 78 [ 50/461 ( 11%)] Loss: 0.667841 (0.6788) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.979s, 32.69/s (0.950s, 33.67/s) LR: 5.000e-04 Data: 0.001 (0.094) +2025-04-19 15:48:41,635 - train: [ INFO] - Train: 78 [ 100/461 ( 22%)] Loss: 0.666614 (0.6747) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.802s, 39.91/s (0.900s, 35.57/s) LR: 5.000e-04 Data: 0.000 (0.048) +2025-04-19 15:49:23,393 - train: [ INFO] - Train: 78 [ 150/461 ( 33%)] Loss: 0.671320 (0.6739) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.711s, 45.01/s (0.878s, 36.45/s) LR: 5.000e-04 Data: 0.001 (0.032) +2025-04-19 15:50:03,621 - train: [ INFO] - Train: 78 [ 200/461 ( 43%)] Loss: 0.667026 (0.6725) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.775s, 41.27/s (0.859s, 37.24/s) LR: 5.000e-04 Data: 0.002 (0.025) +2025-04-19 15:50:40,924 - train: [ INFO] - Train: 78 [ 250/461 ( 54%)] Loss: 0.668062 (0.6718) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.608s, 52.66/s (0.836s, 38.26/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 15:51:17,950 - train: [ INFO] - Train: 78 [ 300/461 ( 65%)] Loss: 0.674639 (0.6722) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.827s, 38.72/s (0.820s, 39.01/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 15:51:57,479 - train: [ INFO] - Train: 78 [ 350/461 ( 76%)] Loss: 0.687458 (0.6741) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.695s, 46.06/s (0.816s, 39.22/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 15:52:37,425 - train: [ INFO] - Train: 78 [ 400/461 ( 87%)] Loss: 0.675793 (0.6743) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.989s, 32.36/s (0.813s, 39.34/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:53:13,845 - train: [ INFO] - Train: 78 [ 450/461 ( 98%)] Loss: 0.671380 (0.6740) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.759s, 42.17/s (0.804s, 39.81/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 15:53:21,620 - train: [ INFO] - Train: 78 [ 460/461 (100%)] Loss: 0.689124 (0.6754) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.717s, 44.64/s (0.803s, 39.84/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:53:27,280 - train: [ INFO] - Eval : 78 Time: 5.264 (5.264) Loss: 2.0957 (2.0957) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-19 15:53:41,323 - train: [ INFO] - Eval : 78 Time: 0.262 (0.379) Loss: 1.8303 (1.9965) Acc@1: 59.3750 (50.0613)Acc@5: 75.0000 (75.6127) +2025-04-19 15:53:48,461 - train: [ INFO] - Eval : 78 Time: 0.065 (0.323) Loss: 3.3294 (1.9920) Acc@1: 0.0000 (50.1157)Acc@5: 50.0000 (75.8674) +2025-04-19 15:53:57,339 - train: [ INFO] - Train: 79 [ 0/461 ( 0%)] Loss: 0.666870 (0.6669) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.926s, 6.50/s (4.926s, 6.50/s) LR: 5.000e-04 Data: 3.915 (3.915) +2025-04-19 15:54:38,922 - train: [ INFO] - Train: 79 [ 50/461 ( 11%)] Loss: 0.669133 (0.6680) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.604s, 52.98/s (0.911s, 35.13/s) LR: 5.000e-04 Data: 0.000 (0.078) +2025-04-19 15:55:16,865 - train: [ INFO] - Train: 79 [ 100/461 ( 22%)] Loss: 0.670048 (0.6687) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.876s, 36.54/s (0.834s, 38.35/s) LR: 5.000e-04 Data: 0.000 (0.040) +2025-04-19 15:55:54,995 - train: [ INFO] - Train: 79 [ 150/461 ( 33%)] Loss: 0.665911 (0.6680) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.874s, 36.62/s (0.810s, 39.49/s) LR: 5.000e-04 Data: 0.001 (0.027) +2025-04-19 15:56:33,517 - train: [ INFO] - Train: 79 [ 200/461 ( 43%)] Loss: 0.668514 (0.6681) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.736s, 43.48/s (0.800s, 39.99/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 15:57:11,376 - train: [ INFO] - Train: 79 [ 250/461 ( 54%)] Loss: 0.676549 (0.6695) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.764s, 41.90/s (0.791s, 40.44/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 15:57:50,412 - train: [ INFO] - Train: 79 [ 300/461 ( 65%)] Loss: 0.668144 (0.6693) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.713s, 44.90/s (0.789s, 40.54/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-19 15:58:28,442 - train: [ INFO] - Train: 79 [ 350/461 ( 76%)] Loss: 0.663881 (0.6686) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.023s, 31.28/s (0.785s, 40.76/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 15:59:09,438 - train: [ INFO] - Train: 79 [ 400/461 ( 87%)] Loss: 0.746056 (0.6772) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 96.8750 (99.6528) Time: 0.742s, 43.14/s (0.789s, 40.54/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:59:50,647 - train: [ INFO] - Train: 79 [ 450/461 ( 98%)] Loss: 0.670976 (0.6766) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.937s, 34.14/s (0.793s, 40.35/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-19 15:59:59,020 - train: [ INFO] - Train: 79 [ 460/461 (100%)] Loss: 0.663000 (0.6754) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.936s, 34.20/s (0.794s, 40.31/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-19 16:00:04,804 - train: [ INFO] - Eval : 79 Time: 5.418 (5.418) Loss: 2.1170 (2.1170) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-19 16:00:18,364 - train: [ INFO] - Eval : 79 Time: 0.257 (0.372) Loss: 1.8367 (1.9922) Acc@1: 53.1250 (50.2451)Acc@5: 71.8750 (75.3676) +2025-04-19 16:00:26,215 - train: [ INFO] - Eval : 79 Time: 0.063 (0.327) Loss: 3.4021 (1.9859) Acc@1: 0.0000 (50.2699)Acc@5: 50.0000 (75.8674) +2025-04-19 16:00:34,823 - train: [ INFO] - Train: 80 [ 0/461 ( 0%)] Loss: 0.673787 (0.6738) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.714s, 6.79/s (4.714s, 6.79/s) LR: 5.000e-04 Data: 3.891 (3.891) +2025-04-19 16:01:13,292 - train: [ INFO] - Train: 80 [ 50/461 ( 11%)] Loss: 0.667988 (0.6709) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.770s, 41.56/s (0.844s, 37.91/s) LR: 5.000e-04 Data: 0.000 (0.078) +2025-04-19 16:01:52,532 - train: [ INFO] - Train: 80 [ 100/461 ( 22%)] Loss: 0.670624 (0.6708) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.630s, 50.81/s (0.813s, 39.35/s) LR: 5.000e-04 Data: 0.006 (0.040) +2025-04-19 16:02:29,957 - train: [ INFO] - Train: 80 [ 150/461 ( 33%)] Loss: 0.670898 (0.6708) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.673s, 47.56/s (0.791s, 40.44/s) LR: 5.000e-04 Data: 0.001 (0.027) +2025-04-19 16:03:02,687 - train: [ INFO] - Train: 80 [ 200/461 ( 43%)] Loss: 0.673418 (0.6713) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.631s, 50.72/s (0.757s, 42.28/s) LR: 5.000e-04 Data: 0.003 (0.021) +2025-04-19 16:03:42,811 - train: [ INFO] - Train: 80 [ 250/461 ( 54%)] Loss: 0.672702 (0.6716) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.859s, 37.25/s (0.766s, 41.80/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 16:04:20,968 - train: [ INFO] - Train: 80 [ 300/461 ( 65%)] Loss: 0.668211 (0.6711) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.612s, 52.28/s (0.765s, 41.83/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:04:58,595 - train: [ INFO] - Train: 80 [ 350/461 ( 76%)] Loss: 0.669295 (0.6709) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.579s, 55.22/s (0.763s, 41.95/s) LR: 5.000e-04 Data: 0.001 (0.012) +2025-04-19 16:05:36,678 - train: [ INFO] - Train: 80 [ 400/461 ( 87%)] Loss: 0.671950 (0.6710) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.785s, 40.75/s (0.762s, 41.97/s) LR: 5.000e-04 Data: 0.006 (0.011) +2025-04-19 16:06:13,638 - train: [ INFO] - Train: 80 [ 450/461 ( 98%)] Loss: 0.673647 (0.6713) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.684s, 46.80/s (0.760s, 42.12/s) LR: 5.000e-04 Data: 0.007 (0.010) +2025-04-19 16:06:20,859 - train: [ INFO] - Train: 80 [ 460/461 (100%)] Loss: 0.670974 (0.6712) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.638s, 50.19/s (0.759s, 42.17/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-19 16:06:26,868 - train: [ INFO] - Eval : 80 Time: 5.660 (5.660) Loss: 2.1298 (2.1298) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-19 16:06:40,848 - train: [ INFO] - Eval : 80 Time: 0.331 (0.385) Loss: 1.8241 (1.9896) Acc@1: 56.2500 (50.5515)Acc@5: 84.3750 (76.0417) +2025-04-19 16:06:48,570 - train: [ INFO] - Eval : 80 Time: 0.066 (0.334) Loss: 3.3770 (1.9835) Acc@1: 0.0000 (50.7325)Acc@5: 50.0000 (76.2529) +2025-04-19 16:06:58,734 - train: [ INFO] - Train: 81 [ 0/461 ( 0%)] Loss: 0.669286 (0.6693) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.476s, 5.84/s (5.476s, 5.84/s) LR: 5.000e-04 Data: 4.751 (4.751) +2025-04-19 16:07:36,642 - train: [ INFO] - Train: 81 [ 50/461 ( 11%)] Loss: 0.670433 (0.6699) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.626s, 51.15/s (0.848s, 37.72/s) LR: 5.000e-04 Data: 0.000 (0.096) +2025-04-19 16:08:10,934 - train: [ INFO] - Train: 81 [ 100/461 ( 22%)] Loss: 0.710469 (0.6834) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.868s, 36.87/s (0.767s, 41.72/s) LR: 5.000e-04 Data: 0.004 (0.049) +2025-04-19 16:08:46,698 - train: [ INFO] - Train: 81 [ 150/461 ( 33%)] Loss: 0.669784 (0.6800) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.473s, 67.66/s (0.749s, 42.70/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-19 16:09:27,660 - train: [ INFO] - Train: 81 [ 200/461 ( 43%)] Loss: 0.669789 (0.6780) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.982s, 32.60/s (0.766s, 41.76/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-19 16:10:07,730 - train: [ INFO] - Train: 81 [ 250/461 ( 54%)] Loss: 0.670675 (0.6767) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.784s, 40.84/s (0.773s, 41.39/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 16:10:48,280 - train: [ INFO] - Train: 81 [ 300/461 ( 65%)] Loss: 0.665321 (0.6751) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.000s, 32.01/s (0.779s, 41.07/s) LR: 5.000e-04 Data: 0.002 (0.017) +2025-04-19 16:11:28,479 - train: [ INFO] - Train: 81 [ 350/461 ( 76%)] Loss: 0.671062 (0.6746) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.584s, 54.78/s (0.782s, 40.90/s) LR: 5.000e-04 Data: 0.006 (0.015) +2025-04-19 16:12:09,195 - train: [ INFO] - Train: 81 [ 400/461 ( 87%)] Loss: 0.672061 (0.6743) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.609s, 52.51/s (0.786s, 40.71/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:12:48,048 - train: [ INFO] - Train: 81 [ 450/461 ( 98%)] Loss: 0.679171 (0.6748) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.878s, 36.46/s (0.785s, 40.77/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:12:55,630 - train: [ INFO] - Train: 81 [ 460/461 (100%)] Loss: 0.669113 (0.6743) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.821s, 38.97/s (0.784s, 40.80/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 16:13:01,574 - train: [ INFO] - Eval : 81 Time: 5.601 (5.601) Loss: 2.1256 (2.1256) Acc@1: 40.6250 (40.6250)Acc@5: 78.1250 (78.1250) +2025-04-19 16:13:15,229 - train: [ INFO] - Eval : 81 Time: 0.303 (0.378) Loss: 1.8212 (2.0020) Acc@1: 56.2500 (49.5098)Acc@5: 75.0000 (75.8578) +2025-04-19 16:13:22,856 - train: [ INFO] - Eval : 81 Time: 0.058 (0.328) Loss: 3.4205 (1.9978) Acc@1: 0.0000 (49.6916)Acc@5: 50.0000 (76.0216) +2025-04-19 16:13:33,070 - train: [ INFO] - Train: 82 [ 0/461 ( 0%)] Loss: 0.673521 (0.6735) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.610s, 5.70/s (5.610s, 5.70/s) LR: 5.000e-04 Data: 4.917 (4.917) +2025-04-19 16:14:09,060 - train: [ INFO] - Train: 82 [ 50/461 ( 11%)] Loss: 0.668672 (0.6711) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.627s, 51.06/s (0.814s, 39.30/s) LR: 5.000e-04 Data: 0.002 (0.097) +2025-04-19 16:14:44,669 - train: [ INFO] - Train: 82 [ 100/461 ( 22%)] Loss: 0.664968 (0.6691) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.741s, 43.21/s (0.763s, 41.94/s) LR: 5.000e-04 Data: 0.000 (0.050) +2025-04-19 16:15:22,772 - train: [ INFO] - Train: 82 [ 150/461 ( 33%)] Loss: 0.669469 (0.6692) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.576s, 55.54/s (0.762s, 41.98/s) LR: 5.000e-04 Data: 0.001 (0.033) +2025-04-19 16:15:56,905 - train: [ INFO] - Train: 82 [ 200/461 ( 43%)] Loss: 0.665421 (0.6684) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.748s, 42.81/s (0.742s, 43.12/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-19 16:16:33,001 - train: [ INFO] - Train: 82 [ 250/461 ( 54%)] Loss: 0.707289 (0.6749) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.859s, 37.24/s (0.738s, 43.37/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 16:17:07,961 - train: [ INFO] - Train: 82 [ 300/461 ( 65%)] Loss: 0.672380 (0.6745) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.714s, 44.81/s (0.731s, 43.77/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 16:17:46,829 - train: [ INFO] - Train: 82 [ 350/461 ( 76%)] Loss: 0.667709 (0.6737) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.577s, 55.46/s (0.737s, 43.39/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 16:18:22,840 - train: [ INFO] - Train: 82 [ 400/461 ( 87%)] Loss: 0.692520 (0.6758) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.721s, 44.36/s (0.735s, 43.53/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:19:01,922 - train: [ INFO] - Train: 82 [ 450/461 ( 98%)] Loss: 0.665679 (0.6748) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.675s, 47.38/s (0.740s, 43.24/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:19:09,896 - train: [ INFO] - Train: 82 [ 460/461 (100%)] Loss: 0.739886 (0.6807) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.627s, 51.07/s (0.741s, 43.17/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:19:15,656 - train: [ INFO] - Eval : 82 Time: 5.400 (5.400) Loss: 2.1451 (2.1451) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-19 16:19:29,010 - train: [ INFO] - Eval : 82 Time: 0.233 (0.368) Loss: 1.8316 (1.9974) Acc@1: 53.1250 (50.4289)Acc@5: 78.1250 (75.1838) +2025-04-19 16:19:36,701 - train: [ INFO] - Eval : 82 Time: 0.073 (0.323) Loss: 3.2902 (1.9956) Acc@1: 0.0000 (50.3470)Acc@5: 50.0000 (75.0193) +2025-04-19 16:19:46,110 - train: [ INFO] - Train: 83 [ 0/461 ( 0%)] Loss: 0.673809 (0.6738) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.847s, 6.60/s (4.847s, 6.60/s) LR: 5.000e-04 Data: 4.028 (4.028) +2025-04-19 16:20:26,896 - train: [ INFO] - Train: 83 [ 50/461 ( 11%)] Loss: 0.668340 (0.6711) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.799s, 40.04/s (0.894s, 35.81/s) LR: 5.000e-04 Data: 0.000 (0.088) +2025-04-19 16:21:01,146 - train: [ INFO] - Train: 83 [ 100/461 ( 22%)] Loss: 0.693588 (0.6786) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.721s, 44.37/s (0.790s, 40.52/s) LR: 5.000e-04 Data: 0.003 (0.045) +2025-04-19 16:21:41,882 - train: [ INFO] - Train: 83 [ 150/461 ( 33%)] Loss: 0.668417 (0.6760) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.732s, 43.69/s (0.798s, 40.12/s) LR: 5.000e-04 Data: 0.000 (0.030) +2025-04-19 16:22:19,517 - train: [ INFO] - Train: 83 [ 200/461 ( 43%)] Loss: 0.663942 (0.6736) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.698s, 45.84/s (0.786s, 40.72/s) LR: 5.000e-04 Data: 0.000 (0.023) +2025-04-19 16:22:54,930 - train: [ INFO] - Train: 83 [ 250/461 ( 54%)] Loss: 0.665295 (0.6722) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.609s, 52.56/s (0.770s, 41.56/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-19 16:23:31,633 - train: [ INFO] - Train: 83 [ 300/461 ( 65%)] Loss: 0.671955 (0.6722) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.562s, 56.89/s (0.764s, 41.90/s) LR: 5.000e-04 Data: 0.002 (0.016) +2025-04-19 16:24:09,044 - train: [ INFO] - Train: 83 [ 350/461 ( 76%)] Loss: 0.668700 (0.6718) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.711s, 45.04/s (0.761s, 42.04/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:24:47,891 - train: [ INFO] - Train: 83 [ 400/461 ( 87%)] Loss: 0.670402 (0.6716) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.699s, 45.79/s (0.763s, 41.94/s) LR: 5.000e-04 Data: 0.005 (0.012) +2025-04-19 16:25:23,783 - train: [ INFO] - Train: 83 [ 450/461 ( 98%)] Loss: 0.663721 (0.6708) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.920s, 34.78/s (0.758s, 42.23/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 16:25:31,831 - train: [ INFO] - Train: 83 [ 460/461 (100%)] Loss: 0.676055 (0.6713) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.858s, 37.28/s (0.759s, 42.18/s) LR: 5.000e-04 Data: 0.001 (0.011) +2025-04-19 16:25:38,032 - train: [ INFO] - Eval : 83 Time: 5.840 (5.840) Loss: 2.1436 (2.1436) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 16:25:51,463 - train: [ INFO] - Eval : 83 Time: 0.202 (0.378) Loss: 1.8369 (2.0107) Acc@1: 53.1250 (50.3064)Acc@5: 68.7500 (75.0000) +2025-04-19 16:25:59,460 - train: [ INFO] - Eval : 83 Time: 0.072 (0.333) Loss: 3.1333 (2.0079) Acc@1: 0.0000 (50.2699)Acc@5: 50.0000 (75.0193) +2025-04-19 16:26:09,446 - train: [ INFO] - Train: 84 [ 0/461 ( 0%)] Loss: 0.667086 (0.6671) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.774s, 5.54/s (5.774s, 5.54/s) LR: 5.000e-04 Data: 4.947 (4.947) +2025-04-19 16:26:49,677 - train: [ INFO] - Train: 84 [ 50/461 ( 11%)] Loss: 0.666178 (0.6666) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.718s, 44.59/s (0.899s, 35.59/s) LR: 5.000e-04 Data: 0.000 (0.098) +2025-04-19 16:27:28,826 - train: [ INFO] - Train: 84 [ 100/461 ( 22%)] Loss: 0.668872 (0.6674) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.774s, 41.32/s (0.841s, 38.06/s) LR: 5.000e-04 Data: 0.000 (0.050) +2025-04-19 16:28:09,082 - train: [ INFO] - Train: 84 [ 150/461 ( 33%)] Loss: 0.666031 (0.6670) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.978s, 32.72/s (0.828s, 38.63/s) LR: 5.000e-04 Data: 0.001 (0.033) +2025-04-19 16:28:51,252 - train: [ INFO] - Train: 84 [ 200/461 ( 43%)] Loss: 0.665496 (0.6667) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.723s, 44.27/s (0.832s, 38.48/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-19 16:29:32,861 - train: [ INFO] - Train: 84 [ 250/461 ( 54%)] Loss: 0.670360 (0.6673) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.814s, 39.29/s (0.831s, 38.49/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 16:30:12,833 - train: [ INFO] - Train: 84 [ 300/461 ( 65%)] Loss: 0.673669 (0.6682) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.820s, 39.01/s (0.826s, 38.75/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 16:30:50,477 - train: [ INFO] - Train: 84 [ 350/461 ( 76%)] Loss: 0.689779 (0.6709) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.685s, 46.74/s (0.815s, 39.25/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 16:31:30,166 - train: [ INFO] - Train: 84 [ 400/461 ( 87%)] Loss: 0.666243 (0.6704) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.691s, 46.33/s (0.812s, 39.39/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:32:06,329 - train: [ INFO] - Train: 84 [ 450/461 ( 98%)] Loss: 0.666432 (0.6700) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.736s, 43.48/s (0.802s, 39.89/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:32:13,717 - train: [ INFO] - Train: 84 [ 460/461 (100%)] Loss: 0.665067 (0.6696) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.853s, 37.51/s (0.801s, 39.96/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:32:18,344 - train: [ INFO] - Eval : 84 Time: 4.298 (4.298) Loss: 2.1204 (2.1204) Acc@1: 43.7500 (43.7500)Acc@5: 81.2500 (81.2500) +2025-04-19 16:32:32,560 - train: [ INFO] - Eval : 84 Time: 0.266 (0.363) Loss: 1.8500 (2.0016) Acc@1: 53.1250 (49.7549)Acc@5: 68.7500 (76.4706) +2025-04-19 16:32:40,466 - train: [ INFO] - Eval : 84 Time: 0.077 (0.322) Loss: 3.2543 (1.9975) Acc@1: 0.0000 (50.1928)Acc@5: 50.0000 (75.9445) +2025-04-19 16:32:50,346 - train: [ INFO] - Train: 85 [ 0/461 ( 0%)] Loss: 0.666370 (0.6664) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.180s, 5.18/s (6.180s, 5.18/s) LR: 5.000e-04 Data: 5.454 (5.454) +2025-04-19 16:33:30,352 - train: [ INFO] - Train: 85 [ 50/461 ( 11%)] Loss: 0.673128 (0.6697) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.764s, 41.91/s (0.904s, 35.39/s) LR: 5.000e-04 Data: 0.000 (0.108) +2025-04-19 16:34:10,105 - train: [ INFO] - Train: 85 [ 100/461 ( 22%)] Loss: 0.668399 (0.6693) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.052s, 30.41/s (0.850s, 37.67/s) LR: 5.000e-04 Data: 0.001 (0.055) +2025-04-19 16:34:48,878 - train: [ INFO] - Train: 85 [ 150/461 ( 33%)] Loss: 0.679280 (0.6718) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.987s, 32.43/s (0.824s, 38.81/s) LR: 5.000e-04 Data: 0.000 (0.037) +2025-04-19 16:35:26,472 - train: [ INFO] - Train: 85 [ 200/461 ( 43%)] Loss: 0.666068 (0.6706) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.974s, 32.86/s (0.806s, 39.70/s) LR: 5.000e-04 Data: 0.000 (0.028) +2025-04-19 16:36:06,330 - train: [ INFO] - Train: 85 [ 250/461 ( 54%)] Loss: 0.673371 (0.6711) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.985s, 32.48/s (0.804s, 39.81/s) LR: 5.000e-04 Data: 0.000 (0.023) +2025-04-19 16:36:45,108 - train: [ INFO] - Train: 85 [ 300/461 ( 65%)] Loss: 0.689663 (0.6738) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.959s, 33.36/s (0.799s, 40.06/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 16:37:24,184 - train: [ INFO] - Train: 85 [ 350/461 ( 76%)] Loss: 0.661232 (0.6722) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.776s, 41.25/s (0.796s, 40.20/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 16:37:59,123 - train: [ INFO] - Train: 85 [ 400/461 ( 87%)] Loss: 0.675620 (0.6726) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.760s, 42.11/s (0.784s, 40.83/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:38:38,957 - train: [ INFO] - Train: 85 [ 450/461 ( 98%)] Loss: 0.670866 (0.6724) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.603s, 53.07/s (0.785s, 40.77/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:38:45,666 - train: [ INFO] - Train: 85 [ 460/461 (100%)] Loss: 0.662382 (0.6715) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.745s, 42.95/s (0.782s, 40.90/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:38:51,142 - train: [ INFO] - Eval : 85 Time: 5.139 (5.139) Loss: 2.1062 (2.1062) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-19 16:39:05,175 - train: [ INFO] - Eval : 85 Time: 0.327 (0.376) Loss: 1.8148 (2.0021) Acc@1: 53.1250 (50.3676)Acc@5: 75.0000 (75.3064) +2025-04-19 16:39:12,662 - train: [ INFO] - Eval : 85 Time: 0.069 (0.325) Loss: 3.3636 (1.9963) Acc@1: 0.0000 (50.6939)Acc@5: 50.0000 (75.6361) +2025-04-19 16:39:23,086 - train: [ INFO] - Train: 86 [ 0/461 ( 0%)] Loss: 0.687293 (0.6873) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.202s, 5.16/s (6.202s, 5.16/s) LR: 5.000e-04 Data: 5.264 (5.264) +2025-04-19 16:40:02,156 - train: [ INFO] - Train: 86 [ 50/461 ( 11%)] Loss: 0.661518 (0.6744) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.634s, 50.49/s (0.886s, 36.11/s) LR: 5.000e-04 Data: 0.000 (0.104) +2025-04-19 16:40:42,120 - train: [ INFO] - Train: 86 [ 100/461 ( 22%)] Loss: 0.691585 (0.6801) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.688s, 46.50/s (0.842s, 37.99/s) LR: 5.000e-04 Data: 0.001 (0.053) +2025-04-19 16:41:17,572 - train: [ INFO] - Train: 86 [ 150/461 ( 33%)] Loss: 0.673453 (0.6785) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.782s, 40.93/s (0.798s, 40.12/s) LR: 5.000e-04 Data: 0.009 (0.036) +2025-04-19 16:41:52,544 - train: [ INFO] - Train: 86 [ 200/461 ( 43%)] Loss: 0.666047 (0.6760) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.964s, 33.20/s (0.773s, 41.41/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-19 16:42:30,592 - train: [ INFO] - Train: 86 [ 250/461 ( 54%)] Loss: 0.662670 (0.6738) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.633s, 50.56/s (0.770s, 41.55/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-19 16:43:08,854 - train: [ INFO] - Train: 86 [ 300/461 ( 65%)] Loss: 0.667346 (0.6728) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.828s, 38.66/s (0.769s, 41.61/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-19 16:43:46,782 - train: [ INFO] - Train: 86 [ 350/461 ( 76%)] Loss: 0.665533 (0.6719) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.606s, 52.84/s (0.767s, 41.71/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 16:44:26,801 - train: [ INFO] - Train: 86 [ 400/461 ( 87%)] Loss: 0.668526 (0.6716) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.827s, 38.67/s (0.771s, 41.50/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:44:58,583 - train: [ INFO] - Train: 86 [ 450/461 ( 98%)] Loss: 0.666209 (0.6710) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.990s, 32.31/s (0.756s, 42.34/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:45:06,562 - train: [ INFO] - Train: 86 [ 460/461 (100%)] Loss: 0.664021 (0.6704) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.971s, 32.95/s (0.757s, 42.29/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:45:11,701 - train: [ INFO] - Eval : 86 Time: 4.758 (4.758) Loss: 2.1400 (2.1400) Acc@1: 40.6250 (40.6250)Acc@5: 68.7500 (68.7500) +2025-04-19 16:45:25,292 - train: [ INFO] - Eval : 86 Time: 0.267 (0.360) Loss: 1.8517 (2.0135) Acc@1: 53.1250 (49.8775)Acc@5: 71.8750 (75.1225) +2025-04-19 16:45:33,303 - train: [ INFO] - Eval : 86 Time: 0.058 (0.321) Loss: 3.3616 (2.0085) Acc@1: 0.0000 (49.6530)Acc@5: 50.0000 (75.1735) +2025-04-19 16:45:43,392 - train: [ INFO] - Train: 87 [ 0/461 ( 0%)] Loss: 0.664400 (0.6644) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.918s, 5.41/s (5.918s, 5.41/s) LR: 5.000e-04 Data: 5.034 (5.034) +2025-04-19 16:46:23,772 - train: [ INFO] - Train: 87 [ 50/461 ( 11%)] Loss: 0.677518 (0.6710) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.582s, 54.99/s (0.906s, 35.31/s) LR: 5.000e-04 Data: 0.000 (0.100) +2025-04-19 16:47:00,119 - train: [ INFO] - Train: 87 [ 100/461 ( 22%)] Loss: 0.685595 (0.6758) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.792s, 40.41/s (0.817s, 39.19/s) LR: 5.000e-04 Data: 0.000 (0.051) +2025-04-19 16:47:36,045 - train: [ INFO] - Train: 87 [ 150/461 ( 33%)] Loss: 0.672629 (0.6750) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.998s, 32.08/s (0.783s, 40.85/s) LR: 5.000e-04 Data: 0.000 (0.034) +2025-04-19 16:48:17,436 - train: [ INFO] - Train: 87 [ 200/461 ( 43%)] Loss: 0.664059 (0.6728) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.458s, 69.80/s (0.794s, 40.30/s) LR: 5.000e-04 Data: 0.005 (0.026) +2025-04-19 16:48:59,749 - train: [ INFO] - Train: 87 [ 250/461 ( 54%)] Loss: 0.670427 (0.6724) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.979s, 32.69/s (0.804s, 39.80/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 16:49:40,134 - train: [ INFO] - Train: 87 [ 300/461 ( 65%)] Loss: 0.665819 (0.6715) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.922s, 34.70/s (0.804s, 39.78/s) LR: 5.000e-04 Data: 0.005 (0.018) +2025-04-19 16:50:18,317 - train: [ INFO] - Train: 87 [ 350/461 ( 76%)] Loss: 0.684944 (0.6732) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.710s, 45.08/s (0.798s, 40.08/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 16:50:56,517 - train: [ INFO] - Train: 87 [ 400/461 ( 87%)] Loss: 0.670349 (0.6729) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.829s, 38.60/s (0.794s, 40.31/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:51:37,142 - train: [ INFO] - Train: 87 [ 450/461 ( 98%)] Loss: 0.665403 (0.6721) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.716s, 44.72/s (0.796s, 40.21/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:51:45,331 - train: [ INFO] - Train: 87 [ 460/461 (100%)] Loss: 0.666141 (0.6716) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.597s, 53.61/s (0.796s, 40.19/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:51:50,508 - train: [ INFO] - Eval : 87 Time: 4.884 (4.884) Loss: 2.1778 (2.1778) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-19 16:52:04,727 - train: [ INFO] - Eval : 87 Time: 0.211 (0.375) Loss: 1.8245 (2.0158) Acc@1: 53.1250 (50.3064)Acc@5: 75.0000 (74.6324) +2025-04-19 16:52:12,513 - train: [ INFO] - Eval : 87 Time: 0.059 (0.328) Loss: 3.3438 (2.0100) Acc@1: 0.0000 (50.1157)Acc@5: 50.0000 (74.7880) +2025-04-19 16:52:21,716 - train: [ INFO] - Train: 88 [ 0/461 ( 0%)] Loss: 0.666245 (0.6662) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.192s, 6.16/s (5.192s, 6.16/s) LR: 5.000e-04 Data: 4.375 (4.375) +2025-04-19 16:52:59,533 - train: [ INFO] - Train: 88 [ 50/461 ( 11%)] Loss: 0.665070 (0.6657) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.852s, 37.55/s (0.841s, 38.03/s) LR: 5.000e-04 Data: 0.000 (0.087) +2025-04-19 16:53:37,816 - train: [ INFO] - Train: 88 [ 100/461 ( 22%)] Loss: 0.663617 (0.6650) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.514s, 62.25/s (0.803s, 39.86/s) LR: 5.000e-04 Data: 0.000 (0.045) +2025-04-19 16:54:15,124 - train: [ INFO] - Train: 88 [ 150/461 ( 33%)] Loss: 0.662894 (0.6645) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.759s, 42.17/s (0.783s, 40.87/s) LR: 5.000e-04 Data: 0.000 (0.030) +2025-04-19 16:54:53,946 - train: [ INFO] - Train: 88 [ 200/461 ( 43%)] Loss: 0.675264 (0.6666) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.985s, 32.50/s (0.781s, 40.97/s) LR: 5.000e-04 Data: 0.000 (0.023) +2025-04-19 16:55:32,509 - train: [ INFO] - Train: 88 [ 250/461 ( 54%)] Loss: 0.664228 (0.6662) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.556s, 57.50/s (0.779s, 41.10/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 16:56:09,532 - train: [ INFO] - Train: 88 [ 300/461 ( 65%)] Loss: 0.683567 (0.6687) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.589s, 54.37/s (0.772s, 41.46/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 16:56:46,932 - train: [ INFO] - Train: 88 [ 350/461 ( 76%)] Loss: 0.664972 (0.6682) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.907s, 35.28/s (0.768s, 41.65/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:57:24,931 - train: [ INFO] - Train: 88 [ 400/461 ( 87%)] Loss: 0.669194 (0.6683) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.526s, 60.80/s (0.767s, 41.73/s) LR: 5.000e-04 Data: 0.001 (0.012) +2025-04-19 16:58:01,362 - train: [ INFO] - Train: 88 [ 450/461 ( 98%)] Loss: 0.674826 (0.6690) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.642s, 49.85/s (0.762s, 41.97/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 16:58:09,048 - train: [ INFO] - Train: 88 [ 460/461 (100%)] Loss: 0.706166 (0.6724) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.926s, 34.54/s (0.762s, 41.97/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-19 16:58:15,115 - train: [ INFO] - Eval : 88 Time: 5.708 (5.708) Loss: 2.1325 (2.1325) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-19 16:58:27,760 - train: [ INFO] - Eval : 88 Time: 0.185 (0.360) Loss: 1.8421 (2.0089) Acc@1: 50.0000 (50.4289)Acc@5: 71.8750 (75.4289) +2025-04-19 16:58:34,869 - train: [ INFO] - Eval : 88 Time: 0.066 (0.311) Loss: 3.3676 (2.0046) Acc@1: 0.0000 (50.3855)Acc@5: 0.0000 (75.2506) +2025-04-19 16:58:44,274 - train: [ INFO] - Train: 89 [ 0/461 ( 0%)] Loss: 0.669905 (0.6699) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.374s, 5.95/s (5.374s, 5.95/s) LR: 5.000e-04 Data: 4.760 (4.760) +2025-04-19 16:59:22,108 - train: [ INFO] - Train: 89 [ 50/461 ( 11%)] Loss: 0.676610 (0.6733) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.762s, 42.01/s (0.846s, 37.81/s) LR: 5.000e-04 Data: 0.000 (0.095) +2025-04-19 16:59:59,772 - train: [ INFO] - Train: 89 [ 100/461 ( 22%)] Loss: 0.715875 (0.6875) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.563s, 56.86/s (0.799s, 40.04/s) LR: 5.000e-04 Data: 0.000 (0.049) +2025-04-19 17:00:37,892 - train: [ INFO] - Train: 89 [ 150/461 ( 33%)] Loss: 0.672276 (0.6837) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.706s, 45.32/s (0.786s, 40.69/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-19 17:01:15,682 - train: [ INFO] - Train: 89 [ 200/461 ( 43%)] Loss: 0.668179 (0.6806) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.637s, 50.25/s (0.778s, 41.11/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-19 17:01:52,480 - train: [ INFO] - Train: 89 [ 250/461 ( 54%)] Loss: 0.662462 (0.6776) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.906s, 35.31/s (0.770s, 41.58/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 17:02:27,150 - train: [ INFO] - Train: 89 [ 300/461 ( 65%)] Loss: 0.663579 (0.6756) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.604s, 52.94/s (0.757s, 42.29/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 17:03:04,323 - train: [ INFO] - Train: 89 [ 350/461 ( 76%)] Loss: 0.663844 (0.6741) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.903s, 35.44/s (0.755s, 42.40/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-19 17:03:40,402 - train: [ INFO] - Train: 89 [ 400/461 ( 87%)] Loss: 0.701734 (0.6772) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.905s, 35.37/s (0.750s, 42.64/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 17:04:17,791 - train: [ INFO] - Train: 89 [ 450/461 ( 98%)] Loss: 0.713574 (0.6808) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.651s, 49.15/s (0.750s, 42.67/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:04:25,675 - train: [ INFO] - Train: 89 [ 460/461 (100%)] Loss: 0.663727 (0.6793) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.762s, 42.01/s (0.751s, 42.63/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 17:04:30,885 - train: [ INFO] - Eval : 89 Time: 4.871 (4.871) Loss: 2.1186 (2.1186) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-19 17:04:44,773 - train: [ INFO] - Eval : 89 Time: 0.335 (0.368) Loss: 1.8306 (2.0181) Acc@1: 53.1250 (49.8775)Acc@5: 71.8750 (75.2451) +2025-04-19 17:04:52,816 - train: [ INFO] - Eval : 89 Time: 0.060 (0.327) Loss: 3.2242 (2.0147) Acc@1: 0.0000 (49.7687)Acc@5: 50.0000 (75.0193) +2025-04-19 17:05:03,556 - train: [ INFO] - Train: 90 [ 0/461 ( 0%)] Loss: 0.665240 (0.6652) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.248s, 5.12/s (6.248s, 5.12/s) LR: 5.000e-04 Data: 5.271 (5.271) +2025-04-19 17:05:41,386 - train: [ INFO] - Train: 90 [ 50/461 ( 11%)] Loss: 0.668368 (0.6668) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.829s, 38.60/s (0.863s, 37.10/s) LR: 5.000e-04 Data: 0.000 (0.106) +2025-04-19 17:06:23,129 - train: [ INFO] - Train: 90 [ 100/461 ( 22%)] Loss: 0.693133 (0.6756) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.613s, 52.19/s (0.848s, 37.73/s) LR: 5.000e-04 Data: 0.006 (0.054) +2025-04-19 17:07:02,405 - train: [ INFO] - Train: 90 [ 150/461 ( 33%)] Loss: 0.664210 (0.6727) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.724s, 44.20/s (0.827s, 38.70/s) LR: 5.000e-04 Data: 0.000 (0.036) +2025-04-19 17:07:41,538 - train: [ INFO] - Train: 90 [ 200/461 ( 43%)] Loss: 0.665344 (0.6713) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.653s, 49.04/s (0.815s, 39.24/s) LR: 5.000e-04 Data: 0.000 (0.028) +2025-04-19 17:08:16,613 - train: [ INFO] - Train: 90 [ 250/461 ( 54%)] Loss: 0.665018 (0.6702) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.882s, 36.26/s (0.793s, 40.38/s) LR: 5.000e-04 Data: 0.000 (0.022) +2025-04-19 17:08:53,776 - train: [ INFO] - Train: 90 [ 300/461 ( 65%)] Loss: 0.672551 (0.6706) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.724s, 44.20/s (0.784s, 40.81/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 17:09:30,732 - train: [ INFO] - Train: 90 [ 350/461 ( 76%)] Loss: 0.684153 (0.6723) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.610s, 52.46/s (0.777s, 41.16/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 17:10:07,870 - train: [ INFO] - Train: 90 [ 400/461 ( 87%)] Loss: 0.692625 (0.6745) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.893s, 35.85/s (0.773s, 41.42/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 17:10:47,649 - train: [ INFO] - Train: 90 [ 450/461 ( 98%)] Loss: 0.686040 (0.6757) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.722s, 44.32/s (0.775s, 41.29/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 17:10:56,024 - train: [ INFO] - Train: 90 [ 460/461 (100%)] Loss: 0.692302 (0.6772) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.872s, 36.70/s (0.776s, 41.23/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 17:11:02,224 - train: [ INFO] - Eval : 90 Time: 5.813 (5.813) Loss: 2.1638 (2.1638) Acc@1: 40.6250 (40.6250)Acc@5: 78.1250 (78.1250) +2025-04-19 17:11:16,731 - train: [ INFO] - Eval : 90 Time: 0.270 (0.399) Loss: 1.8776 (2.0184) Acc@1: 50.0000 (49.8162)Acc@5: 71.8750 (75.3064) +2025-04-19 17:11:24,427 - train: [ INFO] - Eval : 90 Time: 0.093 (0.342) Loss: 3.3733 (2.0149) Acc@1: 0.0000 (49.4217)Acc@5: 0.0000 (75.4048) +2025-04-19 17:11:34,114 - train: [ INFO] - Train: 91 [ 0/461 ( 0%)] Loss: 0.663324 (0.6633) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.490s, 5.83/s (5.490s, 5.83/s) LR: 5.000e-04 Data: 4.671 (4.671) +2025-04-19 17:12:12,815 - train: [ INFO] - Train: 91 [ 50/461 ( 11%)] Loss: 0.663310 (0.6633) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.737s, 43.40/s (0.865s, 36.99/s) LR: 5.000e-04 Data: 0.000 (0.098) +2025-04-19 17:12:50,406 - train: [ INFO] - Train: 91 [ 100/461 ( 22%)] Loss: 0.665511 (0.6640) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.770s, 41.55/s (0.808s, 39.59/s) LR: 5.000e-04 Data: 0.000 (0.050) +2025-04-19 17:13:27,480 - train: [ INFO] - Train: 91 [ 150/461 ( 33%)] Loss: 0.739080 (0.6828) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.676s, 47.37/s (0.785s, 40.75/s) LR: 5.000e-04 Data: 0.000 (0.034) +2025-04-19 17:14:03,610 - train: [ INFO] - Train: 91 [ 200/461 ( 43%)] Loss: 0.662608 (0.6788) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.543s, 58.98/s (0.769s, 41.60/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-19 17:14:40,516 - train: [ INFO] - Train: 91 [ 250/461 ( 54%)] Loss: 0.663809 (0.6763) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.764s, 41.86/s (0.763s, 41.96/s) LR: 5.000e-04 Data: 0.011 (0.021) +2025-04-19 17:15:19,103 - train: [ INFO] - Train: 91 [ 300/461 ( 65%)] Loss: 0.663103 (0.6744) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.824s, 38.83/s (0.764s, 41.90/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 17:15:56,900 - train: [ INFO] - Train: 91 [ 350/461 ( 76%)] Loss: 0.661450 (0.6728) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.656s, 48.76/s (0.762s, 41.97/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-19 17:16:37,351 - train: [ INFO] - Train: 91 [ 400/461 ( 87%)] Loss: 0.665916 (0.6720) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.752s, 42.58/s (0.768s, 41.66/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-19 17:17:13,867 - train: [ INFO] - Train: 91 [ 450/461 ( 98%)] Loss: 0.666623 (0.6715) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.783s, 40.86/s (0.764s, 41.91/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:17:21,597 - train: [ INFO] - Train: 91 [ 460/461 (100%)] Loss: 0.672148 (0.6715) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.809s, 39.57/s (0.764s, 41.90/s) LR: 5.000e-04 Data: 0.003 (0.012) +2025-04-19 17:17:26,861 - train: [ INFO] - Eval : 91 Time: 4.874 (4.874) Loss: 2.1318 (2.1318) Acc@1: 40.6250 (40.6250)Acc@5: 81.2500 (81.2500) +2025-04-19 17:17:40,998 - train: [ INFO] - Eval : 91 Time: 0.302 (0.373) Loss: 1.8570 (2.0279) Acc@1: 50.0000 (49.1422)Acc@5: 71.8750 (74.6324) +2025-04-19 17:17:48,643 - train: [ INFO] - Eval : 91 Time: 0.074 (0.325) Loss: 3.2572 (2.0270) Acc@1: 0.0000 (49.4217)Acc@5: 0.0000 (74.6723) +2025-04-19 17:17:59,708 - train: [ INFO] - Train: 92 [ 0/461 ( 0%)] Loss: 0.663267 (0.6633) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.327s, 5.06/s (6.327s, 5.06/s) LR: 5.000e-04 Data: 5.331 (5.331) +2025-04-19 17:18:36,275 - train: [ INFO] - Train: 92 [ 50/461 ( 11%)] Loss: 0.663675 (0.6635) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.757s, 42.29/s (0.839s, 38.13/s) LR: 5.000e-04 Data: 0.000 (0.106) +2025-04-19 17:19:15,703 - train: [ INFO] - Train: 92 [ 100/461 ( 22%)] Loss: 0.678358 (0.6684) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.839s, 38.16/s (0.813s, 39.34/s) LR: 5.000e-04 Data: 0.001 (0.054) +2025-04-19 17:19:55,795 - train: [ INFO] - Train: 92 [ 150/461 ( 33%)] Loss: 0.665870 (0.6678) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.891s, 35.93/s (0.809s, 39.55/s) LR: 5.000e-04 Data: 0.000 (0.036) +2025-04-19 17:20:37,077 - train: [ INFO] - Train: 92 [ 200/461 ( 43%)] Loss: 0.670150 (0.6683) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.781s, 40.98/s (0.813s, 39.37/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-19 17:21:15,773 - train: [ INFO] - Train: 92 [ 250/461 ( 54%)] Loss: 0.670290 (0.6686) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.773s, 41.41/s (0.805s, 39.77/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-19 17:21:57,096 - train: [ INFO] - Train: 92 [ 300/461 ( 65%)] Loss: 0.664869 (0.6681) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.671s, 47.66/s (0.808s, 39.60/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 17:22:39,644 - train: [ INFO] - Train: 92 [ 350/461 ( 76%)] Loss: 0.662250 (0.6673) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.895s, 35.74/s (0.814s, 39.32/s) LR: 5.000e-04 Data: 0.004 (0.016) +2025-04-19 17:23:19,669 - train: [ INFO] - Train: 92 [ 400/461 ( 87%)] Loss: 0.659861 (0.6665) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.989s, 32.34/s (0.812s, 39.41/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 17:24:01,424 - train: [ INFO] - Train: 92 [ 450/461 ( 98%)] Loss: 0.668110 (0.6667) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.575s, 55.64/s (0.814s, 39.30/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-19 17:24:09,902 - train: [ INFO] - Train: 92 [ 460/461 (100%)] Loss: 0.671705 (0.6671) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.872s, 36.68/s (0.815s, 39.27/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:24:15,945 - train: [ INFO] - Eval : 92 Time: 5.682 (5.682) Loss: 2.0883 (2.0883) Acc@1: 46.8750 (46.8750)Acc@5: 84.3750 (84.3750) +2025-04-19 17:24:29,424 - train: [ INFO] - Eval : 92 Time: 0.279 (0.376) Loss: 1.8258 (2.0228) Acc@1: 50.0000 (49.8775)Acc@5: 78.1250 (75.7353) +2025-04-19 17:24:36,897 - train: [ INFO] - Eval : 92 Time: 0.060 (0.325) Loss: 3.3541 (2.0215) Acc@1: 0.0000 (49.7687)Acc@5: 50.0000 (75.1735) +2025-04-19 17:24:46,446 - train: [ INFO] - Train: 93 [ 0/461 ( 0%)] Loss: 0.695415 (0.6954) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.139s, 6.23/s (5.139s, 6.23/s) LR: 5.000e-04 Data: 4.402 (4.402) +2025-04-19 17:25:26,116 - train: [ INFO] - Train: 93 [ 50/461 ( 11%)] Loss: 0.718384 (0.7069) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.777s, 41.16/s (0.876s, 36.52/s) LR: 5.000e-04 Data: 0.000 (0.087) +2025-04-19 17:26:06,647 - train: [ INFO] - Train: 93 [ 100/461 ( 22%)] Loss: 0.679679 (0.6978) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.902s, 35.48/s (0.843s, 37.96/s) LR: 5.000e-04 Data: 0.000 (0.044) +2025-04-19 17:26:44,723 - train: [ INFO] - Train: 93 [ 150/461 ( 33%)] Loss: 0.669994 (0.6909) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.863s, 37.09/s (0.815s, 39.24/s) LR: 5.000e-04 Data: 0.000 (0.030) +2025-04-19 17:27:21,630 - train: [ INFO] - Train: 93 [ 200/461 ( 43%)] Loss: 0.665437 (0.6858) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.037s, 30.87/s (0.796s, 40.22/s) LR: 5.000e-04 Data: 0.011 (0.023) +2025-04-19 17:27:58,051 - train: [ INFO] - Train: 93 [ 250/461 ( 54%)] Loss: 0.735193 (0.6940) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.758s, 42.19/s (0.782s, 40.93/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 17:28:34,594 - train: [ INFO] - Train: 93 [ 300/461 ( 65%)] Loss: 0.664639 (0.6898) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.811s, 39.47/s (0.773s, 41.39/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 17:29:13,333 - train: [ INFO] - Train: 93 [ 350/461 ( 76%)] Loss: 0.678996 (0.6885) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.686s, 46.65/s (0.773s, 41.39/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 17:29:51,083 - train: [ INFO] - Train: 93 [ 400/461 ( 87%)] Loss: 0.692123 (0.6889) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.693s, 46.15/s (0.771s, 41.53/s) LR: 5.000e-04 Data: 0.001 (0.012) +2025-04-19 17:30:30,540 - train: [ INFO] - Train: 93 [ 450/461 ( 98%)] Loss: 0.734445 (0.6934) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.859s, 37.27/s (0.772s, 41.43/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 17:30:38,125 - train: [ INFO] - Train: 93 [ 460/461 (100%)] Loss: 0.664781 (0.6908) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.795s, 40.23/s (0.772s, 41.45/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 17:30:44,386 - train: [ INFO] - Eval : 93 Time: 5.894 (5.894) Loss: 2.1419 (2.1419) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-19 17:30:58,326 - train: [ INFO] - Eval : 93 Time: 0.362 (0.389) Loss: 1.8567 (2.0282) Acc@1: 50.0000 (49.5711)Acc@5: 68.7500 (74.5711) +2025-04-19 17:31:06,272 - train: [ INFO] - Eval : 93 Time: 0.092 (0.339) Loss: 3.2850 (2.0235) Acc@1: 0.0000 (49.9229)Acc@5: 50.0000 (74.5952) +2025-04-19 17:31:16,240 - train: [ INFO] - Train: 94 [ 0/461 ( 0%)] Loss: 0.672548 (0.6725) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.162s, 6.20/s (5.162s, 6.20/s) LR: 5.000e-04 Data: 4.299 (4.299) +2025-04-19 17:31:55,893 - train: [ INFO] - Train: 94 [ 50/461 ( 11%)] Loss: 0.670994 (0.6718) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.025s, 31.22/s (0.877s, 36.48/s) LR: 5.000e-04 Data: 0.001 (0.090) +2025-04-19 17:32:35,195 - train: [ INFO] - Train: 94 [ 100/461 ( 22%)] Loss: 0.663369 (0.6690) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.780s, 41.01/s (0.831s, 38.49/s) LR: 5.000e-04 Data: 0.000 (0.046) +2025-04-19 17:33:14,185 - train: [ INFO] - Train: 94 [ 150/461 ( 33%)] Loss: 0.674426 (0.6703) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.017s, 31.48/s (0.814s, 39.33/s) LR: 5.000e-04 Data: 0.000 (0.031) +2025-04-19 17:33:53,139 - train: [ INFO] - Train: 94 [ 200/461 ( 43%)] Loss: 0.662725 (0.6688) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.779s, 41.10/s (0.805s, 39.77/s) LR: 5.000e-04 Data: 0.001 (0.024) +2025-04-19 17:34:30,170 - train: [ INFO] - Train: 94 [ 250/461 ( 54%)] Loss: 0.672004 (0.6693) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.794s, 40.30/s (0.792s, 40.42/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 17:35:07,301 - train: [ INFO] - Train: 94 [ 300/461 ( 65%)] Loss: 0.663860 (0.6686) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.588s, 54.40/s (0.783s, 40.86/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 17:35:40,032 - train: [ INFO] - Train: 94 [ 350/461 ( 76%)] Loss: 0.664975 (0.6681) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.427s, 75.00/s (0.765s, 41.85/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 17:36:20,696 - train: [ INFO] - Train: 94 [ 400/461 ( 87%)] Loss: 0.673246 (0.6687) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.812s, 39.43/s (0.771s, 41.53/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:37:03,530 - train: [ INFO] - Train: 94 [ 450/461 ( 98%)] Loss: 0.663595 (0.6682) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.795s, 40.27/s (0.780s, 41.03/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 17:37:11,833 - train: [ INFO] - Train: 94 [ 460/461 (100%)] Loss: 0.668930 (0.6682) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.678s, 47.23/s (0.781s, 40.98/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 17:37:17,484 - train: [ INFO] - Eval : 94 Time: 5.290 (5.290) Loss: 2.1072 (2.1072) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-19 17:37:32,092 - train: [ INFO] - Eval : 94 Time: 0.272 (0.390) Loss: 1.8345 (2.0315) Acc@1: 56.2500 (49.6324)Acc@5: 75.0000 (75.1838) +2025-04-19 17:37:40,260 - train: [ INFO] - Eval : 94 Time: 0.067 (0.342) Loss: 3.3518 (2.0290) Acc@1: 0.0000 (49.6916)Acc@5: 50.0000 (74.7109) +2025-04-19 17:37:49,813 - train: [ INFO] - Train: 95 [ 0/461 ( 0%)] Loss: 0.664977 (0.6650) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.494s, 5.82/s (5.494s, 5.82/s) LR: 5.000e-04 Data: 4.628 (4.628) +2025-04-19 17:38:33,763 - train: [ INFO] - Train: 95 [ 50/461 ( 11%)] Loss: 0.752275 (0.7086) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (98.4375) Time: 1.021s, 31.35/s (0.968s, 33.07/s) LR: 5.000e-04 Data: 0.000 (0.092) +2025-04-19 17:39:15,762 - train: [ INFO] - Train: 95 [ 100/461 ( 22%)] Loss: 0.663863 (0.6937) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.760s, 42.09/s (0.904s, 35.41/s) LR: 5.000e-04 Data: 0.000 (0.047) +2025-04-19 17:39:51,776 - train: [ INFO] - Train: 95 [ 150/461 ( 33%)] Loss: 0.686239 (0.6918) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.579s, 55.23/s (0.842s, 37.99/s) LR: 5.000e-04 Data: 0.001 (0.032) +2025-04-19 17:40:30,356 - train: [ INFO] - Train: 95 [ 200/461 ( 43%)] Loss: 0.680675 (0.6896) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.702s, 45.57/s (0.824s, 38.83/s) LR: 5.000e-04 Data: 0.001 (0.024) +2025-04-19 17:41:07,933 - train: [ INFO] - Train: 95 [ 250/461 ( 54%)] Loss: 0.663514 (0.6853) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.594s, 53.86/s (0.809s, 39.54/s) LR: 5.000e-04 Data: 0.002 (0.019) +2025-04-19 17:41:46,419 - train: [ INFO] - Train: 95 [ 300/461 ( 65%)] Loss: 0.667904 (0.6828) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.844s, 37.92/s (0.802s, 39.88/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 17:42:22,562 - train: [ INFO] - Train: 95 [ 350/461 ( 76%)] Loss: 0.665230 (0.6806) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.846s, 37.85/s (0.791s, 40.46/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-19 17:43:00,723 - train: [ INFO] - Train: 95 [ 400/461 ( 87%)] Loss: 0.664508 (0.6788) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.465s, 68.79/s (0.787s, 40.66/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-19 17:43:37,213 - train: [ INFO] - Train: 95 [ 450/461 ( 98%)] Loss: 0.662195 (0.6771) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.861s, 37.17/s (0.781s, 41.00/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 17:43:44,185 - train: [ INFO] - Train: 95 [ 460/461 (100%)] Loss: 0.722122 (0.6812) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.609s, 52.53/s (0.779s, 41.10/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 17:43:51,657 - train: [ INFO] - Eval : 95 Time: 7.147 (7.147) Loss: 2.1763 (2.1763) Acc@1: 40.6250 (40.6250)Acc@5: 75.0000 (75.0000) +2025-04-19 17:44:05,163 - train: [ INFO] - Eval : 95 Time: 0.310 (0.405) Loss: 1.8261 (2.0316) Acc@1: 53.1250 (49.2034)Acc@5: 75.0000 (75.2451) +2025-04-19 17:44:12,611 - train: [ INFO] - Eval : 95 Time: 0.061 (0.343) Loss: 3.4039 (2.0242) Acc@1: 0.0000 (49.5759)Acc@5: 50.0000 (75.0964) +2025-04-19 17:44:22,463 - train: [ INFO] - Train: 96 [ 0/461 ( 0%)] Loss: 0.697367 (0.6974) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.646s, 5.67/s (5.646s, 5.67/s) LR: 5.000e-04 Data: 4.952 (4.952) +2025-04-19 17:45:00,396 - train: [ INFO] - Train: 96 [ 50/461 ( 11%)] Loss: 0.674816 (0.6861) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.796s, 40.21/s (0.853s, 37.52/s) LR: 5.000e-04 Data: 0.001 (0.098) +2025-04-19 17:45:37,259 - train: [ INFO] - Train: 96 [ 100/461 ( 22%)] Loss: 0.669487 (0.6806) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.974s, 32.87/s (0.795s, 40.26/s) LR: 5.000e-04 Data: 0.000 (0.050) +2025-04-19 17:46:14,096 - train: [ INFO] - Train: 96 [ 150/461 ( 33%)] Loss: 0.694071 (0.6839) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.616s, 51.96/s (0.775s, 41.29/s) LR: 5.000e-04 Data: 0.000 (0.034) +2025-04-19 17:46:55,710 - train: [ INFO] - Train: 96 [ 200/461 ( 43%)] Loss: 0.663835 (0.6799) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.801s, 39.96/s (0.789s, 40.56/s) LR: 5.000e-04 Data: 0.001 (0.026) +2025-04-19 17:47:34,079 - train: [ INFO] - Train: 96 [ 250/461 ( 54%)] Loss: 0.700219 (0.6833) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.547s, 58.55/s (0.784s, 40.80/s) LR: 5.000e-04 Data: 0.007 (0.021) +2025-04-19 17:48:11,941 - train: [ INFO] - Train: 96 [ 300/461 ( 65%)] Loss: 0.683628 (0.6833) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.762s, 42.00/s (0.779s, 41.06/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 17:48:49,857 - train: [ INFO] - Train: 96 [ 350/461 ( 76%)] Loss: 0.664084 (0.6809) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.993s, 32.22/s (0.776s, 41.23/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 17:49:28,590 - train: [ INFO] - Train: 96 [ 400/461 ( 87%)] Loss: 0.664456 (0.6791) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.46/s (0.776s, 41.25/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 17:50:06,721 - train: [ INFO] - Train: 96 [ 450/461 ( 98%)] Loss: 0.659324 (0.6771) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.782s, 40.94/s (0.774s, 41.33/s) LR: 5.000e-04 Data: 0.006 (0.012) +2025-04-19 17:50:14,474 - train: [ INFO] - Train: 96 [ 460/461 (100%)] Loss: 0.664008 (0.6759) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.818s, 39.13/s (0.774s, 41.34/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:50:20,293 - train: [ INFO] - Eval : 96 Time: 5.465 (5.465) Loss: 2.1136 (2.1136) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-19 17:50:34,489 - train: [ INFO] - Eval : 96 Time: 0.301 (0.386) Loss: 1.8419 (2.0278) Acc@1: 56.2500 (50.2451)Acc@5: 75.0000 (75.1838) +2025-04-19 17:50:42,499 - train: [ INFO] - Eval : 96 Time: 0.060 (0.337) Loss: 3.2011 (2.0231) Acc@1: 0.0000 (50.1928)Acc@5: 50.0000 (75.0964) +2025-04-19 17:50:53,973 - train: [ INFO] - Train: 97 [ 0/461 ( 0%)] Loss: 0.661895 (0.6619) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.947s, 4.61/s (6.947s, 4.61/s) LR: 5.000e-04 Data: 5.878 (5.878) +2025-04-19 17:51:35,315 - train: [ INFO] - Train: 97 [ 50/461 ( 11%)] Loss: 0.673777 (0.6678) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.824s, 38.84/s (0.944s, 33.89/s) LR: 5.000e-04 Data: 0.000 (0.116) +2025-04-19 17:52:15,860 - train: [ INFO] - Train: 97 [ 100/461 ( 22%)] Loss: 0.663886 (0.6665) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.880s, 36.36/s (0.877s, 36.48/s) LR: 5.000e-04 Data: 0.000 (0.059) +2025-04-19 17:52:53,363 - train: [ INFO] - Train: 97 [ 150/461 ( 33%)] Loss: 0.671668 (0.6678) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.803s, 39.85/s (0.834s, 38.35/s) LR: 5.000e-04 Data: 0.011 (0.040) +2025-04-19 17:53:23,520 - train: [ INFO] - Train: 97 [ 200/461 ( 43%)] Loss: 0.663657 (0.6670) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.522s, 61.33/s (0.776s, 41.21/s) LR: 5.000e-04 Data: 0.001 (0.031) +2025-04-19 17:53:51,548 - train: [ INFO] - Train: 97 [ 250/461 ( 54%)] Loss: 0.666963 (0.6670) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.900s, 35.56/s (0.733s, 43.66/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-19 17:54:29,843 - train: [ INFO] - Train: 97 [ 300/461 ( 65%)] Loss: 0.661279 (0.6662) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.587s, 54.56/s (0.738s, 43.34/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 17:55:07,162 - train: [ INFO] - Train: 97 [ 350/461 ( 76%)] Loss: 0.664281 (0.6659) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.751s, 42.63/s (0.739s, 43.30/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 17:55:44,695 - train: [ INFO] - Train: 97 [ 400/461 ( 87%)] Loss: 0.661464 (0.6654) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.522s, 61.32/s (0.740s, 43.23/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 17:56:21,518 - train: [ INFO] - Train: 97 [ 450/461 ( 98%)] Loss: 0.667716 (0.6657) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.659s, 48.59/s (0.740s, 43.26/s) LR: 5.000e-04 Data: 0.003 (0.014) +2025-04-19 17:56:29,087 - train: [ INFO] - Train: 97 [ 460/461 (100%)] Loss: 0.662850 (0.6654) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.692s, 46.24/s (0.740s, 43.24/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 17:56:35,357 - train: [ INFO] - Eval : 97 Time: 5.959 (5.959) Loss: 2.1980 (2.1980) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-19 17:56:49,738 - train: [ INFO] - Eval : 97 Time: 0.329 (0.399) Loss: 1.8572 (2.0396) Acc@1: 53.1250 (49.5098)Acc@5: 75.0000 (75.1838) +2025-04-19 17:56:57,914 - train: [ INFO] - Eval : 97 Time: 0.080 (0.348) Loss: 3.0723 (2.0359) Acc@1: 0.0000 (49.6145)Acc@5: 50.0000 (75.0578) +2025-04-19 17:57:08,366 - train: [ INFO] - Train: 98 [ 0/461 ( 0%)] Loss: 0.678724 (0.6787) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.124s, 5.23/s (6.124s, 5.23/s) LR: 5.000e-04 Data: 5.359 (5.359) +2025-04-19 17:57:48,966 - train: [ INFO] - Train: 98 [ 50/461 ( 11%)] Loss: 0.661164 (0.6699) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.791s, 40.48/s (0.914s, 35.01/s) LR: 5.000e-04 Data: 0.000 (0.106) +2025-04-19 17:58:30,289 - train: [ INFO] - Train: 98 [ 100/461 ( 22%)] Loss: 0.665721 (0.6685) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.997s, 32.10/s (0.869s, 36.81/s) LR: 5.000e-04 Data: 0.001 (0.054) +2025-04-19 17:59:10,664 - train: [ INFO] - Train: 98 [ 150/461 ( 33%)] Loss: 0.665182 (0.6677) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.778s, 41.12/s (0.848s, 37.73/s) LR: 5.000e-04 Data: 0.000 (0.037) +2025-04-19 17:59:47,489 - train: [ INFO] - Train: 98 [ 200/461 ( 43%)] Loss: 0.665278 (0.6672) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.981s, 32.63/s (0.820s, 39.03/s) LR: 5.000e-04 Data: 0.001 (0.028) +2025-04-19 18:00:25,975 - train: [ INFO] - Train: 98 [ 250/461 ( 54%)] Loss: 0.660683 (0.6661) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.656s, 48.79/s (0.810s, 39.53/s) LR: 5.000e-04 Data: 0.001 (0.023) +2025-04-19 18:01:03,936 - train: [ INFO] - Train: 98 [ 300/461 ( 65%)] Loss: 0.666341 (0.6662) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.597s, 53.59/s (0.801s, 39.95/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-19 18:01:41,157 - train: [ INFO] - Train: 98 [ 350/461 ( 76%)] Loss: 0.668622 (0.6665) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.485s, 66.02/s (0.793s, 40.37/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 18:02:17,988 - train: [ INFO] - Train: 98 [ 400/461 ( 87%)] Loss: 0.674121 (0.6673) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.943s, 33.94/s (0.785s, 40.74/s) LR: 5.000e-04 Data: 0.002 (0.015) +2025-04-19 18:02:53,339 - train: [ INFO] - Train: 98 [ 450/461 ( 98%)] Loss: 0.661518 (0.6667) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.796s, 40.22/s (0.776s, 41.21/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-19 18:03:01,223 - train: [ INFO] - Train: 98 [ 460/461 (100%)] Loss: 0.672139 (0.6672) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.946s, 33.84/s (0.777s, 41.20/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 18:03:06,470 - train: [ INFO] - Eval : 98 Time: 4.883 (4.883) Loss: 2.1616 (2.1616) Acc@1: 40.6250 (40.6250)Acc@5: 78.1250 (78.1250) +2025-04-19 18:03:20,484 - train: [ INFO] - Eval : 98 Time: 0.293 (0.370) Loss: 1.8796 (2.0342) Acc@1: 56.2500 (50.1838)Acc@5: 71.8750 (74.2034) +2025-04-19 18:03:28,371 - train: [ INFO] - Eval : 98 Time: 0.073 (0.327) Loss: 3.1820 (2.0301) Acc@1: 0.0000 (50.1157)Acc@5: 50.0000 (74.5181) +2025-04-19 18:03:38,897 - train: [ INFO] - Train: 99 [ 0/461 ( 0%)] Loss: 0.659699 (0.6597) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.961s, 5.37/s (5.961s, 5.37/s) LR: 5.000e-04 Data: 5.109 (5.109) +2025-04-19 18:04:16,324 - train: [ INFO] - Train: 99 [ 50/461 ( 11%)] Loss: 0.662370 (0.6610) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.826s, 38.74/s (0.849s, 37.71/s) LR: 5.000e-04 Data: 0.001 (0.101) +2025-04-19 18:04:53,381 - train: [ INFO] - Train: 99 [ 100/461 ( 22%)] Loss: 0.663880 (0.6620) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.632s, 50.67/s (0.795s, 40.27/s) LR: 5.000e-04 Data: 0.000 (0.052) +2025-04-19 18:05:33,267 - train: [ INFO] - Train: 99 [ 150/461 ( 33%)] Loss: 0.669046 (0.6637) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.833s, 38.42/s (0.795s, 40.25/s) LR: 5.000e-04 Data: 0.000 (0.035) +2025-04-19 18:06:11,468 - train: [ INFO] - Train: 99 [ 200/461 ( 43%)] Loss: 0.673625 (0.6657) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.487s, 65.65/s (0.787s, 40.67/s) LR: 5.000e-04 Data: 0.001 (0.026) +2025-04-19 18:06:52,012 - train: [ INFO] - Train: 99 [ 250/461 ( 54%)] Loss: 0.702788 (0.6719) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.875s, 36.56/s (0.791s, 40.44/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 18:07:32,777 - train: [ INFO] - Train: 99 [ 300/461 ( 65%)] Loss: 0.663374 (0.6707) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.804s, 39.81/s (0.795s, 40.26/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 18:08:12,283 - train: [ INFO] - Train: 99 [ 350/461 ( 76%)] Loss: 0.661744 (0.6696) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.633s, 50.56/s (0.794s, 40.31/s) LR: 5.000e-04 Data: 0.001 (0.016) +2025-04-19 18:08:52,544 - train: [ INFO] - Train: 99 [ 400/461 ( 87%)] Loss: 0.661624 (0.6687) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.941s, 34.00/s (0.795s, 40.25/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-19 18:09:33,612 - train: [ INFO] - Train: 99 [ 450/461 ( 98%)] Loss: 0.669596 (0.6688) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.825s, 38.77/s (0.798s, 40.11/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 18:09:41,936 - train: [ INFO] - Train: 99 [ 460/461 (100%)] Loss: 0.671188 (0.6690) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.930s, 34.41/s (0.798s, 40.08/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 18:09:47,631 - train: [ INFO] - Eval : 99 Time: 5.328 (5.328) Loss: 2.1797 (2.1797) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-19 18:10:01,560 - train: [ INFO] - Eval : 99 Time: 0.277 (0.377) Loss: 1.8551 (2.0301) Acc@1: 59.3750 (50.0613)Acc@5: 78.1250 (75.6127) +2025-04-19 18:10:09,186 - train: [ INFO] - Eval : 99 Time: 0.072 (0.328) Loss: 3.4205 (2.0271) Acc@1: 0.0000 (50.2313)Acc@5: 0.0000 (75.1735) +2025-04-19 18:10:13,875 - train: [ INFO] - *** Best metric: 52.85273708558211 (epoch 18) diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/model_best.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/model_best.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..cfebeea6a4d83b1416464a359a2a6a6513c6b05f --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/model_best.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725a2ecb9fbf7fe1401787f341a2c5634359273ed94e8e79027b54d10685ace4 +size 179373193 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/summary.csv b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/summary.csv new file mode 100644 index 0000000000000000000000000000000000000000..aece782831e94c61c7faa8002da8843d79511193 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4/summary.csv @@ -0,0 +1,101 @@ +epoch,train_loss,train_loss_single,train_loss_inverse,eval_loss,eval_top1,eval_top1_a,eval_top1_v +0,2.842534065246582,0,0,2.413750838571635,32.15111796453354,3.353893600616808,2.197378565921357 +1,2.3762368722395464,0,0,2.262783727741462,35.50501156515035,2.351580570547417,1.4649190439475712 +2,2.1767641847783867,0,0,1.9476832593507554,43.79336931380108,2.004626060138782,2.7370855821125675 +3,1.9504853161898525,0,0,1.9157202124319908,44.41017733230532,1.9275250578257517,3.430994602929838 +4,1.9574416225606746,0,0,1.9150981292783433,44.75713184271395,2.3901310717039324,3.199691595990748 +5,1.896279356696389,0,0,1.8586478707601037,46.87740940632228,2.6599845797995374,3.700848111025443 +6,1.861331289464777,0,0,1.8515102280592495,47.84117193523516,2.043176561295297,3.623747108712413 +7,1.6339806751771406,0,0,1.812731942858435,49.38319198149576,1.6962220508866614,3.469545104086353 +8,1.7054612203077837,0,0,1.7926980197291789,49.80724749421743,1.5420200462606013,4.356206630686199 +9,1.55348078771071,0,0,1.829169128891497,49.88434849653046,3.0069390902081725,3.8164996144949885 +10,1.5169338638132268,0,0,1.8783849820598053,48.57363145720895,2.235929067077872,4.89591364687741 +11,1.432269356467507,0,0,1.8311538615406893,49.61449498843485,2.043176561295297,3.5080956052428682 +12,1.159691420468417,0,0,1.8690683553103034,49.15188897455667,2.235929067077872,4.973014649190439 +13,1.08019005168568,0,0,1.9097255660463686,49.03623747108713,2.235929067077872,4.7417116422513494 +14,0.9812171079895713,0,0,1.8703448171328836,50.07710100231303,3.430994602929838,4.009252120277564 +15,0.8970372460105203,0,0,1.8974868955296007,48.920585967617576,3.0840400925212026,4.163454124903624 +16,0.8476931290193037,0,0,1.8760049203403564,49.76869699306091,2.197378565921357,3.7779491133384733 +17,0.7974537340077487,0,0,1.815794890535365,51.5420200462606,2.3901310717039324,4.047802621434078 +18,0.8030600222674283,0,0,1.7802978856065408,52.85273708558211,2.9298380878951424,3.6622976098689284 +19,0.7467837821353566,0,0,1.826355043336255,51.50346954510409,2.5057825751734772,4.433307632999229 +20,0.7559020681814714,0,0,1.8337618179659523,50.38550501156515,2.9683885890516577,4.163454124903624 +21,0.7487536831335588,0,0,1.8160734474429188,51.464919043947575,3.199691595990748,5.0115651503469545 +22,0.7532314495606856,0,0,1.81891066824002,52.582883577486506,2.8141865844255975,4.7417116422513494 +23,0.7439591396938671,0,0,1.8133797384540025,51.61912104857363,2.9683885890516577,4.548959136468774 +24,0.7267032590779391,0,0,1.8581266364595388,51.15651503469545,3.353893600616808,4.664610639938319 +25,0.7342003854838285,0,0,1.8453405074367362,50.886661526599845,2.7756360832690823,4.6260601387818046 +26,0.7209941853176464,0,0,1.8723233523696041,50.0,2.351580570547417,3.9707016191210487 +27,0.7215252789584073,0,0,1.8430919454202528,50.96376252891287,3.122590593677718,4.356206630686199 +28,0.7253152132034302,0,0,1.8472302351534688,51.079414032382424,3.122590593677718,5.0115651503469545 +29,0.7342924096367576,0,0,1.872821488744402,50.424055512721665,2.274479568234387,3.8550501156515034 +30,0.7284909324212507,0,0,1.863040382161725,51.15651503469545,2.8141865844255975,4.124903623747109 +31,0.7121335105462507,0,0,1.8921648047939115,50.26985350809561,2.3130300693909023,4.279105628373169 +32,0.7131044051863931,0,0,1.8635855410406015,51.349267540478024,2.158828064764842,3.8936006168080186 +33,0.7211100133982572,0,0,1.9082302536151918,50.61680801850424,3.0454895913646878,4.356206630686199 +34,0.7061974189498208,0,0,1.8796920517176596,51.23361603700848,2.3901310717039324,5.165767154973015 +35,0.7145656184716658,0,0,1.9016714730259079,50.26985350809561,2.5057825751734772,4.163454124903624 +36,0.7123901139606129,0,0,1.8908633457851483,51.61912104857363,2.197378565921357,3.5851966075558983 +37,0.7166036800904707,0,0,1.924300892498278,49.961449498843486,2.4672320740169624,3.623747108712413 +38,0.7160452441735701,0,0,1.9210228401601728,50.07710100231303,2.274479568234387,4.124903623747109 +39,0.7101800821044228,0,0,1.8868946819555419,51.349267540478024,2.5828835774865073,4.548959136468774 +40,0.7167113152417269,0,0,1.9452573532495667,49.07478797224364,2.351580570547417,3.469545104086353 +41,0.7237472805109891,0,0,1.9285885649823002,50.61680801850424,2.3901310717039324,3.469545104086353 +42,0.7169086878949945,0,0,1.9345158828435352,49.498843484965306,2.5828835774865073,3.623747108712413 +43,0.7100526040250604,0,0,1.923240745628257,50.07710100231303,2.7756360832690823,3.0454895913646878 +44,0.7085476463491266,0,0,1.9688613126162116,47.76407093292213,2.274479568234387,3.0840400925212026 +45,0.7085912227630615,0,0,1.9245480682267164,49.92289899768697,3.2382420971472627,3.5080956052428682 +46,0.7055061622099443,0,0,1.9364356520365271,49.2289899768697,2.698535080956052,3.2382420971472627 +47,0.7136128707365557,0,0,1.917493371662031,50.23130300693909,2.6599845797995374,3.353893600616808 +48,0.7223523801023309,0,0,1.9193070572711177,50.30840400925212,2.5443330763299925,4.009252120277564 +49,0.7110848697749051,0,0,1.9484993907793173,49.961449498843486,2.8141865844255975,2.698535080956052 +50,0.7217407876794989,0,0,1.943437856072725,50.61680801850424,2.9683885890516577,3.122590593677718 +51,0.7090224894610319,0,0,1.9510596476799722,50.07710100231303,2.8141865844255975,3.0069390902081725 +52,0.7060390168970282,0,0,1.9396294253370627,50.7710100231303,2.7756360832690823,2.8912875867386276 +53,0.7102431763302196,0,0,1.9259352441374484,50.38550501156515,2.698535080956052,2.9683885890516577 +54,0.7168587879701094,0,0,1.936278174818711,49.38319198149576,2.5057825751734772,3.469545104086353 +55,0.7223646911707792,0,0,1.9537237346769758,49.61449498843485,2.3130300693909023,2.5057825751734772 +56,0.7149513147094033,0,0,1.9377238414061464,51.42636854279105,2.158828064764842,2.7370855821125675 +57,0.7087189500982111,0,0,1.9575189408101572,49.30609097918273,2.3130300693909023,2.698535080956052 +58,0.701707043431022,0,0,1.9589374427530706,49.07478797224364,2.043176561295297,3.0069390902081725 +59,0.7103474031795155,0,0,1.976736840047373,48.49653045489591,2.6214340786430226,2.274479568234387 +60,0.7034232128750194,0,0,1.9397829856519617,50.23130300693909,2.235929067077872,2.3901310717039324 +61,0.7162309722466902,0,0,1.9330084149251099,50.65535851966076,2.4672320740169624,2.4672320740169624 +62,0.7023949568921869,0,0,1.9759877814452467,49.69159599074788,2.004626060138782,3.5080956052428682 +63,0.710597650571303,0,0,1.9781732340454596,49.30609097918273,2.120277563608327,3.2382420971472627 +64,0.7039800882339478,0,0,1.9892029861532547,48.61218195836546,2.235929067077872,3.1611410948342327 +65,0.7132458307526328,0,0,2.0308918272796372,47.301464919043944,2.428681572860447,2.8141865844255975 +66,0.7060372233390808,0,0,1.982478394357627,48.14957594448728,1.9275250578257517,2.4672320740169624 +67,0.7156617749821056,0,0,1.9636854708148777,49.07478797224364,2.4672320740169624,2.9298380878951424 +68,0.6998460726304487,0,0,1.9446603768406783,49.65304548959136,2.4672320740169624,3.199691595990748 +69,0.7028526826338335,0,0,2.0081009813336657,48.14957594448728,2.081727062451812,3.122590593677718 +70,0.6947443160143766,0,0,1.9576997668722913,50.15420200462606,2.235929067077872,3.392444101773323 +71,0.6898265480995178,0,0,1.9384402094571151,51.00231303006939,2.235929067077872,3.276792598303778 +72,0.6869108893654563,0,0,1.9484899123080803,51.19506553585197,2.081727062451812,2.9298380878951424 +73,0.6917671452869069,0,0,1.9716085108225403,50.886661526599845,2.5057825751734772,3.6622976098689284 +74,0.6779362992806868,0,0,1.96859073933033,51.00231303006939,1.8889745566692366,3.469545104086353 +75,0.6803765622052279,0,0,1.9765976646264516,50.07710100231303,2.3130300693909023,3.6622976098689284 +76,0.6840457916259766,0,0,1.9753385332794307,50.809560524286816,2.274479568234387,3.6622976098689284 +77,0.6730025789954446,0,0,1.975600912098528,50.84811102544333,2.3901310717039324,3.5080956052428682 +78,0.6753658923235807,0,0,1.9920381619182108,50.11565150346954,2.351580570547417,3.430994602929838 +79,0.675371148369529,0,0,1.9859073994797565,50.26985350809561,1.9275250578257517,3.700848111025443 +80,0.6712266206741333,0,0,1.9835092754849306,50.73245952197379,2.081727062451812,3.7779491133384733 +81,0.6742876822298224,0,0,1.997756567935164,49.69159599074788,2.4672320740169624,3.276792598303778 +82,0.6806832172653892,0,0,1.9956035683866455,50.34695451040864,2.3901310717039324,3.392444101773323 +83,0.671293009411205,0,0,2.0078757572100545,50.26985350809561,2.5057825751734772,3.5080956052428682 +84,0.6695648052475669,0,0,1.9975304324165526,50.19275250578257,2.197378565921357,3.469545104086353 +85,0.6714890382506631,0,0,1.9962509038729583,50.69390902081727,2.3130300693909023,3.276792598303778 +86,0.6703818819739602,0,0,2.0085214722956155,49.65304548959136,2.3130300693909023,3.199691595990748 +87,0.6715712384744124,0,0,2.01004432804693,50.11565150346954,2.274479568234387,3.276792598303778 +88,0.6723676052960482,0,0,2.0045646898729945,50.38550501156515,2.6599845797995374,4.124903623747109 +89,0.6792512915351174,0,0,2.0146556974100718,49.76869699306091,2.5443330763299925,3.430994602929838 +90,0.6771803769198331,0,0,2.0149489555711826,49.42174248265228,2.274479568234387,3.276792598303778 +91,0.6715349013155157,0,0,2.0269692107724886,49.42174248265228,2.274479568234387,3.6622976098689284 +92,0.6671275062994524,0,0,2.0215061569360926,49.76869699306091,2.698535080956052,3.392444101773323 +93,0.6908258199691772,0,0,2.023453015957599,49.92289899768697,2.3130300693909023,3.353893600616808 +94,0.6682428825985302,0,0,2.0289967890969587,49.69159599074788,2.3901310717039324,3.353893600616808 +95,0.6812275973233309,0,0,2.024159437339859,49.575944487278335,2.5828835774865073,3.392444101773323 +96,0.675935918634588,0,0,2.0231098336445523,50.19275250578257,2.4672320740169624,3.199691595990748 +97,0.6654033064842224,0,0,2.035943557228965,49.61449498843485,2.428681572860447,3.2382420971472627 +98,0.6672264337539673,0,0,2.0301050680273756,50.11565150346954,2.5443330763299925,3.7393986121819585 +99,0.6689940094947815,0,0,2.0271076736950193,50.23130300693909,2.428681572860447,3.0840400925212026 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5 b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5 new file mode 100644 index 0000000000000000000000000000000000000000..c986a17ead0a20df5035dae266d460e6c5ea2c74 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0500a7fb7843992db7dfc3575610fd1f4fa41517040b8c5387a460c8e51579be +size 179467884 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5_[-10.0,10.0,51]x[-10.0,10.0,51].h5 b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5_[-10.0,10.0,51]x[-10.0,10.0,51].h5 new file mode 100644 index 0000000000000000000000000000000000000000..51cbcf5b4ff3bc4a4c4027c7d9c2dd4d76537d56 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5_[-10.0,10.0,51]x[-10.0,10.0,51].h5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2014ac2b7660e3d6d64297cd3b8a889a7fe7a116d27b36fbd918cb3e332f0577 +size 50640 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/args.yaml b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/args.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1bb4d0976821ef455b2f1473c00d2c751e1aa98b --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/args.yaml @@ -0,0 +1,162 @@ +aa: rand-m9-mstd0.5-inc1 +act_fun: QGateGrad +adam_epoch: 1000 +adaptation_info: false +adaptive_node: false +alpha: 0.8 +amp: false +apex_amp: false +audio_path: /mnt/home/hexiang/datasets/CREMA-D/AudioWAV/ +aug_splits: 0 +batch_size: 32 +bn_eps: null +bn_momentum: null +bn_tf: false +channels_last: false +clip_grad: null +color_jitter: 0.4 +conf_mat: false +conv_type: normal +cooldown_epochs: 10 +critical_loss: false +crop_pct: null +cut_mix: false +cutmix: 0.0 +cutmix_beta: 2.0 +cutmix_minmax: null +cutmix_noise: 0.0 +cutmix_num: 1 +cutmix_prob: 0.5 +dataset: KineticSound +decay_epochs: 70 +decay_rate: 0.1 +device: 0 +dist_bn: '' +drop: 0.0 +drop_block: null +drop_connect: null +drop_path: 0.1 +encode: direct +epochs: 100 +eval: false +eval_checkpoint: '' +eval_metric: top1 +event_mix: false +event_size: 48 +fps: 1 +fusion_method: concat +gaussian_n: 3 +gp: null +hflip: 0.5 +img_size: 224 +initial_checkpoint: '' +interpolation: '' +inverse: false +inverse_ends: 100 +inverse_starts: 0 +jsd: false +kernel_method: cuda +layer_by_layer: false +local_rank: 0 +log_interval: 50 +loss_fn: ce +lr: 0.005 +lr_cycle_limit: 1 +lr_cycle_mul: 1.0 +lr_noise: null +lr_noise_pct: 0.67 +lr_noise_std: 1.0 +mean: null +mem_dist: false +meta_ratio: -1.0 +min_lr: 1.0e-05 +mix_up: false +mixup: 0.0 +mixup_mode: batch +mixup_off_epoch: 0 +mixup_prob: 0.0 +mixup_switch_prob: 0.5 +modality: audio-visual +model: AVresnet18 +model_ema: false +model_ema_decay: 0.99996 +model_ema_force_cpu: false +modulation: Normal +modulation_ends: 50 +modulation_starts: 0 +momentum: 0.9 +n_encode_type: linear +n_groups: 1 +n_preact: false +native_amp: false +newton_maxiter: 20 +no_aug: false +no_prefetcher: false +no_resume_opt: false +node_resume: '' +node_type: ReLUNode +noisy_grad: 0.0 +num_classes: 31 +num_gpu: 1 +opt: sgd +opt_betas: null +opt_eps: 1.0e-08 +output: ./exp_results +patience_epochs: 10 +pin_mem: false +power: 1 +pretrained: false +psai: 1.0 +rand_aug: false +rand_step: false +randaug_m: 15 +randaug_n: 3 +ratio: +- 0.75 +- 1.3333333333333333 +recount: 1 +recovery_interval: 0 +remode: pixel +reprob: 0.25 +requires_thres_grad: false +reset_drop: false +resplit: false +resume: '' +save_images: false +scale: +- 0.08 +- 1.0 +sched: step +seed: 2025 +sew_cnf: ADD +sigmoid_thres: false +smoothing: 0.1 +snr: -100 +snrModality: null +spike_output: false +spike_rate: false +split_bn: false +start_epoch: null +std: null +step: 1 +suffix: '' +sync_bn: false +tau: 2.0 +temporal_flatten: false +tensorboard_dir: ./exp_results +tet_loss: false +threshold: 0.5 +train_interpolation: random +train_portion: 0.9 +tsne: false +tta: 0 +use_multi_epochs_loader: false +use_video_frames: 3 +validation_batch_size_multiplier: 1 +vflip: 0.0 +visual_path: /mnt/home/hexiang/datasets/CREMA-D/ +visualize: false +warmup_epochs: 0 +warmup_lr: 1.0e-06 +weight_decay: 0.0005 +workers: 8 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-23.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-23.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..72f5420e6db6d21f40baddbc5f8686c2ed32b54d --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-23.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e37a7e4a985649da5c2ee3eb338970317ec8466040e0bc54a23d9d96e94dc97 +size 179373193 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/events.out.tfevents.1744967800.af1fd63cd999.621245.0 b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/events.out.tfevents.1744967800.af1fd63cd999.621245.0 new file mode 100644 index 0000000000000000000000000000000000000000..e05b502c904c25a399978e7957ee25930d5ed1e5 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/events.out.tfevents.1744967800.af1fd63cd999.621245.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb9b357bcaa134dee315d5ca15d71fd18777a60171fe5d1419610a751c65483 +size 12954544 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/last.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/last.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..2adb4470f78553d9a0f12b2be9fe283dfd047f3d --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/last.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0193865170edd532847252831b4bc3838d6f440ec420a24e0c0dc0fc73f4af78 +size 179373193 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/log.txt b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..8ecaeafb050cd4a60e4c7974ccbcebf1000b8e8e --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/log.txt @@ -0,0 +1,1437 @@ +2025-04-18 09:16:40,292 - train: [ INFO] - Training with a single process on 1 GPUs. +2025-04-18 09:16:44,484 - train: [ INFO] - AMP not enabled. Training in float32. +2025-04-18 09:16:44,486 - train: [ INFO] - Scheduled epochs: 100 +2025-04-18 09:16:57,411 - train: [ INFO] - Train: 0 [ 0/461 ( 0%)] Loss: 3.647504 (3.6475) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 3.1250 ( 3.1250) Acc@5: 18.7500 (18.7500) Time: 12.916s, 2.48/s (12.916s, 2.48/s) LR: 5.000e-03 Data: 6.761 (6.761) +2025-04-18 09:17:06,084 - train: [ INFO] - Train: 0 [ 50/461 ( 11%)] Loss: 3.449055 (3.5483) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 15.6250 ( 9.3750) Acc@5: 28.1250 (23.4375) Time: 0.088s, 365.05/s (0.421s, 76.08/s) LR: 5.000e-03 Data: 0.000 (0.227) +2025-04-18 09:17:21,184 - train: [ INFO] - Train: 0 [ 100/461 ( 22%)] Loss: 2.873326 (3.3233) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 15.6250 (11.4583) Acc@5: 59.3750 (35.4167) Time: 0.078s, 410.96/s (0.360s, 88.86/s) LR: 5.000e-03 Data: 0.001 (0.222) +2025-04-18 09:17:37,331 - train: [ INFO] - Train: 0 [ 150/461 ( 33%)] Loss: 2.758191 (3.1820) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 12.5000 (11.7188) Acc@5: 56.2500 (40.6250) Time: 1.038s, 30.83/s (0.347s, 92.34/s) LR: 5.000e-03 Data: 0.938 (0.226) +2025-04-18 09:17:52,115 - train: [ INFO] - Train: 0 [ 200/461 ( 43%)] Loss: 2.420187 (3.0297) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (18.1250) Acc@5: 75.0000 (47.5000) Time: 0.070s, 455.09/s (0.333s, 96.08/s) LR: 5.000e-03 Data: 0.000 (0.221) +2025-04-18 09:18:07,107 - train: [ INFO] - Train: 0 [ 250/461 ( 54%)] Loss: 2.642209 (2.9651) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (20.8333) Acc@5: 68.7500 (51.0417) Time: 0.139s, 230.66/s (0.326s, 98.12/s) LR: 5.000e-03 Data: 0.000 (0.219) +2025-04-18 09:18:41,529 - train: [ INFO] - Train: 0 [ 300/461 ( 65%)] Loss: 2.601324 (2.9131) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 25.0000 (21.4286) Acc@5: 68.7500 (53.5714) Time: 0.079s, 406.03/s (0.370s, 86.43/s) LR: 5.000e-03 Data: 0.001 (0.267) +2025-04-18 09:18:59,278 - train: [ INFO] - Train: 0 [ 350/461 ( 76%)] Loss: 2.813990 (2.9007) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 21.8750 (21.4844) Acc@5: 59.3750 (54.2969) Time: 0.071s, 451.86/s (0.367s, 87.17/s) LR: 5.000e-03 Data: 0.000 (0.267) +2025-04-18 09:19:13,410 - train: [ INFO] - Train: 0 [ 400/461 ( 87%)] Loss: 2.809765 (2.8906) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 21.8750 (21.5278) Acc@5: 62.5000 (55.2083) Time: 0.069s, 463.80/s (0.356s, 89.88/s) LR: 5.000e-03 Data: 0.000 (0.259) +2025-04-18 09:19:29,765 - train: [ INFO] - Train: 0 [ 450/461 ( 98%)] Loss: 2.635707 (2.8651) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 18.7500 (21.2500) Acc@5: 71.8750 (56.8750) Time: 0.068s, 468.79/s (0.353s, 90.72/s) LR: 5.000e-03 Data: 0.000 (0.257) +2025-04-18 09:19:31,087 - train: [ INFO] - Train: 0 [ 460/461 (100%)] Loss: 2.644091 (2.8450) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (22.7273) Acc@5: 68.7500 (57.9545) Time: 0.071s, 449.08/s (0.348s, 91.98/s) LR: 5.000e-03 Data: 0.000 (0.253) +2025-04-18 09:19:39,002 - train: [ INFO] - Eval : 0 Time: 7.749 (7.749) Loss: 2.2874 (2.2874) Acc@1: 31.2500 (31.2500)Acc@5: 65.6250 (65.6250) +2025-04-18 09:19:53,663 - train: [ INFO] - Eval : 0 Time: 0.204 (0.439) Loss: 2.6116 (2.4307) Acc@1: 31.2500 (31.3113)Acc@5: 56.2500 (66.6054) +2025-04-18 09:19:58,822 - train: [ INFO] - Eval : 0 Time: 0.017 (0.336) Loss: 4.7172 (2.4357) Acc@1: 0.0000 (30.7247)Acc@5: 0.0000 (66.2298) +2025-04-18 09:20:08,544 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-0.pth.tar', 30.724749421742484) + +2025-04-18 09:20:12,611 - train: [ INFO] - Train: 1 [ 0/461 ( 0%)] Loss: 2.399671 (2.3997) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 31.2500 (31.2500) Acc@5: 78.1250 (78.1250) Time: 4.057s, 7.89/s (4.057s, 7.89/s) LR: 5.000e-03 Data: 3.832 (3.832) +2025-04-18 09:20:19,114 - train: [ INFO] - Train: 1 [ 50/461 ( 11%)] Loss: 2.674934 (2.5373) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 28.1250 (29.6875) Acc@5: 65.6250 (71.8750) Time: 0.102s, 314.32/s (0.202s, 158.14/s) LR: 5.000e-03 Data: 0.001 (0.079) +2025-04-18 09:20:24,220 - train: [ INFO] - Train: 1 [ 100/461 ( 22%)] Loss: 2.310231 (2.4616) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (35.4167) Acc@5: 78.1250 (73.9583) Time: 0.098s, 326.65/s (0.149s, 214.92/s) LR: 5.000e-03 Data: 0.000 (0.040) +2025-04-18 09:20:29,119 - train: [ INFO] - Train: 1 [ 150/461 ( 33%)] Loss: 2.236841 (2.4054) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (35.9375) Acc@5: 75.0000 (74.2188) Time: 0.134s, 239.59/s (0.130s, 246.14/s) LR: 5.000e-03 Data: 0.001 (0.027) +2025-04-18 09:20:34,221 - train: [ INFO] - Train: 1 [ 200/461 ( 43%)] Loss: 2.108542 (2.3460) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (38.7500) Acc@5: 84.3750 (76.2500) Time: 0.156s, 205.14/s (0.122s, 262.70/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-18 09:20:39,316 - train: [ INFO] - Train: 1 [ 250/461 ( 54%)] Loss: 2.408584 (2.3565) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (38.5417) Acc@5: 87.5000 (78.1250) Time: 0.084s, 380.92/s (0.117s, 273.88/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-18 09:20:44,582 - train: [ INFO] - Train: 1 [ 300/461 ( 65%)] Loss: 2.491824 (2.3758) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 28.1250 (37.0536) Acc@5: 68.7500 (76.7857) Time: 0.089s, 361.39/s (0.114s, 280.31/s) LR: 5.000e-03 Data: 0.006 (0.014) +2025-04-18 09:20:49,806 - train: [ INFO] - Train: 1 [ 350/461 ( 76%)] Loss: 2.468395 (2.3874) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (37.8906) Acc@5: 68.7500 (75.7812) Time: 0.103s, 311.37/s (0.111s, 288.88/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-18 09:20:55,112 - train: [ INFO] - Train: 1 [ 400/461 ( 87%)] Loss: 2.434079 (2.3926) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (37.8472) Acc@5: 71.8750 (75.3472) Time: 0.075s, 426.67/s (0.109s, 292.82/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-18 09:20:59,752 - train: [ INFO] - Train: 1 [ 450/461 ( 98%)] Loss: 2.380764 (2.3914) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 31.2500 (37.1875) Acc@5: 78.1250 (75.6250) Time: 0.075s, 426.25/s (0.107s, 298.94/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 09:21:00,477 - train: [ INFO] - Train: 1 [ 460/461 (100%)] Loss: 2.150510 (2.3695) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (38.6364) Acc@5: 75.0000 (75.5682) Time: 0.070s, 456.96/s (0.106s, 301.16/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 09:21:04,839 - train: [ INFO] - Eval : 1 Time: 4.091 (4.091) Loss: 3.0597 (3.0597) Acc@1: 18.7500 (18.7500)Acc@5: 53.1250 (53.1250) +2025-04-18 09:21:07,386 - train: [ INFO] - Eval : 1 Time: 0.046 (0.130) Loss: 3.0927 (2.8159) Acc@1: 34.3750 (28.1250)Acc@5: 46.8750 (60.3554) +2025-04-18 09:21:08,483 - train: [ INFO] - Eval : 1 Time: 0.014 (0.094) Loss: 5.7347 (2.8123) Acc@1: 0.0000 (28.0648)Acc@5: 0.0000 (59.9846) +2025-04-18 09:21:16,140 - train: [ INFO] - Train: 2 [ 0/461 ( 0%)] Loss: 1.955608 (1.9556) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (53.1250) Acc@5: 87.5000 (87.5000) Time: 4.904s, 6.52/s (4.904s, 6.52/s) LR: 5.000e-03 Data: 4.777 (4.777) +2025-04-18 09:21:25,889 - train: [ INFO] - Train: 2 [ 50/461 ( 11%)] Loss: 2.377649 (2.1666) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (43.7500) Acc@5: 75.0000 (81.2500) Time: 0.078s, 408.25/s (0.198s, 161.81/s) LR: 5.000e-03 Data: 0.001 (0.100) +2025-04-18 09:21:31,433 - train: [ INFO] - Train: 2 [ 100/461 ( 22%)] Loss: 2.102131 (2.1451) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (44.7917) Acc@5: 78.1250 (80.2083) Time: 0.120s, 267.72/s (0.151s, 212.10/s) LR: 5.000e-03 Data: 0.001 (0.051) +2025-04-18 09:21:36,741 - train: [ INFO] - Train: 2 [ 150/461 ( 33%)] Loss: 2.003976 (2.1098) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (46.8750) Acc@5: 75.0000 (78.9062) Time: 0.102s, 313.27/s (0.135s, 237.28/s) LR: 5.000e-03 Data: 0.001 (0.034) +2025-04-18 09:21:42,003 - train: [ INFO] - Train: 2 [ 200/461 ( 43%)] Loss: 2.125160 (2.1129) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (45.6250) Acc@5: 78.1250 (78.7500) Time: 0.098s, 325.32/s (0.126s, 253.06/s) LR: 5.000e-03 Data: 0.001 (0.026) +2025-04-18 09:21:46,628 - train: [ INFO] - Train: 2 [ 250/461 ( 54%)] Loss: 2.156450 (2.1202) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (44.7917) Acc@5: 81.2500 (79.1667) Time: 0.075s, 423.99/s (0.119s, 269.05/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-18 09:21:51,671 - train: [ INFO] - Train: 2 [ 300/461 ( 65%)] Loss: 2.340553 (2.1516) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (44.6429) Acc@5: 78.1250 (79.0179) Time: 0.098s, 327.29/s (0.115s, 277.84/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 09:21:56,761 - train: [ INFO] - Train: 2 [ 350/461 ( 76%)] Loss: 2.233538 (2.1619) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (44.5312) Acc@5: 78.1250 (78.9062) Time: 0.121s, 265.43/s (0.112s, 284.47/s) LR: 5.000e-03 Data: 0.025 (0.016) +2025-04-18 09:22:01,814 - train: [ INFO] - Train: 2 [ 400/461 ( 87%)] Loss: 2.063716 (2.1510) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (45.1389) Acc@5: 84.3750 (79.5139) Time: 0.130s, 245.38/s (0.110s, 289.84/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-18 09:22:06,639 - train: [ INFO] - Train: 2 [ 450/461 ( 98%)] Loss: 2.117979 (2.1477) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (45.0000) Acc@5: 87.5000 (80.3125) Time: 0.087s, 367.02/s (0.108s, 295.03/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 09:22:07,372 - train: [ INFO] - Train: 2 [ 460/461 (100%)] Loss: 2.245331 (2.1566) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (44.6023) Acc@5: 84.3750 (80.6818) Time: 0.069s, 460.49/s (0.108s, 297.22/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 09:22:13,044 - train: [ INFO] - Eval : 2 Time: 5.289 (5.289) Loss: 1.7362 (1.7362) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-18 09:22:16,419 - train: [ INFO] - Eval : 2 Time: 0.022 (0.170) Loss: 2.4043 (2.0475) Acc@1: 40.6250 (41.8505)Acc@5: 71.8750 (75.1838) +2025-04-18 09:22:17,839 - train: [ INFO] - Eval : 2 Time: 0.015 (0.123) Loss: 3.6826 (2.0462) Acc@1: 0.0000 (41.1719)Acc@5: 0.0000 (74.8265) +2025-04-18 09:22:20,737 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-2.pth.tar', 41.17193523515806) + +2025-04-18 09:22:24,530 - train: [ INFO] - Train: 3 [ 0/461 ( 0%)] Loss: 2.085600 (2.0856) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (46.8750) Acc@5: 84.3750 (84.3750) Time: 3.764s, 8.50/s (3.764s, 8.50/s) LR: 5.000e-03 Data: 3.644 (3.644) +2025-04-18 09:22:32,314 - train: [ INFO] - Train: 3 [ 50/461 ( 11%)] Loss: 1.852353 (1.9690) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (53.1250) Acc@5: 84.3750 (84.3750) Time: 0.150s, 212.82/s (0.176s, 182.07/s) LR: 5.000e-03 Data: 0.001 (0.074) +2025-04-18 09:22:38,714 - train: [ INFO] - Train: 3 [ 100/461 ( 22%)] Loss: 2.137897 (2.0253) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (54.1667) Acc@5: 75.0000 (81.2500) Time: 0.068s, 467.18/s (0.138s, 231.66/s) LR: 5.000e-03 Data: 0.000 (0.038) +2025-04-18 09:22:45,128 - train: [ INFO] - Train: 3 [ 150/461 ( 33%)] Loss: 2.065635 (2.0354) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (52.3438) Acc@5: 81.2500 (81.2500) Time: 0.072s, 444.25/s (0.124s, 257.44/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-18 09:22:50,342 - train: [ INFO] - Train: 3 [ 200/461 ( 43%)] Loss: 2.282525 (2.0848) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (51.2500) Acc@5: 71.8750 (79.3750) Time: 0.072s, 445.17/s (0.118s, 270.71/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-18 09:22:55,677 - train: [ INFO] - Train: 3 [ 250/461 ( 54%)] Loss: 1.846044 (2.0450) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (52.6042) Acc@5: 90.6250 (81.2500) Time: 0.076s, 423.57/s (0.115s, 278.63/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-18 09:23:00,940 - train: [ INFO] - Train: 3 [ 300/461 ( 65%)] Loss: 1.835727 (2.0151) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (53.1250) Acc@5: 84.3750 (81.6964) Time: 0.073s, 439.95/s (0.112s, 285.35/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-18 09:23:06,184 - train: [ INFO] - Train: 3 [ 350/461 ( 76%)] Loss: 1.732286 (1.9798) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (52.3438) Acc@5: 96.8750 (83.5938) Time: 0.082s, 390.34/s (0.110s, 290.55/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-18 09:23:11,119 - train: [ INFO] - Train: 3 [ 400/461 ( 87%)] Loss: 1.723485 (1.9513) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (54.5139) Acc@5: 87.5000 (84.0278) Time: 0.106s, 302.22/s (0.108s, 296.13/s) LR: 5.000e-03 Data: 0.001 (0.010) +2025-04-18 09:23:15,847 - train: [ INFO] - Train: 3 [ 450/461 ( 98%)] Loss: 2.049324 (1.9611) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (54.0625) Acc@5: 84.3750 (84.0625) Time: 0.082s, 391.69/s (0.106s, 301.22/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-18 09:23:16,716 - train: [ INFO] - Train: 3 [ 460/461 (100%)] Loss: 2.038404 (1.9681) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (54.2614) Acc@5: 81.2500 (83.8068) Time: 0.078s, 409.05/s (0.106s, 302.57/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-18 09:23:22,106 - train: [ INFO] - Eval : 3 Time: 4.878 (4.878) Loss: 1.9121 (1.9121) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-18 09:23:25,101 - train: [ INFO] - Eval : 3 Time: 0.050 (0.154) Loss: 1.8394 (2.0166) Acc@1: 46.8750 (45.0980)Acc@5: 78.1250 (75.1838) +2025-04-18 09:23:26,652 - train: [ INFO] - Eval : 3 Time: 0.014 (0.115) Loss: 4.1252 (1.9930) Acc@1: 0.0000 (44.7957)Acc@5: 50.0000 (75.6746) +2025-04-18 09:23:29,696 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-3.pth.tar', 44.79568234387047) + +2025-04-18 09:23:34,090 - train: [ INFO] - Train: 4 [ 0/461 ( 0%)] Loss: 1.594517 (1.5945) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (78.1250) Acc@5: 93.7500 (93.7500) Time: 4.361s, 7.34/s (4.361s, 7.34/s) LR: 5.000e-03 Data: 4.206 (4.206) +2025-04-18 09:23:39,343 - train: [ INFO] - Train: 4 [ 50/461 ( 11%)] Loss: 1.939062 (1.7668) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (67.1875) Acc@5: 87.5000 (90.6250) Time: 0.077s, 413.70/s (0.182s, 175.70/s) LR: 5.000e-03 Data: 0.000 (0.084) +2025-04-18 09:23:45,559 - train: [ INFO] - Train: 4 [ 100/461 ( 22%)] Loss: 1.900476 (1.8114) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (64.5833) Acc@5: 90.6250 (90.6250) Time: 0.068s, 468.26/s (0.138s, 232.16/s) LR: 5.000e-03 Data: 0.000 (0.043) +2025-04-18 09:23:51,661 - train: [ INFO] - Train: 4 [ 150/461 ( 33%)] Loss: 2.111893 (1.8865) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (59.3750) Acc@5: 87.5000 (89.8438) Time: 0.143s, 224.24/s (0.123s, 259.74/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-18 09:23:58,221 - train: [ INFO] - Train: 4 [ 200/461 ( 43%)] Loss: 2.332139 (1.9756) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (54.3750) Acc@5: 78.1250 (87.5000) Time: 0.089s, 358.59/s (0.118s, 270.88/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-18 09:24:03,201 - train: [ INFO] - Train: 4 [ 250/461 ( 54%)] Loss: 2.055799 (1.9890) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (55.2083) Acc@5: 75.0000 (85.4167) Time: 0.078s, 407.98/s (0.114s, 280.95/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-18 09:24:08,271 - train: [ INFO] - Train: 4 [ 300/461 ( 65%)] Loss: 1.898289 (1.9760) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (55.3571) Acc@5: 87.5000 (85.7143) Time: 0.119s, 268.93/s (0.111s, 287.81/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-18 09:24:13,869 - train: [ INFO] - Train: 4 [ 350/461 ( 76%)] Loss: 2.066768 (1.9874) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (53.9062) Acc@5: 84.3750 (85.5469) Time: 0.070s, 454.71/s (0.108s, 297.49/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 09:24:23,348 - train: [ INFO] - Train: 4 [ 400/461 ( 87%)] Loss: 1.836387 (1.9706) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (55.2083) Acc@5: 81.2500 (85.0694) Time: 0.070s, 456.48/s (0.116s, 275.58/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-18 09:24:29,837 - train: [ INFO] - Train: 4 [ 450/461 ( 98%)] Loss: 2.022799 (1.9758) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (55.3125) Acc@5: 78.1250 (84.3750) Time: 0.069s, 463.52/s (0.116s, 275.31/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-18 09:24:32,488 - train: [ INFO] - Train: 4 [ 460/461 (100%)] Loss: 1.772354 (1.9573) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (55.1136) Acc@5: 90.6250 (84.9432) Time: 1.596s, 20.05/s (0.119s, 268.74/s) LR: 5.000e-03 Data: 1.527 (0.028) +2025-04-18 09:24:41,175 - train: [ INFO] - Eval : 4 Time: 8.399 (8.399) Loss: 2.3358 (2.3358) Acc@1: 31.2500 (31.2500)Acc@5: 75.0000 (75.0000) +2025-04-18 09:24:50,485 - train: [ INFO] - Eval : 4 Time: 0.262 (0.347) Loss: 2.3036 (2.2210) Acc@1: 46.8750 (38.4191)Acc@5: 75.0000 (76.8995) +2025-04-18 09:24:52,200 - train: [ INFO] - Eval : 4 Time: 0.016 (0.237) Loss: 4.7585 (2.1866) Acc@1: 0.0000 (38.8589)Acc@5: 0.0000 (76.5227) +2025-04-18 09:25:01,924 - train: [ INFO] - Train: 5 [ 0/461 ( 0%)] Loss: 1.882826 (1.8828) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (53.1250) Acc@5: 81.2500 (81.2500) Time: 6.992s, 4.58/s (6.992s, 4.58/s) LR: 5.000e-03 Data: 6.850 (6.850) +2025-04-18 09:25:08,242 - train: [ INFO] - Train: 5 [ 50/461 ( 11%)] Loss: 1.949756 (1.9163) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (56.2500) Acc@5: 81.2500 (81.2500) Time: 0.164s, 194.76/s (0.256s, 124.93/s) LR: 5.000e-03 Data: 0.001 (0.169) +2025-04-18 09:25:19,221 - train: [ INFO] - Train: 5 [ 100/461 ( 22%)] Loss: 1.823427 (1.8853) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (59.3750) Acc@5: 84.3750 (82.2917) Time: 0.156s, 204.71/s (0.217s, 147.19/s) LR: 5.000e-03 Data: 0.001 (0.129) +2025-04-18 09:25:32,447 - train: [ INFO] - Train: 5 [ 150/461 ( 33%)] Loss: 1.586264 (1.8106) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (59.3750) Acc@5: 93.7500 (85.1562) Time: 0.484s, 66.15/s (0.224s, 142.79/s) LR: 5.000e-03 Data: 0.413 (0.138) +2025-04-18 09:25:40,724 - train: [ INFO] - Train: 5 [ 200/461 ( 43%)] Loss: 1.970290 (1.8425) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (57.5000) Acc@5: 84.3750 (85.0000) Time: 0.113s, 283.34/s (0.200s, 159.82/s) LR: 5.000e-03 Data: 0.000 (0.112) +2025-04-18 09:25:47,038 - train: [ INFO] - Train: 5 [ 250/461 ( 54%)] Loss: 1.813577 (1.8377) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (58.3333) Acc@5: 84.3750 (84.8958) Time: 0.072s, 444.00/s (0.178s, 179.82/s) LR: 5.000e-03 Data: 0.001 (0.091) +2025-04-18 09:26:00,657 - train: [ INFO] - Train: 5 [ 300/461 ( 65%)] Loss: 1.885939 (1.8446) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (57.5893) Acc@5: 81.2500 (84.3750) Time: 1.254s, 25.51/s (0.188s, 170.30/s) LR: 5.000e-03 Data: 1.184 (0.102) +2025-04-18 09:26:10,009 - train: [ INFO] - Train: 5 [ 350/461 ( 76%)] Loss: 1.757159 (1.8337) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (58.2031) Acc@5: 93.7500 (85.5469) Time: 0.070s, 457.73/s (0.187s, 171.47/s) LR: 5.000e-03 Data: 0.000 (0.101) +2025-04-18 09:26:15,085 - train: [ INFO] - Train: 5 [ 400/461 ( 87%)] Loss: 1.996732 (1.8518) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (57.6389) Acc@5: 84.3750 (85.4167) Time: 0.070s, 454.16/s (0.175s, 182.59/s) LR: 5.000e-03 Data: 0.000 (0.088) +2025-04-18 09:26:19,752 - train: [ INFO] - Train: 5 [ 450/461 ( 98%)] Loss: 2.033332 (1.8699) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (57.5000) Acc@5: 75.0000 (84.3750) Time: 0.073s, 439.57/s (0.166s, 192.93/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 09:26:20,540 - train: [ INFO] - Train: 5 [ 460/461 (100%)] Loss: 1.998209 (1.8816) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (56.8182) Acc@5: 81.2500 (84.0909) Time: 0.074s, 435.08/s (0.164s, 195.19/s) LR: 5.000e-03 Data: 0.000 (0.077) +2025-04-18 09:26:26,238 - train: [ INFO] - Eval : 5 Time: 5.394 (5.394) Loss: 2.1247 (2.1247) Acc@1: 28.1250 (28.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 09:26:32,493 - train: [ INFO] - Eval : 5 Time: 0.049 (0.228) Loss: 1.8843 (1.9317) Acc@1: 53.1250 (44.3627)Acc@5: 62.5000 (77.8186) +2025-04-18 09:26:37,269 - train: [ INFO] - Eval : 5 Time: 0.015 (0.200) Loss: 3.1768 (1.9351) Acc@1: 0.0000 (44.8342)Acc@5: 50.0000 (77.3709) +2025-04-18 09:26:40,732 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-5.pth.tar', 44.83423284502698) + +2025-04-18 09:26:47,810 - train: [ INFO] - Train: 6 [ 0/461 ( 0%)] Loss: 1.927130 (1.9271) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (56.2500) Acc@5: 90.6250 (90.6250) Time: 6.955s, 4.60/s (6.955s, 4.60/s) LR: 5.000e-03 Data: 6.831 (6.831) +2025-04-18 09:27:02,922 - train: [ INFO] - Train: 6 [ 50/461 ( 11%)] Loss: 2.426864 (2.1770) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (48.4375) Acc@5: 68.7500 (79.6875) Time: 0.093s, 342.76/s (0.377s, 84.84/s) LR: 5.000e-03 Data: 0.000 (0.295) +2025-04-18 09:27:19,135 - train: [ INFO] - Train: 6 [ 100/461 ( 22%)] Loss: 1.455647 (1.9365) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (56.2500) Acc@5: 93.7500 (84.3750) Time: 0.075s, 426.42/s (0.308s, 103.75/s) LR: 5.000e-03 Data: 0.000 (0.226) +2025-04-18 09:27:36,596 - train: [ INFO] - Train: 6 [ 150/461 ( 33%)] Loss: 1.744314 (1.8885) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (58.5938) Acc@5: 93.7500 (86.7188) Time: 0.069s, 461.71/s (0.297s, 107.92/s) LR: 5.000e-03 Data: 0.000 (0.215) +2025-04-18 09:27:48,090 - train: [ INFO] - Train: 6 [ 200/461 ( 43%)] Loss: 2.089370 (1.9287) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (55.6250) Acc@5: 84.3750 (86.2500) Time: 0.073s, 436.07/s (0.263s, 121.55/s) LR: 5.000e-03 Data: 0.001 (0.181) +2025-04-18 09:28:03,394 - train: [ INFO] - Train: 6 [ 250/461 ( 54%)] Loss: 1.603654 (1.8745) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (57.2917) Acc@5: 93.7500 (87.5000) Time: 0.075s, 427.15/s (0.258s, 124.01/s) LR: 5.000e-03 Data: 0.000 (0.177) +2025-04-18 09:28:16,890 - train: [ INFO] - Train: 6 [ 300/461 ( 65%)] Loss: 2.062644 (1.9014) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (56.6964) Acc@5: 75.0000 (85.7143) Time: 0.070s, 455.67/s (0.248s, 128.77/s) LR: 5.000e-03 Data: 0.001 (0.167) +2025-04-18 09:28:32,157 - train: [ INFO] - Train: 6 [ 350/461 ( 76%)] Loss: 1.763681 (1.8842) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (57.8125) Acc@5: 87.5000 (85.9375) Time: 0.070s, 454.92/s (0.244s, 131.13/s) LR: 5.000e-03 Data: 0.000 (0.163) +2025-04-18 09:28:52,441 - train: [ INFO] - Train: 6 [ 400/461 ( 87%)] Loss: 1.470691 (1.8382) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (58.6806) Acc@5: 93.7500 (86.8056) Time: 1.829s, 17.49/s (0.253s, 126.71/s) LR: 5.000e-03 Data: 1.712 (0.171) +2025-04-18 09:28:59,960 - train: [ INFO] - Train: 6 [ 450/461 ( 98%)] Loss: 1.928178 (1.8472) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (58.7500) Acc@5: 81.2500 (86.2500) Time: 0.069s, 464.46/s (0.240s, 133.44/s) LR: 5.000e-03 Data: 0.000 (0.159) +2025-04-18 09:29:01,294 - train: [ INFO] - Train: 6 [ 460/461 (100%)] Loss: 1.594640 (1.8243) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (59.3750) Acc@5: 90.6250 (86.6477) Time: 0.068s, 473.40/s (0.237s, 134.80/s) LR: 5.000e-03 Data: 0.000 (0.157) +2025-04-18 09:29:07,868 - train: [ INFO] - Eval : 6 Time: 6.232 (6.232) Loss: 2.0451 (2.0451) Acc@1: 43.7500 (43.7500)Acc@5: 81.2500 (81.2500) +2025-04-18 09:29:23,674 - train: [ INFO] - Eval : 6 Time: 0.027 (0.432) Loss: 2.2054 (2.0588) Acc@1: 50.0000 (44.3627)Acc@5: 65.6250 (75.4289) +2025-04-18 09:29:32,185 - train: [ INFO] - Eval : 6 Time: 0.013 (0.373) Loss: 4.6397 (2.0736) Acc@1: 0.0000 (43.8705)Acc@5: 0.0000 (74.7880) +2025-04-18 09:29:45,135 - train: [ INFO] - Train: 7 [ 0/461 ( 0%)] Loss: 1.638229 (1.6382) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (56.2500) Acc@5: 96.8750 (96.8750) Time: 8.045s, 3.98/s (8.045s, 3.98/s) LR: 5.000e-03 Data: 7.939 (7.939) +2025-04-18 09:30:03,000 - train: [ INFO] - Train: 7 [ 50/461 ( 11%)] Loss: 1.747091 (1.6927) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (59.3750) Acc@5: 84.3750 (90.6250) Time: 0.087s, 369.45/s (0.399s, 80.22/s) LR: 5.000e-03 Data: 0.000 (0.319) +2025-04-18 09:30:10,747 - train: [ INFO] - Train: 7 [ 100/461 ( 22%)] Loss: 1.609111 (1.6648) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (65.6250) Acc@5: 90.6250 (90.6250) Time: 0.071s, 451.39/s (0.272s, 117.74/s) LR: 5.000e-03 Data: 0.000 (0.196) +2025-04-18 09:30:17,016 - train: [ INFO] - Train: 7 [ 150/461 ( 33%)] Loss: 1.837186 (1.7079) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (62.5000) Acc@5: 81.2500 (88.2812) Time: 0.100s, 319.99/s (0.214s, 149.37/s) LR: 5.000e-03 Data: 0.001 (0.132) +2025-04-18 09:30:23,466 - train: [ INFO] - Train: 7 [ 200/461 ( 43%)] Loss: 1.727812 (1.7119) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (63.1250) Acc@5: 90.6250 (88.7500) Time: 0.068s, 472.11/s (0.183s, 175.10/s) LR: 5.000e-03 Data: 0.000 (0.099) +2025-04-18 09:30:37,748 - train: [ INFO] - Train: 7 [ 250/461 ( 54%)] Loss: 1.540525 (1.6833) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (64.5833) Acc@5: 96.8750 (90.1042) Time: 0.070s, 458.22/s (0.199s, 160.75/s) LR: 5.000e-03 Data: 0.000 (0.117) +2025-04-18 09:30:51,278 - train: [ INFO] - Train: 7 [ 300/461 ( 65%)] Loss: 1.476496 (1.6538) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (66.5179) Acc@5: 100.0000 (91.5179) Time: 0.069s, 466.33/s (0.208s, 153.67/s) LR: 5.000e-03 Data: 0.000 (0.126) +2025-04-18 09:31:07,762 - train: [ INFO] - Train: 7 [ 350/461 ( 76%)] Loss: 1.819243 (1.6745) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (66.0156) Acc@5: 84.3750 (90.6250) Time: 0.498s, 64.25/s (0.224s, 142.68/s) LR: 5.000e-03 Data: 0.424 (0.142) +2025-04-18 09:31:24,799 - train: [ INFO] - Train: 7 [ 400/461 ( 87%)] Loss: 1.418026 (1.6460) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (67.0139) Acc@5: 100.0000 (91.6667) Time: 0.069s, 461.53/s (0.238s, 134.33/s) LR: 5.000e-03 Data: 0.000 (0.156) +2025-04-18 09:31:41,481 - train: [ INFO] - Train: 7 [ 450/461 ( 98%)] Loss: 1.566283 (1.6380) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (67.5000) Acc@5: 84.3750 (90.9375) Time: 0.072s, 445.13/s (0.248s, 129.05/s) LR: 5.000e-03 Data: 0.000 (0.166) +2025-04-18 09:31:42,560 - train: [ INFO] - Train: 7 [ 460/461 (100%)] Loss: 1.574754 (1.6323) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (66.7614) Acc@5: 90.6250 (90.9091) Time: 0.068s, 472.65/s (0.245s, 130.66/s) LR: 5.000e-03 Data: 0.000 (0.163) +2025-04-18 09:31:50,447 - train: [ INFO] - Eval : 7 Time: 7.635 (7.635) Loss: 2.0824 (2.0824) Acc@1: 37.5000 (37.5000)Acc@5: 68.7500 (68.7500) +2025-04-18 09:31:56,229 - train: [ INFO] - Eval : 7 Time: 0.021 (0.263) Loss: 2.2826 (1.9402) Acc@1: 50.0000 (45.4657)Acc@5: 68.7500 (79.0441) +2025-04-18 09:31:58,820 - train: [ INFO] - Eval : 7 Time: 0.014 (0.195) Loss: 4.8871 (1.9467) Acc@1: 0.0000 (45.4125)Acc@5: 0.0000 (78.6430) +2025-04-18 09:32:01,815 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-7.pth.tar', 45.41249036237471) + +2025-04-18 09:32:05,562 - train: [ INFO] - Train: 8 [ 0/461 ( 0%)] Loss: 1.540619 (1.5406) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (78.1250) Acc@5: 96.8750 (96.8750) Time: 3.708s, 8.63/s (3.708s, 8.63/s) LR: 5.000e-03 Data: 3.562 (3.562) +2025-04-18 09:32:18,682 - train: [ INFO] - Train: 8 [ 50/461 ( 11%)] Loss: 1.711728 (1.6262) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (76.5625) Acc@5: 81.2500 (89.0625) Time: 0.073s, 439.08/s (0.278s, 115.09/s) LR: 5.000e-03 Data: 0.000 (0.196) +2025-04-18 09:32:30,460 - train: [ INFO] - Train: 8 [ 100/461 ( 22%)] Loss: 1.340014 (1.5308) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (77.0833) Acc@5: 100.0000 (92.7083) Time: 0.074s, 434.69/s (0.238s, 134.42/s) LR: 5.000e-03 Data: 0.000 (0.158) +2025-04-18 09:32:43,167 - train: [ INFO] - Train: 8 [ 150/461 ( 33%)] Loss: 1.629284 (1.5554) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (74.2188) Acc@5: 93.7500 (92.9688) Time: 0.115s, 278.25/s (0.231s, 138.25/s) LR: 5.000e-03 Data: 0.001 (0.150) +2025-04-18 09:32:58,085 - train: [ INFO] - Train: 8 [ 200/461 ( 43%)] Loss: 1.722541 (1.5888) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (70.6250) Acc@5: 90.6250 (92.5000) Time: 0.120s, 266.54/s (0.241s, 132.52/s) LR: 5.000e-03 Data: 0.001 (0.160) +2025-04-18 09:33:04,801 - train: [ INFO] - Train: 8 [ 250/461 ( 54%)] Loss: 1.842607 (1.6311) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (67.7083) Acc@5: 87.5000 (91.6667) Time: 0.121s, 263.81/s (0.215s, 148.66/s) LR: 5.000e-03 Data: 0.001 (0.130) +2025-04-18 09:33:09,454 - train: [ INFO] - Train: 8 [ 300/461 ( 65%)] Loss: 1.670681 (1.6368) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (66.9643) Acc@5: 96.8750 (92.4107) Time: 0.078s, 412.68/s (0.194s, 164.61/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 09:33:14,940 - train: [ INFO] - Train: 8 [ 350/461 ( 76%)] Loss: 1.587022 (1.6306) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (67.9688) Acc@5: 90.6250 (92.1875) Time: 0.074s, 432.11/s (0.179s, 178.39/s) LR: 5.000e-03 Data: 0.001 (0.093) +2025-04-18 09:33:23,288 - train: [ INFO] - Train: 8 [ 400/461 ( 87%)] Loss: 2.033419 (1.6753) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (66.3194) Acc@5: 78.1250 (90.6250) Time: 0.078s, 411.22/s (0.170s, 187.81/s) LR: 5.000e-03 Data: 0.001 (0.084) +2025-04-18 09:33:39,840 - train: [ INFO] - Train: 8 [ 450/461 ( 98%)] Loss: 1.872693 (1.6951) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (65.6250) Acc@5: 90.6250 (90.6250) Time: 0.080s, 400.29/s (0.183s, 174.72/s) LR: 5.000e-03 Data: 0.000 (0.097) +2025-04-18 09:33:44,636 - train: [ INFO] - Train: 8 [ 460/461 (100%)] Loss: 1.668600 (1.6927) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (66.4773) Acc@5: 90.6250 (90.6250) Time: 0.073s, 440.02/s (0.189s, 169.32/s) LR: 5.000e-03 Data: 0.000 (0.103) +2025-04-18 09:33:51,462 - train: [ INFO] - Eval : 8 Time: 6.520 (6.520) Loss: 2.2015 (2.2015) Acc@1: 31.2500 (31.2500)Acc@5: 68.7500 (68.7500) +2025-04-18 09:34:06,881 - train: [ INFO] - Eval : 8 Time: 0.062 (0.430) Loss: 2.1994 (1.9062) Acc@1: 50.0000 (47.4265)Acc@5: 68.7500 (77.8186) +2025-04-18 09:34:13,029 - train: [ INFO] - Eval : 8 Time: 0.015 (0.343) Loss: 3.2493 (1.8838) Acc@1: 0.0000 (47.4171)Acc@5: 50.0000 (78.1804) +2025-04-18 09:34:17,539 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-8.pth.tar', 47.417116422513494) + +2025-04-18 09:34:24,536 - train: [ INFO] - Train: 9 [ 0/461 ( 0%)] Loss: 1.566545 (1.5665) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (71.8750) Acc@5: 93.7500 (93.7500) Time: 6.840s, 4.68/s (6.840s, 4.68/s) LR: 5.000e-03 Data: 6.688 (6.688) +2025-04-18 09:34:35,343 - train: [ INFO] - Train: 9 [ 50/461 ( 11%)] Loss: 1.485479 (1.5260) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (76.5625) Acc@5: 90.6250 (92.1875) Time: 0.085s, 375.16/s (0.321s, 99.73/s) LR: 5.000e-03 Data: 0.000 (0.235) +2025-04-18 09:34:50,782 - train: [ INFO] - Train: 9 [ 100/461 ( 22%)] Loss: 1.453511 (1.5018) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (73.9583) Acc@5: 100.0000 (94.7917) Time: 0.089s, 358.38/s (0.285s, 112.13/s) LR: 5.000e-03 Data: 0.000 (0.202) +2025-04-18 09:35:02,070 - train: [ INFO] - Train: 9 [ 150/461 ( 33%)] Loss: 1.484093 (1.4974) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (72.6562) Acc@5: 96.8750 (95.3125) Time: 0.070s, 459.46/s (0.249s, 128.62/s) LR: 5.000e-03 Data: 0.001 (0.160) +2025-04-18 09:35:10,147 - train: [ INFO] - Train: 9 [ 200/461 ( 43%)] Loss: 1.296739 (1.4573) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (75.0000) Acc@5: 96.8750 (95.6250) Time: 0.835s, 38.33/s (0.211s, 151.34/s) LR: 5.000e-03 Data: 0.747 (0.124) +2025-04-18 09:35:27,596 - train: [ INFO] - Train: 9 [ 250/461 ( 54%)] Loss: 1.410087 (1.4494) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (75.5208) Acc@5: 96.8750 (95.8333) Time: 0.963s, 33.22/s (0.238s, 134.51/s) LR: 5.000e-03 Data: 0.870 (0.152) +2025-04-18 09:35:38,427 - train: [ INFO] - Train: 9 [ 300/461 ( 65%)] Loss: 1.929894 (1.5180) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (71.4286) Acc@5: 93.7500 (95.5357) Time: 0.073s, 438.64/s (0.234s, 137.04/s) LR: 5.000e-03 Data: 0.001 (0.146) +2025-04-18 09:35:43,719 - train: [ INFO] - Train: 9 [ 350/461 ( 76%)] Loss: 1.422347 (1.5061) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (71.4844) Acc@5: 93.7500 (95.3125) Time: 0.120s, 265.88/s (0.215s, 149.12/s) LR: 5.000e-03 Data: 0.001 (0.125) +2025-04-18 09:35:52,936 - train: [ INFO] - Train: 9 [ 400/461 ( 87%)] Loss: 1.545712 (1.5105) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (71.5278) Acc@5: 90.6250 (94.7917) Time: 0.070s, 457.67/s (0.198s, 161.25/s) LR: 5.000e-03 Data: 0.001 (0.110) +2025-04-18 09:36:09,452 - train: [ INFO] - Train: 9 [ 450/461 ( 98%)] Loss: 1.661492 (1.5256) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (71.2500) Acc@5: 87.5000 (94.0625) Time: 0.093s, 342.35/s (0.212s, 150.74/s) LR: 5.000e-03 Data: 0.000 (0.124) +2025-04-18 09:36:12,841 - train: [ INFO] - Train: 9 [ 460/461 (100%)] Loss: 1.705517 (1.5419) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (70.7386) Acc@5: 87.5000 (93.4659) Time: 0.070s, 456.38/s (0.215s, 148.92/s) LR: 5.000e-03 Data: 0.000 (0.127) +2025-04-18 09:36:20,007 - train: [ INFO] - Eval : 9 Time: 6.847 (6.847) Loss: 2.6819 (2.6819) Acc@1: 31.2500 (31.2500)Acc@5: 71.8750 (71.8750) +2025-04-18 09:36:27,903 - train: [ INFO] - Eval : 9 Time: 0.054 (0.289) Loss: 2.2296 (2.1733) Acc@1: 53.1250 (42.8922)Acc@5: 78.1250 (73.7745) +2025-04-18 09:36:30,125 - train: [ INFO] - Eval : 9 Time: 0.017 (0.207) Loss: 3.5436 (2.1788) Acc@1: 0.0000 (43.0609)Acc@5: 50.0000 (73.5544) +2025-04-18 09:36:42,515 - train: [ INFO] - Train: 10 [ 0/461 ( 0%)] Loss: 1.549499 (1.5495) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (65.6250) Acc@5: 93.7500 (93.7500) Time: 8.350s, 3.83/s (8.350s, 3.83/s) LR: 5.000e-03 Data: 8.167 (8.167) +2025-04-18 09:36:54,216 - train: [ INFO] - Train: 10 [ 50/461 ( 11%)] Loss: 1.453685 (1.5016) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (68.7500) Acc@5: 93.7500 (93.7500) Time: 0.097s, 331.38/s (0.349s, 91.58/s) LR: 5.000e-03 Data: 0.001 (0.266) +2025-04-18 09:37:05,864 - train: [ INFO] - Train: 10 [ 100/461 ( 22%)] Loss: 1.342934 (1.4487) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (71.8750) Acc@5: 96.8750 (94.7917) Time: 0.119s, 269.14/s (0.272s, 117.45/s) LR: 5.000e-03 Data: 0.000 (0.189) +2025-04-18 09:37:12,114 - train: [ INFO] - Train: 10 [ 150/461 ( 33%)] Loss: 1.459215 (1.4513) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (71.0938) Acc@5: 96.8750 (95.3125) Time: 0.140s, 228.94/s (0.215s, 149.14/s) LR: 5.000e-03 Data: 0.000 (0.127) +2025-04-18 09:37:19,140 - train: [ INFO] - Train: 10 [ 200/461 ( 43%)] Loss: 1.466373 (1.4543) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (70.6250) Acc@5: 93.7500 (95.0000) Time: 0.100s, 319.48/s (0.184s, 173.62/s) LR: 5.000e-03 Data: 0.001 (0.096) +2025-04-18 09:37:29,803 - train: [ INFO] - Train: 10 [ 250/461 ( 54%)] Loss: 1.191453 (1.4105) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (73.4375) Acc@5: 100.0000 (95.8333) Time: 0.073s, 439.15/s (0.177s, 180.87/s) LR: 5.000e-03 Data: 0.000 (0.090) +2025-04-18 09:37:44,377 - train: [ INFO] - Train: 10 [ 300/461 ( 65%)] Loss: 1.575264 (1.4341) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (72.3214) Acc@5: 93.7500 (95.5357) Time: 0.069s, 463.29/s (0.188s, 169.82/s) LR: 5.000e-03 Data: 0.000 (0.103) +2025-04-18 09:38:01,242 - train: [ INFO] - Train: 10 [ 350/461 ( 76%)] Loss: 1.535267 (1.4467) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (72.6562) Acc@5: 93.7500 (95.3125) Time: 0.114s, 279.97/s (0.201s, 158.92/s) LR: 5.000e-03 Data: 0.000 (0.116) +2025-04-18 09:38:13,716 - train: [ INFO] - Train: 10 [ 400/461 ( 87%)] Loss: 1.367886 (1.4380) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (72.9167) Acc@5: 100.0000 (95.8333) Time: 0.073s, 439.98/s (0.204s, 157.05/s) LR: 5.000e-03 Data: 0.001 (0.118) +2025-04-18 09:38:22,509 - train: [ INFO] - Train: 10 [ 450/461 ( 98%)] Loss: 1.798386 (1.4740) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (71.5625) Acc@5: 90.6250 (95.3125) Time: 0.075s, 428.70/s (0.199s, 160.55/s) LR: 5.000e-03 Data: 0.000 (0.113) +2025-04-18 09:38:23,258 - train: [ INFO] - Train: 10 [ 460/461 (100%)] Loss: 1.521883 (1.4783) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (71.5909) Acc@5: 90.6250 (94.8864) Time: 0.068s, 469.90/s (0.197s, 162.77/s) LR: 5.000e-03 Data: 0.000 (0.110) +2025-04-18 09:38:28,928 - train: [ INFO] - Eval : 10 Time: 5.399 (5.399) Loss: 2.1008 (2.1008) Acc@1: 46.8750 (46.8750)Acc@5: 81.2500 (81.2500) +2025-04-18 09:38:43,765 - train: [ INFO] - Eval : 10 Time: 0.030 (0.397) Loss: 2.1989 (2.0112) Acc@1: 43.7500 (45.2206)Acc@5: 68.7500 (78.5539) +2025-04-18 09:38:53,075 - train: [ INFO] - Eval : 10 Time: 0.017 (0.360) Loss: 3.8303 (1.9968) Acc@1: 0.0000 (46.1064)Acc@5: 50.0000 (78.2575) +2025-04-18 09:39:01,345 - train: [ INFO] - Train: 11 [ 0/461 ( 0%)] Loss: 1.444768 (1.4448) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (71.8750) Acc@5: 96.8750 (96.8750) Time: 4.668s, 6.86/s (4.668s, 6.86/s) LR: 5.000e-03 Data: 4.553 (4.553) +2025-04-18 09:39:06,260 - train: [ INFO] - Train: 11 [ 50/461 ( 11%)] Loss: 1.328073 (1.3864) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (76.5625) Acc@5: 96.8750 (96.8750) Time: 0.103s, 309.38/s (0.183s, 174.41/s) LR: 5.000e-03 Data: 0.001 (0.090) +2025-04-18 09:39:13,018 - train: [ INFO] - Train: 11 [ 100/461 ( 22%)] Loss: 1.379016 (1.3840) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (76.0417) Acc@5: 96.8750 (96.8750) Time: 0.142s, 225.83/s (0.134s, 238.17/s) LR: 5.000e-03 Data: 0.001 (0.046) +2025-04-18 09:39:23,759 - train: [ INFO] - Train: 11 [ 150/461 ( 33%)] Loss: 1.409106 (1.3902) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (76.5625) Acc@5: 93.7500 (96.0938) Time: 0.547s, 58.54/s (0.148s, 216.74/s) LR: 5.000e-03 Data: 0.460 (0.062) +2025-04-18 09:39:38,112 - train: [ INFO] - Train: 11 [ 200/461 ( 43%)] Loss: 1.278083 (1.3678) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (76.2500) Acc@5: 96.8750 (96.2500) Time: 0.072s, 445.70/s (0.173s, 185.41/s) LR: 5.000e-03 Data: 0.000 (0.089) +2025-04-18 09:39:51,685 - train: [ INFO] - Train: 11 [ 250/461 ( 54%)] Loss: 1.220182 (1.3432) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (77.6042) Acc@5: 100.0000 (96.8750) Time: 0.104s, 308.67/s (0.186s, 172.14/s) LR: 5.000e-03 Data: 0.001 (0.102) +2025-04-18 09:40:00,849 - train: [ INFO] - Train: 11 [ 300/461 ( 65%)] Loss: 1.299987 (1.3370) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (78.5714) Acc@5: 90.6250 (95.9821) Time: 0.139s, 229.71/s (0.171s, 186.76/s) LR: 5.000e-03 Data: 0.001 (0.085) +2025-04-18 09:40:08,520 - train: [ INFO] - Train: 11 [ 350/461 ( 76%)] Loss: 1.434553 (1.3492) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (77.3438) Acc@5: 96.8750 (96.0938) Time: 0.072s, 446.60/s (0.165s, 193.60/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 09:40:13,732 - train: [ INFO] - Train: 11 [ 400/461 ( 87%)] Loss: 1.670501 (1.3849) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (76.0417) Acc@5: 90.6250 (95.4861) Time: 0.098s, 324.88/s (0.157s, 204.14/s) LR: 5.000e-03 Data: 0.001 (0.069) +2025-04-18 09:40:18,471 - train: [ INFO] - Train: 11 [ 450/461 ( 98%)] Loss: 1.393650 (1.3858) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (75.9375) Acc@5: 96.8750 (95.6250) Time: 0.069s, 461.44/s (0.149s, 214.21/s) LR: 5.000e-03 Data: 0.000 (0.062) +2025-04-18 09:40:19,297 - train: [ INFO] - Train: 11 [ 460/461 (100%)] Loss: 1.917785 (1.4342) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (73.5795) Acc@5: 90.6250 (95.1705) Time: 0.070s, 456.13/s (0.148s, 216.33/s) LR: 5.000e-03 Data: 0.000 (0.060) +2025-04-18 09:40:24,923 - train: [ INFO] - Eval : 11 Time: 5.368 (5.368) Loss: 2.4001 (2.4001) Acc@1: 37.5000 (37.5000)Acc@5: 68.7500 (68.7500) +2025-04-18 09:40:36,254 - train: [ INFO] - Eval : 11 Time: 0.238 (0.327) Loss: 2.1505 (1.8773) Acc@1: 53.1250 (46.7525)Acc@5: 65.6250 (79.1667) +2025-04-18 09:40:45,601 - train: [ INFO] - Eval : 11 Time: 0.016 (0.318) Loss: 3.1135 (1.9034) Acc@1: 0.0000 (47.1087)Acc@5: 50.0000 (78.0648) +2025-04-18 09:40:57,383 - train: [ INFO] - Train: 12 [ 0/461 ( 0%)] Loss: 1.157655 (1.1577) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (93.7500) Acc@5: 96.8750 (96.8750) Time: 7.755s, 4.13/s (7.755s, 4.13/s) LR: 5.000e-03 Data: 7.614 (7.614) +2025-04-18 09:41:09,053 - train: [ INFO] - Train: 12 [ 50/461 ( 11%)] Loss: 0.967842 (1.0627) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (95.3125) Acc@5: 100.0000 (98.4375) Time: 0.399s, 80.28/s (0.334s, 95.90/s) LR: 5.000e-03 Data: 0.277 (0.248) +2025-04-18 09:41:16,438 - train: [ INFO] - Train: 12 [ 100/461 ( 22%)] Loss: 1.092363 (1.0726) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (93.7500) Acc@5: 100.0000 (98.9583) Time: 0.070s, 454.75/s (0.228s, 140.30/s) LR: 5.000e-03 Data: 0.000 (0.137) +2025-04-18 09:41:23,491 - train: [ INFO] - Train: 12 [ 150/461 ( 33%)] Loss: 1.100168 (1.0795) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (92.1875) Acc@5: 100.0000 (99.2188) Time: 0.093s, 343.78/s (0.185s, 173.15/s) LR: 5.000e-03 Data: 0.001 (0.092) +2025-04-18 09:41:34,901 - train: [ INFO] - Train: 12 [ 200/461 ( 43%)] Loss: 0.985858 (1.0608) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (92.5000) Acc@5: 100.0000 (99.3750) Time: 0.742s, 43.13/s (0.180s, 178.09/s) LR: 5.000e-03 Data: 0.652 (0.088) +2025-04-18 09:41:44,264 - train: [ INFO] - Train: 12 [ 250/461 ( 54%)] Loss: 1.080323 (1.0640) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (92.1875) Acc@5: 96.8750 (98.9583) Time: 0.072s, 447.05/s (0.180s, 177.35/s) LR: 5.000e-03 Data: 0.000 (0.091) +2025-04-18 09:41:58,173 - train: [ INFO] - Train: 12 [ 300/461 ( 65%)] Loss: 1.057972 (1.0632) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (91.9643) Acc@5: 100.0000 (99.1071) Time: 0.805s, 39.75/s (0.194s, 165.34/s) LR: 5.000e-03 Data: 0.732 (0.105) +2025-04-18 09:42:12,571 - train: [ INFO] - Train: 12 [ 350/461 ( 76%)] Loss: 1.007929 (1.0563) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (92.1875) Acc@5: 100.0000 (99.2188) Time: 0.075s, 426.69/s (0.204s, 157.24/s) LR: 5.000e-03 Data: 0.001 (0.116) +2025-04-18 09:42:19,634 - train: [ INFO] - Train: 12 [ 400/461 ( 87%)] Loss: 1.342001 (1.0880) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (90.6250) Acc@5: 100.0000 (99.3056) Time: 0.100s, 321.39/s (0.195s, 163.98/s) LR: 5.000e-03 Data: 0.001 (0.106) +2025-04-18 09:42:24,820 - train: [ INFO] - Train: 12 [ 450/461 ( 98%)] Loss: 1.367826 (1.1160) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (90.0000) Acc@5: 93.7500 (98.7500) Time: 0.069s, 462.75/s (0.183s, 174.77/s) LR: 5.000e-03 Data: 0.000 (0.094) +2025-04-18 09:42:25,542 - train: [ INFO] - Train: 12 [ 460/461 (100%)] Loss: 1.117268 (1.1161) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (89.4886) Acc@5: 96.8750 (98.5795) Time: 0.081s, 396.33/s (0.181s, 177.11/s) LR: 5.000e-03 Data: 0.000 (0.092) +2025-04-18 09:42:34,815 - train: [ INFO] - Eval : 12 Time: 9.011 (9.011) Loss: 2.6202 (2.6202) Acc@1: 43.7500 (43.7500)Acc@5: 62.5000 (62.5000) +2025-04-18 09:42:52,353 - train: [ INFO] - Eval : 12 Time: 0.030 (0.521) Loss: 2.8381 (2.3389) Acc@1: 46.8750 (43.8113)Acc@5: 65.6250 (74.0196) +2025-04-18 09:42:57,877 - train: [ INFO] - Eval : 12 Time: 0.014 (0.391) Loss: 4.1655 (2.3359) Acc@1: 0.0000 (43.9090)Acc@5: 50.0000 (73.3616) +2025-04-18 09:43:06,349 - train: [ INFO] - Train: 13 [ 0/461 ( 0%)] Loss: 1.086743 (1.0867) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (90.6250) Acc@5: 100.0000 (100.0000) Time: 4.473s, 7.15/s (4.473s, 7.15/s) LR: 5.000e-03 Data: 4.370 (4.370) +2025-04-18 09:43:18,990 - train: [ INFO] - Train: 13 [ 50/461 ( 11%)] Loss: 1.103043 (1.0949) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (89.0625) Acc@5: 96.8750 (98.4375) Time: 0.114s, 280.81/s (0.313s, 102.38/s) LR: 5.000e-03 Data: 0.001 (0.231) +2025-04-18 09:43:25,378 - train: [ INFO] - Train: 13 [ 100/461 ( 22%)] Loss: 1.176597 (1.1221) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (88.5417) Acc@5: 96.8750 (97.9167) Time: 0.068s, 471.30/s (0.217s, 147.20/s) LR: 5.000e-03 Data: 0.000 (0.134) +2025-04-18 09:43:32,417 - train: [ INFO] - Train: 13 [ 150/461 ( 33%)] Loss: 0.957175 (1.0809) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (89.8438) Acc@5: 100.0000 (98.4375) Time: 0.086s, 372.95/s (0.176s, 181.66/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-18 09:43:45,377 - train: [ INFO] - Train: 13 [ 200/461 ( 43%)] Loss: 1.080289 (1.0808) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (90.6250) Acc@5: 96.8750 (98.1250) Time: 0.069s, 465.11/s (0.179s, 178.86/s) LR: 5.000e-03 Data: 0.000 (0.097) +2025-04-18 09:44:00,066 - train: [ INFO] - Train: 13 [ 250/461 ( 54%)] Loss: 1.086750 (1.0818) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.1458) Acc@5: 100.0000 (98.4375) Time: 0.069s, 461.98/s (0.191s, 167.75/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 09:44:11,143 - train: [ INFO] - Train: 13 [ 300/461 ( 65%)] Loss: 1.057725 (1.0783) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (91.9643) Acc@5: 100.0000 (98.6607) Time: 0.112s, 286.81/s (0.192s, 166.40/s) LR: 5.000e-03 Data: 0.000 (0.110) +2025-04-18 09:44:17,102 - train: [ INFO] - Train: 13 [ 350/461 ( 76%)] Loss: 1.141203 (1.0862) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (91.7969) Acc@5: 100.0000 (98.8281) Time: 0.097s, 330.32/s (0.179s, 178.92/s) LR: 5.000e-03 Data: 0.000 (0.095) +2025-04-18 09:44:22,996 - train: [ INFO] - Train: 13 [ 400/461 ( 87%)] Loss: 1.054344 (1.0827) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (91.6667) Acc@5: 100.0000 (98.9583) Time: 0.083s, 383.32/s (0.170s, 187.81/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-18 09:44:27,745 - train: [ INFO] - Train: 13 [ 450/461 ( 98%)] Loss: 1.042213 (1.0786) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.8750) Acc@5: 100.0000 (99.0625) Time: 0.068s, 473.07/s (0.162s, 197.96/s) LR: 5.000e-03 Data: 0.000 (0.075) +2025-04-18 09:44:28,500 - train: [ INFO] - Train: 13 [ 460/461 (100%)] Loss: 1.184262 (1.0882) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (91.1932) Acc@5: 93.7500 (98.5795) Time: 0.077s, 415.37/s (0.160s, 200.30/s) LR: 5.000e-03 Data: 0.000 (0.074) +2025-04-18 09:44:32,464 - train: [ INFO] - Eval : 13 Time: 3.708 (3.708) Loss: 2.1735 (2.1735) Acc@1: 50.0000 (50.0000)Acc@5: 68.7500 (68.7500) +2025-04-18 09:44:37,212 - train: [ INFO] - Eval : 13 Time: 0.076 (0.166) Loss: 2.2998 (2.0935) Acc@1: 46.8750 (46.2623)Acc@5: 71.8750 (74.7549) +2025-04-18 09:44:46,467 - train: [ INFO] - Eval : 13 Time: 0.014 (0.216) Loss: 4.4981 (2.0791) Acc@1: 0.0000 (46.2606)Acc@5: 0.0000 (74.9807) +2025-04-18 09:44:58,022 - train: [ INFO] - Train: 14 [ 0/461 ( 0%)] Loss: 1.023345 (1.0233) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 6.931s, 4.62/s (6.931s, 4.62/s) LR: 5.000e-03 Data: 6.826 (6.826) +2025-04-18 09:45:08,828 - train: [ INFO] - Train: 14 [ 50/461 ( 11%)] Loss: 0.835526 (0.9294) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 0.086s, 370.99/s (0.316s, 101.17/s) LR: 5.000e-03 Data: 0.000 (0.242) +2025-04-18 09:45:22,290 - train: [ INFO] - Train: 14 [ 100/461 ( 22%)] Loss: 1.111322 (0.9901) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (95.8333) Acc@5: 96.8750 (98.9583) Time: 0.075s, 429.29/s (0.258s, 124.01/s) LR: 5.000e-03 Data: 0.000 (0.183) +2025-04-18 09:45:34,013 - train: [ INFO] - Train: 14 [ 150/461 ( 33%)] Loss: 1.046382 (1.0041) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (94.5312) Acc@5: 100.0000 (99.2188) Time: 0.068s, 469.07/s (0.229s, 139.76/s) LR: 5.000e-03 Data: 0.000 (0.151) +2025-04-18 09:45:48,495 - train: [ INFO] - Train: 14 [ 200/461 ( 43%)] Loss: 0.916553 (0.9866) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (95.0000) Acc@5: 100.0000 (99.3750) Time: 0.070s, 456.75/s (0.228s, 140.64/s) LR: 5.000e-03 Data: 0.000 (0.150) +2025-04-18 09:45:59,116 - train: [ INFO] - Train: 14 [ 250/461 ( 54%)] Loss: 1.119561 (1.0088) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (93.7500) Acc@5: 96.8750 (98.9583) Time: 0.072s, 445.83/s (0.218s, 146.75/s) LR: 5.000e-03 Data: 0.000 (0.139) +2025-04-18 09:46:06,391 - train: [ INFO] - Train: 14 [ 300/461 ( 65%)] Loss: 0.867185 (0.9886) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (94.6429) Acc@5: 100.0000 (99.1071) Time: 0.070s, 454.13/s (0.203s, 157.41/s) LR: 5.000e-03 Data: 0.000 (0.123) +2025-04-18 09:46:18,061 - train: [ INFO] - Train: 14 [ 350/461 ( 76%)] Loss: 0.919202 (0.9799) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (95.3125) Acc@5: 100.0000 (99.2188) Time: 0.110s, 291.93/s (0.203s, 157.28/s) LR: 5.000e-03 Data: 0.000 (0.122) +2025-04-18 09:46:23,473 - train: [ INFO] - Train: 14 [ 400/461 ( 87%)] Loss: 0.881730 (0.9690) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (95.8333) Acc@5: 100.0000 (99.3056) Time: 0.071s, 452.72/s (0.191s, 167.60/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-18 09:46:28,350 - train: [ INFO] - Train: 14 [ 450/461 ( 98%)] Loss: 0.922504 (0.9643) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (96.2500) Acc@5: 100.0000 (99.3750) Time: 0.071s, 451.27/s (0.180s, 177.59/s) LR: 5.000e-03 Data: 0.000 (0.095) +2025-04-18 09:46:29,382 - train: [ INFO] - Train: 14 [ 460/461 (100%)] Loss: 0.948879 (0.9629) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.3068) Acc@5: 100.0000 (99.4318) Time: 0.068s, 471.70/s (0.178s, 180.00/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-18 09:46:37,828 - train: [ INFO] - Eval : 14 Time: 8.118 (8.118) Loss: 2.3325 (2.3325) Acc@1: 31.2500 (31.2500)Acc@5: 71.8750 (71.8750) +2025-04-18 09:46:50,530 - train: [ INFO] - Eval : 14 Time: 0.158 (0.408) Loss: 2.2487 (1.9656) Acc@1: 43.7500 (47.8554)Acc@5: 71.8750 (78.3701) +2025-04-18 09:46:58,556 - train: [ INFO] - Eval : 14 Time: 0.014 (0.352) Loss: 4.2543 (1.9684) Acc@1: 0.0000 (48.4965)Acc@5: 0.0000 (77.1010) +2025-04-18 09:47:02,905 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-14.pth.tar', 48.49653045489591) + +2025-04-18 09:47:10,007 - train: [ INFO] - Train: 15 [ 0/461 ( 0%)] Loss: 0.866829 (0.8668) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.019s, 4.56/s (7.019s, 4.56/s) LR: 5.000e-03 Data: 6.896 (6.896) +2025-04-18 09:47:23,582 - train: [ INFO] - Train: 15 [ 50/461 ( 11%)] Loss: 0.837171 (0.8520) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.139s, 230.62/s (0.360s, 89.01/s) LR: 5.000e-03 Data: 0.001 (0.270) +2025-04-18 09:47:36,491 - train: [ INFO] - Train: 15 [ 100/461 ( 22%)] Loss: 0.893089 (0.8657) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.9167) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.52/s (0.295s, 108.46/s) LR: 5.000e-03 Data: 0.000 (0.209) +2025-04-18 09:47:50,561 - train: [ INFO] - Train: 15 [ 150/461 ( 33%)] Loss: 0.885999 (0.8708) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.6562) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.41/s (0.266s, 120.27/s) LR: 5.000e-03 Data: 0.000 (0.182) +2025-04-18 09:47:59,031 - train: [ INFO] - Train: 15 [ 200/461 ( 43%)] Loss: 0.954825 (0.8876) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (96.8750) Acc@5: 96.8750 (99.3750) Time: 0.071s, 453.70/s (0.232s, 137.90/s) LR: 5.000e-03 Data: 0.001 (0.148) +2025-04-18 09:48:05,509 - train: [ INFO] - Train: 15 [ 250/461 ( 54%)] Loss: 0.875911 (0.8856) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (97.3958) Acc@5: 100.0000 (99.4792) Time: 0.072s, 445.83/s (0.211s, 151.81/s) LR: 5.000e-03 Data: 0.000 (0.128) +2025-04-18 09:48:12,711 - train: [ INFO] - Train: 15 [ 300/461 ( 65%)] Loss: 0.859182 (0.8819) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (97.7679) Acc@5: 100.0000 (99.5536) Time: 0.073s, 441.11/s (0.199s, 160.60/s) LR: 5.000e-03 Data: 0.000 (0.117) +2025-04-18 09:48:22,274 - train: [ INFO] - Train: 15 [ 350/461 ( 76%)] Loss: 0.895680 (0.8836) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.0469) Acc@5: 100.0000 (99.6094) Time: 0.071s, 450.68/s (0.197s, 162.81/s) LR: 5.000e-03 Data: 0.000 (0.114) +2025-04-18 09:48:29,455 - train: [ INFO] - Train: 15 [ 400/461 ( 87%)] Loss: 0.922400 (0.8879) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.9167) Acc@5: 96.8750 (99.3056) Time: 0.105s, 305.78/s (0.189s, 168.89/s) LR: 5.000e-03 Data: 0.001 (0.107) +2025-04-18 09:48:34,905 - train: [ INFO] - Train: 15 [ 450/461 ( 98%)] Loss: 0.855312 (0.8846) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.8125) Acc@5: 100.0000 (99.3750) Time: 0.070s, 457.75/s (0.180s, 177.60/s) LR: 5.000e-03 Data: 0.000 (0.096) +2025-04-18 09:48:35,628 - train: [ INFO] - Train: 15 [ 460/461 (100%)] Loss: 1.030089 (0.8979) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (97.4432) Acc@5: 100.0000 (99.4318) Time: 0.067s, 479.88/s (0.178s, 179.98/s) LR: 5.000e-03 Data: 0.000 (0.094) +2025-04-18 09:48:39,477 - train: [ INFO] - Eval : 15 Time: 3.624 (3.624) Loss: 2.2548 (2.2548) Acc@1: 34.3750 (34.3750)Acc@5: 71.8750 (71.8750) +2025-04-18 09:48:42,881 - train: [ INFO] - Eval : 15 Time: 0.051 (0.138) Loss: 2.0952 (1.9913) Acc@1: 43.7500 (46.9975)Acc@5: 68.7500 (76.8382) +2025-04-18 09:48:44,294 - train: [ INFO] - Eval : 15 Time: 0.016 (0.103) Loss: 2.6848 (2.0056) Acc@1: 0.0000 (46.7232)Acc@5: 50.0000 (76.6384) +2025-04-18 09:48:52,191 - train: [ INFO] - Train: 16 [ 0/461 ( 0%)] Loss: 0.857122 (0.8571) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.824s, 6.63/s (4.824s, 6.63/s) LR: 5.000e-03 Data: 4.698 (4.698) +2025-04-18 09:48:57,558 - train: [ INFO] - Train: 16 [ 50/461 ( 11%)] Loss: 0.817459 (0.8373) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.087s, 367.23/s (0.193s, 165.78/s) LR: 5.000e-03 Data: 0.000 (0.094) +2025-04-18 09:49:02,706 - train: [ INFO] - Train: 16 [ 100/461 ( 22%)] Loss: 0.813650 (0.8294) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 346.04/s (0.146s, 219.52/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-18 09:49:09,162 - train: [ INFO] - Train: 16 [ 150/461 ( 33%)] Loss: 0.804986 (0.8233) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 433.02/s (0.129s, 247.40/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-18 09:49:14,807 - train: [ INFO] - Train: 16 [ 200/461 ( 43%)] Loss: 0.816708 (0.8220) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 441.96/s (0.121s, 264.57/s) LR: 5.000e-03 Data: 0.001 (0.025) +2025-04-18 09:49:26,137 - train: [ INFO] - Train: 16 [ 250/461 ( 54%)] Loss: 0.880858 (0.8318) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.070s, 453.99/s (0.120s, 267.31/s) LR: 5.000e-03 Data: 0.001 (0.027) +2025-04-18 09:49:38,364 - train: [ INFO] - Train: 16 [ 300/461 ( 65%)] Loss: 0.948839 (0.8485) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.072s, 443.56/s (0.132s, 243.06/s) LR: 5.000e-03 Data: 0.001 (0.039) +2025-04-18 09:49:53,580 - train: [ INFO] - Train: 16 [ 350/461 ( 76%)] Loss: 0.788747 (0.8410) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.070s, 455.81/s (0.147s, 218.03/s) LR: 5.000e-03 Data: 0.000 (0.055) +2025-04-18 09:50:09,773 - train: [ INFO] - Train: 16 [ 400/461 ( 87%)] Loss: 0.872028 (0.8445) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.86/s (0.162s, 197.71/s) LR: 5.000e-03 Data: 0.000 (0.071) +2025-04-18 09:50:24,067 - train: [ INFO] - Train: 16 [ 450/461 ( 98%)] Loss: 0.811147 (0.8412) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (100.0000) Time: 0.107s, 299.62/s (0.170s, 188.27/s) LR: 5.000e-03 Data: 0.000 (0.081) +2025-04-18 09:50:25,756 - train: [ INFO] - Train: 16 [ 460/461 (100%)] Loss: 0.885877 (0.8452) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8636) Acc@5: 96.8750 (99.7159) Time: 0.175s, 183.22/s (0.168s, 190.18/s) LR: 5.000e-03 Data: 0.104 (0.079) +2025-04-18 09:50:36,177 - train: [ INFO] - Eval : 16 Time: 9.930 (9.930) Loss: 2.2339 (2.2339) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-18 09:50:53,668 - train: [ INFO] - Eval : 16 Time: 0.027 (0.538) Loss: 2.0370 (1.9057) Acc@1: 53.1250 (51.1029)Acc@5: 78.1250 (76.1642) +2025-04-18 09:50:59,952 - train: [ INFO] - Eval : 16 Time: 0.016 (0.411) Loss: 2.6219 (1.9178) Acc@1: 0.0000 (49.9229)Acc@5: 50.0000 (76.4071) +2025-04-18 09:51:04,152 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-16.pth.tar', 49.92289899768697) + +2025-04-18 09:51:11,698 - train: [ INFO] - Train: 17 [ 0/461 ( 0%)] Loss: 0.780277 (0.7803) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.426s, 4.31/s (7.426s, 4.31/s) LR: 5.000e-03 Data: 7.279 (7.279) +2025-04-18 09:51:27,771 - train: [ INFO] - Train: 17 [ 50/461 ( 11%)] Loss: 0.771091 (0.7757) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 403.76/s (0.375s, 85.39/s) LR: 5.000e-03 Data: 0.001 (0.295) +2025-04-18 09:51:42,349 - train: [ INFO] - Train: 17 [ 100/461 ( 22%)] Loss: 0.799150 (0.7835) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.29/s (0.299s, 106.94/s) LR: 5.000e-03 Data: 0.000 (0.221) +2025-04-18 09:51:54,072 - train: [ INFO] - Train: 17 [ 150/461 ( 33%)] Loss: 0.811192 (0.7904) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.135s, 236.98/s (0.270s, 118.53/s) LR: 5.000e-03 Data: 0.065 (0.192) +2025-04-18 09:52:07,343 - train: [ INFO] - Train: 17 [ 200/461 ( 43%)] Loss: 0.832447 (0.7988) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.111s, 288.46/s (0.264s, 121.16/s) LR: 5.000e-03 Data: 0.002 (0.186) +2025-04-18 09:52:21,976 - train: [ INFO] - Train: 17 [ 250/461 ( 54%)] Loss: 0.829425 (0.8039) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.48/s (0.261s, 122.55/s) LR: 5.000e-03 Data: 0.001 (0.182) +2025-04-18 09:52:36,249 - train: [ INFO] - Train: 17 [ 300/461 ( 65%)] Loss: 0.786410 (0.8014) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.070s, 455.77/s (0.258s, 124.15/s) LR: 5.000e-03 Data: 0.000 (0.179) +2025-04-18 09:52:50,049 - train: [ INFO] - Train: 17 [ 350/461 ( 76%)] Loss: 0.809013 (0.8024) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.068s, 467.31/s (0.257s, 124.37/s) LR: 5.000e-03 Data: 0.000 (0.178) +2025-04-18 09:53:06,161 - train: [ INFO] - Train: 17 [ 400/461 ( 87%)] Loss: 0.807393 (0.8029) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.073s, 437.70/s (0.254s, 126.00/s) LR: 5.000e-03 Data: 0.001 (0.174) +2025-04-18 09:53:26,043 - train: [ INFO] - Train: 17 [ 450/461 ( 98%)] Loss: 0.842774 (0.8069) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 100.0000 (100.0000) Time: 0.097s, 328.61/s (0.261s, 122.82/s) LR: 5.000e-03 Data: 0.000 (0.180) +2025-04-18 09:53:27,665 - train: [ INFO] - Train: 17 [ 460/461 (100%)] Loss: 0.809399 (0.8071) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (100.0000) Time: 0.078s, 412.35/s (0.257s, 124.74/s) LR: 5.000e-03 Data: 0.000 (0.176) +2025-04-18 09:53:36,491 - train: [ INFO] - Eval : 17 Time: 8.511 (8.511) Loss: 1.9052 (1.9052) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 09:53:41,856 - train: [ INFO] - Eval : 17 Time: 0.064 (0.272) Loss: 1.9568 (1.9283) Acc@1: 53.1250 (49.8162)Acc@5: 71.8750 (75.0613) +2025-04-18 09:53:43,572 - train: [ INFO] - Eval : 17 Time: 0.014 (0.190) Loss: 4.0053 (1.9287) Acc@1: 0.0000 (49.0362)Acc@5: 50.0000 (75.4433) +2025-04-18 09:53:51,911 - train: [ INFO] - Train: 18 [ 0/461 ( 0%)] Loss: 0.729010 (0.7290) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.314s, 6.02/s (5.314s, 6.02/s) LR: 5.000e-03 Data: 5.191 (5.191) +2025-04-18 09:54:04,851 - train: [ INFO] - Train: 18 [ 50/461 ( 11%)] Loss: 0.787481 (0.7582) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.352s, 23.67/s (0.312s, 102.70/s) LR: 5.000e-03 Data: 1.257 (0.232) +2025-04-18 09:54:19,784 - train: [ INFO] - Train: 18 [ 100/461 ( 22%)] Loss: 0.941926 (0.8195) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (97.9167) Acc@5: 96.8750 (98.9583) Time: 0.073s, 438.48/s (0.286s, 111.91/s) LR: 5.000e-03 Data: 0.000 (0.206) +2025-04-18 09:54:33,210 - train: [ INFO] - Train: 18 [ 150/461 ( 33%)] Loss: 0.771909 (0.8076) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.6562) Acc@5: 100.0000 (99.2188) Time: 0.316s, 101.19/s (0.265s, 120.78/s) LR: 5.000e-03 Data: 0.249 (0.184) +2025-04-18 09:54:50,083 - train: [ INFO] - Train: 18 [ 200/461 ( 43%)] Loss: 0.750010 (0.7961) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.1250) Acc@5: 100.0000 (99.3750) Time: 0.072s, 445.67/s (0.274s, 116.91/s) LR: 5.000e-03 Data: 0.000 (0.195) +2025-04-18 09:55:05,601 - train: [ INFO] - Train: 18 [ 250/461 ( 54%)] Loss: 0.788545 (0.7948) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.4792) Time: 0.069s, 462.17/s (0.270s, 118.41/s) LR: 5.000e-03 Data: 0.000 (0.191) +2025-04-18 09:55:17,688 - train: [ INFO] - Train: 18 [ 300/461 ( 65%)] Loss: 1.026471 (0.8279) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (97.3214) Acc@5: 93.7500 (98.6607) Time: 0.080s, 398.33/s (0.260s, 123.19/s) LR: 5.000e-03 Data: 0.000 (0.179) +2025-04-18 09:55:22,740 - train: [ INFO] - Train: 18 [ 350/461 ( 76%)] Loss: 0.761200 (0.8196) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (97.6562) Acc@5: 100.0000 (98.8281) Time: 0.069s, 463.39/s (0.236s, 135.38/s) LR: 5.000e-03 Data: 0.000 (0.153) +2025-04-18 09:55:32,376 - train: [ INFO] - Train: 18 [ 400/461 ( 87%)] Loss: 0.769670 (0.8140) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (97.9167) Acc@5: 100.0000 (98.9583) Time: 0.071s, 453.30/s (0.217s, 147.40/s) LR: 5.000e-03 Data: 0.000 (0.134) +2025-04-18 09:55:46,413 - train: [ INFO] - Train: 18 [ 450/461 ( 98%)] Loss: 0.734662 (0.8061) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.1250) Acc@5: 100.0000 (99.0625) Time: 0.778s, 41.15/s (0.218s, 146.49/s) LR: 5.000e-03 Data: 0.662 (0.136) +2025-04-18 09:55:48,245 - train: [ INFO] - Train: 18 [ 460/461 (100%)] Loss: 0.759225 (0.8018) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.2955) Acc@5: 100.0000 (99.1477) Time: 0.071s, 452.90/s (0.217s, 147.80/s) LR: 5.000e-03 Data: 0.000 (0.134) +2025-04-18 09:55:57,537 - train: [ INFO] - Eval : 18 Time: 8.965 (8.965) Loss: 1.8920 (1.8920) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 09:56:08,258 - train: [ INFO] - Eval : 18 Time: 0.119 (0.386) Loss: 1.7739 (1.8742) Acc@1: 59.3750 (49.8775)Acc@5: 75.0000 (76.6544) +2025-04-18 09:56:11,375 - train: [ INFO] - Eval : 18 Time: 0.014 (0.278) Loss: 3.0796 (1.8818) Acc@1: 0.0000 (49.7301)Acc@5: 50.0000 (76.4456) +2025-04-18 09:56:18,851 - train: [ INFO] - Train: 19 [ 0/461 ( 0%)] Loss: 0.761857 (0.7619) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.493s, 7.12/s (4.493s, 7.12/s) LR: 5.000e-03 Data: 4.349 (4.349) +2025-04-18 09:56:23,959 - train: [ INFO] - Train: 19 [ 50/461 ( 11%)] Loss: 0.716655 (0.7393) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 441.62/s (0.185s, 173.27/s) LR: 5.000e-03 Data: 0.000 (0.089) +2025-04-18 09:56:30,810 - train: [ INFO] - Train: 19 [ 100/461 ( 22%)] Loss: 0.744611 (0.7410) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.105s, 304.73/s (0.140s, 229.38/s) LR: 5.000e-03 Data: 0.001 (0.046) +2025-04-18 09:56:44,545 - train: [ INFO] - Train: 19 [ 150/461 ( 33%)] Loss: 0.761697 (0.7462) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.47/s (0.164s, 194.91/s) LR: 5.000e-03 Data: 0.000 (0.072) +2025-04-18 09:56:57,757 - train: [ INFO] - Train: 19 [ 200/461 ( 43%)] Loss: 0.734078 (0.7438) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 436.21/s (0.175s, 183.19/s) LR: 5.000e-03 Data: 0.001 (0.084) +2025-04-18 09:57:14,689 - train: [ INFO] - Train: 19 [ 250/461 ( 54%)] Loss: 0.745043 (0.7440) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.067s, 475.39/s (0.196s, 163.23/s) LR: 5.000e-03 Data: 0.000 (0.108) +2025-04-18 09:57:23,463 - train: [ INFO] - Train: 19 [ 300/461 ( 65%)] Loss: 0.714340 (0.7398) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.23/s (0.192s, 167.08/s) LR: 5.000e-03 Data: 0.001 (0.104) +2025-04-18 09:57:37,701 - train: [ INFO] - Train: 19 [ 350/461 ( 76%)] Loss: 0.735139 (0.7392) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 441.76/s (0.200s, 160.19/s) LR: 5.000e-03 Data: 0.001 (0.114) +2025-04-18 09:57:48,770 - train: [ INFO] - Train: 19 [ 400/461 ( 87%)] Loss: 0.775652 (0.7432) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 333.92/s (0.198s, 161.44/s) LR: 5.000e-03 Data: 0.001 (0.113) +2025-04-18 09:57:53,961 - train: [ INFO] - Train: 19 [ 450/461 ( 98%)] Loss: 0.737756 (0.7427) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 463.05/s (0.187s, 170.98/s) LR: 5.000e-03 Data: 0.000 (0.101) +2025-04-18 09:57:54,694 - train: [ INFO] - Train: 19 [ 460/461 (100%)] Loss: 0.747656 (0.7431) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 343.10/s (0.185s, 173.28/s) LR: 5.000e-03 Data: 0.000 (0.099) +2025-04-18 09:58:00,036 - train: [ INFO] - Eval : 19 Time: 5.065 (5.065) Loss: 1.9260 (1.9260) Acc@1: 53.1250 (53.1250)Acc@5: 71.8750 (71.8750) +2025-04-18 09:58:07,029 - train: [ INFO] - Eval : 19 Time: 0.053 (0.236) Loss: 1.7567 (1.8668) Acc@1: 56.2500 (50.1838)Acc@5: 75.0000 (75.7353) +2025-04-18 09:58:12,745 - train: [ INFO] - Eval : 19 Time: 0.014 (0.217) Loss: 3.7885 (1.8693) Acc@1: 0.0000 (50.6168)Acc@5: 50.0000 (76.2143) +2025-04-18 09:58:17,593 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-19.pth.tar', 50.61680801850424) + +2025-04-18 09:58:25,576 - train: [ INFO] - Train: 20 [ 0/461 ( 0%)] Loss: 0.770810 (0.7708) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.753s, 4.13/s (7.753s, 4.13/s) LR: 5.000e-03 Data: 7.609 (7.609) +2025-04-18 09:58:37,908 - train: [ INFO] - Train: 20 [ 50/461 ( 11%)] Loss: 0.724237 (0.7475) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.112s, 285.57/s (0.361s, 88.71/s) LR: 5.000e-03 Data: 0.001 (0.274) +2025-04-18 09:58:44,055 - train: [ INFO] - Train: 20 [ 100/461 ( 22%)] Loss: 0.731076 (0.7420) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.101s, 317.79/s (0.229s, 139.76/s) LR: 5.000e-03 Data: 0.000 (0.139) +2025-04-18 09:58:51,423 - train: [ INFO] - Train: 20 [ 150/461 ( 33%)] Loss: 0.822208 (0.7621) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.071s, 451.44/s (0.188s, 170.42/s) LR: 5.000e-03 Data: 0.000 (0.096) +2025-04-18 09:59:08,006 - train: [ INFO] - Train: 20 [ 200/461 ( 43%)] Loss: 0.717436 (0.7532) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.280s, 114.37/s (0.219s, 146.33/s) LR: 5.000e-03 Data: 0.211 (0.130) +2025-04-18 09:59:23,203 - train: [ INFO] - Train: 20 [ 250/461 ( 54%)] Loss: 0.766361 (0.7554) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.099s, 322.87/s (0.232s, 138.07/s) LR: 5.000e-03 Data: 0.001 (0.145) +2025-04-18 09:59:31,040 - train: [ INFO] - Train: 20 [ 300/461 ( 65%)] Loss: 0.747915 (0.7543) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.113s, 282.23/s (0.218s, 146.85/s) LR: 5.000e-03 Data: 0.001 (0.128) +2025-04-18 09:59:36,008 - train: [ INFO] - Train: 20 [ 350/461 ( 76%)] Loss: 0.719030 (0.7499) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.076s, 422.55/s (0.200s, 159.79/s) LR: 5.000e-03 Data: 0.001 (0.110) +2025-04-18 09:59:42,151 - train: [ INFO] - Train: 20 [ 400/461 ( 87%)] Loss: 0.731598 (0.7479) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.73/s (0.188s, 170.60/s) LR: 5.000e-03 Data: 0.000 (0.097) +2025-04-18 09:59:56,328 - train: [ INFO] - Train: 20 [ 450/461 ( 98%)] Loss: 0.774637 (0.7505) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.333s, 96.15/s (0.191s, 167.75/s) LR: 5.000e-03 Data: 0.258 (0.101) +2025-04-18 09:59:58,476 - train: [ INFO] - Train: 20 [ 460/461 (100%)] Loss: 0.732109 (0.7489) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.21/s (0.190s, 168.84/s) LR: 5.000e-03 Data: 0.000 (0.100) +2025-04-18 10:00:02,624 - train: [ INFO] - Eval : 20 Time: 3.910 (3.910) Loss: 2.1298 (2.1298) Acc@1: 37.5000 (37.5000)Acc@5: 75.0000 (75.0000) +2025-04-18 10:00:13,922 - train: [ INFO] - Eval : 20 Time: 0.054 (0.298) Loss: 1.8143 (1.9160) Acc@1: 53.1250 (49.3873)Acc@5: 71.8750 (77.2059) +2025-04-18 10:00:22,330 - train: [ INFO] - Eval : 20 Time: 0.016 (0.288) Loss: 3.7313 (1.9402) Acc@1: 0.0000 (48.0339)Acc@5: 50.0000 (76.6769) +2025-04-18 10:00:34,886 - train: [ INFO] - Train: 21 [ 0/461 ( 0%)] Loss: 0.733471 (0.7335) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.542s, 4.24/s (7.542s, 4.24/s) LR: 5.000e-03 Data: 7.445 (7.445) +2025-04-18 10:00:40,876 - train: [ INFO] - Train: 21 [ 50/461 ( 11%)] Loss: 0.725350 (0.7294) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.106s, 303.24/s (0.245s, 130.50/s) LR: 5.000e-03 Data: 0.001 (0.153) +2025-04-18 10:00:46,663 - train: [ INFO] - Train: 21 [ 100/461 ( 22%)] Loss: 0.726231 (0.7284) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.110s, 290.64/s (0.168s, 190.78/s) LR: 5.000e-03 Data: 0.001 (0.078) +2025-04-18 10:00:51,832 - train: [ INFO] - Train: 21 [ 150/461 ( 33%)] Loss: 0.746786 (0.7330) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.085s, 374.35/s (0.145s, 221.34/s) LR: 5.000e-03 Data: 0.000 (0.052) +2025-04-18 10:01:00,077 - train: [ INFO] - Train: 21 [ 200/461 ( 43%)] Loss: 0.737060 (0.7338) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.91/s (0.131s, 244.07/s) LR: 5.000e-03 Data: 0.000 (0.041) +2025-04-18 10:01:18,356 - train: [ INFO] - Train: 21 [ 250/461 ( 54%)] Loss: 0.726120 (0.7325) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.147s, 218.31/s (0.175s, 183.36/s) LR: 5.000e-03 Data: 0.000 (0.086) +2025-04-18 10:01:33,259 - train: [ INFO] - Train: 21 [ 300/461 ( 65%)] Loss: 0.734764 (0.7328) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 417.35/s (0.191s, 167.51/s) LR: 5.000e-03 Data: 0.000 (0.104) +2025-04-18 10:01:50,344 - train: [ INFO] - Train: 21 [ 350/461 ( 76%)] Loss: 0.750864 (0.7351) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.01/s (0.210s, 152.68/s) LR: 5.000e-03 Data: 0.000 (0.124) +2025-04-18 10:02:00,092 - train: [ INFO] - Train: 21 [ 400/461 ( 87%)] Loss: 0.797712 (0.7420) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.106s, 302.07/s (0.205s, 155.94/s) LR: 5.000e-03 Data: 0.001 (0.118) +2025-04-18 10:02:06,588 - train: [ INFO] - Train: 21 [ 450/461 ( 98%)] Loss: 0.801843 (0.7480) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.85/s (0.193s, 165.40/s) LR: 5.000e-03 Data: 0.000 (0.105) +2025-04-18 10:02:07,601 - train: [ INFO] - Train: 21 [ 460/461 (100%)] Loss: 0.730326 (0.7464) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.069s, 461.31/s (0.191s, 167.75/s) LR: 5.000e-03 Data: 0.000 (0.103) +2025-04-18 10:02:16,322 - train: [ INFO] - Eval : 21 Time: 8.428 (8.428) Loss: 2.0637 (2.0637) Acc@1: 50.0000 (50.0000)Acc@5: 65.6250 (65.6250) +2025-04-18 10:02:33,030 - train: [ INFO] - Eval : 21 Time: 0.045 (0.493) Loss: 1.8287 (1.8811) Acc@1: 50.0000 (50.0613)Acc@5: 75.0000 (76.7770) +2025-04-18 10:02:39,227 - train: [ INFO] - Eval : 21 Time: 0.014 (0.382) Loss: 3.2270 (1.8861) Acc@1: 0.0000 (49.4603)Acc@5: 50.0000 (76.4842) +2025-04-18 10:02:49,055 - train: [ INFO] - Train: 22 [ 0/461 ( 0%)] Loss: 0.725113 (0.7251) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.087s, 6.29/s (5.087s, 6.29/s) LR: 5.000e-03 Data: 4.966 (4.966) +2025-04-18 10:02:54,973 - train: [ INFO] - Train: 22 [ 50/461 ( 11%)] Loss: 0.766420 (0.7458) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 434.69/s (0.200s, 160.22/s) LR: 5.000e-03 Data: 0.001 (0.105) +2025-04-18 10:03:06,355 - train: [ INFO] - Train: 22 [ 100/461 ( 22%)] Loss: 0.720903 (0.7375) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 463.44/s (0.168s, 190.75/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 10:03:19,972 - train: [ INFO] - Train: 22 [ 150/461 ( 33%)] Loss: 0.716961 (0.7323) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.418s, 76.52/s (0.201s, 159.18/s) LR: 5.000e-03 Data: 0.318 (0.115) +2025-04-18 10:03:33,935 - train: [ INFO] - Train: 22 [ 200/461 ( 43%)] Loss: 0.792321 (0.7443) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.112s, 285.86/s (0.219s, 146.11/s) LR: 5.000e-03 Data: 0.001 (0.132) +2025-04-18 10:03:40,573 - train: [ INFO] - Train: 22 [ 250/461 ( 54%)] Loss: 0.740034 (0.7436) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.101s, 316.06/s (0.195s, 164.01/s) LR: 5.000e-03 Data: 0.000 (0.106) +2025-04-18 10:03:47,573 - train: [ INFO] - Train: 22 [ 300/461 ( 65%)] Loss: 0.740705 (0.7432) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.070s, 455.92/s (0.177s, 180.91/s) LR: 5.000e-03 Data: 0.001 (0.089) +2025-04-18 10:03:56,700 - train: [ INFO] - Train: 22 [ 350/461 ( 76%)] Loss: 0.808781 (0.7514) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.6094) Time: 0.074s, 434.11/s (0.174s, 184.10/s) LR: 5.000e-03 Data: 0.001 (0.086) +2025-04-18 10:04:14,308 - train: [ INFO] - Train: 22 [ 400/461 ( 87%)] Loss: 0.720308 (0.7479) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.071s, 453.29/s (0.194s, 164.64/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-18 10:04:28,171 - train: [ INFO] - Train: 22 [ 450/461 ( 98%)] Loss: 0.717603 (0.7449) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.123s, 260.59/s (0.200s, 160.27/s) LR: 5.000e-03 Data: 0.001 (0.112) +2025-04-18 10:04:28,909 - train: [ INFO] - Train: 22 [ 460/461 (100%)] Loss: 0.899607 (0.7590) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (98.8636) Acc@5: 96.8750 (99.4318) Time: 0.070s, 454.93/s (0.197s, 162.51/s) LR: 5.000e-03 Data: 0.000 (0.110) +2025-04-18 10:04:33,870 - train: [ INFO] - Eval : 22 Time: 4.667 (4.667) Loss: 2.0115 (2.0115) Acc@1: 37.5000 (37.5000)Acc@5: 75.0000 (75.0000) +2025-04-18 10:04:47,178 - train: [ INFO] - Eval : 22 Time: 0.024 (0.352) Loss: 1.6727 (1.8570) Acc@1: 59.3750 (50.8578)Acc@5: 84.3750 (77.6348) +2025-04-18 10:04:48,931 - train: [ INFO] - Eval : 22 Time: 0.015 (0.241) Loss: 3.3555 (1.8588) Acc@1: 0.0000 (50.8096)Acc@5: 50.0000 (77.7949) +2025-04-18 10:04:51,988 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-22.pth.tar', 50.809560524286816) + +2025-04-18 10:04:55,992 - train: [ INFO] - Train: 23 [ 0/461 ( 0%)] Loss: 0.747337 (0.7473) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 3.962s, 8.08/s (3.962s, 8.08/s) LR: 5.000e-03 Data: 3.783 (3.783) +2025-04-18 10:05:01,297 - train: [ INFO] - Train: 23 [ 50/461 ( 11%)] Loss: 0.709165 (0.7283) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 333.38/s (0.174s, 183.80/s) LR: 5.000e-03 Data: 0.000 (0.077) +2025-04-18 10:05:06,760 - train: [ INFO] - Train: 23 [ 100/461 ( 22%)] Loss: 0.722618 (0.7264) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 409.70/s (0.134s, 238.21/s) LR: 5.000e-03 Data: 0.001 (0.039) +2025-04-18 10:05:14,681 - train: [ INFO] - Train: 23 [ 150/461 ( 33%)] Loss: 0.742929 (0.7305) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.136s, 234.99/s (0.126s, 254.59/s) LR: 5.000e-03 Data: 0.058 (0.033) +2025-04-18 10:05:31,302 - train: [ INFO] - Train: 23 [ 200/461 ( 43%)] Loss: 0.731630 (0.7307) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.218s, 147.00/s (0.177s, 181.27/s) LR: 5.000e-03 Data: 0.145 (0.088) +2025-04-18 10:05:46,810 - train: [ INFO] - Train: 23 [ 250/461 ( 54%)] Loss: 0.733799 (0.7312) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.079s, 29.66/s (0.200s, 160.02/s) LR: 5.000e-03 Data: 0.985 (0.113) +2025-04-18 10:06:01,043 - train: [ INFO] - Train: 23 [ 300/461 ( 65%)] Loss: 0.758241 (0.7351) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.095s, 338.48/s (0.208s, 153.68/s) LR: 5.000e-03 Data: 0.000 (0.122) +2025-04-18 10:06:16,562 - train: [ INFO] - Train: 23 [ 350/461 ( 76%)] Loss: 0.782241 (0.7410) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.068s, 467.69/s (0.216s, 148.20/s) LR: 5.000e-03 Data: 0.000 (0.131) +2025-04-18 10:06:28,355 - train: [ INFO] - Train: 23 [ 400/461 ( 87%)] Loss: 0.726496 (0.7394) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 1.046s, 30.60/s (0.215s, 148.89/s) LR: 5.000e-03 Data: 0.916 (0.130) +2025-04-18 10:06:33,444 - train: [ INFO] - Train: 23 [ 450/461 ( 98%)] Loss: 0.715226 (0.7370) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.14/s (0.202s, 158.60/s) LR: 5.000e-03 Data: 0.000 (0.115) +2025-04-18 10:06:34,209 - train: [ INFO] - Train: 23 [ 460/461 (100%)] Loss: 0.743248 (0.7375) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.095s, 337.13/s (0.199s, 160.78/s) LR: 5.000e-03 Data: 0.000 (0.113) +2025-04-18 10:06:38,532 - train: [ INFO] - Eval : 23 Time: 4.009 (4.009) Loss: 1.9478 (1.9478) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 10:06:42,370 - train: [ INFO] - Eval : 23 Time: 0.061 (0.154) Loss: 1.6900 (1.8230) Acc@1: 56.2500 (52.2059)Acc@5: 78.1250 (77.2672) +2025-04-18 10:06:43,944 - train: [ INFO] - Eval : 23 Time: 0.014 (0.115) Loss: 3.4440 (1.8347) Acc@1: 50.0000 (51.5806)Acc@5: 50.0000 (77.4094) +2025-04-18 10:06:46,674 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-23.pth.tar', 51.58057054741712) + +2025-04-18 10:06:52,801 - train: [ INFO] - Train: 24 [ 0/461 ( 0%)] Loss: 0.731727 (0.7317) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.085s, 5.26/s (6.085s, 5.26/s) LR: 5.000e-03 Data: 5.883 (5.883) +2025-04-18 10:07:02,067 - train: [ INFO] - Train: 24 [ 50/461 ( 11%)] Loss: 0.716753 (0.7242) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 340.19/s (0.250s, 128.21/s) LR: 5.000e-03 Data: 0.001 (0.166) +2025-04-18 10:07:15,188 - train: [ INFO] - Train: 24 [ 100/461 ( 22%)] Loss: 0.730102 (0.7262) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.106s, 28.93/s (0.232s, 138.20/s) LR: 5.000e-03 Data: 0.989 (0.148) +2025-04-18 10:07:26,687 - train: [ INFO] - Train: 24 [ 150/461 ( 33%)] Loss: 0.720242 (0.7247) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.067s, 475.36/s (0.218s, 146.49/s) LR: 5.000e-03 Data: 0.000 (0.130) +2025-04-18 10:07:32,849 - train: [ INFO] - Train: 24 [ 200/461 ( 43%)] Loss: 0.734066 (0.7266) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 438.71/s (0.187s, 170.86/s) LR: 5.000e-03 Data: 0.000 (0.098) +2025-04-18 10:07:39,106 - train: [ INFO] - Train: 24 [ 250/461 ( 54%)] Loss: 0.718378 (0.7252) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.120s, 267.36/s (0.168s, 189.96/s) LR: 5.000e-03 Data: 0.001 (0.078) +2025-04-18 10:07:46,569 - train: [ INFO] - Train: 24 [ 300/461 ( 65%)] Loss: 0.719402 (0.7244) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 396.87/s (0.155s, 206.68/s) LR: 5.000e-03 Data: 0.001 (0.066) +2025-04-18 10:07:59,702 - train: [ INFO] - Train: 24 [ 350/461 ( 76%)] Loss: 0.707688 (0.7223) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.60/s (0.162s, 198.01/s) LR: 5.000e-03 Data: 0.001 (0.073) +2025-04-18 10:08:13,152 - train: [ INFO] - Train: 24 [ 400/461 ( 87%)] Loss: 0.751706 (0.7256) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.108s, 295.94/s (0.172s, 185.87/s) LR: 5.000e-03 Data: 0.001 (0.084) +2025-04-18 10:08:21,477 - train: [ INFO] - Train: 24 [ 450/461 ( 98%)] Loss: 0.705378 (0.7235) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 471.52/s (0.169s, 189.19/s) LR: 5.000e-03 Data: 0.000 (0.082) +2025-04-18 10:08:25,386 - train: [ INFO] - Train: 24 [ 460/461 (100%)] Loss: 0.723230 (0.7235) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 473.65/s (0.173s, 184.44/s) LR: 5.000e-03 Data: 0.000 (0.087) +2025-04-18 10:08:34,334 - train: [ INFO] - Eval : 24 Time: 8.549 (8.549) Loss: 2.0482 (2.0482) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 10:08:49,800 - train: [ INFO] - Eval : 24 Time: 0.055 (0.471) Loss: 1.7808 (1.8564) Acc@1: 59.3750 (51.4706)Acc@5: 78.1250 (76.2255) +2025-04-18 10:08:53,531 - train: [ INFO] - Eval : 24 Time: 0.377 (0.336) Loss: 3.0334 (1.8571) Acc@1: 0.0000 (50.8481)Acc@5: 50.0000 (76.5998) +2025-04-18 10:09:04,774 - train: [ INFO] - Train: 25 [ 0/461 ( 0%)] Loss: 0.767612 (0.7676) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.582s, 4.22/s (7.582s, 4.22/s) LR: 5.000e-03 Data: 7.429 (7.429) +2025-04-18 10:09:12,376 - train: [ INFO] - Train: 25 [ 50/461 ( 11%)] Loss: 0.716984 (0.7423) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.45/s (0.270s, 118.70/s) LR: 5.000e-03 Data: 0.000 (0.173) +2025-04-18 10:09:17,432 - train: [ INFO] - Train: 25 [ 100/461 ( 22%)] Loss: 0.696348 (0.7270) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.105s, 304.90/s (0.184s, 174.11/s) LR: 5.000e-03 Data: 0.001 (0.088) +2025-04-18 10:09:22,761 - train: [ INFO] - Train: 25 [ 150/461 ( 33%)] Loss: 0.715669 (0.7242) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 436.92/s (0.155s, 206.19/s) LR: 5.000e-03 Data: 0.001 (0.059) +2025-04-18 10:09:28,707 - train: [ INFO] - Train: 25 [ 200/461 ( 43%)] Loss: 0.706804 (0.7207) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.087s, 368.15/s (0.139s, 230.07/s) LR: 5.000e-03 Data: 0.001 (0.045) +2025-04-18 10:09:41,934 - train: [ INFO] - Train: 25 [ 250/461 ( 54%)] Loss: 0.806486 (0.7350) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.643s, 49.74/s (0.155s, 206.11/s) LR: 5.000e-03 Data: 0.571 (0.064) +2025-04-18 10:09:57,299 - train: [ INFO] - Train: 25 [ 300/461 ( 65%)] Loss: 0.719213 (0.7327) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.073s, 436.83/s (0.176s, 182.14/s) LR: 5.000e-03 Data: 0.000 (0.087) +2025-04-18 10:10:11,872 - train: [ INFO] - Train: 25 [ 350/461 ( 76%)] Loss: 0.746445 (0.7344) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.47/s (0.183s, 174.54/s) LR: 5.000e-03 Data: 0.001 (0.095) +2025-04-18 10:10:20,391 - train: [ INFO] - Train: 25 [ 400/461 ( 87%)] Loss: 0.712450 (0.7320) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.112s, 286.06/s (0.177s, 181.02/s) LR: 5.000e-03 Data: 0.001 (0.087) +2025-04-18 10:10:28,423 - train: [ INFO] - Train: 25 [ 450/461 ( 98%)] Loss: 0.719885 (0.7308) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.070s, 457.74/s (0.166s, 192.40/s) LR: 5.000e-03 Data: 0.000 (0.077) +2025-04-18 10:10:30,114 - train: [ INFO] - Train: 25 [ 460/461 (100%)] Loss: 0.703094 (0.7283) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.075s, 424.63/s (0.164s, 194.66/s) LR: 5.000e-03 Data: 0.000 (0.076) +2025-04-18 10:10:37,553 - train: [ INFO] - Eval : 25 Time: 7.164 (7.164) Loss: 2.0210 (2.0210) Acc@1: 46.8750 (46.8750)Acc@5: 68.7500 (68.7500) +2025-04-18 10:10:47,669 - train: [ INFO] - Eval : 25 Time: 0.234 (0.338) Loss: 1.8054 (1.8913) Acc@1: 53.1250 (50.5515)Acc@5: 78.1250 (76.2255) +2025-04-18 10:10:52,278 - train: [ INFO] - Eval : 25 Time: 0.015 (0.267) Loss: 2.6926 (1.9045) Acc@1: 0.0000 (50.0000)Acc@5: 50.0000 (76.0216) +2025-04-18 10:11:02,891 - train: [ INFO] - Train: 26 [ 0/461 ( 0%)] Loss: 0.796374 (0.7964) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 4.267s, 7.50/s (4.267s, 7.50/s) LR: 5.000e-03 Data: 4.133 (4.133) +2025-04-18 10:11:12,661 - train: [ INFO] - Train: 26 [ 50/461 ( 11%)] Loss: 0.708417 (0.7524) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.105s, 303.77/s (0.190s, 168.16/s) LR: 5.000e-03 Data: 0.001 (0.098) +2025-04-18 10:11:24,934 - train: [ INFO] - Train: 26 [ 100/461 ( 22%)] Loss: 0.725525 (0.7434) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.072s, 444.22/s (0.203s, 157.53/s) LR: 5.000e-03 Data: 0.000 (0.115) +2025-04-18 10:11:37,584 - train: [ INFO] - Train: 26 [ 150/461 ( 33%)] Loss: 0.722701 (0.7383) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.071s, 452.16/s (0.206s, 155.57/s) LR: 5.000e-03 Data: 0.000 (0.120) +2025-04-18 10:11:52,471 - train: [ INFO] - Train: 26 [ 200/461 ( 43%)] Loss: 0.711100 (0.7328) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.095s, 338.13/s (0.214s, 149.85/s) LR: 5.000e-03 Data: 0.001 (0.130) +2025-04-18 10:12:00,517 - train: [ INFO] - Train: 26 [ 250/461 ( 54%)] Loss: 0.719975 (0.7307) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.170s, 188.73/s (0.196s, 163.23/s) LR: 5.000e-03 Data: 0.001 (0.112) +2025-04-18 10:12:08,370 - train: [ INFO] - Train: 26 [ 300/461 ( 65%)] Loss: 0.735705 (0.7314) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.068s, 472.03/s (0.185s, 173.19/s) LR: 5.000e-03 Data: 0.000 (0.098) +2025-04-18 10:12:13,897 - train: [ INFO] - Train: 26 [ 350/461 ( 76%)] Loss: 0.712987 (0.7291) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.083s, 383.32/s (0.173s, 184.45/s) LR: 5.000e-03 Data: 0.001 (0.084) +2025-04-18 10:12:21,748 - train: [ INFO] - Train: 26 [ 400/461 ( 87%)] Loss: 0.722565 (0.7284) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.607s, 52.71/s (0.164s, 195.21/s) LR: 5.000e-03 Data: 0.535 (0.075) +2025-04-18 10:12:38,030 - train: [ INFO] - Train: 26 [ 450/461 ( 98%)] Loss: 0.711495 (0.7267) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 1.118s, 28.62/s (0.180s, 177.30/s) LR: 5.000e-03 Data: 1.045 (0.092) +2025-04-18 10:12:40,122 - train: [ INFO] - Train: 26 [ 460/461 (100%)] Loss: 0.707185 (0.7249) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.074s, 430.27/s (0.181s, 176.83/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-18 10:12:46,909 - train: [ INFO] - Eval : 26 Time: 6.404 (6.404) Loss: 1.8675 (1.8675) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-18 10:12:56,387 - train: [ INFO] - Eval : 26 Time: 0.136 (0.311) Loss: 1.8200 (1.9238) Acc@1: 56.2500 (48.8358)Acc@5: 75.0000 (75.8578) +2025-04-18 10:12:58,784 - train: [ INFO] - Eval : 26 Time: 0.021 (0.223) Loss: 2.5079 (1.9350) Acc@1: 50.0000 (48.2652)Acc@5: 50.0000 (75.5975) +2025-04-18 10:13:09,737 - train: [ INFO] - Train: 27 [ 0/461 ( 0%)] Loss: 0.708566 (0.7086) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.411s, 4.32/s (7.411s, 4.32/s) LR: 5.000e-03 Data: 7.311 (7.311) +2025-04-18 10:13:17,493 - train: [ INFO] - Train: 27 [ 50/461 ( 11%)] Loss: 0.701707 (0.7051) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.64/s (0.254s, 125.74/s) LR: 5.000e-03 Data: 0.000 (0.172) +2025-04-18 10:13:30,736 - train: [ INFO] - Train: 27 [ 100/461 ( 22%)] Loss: 0.712077 (0.7075) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 438.52/s (0.233s, 137.15/s) LR: 5.000e-03 Data: 0.001 (0.154) +2025-04-18 10:13:46,256 - train: [ INFO] - Train: 27 [ 150/461 ( 33%)] Loss: 0.761827 (0.7210) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 466.51/s (0.242s, 132.18/s) LR: 5.000e-03 Data: 0.000 (0.164) +2025-04-18 10:13:56,384 - train: [ INFO] - Train: 27 [ 200/461 ( 43%)] Loss: 0.705036 (0.7178) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.86/s (0.219s, 145.87/s) LR: 5.000e-03 Data: 0.000 (0.140) +2025-04-18 10:14:04,612 - train: [ INFO] - Train: 27 [ 250/461 ( 54%)] Loss: 0.708802 (0.7163) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.101s, 316.98/s (0.206s, 155.06/s) LR: 5.000e-03 Data: 0.001 (0.124) +2025-04-18 10:14:11,913 - train: [ INFO] - Train: 27 [ 300/461 ( 65%)] Loss: 0.698497 (0.7138) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 461.73/s (0.186s, 172.02/s) LR: 5.000e-03 Data: 0.000 (0.103) +2025-04-18 10:14:25,980 - train: [ INFO] - Train: 27 [ 350/461 ( 76%)] Loss: 0.730309 (0.7159) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.216s, 148.43/s (0.187s, 170.77/s) LR: 5.000e-03 Data: 0.001 (0.104) +2025-04-18 10:14:40,447 - train: [ INFO] - Train: 27 [ 400/461 ( 87%)] Loss: 0.716995 (0.7160) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.797s, 17.81/s (0.197s, 162.84/s) LR: 5.000e-03 Data: 1.702 (0.114) +2025-04-18 10:14:50,046 - train: [ INFO] - Train: 27 [ 450/461 ( 98%)] Loss: 0.741269 (0.7185) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.57/s (0.193s, 166.04/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 10:14:50,755 - train: [ INFO] - Train: 27 [ 460/461 (100%)] Loss: 0.702813 (0.7171) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 465.42/s (0.190s, 168.37/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-18 10:14:59,315 - train: [ INFO] - Eval : 27 Time: 8.169 (8.169) Loss: 1.9614 (1.9614) Acc@1: 53.1250 (53.1250)Acc@5: 68.7500 (68.7500) +2025-04-18 10:15:10,312 - train: [ INFO] - Eval : 27 Time: 0.065 (0.376) Loss: 1.9416 (1.8884) Acc@1: 56.2500 (51.3480)Acc@5: 71.8750 (75.5515) +2025-04-18 10:15:16,298 - train: [ INFO] - Eval : 27 Time: 0.019 (0.307) Loss: 3.0858 (1.8987) Acc@1: 0.0000 (50.8096)Acc@5: 50.0000 (75.5590) +2025-04-18 10:15:25,813 - train: [ INFO] - Train: 28 [ 0/461 ( 0%)] Loss: 0.726455 (0.7265) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.197s, 6.16/s (5.197s, 6.16/s) LR: 5.000e-03 Data: 5.061 (5.061) +2025-04-18 10:15:35,574 - train: [ INFO] - Train: 28 [ 50/461 ( 11%)] Loss: 0.764160 (0.7453) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.123s, 261.13/s (0.246s, 129.84/s) LR: 5.000e-03 Data: 0.001 (0.158) +2025-04-18 10:15:41,465 - train: [ INFO] - Train: 28 [ 100/461 ( 22%)] Loss: 0.756531 (0.7490) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.9167) Acc@5: 100.0000 (100.0000) Time: 0.105s, 305.15/s (0.169s, 189.47/s) LR: 5.000e-03 Data: 0.002 (0.081) +2025-04-18 10:15:52,009 - train: [ INFO] - Train: 28 [ 150/461 ( 33%)] Loss: 0.703479 (0.7377) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.086s, 370.63/s (0.168s, 190.17/s) LR: 5.000e-03 Data: 0.000 (0.083) +2025-04-18 10:16:04,165 - train: [ INFO] - Train: 28 [ 200/461 ( 43%)] Loss: 0.738674 (0.7379) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.069s, 465.50/s (0.180s, 178.14/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-18 10:16:09,820 - train: [ INFO] - Train: 28 [ 250/461 ( 54%)] Loss: 0.702306 (0.7319) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.090s, 354.29/s (0.163s, 196.63/s) LR: 5.000e-03 Data: 0.001 (0.075) +2025-04-18 10:16:15,869 - train: [ INFO] - Train: 28 [ 300/461 ( 65%)] Loss: 0.741767 (0.7333) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.084s, 381.68/s (0.151s, 212.24/s) LR: 5.000e-03 Data: 0.000 (0.062) +2025-04-18 10:16:25,048 - train: [ INFO] - Train: 28 [ 350/461 ( 76%)] Loss: 0.700283 (0.7292) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.461s, 69.44/s (0.146s, 218.97/s) LR: 5.000e-03 Data: 0.389 (0.059) +2025-04-18 10:16:41,512 - train: [ INFO] - Train: 28 [ 400/461 ( 87%)] Loss: 0.709672 (0.7270) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.080s, 397.62/s (0.166s, 193.04/s) LR: 5.000e-03 Data: 0.001 (0.079) +2025-04-18 10:16:57,602 - train: [ INFO] - Train: 28 [ 450/461 ( 98%)] Loss: 0.732672 (0.7276) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.760s, 42.12/s (0.181s, 176.59/s) LR: 5.000e-03 Data: 0.691 (0.095) +2025-04-18 10:17:00,859 - train: [ INFO] - Train: 28 [ 460/461 (100%)] Loss: 0.718270 (0.7268) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.368s, 86.98/s (0.184s, 173.87/s) LR: 5.000e-03 Data: 0.286 (0.098) +2025-04-18 10:17:08,424 - train: [ INFO] - Eval : 28 Time: 7.213 (7.213) Loss: 1.9735 (1.9735) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-18 10:17:18,135 - train: [ INFO] - Eval : 28 Time: 0.032 (0.332) Loss: 1.8585 (1.9316) Acc@1: 46.8750 (48.8971)Acc@5: 75.0000 (74.5711) +2025-04-18 10:17:19,741 - train: [ INFO] - Eval : 28 Time: 0.020 (0.226) Loss: 2.7214 (1.9323) Acc@1: 50.0000 (48.9977)Acc@5: 50.0000 (74.4025) +2025-04-18 10:17:30,359 - train: [ INFO] - Train: 29 [ 0/461 ( 0%)] Loss: 0.710600 (0.7106) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.891s, 5.43/s (5.891s, 5.43/s) LR: 5.000e-03 Data: 5.762 (5.762) +2025-04-18 10:17:44,326 - train: [ INFO] - Train: 29 [ 50/461 ( 11%)] Loss: 0.705642 (0.7081) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.086s, 372.85/s (0.341s, 93.92/s) LR: 5.000e-03 Data: 0.001 (0.254) +2025-04-18 10:17:57,745 - train: [ INFO] - Train: 29 [ 100/461 ( 22%)] Loss: 0.791052 (0.7358) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.070s, 456.45/s (0.268s, 119.44/s) LR: 5.000e-03 Data: 0.001 (0.183) +2025-04-18 10:18:05,489 - train: [ INFO] - Train: 29 [ 150/461 ( 33%)] Loss: 0.733485 (0.7352) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.071s, 449.56/s (0.228s, 140.33/s) LR: 5.000e-03 Data: 0.000 (0.143) +2025-04-18 10:18:11,080 - train: [ INFO] - Train: 29 [ 200/461 ( 43%)] Loss: 0.704397 (0.7290) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.105s, 305.96/s (0.198s, 161.76/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-18 10:18:17,782 - train: [ INFO] - Train: 29 [ 250/461 ( 54%)] Loss: 0.790802 (0.7393) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.073s, 437.43/s (0.177s, 180.52/s) LR: 5.000e-03 Data: 0.001 (0.086) +2025-04-18 10:18:27,010 - train: [ INFO] - Train: 29 [ 300/461 ( 65%)] Loss: 0.702981 (0.7341) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.1071) Time: 0.071s, 450.90/s (0.169s, 189.85/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 10:18:43,411 - train: [ INFO] - Train: 29 [ 350/461 ( 76%)] Loss: 0.783713 (0.7403) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8281) Acc@5: 100.0000 (99.2188) Time: 0.071s, 452.93/s (0.185s, 172.52/s) LR: 5.000e-03 Data: 0.001 (0.097) +2025-04-18 10:18:54,906 - train: [ INFO] - Train: 29 [ 400/461 ( 87%)] Loss: 0.709185 (0.7369) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.3056) Time: 0.068s, 467.42/s (0.190s, 168.31/s) LR: 5.000e-03 Data: 0.000 (0.103) +2025-04-18 10:19:07,161 - train: [ INFO] - Train: 29 [ 450/461 ( 98%)] Loss: 0.708373 (0.7340) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.3750) Time: 0.100s, 318.43/s (0.195s, 164.07/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 10:19:09,857 - train: [ INFO] - Train: 29 [ 460/461 (100%)] Loss: 0.698321 (0.7308) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.4318) Time: 0.071s, 448.33/s (0.197s, 162.79/s) LR: 5.000e-03 Data: 0.000 (0.111) +2025-04-18 10:19:18,148 - train: [ INFO] - Eval : 29 Time: 8.013 (8.013) Loss: 2.0857 (2.0857) Acc@1: 46.8750 (46.8750)Acc@5: 65.6250 (65.6250) +2025-04-18 10:19:26,004 - train: [ INFO] - Eval : 29 Time: 0.022 (0.311) Loss: 1.7930 (1.9094) Acc@1: 59.3750 (50.7966)Acc@5: 75.0000 (75.5515) +2025-04-18 10:19:28,000 - train: [ INFO] - Eval : 29 Time: 0.022 (0.218) Loss: 2.4158 (1.9070) Acc@1: 0.0000 (50.7325)Acc@5: 50.0000 (75.1735) +2025-04-18 10:19:35,734 - train: [ INFO] - Train: 30 [ 0/461 ( 0%)] Loss: 0.710745 (0.7107) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.538s, 7.05/s (4.538s, 7.05/s) LR: 5.000e-03 Data: 4.400 (4.400) +2025-04-18 10:19:50,411 - train: [ INFO] - Train: 30 [ 50/461 ( 11%)] Loss: 0.693787 (0.7023) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 442.89/s (0.282s, 113.54/s) LR: 5.000e-03 Data: 0.000 (0.199) +2025-04-18 10:20:03,459 - train: [ INFO] - Train: 30 [ 100/461 ( 22%)] Loss: 0.698840 (0.7011) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 449.09/s (0.250s, 127.89/s) LR: 5.000e-03 Data: 0.001 (0.171) +2025-04-18 10:20:18,365 - train: [ INFO] - Train: 30 [ 150/461 ( 33%)] Loss: 0.706295 (0.7024) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 424.32/s (0.245s, 130.65/s) LR: 5.000e-03 Data: 0.001 (0.167) +2025-04-18 10:20:32,188 - train: [ INFO] - Train: 30 [ 200/461 ( 43%)] Loss: 0.702452 (0.7024) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.80/s (0.242s, 132.50/s) LR: 5.000e-03 Data: 0.000 (0.163) +2025-04-18 10:20:39,130 - train: [ INFO] - Train: 30 [ 250/461 ( 54%)] Loss: 0.757677 (0.7116) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.133s, 241.15/s (0.212s, 150.70/s) LR: 5.000e-03 Data: 0.001 (0.131) +2025-04-18 10:20:44,628 - train: [ INFO] - Train: 30 [ 300/461 ( 65%)] Loss: 0.759557 (0.7185) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.069s, 462.22/s (0.194s, 164.85/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 10:20:51,156 - train: [ INFO] - Train: 30 [ 350/461 ( 76%)] Loss: 0.721170 (0.7188) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.093s, 345.02/s (0.180s, 177.40/s) LR: 5.000e-03 Data: 0.001 (0.094) +2025-04-18 10:21:01,462 - train: [ INFO] - Train: 30 [ 400/461 ( 87%)] Loss: 0.703224 (0.7171) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.730s, 43.84/s (0.173s, 185.00/s) LR: 5.000e-03 Data: 0.657 (0.087) +2025-04-18 10:21:12,609 - train: [ INFO] - Train: 30 [ 450/461 ( 98%)] Loss: 0.702866 (0.7157) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.079s, 405.08/s (0.176s, 181.75/s) LR: 5.000e-03 Data: 0.000 (0.091) +2025-04-18 10:21:15,761 - train: [ INFO] - Train: 30 [ 460/461 (100%)] Loss: 0.800920 (0.7234) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4318) Acc@5: 96.8750 (99.7159) Time: 0.631s, 50.74/s (0.179s, 179.06/s) LR: 5.000e-03 Data: 0.559 (0.094) +2025-04-18 10:21:23,909 - train: [ INFO] - Eval : 30 Time: 7.837 (7.837) Loss: 1.8956 (1.8956) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 10:21:40,713 - train: [ INFO] - Eval : 30 Time: 0.028 (0.483) Loss: 1.7248 (1.8925) Acc@1: 59.3750 (51.5931)Acc@5: 81.2500 (75.8578) +2025-04-18 10:21:46,971 - train: [ INFO] - Eval : 30 Time: 0.017 (0.377) Loss: 2.6404 (1.8933) Acc@1: 50.0000 (51.0023)Acc@5: 50.0000 (76.3300) +2025-04-18 10:21:53,590 - train: [ INFO] - Train: 31 [ 0/461 ( 0%)] Loss: 0.695651 (0.6957) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 3.491s, 9.17/s (3.491s, 9.17/s) LR: 5.000e-03 Data: 3.356 (3.356) +2025-04-18 10:22:00,569 - train: [ INFO] - Train: 31 [ 50/461 ( 11%)] Loss: 0.694944 (0.6953) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.41/s (0.154s, 207.14/s) LR: 5.000e-03 Data: 0.000 (0.066) +2025-04-18 10:22:13,189 - train: [ INFO] - Train: 31 [ 100/461 ( 22%)] Loss: 0.723133 (0.7046) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 466.78/s (0.173s, 185.10/s) LR: 5.000e-03 Data: 0.000 (0.087) +2025-04-18 10:22:24,317 - train: [ INFO] - Train: 31 [ 150/461 ( 33%)] Loss: 0.731977 (0.7114) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.091s, 353.50/s (0.182s, 175.59/s) LR: 5.000e-03 Data: 0.000 (0.097) +2025-04-18 10:22:40,160 - train: [ INFO] - Train: 31 [ 200/461 ( 43%)] Loss: 0.701207 (0.7094) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.164s, 195.39/s (0.205s, 156.04/s) LR: 5.000e-03 Data: 0.000 (0.120) +2025-04-18 10:22:46,423 - train: [ INFO] - Train: 31 [ 250/461 ( 54%)] Loss: 0.713492 (0.7101) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 402.60/s (0.183s, 174.61/s) LR: 5.000e-03 Data: 0.001 (0.097) +2025-04-18 10:22:52,029 - train: [ INFO] - Train: 31 [ 300/461 ( 65%)] Loss: 0.743506 (0.7148) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 447.46/s (0.171s, 187.43/s) LR: 5.000e-03 Data: 0.000 (0.081) +2025-04-18 10:22:58,354 - train: [ INFO] - Train: 31 [ 350/461 ( 76%)] Loss: 0.701342 (0.7132) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.18/s (0.159s, 200.88/s) LR: 5.000e-03 Data: 0.000 (0.070) +2025-04-18 10:23:05,800 - train: [ INFO] - Train: 31 [ 400/461 ( 87%)] Loss: 0.732112 (0.7153) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.71/s (0.151s, 211.52/s) LR: 5.000e-03 Data: 0.000 (0.061) +2025-04-18 10:23:18,196 - train: [ INFO] - Train: 31 [ 450/461 ( 98%)] Loss: 0.688596 (0.7126) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 472.63/s (0.157s, 204.29/s) LR: 5.000e-03 Data: 0.000 (0.068) +2025-04-18 10:23:21,628 - train: [ INFO] - Train: 31 [ 460/461 (100%)] Loss: 0.707852 (0.7122) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 432.15/s (0.160s, 199.41/s) LR: 5.000e-03 Data: 0.004 (0.072) +2025-04-18 10:23:30,858 - train: [ INFO] - Eval : 31 Time: 8.942 (8.942) Loss: 1.8791 (1.8791) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 10:23:44,175 - train: [ INFO] - Eval : 31 Time: 0.261 (0.436) Loss: 1.8831 (1.9013) Acc@1: 50.0000 (51.2255)Acc@5: 71.8750 (76.3480) +2025-04-18 10:23:52,153 - train: [ INFO] - Eval : 31 Time: 0.014 (0.369) Loss: 2.7927 (1.9132) Acc@1: 50.0000 (50.3084)Acc@5: 50.0000 (75.8674) +2025-04-18 10:24:01,469 - train: [ INFO] - Train: 32 [ 0/461 ( 0%)] Loss: 0.729413 (0.7294) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.837s, 5.48/s (5.837s, 5.48/s) LR: 5.000e-03 Data: 5.691 (5.691) +2025-04-18 10:24:14,817 - train: [ INFO] - Train: 32 [ 50/461 ( 11%)] Loss: 0.701050 (0.7152) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 396.85/s (0.312s, 102.43/s) LR: 5.000e-03 Data: 0.000 (0.226) +2025-04-18 10:24:29,238 - train: [ INFO] - Train: 32 [ 100/461 ( 22%)] Loss: 0.710947 (0.7138) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 465.20/s (0.266s, 120.10/s) LR: 5.000e-03 Data: 0.000 (0.183) +2025-04-18 10:24:41,976 - train: [ INFO] - Train: 32 [ 150/461 ( 33%)] Loss: 0.698819 (0.7101) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 455.72/s (0.240s, 133.26/s) LR: 5.000e-03 Data: 0.000 (0.158) +2025-04-18 10:24:53,700 - train: [ INFO] - Train: 32 [ 200/461 ( 43%)] Loss: 0.705190 (0.7091) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 465.51/s (0.222s, 144.46/s) LR: 5.000e-03 Data: 0.000 (0.140) +2025-04-18 10:25:03,370 - train: [ INFO] - Train: 32 [ 250/461 ( 54%)] Loss: 0.737399 (0.7138) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 349.31/s (0.208s, 153.62/s) LR: 5.000e-03 Data: 0.000 (0.127) +2025-04-18 10:25:09,716 - train: [ INFO] - Train: 32 [ 300/461 ( 65%)] Loss: 0.718311 (0.7144) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 449.36/s (0.190s, 168.21/s) LR: 5.000e-03 Data: 0.000 (0.106) +2025-04-18 10:25:20,051 - train: [ INFO] - Train: 32 [ 350/461 ( 76%)] Loss: 0.724213 (0.7157) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 383.03/s (0.181s, 176.92/s) LR: 5.000e-03 Data: 0.001 (0.098) +2025-04-18 10:25:36,467 - train: [ INFO] - Train: 32 [ 400/461 ( 87%)] Loss: 0.714321 (0.7155) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.58/s (0.193s, 166.00/s) LR: 5.000e-03 Data: 0.000 (0.110) +2025-04-18 10:25:54,886 - train: [ INFO] - Train: 32 [ 450/461 ( 98%)] Loss: 0.714960 (0.7155) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 470.74/s (0.204s, 156.91/s) LR: 5.000e-03 Data: 0.000 (0.121) +2025-04-18 10:25:59,643 - train: [ INFO] - Train: 32 [ 460/461 (100%)] Loss: 0.738479 (0.7176) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 100.0000 (100.0000) Time: 1.130s, 28.32/s (0.208s, 153.74/s) LR: 5.000e-03 Data: 1.036 (0.125) +2025-04-18 10:26:08,016 - train: [ INFO] - Eval : 32 Time: 8.030 (8.030) Loss: 1.8675 (1.8675) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-18 10:26:21,443 - train: [ INFO] - Eval : 32 Time: 0.028 (0.421) Loss: 1.8388 (1.8665) Acc@1: 50.0000 (51.2868)Acc@5: 75.0000 (76.5931) +2025-04-18 10:26:33,641 - train: [ INFO] - Eval : 32 Time: 0.021 (0.410) Loss: 2.9805 (1.8778) Acc@1: 50.0000 (50.1157)Acc@5: 50.0000 (76.4842) +2025-04-18 10:26:45,907 - train: [ INFO] - Train: 33 [ 0/461 ( 0%)] Loss: 0.746114 (0.7461) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.886s, 4.06/s (7.886s, 4.06/s) LR: 5.000e-03 Data: 7.788 (7.788) +2025-04-18 10:27:05,379 - train: [ INFO] - Train: 33 [ 50/461 ( 11%)] Loss: 0.749132 (0.7476) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.133s, 240.47/s (0.415s, 77.16/s) LR: 5.000e-03 Data: 0.045 (0.335) +2025-04-18 10:27:17,682 - train: [ INFO] - Train: 33 [ 100/461 ( 22%)] Loss: 0.782149 (0.7591) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.069s, 462.21/s (0.302s, 106.09/s) LR: 5.000e-03 Data: 0.000 (0.225) +2025-04-18 10:27:30,306 - train: [ INFO] - Train: 33 [ 150/461 ( 33%)] Loss: 0.708277 (0.7464) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.123s, 260.08/s (0.263s, 121.47/s) LR: 5.000e-03 Data: 0.000 (0.187) +2025-04-18 10:27:48,813 - train: [ INFO] - Train: 33 [ 200/461 ( 43%)] Loss: 0.695104 (0.7362) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.068s, 467.57/s (0.258s, 124.13/s) LR: 5.000e-03 Data: 0.000 (0.181) +2025-04-18 10:28:06,936 - train: [ INFO] - Train: 33 [ 250/461 ( 54%)] Loss: 0.699559 (0.7301) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.13/s (0.251s, 127.44/s) LR: 5.000e-03 Data: 0.000 (0.174) +2025-04-18 10:28:21,401 - train: [ INFO] - Train: 33 [ 300/461 ( 65%)] Loss: 0.710094 (0.7272) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.111s, 287.00/s (0.244s, 130.98/s) LR: 5.000e-03 Data: 0.001 (0.167) +2025-04-18 10:28:39,147 - train: [ INFO] - Train: 33 [ 350/461 ( 76%)] Loss: 0.711925 (0.7253) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.081s, 395.32/s (0.242s, 132.26/s) LR: 5.000e-03 Data: 0.000 (0.165) +2025-04-18 10:28:58,519 - train: [ INFO] - Train: 33 [ 400/461 ( 87%)] Loss: 0.696953 (0.7221) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 2.717s, 11.78/s (0.249s, 128.58/s) LR: 5.000e-03 Data: 2.620 (0.172) +2025-04-18 10:29:14,495 - train: [ INFO] - Train: 33 [ 450/461 ( 98%)] Loss: 0.715194 (0.7215) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.119s, 269.75/s (0.247s, 129.43/s) LR: 5.000e-03 Data: 0.037 (0.170) +2025-04-18 10:29:16,374 - train: [ INFO] - Train: 33 [ 460/461 (100%)] Loss: 0.697882 (0.7193) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.068s, 473.34/s (0.244s, 131.41/s) LR: 5.000e-03 Data: 0.000 (0.167) +2025-04-18 10:29:24,598 - train: [ INFO] - Eval : 33 Time: 7.930 (7.930) Loss: 2.0715 (2.0715) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-18 10:29:39,584 - train: [ INFO] - Eval : 33 Time: 0.032 (0.449) Loss: 1.7983 (1.9250) Acc@1: 53.1250 (50.0000)Acc@5: 75.0000 (75.7966) +2025-04-18 10:29:47,864 - train: [ INFO] - Eval : 33 Time: 0.014 (0.380) Loss: 2.7901 (1.9337) Acc@1: 0.0000 (49.4217)Acc@5: 50.0000 (75.5590) +2025-04-18 10:30:00,938 - train: [ INFO] - Train: 34 [ 0/461 ( 0%)] Loss: 0.696158 (0.6962) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.399s, 3.81/s (8.399s, 3.81/s) LR: 5.000e-03 Data: 8.281 (8.281) +2025-04-18 10:30:13,033 - train: [ INFO] - Train: 34 [ 50/461 ( 11%)] Loss: 0.695450 (0.6958) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 340.83/s (0.361s, 88.70/s) LR: 5.000e-03 Data: 0.000 (0.278) +2025-04-18 10:30:28,511 - train: [ INFO] - Train: 34 [ 100/461 ( 22%)] Loss: 0.718319 (0.7033) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 379.69/s (0.296s, 108.25/s) LR: 5.000e-03 Data: 0.000 (0.214) +2025-04-18 10:30:47,835 - train: [ INFO] - Train: 34 [ 150/461 ( 33%)] Loss: 0.701906 (0.7030) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.132s, 242.18/s (0.295s, 108.47/s) LR: 5.000e-03 Data: 0.063 (0.213) +2025-04-18 10:31:01,632 - train: [ INFO] - Train: 34 [ 200/461 ( 43%)] Loss: 0.775108 (0.7174) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.068s, 473.46/s (0.275s, 116.47/s) LR: 5.000e-03 Data: 0.000 (0.193) +2025-04-18 10:31:10,333 - train: [ INFO] - Train: 34 [ 250/461 ( 54%)] Loss: 0.691312 (0.7130) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.068s, 471.32/s (0.247s, 129.35/s) LR: 5.000e-03 Data: 0.000 (0.165) +2025-04-18 10:31:26,827 - train: [ INFO] - Train: 34 [ 300/461 ( 65%)] Loss: 0.702838 (0.7116) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.077s, 417.45/s (0.248s, 129.05/s) LR: 5.000e-03 Data: 0.000 (0.165) +2025-04-18 10:31:37,109 - train: [ INFO] - Train: 34 [ 350/461 ( 76%)] Loss: 0.692497 (0.7092) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.071s, 447.57/s (0.237s, 134.88/s) LR: 5.000e-03 Data: 0.000 (0.154) +2025-04-18 10:31:48,128 - train: [ INFO] - Train: 34 [ 400/461 ( 87%)] Loss: 0.715093 (0.7099) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 2.032s, 15.75/s (0.232s, 137.75/s) LR: 5.000e-03 Data: 1.927 (0.149) +2025-04-18 10:32:02,769 - train: [ INFO] - Train: 34 [ 450/461 ( 98%)] Loss: 0.707214 (0.7096) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.087s, 369.02/s (0.233s, 137.63/s) LR: 5.000e-03 Data: 0.000 (0.149) +2025-04-18 10:32:04,476 - train: [ INFO] - Train: 34 [ 460/461 (100%)] Loss: 0.701964 (0.7089) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.070s, 458.79/s (0.230s, 138.96/s) LR: 5.000e-03 Data: 0.000 (0.147) +2025-04-18 10:32:12,158 - train: [ INFO] - Eval : 34 Time: 7.381 (7.381) Loss: 1.9746 (1.9746) Acc@1: 53.1250 (53.1250)Acc@5: 78.1250 (78.1250) +2025-04-18 10:32:26,094 - train: [ INFO] - Eval : 34 Time: 0.060 (0.418) Loss: 1.8178 (1.9056) Acc@1: 56.2500 (51.4706)Acc@5: 75.0000 (75.9191) +2025-04-18 10:32:34,011 - train: [ INFO] - Eval : 34 Time: 0.038 (0.357) Loss: 2.9430 (1.9176) Acc@1: 0.0000 (50.6939)Acc@5: 50.0000 (75.5590) +2025-04-18 10:32:49,109 - train: [ INFO] - Train: 35 [ 0/461 ( 0%)] Loss: 0.702626 (0.7026) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.402s, 3.81/s (8.402s, 3.81/s) LR: 5.000e-03 Data: 8.276 (8.276) +2025-04-18 10:32:56,652 - train: [ INFO] - Train: 35 [ 50/461 ( 11%)] Loss: 0.724697 (0.7137) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 336.54/s (0.301s, 106.37/s) LR: 5.000e-03 Data: 0.000 (0.221) +2025-04-18 10:33:04,728 - train: [ INFO] - Train: 35 [ 100/461 ( 22%)] Loss: 0.705901 (0.7111) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.159s, 201.45/s (0.219s, 145.81/s) LR: 5.000e-03 Data: 0.000 (0.133) +2025-04-18 10:33:10,616 - train: [ INFO] - Train: 35 [ 150/461 ( 33%)] Loss: 0.697472 (0.7077) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 402.97/s (0.176s, 181.71/s) LR: 5.000e-03 Data: 0.000 (0.089) +2025-04-18 10:33:26,540 - train: [ INFO] - Train: 35 [ 200/461 ( 43%)] Loss: 0.717104 (0.7096) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.218s, 146.62/s (0.183s, 174.98/s) LR: 5.000e-03 Data: 0.131 (0.096) +2025-04-18 10:33:37,601 - train: [ INFO] - Train: 35 [ 250/461 ( 54%)] Loss: 0.695690 (0.7072) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 467.73/s (0.182s, 175.47/s) LR: 5.000e-03 Data: 0.000 (0.096) +2025-04-18 10:33:52,132 - train: [ INFO] - Train: 35 [ 300/461 ( 65%)] Loss: 0.701782 (0.7065) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.171s, 187.25/s (0.195s, 163.85/s) LR: 5.000e-03 Data: 0.001 (0.108) +2025-04-18 10:33:58,084 - train: [ INFO] - Train: 35 [ 350/461 ( 76%)] Loss: 0.695119 (0.7050) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 470.00/s (0.184s, 174.31/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-18 10:34:04,924 - train: [ INFO] - Train: 35 [ 400/461 ( 87%)] Loss: 0.762467 (0.7114) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.07/s (0.173s, 185.21/s) LR: 5.000e-03 Data: 0.001 (0.081) +2025-04-18 10:34:13,554 - train: [ INFO] - Train: 35 [ 450/461 ( 98%)] Loss: 0.707452 (0.7110) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.069s, 461.22/s (0.165s, 193.95/s) LR: 5.000e-03 Data: 0.000 (0.075) +2025-04-18 10:34:17,203 - train: [ INFO] - Train: 35 [ 460/461 (100%)] Loss: 0.705440 (0.7105) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.069s, 462.56/s (0.169s, 189.23/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 10:34:25,336 - train: [ INFO] - Eval : 35 Time: 7.798 (7.798) Loss: 2.0409 (2.0409) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 10:34:43,579 - train: [ INFO] - Eval : 35 Time: 0.028 (0.511) Loss: 1.6775 (1.9305) Acc@1: 65.6250 (49.6324)Acc@5: 75.0000 (75.6127) +2025-04-18 10:34:51,078 - train: [ INFO] - Eval : 35 Time: 0.017 (0.409) Loss: 3.1791 (1.9279) Acc@1: 0.0000 (50.0771)Acc@5: 50.0000 (75.8674) +2025-04-18 10:35:00,615 - train: [ INFO] - Train: 36 [ 0/461 ( 0%)] Loss: 0.798556 (0.7986) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 4.413s, 7.25/s (4.413s, 7.25/s) LR: 5.000e-03 Data: 4.284 (4.284) +2025-04-18 10:35:09,933 - train: [ INFO] - Train: 36 [ 50/461 ( 11%)] Loss: 0.682526 (0.7405) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.083s, 383.85/s (0.228s, 140.07/s) LR: 5.000e-03 Data: 0.000 (0.139) +2025-04-18 10:35:25,778 - train: [ INFO] - Train: 36 [ 100/461 ( 22%)] Loss: 0.701358 (0.7275) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.132s, 241.67/s (0.237s, 134.91/s) LR: 5.000e-03 Data: 0.000 (0.151) +2025-04-18 10:35:38,262 - train: [ INFO] - Train: 36 [ 150/461 ( 33%)] Loss: 0.723530 (0.7265) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.28/s (0.228s, 140.05/s) LR: 5.000e-03 Data: 0.000 (0.143) +2025-04-18 10:35:44,520 - train: [ INFO] - Train: 36 [ 200/461 ( 43%)] Loss: 0.749211 (0.7310) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.87/s (0.197s, 162.62/s) LR: 5.000e-03 Data: 0.001 (0.110) +2025-04-18 10:35:53,399 - train: [ INFO] - Train: 36 [ 250/461 ( 54%)] Loss: 0.698464 (0.7256) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.096s, 331.72/s (0.175s, 182.83/s) LR: 5.000e-03 Data: 0.001 (0.088) +2025-04-18 10:36:07,821 - train: [ INFO] - Train: 36 [ 300/461 ( 65%)] Loss: 0.703727 (0.7225) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.098s, 327.94/s (0.176s, 182.33/s) LR: 5.000e-03 Data: 0.001 (0.088) +2025-04-18 10:36:18,880 - train: [ INFO] - Train: 36 [ 350/461 ( 76%)] Loss: 0.702375 (0.7200) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.126s, 253.68/s (0.179s, 178.86/s) LR: 5.000e-03 Data: 0.000 (0.092) +2025-04-18 10:36:29,524 - train: [ INFO] - Train: 36 [ 400/461 ( 87%)] Loss: 0.693982 (0.7171) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.072s, 443.58/s (0.179s, 178.89/s) LR: 5.000e-03 Data: 0.001 (0.090) +2025-04-18 10:36:35,785 - train: [ INFO] - Train: 36 [ 450/461 ( 98%)] Loss: 0.740393 (0.7194) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.070s, 460.37/s (0.169s, 189.68/s) LR: 5.000e-03 Data: 0.000 (0.080) +2025-04-18 10:36:36,478 - train: [ INFO] - Train: 36 [ 460/461 (100%)] Loss: 0.710071 (0.7186) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.068s, 472.63/s (0.167s, 192.15/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 10:36:44,383 - train: [ INFO] - Eval : 36 Time: 7.619 (7.619) Loss: 2.0388 (2.0388) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-18 10:36:54,768 - train: [ INFO] - Eval : 36 Time: 0.027 (0.353) Loss: 1.8501 (1.9114) Acc@1: 62.5000 (52.0221)Acc@5: 68.7500 (75.1225) +2025-04-18 10:37:04,633 - train: [ INFO] - Eval : 36 Time: 0.018 (0.340) Loss: 2.9744 (1.9110) Acc@1: 0.0000 (51.3493)Acc@5: 50.0000 (75.9445) +2025-04-18 10:37:18,364 - train: [ INFO] - Train: 37 [ 0/461 ( 0%)] Loss: 0.715383 (0.7154) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 9.146s, 3.50/s (9.146s, 3.50/s) LR: 5.000e-03 Data: 9.015 (9.015) +2025-04-18 10:37:27,364 - train: [ INFO] - Train: 37 [ 50/461 ( 11%)] Loss: 0.706237 (0.7108) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.128s, 250.03/s (0.316s, 101.38/s) LR: 5.000e-03 Data: 0.000 (0.226) +2025-04-18 10:37:36,329 - train: [ INFO] - Train: 37 [ 100/461 ( 22%)] Loss: 0.735043 (0.7189) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.19/s (0.234s, 136.65/s) LR: 5.000e-03 Data: 0.000 (0.149) +2025-04-18 10:37:42,766 - train: [ INFO] - Train: 37 [ 150/461 ( 33%)] Loss: 0.755213 (0.7280) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.079s, 403.18/s (0.191s, 167.56/s) LR: 5.000e-03 Data: 0.001 (0.104) +2025-04-18 10:37:52,628 - train: [ INFO] - Train: 37 [ 200/461 ( 43%)] Loss: 0.761789 (0.7347) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.070s, 460.00/s (0.178s, 179.40/s) LR: 5.000e-03 Data: 0.000 (0.091) +2025-04-18 10:38:03,980 - train: [ INFO] - Train: 37 [ 250/461 ( 54%)] Loss: 0.697357 (0.7285) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.068s, 470.94/s (0.179s, 178.85/s) LR: 5.000e-03 Data: 0.000 (0.092) +2025-04-18 10:38:16,500 - train: [ INFO] - Train: 37 [ 300/461 ( 65%)] Loss: 0.704809 (0.7251) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.082s, 389.85/s (0.181s, 176.77/s) LR: 5.000e-03 Data: 0.001 (0.095) +2025-04-18 10:38:29,805 - train: [ INFO] - Train: 37 [ 350/461 ( 76%)] Loss: 0.718186 (0.7243) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.118s, 270.31/s (0.183s, 175.33/s) LR: 5.000e-03 Data: 0.001 (0.097) +2025-04-18 10:38:35,247 - train: [ INFO] - Train: 37 [ 400/461 ( 87%)] Loss: 0.707076 (0.7223) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.087s, 369.55/s (0.173s, 185.28/s) LR: 5.000e-03 Data: 0.001 (0.085) +2025-04-18 10:38:43,311 - train: [ INFO] - Train: 37 [ 450/461 ( 98%)] Loss: 0.695756 (0.7197) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.096s, 334.60/s (0.165s, 193.98/s) LR: 5.000e-03 Data: 0.001 (0.077) +2025-04-18 10:38:44,357 - train: [ INFO] - Train: 37 [ 460/461 (100%)] Loss: 0.691223 (0.7171) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.283s, 112.93/s (0.164s, 195.67/s) LR: 5.000e-03 Data: 0.211 (0.076) +2025-04-18 10:38:52,794 - train: [ INFO] - Eval : 37 Time: 7.931 (7.931) Loss: 1.9222 (1.9222) Acc@1: 56.2500 (56.2500)Acc@5: 75.0000 (75.0000) +2025-04-18 10:39:10,917 - train: [ INFO] - Eval : 37 Time: 0.080 (0.511) Loss: 1.9119 (1.8921) Acc@1: 62.5000 (51.5931)Acc@5: 71.8750 (75.6740) +2025-04-18 10:39:17,602 - train: [ INFO] - Eval : 37 Time: 0.014 (0.399) Loss: 2.8360 (1.8927) Acc@1: 0.0000 (50.9252)Acc@5: 50.0000 (75.9830) +2025-04-18 10:39:25,500 - train: [ INFO] - Train: 38 [ 0/461 ( 0%)] Loss: 0.703717 (0.7037) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.763s, 6.72/s (4.763s, 6.72/s) LR: 5.000e-03 Data: 4.628 (4.628) +2025-04-18 10:39:31,146 - train: [ INFO] - Train: 38 [ 50/461 ( 11%)] Loss: 0.694948 (0.6993) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 424.60/s (0.186s, 172.50/s) LR: 5.000e-03 Data: 0.000 (0.091) +2025-04-18 10:39:35,880 - train: [ INFO] - Train: 38 [ 100/461 ( 22%)] Loss: 0.795609 (0.7314) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.114s, 280.37/s (0.138s, 232.70/s) LR: 5.000e-03 Data: 0.001 (0.046) +2025-04-18 10:39:42,791 - train: [ INFO] - Train: 38 [ 150/461 ( 33%)] Loss: 0.707114 (0.7253) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.069s, 460.50/s (0.121s, 263.62/s) LR: 5.000e-03 Data: 0.001 (0.031) +2025-04-18 10:39:56,321 - train: [ INFO] - Train: 38 [ 200/461 ( 43%)] Loss: 0.697462 (0.7198) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.083s, 383.88/s (0.153s, 209.68/s) LR: 5.000e-03 Data: 0.000 (0.065) +2025-04-18 10:40:02,466 - train: [ INFO] - Train: 38 [ 250/461 ( 54%)] Loss: 0.772172 (0.7285) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.072s, 444.97/s (0.145s, 221.16/s) LR: 5.000e-03 Data: 0.000 (0.057) +2025-04-18 10:40:18,635 - train: [ INFO] - Train: 38 [ 300/461 ( 65%)] Loss: 0.696363 (0.7239) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.071s, 452.14/s (0.174s, 184.31/s) LR: 5.000e-03 Data: 0.000 (0.088) +2025-04-18 10:40:32,371 - train: [ INFO] - Train: 38 [ 350/461 ( 76%)] Loss: 0.702385 (0.7212) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.072s, 442.36/s (0.188s, 170.58/s) LR: 5.000e-03 Data: 0.000 (0.102) +2025-04-18 10:40:45,252 - train: [ INFO] - Train: 38 [ 400/461 ( 87%)] Loss: 0.727690 (0.7219) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 1.001s, 31.98/s (0.195s, 163.81/s) LR: 5.000e-03 Data: 0.929 (0.111) +2025-04-18 10:40:59,776 - train: [ INFO] - Train: 38 [ 450/461 ( 98%)] Loss: 0.699624 (0.7197) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.123s, 259.25/s (0.205s, 156.14/s) LR: 5.000e-03 Data: 0.002 (0.121) +2025-04-18 10:41:02,027 - train: [ INFO] - Train: 38 [ 460/461 (100%)] Loss: 0.702040 (0.7181) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.067s, 475.10/s (0.205s, 155.86/s) LR: 5.000e-03 Data: 0.000 (0.121) +2025-04-18 10:41:09,978 - train: [ INFO] - Eval : 38 Time: 7.634 (7.634) Loss: 1.9281 (1.9281) Acc@1: 56.2500 (56.2500)Acc@5: 75.0000 (75.0000) +2025-04-18 10:41:16,531 - train: [ INFO] - Eval : 38 Time: 0.168 (0.278) Loss: 1.8943 (1.9364) Acc@1: 59.3750 (50.4289)Acc@5: 68.7500 (75.2451) +2025-04-18 10:41:19,317 - train: [ INFO] - Eval : 38 Time: 0.014 (0.207) Loss: 2.3959 (1.9402) Acc@1: 0.0000 (49.4603)Acc@5: 50.0000 (75.2120) +2025-04-18 10:41:32,796 - train: [ INFO] - Train: 39 [ 0/461 ( 0%)] Loss: 0.689421 (0.6894) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 9.053s, 3.53/s (9.053s, 3.53/s) LR: 5.000e-03 Data: 8.953 (8.953) +2025-04-18 10:41:40,750 - train: [ INFO] - Train: 39 [ 50/461 ( 11%)] Loss: 0.715702 (0.7026) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 429.57/s (0.318s, 100.63/s) LR: 5.000e-03 Data: 0.000 (0.232) +2025-04-18 10:41:52,963 - train: [ INFO] - Train: 39 [ 100/461 ( 22%)] Loss: 0.695434 (0.7002) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 438.21/s (0.249s, 128.64/s) LR: 5.000e-03 Data: 0.000 (0.162) +2025-04-18 10:42:06,998 - train: [ INFO] - Train: 39 [ 150/461 ( 33%)] Loss: 0.688625 (0.6973) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 455.14/s (0.232s, 138.08/s) LR: 5.000e-03 Data: 0.000 (0.149) +2025-04-18 10:42:16,916 - train: [ INFO] - Train: 39 [ 200/461 ( 43%)] Loss: 0.704215 (0.6987) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.47/s (0.216s, 148.39/s) LR: 5.000e-03 Data: 0.000 (0.135) +2025-04-18 10:42:33,077 - train: [ INFO] - Train: 39 [ 250/461 ( 54%)] Loss: 0.699312 (0.6988) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 460.30/s (0.213s, 149.95/s) LR: 5.000e-03 Data: 0.000 (0.133) +2025-04-18 10:42:49,824 - train: [ INFO] - Train: 39 [ 300/461 ( 65%)] Loss: 0.715364 (0.7012) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 392.62/s (0.214s, 149.56/s) LR: 5.000e-03 Data: 0.000 (0.134) +2025-04-18 10:43:06,140 - train: [ INFO] - Train: 39 [ 350/461 ( 76%)] Loss: 0.686610 (0.6993) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 426.01/s (0.216s, 148.06/s) LR: 5.000e-03 Data: 0.001 (0.137) +2025-04-18 10:43:24,367 - train: [ INFO] - Train: 39 [ 400/461 ( 87%)] Loss: 0.714422 (0.7010) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 2.495s, 12.83/s (0.218s, 146.49/s) LR: 5.000e-03 Data: 2.400 (0.139) +2025-04-18 10:43:39,968 - train: [ INFO] - Train: 39 [ 450/461 ( 98%)] Loss: 0.741733 (0.7051) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 459.10/s (0.218s, 147.09/s) LR: 5.000e-03 Data: 0.000 (0.138) +2025-04-18 10:43:41,352 - train: [ INFO] - Train: 39 [ 460/461 (100%)] Loss: 0.705214 (0.7051) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 465.46/s (0.214s, 149.24/s) LR: 5.000e-03 Data: 0.000 (0.135) +2025-04-18 10:43:47,774 - train: [ INFO] - Eval : 39 Time: 6.151 (6.151) Loss: 2.0929 (2.0929) Acc@1: 40.6250 (40.6250)Acc@5: 75.0000 (75.0000) +2025-04-18 10:44:00,032 - train: [ INFO] - Eval : 39 Time: 0.027 (0.361) Loss: 1.8500 (1.9349) Acc@1: 53.1250 (49.6324)Acc@5: 84.3750 (74.6936) +2025-04-18 10:44:10,371 - train: [ INFO] - Eval : 39 Time: 0.016 (0.351) Loss: 2.8842 (1.9436) Acc@1: 0.0000 (49.1519)Acc@5: 50.0000 (74.8651) +2025-04-18 10:44:23,174 - train: [ INFO] - Train: 40 [ 0/461 ( 0%)] Loss: 0.690471 (0.6905) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.714s, 3.67/s (8.714s, 3.67/s) LR: 5.000e-03 Data: 8.589 (8.589) +2025-04-18 10:44:34,394 - train: [ INFO] - Train: 40 [ 50/461 ( 11%)] Loss: 0.716361 (0.7034) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.136s, 235.39/s (0.365s, 87.73/s) LR: 5.000e-03 Data: 0.000 (0.278) +2025-04-18 10:44:53,080 - train: [ INFO] - Train: 40 [ 100/461 ( 22%)] Loss: 0.761112 (0.7226) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.13/s (0.307s, 104.32/s) LR: 5.000e-03 Data: 0.000 (0.223) +2025-04-18 10:44:58,918 - train: [ INFO] - Train: 40 [ 150/461 ( 33%)] Loss: 0.691085 (0.7148) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.092s, 349.59/s (0.242s, 132.31/s) LR: 5.000e-03 Data: 0.000 (0.156) +2025-04-18 10:45:03,499 - train: [ INFO] - Train: 40 [ 200/461 ( 43%)] Loss: 0.775221 (0.7268) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.122s, 262.21/s (0.203s, 157.52/s) LR: 5.000e-03 Data: 0.000 (0.118) +2025-04-18 10:45:08,416 - train: [ INFO] - Train: 40 [ 250/461 ( 54%)] Loss: 0.703552 (0.7230) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.098s, 326.71/s (0.181s, 176.31/s) LR: 5.000e-03 Data: 0.001 (0.094) +2025-04-18 10:45:15,423 - train: [ INFO] - Train: 40 [ 300/461 ( 65%)] Loss: 0.696994 (0.7193) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.068s, 471.17/s (0.166s, 192.45/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 10:45:30,181 - train: [ INFO] - Train: 40 [ 350/461 ( 76%)] Loss: 0.692054 (0.7159) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.068s, 473.79/s (0.179s, 178.36/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-18 10:45:46,489 - train: [ INFO] - Train: 40 [ 400/461 ( 87%)] Loss: 0.738795 (0.7184) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.462s, 69.23/s (0.197s, 162.27/s) LR: 5.000e-03 Data: 0.356 (0.112) +2025-04-18 10:45:58,149 - train: [ INFO] - Train: 40 [ 450/461 ( 98%)] Loss: 0.710854 (0.7176) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.088s, 365.51/s (0.200s, 159.78/s) LR: 5.000e-03 Data: 0.000 (0.116) +2025-04-18 10:46:00,067 - train: [ INFO] - Train: 40 [ 460/461 (100%)] Loss: 0.693058 (0.7154) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.067s, 475.04/s (0.200s, 160.40/s) LR: 5.000e-03 Data: 0.000 (0.115) +2025-04-18 10:46:09,438 - train: [ INFO] - Eval : 40 Time: 9.093 (9.093) Loss: 2.0410 (2.0410) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 10:46:25,819 - train: [ INFO] - Eval : 40 Time: 0.033 (0.500) Loss: 1.8235 (1.9992) Acc@1: 62.5000 (47.7941)Acc@5: 75.0000 (74.0196) +2025-04-18 10:46:29,798 - train: [ INFO] - Eval : 40 Time: 0.014 (0.359) Loss: 2.7637 (1.9956) Acc@1: 0.0000 (47.9183)Acc@5: 100.0000 (73.5929) +2025-04-18 10:46:41,056 - train: [ INFO] - Train: 41 [ 0/461 ( 0%)] Loss: 0.712993 (0.7130) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.720s, 5.59/s (5.720s, 5.59/s) LR: 5.000e-03 Data: 5.570 (5.570) +2025-04-18 10:46:46,864 - train: [ INFO] - Train: 41 [ 50/461 ( 11%)] Loss: 0.758119 (0.7356) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 407.40/s (0.221s, 144.78/s) LR: 5.000e-03 Data: 0.000 (0.114) +2025-04-18 10:46:54,309 - train: [ INFO] - Train: 41 [ 100/461 ( 22%)] Loss: 0.704090 (0.7251) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 453.73/s (0.159s, 201.50/s) LR: 5.000e-03 Data: 0.001 (0.059) +2025-04-18 10:47:06,838 - train: [ INFO] - Train: 41 [ 150/461 ( 33%)] Loss: 0.715646 (0.7227) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.127s, 252.52/s (0.172s, 186.52/s) LR: 5.000e-03 Data: 0.000 (0.075) +2025-04-18 10:47:20,667 - train: [ INFO] - Train: 41 [ 200/461 ( 43%)] Loss: 0.698415 (0.7179) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.086s, 371.42/s (0.191s, 167.31/s) LR: 5.000e-03 Data: 0.000 (0.098) +2025-04-18 10:47:36,268 - train: [ INFO] - Train: 41 [ 250/461 ( 54%)] Loss: 0.841349 (0.7384) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.04/s (0.211s, 151.63/s) LR: 5.000e-03 Data: 0.000 (0.120) +2025-04-18 10:47:45,080 - train: [ INFO] - Train: 41 [ 300/461 ( 65%)] Loss: 0.713659 (0.7349) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.103s, 310.23/s (0.205s, 156.38/s) LR: 5.000e-03 Data: 0.001 (0.113) +2025-04-18 10:47:52,836 - train: [ INFO] - Train: 41 [ 350/461 ( 76%)] Loss: 0.693009 (0.7297) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 465.35/s (0.190s, 168.05/s) LR: 5.000e-03 Data: 0.000 (0.099) +2025-04-18 10:48:09,850 - train: [ INFO] - Train: 41 [ 400/461 ( 87%)] Loss: 0.711875 (0.7277) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.79/s (0.199s, 160.56/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 10:48:22,146 - train: [ INFO] - Train: 41 [ 450/461 ( 98%)] Loss: 0.711609 (0.7261) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.178s, 179.75/s (0.202s, 158.56/s) LR: 5.000e-03 Data: 0.110 (0.112) +2025-04-18 10:48:24,255 - train: [ INFO] - Train: 41 [ 460/461 (100%)] Loss: 0.738399 (0.7272) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.56/s (0.199s, 160.75/s) LR: 5.000e-03 Data: 0.000 (0.110) +2025-04-18 10:48:30,912 - train: [ INFO] - Eval : 41 Time: 6.320 (6.320) Loss: 2.0367 (2.0367) Acc@1: 50.0000 (50.0000)Acc@5: 68.7500 (68.7500) +2025-04-18 10:48:36,938 - train: [ INFO] - Eval : 41 Time: 0.022 (0.242) Loss: 1.9745 (1.9633) Acc@1: 56.2500 (48.9583)Acc@5: 68.7500 (73.7132) +2025-04-18 10:48:43,620 - train: [ INFO] - Eval : 41 Time: 0.035 (0.232) Loss: 3.2039 (1.9499) Acc@1: 0.0000 (49.1904)Acc@5: 50.0000 (74.2483) +2025-04-18 10:48:55,698 - train: [ INFO] - Train: 42 [ 0/461 ( 0%)] Loss: 0.693121 (0.6931) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.140s, 3.93/s (8.140s, 3.93/s) LR: 5.000e-03 Data: 7.999 (7.999) +2025-04-18 10:49:06,955 - train: [ INFO] - Train: 42 [ 50/461 ( 11%)] Loss: 0.718144 (0.7056) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.102s, 313.08/s (0.339s, 94.35/s) LR: 5.000e-03 Data: 0.000 (0.253) +2025-04-18 10:49:17,372 - train: [ INFO] - Train: 42 [ 100/461 ( 22%)] Loss: 0.691396 (0.7009) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.111s, 288.03/s (0.260s, 123.18/s) LR: 5.000e-03 Data: 0.001 (0.173) +2025-04-18 10:49:22,834 - train: [ INFO] - Train: 42 [ 150/461 ( 33%)] Loss: 0.731758 (0.7086) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 442.79/s (0.208s, 153.56/s) LR: 5.000e-03 Data: 0.000 (0.116) +2025-04-18 10:49:28,539 - train: [ INFO] - Train: 42 [ 200/461 ( 43%)] Loss: 0.701960 (0.7073) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.81/s (0.178s, 180.15/s) LR: 5.000e-03 Data: 0.000 (0.087) +2025-04-18 10:49:36,917 - train: [ INFO] - Train: 42 [ 250/461 ( 54%)] Loss: 0.708479 (0.7075) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 339.28/s (0.165s, 193.47/s) LR: 5.000e-03 Data: 0.000 (0.077) +2025-04-18 10:49:45,789 - train: [ INFO] - Train: 42 [ 300/461 ( 65%)] Loss: 0.794584 (0.7199) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.200s, 159.85/s (0.162s, 197.03/s) LR: 5.000e-03 Data: 0.092 (0.074) +2025-04-18 10:50:01,971 - train: [ INFO] - Train: 42 [ 350/461 ( 76%)] Loss: 0.777159 (0.7271) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.094s, 340.75/s (0.177s, 181.02/s) LR: 5.000e-03 Data: 0.001 (0.089) +2025-04-18 10:50:15,157 - train: [ INFO] - Train: 42 [ 400/461 ( 87%)] Loss: 0.686885 (0.7226) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.105s, 303.90/s (0.183s, 175.16/s) LR: 5.000e-03 Data: 0.001 (0.096) +2025-04-18 10:50:24,100 - train: [ INFO] - Train: 42 [ 450/461 ( 98%)] Loss: 0.716258 (0.7220) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.79/s (0.180s, 177.59/s) LR: 5.000e-03 Data: 0.000 (0.094) +2025-04-18 10:50:26,878 - train: [ INFO] - Train: 42 [ 460/461 (100%)] Loss: 0.687944 (0.7189) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.291s, 109.95/s (0.182s, 175.77/s) LR: 5.000e-03 Data: 0.220 (0.096) +2025-04-18 10:50:33,573 - train: [ INFO] - Eval : 42 Time: 6.401 (6.401) Loss: 2.0925 (2.0925) Acc@1: 40.6250 (40.6250)Acc@5: 71.8750 (71.8750) +2025-04-18 10:50:42,581 - train: [ INFO] - Eval : 42 Time: 0.453 (0.302) Loss: 1.8436 (1.9496) Acc@1: 59.3750 (50.6740)Acc@5: 68.7500 (75.4289) +2025-04-18 10:50:43,800 - train: [ INFO] - Eval : 42 Time: 0.043 (0.203) Loss: 3.1521 (1.9529) Acc@1: 0.0000 (50.5397)Acc@5: 50.0000 (75.5590) +2025-04-18 10:50:54,557 - train: [ INFO] - Train: 43 [ 0/461 ( 0%)] Loss: 0.710053 (0.7101) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.684s, 5.63/s (5.684s, 5.63/s) LR: 5.000e-03 Data: 5.552 (5.552) +2025-04-18 10:51:02,680 - train: [ INFO] - Train: 43 [ 50/461 ( 11%)] Loss: 0.728506 (0.7193) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.107s, 300.08/s (0.207s, 154.25/s) LR: 5.000e-03 Data: 0.001 (0.114) +2025-04-18 10:51:19,889 - train: [ INFO] - Train: 43 [ 100/461 ( 22%)] Loss: 0.690312 (0.7096) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 453.98/s (0.237s, 134.88/s) LR: 5.000e-03 Data: 0.000 (0.148) +2025-04-18 10:51:32,469 - train: [ INFO] - Train: 43 [ 150/461 ( 33%)] Loss: 0.710754 (0.7099) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 451.81/s (0.232s, 137.90/s) LR: 5.000e-03 Data: 0.000 (0.144) +2025-04-18 10:51:44,766 - train: [ INFO] - Train: 43 [ 200/461 ( 43%)] Loss: 0.753198 (0.7186) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 469.75/s (0.229s, 139.69/s) LR: 5.000e-03 Data: 0.000 (0.144) +2025-04-18 10:51:55,795 - train: [ INFO] - Train: 43 [ 250/461 ( 54%)] Loss: 0.722769 (0.7193) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.128s, 250.46/s (0.220s, 145.38/s) LR: 5.000e-03 Data: 0.001 (0.131) +2025-04-18 10:52:00,753 - train: [ INFO] - Train: 43 [ 300/461 ( 65%)] Loss: 0.700256 (0.7165) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 404.65/s (0.199s, 160.45/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 10:52:05,856 - train: [ INFO] - Train: 43 [ 350/461 ( 76%)] Loss: 0.748813 (0.7206) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.113s, 282.10/s (0.184s, 173.53/s) LR: 5.000e-03 Data: 0.001 (0.094) +2025-04-18 10:52:10,975 - train: [ INFO] - Train: 43 [ 400/461 ( 87%)] Loss: 0.697829 (0.7181) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.123s, 260.81/s (0.173s, 184.52/s) LR: 5.000e-03 Data: 0.001 (0.082) +2025-04-18 10:52:15,904 - train: [ INFO] - Train: 43 [ 450/461 ( 98%)] Loss: 0.712005 (0.7174) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.92/s (0.165s, 194.18/s) LR: 5.000e-03 Data: 0.000 (0.073) +2025-04-18 10:52:16,629 - train: [ INFO] - Train: 43 [ 460/461 (100%)] Loss: 0.709975 (0.7168) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.82/s (0.163s, 196.59/s) LR: 5.000e-03 Data: 0.000 (0.072) +2025-04-18 10:52:20,759 - train: [ INFO] - Eval : 43 Time: 3.812 (3.812) Loss: 2.2759 (2.2759) Acc@1: 40.6250 (40.6250)Acc@5: 62.5000 (62.5000) +2025-04-18 10:52:24,074 - train: [ INFO] - Eval : 43 Time: 0.109 (0.140) Loss: 1.8616 (1.9566) Acc@1: 59.3750 (49.5098)Acc@5: 75.0000 (75.1838) +2025-04-18 10:52:25,727 - train: [ INFO] - Eval : 43 Time: 0.019 (0.107) Loss: 2.9432 (1.9594) Acc@1: 0.0000 (49.4988)Acc@5: 50.0000 (75.0193) +2025-04-18 10:52:35,024 - train: [ INFO] - Train: 44 [ 0/461 ( 0%)] Loss: 0.701086 (0.7011) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.214s, 5.15/s (6.214s, 5.15/s) LR: 5.000e-03 Data: 5.999 (5.999) +2025-04-18 10:52:41,960 - train: [ INFO] - Train: 44 [ 50/461 ( 11%)] Loss: 0.686658 (0.6939) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 427.83/s (0.233s, 137.35/s) LR: 5.000e-03 Data: 0.000 (0.119) +2025-04-18 10:52:48,195 - train: [ INFO] - Train: 44 [ 100/461 ( 22%)] Loss: 0.698860 (0.6955) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.118s, 270.06/s (0.165s, 194.52/s) LR: 5.000e-03 Data: 0.000 (0.061) +2025-04-18 10:52:53,121 - train: [ INFO] - Train: 44 [ 150/461 ( 33%)] Loss: 0.700404 (0.6968) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.93/s (0.141s, 227.16/s) LR: 5.000e-03 Data: 0.000 (0.041) +2025-04-18 10:53:00,278 - train: [ INFO] - Train: 44 [ 200/461 ( 43%)] Loss: 0.725086 (0.7024) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.124s, 257.47/s (0.131s, 244.46/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-18 10:53:05,564 - train: [ INFO] - Train: 44 [ 250/461 ( 54%)] Loss: 0.690138 (0.7004) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.119s, 268.28/s (0.125s, 256.24/s) LR: 5.000e-03 Data: 0.001 (0.025) +2025-04-18 10:53:10,958 - train: [ INFO] - Train: 44 [ 300/461 ( 65%)] Loss: 0.696318 (0.6998) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.105s, 305.57/s (0.121s, 263.66/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-18 10:53:16,274 - train: [ INFO] - Train: 44 [ 350/461 ( 76%)] Loss: 0.729548 (0.7035) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.106s, 301.34/s (0.119s, 269.57/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-18 10:53:21,272 - train: [ INFO] - Train: 44 [ 400/461 ( 87%)] Loss: 0.697878 (0.7029) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.117s, 274.33/s (0.116s, 276.08/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-18 10:53:26,200 - train: [ INFO] - Train: 44 [ 450/461 ( 98%)] Loss: 0.717003 (0.7043) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 441.29/s (0.113s, 282.20/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 10:53:26,910 - train: [ INFO] - Train: 44 [ 460/461 (100%)] Loss: 0.724935 (0.7062) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.27/s (0.112s, 284.55/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 10:53:32,257 - train: [ INFO] - Eval : 44 Time: 4.921 (4.921) Loss: 2.0692 (2.0692) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 10:53:35,272 - train: [ INFO] - Eval : 44 Time: 0.024 (0.156) Loss: 1.8240 (1.9801) Acc@1: 53.1250 (48.7132)Acc@5: 68.7500 (74.7549) +2025-04-18 10:53:36,446 - train: [ INFO] - Eval : 44 Time: 0.014 (0.111) Loss: 2.5749 (1.9899) Acc@1: 0.0000 (47.9568)Acc@5: 100.0000 (74.9422) +2025-04-18 10:53:44,469 - train: [ INFO] - Train: 45 [ 0/461 ( 0%)] Loss: 0.744094 (0.7441) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.241s, 6.11/s (5.241s, 6.11/s) LR: 5.000e-03 Data: 5.076 (5.076) +2025-04-18 10:53:51,631 - train: [ INFO] - Train: 45 [ 50/461 ( 11%)] Loss: 0.726123 (0.7351) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.62/s (0.194s, 165.01/s) LR: 5.000e-03 Data: 0.000 (0.100) +2025-04-18 10:53:57,574 - train: [ INFO] - Train: 45 [ 100/461 ( 22%)] Loss: 0.726593 (0.7323) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.121s, 263.57/s (0.150s, 213.58/s) LR: 5.000e-03 Data: 0.001 (0.051) +2025-04-18 10:54:03,766 - train: [ INFO] - Train: 45 [ 150/461 ( 33%)] Loss: 0.697526 (0.7236) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.219s, 146.37/s (0.131s, 243.90/s) LR: 5.000e-03 Data: 0.001 (0.035) +2025-04-18 10:54:08,922 - train: [ INFO] - Train: 45 [ 200/461 ( 43%)] Loss: 0.694484 (0.7178) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 410.16/s (0.124s, 258.94/s) LR: 5.000e-03 Data: 0.001 (0.026) +2025-04-18 10:54:14,187 - train: [ INFO] - Train: 45 [ 250/461 ( 54%)] Loss: 0.692492 (0.7136) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.132s, 242.89/s (0.119s, 269.34/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-18 10:54:19,165 - train: [ INFO] - Train: 45 [ 300/461 ( 65%)] Loss: 0.686229 (0.7096) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 393.67/s (0.115s, 278.90/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 10:54:24,131 - train: [ INFO] - Train: 45 [ 350/461 ( 76%)] Loss: 0.695247 (0.7078) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.106s, 301.61/s (0.112s, 285.99/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-18 10:54:29,180 - train: [ INFO] - Train: 45 [ 400/461 ( 87%)] Loss: 0.702197 (0.7072) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 348.88/s (0.110s, 291.08/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-18 10:54:33,849 - train: [ INFO] - Train: 45 [ 450/461 ( 98%)] Loss: 0.692459 (0.7057) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 462.84/s (0.108s, 297.05/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:54:34,565 - train: [ INFO] - Train: 45 [ 460/461 (100%)] Loss: 0.774884 (0.7120) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.070s, 458.63/s (0.107s, 299.26/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:54:39,616 - train: [ INFO] - Eval : 45 Time: 4.773 (4.773) Loss: 2.0559 (2.0559) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 10:54:43,560 - train: [ INFO] - Eval : 45 Time: 0.065 (0.171) Loss: 1.9945 (1.9497) Acc@1: 46.8750 (50.2451)Acc@5: 75.0000 (74.8775) +2025-04-18 10:54:45,498 - train: [ INFO] - Eval : 45 Time: 0.014 (0.130) Loss: 2.8394 (1.9512) Acc@1: 0.0000 (49.7301)Acc@5: 100.0000 (74.9036) +2025-04-18 10:54:53,556 - train: [ INFO] - Train: 46 [ 0/461 ( 0%)] Loss: 0.691965 (0.6920) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.969s, 6.44/s (4.969s, 6.44/s) LR: 5.000e-03 Data: 4.790 (4.790) +2025-04-18 10:54:58,691 - train: [ INFO] - Train: 46 [ 50/461 ( 11%)] Loss: 0.712016 (0.7020) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.125s, 255.01/s (0.195s, 163.98/s) LR: 5.000e-03 Data: 0.001 (0.095) +2025-04-18 10:55:04,755 - train: [ INFO] - Train: 46 [ 100/461 ( 22%)] Loss: 0.706017 (0.7033) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.59/s (0.145s, 220.33/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-18 10:55:11,839 - train: [ INFO] - Train: 46 [ 150/461 ( 33%)] Loss: 0.723612 (0.7084) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.110s, 291.29/s (0.128s, 249.76/s) LR: 5.000e-03 Data: 0.001 (0.032) +2025-04-18 10:55:17,637 - train: [ INFO] - Train: 46 [ 200/461 ( 43%)] Loss: 0.701982 (0.7071) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 460.80/s (0.121s, 264.36/s) LR: 5.000e-03 Data: 0.001 (0.025) +2025-04-18 10:55:23,512 - train: [ INFO] - Train: 46 [ 250/461 ( 54%)] Loss: 0.693036 (0.7048) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.098s, 325.64/s (0.117s, 274.34/s) LR: 5.000e-03 Data: 0.001 (0.020) +2025-04-18 10:55:28,760 - train: [ INFO] - Train: 46 [ 300/461 ( 65%)] Loss: 0.689568 (0.7026) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.124s, 258.15/s (0.113s, 282.64/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-18 10:55:34,028 - train: [ INFO] - Train: 46 [ 350/461 ( 76%)] Loss: 0.697877 (0.7020) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.150s, 213.38/s (0.111s, 287.36/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 10:55:39,225 - train: [ INFO] - Train: 46 [ 400/461 ( 87%)] Loss: 0.707897 (0.7027) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 363.84/s (0.110s, 292.23/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 10:55:44,105 - train: [ INFO] - Train: 46 [ 450/461 ( 98%)] Loss: 0.734749 (0.7059) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 457.49/s (0.107s, 297.94/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:55:44,895 - train: [ INFO] - Train: 46 [ 460/461 (100%)] Loss: 0.716761 (0.7069) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 416.94/s (0.107s, 299.80/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 10:55:50,606 - train: [ INFO] - Eval : 46 Time: 5.343 (5.343) Loss: 1.8939 (1.8939) Acc@1: 46.8750 (46.8750)Acc@5: 81.2500 (81.2500) +2025-04-18 10:55:53,815 - train: [ INFO] - Eval : 46 Time: 0.022 (0.168) Loss: 1.9504 (1.9433) Acc@1: 53.1250 (48.8358)Acc@5: 78.1250 (75.2451) +2025-04-18 10:55:55,364 - train: [ INFO] - Eval : 46 Time: 0.017 (0.123) Loss: 3.0233 (1.9517) Acc@1: 0.0000 (48.4580)Acc@5: 50.0000 (75.7903) +2025-04-18 10:56:02,304 - train: [ INFO] - Train: 47 [ 0/461 ( 0%)] Loss: 0.818377 (0.8184) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 4.040s, 7.92/s (4.040s, 7.92/s) LR: 5.000e-03 Data: 3.858 (3.858) +2025-04-18 10:56:07,829 - train: [ INFO] - Train: 47 [ 50/461 ( 11%)] Loss: 0.714071 (0.7662) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.087s, 369.88/s (0.184s, 173.49/s) LR: 5.000e-03 Data: 0.001 (0.083) +2025-04-18 10:56:12,834 - train: [ INFO] - Train: 47 [ 100/461 ( 22%)] Loss: 0.689896 (0.7408) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.29/s (0.139s, 230.74/s) LR: 5.000e-03 Data: 0.000 (0.042) +2025-04-18 10:56:19,398 - train: [ INFO] - Train: 47 [ 150/461 ( 33%)] Loss: 0.700812 (0.7308) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.072s, 446.13/s (0.126s, 254.47/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-18 10:56:25,497 - train: [ INFO] - Train: 47 [ 200/461 ( 43%)] Loss: 0.701900 (0.7250) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.180s, 177.92/s (0.117s, 272.39/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-18 10:56:31,478 - train: [ INFO] - Train: 47 [ 250/461 ( 54%)] Loss: 0.703058 (0.7214) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.89/s (0.114s, 281.67/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-18 10:56:37,884 - train: [ INFO] - Train: 47 [ 300/461 ( 65%)] Loss: 0.712009 (0.7200) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.139s, 230.62/s (0.111s, 288.07/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-18 10:56:43,009 - train: [ INFO] - Train: 47 [ 350/461 ( 76%)] Loss: 0.700863 (0.7176) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.128s, 249.12/s (0.109s, 293.58/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-18 10:56:47,864 - train: [ INFO] - Train: 47 [ 400/461 ( 87%)] Loss: 0.697358 (0.7154) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.96/s (0.107s, 299.82/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 10:56:52,935 - train: [ INFO] - Train: 47 [ 450/461 ( 98%)] Loss: 0.693717 (0.7132) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.076s, 423.40/s (0.105s, 303.38/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 10:56:53,697 - train: [ INFO] - Train: 47 [ 460/461 (100%)] Loss: 0.703387 (0.7123) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.072s, 446.88/s (0.105s, 305.27/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 10:57:00,464 - train: [ INFO] - Eval : 47 Time: 6.440 (6.440) Loss: 2.1781 (2.1781) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 10:57:06,208 - train: [ INFO] - Eval : 47 Time: 0.379 (0.239) Loss: 1.7202 (1.9418) Acc@1: 62.5000 (50.9191)Acc@5: 71.8750 (75.3064) +2025-04-18 10:57:08,571 - train: [ INFO] - Eval : 47 Time: 0.022 (0.177) Loss: 2.6478 (1.9464) Acc@1: 0.0000 (50.1157)Acc@5: 50.0000 (74.9807) +2025-04-18 10:57:16,771 - train: [ INFO] - Train: 48 [ 0/461 ( 0%)] Loss: 0.705232 (0.7052) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.091s, 6.29/s (5.091s, 6.29/s) LR: 5.000e-03 Data: 4.937 (4.937) +2025-04-18 10:57:22,083 - train: [ INFO] - Train: 48 [ 50/461 ( 11%)] Loss: 0.716298 (0.7108) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.126s, 254.45/s (0.198s, 161.31/s) LR: 5.000e-03 Data: 0.001 (0.098) +2025-04-18 10:57:27,964 - train: [ INFO] - Train: 48 [ 100/461 ( 22%)] Loss: 0.707439 (0.7097) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 416.06/s (0.143s, 223.19/s) LR: 5.000e-03 Data: 0.001 (0.050) +2025-04-18 10:57:33,125 - train: [ INFO] - Train: 48 [ 150/461 ( 33%)] Loss: 0.696242 (0.7063) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.112s, 284.52/s (0.127s, 252.05/s) LR: 5.000e-03 Data: 0.001 (0.034) +2025-04-18 10:57:37,964 - train: [ INFO] - Train: 48 [ 200/461 ( 43%)] Loss: 0.788890 (0.7228) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.133s, 240.72/s (0.118s, 270.13/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-18 10:57:44,195 - train: [ INFO] - Train: 48 [ 250/461 ( 54%)] Loss: 0.793787 (0.7346) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.08/s (0.113s, 282.72/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-18 10:57:49,064 - train: [ INFO] - Train: 48 [ 300/461 ( 65%)] Loss: 0.701726 (0.7299) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.129s, 247.97/s (0.110s, 291.49/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-18 10:57:55,838 - train: [ INFO] - Train: 48 [ 350/461 ( 76%)] Loss: 0.726478 (0.7295) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.085s, 377.86/s (0.109s, 294.66/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-18 10:58:01,182 - train: [ INFO] - Train: 48 [ 400/461 ( 87%)] Loss: 0.699834 (0.7262) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.073s, 437.42/s (0.108s, 297.38/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-18 10:58:05,873 - train: [ INFO] - Train: 48 [ 450/461 ( 98%)] Loss: 0.703589 (0.7240) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.071s, 451.66/s (0.106s, 303.25/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:58:06,570 - train: [ INFO] - Train: 48 [ 460/461 (100%)] Loss: 0.747829 (0.7261) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1477) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.17/s (0.105s, 305.54/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:58:11,342 - train: [ INFO] - Eval : 48 Time: 4.485 (4.485) Loss: 1.9371 (1.9371) Acc@1: 53.1250 (53.1250)Acc@5: 71.8750 (71.8750) +2025-04-18 10:58:15,506 - train: [ INFO] - Eval : 48 Time: 0.025 (0.170) Loss: 1.7963 (1.9589) Acc@1: 62.5000 (50.9804)Acc@5: 71.8750 (72.7328) +2025-04-18 10:58:17,545 - train: [ INFO] - Eval : 48 Time: 0.014 (0.130) Loss: 2.6742 (1.9640) Acc@1: 0.0000 (50.1928)Acc@5: 50.0000 (73.0918) +2025-04-18 10:58:25,160 - train: [ INFO] - Train: 49 [ 0/461 ( 0%)] Loss: 0.755330 (0.7553) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.775s, 6.70/s (4.775s, 6.70/s) LR: 5.000e-03 Data: 4.657 (4.657) +2025-04-18 10:58:30,436 - train: [ INFO] - Train: 49 [ 50/461 ( 11%)] Loss: 0.710728 (0.7330) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.098s, 326.00/s (0.191s, 167.12/s) LR: 5.000e-03 Data: 0.000 (0.092) +2025-04-18 10:58:35,677 - train: [ INFO] - Train: 49 [ 100/461 ( 22%)] Loss: 0.716860 (0.7276) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 341.12/s (0.147s, 217.62/s) LR: 5.000e-03 Data: 0.001 (0.047) +2025-04-18 10:58:42,054 - train: [ INFO] - Train: 49 [ 150/461 ( 33%)] Loss: 0.763077 (0.7365) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.095s, 335.81/s (0.129s, 248.75/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-18 10:58:47,331 - train: [ INFO] - Train: 49 [ 200/461 ( 43%)] Loss: 0.706094 (0.7304) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.074s, 434.43/s (0.121s, 263.83/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-18 10:58:52,404 - train: [ INFO] - Train: 49 [ 250/461 ( 54%)] Loss: 0.700235 (0.7254) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.099s, 324.66/s (0.117s, 274.42/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-18 10:58:58,099 - train: [ INFO] - Train: 49 [ 300/461 ( 65%)] Loss: 0.715716 (0.7240) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.069s, 461.16/s (0.112s, 286.36/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 10:59:03,377 - train: [ INFO] - Train: 49 [ 350/461 ( 76%)] Loss: 0.695484 (0.7204) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.123s, 259.46/s (0.110s, 290.63/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-18 10:59:09,535 - train: [ INFO] - Train: 49 [ 400/461 ( 87%)] Loss: 0.707010 (0.7189) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.094s, 341.57/s (0.108s, 295.96/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:59:14,164 - train: [ INFO] - Train: 49 [ 450/461 ( 98%)] Loss: 0.698110 (0.7169) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.58/s (0.106s, 301.93/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 10:59:14,898 - train: [ INFO] - Train: 49 [ 460/461 (100%)] Loss: 0.690001 (0.7144) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.41/s (0.105s, 304.02/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 10:59:20,914 - train: [ INFO] - Eval : 49 Time: 5.674 (5.674) Loss: 2.0410 (2.0410) Acc@1: 53.1250 (53.1250)Acc@5: 78.1250 (78.1250) +2025-04-18 10:59:24,254 - train: [ INFO] - Eval : 49 Time: 0.240 (0.176) Loss: 1.8499 (1.9809) Acc@1: 53.1250 (50.3064)Acc@5: 78.1250 (73.5294) +2025-04-18 10:59:26,238 - train: [ INFO] - Eval : 49 Time: 0.016 (0.134) Loss: 3.2646 (1.9756) Acc@1: 0.0000 (49.4217)Acc@5: 50.0000 (74.1712) +2025-04-18 10:59:35,094 - train: [ INFO] - Train: 50 [ 0/461 ( 0%)] Loss: 0.720967 (0.7210) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.722s, 5.59/s (5.722s, 5.59/s) LR: 5.000e-03 Data: 5.548 (5.548) +2025-04-18 10:59:39,948 - train: [ INFO] - Train: 50 [ 50/461 ( 11%)] Loss: 0.764811 (0.7429) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 458.87/s (0.203s, 157.77/s) LR: 5.000e-03 Data: 0.000 (0.110) +2025-04-18 10:59:44,852 - train: [ INFO] - Train: 50 [ 100/461 ( 22%)] Loss: 0.753367 (0.7464) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 431.72/s (0.148s, 216.19/s) LR: 5.000e-03 Data: 0.000 (0.056) +2025-04-18 10:59:51,057 - train: [ INFO] - Train: 50 [ 150/461 ( 33%)] Loss: 0.700106 (0.7348) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.39/s (0.130s, 246.92/s) LR: 5.000e-03 Data: 0.001 (0.038) +2025-04-18 10:59:55,719 - train: [ INFO] - Train: 50 [ 200/461 ( 43%)] Loss: 0.707171 (0.7293) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 443.13/s (0.119s, 269.28/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-18 11:00:00,618 - train: [ INFO] - Train: 50 [ 250/461 ( 54%)] Loss: 0.761058 (0.7346) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.106s, 301.59/s (0.114s, 281.47/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-18 11:00:05,397 - train: [ INFO] - Train: 50 [ 300/461 ( 65%)] Loss: 0.715948 (0.7319) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 336.75/s (0.110s, 291.05/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-18 11:00:10,499 - train: [ INFO] - Train: 50 [ 350/461 ( 76%)] Loss: 0.688408 (0.7265) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 413.80/s (0.108s, 296.37/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-18 11:00:16,720 - train: [ INFO] - Train: 50 [ 400/461 ( 87%)] Loss: 0.697616 (0.7233) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 439.18/s (0.106s, 301.16/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 11:00:23,232 - train: [ INFO] - Train: 50 [ 450/461 ( 98%)] Loss: 0.747033 (0.7256) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.073s, 438.63/s (0.105s, 304.26/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:00:23,942 - train: [ INFO] - Train: 50 [ 460/461 (100%)] Loss: 0.707808 (0.7240) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.40/s (0.104s, 306.49/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:00:29,656 - train: [ INFO] - Eval : 50 Time: 5.346 (5.346) Loss: 2.1652 (2.1652) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 11:00:34,065 - train: [ INFO] - Eval : 50 Time: 0.452 (0.191) Loss: 1.9072 (1.9987) Acc@1: 46.8750 (47.5490)Acc@5: 75.0000 (74.0809) +2025-04-18 11:00:35,815 - train: [ INFO] - Eval : 50 Time: 0.015 (0.140) Loss: 2.6764 (2.0023) Acc@1: 0.0000 (47.6870)Acc@5: 100.0000 (74.1712) +2025-04-18 11:00:43,744 - train: [ INFO] - Train: 51 [ 0/461 ( 0%)] Loss: 0.697712 (0.6977) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.074s, 6.31/s (5.074s, 6.31/s) LR: 5.000e-03 Data: 4.928 (4.928) +2025-04-18 11:00:48,923 - train: [ INFO] - Train: 51 [ 50/461 ( 11%)] Loss: 0.695291 (0.6965) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.090s, 354.08/s (0.196s, 162.98/s) LR: 5.000e-03 Data: 0.000 (0.099) +2025-04-18 11:00:53,476 - train: [ INFO] - Train: 51 [ 100/461 ( 22%)] Loss: 0.790029 (0.7277) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.26/s (0.143s, 224.14/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-18 11:00:59,239 - train: [ INFO] - Train: 51 [ 150/461 ( 33%)] Loss: 0.700880 (0.7210) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.070s, 457.05/s (0.126s, 254.02/s) LR: 5.000e-03 Data: 0.001 (0.034) +2025-04-18 11:01:04,990 - train: [ INFO] - Train: 51 [ 200/461 ( 43%)] Loss: 0.693225 (0.7154) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.097s, 329.98/s (0.120s, 266.51/s) LR: 5.000e-03 Data: 0.001 (0.026) +2025-04-18 11:01:09,947 - train: [ INFO] - Train: 51 [ 250/461 ( 54%)] Loss: 0.710928 (0.7147) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.111s, 288.26/s (0.115s, 279.13/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-18 11:01:14,904 - train: [ INFO] - Train: 51 [ 300/461 ( 65%)] Loss: 0.701362 (0.7128) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.100s, 320.74/s (0.111s, 287.87/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-18 11:01:20,544 - train: [ INFO] - Train: 51 [ 350/461 ( 76%)] Loss: 0.703039 (0.7116) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.142s, 224.90/s (0.109s, 292.31/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-18 11:01:25,193 - train: [ INFO] - Train: 51 [ 400/461 ( 87%)] Loss: 0.684733 (0.7086) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.072s, 446.12/s (0.107s, 300.02/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:01:29,506 - train: [ INFO] - Train: 51 [ 450/461 ( 98%)] Loss: 0.709730 (0.7087) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.072s, 443.40/s (0.104s, 307.03/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 11:01:30,247 - train: [ INFO] - Train: 51 [ 460/461 (100%)] Loss: 0.700353 (0.7079) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.074s, 435.11/s (0.104s, 309.02/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 11:01:35,649 - train: [ INFO] - Eval : 51 Time: 5.100 (5.100) Loss: 2.1418 (2.1418) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-18 11:01:40,248 - train: [ INFO] - Eval : 51 Time: 0.091 (0.190) Loss: 1.8857 (2.0143) Acc@1: 53.1250 (49.0196)Acc@5: 75.0000 (73.1618) +2025-04-18 11:01:41,848 - train: [ INFO] - Eval : 51 Time: 0.014 (0.138) Loss: 3.3826 (2.0168) Acc@1: 0.0000 (49.0748)Acc@5: 50.0000 (73.5929) +2025-04-18 11:01:50,986 - train: [ INFO] - Train: 52 [ 0/461 ( 0%)] Loss: 0.707132 (0.7071) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.263s, 5.11/s (6.263s, 5.11/s) LR: 5.000e-03 Data: 6.129 (6.129) +2025-04-18 11:01:56,597 - train: [ INFO] - Train: 52 [ 50/461 ( 11%)] Loss: 0.701091 (0.7041) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.163s, 195.75/s (0.230s, 138.93/s) LR: 5.000e-03 Data: 0.001 (0.121) +2025-04-18 11:02:01,621 - train: [ INFO] - Train: 52 [ 100/461 ( 22%)] Loss: 0.706072 (0.7048) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 334.58/s (0.162s, 197.66/s) LR: 5.000e-03 Data: 0.001 (0.062) +2025-04-18 11:02:06,177 - train: [ INFO] - Train: 52 [ 150/461 ( 33%)] Loss: 0.693560 (0.7020) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.139s, 230.85/s (0.137s, 233.38/s) LR: 5.000e-03 Data: 0.001 (0.042) +2025-04-18 11:02:11,177 - train: [ INFO] - Train: 52 [ 200/461 ( 43%)] Loss: 0.682215 (0.6980) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 431.20/s (0.127s, 252.70/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-18 11:02:17,084 - train: [ INFO] - Train: 52 [ 250/461 ( 54%)] Loss: 0.706206 (0.6994) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 416.15/s (0.119s, 268.40/s) LR: 5.000e-03 Data: 0.001 (0.025) +2025-04-18 11:02:21,861 - train: [ INFO] - Train: 52 [ 300/461 ( 65%)] Loss: 0.699506 (0.6994) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 438.68/s (0.114s, 279.54/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-18 11:02:27,246 - train: [ INFO] - Train: 52 [ 350/461 ( 76%)] Loss: 0.747055 (0.7054) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.110s, 290.09/s (0.113s, 283.54/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 11:02:32,283 - train: [ INFO] - Train: 52 [ 400/461 ( 87%)] Loss: 0.700087 (0.7048) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 442.43/s (0.111s, 288.88/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 11:02:36,943 - train: [ INFO] - Train: 52 [ 450/461 ( 98%)] Loss: 0.702216 (0.7045) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 471.41/s (0.108s, 295.35/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 11:02:37,647 - train: [ INFO] - Train: 52 [ 460/461 (100%)] Loss: 0.704822 (0.7045) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 437.68/s (0.108s, 297.64/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-18 11:02:41,529 - train: [ INFO] - Eval : 52 Time: 3.447 (3.447) Loss: 2.2612 (2.2612) Acc@1: 37.5000 (37.5000)Acc@5: 65.6250 (65.6250) +2025-04-18 11:02:45,465 - train: [ INFO] - Eval : 52 Time: 0.052 (0.145) Loss: 1.7169 (1.9855) Acc@1: 56.2500 (49.2647)Acc@5: 75.0000 (73.4069) +2025-04-18 11:02:46,852 - train: [ INFO] - Eval : 52 Time: 0.014 (0.107) Loss: 2.8487 (1.9849) Acc@1: 0.0000 (48.9206)Acc@5: 100.0000 (73.7857) +2025-04-18 11:02:59,193 - train: [ INFO] - Train: 53 [ 0/461 ( 0%)] Loss: 0.715954 (0.7160) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.485s, 5.83/s (5.485s, 5.83/s) LR: 5.000e-03 Data: 5.338 (5.338) +2025-04-18 11:03:05,462 - train: [ INFO] - Train: 53 [ 50/461 ( 11%)] Loss: 0.703110 (0.7095) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 439.72/s (0.230s, 139.37/s) LR: 5.000e-03 Data: 0.000 (0.150) +2025-04-18 11:03:14,266 - train: [ INFO] - Train: 53 [ 100/461 ( 22%)] Loss: 0.699389 (0.7062) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 438.71/s (0.184s, 173.94/s) LR: 5.000e-03 Data: 0.001 (0.105) +2025-04-18 11:03:21,105 - train: [ INFO] - Train: 53 [ 150/461 ( 33%)] Loss: 0.698684 (0.7043) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 411.57/s (0.167s, 191.14/s) LR: 5.000e-03 Data: 0.001 (0.087) +2025-04-18 11:03:28,436 - train: [ INFO] - Train: 53 [ 200/461 ( 43%)] Loss: 0.721014 (0.7076) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 422.98/s (0.161s, 198.78/s) LR: 5.000e-03 Data: 0.001 (0.078) +2025-04-18 11:03:35,098 - train: [ INFO] - Train: 53 [ 250/461 ( 54%)] Loss: 0.695086 (0.7055) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.85/s (0.149s, 214.24/s) LR: 5.000e-03 Data: 0.001 (0.065) +2025-04-18 11:03:40,309 - train: [ INFO] - Train: 53 [ 300/461 ( 65%)] Loss: 0.694342 (0.7039) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 338.18/s (0.141s, 227.18/s) LR: 5.000e-03 Data: 0.001 (0.054) +2025-04-18 11:03:45,470 - train: [ INFO] - Train: 53 [ 350/461 ( 76%)] Loss: 0.727151 (0.7068) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 405.97/s (0.135s, 237.24/s) LR: 5.000e-03 Data: 0.001 (0.047) +2025-04-18 11:03:50,118 - train: [ INFO] - Train: 53 [ 400/461 ( 87%)] Loss: 0.700170 (0.7061) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 348.60/s (0.129s, 247.97/s) LR: 5.000e-03 Data: 0.000 (0.041) +2025-04-18 11:03:54,769 - train: [ INFO] - Train: 53 [ 450/461 ( 98%)] Loss: 0.701237 (0.7056) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.21/s (0.125s, 256.92/s) LR: 5.000e-03 Data: 0.000 (0.036) +2025-04-18 11:03:55,498 - train: [ INFO] - Train: 53 [ 460/461 (100%)] Loss: 0.698010 (0.7049) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 433.37/s (0.123s, 259.30/s) LR: 5.000e-03 Data: 0.000 (0.036) +2025-04-18 11:04:01,556 - train: [ INFO] - Eval : 53 Time: 5.726 (5.726) Loss: 2.2868 (2.2868) Acc@1: 37.5000 (37.5000)Acc@5: 71.8750 (71.8750) +2025-04-18 11:04:04,188 - train: [ INFO] - Eval : 53 Time: 0.056 (0.164) Loss: 1.8065 (1.9742) Acc@1: 65.6250 (49.6324)Acc@5: 71.8750 (73.7745) +2025-04-18 11:04:05,744 - train: [ INFO] - Eval : 53 Time: 0.014 (0.121) Loss: 2.7989 (1.9770) Acc@1: 0.0000 (49.0748)Acc@5: 100.0000 (74.2483) +2025-04-18 11:04:15,011 - train: [ INFO] - Train: 54 [ 0/461 ( 0%)] Loss: 0.702109 (0.7021) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.280s, 5.10/s (6.280s, 5.10/s) LR: 5.000e-03 Data: 6.068 (6.068) +2025-04-18 11:04:21,591 - train: [ INFO] - Train: 54 [ 50/461 ( 11%)] Loss: 0.719222 (0.7107) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 320.97/s (0.223s, 143.67/s) LR: 5.000e-03 Data: 0.001 (0.123) +2025-04-18 11:04:26,810 - train: [ INFO] - Train: 54 [ 100/461 ( 22%)] Loss: 0.730593 (0.7173) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.155s, 207.03/s (0.162s, 197.87/s) LR: 5.000e-03 Data: 0.002 (0.062) +2025-04-18 11:04:32,851 - train: [ INFO] - Train: 54 [ 150/461 ( 33%)] Loss: 0.698832 (0.7127) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.18/s (0.138s, 231.21/s) LR: 5.000e-03 Data: 0.000 (0.042) +2025-04-18 11:04:37,423 - train: [ INFO] - Train: 54 [ 200/461 ( 43%)] Loss: 0.712100 (0.7126) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.104s, 307.63/s (0.126s, 253.82/s) LR: 5.000e-03 Data: 0.001 (0.032) +2025-04-18 11:04:43,697 - train: [ INFO] - Train: 54 [ 250/461 ( 54%)] Loss: 0.720399 (0.7139) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.102s, 314.22/s (0.119s, 268.20/s) LR: 5.000e-03 Data: 0.001 (0.025) +2025-04-18 11:04:48,691 - train: [ INFO] - Train: 54 [ 300/461 ( 65%)] Loss: 0.694845 (0.7112) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.74/s (0.115s, 277.47/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-18 11:04:53,828 - train: [ INFO] - Train: 54 [ 350/461 ( 76%)] Loss: 0.718047 (0.7120) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.138s, 232.45/s (0.113s, 284.23/s) LR: 5.000e-03 Data: 0.024 (0.019) +2025-04-18 11:04:59,273 - train: [ INFO] - Train: 54 [ 400/461 ( 87%)] Loss: 0.713037 (0.7121) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 391.60/s (0.111s, 289.08/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 11:05:04,180 - train: [ INFO] - Train: 54 [ 450/461 ( 98%)] Loss: 0.701591 (0.7111) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.29/s (0.109s, 293.18/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 11:05:04,950 - train: [ INFO] - Train: 54 [ 460/461 (100%)] Loss: 0.714579 (0.7114) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 396.96/s (0.108s, 295.14/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 11:05:10,801 - train: [ INFO] - Eval : 54 Time: 5.454 (5.454) Loss: 2.2140 (2.2140) Acc@1: 56.2500 (56.2500)Acc@5: 71.8750 (71.8750) +2025-04-18 11:05:14,742 - train: [ INFO] - Eval : 54 Time: 0.050 (0.184) Loss: 1.6768 (1.9732) Acc@1: 59.3750 (50.1225)Acc@5: 78.1250 (74.3873) +2025-04-18 11:05:16,339 - train: [ INFO] - Eval : 54 Time: 0.015 (0.134) Loss: 2.8713 (1.9720) Acc@1: 0.0000 (49.6145)Acc@5: 100.0000 (75.0578) +2025-04-18 11:05:22,895 - train: [ INFO] - Train: 55 [ 0/461 ( 0%)] Loss: 0.710015 (0.7100) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 3.827s, 8.36/s (3.827s, 8.36/s) LR: 5.000e-03 Data: 3.720 (3.720) +2025-04-18 11:05:29,291 - train: [ INFO] - Train: 55 [ 50/461 ( 11%)] Loss: 0.719084 (0.7145) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.47/s (0.195s, 164.10/s) LR: 5.000e-03 Data: 0.001 (0.085) +2025-04-18 11:05:35,380 - train: [ INFO] - Train: 55 [ 100/461 ( 22%)] Loss: 0.779103 (0.7361) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 463.17/s (0.144s, 221.57/s) LR: 5.000e-03 Data: 0.000 (0.043) +2025-04-18 11:05:40,490 - train: [ INFO] - Train: 55 [ 150/461 ( 33%)] Loss: 0.752929 (0.7403) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 460.84/s (0.129s, 248.90/s) LR: 5.000e-03 Data: 0.001 (0.029) +2025-04-18 11:05:47,288 - train: [ INFO] - Train: 55 [ 200/461 ( 43%)] Loss: 0.742571 (0.7407) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 439.04/s (0.123s, 261.00/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-18 11:05:53,902 - train: [ INFO] - Train: 55 [ 250/461 ( 54%)] Loss: 0.703954 (0.7346) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.089s, 357.73/s (0.118s, 271.16/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 11:05:59,580 - train: [ INFO] - Train: 55 [ 300/461 ( 65%)] Loss: 0.707071 (0.7307) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.131s, 245.05/s (0.114s, 280.77/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 11:06:04,810 - train: [ INFO] - Train: 55 [ 350/461 ( 76%)] Loss: 0.711467 (0.7283) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.99/s (0.112s, 286.04/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:06:09,732 - train: [ INFO] - Train: 55 [ 400/461 ( 87%)] Loss: 0.689916 (0.7240) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 458.26/s (0.109s, 292.95/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 11:06:15,111 - train: [ INFO] - Train: 55 [ 450/461 ( 98%)] Loss: 0.704676 (0.7221) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.34/s (0.107s, 299.28/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 11:06:15,892 - train: [ INFO] - Train: 55 [ 460/461 (100%)] Loss: 0.692643 (0.7194) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.06/s (0.106s, 301.11/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 11:06:21,594 - train: [ INFO] - Eval : 55 Time: 5.327 (5.327) Loss: 2.1299 (2.1299) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:06:25,305 - train: [ INFO] - Eval : 55 Time: 0.056 (0.177) Loss: 1.6598 (1.9293) Acc@1: 62.5000 (50.5515)Acc@5: 78.1250 (74.7549) +2025-04-18 11:06:26,993 - train: [ INFO] - Eval : 55 Time: 0.016 (0.131) Loss: 3.0091 (1.9298) Acc@1: 0.0000 (50.2699)Acc@5: 50.0000 (75.4048) +2025-04-18 11:06:34,867 - train: [ INFO] - Train: 56 [ 0/461 ( 0%)] Loss: 0.727897 (0.7279) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.816s, 6.64/s (4.816s, 6.64/s) LR: 5.000e-03 Data: 4.676 (4.676) +2025-04-18 11:06:40,447 - train: [ INFO] - Train: 56 [ 50/461 ( 11%)] Loss: 0.690632 (0.7093) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 428.55/s (0.195s, 164.36/s) LR: 5.000e-03 Data: 0.001 (0.093) +2025-04-18 11:06:46,463 - train: [ INFO] - Train: 56 [ 100/461 ( 22%)] Loss: 0.705824 (0.7081) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.137s, 233.03/s (0.154s, 207.33/s) LR: 5.000e-03 Data: 0.000 (0.047) +2025-04-18 11:06:52,780 - train: [ INFO] - Train: 56 [ 150/461 ( 33%)] Loss: 0.808840 (0.7333) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.096s, 334.72/s (0.135s, 236.53/s) LR: 5.000e-03 Data: 0.001 (0.032) +2025-04-18 11:06:59,569 - train: [ INFO] - Train: 56 [ 200/461 ( 43%)] Loss: 0.695443 (0.7257) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.120s, 267.57/s (0.127s, 252.16/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-18 11:07:06,063 - train: [ INFO] - Train: 56 [ 250/461 ( 54%)] Loss: 0.684533 (0.7189) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.106s, 301.23/s (0.121s, 263.58/s) LR: 5.000e-03 Data: 0.001 (0.020) +2025-04-18 11:07:11,928 - train: [ INFO] - Train: 56 [ 300/461 ( 65%)] Loss: 0.703383 (0.7167) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.110s, 290.30/s (0.120s, 266.91/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-18 11:07:17,220 - train: [ INFO] - Train: 56 [ 350/461 ( 76%)] Loss: 0.698240 (0.7143) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.071s, 451.15/s (0.117s, 273.29/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-18 11:07:22,905 - train: [ INFO] - Train: 56 [ 400/461 ( 87%)] Loss: 0.724639 (0.7155) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.072s, 441.45/s (0.116s, 276.78/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-18 11:07:27,829 - train: [ INFO] - Train: 56 [ 450/461 ( 98%)] Loss: 0.754114 (0.7194) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.070s, 456.28/s (0.113s, 282.74/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 11:07:28,550 - train: [ INFO] - Train: 56 [ 460/461 (100%)] Loss: 0.691349 (0.7168) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.071s, 453.12/s (0.112s, 285.03/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 11:07:34,312 - train: [ INFO] - Eval : 56 Time: 5.489 (5.489) Loss: 1.9741 (1.9741) Acc@1: 62.5000 (62.5000)Acc@5: 68.7500 (68.7500) +2025-04-18 11:07:37,749 - train: [ INFO] - Eval : 56 Time: 0.063 (0.175) Loss: 1.8250 (2.0033) Acc@1: 53.1250 (49.0196)Acc@5: 75.0000 (74.1422) +2025-04-18 11:07:39,500 - train: [ INFO] - Eval : 56 Time: 0.014 (0.130) Loss: 3.7850 (1.9945) Acc@1: 0.0000 (48.8820)Acc@5: 0.0000 (74.7109) +2025-04-18 11:07:48,013 - train: [ INFO] - Train: 57 [ 0/461 ( 0%)] Loss: 0.722430 (0.7224) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.440s, 5.88/s (5.440s, 5.88/s) LR: 5.000e-03 Data: 5.292 (5.292) +2025-04-18 11:07:53,448 - train: [ INFO] - Train: 57 [ 50/461 ( 11%)] Loss: 0.685434 (0.7039) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 341.55/s (0.209s, 153.18/s) LR: 5.000e-03 Data: 0.001 (0.104) +2025-04-18 11:07:59,192 - train: [ INFO] - Train: 57 [ 100/461 ( 22%)] Loss: 0.780795 (0.7296) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.071s, 453.77/s (0.152s, 210.78/s) LR: 5.000e-03 Data: 0.000 (0.053) +2025-04-18 11:08:05,484 - train: [ INFO] - Train: 57 [ 150/461 ( 33%)] Loss: 0.709982 (0.7247) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.68/s (0.132s, 241.56/s) LR: 5.000e-03 Data: 0.000 (0.036) +2025-04-18 11:08:11,780 - train: [ INFO] - Train: 57 [ 200/461 ( 43%)] Loss: 0.699269 (0.7196) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.84/s (0.123s, 259.62/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-18 11:08:16,715 - train: [ INFO] - Train: 57 [ 250/461 ( 54%)] Loss: 0.698406 (0.7161) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.134s, 238.84/s (0.117s, 272.68/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-18 11:08:23,456 - train: [ INFO] - Train: 57 [ 300/461 ( 65%)] Loss: 0.696406 (0.7132) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.123s, 260.03/s (0.115s, 278.61/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-18 11:08:28,521 - train: [ INFO] - Train: 57 [ 350/461 ( 76%)] Loss: 0.701367 (0.7118) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.122s, 262.49/s (0.112s, 284.87/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-18 11:08:33,469 - train: [ INFO] - Train: 57 [ 400/461 ( 87%)] Loss: 0.712982 (0.7119) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.103s, 312.16/s (0.110s, 290.33/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 11:08:38,980 - train: [ INFO] - Train: 57 [ 450/461 ( 98%)] Loss: 0.696513 (0.7104) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.072s, 443.58/s (0.108s, 294.98/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:08:39,767 - train: [ INFO] - Train: 57 [ 460/461 (100%)] Loss: 0.699014 (0.7093) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.95/s (0.108s, 296.81/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 11:08:44,932 - train: [ INFO] - Eval : 57 Time: 4.901 (4.901) Loss: 2.0645 (2.0645) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 11:08:49,450 - train: [ INFO] - Eval : 57 Time: 0.028 (0.185) Loss: 1.7151 (1.9460) Acc@1: 56.2500 (49.4485)Acc@5: 78.1250 (75.1225) +2025-04-18 11:08:51,586 - train: [ INFO] - Eval : 57 Time: 0.014 (0.141) Loss: 3.4261 (1.9509) Acc@1: 0.0000 (49.1133)Acc@5: 0.0000 (74.4410) +2025-04-18 11:09:00,560 - train: [ INFO] - Train: 58 [ 0/461 ( 0%)] Loss: 0.697037 (0.6970) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.100s, 5.25/s (6.100s, 5.25/s) LR: 5.000e-03 Data: 5.940 (5.940) +2025-04-18 11:09:06,081 - train: [ INFO] - Train: 58 [ 50/461 ( 11%)] Loss: 0.688782 (0.6929) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.13/s (0.220s, 145.68/s) LR: 5.000e-03 Data: 0.000 (0.118) +2025-04-18 11:09:11,063 - train: [ INFO] - Train: 58 [ 100/461 ( 22%)] Loss: 0.694363 (0.6934) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 321.02/s (0.156s, 205.04/s) LR: 5.000e-03 Data: 0.001 (0.060) +2025-04-18 11:09:17,151 - train: [ INFO] - Train: 58 [ 150/461 ( 33%)] Loss: 0.691501 (0.6929) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 398.36/s (0.134s, 238.38/s) LR: 5.000e-03 Data: 0.001 (0.040) +2025-04-18 11:09:23,588 - train: [ INFO] - Train: 58 [ 200/461 ( 43%)] Loss: 0.695354 (0.6934) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 460.62/s (0.126s, 254.86/s) LR: 5.000e-03 Data: 0.001 (0.030) +2025-04-18 11:09:28,954 - train: [ INFO] - Train: 58 [ 250/461 ( 54%)] Loss: 0.693746 (0.6935) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 433.13/s (0.121s, 264.88/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-18 11:09:33,972 - train: [ INFO] - Train: 58 [ 300/461 ( 65%)] Loss: 0.707028 (0.6954) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 332.51/s (0.117s, 274.19/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-18 11:09:39,354 - train: [ INFO] - Train: 58 [ 350/461 ( 76%)] Loss: 0.691938 (0.6950) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 447.75/s (0.114s, 280.74/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 11:09:45,122 - train: [ INFO] - Train: 58 [ 400/461 ( 87%)] Loss: 0.703239 (0.6959) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 451.04/s (0.111s, 287.69/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 11:09:50,001 - train: [ INFO] - Train: 58 [ 450/461 ( 98%)] Loss: 0.699061 (0.6962) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.23/s (0.109s, 293.61/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 11:09:50,710 - train: [ INFO] - Train: 58 [ 460/461 (100%)] Loss: 0.782870 (0.7041) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.068s, 467.16/s (0.108s, 295.89/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 11:09:56,546 - train: [ INFO] - Eval : 58 Time: 5.426 (5.426) Loss: 2.2690 (2.2690) Acc@1: 37.5000 (37.5000)Acc@5: 68.7500 (68.7500) +2025-04-18 11:10:02,129 - train: [ INFO] - Eval : 58 Time: 0.173 (0.215) Loss: 1.8743 (2.0038) Acc@1: 56.2500 (47.6716)Acc@5: 75.0000 (74.5098) +2025-04-18 11:10:04,659 - train: [ INFO] - Eval : 58 Time: 0.015 (0.165) Loss: 3.1532 (2.0026) Acc@1: 0.0000 (47.1473)Acc@5: 0.0000 (75.0578) +2025-04-18 11:10:12,215 - train: [ INFO] - Train: 59 [ 0/461 ( 0%)] Loss: 0.752002 (0.7520) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 4.265s, 7.50/s (4.265s, 7.50/s) LR: 5.000e-03 Data: 4.086 (4.086) +2025-04-18 11:10:17,841 - train: [ INFO] - Train: 59 [ 50/461 ( 11%)] Loss: 0.690228 (0.7211) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.073s, 437.59/s (0.187s, 171.39/s) LR: 5.000e-03 Data: 0.000 (0.082) +2025-04-18 11:10:23,410 - train: [ INFO] - Train: 59 [ 100/461 ( 22%)] Loss: 0.694326 (0.7122) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.075s, 427.64/s (0.148s, 216.37/s) LR: 5.000e-03 Data: 0.001 (0.042) +2025-04-18 11:10:29,539 - train: [ INFO] - Train: 59 [ 150/461 ( 33%)] Loss: 0.692826 (0.7073) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.071s, 453.40/s (0.129s, 247.98/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-18 11:10:34,476 - train: [ INFO] - Train: 59 [ 200/461 ( 43%)] Loss: 0.719321 (0.7097) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.080s, 398.57/s (0.119s, 268.23/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-18 11:10:40,814 - train: [ INFO] - Train: 59 [ 250/461 ( 54%)] Loss: 0.707640 (0.7094) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.144s, 222.20/s (0.114s, 279.51/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 11:10:46,469 - train: [ INFO] - Train: 59 [ 300/461 ( 65%)] Loss: 0.708008 (0.7092) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.116s, 274.95/s (0.113s, 282.58/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-18 11:10:51,770 - train: [ INFO] - Train: 59 [ 350/461 ( 76%)] Loss: 0.698290 (0.7078) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.073s, 437.32/s (0.112s, 286.83/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-18 11:10:57,088 - train: [ INFO] - Train: 59 [ 400/461 ( 87%)] Loss: 0.703098 (0.7073) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.76/s (0.110s, 290.72/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 11:11:03,251 - train: [ INFO] - Train: 59 [ 450/461 ( 98%)] Loss: 0.699980 (0.7066) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.069s, 462.70/s (0.108s, 296.57/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 11:11:04,028 - train: [ INFO] - Train: 59 [ 460/461 (100%)] Loss: 0.696602 (0.7057) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.073s, 436.11/s (0.107s, 298.43/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 11:11:09,542 - train: [ INFO] - Eval : 59 Time: 5.231 (5.231) Loss: 2.0120 (2.0120) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 11:11:12,797 - train: [ INFO] - Eval : 59 Time: 0.047 (0.166) Loss: 1.8797 (1.9768) Acc@1: 53.1250 (49.8162)Acc@5: 71.8750 (75.9804) +2025-04-18 11:11:14,074 - train: [ INFO] - Eval : 59 Time: 0.015 (0.119) Loss: 2.9774 (1.9888) Acc@1: 0.0000 (49.1519)Acc@5: 50.0000 (75.1349) +2025-04-18 11:11:22,006 - train: [ INFO] - Train: 60 [ 0/461 ( 0%)] Loss: 0.697206 (0.6972) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.560s, 7.02/s (4.560s, 7.02/s) LR: 5.000e-03 Data: 4.418 (4.418) +2025-04-18 11:11:26,906 - train: [ INFO] - Train: 60 [ 50/461 ( 11%)] Loss: 0.698038 (0.6976) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 347.07/s (0.180s, 177.72/s) LR: 5.000e-03 Data: 0.001 (0.087) +2025-04-18 11:11:32,115 - train: [ INFO] - Train: 60 [ 100/461 ( 22%)] Loss: 0.721369 (0.7055) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.65/s (0.137s, 234.37/s) LR: 5.000e-03 Data: 0.001 (0.044) +2025-04-18 11:11:38,509 - train: [ INFO] - Train: 60 [ 150/461 ( 33%)] Loss: 0.692259 (0.7022) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 408.65/s (0.125s, 255.26/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-18 11:11:43,690 - train: [ INFO] - Train: 60 [ 200/461 ( 43%)] Loss: 0.699240 (0.7016) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 463.34/s (0.119s, 270.03/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-18 11:11:49,086 - train: [ INFO] - Train: 60 [ 250/461 ( 54%)] Loss: 0.691466 (0.6999) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.109s, 292.33/s (0.116s, 276.95/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 11:11:55,097 - train: [ INFO] - Train: 60 [ 300/461 ( 65%)] Loss: 0.702336 (0.7003) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 414.31/s (0.111s, 288.22/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-18 11:12:00,394 - train: [ INFO] - Train: 60 [ 350/461 ( 76%)] Loss: 0.675410 (0.6972) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.146s, 218.47/s (0.110s, 292.12/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:12:05,383 - train: [ INFO] - Train: 60 [ 400/461 ( 87%)] Loss: 0.692687 (0.6967) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 347.30/s (0.107s, 297.83/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 11:12:09,790 - train: [ INFO] - Train: 60 [ 450/461 ( 98%)] Loss: 0.709255 (0.6979) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 460.67/s (0.105s, 304.95/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 11:12:10,500 - train: [ INFO] - Train: 60 [ 460/461 (100%)] Loss: 0.736195 (0.7014) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 442.31/s (0.104s, 307.14/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 11:12:17,277 - train: [ INFO] - Eval : 60 Time: 6.472 (6.472) Loss: 2.0720 (2.0720) Acc@1: 40.6250 (40.6250)Acc@5: 68.7500 (68.7500) +2025-04-18 11:12:21,326 - train: [ INFO] - Eval : 60 Time: 0.344 (0.206) Loss: 1.8267 (1.9420) Acc@1: 56.2500 (49.5098)Acc@5: 75.0000 (75.8578) +2025-04-18 11:12:23,853 - train: [ INFO] - Eval : 60 Time: 0.016 (0.159) Loss: 2.7064 (1.9526) Acc@1: 0.0000 (49.0362)Acc@5: 100.0000 (75.6361) +2025-04-18 11:12:33,366 - train: [ INFO] - Train: 61 [ 0/461 ( 0%)] Loss: 0.694232 (0.6942) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.452s, 4.96/s (6.452s, 4.96/s) LR: 5.000e-03 Data: 6.284 (6.284) +2025-04-18 11:12:38,597 - train: [ INFO] - Train: 61 [ 50/461 ( 11%)] Loss: 0.700604 (0.6974) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.130s, 246.32/s (0.224s, 142.83/s) LR: 5.000e-03 Data: 0.001 (0.125) +2025-04-18 11:12:43,956 - train: [ INFO] - Train: 61 [ 100/461 ( 22%)] Loss: 0.694351 (0.6964) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.106s, 300.87/s (0.164s, 195.32/s) LR: 5.000e-03 Data: 0.001 (0.064) +2025-04-18 11:12:50,069 - train: [ INFO] - Train: 61 [ 150/461 ( 33%)] Loss: 0.697002 (0.6965) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.117s, 272.75/s (0.140s, 228.69/s) LR: 5.000e-03 Data: 0.001 (0.043) +2025-04-18 11:12:55,186 - train: [ INFO] - Train: 61 [ 200/461 ( 43%)] Loss: 0.707289 (0.6987) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.11/s (0.129s, 247.86/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-18 11:13:00,060 - train: [ INFO] - Train: 61 [ 250/461 ( 54%)] Loss: 0.771083 (0.7108) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 457.53/s (0.121s, 263.59/s) LR: 5.000e-03 Data: 0.001 (0.026) +2025-04-18 11:13:04,947 - train: [ INFO] - Train: 61 [ 300/461 ( 65%)] Loss: 0.708912 (0.7105) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 414.85/s (0.116s, 275.95/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-18 11:13:11,408 - train: [ INFO] - Train: 61 [ 350/461 ( 76%)] Loss: 0.730239 (0.7130) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.141s, 227.37/s (0.113s, 282.75/s) LR: 5.000e-03 Data: 0.022 (0.019) +2025-04-18 11:13:16,714 - train: [ INFO] - Train: 61 [ 400/461 ( 87%)] Loss: 0.744026 (0.7164) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 404.07/s (0.112s, 286.54/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-18 11:13:21,711 - train: [ INFO] - Train: 61 [ 450/461 ( 98%)] Loss: 0.753309 (0.7201) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 453.70/s (0.110s, 291.15/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 11:13:22,443 - train: [ INFO] - Train: 61 [ 460/461 (100%)] Loss: 0.726937 (0.7207) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 403.46/s (0.109s, 293.32/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 11:13:28,477 - train: [ INFO] - Eval : 61 Time: 5.720 (5.720) Loss: 2.0666 (2.0666) Acc@1: 37.5000 (37.5000)Acc@5: 78.1250 (78.1250) +2025-04-18 11:13:32,413 - train: [ INFO] - Eval : 61 Time: 0.055 (0.189) Loss: 1.8647 (1.9661) Acc@1: 53.1250 (49.8775)Acc@5: 71.8750 (75.3064) +2025-04-18 11:13:38,890 - train: [ INFO] - Eval : 61 Time: 0.014 (0.197) Loss: 2.6070 (1.9701) Acc@1: 0.0000 (49.3832)Acc@5: 50.0000 (75.4819) +2025-04-18 11:13:49,519 - train: [ INFO] - Train: 62 [ 0/461 ( 0%)] Loss: 0.695665 (0.6957) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.035s, 4.55/s (7.035s, 4.55/s) LR: 5.000e-03 Data: 6.882 (6.882) +2025-04-18 11:13:59,196 - train: [ INFO] - Train: 62 [ 50/461 ( 11%)] Loss: 0.729540 (0.7126) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.098s, 327.26/s (0.293s, 109.11/s) LR: 5.000e-03 Data: 0.000 (0.216) +2025-04-18 11:14:08,782 - train: [ INFO] - Train: 62 [ 100/461 ( 22%)] Loss: 0.696524 (0.7072) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.270s, 118.30/s (0.220s, 145.50/s) LR: 5.000e-03 Data: 0.196 (0.137) +2025-04-18 11:14:29,864 - train: [ INFO] - Train: 62 [ 150/461 ( 33%)] Loss: 0.691394 (0.7033) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 424.47/s (0.241s, 132.90/s) LR: 5.000e-03 Data: 0.000 (0.157) +2025-04-18 11:14:50,985 - train: [ INFO] - Train: 62 [ 200/461 ( 43%)] Loss: 0.697559 (0.7021) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.099s, 322.96/s (0.252s, 127.10/s) LR: 5.000e-03 Data: 0.003 (0.168) +2025-04-18 11:15:12,008 - train: [ INFO] - Train: 62 [ 250/461 ( 54%)] Loss: 0.694476 (0.7009) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 428.29/s (0.260s, 123.24/s) LR: 5.000e-03 Data: 0.001 (0.177) +2025-04-18 11:15:28,286 - train: [ INFO] - Train: 62 [ 300/461 ( 65%)] Loss: 0.700617 (0.7008) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 470.69/s (0.258s, 123.92/s) LR: 5.000e-03 Data: 0.000 (0.176) +2025-04-18 11:15:50,278 - train: [ INFO] - Train: 62 [ 350/461 ( 76%)] Loss: 0.692657 (0.6998) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 406.32/s (0.269s, 118.99/s) LR: 5.000e-03 Data: 0.000 (0.187) +2025-04-18 11:16:09,848 - train: [ INFO] - Train: 62 [ 400/461 ( 87%)] Loss: 0.711027 (0.7011) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 2.665s, 12.01/s (0.277s, 115.34/s) LR: 5.000e-03 Data: 2.568 (0.196) +2025-04-18 11:16:26,671 - train: [ INFO] - Train: 62 [ 450/461 ( 98%)] Loss: 0.717228 (0.7027) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 346.93/s (0.278s, 115.23/s) LR: 5.000e-03 Data: 0.000 (0.197) +2025-04-18 11:16:28,436 - train: [ INFO] - Train: 62 [ 460/461 (100%)] Loss: 0.769252 (0.7087) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 430.68/s (0.275s, 116.50/s) LR: 5.000e-03 Data: 0.000 (0.194) +2025-04-18 11:16:36,768 - train: [ INFO] - Eval : 62 Time: 8.023 (8.023) Loss: 2.1627 (2.1627) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 11:16:47,070 - train: [ INFO] - Eval : 62 Time: 0.030 (0.359) Loss: 1.6637 (1.9842) Acc@1: 62.5000 (49.2647)Acc@5: 81.2500 (74.4485) +2025-04-18 11:16:56,420 - train: [ INFO] - Eval : 62 Time: 0.014 (0.338) Loss: 3.7511 (1.9786) Acc@1: 0.0000 (49.2290)Acc@5: 0.0000 (74.3639) +2025-04-18 11:17:12,209 - train: [ INFO] - Train: 63 [ 0/461 ( 0%)] Loss: 0.775381 (0.7754) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 10.287s, 3.11/s (10.287s, 3.11/s) LR: 5.000e-03 Data: 10.130 (10.130) +2025-04-18 11:17:28,406 - train: [ INFO] - Train: 63 [ 50/461 ( 11%)] Loss: 0.697404 (0.7364) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.800s, 40.00/s (0.468s, 68.34/s) LR: 5.000e-03 Data: 0.709 (0.389) +2025-04-18 11:17:41,931 - train: [ INFO] - Train: 63 [ 100/461 ( 22%)] Loss: 0.727601 (0.7335) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.074s, 429.91/s (0.351s, 91.14/s) LR: 5.000e-03 Data: 0.000 (0.272) +2025-04-18 11:17:55,528 - train: [ INFO] - Train: 63 [ 150/461 ( 33%)] Loss: 0.706366 (0.7267) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.071s, 451.02/s (0.307s, 104.11/s) LR: 5.000e-03 Data: 0.001 (0.227) +2025-04-18 11:18:05,997 - train: [ INFO] - Train: 63 [ 200/461 ( 43%)] Loss: 0.705522 (0.7225) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.068s, 472.76/s (0.279s, 114.88/s) LR: 5.000e-03 Data: 0.000 (0.199) +2025-04-18 11:18:13,904 - train: [ INFO] - Train: 63 [ 250/461 ( 54%)] Loss: 0.722394 (0.7224) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.073s, 437.90/s (0.251s, 127.28/s) LR: 5.000e-03 Data: 0.000 (0.172) +2025-04-18 11:18:20,791 - train: [ INFO] - Train: 63 [ 300/461 ( 65%)] Loss: 0.694494 (0.7185) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.070s, 459.33/s (0.232s, 137.84/s) LR: 5.000e-03 Data: 0.000 (0.153) +2025-04-18 11:18:28,349 - train: [ INFO] - Train: 63 [ 350/461 ( 76%)] Loss: 0.694519 (0.7155) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.071s, 448.86/s (0.219s, 145.88/s) LR: 5.000e-03 Data: 0.000 (0.140) +2025-04-18 11:18:36,792 - train: [ INFO] - Train: 63 [ 400/461 ( 87%)] Loss: 0.695397 (0.7132) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.927s, 34.53/s (0.210s, 152.67/s) LR: 5.000e-03 Data: 0.828 (0.129) +2025-04-18 11:18:41,915 - train: [ INFO] - Train: 63 [ 450/461 ( 98%)] Loss: 0.710084 (0.7129) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.228s, 140.57/s (0.197s, 162.12/s) LR: 5.000e-03 Data: 0.094 (0.116) +2025-04-18 11:18:42,694 - train: [ INFO] - Train: 63 [ 460/461 (100%)] Loss: 0.692884 (0.7111) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.070s, 456.75/s (0.195s, 164.29/s) LR: 5.000e-03 Data: 0.000 (0.113) +2025-04-18 11:18:48,175 - train: [ INFO] - Eval : 63 Time: 5.216 (5.216) Loss: 2.0755 (2.0755) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:18:52,760 - train: [ INFO] - Eval : 63 Time: 0.062 (0.192) Loss: 1.8025 (1.9876) Acc@1: 56.2500 (48.4681)Acc@5: 68.7500 (74.6936) +2025-04-18 11:18:55,323 - train: [ INFO] - Eval : 63 Time: 0.015 (0.151) Loss: 3.1412 (1.9746) Acc@1: 0.0000 (49.0362)Acc@5: 0.0000 (74.3254) +2025-04-18 11:19:08,222 - train: [ INFO] - Train: 64 [ 0/461 ( 0%)] Loss: 0.757798 (0.7578) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 7.397s, 4.33/s (7.397s, 4.33/s) LR: 5.000e-03 Data: 7.274 (7.274) +2025-04-18 11:19:18,925 - train: [ INFO] - Train: 64 [ 50/461 ( 11%)] Loss: 0.700949 (0.7294) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.073s, 436.17/s (0.310s, 103.31/s) LR: 5.000e-03 Data: 0.001 (0.232) +2025-04-18 11:19:29,257 - train: [ INFO] - Train: 64 [ 100/461 ( 22%)] Loss: 0.689785 (0.7162) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.073s, 441.01/s (0.225s, 142.25/s) LR: 5.000e-03 Data: 0.000 (0.147) +2025-04-18 11:19:38,822 - train: [ INFO] - Train: 64 [ 150/461 ( 33%)] Loss: 0.685908 (0.7086) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.074s, 430.45/s (0.206s, 155.34/s) LR: 5.000e-03 Data: 0.001 (0.129) +2025-04-18 11:19:48,550 - train: [ INFO] - Train: 64 [ 200/461 ( 43%)] Loss: 0.688865 (0.7047) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.073s, 435.56/s (0.197s, 162.35/s) LR: 5.000e-03 Data: 0.001 (0.120) +2025-04-18 11:19:59,434 - train: [ INFO] - Train: 64 [ 250/461 ( 54%)] Loss: 0.692505 (0.7026) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.074s, 434.71/s (0.194s, 165.15/s) LR: 5.000e-03 Data: 0.001 (0.115) +2025-04-18 11:20:07,257 - train: [ INFO] - Train: 64 [ 300/461 ( 65%)] Loss: 0.695571 (0.7016) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.229s, 139.85/s (0.187s, 171.47/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-18 11:20:15,386 - train: [ INFO] - Train: 64 [ 350/461 ( 76%)] Loss: 0.692781 (0.7005) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.04/s (0.181s, 176.32/s) LR: 5.000e-03 Data: 0.000 (0.100) +2025-04-18 11:20:22,282 - train: [ INFO] - Train: 64 [ 400/461 ( 87%)] Loss: 0.693887 (0.6998) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.181s, 176.93/s (0.175s, 182.36/s) LR: 5.000e-03 Data: 0.026 (0.092) +2025-04-18 11:20:29,014 - train: [ INFO] - Train: 64 [ 450/461 ( 98%)] Loss: 0.710844 (0.7009) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.090s, 354.04/s (0.170s, 187.90/s) LR: 5.000e-03 Data: 0.001 (0.086) +2025-04-18 11:20:30,274 - train: [ INFO] - Train: 64 [ 460/461 (100%)] Loss: 0.715162 (0.7022) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.090s, 357.29/s (0.169s, 189.06/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-18 11:20:35,182 - train: [ INFO] - Eval : 64 Time: 4.605 (4.605) Loss: 2.1327 (2.1327) Acc@1: 46.8750 (46.8750)Acc@5: 68.7500 (68.7500) +2025-04-18 11:20:41,184 - train: [ INFO] - Eval : 64 Time: 0.351 (0.208) Loss: 1.8252 (2.0224) Acc@1: 53.1250 (48.1618)Acc@5: 71.8750 (73.5907) +2025-04-18 11:20:43,147 - train: [ INFO] - Eval : 64 Time: 0.021 (0.153) Loss: 3.5193 (2.0282) Acc@1: 0.0000 (47.4557)Acc@5: 0.0000 (72.8990) +2025-04-18 11:20:51,767 - train: [ INFO] - Train: 65 [ 0/461 ( 0%)] Loss: 0.697164 (0.6972) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.353s, 5.98/s (5.353s, 5.98/s) LR: 5.000e-03 Data: 5.218 (5.218) +2025-04-18 11:21:00,192 - train: [ INFO] - Train: 65 [ 50/461 ( 11%)] Loss: 0.701490 (0.6993) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 461.63/s (0.200s, 159.71/s) LR: 5.000e-03 Data: 0.000 (0.104) +2025-04-18 11:21:08,929 - train: [ INFO] - Train: 65 [ 100/461 ( 22%)] Loss: 0.700458 (0.6997) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.090s, 356.12/s (0.173s, 185.33/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-18 11:21:18,040 - train: [ INFO] - Train: 65 [ 150/461 ( 33%)] Loss: 0.793122 (0.7231) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.237s, 135.09/s (0.174s, 183.55/s) LR: 5.000e-03 Data: 0.167 (0.087) +2025-04-18 11:21:27,903 - train: [ INFO] - Train: 65 [ 200/461 ( 43%)] Loss: 0.697817 (0.7180) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.074s, 430.33/s (0.179s, 179.04/s) LR: 5.000e-03 Data: 0.000 (0.092) +2025-04-18 11:21:35,108 - train: [ INFO] - Train: 65 [ 250/461 ( 54%)] Loss: 0.689894 (0.7133) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.087s, 369.60/s (0.171s, 187.06/s) LR: 5.000e-03 Data: 0.007 (0.082) +2025-04-18 11:21:42,543 - train: [ INFO] - Train: 65 [ 300/461 ( 65%)] Loss: 0.722269 (0.7146) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.074s, 434.76/s (0.167s, 191.91/s) LR: 5.000e-03 Data: 0.001 (0.076) +2025-04-18 11:21:48,830 - train: [ INFO] - Train: 65 [ 350/461 ( 76%)] Loss: 0.692985 (0.7119) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.074s, 435.04/s (0.160s, 199.82/s) LR: 5.000e-03 Data: 0.001 (0.069) +2025-04-18 11:21:56,389 - train: [ INFO] - Train: 65 [ 400/461 ( 87%)] Loss: 0.691045 (0.7096) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.180s, 178.05/s (0.159s, 201.76/s) LR: 5.000e-03 Data: 0.077 (0.068) +2025-04-18 11:22:03,017 - train: [ INFO] - Train: 65 [ 450/461 ( 98%)] Loss: 0.689503 (0.7076) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.149s, 214.07/s (0.155s, 205.95/s) LR: 5.000e-03 Data: 0.000 (0.065) +2025-04-18 11:22:03,904 - train: [ INFO] - Train: 65 [ 460/461 (100%)] Loss: 0.714199 (0.7082) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.072s, 443.34/s (0.154s, 208.02/s) LR: 5.000e-03 Data: 0.000 (0.063) +2025-04-18 11:22:08,432 - train: [ INFO] - Eval : 65 Time: 4.217 (4.217) Loss: 2.1763 (2.1763) Acc@1: 37.5000 (37.5000)Acc@5: 65.6250 (65.6250) +2025-04-18 11:22:13,890 - train: [ INFO] - Eval : 65 Time: 0.055 (0.190) Loss: 1.7972 (2.0351) Acc@1: 56.2500 (46.7525)Acc@5: 71.8750 (73.4069) +2025-04-18 11:22:17,521 - train: [ INFO] - Eval : 65 Time: 0.014 (0.162) Loss: 3.2217 (2.0330) Acc@1: 0.0000 (46.8003)Acc@5: 50.0000 (73.2460) +2025-04-18 11:22:29,708 - train: [ INFO] - Train: 66 [ 0/461 ( 0%)] Loss: 0.716714 (0.7167) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.657s, 3.70/s (8.657s, 3.70/s) LR: 5.000e-03 Data: 8.435 (8.435) +2025-04-18 11:22:36,726 - train: [ INFO] - Train: 66 [ 50/461 ( 11%)] Loss: 0.696924 (0.7068) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.189s, 169.61/s (0.276s, 115.75/s) LR: 5.000e-03 Data: 0.000 (0.177) +2025-04-18 11:22:44,647 - train: [ INFO] - Train: 66 [ 100/461 ( 22%)] Loss: 0.683797 (0.6991) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 447.58/s (0.213s, 150.24/s) LR: 5.000e-03 Data: 0.000 (0.118) +2025-04-18 11:22:52,224 - train: [ INFO] - Train: 66 [ 150/461 ( 33%)] Loss: 0.696925 (0.6986) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.097s, 328.51/s (0.191s, 167.38/s) LR: 5.000e-03 Data: 0.001 (0.099) +2025-04-18 11:22:59,349 - train: [ INFO] - Train: 66 [ 200/461 ( 43%)] Loss: 0.694245 (0.6977) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.91/s (0.178s, 179.80/s) LR: 5.000e-03 Data: 0.000 (0.089) +2025-04-18 11:23:05,493 - train: [ INFO] - Train: 66 [ 250/461 ( 54%)] Loss: 0.708652 (0.6995) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.90/s (0.166s, 192.40/s) LR: 5.000e-03 Data: 0.001 (0.080) +2025-04-18 11:23:11,763 - train: [ INFO] - Train: 66 [ 300/461 ( 65%)] Loss: 0.721105 (0.7026) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.115s, 277.21/s (0.159s, 201.19/s) LR: 5.000e-03 Data: 0.000 (0.073) +2025-04-18 11:23:17,662 - train: [ INFO] - Train: 66 [ 350/461 ( 76%)] Loss: 0.707279 (0.7032) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.128s, 250.04/s (0.153s, 209.82/s) LR: 5.000e-03 Data: 0.000 (0.067) +2025-04-18 11:23:25,175 - train: [ INFO] - Train: 66 [ 400/461 ( 87%)] Loss: 0.715281 (0.7045) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.68/s (0.150s, 213.40/s) LR: 5.000e-03 Data: 0.001 (0.065) +2025-04-18 11:23:36,799 - train: [ INFO] - Train: 66 [ 450/461 ( 98%)] Loss: 0.751730 (0.7093) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 467.18/s (0.155s, 205.98/s) LR: 5.000e-03 Data: 0.000 (0.071) +2025-04-18 11:23:37,706 - train: [ INFO] - Train: 66 [ 460/461 (100%)] Loss: 0.692492 (0.7077) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.21/s (0.154s, 208.45/s) LR: 5.000e-03 Data: 0.000 (0.070) +2025-04-18 11:23:44,093 - train: [ INFO] - Eval : 66 Time: 6.128 (6.128) Loss: 2.1854 (2.1854) Acc@1: 46.8750 (46.8750)Acc@5: 68.7500 (68.7500) +2025-04-18 11:23:49,465 - train: [ INFO] - Eval : 66 Time: 0.133 (0.226) Loss: 1.9549 (2.0353) Acc@1: 53.1250 (46.5686)Acc@5: 71.8750 (73.5294) +2025-04-18 11:23:55,565 - train: [ INFO] - Eval : 66 Time: 0.016 (0.215) Loss: 2.6913 (2.0280) Acc@1: 0.0000 (47.1858)Acc@5: 100.0000 (74.0555) +2025-04-18 11:24:06,217 - train: [ INFO] - Train: 67 [ 0/461 ( 0%)] Loss: 0.706172 (0.7062) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.029s, 4.55/s (7.029s, 4.55/s) LR: 5.000e-03 Data: 6.861 (6.861) +2025-04-18 11:24:19,631 - train: [ INFO] - Train: 67 [ 50/461 ( 11%)] Loss: 0.690815 (0.6985) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.143s, 223.60/s (0.337s, 94.97/s) LR: 5.000e-03 Data: 0.000 (0.245) +2025-04-18 11:24:29,517 - train: [ INFO] - Train: 67 [ 100/461 ( 22%)] Loss: 0.680546 (0.6925) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.81/s (0.255s, 125.29/s) LR: 5.000e-03 Data: 0.000 (0.166) +2025-04-18 11:24:36,233 - train: [ INFO] - Train: 67 [ 150/461 ( 33%)] Loss: 0.704608 (0.6955) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.49/s (0.214s, 149.48/s) LR: 5.000e-03 Data: 0.001 (0.124) +2025-04-18 11:24:42,997 - train: [ INFO] - Train: 67 [ 200/461 ( 43%)] Loss: 0.708179 (0.6981) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.67/s (0.194s, 164.98/s) LR: 5.000e-03 Data: 0.000 (0.105) +2025-04-18 11:24:49,157 - train: [ INFO] - Train: 67 [ 250/461 ( 54%)] Loss: 0.703716 (0.6990) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 442.92/s (0.179s, 179.02/s) LR: 5.000e-03 Data: 0.000 (0.090) +2025-04-18 11:24:55,000 - train: [ INFO] - Train: 67 [ 300/461 ( 65%)] Loss: 0.714520 (0.7012) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 428.64/s (0.168s, 190.41/s) LR: 5.000e-03 Data: 0.001 (0.079) +2025-04-18 11:25:00,652 - train: [ INFO] - Train: 67 [ 350/461 ( 76%)] Loss: 0.715767 (0.7030) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 420.41/s (0.160s, 200.35/s) LR: 5.000e-03 Data: 0.000 (0.070) +2025-04-18 11:25:06,662 - train: [ INFO] - Train: 67 [ 400/461 ( 87%)] Loss: 0.788978 (0.7126) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.273s, 117.19/s (0.154s, 207.49/s) LR: 5.000e-03 Data: 0.140 (0.064) +2025-04-18 11:25:13,569 - train: [ INFO] - Train: 67 [ 450/461 ( 98%)] Loss: 0.698280 (0.7112) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.54/s (0.148s, 216.79/s) LR: 5.000e-03 Data: 0.000 (0.057) +2025-04-18 11:25:14,426 - train: [ INFO] - Train: 67 [ 460/461 (100%)] Loss: 0.716650 (0.7117) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.127s, 251.31/s (0.146s, 218.94/s) LR: 5.000e-03 Data: 0.000 (0.056) +2025-04-18 11:25:22,152 - train: [ INFO] - Eval : 67 Time: 7.372 (7.372) Loss: 2.0737 (2.0737) Acc@1: 53.1250 (53.1250)Acc@5: 68.7500 (68.7500) +2025-04-18 11:25:27,037 - train: [ INFO] - Eval : 67 Time: 0.058 (0.240) Loss: 1.8450 (2.0021) Acc@1: 56.2500 (48.7745)Acc@5: 75.0000 (73.2230) +2025-04-18 11:25:28,973 - train: [ INFO] - Eval : 67 Time: 0.019 (0.173) Loss: 3.5235 (1.9953) Acc@1: 0.0000 (49.0748)Acc@5: 0.0000 (73.5544) +2025-04-18 11:25:43,034 - train: [ INFO] - Train: 68 [ 0/461 ( 0%)] Loss: 0.699712 (0.6997) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 10.956s, 2.92/s (10.956s, 2.92/s) LR: 5.000e-03 Data: 10.740 (10.740) +2025-04-18 11:25:52,947 - train: [ INFO] - Train: 68 [ 50/461 ( 11%)] Loss: 0.693700 (0.6967) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.40/s (0.392s, 81.72/s) LR: 5.000e-03 Data: 0.000 (0.309) +2025-04-18 11:26:01,215 - train: [ INFO] - Train: 68 [ 100/461 ( 22%)] Loss: 0.694935 (0.6961) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.80/s (0.277s, 115.49/s) LR: 5.000e-03 Data: 0.000 (0.198) +2025-04-18 11:26:08,287 - train: [ INFO] - Train: 68 [ 150/461 ( 33%)] Loss: 0.697398 (0.6964) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.52/s (0.231s, 138.39/s) LR: 5.000e-03 Data: 0.000 (0.153) +2025-04-18 11:26:15,349 - train: [ INFO] - Train: 68 [ 200/461 ( 43%)] Loss: 0.700923 (0.6973) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 453.03/s (0.209s, 153.46/s) LR: 5.000e-03 Data: 0.000 (0.130) +2025-04-18 11:26:21,166 - train: [ INFO] - Train: 68 [ 250/461 ( 54%)] Loss: 0.683873 (0.6951) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 428.58/s (0.190s, 168.84/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 11:26:27,216 - train: [ INFO] - Train: 68 [ 300/461 ( 65%)] Loss: 0.695611 (0.6952) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 403.36/s (0.178s, 180.25/s) LR: 5.000e-03 Data: 0.000 (0.094) +2025-04-18 11:26:32,608 - train: [ INFO] - Train: 68 [ 350/461 ( 76%)] Loss: 0.762119 (0.7035) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.21/s (0.167s, 191.86/s) LR: 5.000e-03 Data: 0.000 (0.081) +2025-04-18 11:26:40,733 - train: [ INFO] - Train: 68 [ 400/461 ( 87%)] Loss: 0.692828 (0.7023) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.76/s (0.159s, 201.74/s) LR: 5.000e-03 Data: 0.000 (0.073) +2025-04-18 11:26:50,015 - train: [ INFO] - Train: 68 [ 450/461 ( 98%)] Loss: 0.686408 (0.7008) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.34/s (0.160s, 199.99/s) LR: 5.000e-03 Data: 0.000 (0.075) +2025-04-18 11:26:52,383 - train: [ INFO] - Train: 68 [ 460/461 (100%)] Loss: 0.692024 (0.7000) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.49/s (0.162s, 197.99/s) LR: 5.000e-03 Data: 0.000 (0.077) +2025-04-18 11:26:59,900 - train: [ INFO] - Eval : 68 Time: 7.201 (7.201) Loss: 2.1932 (2.1932) Acc@1: 40.6250 (40.6250)Acc@5: 68.7500 (68.7500) +2025-04-18 11:27:12,871 - train: [ INFO] - Eval : 68 Time: 0.048 (0.396) Loss: 1.7515 (1.9990) Acc@1: 62.5000 (48.3456)Acc@5: 75.0000 (73.6520) +2025-04-18 11:27:16,605 - train: [ INFO] - Eval : 68 Time: 0.030 (0.292) Loss: 4.1057 (1.9978) Acc@1: 0.0000 (48.1881)Acc@5: 0.0000 (73.7471) +2025-04-18 11:27:28,007 - train: [ INFO] - Train: 69 [ 0/461 ( 0%)] Loss: 0.688500 (0.6885) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.375s, 4.34/s (7.375s, 4.34/s) LR: 5.000e-03 Data: 7.225 (7.225) +2025-04-18 11:27:33,416 - train: [ INFO] - Train: 69 [ 50/461 ( 11%)] Loss: 0.684607 (0.6866) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.75/s (0.248s, 128.90/s) LR: 5.000e-03 Data: 0.000 (0.148) +2025-04-18 11:27:39,803 - train: [ INFO] - Train: 69 [ 100/461 ( 22%)] Loss: 0.725879 (0.6997) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 446.10/s (0.186s, 171.75/s) LR: 5.000e-03 Data: 0.000 (0.092) +2025-04-18 11:27:45,148 - train: [ INFO] - Train: 69 [ 150/461 ( 33%)] Loss: 0.696284 (0.6988) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.132s, 243.11/s (0.159s, 201.44/s) LR: 5.000e-03 Data: 0.000 (0.062) +2025-04-18 11:27:50,655 - train: [ INFO] - Train: 69 [ 200/461 ( 43%)] Loss: 0.693001 (0.6977) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.128s, 250.30/s (0.145s, 220.26/s) LR: 5.000e-03 Data: 0.001 (0.047) +2025-04-18 11:27:55,814 - train: [ INFO] - Train: 69 [ 250/461 ( 54%)] Loss: 0.702188 (0.6984) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 345.29/s (0.136s, 235.50/s) LR: 5.000e-03 Data: 0.001 (0.038) +2025-04-18 11:28:01,203 - train: [ INFO] - Train: 69 [ 300/461 ( 65%)] Loss: 0.701610 (0.6989) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.114s, 280.90/s (0.131s, 244.77/s) LR: 5.000e-03 Data: 0.001 (0.032) +2025-04-18 11:28:08,313 - train: [ INFO] - Train: 69 [ 350/461 ( 76%)] Loss: 0.715234 (0.7009) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 435.84/s (0.125s, 256.63/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-18 11:28:15,402 - train: [ INFO] - Train: 69 [ 400/461 ( 87%)] Loss: 0.691393 (0.6999) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.207s, 154.41/s (0.125s, 255.07/s) LR: 5.000e-03 Data: 0.127 (0.029) +2025-04-18 11:28:22,312 - train: [ INFO] - Train: 69 [ 450/461 ( 98%)] Loss: 0.719511 (0.7018) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 459.47/s (0.126s, 253.39/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-18 11:28:23,068 - train: [ INFO] - Train: 69 [ 460/461 (100%)] Loss: 0.699194 (0.7016) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 469.70/s (0.125s, 255.71/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-18 11:28:30,347 - train: [ INFO] - Eval : 69 Time: 6.984 (6.984) Loss: 1.8984 (1.8984) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 11:28:33,419 - train: [ INFO] - Eval : 69 Time: 0.269 (0.197) Loss: 1.9232 (2.0638) Acc@1: 50.0000 (46.9363)Acc@5: 68.7500 (72.1201) +2025-04-18 11:28:39,139 - train: [ INFO] - Eval : 69 Time: 0.060 (0.192) Loss: 3.5234 (2.0716) Acc@1: 0.0000 (46.2221)Acc@5: 0.0000 (71.8196) +2025-04-18 11:28:52,485 - train: [ INFO] - Train: 70 [ 0/461 ( 0%)] Loss: 0.694851 (0.6949) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.589s, 3.73/s (8.589s, 3.73/s) LR: 5.000e-04 Data: 8.457 (8.457) +2025-04-18 11:29:08,764 - train: [ INFO] - Train: 70 [ 50/461 ( 11%)] Loss: 0.690348 (0.6926) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.350s, 91.45/s (0.414s, 77.34/s) LR: 5.000e-04 Data: 0.130 (0.324) +2025-04-18 11:29:24,339 - train: [ INFO] - Train: 70 [ 100/461 ( 22%)] Loss: 0.729928 (0.7050) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.39/s (0.341s, 93.76/s) LR: 5.000e-04 Data: 0.000 (0.255) +2025-04-18 11:29:33,734 - train: [ INFO] - Train: 70 [ 150/461 ( 33%)] Loss: 0.677458 (0.6981) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 417.31/s (0.290s, 110.46/s) LR: 5.000e-04 Data: 0.000 (0.207) +2025-04-18 11:29:46,789 - train: [ INFO] - Train: 70 [ 200/461 ( 43%)] Loss: 0.687952 (0.6961) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 461.77/s (0.271s, 118.00/s) LR: 5.000e-04 Data: 0.000 (0.190) +2025-04-18 11:29:54,852 - train: [ INFO] - Train: 70 [ 250/461 ( 54%)] Loss: 0.699094 (0.6966) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 439.39/s (0.248s, 129.12/s) LR: 5.000e-04 Data: 0.000 (0.168) +2025-04-18 11:30:03,151 - train: [ INFO] - Train: 70 [ 300/461 ( 65%)] Loss: 0.687966 (0.6954) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.05/s (0.232s, 137.69/s) LR: 5.000e-04 Data: 0.000 (0.153) +2025-04-18 11:30:09,583 - train: [ INFO] - Train: 70 [ 350/461 ( 76%)] Loss: 0.682529 (0.6938) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 339.64/s (0.217s, 147.79/s) LR: 5.000e-04 Data: 0.001 (0.136) +2025-04-18 11:30:21,327 - train: [ INFO] - Train: 70 [ 400/461 ( 87%)] Loss: 0.691449 (0.6935) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.579s, 20.26/s (0.213s, 150.39/s) LR: 5.000e-04 Data: 1.449 (0.132) +2025-04-18 11:30:32,821 - train: [ INFO] - Train: 70 [ 450/461 ( 98%)] Loss: 0.696344 (0.6938) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 440.08/s (0.211s, 151.96/s) LR: 5.000e-04 Data: 0.000 (0.130) +2025-04-18 11:30:34,074 - train: [ INFO] - Train: 70 [ 460/461 (100%)] Loss: 0.718057 (0.6960) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 469.65/s (0.208s, 154.14/s) LR: 5.000e-04 Data: 0.000 (0.128) +2025-04-18 11:30:41,078 - train: [ INFO] - Eval : 70 Time: 6.705 (6.705) Loss: 1.9733 (1.9733) Acc@1: 46.8750 (46.8750)Acc@5: 65.6250 (65.6250) +2025-04-18 11:30:53,091 - train: [ INFO] - Eval : 70 Time: 0.028 (0.367) Loss: 1.8225 (1.9559) Acc@1: 56.2500 (50.0613)Acc@5: 71.8750 (76.4093) +2025-04-18 11:31:01,610 - train: [ INFO] - Eval : 70 Time: 0.020 (0.332) Loss: 3.1548 (1.9543) Acc@1: 0.0000 (50.0386)Acc@5: 50.0000 (76.1372) +2025-04-18 11:31:14,693 - train: [ INFO] - Train: 71 [ 0/461 ( 0%)] Loss: 0.678326 (0.6783) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.604s, 3.72/s (8.604s, 3.72/s) LR: 5.000e-04 Data: 8.504 (8.504) +2025-04-18 11:31:25,737 - train: [ INFO] - Train: 71 [ 50/461 ( 11%)] Loss: 0.697547 (0.6879) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.110s, 290.78/s (0.327s, 97.85/s) LR: 5.000e-04 Data: 0.001 (0.244) +2025-04-18 11:31:32,774 - train: [ INFO] - Train: 71 [ 100/461 ( 22%)] Loss: 0.677806 (0.6846) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 453.39/s (0.234s, 136.60/s) LR: 5.000e-04 Data: 0.000 (0.155) +2025-04-18 11:31:39,968 - train: [ INFO] - Train: 71 [ 150/461 ( 33%)] Loss: 0.685418 (0.6848) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.69/s (0.204s, 156.87/s) LR: 5.000e-04 Data: 0.000 (0.126) +2025-04-18 11:31:48,486 - train: [ INFO] - Train: 71 [ 200/461 ( 43%)] Loss: 0.678971 (0.6836) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.123s, 261.09/s (0.193s, 166.08/s) LR: 5.000e-04 Data: 0.000 (0.116) +2025-04-18 11:31:56,228 - train: [ INFO] - Train: 71 [ 250/461 ( 54%)] Loss: 0.710580 (0.6881) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 456.59/s (0.184s, 173.56/s) LR: 5.000e-04 Data: 0.000 (0.107) +2025-04-18 11:32:02,652 - train: [ INFO] - Train: 71 [ 300/461 ( 65%)] Loss: 0.678559 (0.6867) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.122s, 263.25/s (0.174s, 183.42/s) LR: 5.000e-04 Data: 0.024 (0.093) +2025-04-18 11:32:08,435 - train: [ INFO] - Train: 71 [ 350/461 ( 76%)] Loss: 0.672568 (0.6850) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.098s, 326.99/s (0.166s, 193.32/s) LR: 5.000e-04 Data: 0.001 (0.082) +2025-04-18 11:32:14,159 - train: [ INFO] - Train: 71 [ 400/461 ( 87%)] Loss: 0.741376 (0.6912) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.273s, 117.31/s (0.159s, 201.84/s) LR: 5.000e-04 Data: 0.174 (0.074) +2025-04-18 11:32:18,964 - train: [ INFO] - Train: 71 [ 450/461 ( 98%)] Loss: 0.685632 (0.6907) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 469.33/s (0.151s, 211.87/s) LR: 5.000e-04 Data: 0.000 (0.066) +2025-04-18 11:32:19,667 - train: [ INFO] - Train: 71 [ 460/461 (100%)] Loss: 0.672001 (0.6890) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 435.26/s (0.149s, 214.38/s) LR: 5.000e-04 Data: 0.000 (0.065) +2025-04-18 11:32:24,616 - train: [ INFO] - Eval : 71 Time: 4.689 (4.689) Loss: 1.9817 (1.9817) Acc@1: 46.8750 (46.8750)Acc@5: 68.7500 (68.7500) +2025-04-18 11:32:32,356 - train: [ INFO] - Eval : 71 Time: 0.030 (0.244) Loss: 1.8315 (1.9400) Acc@1: 56.2500 (50.9804)Acc@5: 75.0000 (76.5931) +2025-04-18 11:32:37,169 - train: [ INFO] - Eval : 71 Time: 0.015 (0.210) Loss: 3.0337 (1.9396) Acc@1: 0.0000 (50.6554)Acc@5: 50.0000 (76.2529) +2025-04-18 11:32:51,982 - train: [ INFO] - Train: 72 [ 0/461 ( 0%)] Loss: 0.680529 (0.6805) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 9.300s, 3.44/s (9.300s, 3.44/s) LR: 5.000e-04 Data: 9.199 (9.199) +2025-04-18 11:33:04,273 - train: [ INFO] - Train: 72 [ 50/461 ( 11%)] Loss: 0.672039 (0.6763) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.087s, 369.04/s (0.360s, 88.84/s) LR: 5.000e-04 Data: 0.000 (0.279) +2025-04-18 11:33:11,875 - train: [ INFO] - Train: 72 [ 100/461 ( 22%)] Loss: 0.678531 (0.6770) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 439.96/s (0.256s, 125.10/s) LR: 5.000e-04 Data: 0.000 (0.177) +2025-04-18 11:33:19,449 - train: [ INFO] - Train: 72 [ 150/461 ( 33%)] Loss: 0.716634 (0.6869) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.16/s (0.220s, 145.53/s) LR: 5.000e-04 Data: 0.000 (0.142) +2025-04-18 11:33:25,322 - train: [ INFO] - Train: 72 [ 200/461 ( 43%)] Loss: 0.700164 (0.6896) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.111s, 287.45/s (0.193s, 165.47/s) LR: 5.000e-04 Data: 0.000 (0.110) +2025-04-18 11:33:30,336 - train: [ INFO] - Train: 72 [ 250/461 ( 54%)] Loss: 0.707576 (0.6926) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.109s, 294.55/s (0.174s, 184.05/s) LR: 5.000e-04 Data: 0.001 (0.088) +2025-04-18 11:33:35,180 - train: [ INFO] - Train: 72 [ 300/461 ( 65%)] Loss: 0.677290 (0.6904) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.132s, 243.03/s (0.161s, 199.37/s) LR: 5.000e-04 Data: 0.001 (0.074) +2025-04-18 11:33:40,024 - train: [ INFO] - Train: 72 [ 350/461 ( 76%)] Loss: 0.672757 (0.6882) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 423.75/s (0.151s, 212.21/s) LR: 5.000e-04 Data: 0.000 (0.064) +2025-04-18 11:33:45,047 - train: [ INFO] - Train: 72 [ 400/461 ( 87%)] Loss: 0.678968 (0.6872) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.107s, 299.19/s (0.144s, 222.26/s) LR: 5.000e-04 Data: 0.000 (0.056) +2025-04-18 11:33:49,541 - train: [ INFO] - Train: 72 [ 450/461 ( 98%)] Loss: 0.676605 (0.6861) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 425.20/s (0.138s, 232.51/s) LR: 5.000e-04 Data: 0.000 (0.050) +2025-04-18 11:33:50,228 - train: [ INFO] - Train: 72 [ 460/461 (100%)] Loss: 0.673196 (0.6849) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 471.37/s (0.136s, 235.09/s) LR: 5.000e-04 Data: 0.000 (0.049) +2025-04-18 11:33:55,411 - train: [ INFO] - Eval : 72 Time: 4.851 (4.851) Loss: 1.9995 (1.9995) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:33:57,995 - train: [ INFO] - Eval : 72 Time: 0.142 (0.146) Loss: 1.8420 (1.9537) Acc@1: 53.1250 (50.8578)Acc@5: 68.7500 (76.5931) +2025-04-18 11:34:00,423 - train: [ INFO] - Eval : 72 Time: 0.014 (0.120) Loss: 3.1018 (1.9521) Acc@1: 0.0000 (50.6939)Acc@5: 50.0000 (76.3300) +2025-04-18 11:34:08,238 - train: [ INFO] - Train: 73 [ 0/461 ( 0%)] Loss: 0.683349 (0.6833) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.989s, 6.41/s (4.989s, 6.41/s) LR: 5.000e-04 Data: 4.832 (4.832) +2025-04-18 11:34:14,529 - train: [ INFO] - Train: 73 [ 50/461 ( 11%)] Loss: 0.673046 (0.6782) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.135s, 236.51/s (0.193s, 165.96/s) LR: 5.000e-04 Data: 0.001 (0.095) +2025-04-18 11:34:20,297 - train: [ INFO] - Train: 73 [ 100/461 ( 22%)] Loss: 0.683337 (0.6799) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.119s, 268.65/s (0.140s, 229.28/s) LR: 5.000e-04 Data: 0.001 (0.048) +2025-04-18 11:34:25,113 - train: [ INFO] - Train: 73 [ 150/461 ( 33%)] Loss: 0.672094 (0.6780) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 461.55/s (0.124s, 257.24/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-18 11:34:29,849 - train: [ INFO] - Train: 73 [ 200/461 ( 43%)] Loss: 0.760807 (0.6945) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.087s, 365.84/s (0.116s, 276.13/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-18 11:34:34,880 - train: [ INFO] - Train: 73 [ 250/461 ( 54%)] Loss: 0.706762 (0.6966) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.107s, 299.59/s (0.112s, 286.62/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:34:39,825 - train: [ INFO] - Train: 73 [ 300/461 ( 65%)] Loss: 0.674063 (0.6934) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.074s, 432.84/s (0.108s, 295.35/s) LR: 5.000e-04 Data: 0.001 (0.017) +2025-04-18 11:34:44,507 - train: [ INFO] - Train: 73 [ 350/461 ( 76%)] Loss: 0.676153 (0.6912) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.103s, 311.45/s (0.106s, 302.46/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:34:49,706 - train: [ INFO] - Train: 73 [ 400/461 ( 87%)] Loss: 0.680974 (0.6901) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.100s, 318.58/s (0.105s, 305.04/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:34:54,310 - train: [ INFO] - Train: 73 [ 450/461 ( 98%)] Loss: 0.710340 (0.6921) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.01/s (0.103s, 310.62/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:34:55,433 - train: [ INFO] - Train: 73 [ 460/461 (100%)] Loss: 0.712870 (0.6940) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.071s, 451.09/s (0.102s, 312.83/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:34:59,990 - train: [ INFO] - Eval : 73 Time: 4.278 (4.278) Loss: 1.9862 (1.9862) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 11:35:02,675 - train: [ INFO] - Eval : 73 Time: 0.208 (0.137) Loss: 1.8368 (1.9593) Acc@1: 56.2500 (50.7966)Acc@5: 71.8750 (76.2255) +2025-04-18 11:35:04,552 - train: [ INFO] - Eval : 73 Time: 0.015 (0.108) Loss: 3.0728 (1.9583) Acc@1: 0.0000 (50.7325)Acc@5: 50.0000 (76.2914) +2025-04-18 11:35:13,619 - train: [ INFO] - Train: 74 [ 0/461 ( 0%)] Loss: 0.666253 (0.6663) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.260s, 5.11/s (6.260s, 5.11/s) LR: 5.000e-04 Data: 6.131 (6.131) +2025-04-18 11:35:18,745 - train: [ INFO] - Train: 74 [ 50/461 ( 11%)] Loss: 0.681124 (0.6737) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 431.30/s (0.220s, 145.70/s) LR: 5.000e-04 Data: 0.000 (0.121) +2025-04-18 11:35:24,822 - train: [ INFO] - Train: 74 [ 100/461 ( 22%)] Loss: 0.672607 (0.6733) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.085s, 377.65/s (0.156s, 205.14/s) LR: 5.000e-04 Data: 0.001 (0.061) +2025-04-18 11:35:29,722 - train: [ INFO] - Train: 74 [ 150/461 ( 33%)] Loss: 0.680054 (0.6750) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 408.55/s (0.135s, 237.38/s) LR: 5.000e-04 Data: 0.001 (0.041) +2025-04-18 11:35:36,044 - train: [ INFO] - Train: 74 [ 200/461 ( 43%)] Loss: 0.673081 (0.6746) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 443.17/s (0.124s, 257.38/s) LR: 5.000e-04 Data: 0.001 (0.031) +2025-04-18 11:35:40,976 - train: [ INFO] - Train: 74 [ 250/461 ( 54%)] Loss: 0.678568 (0.6753) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.090s, 355.24/s (0.118s, 272.17/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-18 11:35:45,839 - train: [ INFO] - Train: 74 [ 300/461 ( 65%)] Loss: 0.669130 (0.6744) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 465.83/s (0.114s, 281.78/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-18 11:35:50,619 - train: [ INFO] - Train: 74 [ 350/461 ( 76%)] Loss: 0.674767 (0.6744) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.122s, 263.20/s (0.110s, 290.31/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-18 11:35:55,192 - train: [ INFO] - Train: 74 [ 400/461 ( 87%)] Loss: 0.694926 (0.6767) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.68/s (0.107s, 298.74/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:35:59,420 - train: [ INFO] - Train: 74 [ 450/461 ( 98%)] Loss: 0.702218 (0.6793) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 461.33/s (0.104s, 306.73/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:36:00,110 - train: [ INFO] - Train: 74 [ 460/461 (100%)] Loss: 0.667405 (0.6782) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.067s, 476.07/s (0.104s, 309.04/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:36:05,096 - train: [ INFO] - Eval : 74 Time: 4.693 (4.693) Loss: 2.0488 (2.0488) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:36:07,716 - train: [ INFO] - Eval : 74 Time: 0.047 (0.143) Loss: 1.8416 (1.9619) Acc@1: 56.2500 (51.0417)Acc@5: 71.8750 (76.7770) +2025-04-18 11:36:09,914 - train: [ INFO] - Eval : 74 Time: 0.018 (0.116) Loss: 3.0681 (1.9603) Acc@1: 0.0000 (50.8096)Acc@5: 50.0000 (76.6769) +2025-04-18 11:36:19,833 - train: [ INFO] - Train: 75 [ 0/461 ( 0%)] Loss: 0.673189 (0.6732) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.856s, 4.67/s (6.856s, 4.67/s) LR: 5.000e-04 Data: 6.654 (6.654) +2025-04-18 11:36:25,264 - train: [ INFO] - Train: 75 [ 50/461 ( 11%)] Loss: 0.689210 (0.6812) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.120s, 267.45/s (0.236s, 135.77/s) LR: 5.000e-04 Data: 0.001 (0.131) +2025-04-18 11:36:30,325 - train: [ INFO] - Train: 75 [ 100/461 ( 22%)] Loss: 0.669612 (0.6773) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 434.75/s (0.167s, 191.85/s) LR: 5.000e-04 Data: 0.000 (0.067) +2025-04-18 11:36:37,083 - train: [ INFO] - Train: 75 [ 150/461 ( 33%)] Loss: 0.685604 (0.6794) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.109s, 293.26/s (0.140s, 227.91/s) LR: 5.000e-04 Data: 0.001 (0.045) +2025-04-18 11:36:41,949 - train: [ INFO] - Train: 75 [ 200/461 ( 43%)] Loss: 0.668747 (0.6773) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.110s, 291.12/s (0.128s, 249.18/s) LR: 5.000e-04 Data: 0.001 (0.034) +2025-04-18 11:36:47,915 - train: [ INFO] - Train: 75 [ 250/461 ( 54%)] Loss: 0.681054 (0.6779) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 320.06/s (0.121s, 264.54/s) LR: 5.000e-04 Data: 0.001 (0.027) +2025-04-18 11:36:53,008 - train: [ INFO] - Train: 75 [ 300/461 ( 65%)] Loss: 0.666697 (0.6763) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.111s, 287.59/s (0.117s, 273.36/s) LR: 5.000e-04 Data: 0.001 (0.023) +2025-04-18 11:36:58,080 - train: [ INFO] - Train: 75 [ 350/461 ( 76%)] Loss: 0.673541 (0.6760) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.172s, 186.10/s (0.113s, 282.15/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-18 11:37:03,167 - train: [ INFO] - Train: 75 [ 400/461 ( 87%)] Loss: 0.684308 (0.6769) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.117s, 273.00/s (0.111s, 287.89/s) LR: 5.000e-04 Data: 0.001 (0.017) +2025-04-18 11:37:07,944 - train: [ INFO] - Train: 75 [ 450/461 ( 98%)] Loss: 0.671545 (0.6764) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 436.64/s (0.109s, 294.76/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:37:08,712 - train: [ INFO] - Train: 75 [ 460/461 (100%)] Loss: 0.686115 (0.6772) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 465.28/s (0.108s, 296.72/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-18 11:37:14,098 - train: [ INFO] - Eval : 75 Time: 5.089 (5.089) Loss: 2.0267 (2.0267) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:37:18,011 - train: [ INFO] - Eval : 75 Time: 0.025 (0.177) Loss: 1.8503 (1.9679) Acc@1: 56.2500 (50.7353)Acc@5: 78.1250 (76.5931) +2025-04-18 11:37:19,908 - train: [ INFO] - Eval : 75 Time: 0.014 (0.133) Loss: 3.0229 (1.9658) Acc@1: 0.0000 (50.6939)Acc@5: 50.0000 (76.2914) +2025-04-18 11:37:27,634 - train: [ INFO] - Train: 76 [ 0/461 ( 0%)] Loss: 0.679418 (0.6794) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.678s, 6.84/s (4.678s, 6.84/s) LR: 5.000e-04 Data: 4.524 (4.524) +2025-04-18 11:37:33,014 - train: [ INFO] - Train: 76 [ 50/461 ( 11%)] Loss: 0.695558 (0.6875) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 434.92/s (0.191s, 167.25/s) LR: 5.000e-04 Data: 0.001 (0.097) +2025-04-18 11:37:37,699 - train: [ INFO] - Train: 76 [ 100/461 ( 22%)] Loss: 0.717198 (0.6974) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 344.59/s (0.142s, 225.92/s) LR: 5.000e-04 Data: 0.001 (0.050) +2025-04-18 11:37:42,402 - train: [ INFO] - Train: 76 [ 150/461 ( 33%)] Loss: 0.675705 (0.6920) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 420.66/s (0.124s, 257.58/s) LR: 5.000e-04 Data: 0.001 (0.033) +2025-04-18 11:37:48,706 - train: [ INFO] - Train: 76 [ 200/461 ( 43%)] Loss: 0.666769 (0.6869) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.103s, 310.47/s (0.117s, 273.85/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-18 11:37:53,313 - train: [ INFO] - Train: 76 [ 250/461 ( 54%)] Loss: 0.717992 (0.6921) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.113s, 283.76/s (0.111s, 287.16/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:37:59,813 - train: [ INFO] - Train: 76 [ 300/461 ( 65%)] Loss: 0.670284 (0.6890) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 426.05/s (0.109s, 294.31/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 11:38:04,848 - train: [ INFO] - Train: 76 [ 350/461 ( 76%)] Loss: 0.675123 (0.6873) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 339.52/s (0.107s, 298.52/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-18 11:38:09,699 - train: [ INFO] - Train: 76 [ 400/461 ( 87%)] Loss: 0.673909 (0.6858) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 331.74/s (0.105s, 304.40/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-18 11:38:14,174 - train: [ INFO] - Train: 76 [ 450/461 ( 98%)] Loss: 0.683344 (0.6855) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 469.35/s (0.103s, 310.67/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:38:14,869 - train: [ INFO] - Train: 76 [ 460/461 (100%)] Loss: 0.670398 (0.6842) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.42/s (0.102s, 312.91/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:38:19,550 - train: [ INFO] - Eval : 76 Time: 4.408 (4.408) Loss: 2.0036 (2.0036) Acc@1: 53.1250 (53.1250)Acc@5: 78.1250 (78.1250) +2025-04-18 11:38:22,801 - train: [ INFO] - Eval : 76 Time: 0.026 (0.150) Loss: 1.7966 (1.9637) Acc@1: 56.2500 (50.7966)Acc@5: 75.0000 (75.9804) +2025-04-18 11:38:25,317 - train: [ INFO] - Eval : 76 Time: 0.014 (0.124) Loss: 3.0784 (1.9617) Acc@1: 0.0000 (50.3855)Acc@5: 50.0000 (75.9830) +2025-04-18 11:38:34,474 - train: [ INFO] - Train: 77 [ 0/461 ( 0%)] Loss: 0.671444 (0.6714) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.227s, 5.14/s (6.227s, 5.14/s) LR: 5.000e-04 Data: 6.004 (6.004) +2025-04-18 11:38:39,857 - train: [ INFO] - Train: 77 [ 50/461 ( 11%)] Loss: 0.689852 (0.6806) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.37/s (0.218s, 146.58/s) LR: 5.000e-04 Data: 0.001 (0.118) +2025-04-18 11:38:44,993 - train: [ INFO] - Train: 77 [ 100/461 ( 22%)] Loss: 0.670075 (0.6771) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.121s, 265.27/s (0.159s, 201.88/s) LR: 5.000e-04 Data: 0.001 (0.060) +2025-04-18 11:38:50,108 - train: [ INFO] - Train: 77 [ 150/461 ( 33%)] Loss: 0.664384 (0.6739) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 453.41/s (0.139s, 230.77/s) LR: 5.000e-04 Data: 0.000 (0.040) +2025-04-18 11:38:55,070 - train: [ INFO] - Train: 77 [ 200/461 ( 43%)] Loss: 0.675299 (0.6742) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.104s, 308.91/s (0.127s, 252.39/s) LR: 5.000e-04 Data: 0.001 (0.030) +2025-04-18 11:39:00,974 - train: [ INFO] - Train: 77 [ 250/461 ( 54%)] Loss: 0.670913 (0.6737) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.142s, 224.96/s (0.119s, 268.23/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-18 11:39:05,716 - train: [ INFO] - Train: 77 [ 300/461 ( 65%)] Loss: 0.673142 (0.6736) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 334.91/s (0.114s, 279.83/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-18 11:39:12,129 - train: [ INFO] - Train: 77 [ 350/461 ( 76%)] Loss: 0.682035 (0.6746) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 319.44/s (0.112s, 285.38/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-18 11:39:16,899 - train: [ INFO] - Train: 77 [ 400/461 ( 87%)] Loss: 0.665800 (0.6737) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 449.68/s (0.109s, 292.33/s) LR: 5.000e-04 Data: 0.001 (0.016) +2025-04-18 11:39:21,852 - train: [ INFO] - Train: 77 [ 450/461 ( 98%)] Loss: 0.668519 (0.6731) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.067s, 475.16/s (0.108s, 296.70/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:39:22,601 - train: [ INFO] - Train: 77 [ 460/461 (100%)] Loss: 0.668310 (0.6727) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 469.12/s (0.107s, 298.72/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:39:28,000 - train: [ INFO] - Eval : 77 Time: 5.118 (5.118) Loss: 2.0267 (2.0267) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:39:32,060 - train: [ INFO] - Eval : 77 Time: 0.025 (0.180) Loss: 1.8487 (1.9733) Acc@1: 59.3750 (50.6127)Acc@5: 75.0000 (76.1029) +2025-04-18 11:39:34,506 - train: [ INFO] - Eval : 77 Time: 0.014 (0.142) Loss: 2.9354 (1.9716) Acc@1: 0.0000 (50.8867)Acc@5: 50.0000 (76.0216) +2025-04-18 11:39:42,037 - train: [ INFO] - Train: 78 [ 0/461 ( 0%)] Loss: 0.687700 (0.6877) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.679s, 6.84/s (4.679s, 6.84/s) LR: 5.000e-04 Data: 4.558 (4.558) +2025-04-18 11:39:47,037 - train: [ INFO] - Train: 78 [ 50/461 ( 11%)] Loss: 0.665111 (0.6764) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.090s, 355.00/s (0.186s, 172.45/s) LR: 5.000e-04 Data: 0.001 (0.092) +2025-04-18 11:39:51,699 - train: [ INFO] - Train: 78 [ 100/461 ( 22%)] Loss: 0.672050 (0.6750) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 423.20/s (0.138s, 232.69/s) LR: 5.000e-04 Data: 0.001 (0.046) +2025-04-18 11:39:56,635 - train: [ INFO] - Train: 78 [ 150/461 ( 33%)] Loss: 0.674431 (0.6748) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 338.26/s (0.123s, 260.09/s) LR: 5.000e-04 Data: 0.000 (0.031) +2025-04-18 11:40:01,364 - train: [ INFO] - Train: 78 [ 200/461 ( 43%)] Loss: 0.675091 (0.6749) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.107s, 297.99/s (0.115s, 278.14/s) LR: 5.000e-04 Data: 0.001 (0.024) +2025-04-18 11:40:06,426 - train: [ INFO] - Train: 78 [ 250/461 ( 54%)] Loss: 0.671177 (0.6743) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.091s, 352.14/s (0.111s, 289.24/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-18 11:40:12,656 - train: [ INFO] - Train: 78 [ 300/461 ( 65%)] Loss: 0.673806 (0.6742) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 392.40/s (0.108s, 297.49/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:40:17,554 - train: [ INFO] - Train: 78 [ 350/461 ( 76%)] Loss: 0.688594 (0.6760) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 424.97/s (0.106s, 303.24/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:40:23,566 - train: [ INFO] - Train: 78 [ 400/461 ( 87%)] Loss: 0.678005 (0.6762) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.103s, 312.05/s (0.104s, 309.08/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:40:27,989 - train: [ INFO] - Train: 78 [ 450/461 ( 98%)] Loss: 0.672978 (0.6759) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.067s, 475.65/s (0.101s, 315.76/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:40:28,673 - train: [ INFO] - Train: 78 [ 460/461 (100%)] Loss: 0.680084 (0.6763) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.067s, 475.44/s (0.101s, 318.04/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:40:33,378 - train: [ INFO] - Eval : 78 Time: 4.424 (4.424) Loss: 2.0600 (2.0600) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:40:36,278 - train: [ INFO] - Eval : 78 Time: 0.320 (0.144) Loss: 1.8381 (1.9816) Acc@1: 56.2500 (51.0417)Acc@5: 71.8750 (75.6740) +2025-04-18 11:40:39,110 - train: [ INFO] - Eval : 78 Time: 0.014 (0.124) Loss: 3.0626 (1.9801) Acc@1: 0.0000 (50.9638)Acc@5: 50.0000 (75.8288) +2025-04-18 11:40:49,202 - train: [ INFO] - Train: 79 [ 0/461 ( 0%)] Loss: 0.667787 (0.6678) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.941s, 4.61/s (6.941s, 4.61/s) LR: 5.000e-04 Data: 6.714 (6.714) +2025-04-18 11:40:54,421 - train: [ INFO] - Train: 79 [ 50/461 ( 11%)] Loss: 0.665581 (0.6667) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 455.03/s (0.235s, 136.06/s) LR: 5.000e-04 Data: 0.000 (0.133) +2025-04-18 11:40:59,431 - train: [ INFO] - Train: 79 [ 100/461 ( 22%)] Loss: 0.673737 (0.6690) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.089s, 361.24/s (0.165s, 193.50/s) LR: 5.000e-04 Data: 0.001 (0.068) +2025-04-18 11:41:04,131 - train: [ INFO] - Train: 79 [ 150/461 ( 33%)] Loss: 0.663882 (0.6677) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.087s, 369.67/s (0.139s, 229.49/s) LR: 5.000e-04 Data: 0.001 (0.046) +2025-04-18 11:41:08,904 - train: [ INFO] - Train: 79 [ 200/461 ( 43%)] Loss: 0.669292 (0.6681) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 385.05/s (0.127s, 252.61/s) LR: 5.000e-04 Data: 0.001 (0.034) +2025-04-18 11:41:13,475 - train: [ INFO] - Train: 79 [ 250/461 ( 54%)] Loss: 0.676531 (0.6695) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.30/s (0.119s, 269.32/s) LR: 5.000e-04 Data: 0.000 (0.028) +2025-04-18 11:41:18,085 - train: [ INFO] - Train: 79 [ 300/461 ( 65%)] Loss: 0.675475 (0.6703) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 347.58/s (0.114s, 281.09/s) LR: 5.000e-04 Data: 0.000 (0.023) +2025-04-18 11:41:24,222 - train: [ INFO] - Train: 79 [ 350/461 ( 76%)] Loss: 0.664464 (0.6696) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.105s, 304.20/s (0.110s, 290.01/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:41:28,942 - train: [ INFO] - Train: 79 [ 400/461 ( 87%)] Loss: 0.749551 (0.6785) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 96.8750 (99.6528) Time: 0.177s, 180.33/s (0.108s, 297.21/s) LR: 5.000e-04 Data: 0.007 (0.018) +2025-04-18 11:41:35,249 - train: [ INFO] - Train: 79 [ 450/461 ( 98%)] Loss: 0.673766 (0.6780) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.075s, 424.46/s (0.106s, 301.69/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:41:36,037 - train: [ INFO] - Train: 79 [ 460/461 (100%)] Loss: 0.666925 (0.6770) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.068s, 472.86/s (0.105s, 303.61/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-18 11:41:41,525 - train: [ INFO] - Eval : 79 Time: 5.144 (5.144) Loss: 2.0427 (2.0427) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:41:44,080 - train: [ INFO] - Eval : 79 Time: 0.022 (0.151) Loss: 1.8454 (1.9839) Acc@1: 53.1250 (50.6740)Acc@5: 75.0000 (75.7353) +2025-04-18 11:41:46,441 - train: [ INFO] - Eval : 79 Time: 0.019 (0.123) Loss: 3.1130 (1.9818) Acc@1: 0.0000 (50.5783)Acc@5: 50.0000 (75.8674) +2025-04-18 11:41:54,976 - train: [ INFO] - Train: 80 [ 0/461 ( 0%)] Loss: 0.676119 (0.6761) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.675s, 5.64/s (5.675s, 5.64/s) LR: 5.000e-04 Data: 5.560 (5.560) +2025-04-18 11:41:59,881 - train: [ INFO] - Train: 80 [ 50/461 ( 11%)] Loss: 0.665195 (0.6707) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 381.39/s (0.204s, 156.73/s) LR: 5.000e-04 Data: 0.000 (0.109) +2025-04-18 11:42:04,728 - train: [ INFO] - Train: 80 [ 100/461 ( 22%)] Loss: 0.666772 (0.6694) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.102s, 312.85/s (0.150s, 213.80/s) LR: 5.000e-04 Data: 0.000 (0.056) +2025-04-18 11:42:10,261 - train: [ INFO] - Train: 80 [ 150/461 ( 33%)] Loss: 0.671665 (0.6699) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.104s, 308.60/s (0.134s, 238.82/s) LR: 5.000e-04 Data: 0.001 (0.038) +2025-04-18 11:42:15,363 - train: [ INFO] - Train: 80 [ 200/461 ( 43%)] Loss: 0.669208 (0.6698) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.110s, 290.16/s (0.125s, 256.41/s) LR: 5.000e-04 Data: 0.001 (0.029) +2025-04-18 11:42:20,764 - train: [ INFO] - Train: 80 [ 250/461 ( 54%)] Loss: 0.669166 (0.6697) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.133s, 241.36/s (0.120s, 266.18/s) LR: 5.000e-04 Data: 0.001 (0.023) +2025-04-18 11:42:25,800 - train: [ INFO] - Train: 80 [ 300/461 ( 65%)] Loss: 0.674386 (0.6704) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 432.30/s (0.115s, 277.37/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-18 11:42:31,167 - train: [ INFO] - Train: 80 [ 350/461 ( 76%)] Loss: 0.672673 (0.6706) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.120s, 267.02/s (0.112s, 285.28/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 11:42:37,418 - train: [ INFO] - Train: 80 [ 400/461 ( 87%)] Loss: 0.664768 (0.6700) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.114s, 281.63/s (0.110s, 291.49/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-18 11:42:42,083 - train: [ INFO] - Train: 80 [ 450/461 ( 98%)] Loss: 0.669911 (0.6700) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 457.01/s (0.108s, 296.99/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:42:43,723 - train: [ INFO] - Train: 80 [ 460/461 (100%)] Loss: 0.667340 (0.6697) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 461.57/s (0.107s, 299.20/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:42:47,794 - train: [ INFO] - Eval : 80 Time: 3.656 (3.656) Loss: 2.0339 (2.0339) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:42:52,451 - train: [ INFO] - Eval : 80 Time: 0.150 (0.163) Loss: 1.8514 (1.9840) Acc@1: 56.2500 (51.5931)Acc@5: 75.0000 (75.7966) +2025-04-18 11:42:54,791 - train: [ INFO] - Eval : 80 Time: 0.017 (0.130) Loss: 3.1474 (1.9826) Acc@1: 0.0000 (51.1180)Acc@5: 50.0000 (75.7517) +2025-04-18 11:43:07,124 - train: [ INFO] - Train: 81 [ 0/461 ( 0%)] Loss: 0.663222 (0.6632) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.355s, 3.83/s (8.355s, 3.83/s) LR: 5.000e-04 Data: 8.229 (8.229) +2025-04-18 11:43:18,480 - train: [ INFO] - Train: 81 [ 50/461 ( 11%)] Loss: 0.672533 (0.6679) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.89/s (0.343s, 93.23/s) LR: 5.000e-04 Data: 0.000 (0.263) +2025-04-18 11:43:28,732 - train: [ INFO] - Train: 81 [ 100/461 ( 22%)] Loss: 0.713192 (0.6830) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 459.50/s (0.258s, 124.17/s) LR: 5.000e-04 Data: 0.000 (0.178) +2025-04-18 11:43:37,982 - train: [ INFO] - Train: 81 [ 150/461 ( 33%)] Loss: 0.668006 (0.6792) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.132s, 242.54/s (0.226s, 141.90/s) LR: 5.000e-04 Data: 0.059 (0.145) +2025-04-18 11:43:48,813 - train: [ INFO] - Train: 81 [ 200/461 ( 43%)] Loss: 0.667921 (0.6770) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 455.84/s (0.218s, 146.65/s) LR: 5.000e-04 Data: 0.000 (0.135) +2025-04-18 11:43:59,004 - train: [ INFO] - Train: 81 [ 250/461 ( 54%)] Loss: 0.671179 (0.6760) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.90/s (0.211s, 151.63/s) LR: 5.000e-04 Data: 0.001 (0.129) +2025-04-18 11:44:08,417 - train: [ INFO] - Train: 81 [ 300/461 ( 65%)] Loss: 0.665536 (0.6745) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 471.32/s (0.206s, 155.40/s) LR: 5.000e-04 Data: 0.000 (0.126) +2025-04-18 11:44:16,417 - train: [ INFO] - Train: 81 [ 350/461 ( 76%)] Loss: 0.668020 (0.6737) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 381.31/s (0.198s, 161.58/s) LR: 5.000e-04 Data: 0.001 (0.117) +2025-04-18 11:44:29,052 - train: [ INFO] - Train: 81 [ 400/461 ( 87%)] Loss: 0.668577 (0.6731) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.254s, 25.53/s (0.202s, 158.11/s) LR: 5.000e-04 Data: 1.182 (0.121) +2025-04-18 11:44:41,082 - train: [ INFO] - Train: 81 [ 450/461 ( 98%)] Loss: 0.676920 (0.6735) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 467.12/s (0.204s, 156.85/s) LR: 5.000e-04 Data: 0.000 (0.124) +2025-04-18 11:44:42,611 - train: [ INFO] - Train: 81 [ 460/461 (100%)] Loss: 0.666607 (0.6729) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 472.22/s (0.203s, 157.75/s) LR: 5.000e-04 Data: 0.000 (0.123) +2025-04-18 11:44:47,158 - train: [ INFO] - Eval : 81 Time: 4.275 (4.275) Loss: 2.0590 (2.0590) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:44:58,596 - train: [ INFO] - Eval : 81 Time: 0.052 (0.308) Loss: 1.8345 (1.9907) Acc@1: 56.2500 (50.5515)Acc@5: 78.1250 (75.4289) +2025-04-18 11:45:05,193 - train: [ INFO] - Eval : 81 Time: 0.014 (0.272) Loss: 2.9847 (1.9882) Acc@1: 0.0000 (50.3855)Acc@5: 50.0000 (75.4433) +2025-04-18 11:45:15,335 - train: [ INFO] - Train: 82 [ 0/461 ( 0%)] Loss: 0.672503 (0.6725) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.555s, 4.88/s (6.555s, 4.88/s) LR: 5.000e-04 Data: 6.422 (6.422) +2025-04-18 11:45:22,552 - train: [ INFO] - Train: 82 [ 50/461 ( 11%)] Loss: 0.667244 (0.6699) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.143s, 224.17/s (0.265s, 120.61/s) LR: 5.000e-04 Data: 0.000 (0.179) +2025-04-18 11:45:28,242 - train: [ INFO] - Train: 82 [ 100/461 ( 22%)] Loss: 0.663505 (0.6678) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.44/s (0.189s, 169.39/s) LR: 5.000e-04 Data: 0.000 (0.106) +2025-04-18 11:45:34,674 - train: [ INFO] - Train: 82 [ 150/461 ( 33%)] Loss: 0.666310 (0.6674) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 465.35/s (0.168s, 190.61/s) LR: 5.000e-04 Data: 0.001 (0.083) +2025-04-18 11:45:40,938 - train: [ INFO] - Train: 82 [ 200/461 ( 43%)] Loss: 0.663718 (0.6667) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.130s, 246.15/s (0.156s, 204.67/s) LR: 5.000e-04 Data: 0.001 (0.067) +2025-04-18 11:45:48,591 - train: [ INFO] - Train: 82 [ 250/461 ( 54%)] Loss: 0.702892 (0.6727) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 340.51/s (0.146s, 219.77/s) LR: 5.000e-04 Data: 0.001 (0.054) +2025-04-18 11:45:54,296 - train: [ INFO] - Train: 82 [ 300/461 ( 65%)] Loss: 0.671045 (0.6725) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.099s, 323.71/s (0.139s, 229.45/s) LR: 5.000e-04 Data: 0.001 (0.045) +2025-04-18 11:46:00,332 - train: [ INFO] - Train: 82 [ 350/461 ( 76%)] Loss: 0.662661 (0.6712) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.089s, 359.33/s (0.135s, 236.30/s) LR: 5.000e-04 Data: 0.001 (0.039) +2025-04-18 11:46:07,461 - train: [ INFO] - Train: 82 [ 400/461 ( 87%)] Loss: 0.698409 (0.6743) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.143s, 224.49/s (0.133s, 240.34/s) LR: 5.000e-04 Data: 0.001 (0.034) +2025-04-18 11:46:13,676 - train: [ INFO] - Train: 82 [ 450/461 ( 98%)] Loss: 0.666986 (0.6735) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 473.14/s (0.129s, 248.00/s) LR: 5.000e-04 Data: 0.000 (0.031) +2025-04-18 11:46:14,383 - train: [ INFO] - Train: 82 [ 460/461 (100%)] Loss: 0.737102 (0.6793) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.070s, 458.43/s (0.128s, 250.51/s) LR: 5.000e-04 Data: 0.000 (0.030) +2025-04-18 11:46:24,114 - train: [ INFO] - Eval : 82 Time: 9.421 (9.421) Loss: 2.0769 (2.0769) Acc@1: 50.0000 (50.0000)Acc@5: 71.8750 (71.8750) +2025-04-18 11:46:27,271 - train: [ INFO] - Eval : 82 Time: 0.096 (0.247) Loss: 1.8574 (1.9875) Acc@1: 59.3750 (51.1029)Acc@5: 75.0000 (76.1642) +2025-04-18 11:46:31,631 - train: [ INFO] - Eval : 82 Time: 0.014 (0.207) Loss: 3.0462 (1.9885) Acc@1: 0.0000 (50.9638)Acc@5: 50.0000 (75.9830) +2025-04-18 11:46:39,295 - train: [ INFO] - Train: 83 [ 0/461 ( 0%)] Loss: 0.672170 (0.6722) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.468s, 7.16/s (4.468s, 7.16/s) LR: 5.000e-04 Data: 4.335 (4.335) +2025-04-18 11:46:45,686 - train: [ INFO] - Train: 83 [ 50/461 ( 11%)] Loss: 0.671301 (0.6717) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.124s, 258.10/s (0.205s, 155.83/s) LR: 5.000e-04 Data: 0.001 (0.090) +2025-04-18 11:46:52,021 - train: [ INFO] - Train: 83 [ 100/461 ( 22%)] Loss: 0.696272 (0.6799) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.103s, 309.41/s (0.148s, 215.83/s) LR: 5.000e-04 Data: 0.001 (0.046) +2025-04-18 11:46:57,957 - train: [ INFO] - Train: 83 [ 150/461 ( 33%)] Loss: 0.668668 (0.6771) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.104s, 306.43/s (0.135s, 237.49/s) LR: 5.000e-04 Data: 0.000 (0.031) +2025-04-18 11:47:04,207 - train: [ INFO] - Train: 83 [ 200/461 ( 43%)] Loss: 0.666221 (0.6749) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.244s, 131.12/s (0.131s, 244.28/s) LR: 5.000e-04 Data: 0.001 (0.024) +2025-04-18 11:47:09,637 - train: [ INFO] - Train: 83 [ 250/461 ( 54%)] Loss: 0.662867 (0.6729) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 341.26/s (0.125s, 255.86/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-18 11:47:14,806 - train: [ INFO] - Train: 83 [ 300/461 ( 65%)] Loss: 0.667287 (0.6721) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 386.84/s (0.120s, 266.37/s) LR: 5.000e-04 Data: 0.001 (0.016) +2025-04-18 11:47:20,502 - train: [ INFO] - Train: 83 [ 350/461 ( 76%)] Loss: 0.666045 (0.6714) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 433.23/s (0.118s, 270.41/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:47:26,712 - train: [ INFO] - Train: 83 [ 400/461 ( 87%)] Loss: 0.673370 (0.6716) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.099s, 321.92/s (0.118s, 270.85/s) LR: 5.000e-04 Data: 0.001 (0.012) +2025-04-18 11:47:33,054 - train: [ INFO] - Train: 83 [ 450/461 ( 98%)] Loss: 0.664041 (0.6708) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 448.24/s (0.116s, 274.93/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:47:33,804 - train: [ INFO] - Train: 83 [ 460/461 (100%)] Loss: 0.680320 (0.6717) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 468.56/s (0.115s, 277.26/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:47:40,810 - train: [ INFO] - Eval : 83 Time: 6.360 (6.360) Loss: 2.0721 (2.0721) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:47:47,248 - train: [ INFO] - Eval : 83 Time: 0.051 (0.251) Loss: 1.8600 (1.9970) Acc@1: 59.3750 (51.5319)Acc@5: 75.0000 (75.5515) +2025-04-18 11:47:48,830 - train: [ INFO] - Eval : 83 Time: 0.018 (0.175) Loss: 2.9134 (1.9964) Acc@1: 0.0000 (51.1951)Acc@5: 50.0000 (75.4433) +2025-04-18 11:47:56,619 - train: [ INFO] - Train: 84 [ 0/461 ( 0%)] Loss: 0.664737 (0.6647) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.806s, 6.66/s (4.806s, 6.66/s) LR: 5.000e-04 Data: 4.675 (4.675) +2025-04-18 11:48:02,673 - train: [ INFO] - Train: 84 [ 50/461 ( 11%)] Loss: 0.665242 (0.6650) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 390.72/s (0.209s, 153.32/s) LR: 5.000e-04 Data: 0.001 (0.098) +2025-04-18 11:48:08,564 - train: [ INFO] - Train: 84 [ 100/461 ( 22%)] Loss: 0.667398 (0.6658) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.114s, 280.17/s (0.153s, 209.20/s) LR: 5.000e-04 Data: 0.003 (0.050) +2025-04-18 11:48:15,042 - train: [ INFO] - Train: 84 [ 150/461 ( 33%)] Loss: 0.665701 (0.6658) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.243s, 131.65/s (0.139s, 230.95/s) LR: 5.000e-04 Data: 0.001 (0.034) +2025-04-18 11:48:21,080 - train: [ INFO] - Train: 84 [ 200/461 ( 43%)] Loss: 0.664169 (0.6654) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 406.79/s (0.133s, 240.59/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-18 11:48:26,965 - train: [ INFO] - Train: 84 [ 250/461 ( 54%)] Loss: 0.669088 (0.6661) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 319.43/s (0.128s, 249.48/s) LR: 5.000e-04 Data: 0.001 (0.021) +2025-04-18 11:48:32,167 - train: [ INFO] - Train: 84 [ 300/461 ( 65%)] Loss: 0.671848 (0.6669) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.108s, 295.40/s (0.123s, 259.70/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-18 11:48:37,178 - train: [ INFO] - Train: 84 [ 350/461 ( 76%)] Loss: 0.687323 (0.6694) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 407.82/s (0.119s, 268.13/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-18 11:48:42,718 - train: [ INFO] - Train: 84 [ 400/461 ( 87%)] Loss: 0.666216 (0.6691) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.115s, 277.97/s (0.118s, 271.55/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 11:48:51,407 - train: [ INFO] - Train: 84 [ 450/461 ( 98%)] Loss: 0.665013 (0.6687) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 471.82/s (0.117s, 274.40/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:48:52,288 - train: [ INFO] - Train: 84 [ 460/461 (100%)] Loss: 0.665168 (0.6684) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.56/s (0.116s, 276.06/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:48:57,439 - train: [ INFO] - Eval : 84 Time: 4.736 (4.736) Loss: 2.0829 (2.0829) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:49:02,474 - train: [ INFO] - Eval : 84 Time: 0.025 (0.192) Loss: 1.8610 (1.9983) Acc@1: 56.2500 (51.4093)Acc@5: 75.0000 (75.3676) +2025-04-18 11:49:04,157 - train: [ INFO] - Eval : 84 Time: 0.018 (0.140) Loss: 2.8884 (1.9987) Acc@1: 0.0000 (50.8481)Acc@5: 50.0000 (75.4819) +2025-04-18 11:49:15,160 - train: [ INFO] - Train: 85 [ 0/461 ( 0%)] Loss: 0.663626 (0.6636) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.333s, 7.38/s (4.333s, 7.38/s) LR: 5.000e-04 Data: 4.206 (4.206) +2025-04-18 11:49:20,589 - train: [ INFO] - Train: 85 [ 50/461 ( 11%)] Loss: 0.673745 (0.6687) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 334.48/s (0.187s, 171.36/s) LR: 5.000e-04 Data: 0.000 (0.084) +2025-04-18 11:49:26,505 - train: [ INFO] - Train: 85 [ 100/461 ( 22%)] Loss: 0.668597 (0.6687) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.107s, 299.00/s (0.142s, 224.66/s) LR: 5.000e-04 Data: 0.001 (0.043) +2025-04-18 11:49:31,983 - train: [ INFO] - Train: 85 [ 150/461 ( 33%)] Loss: 0.675271 (0.6703) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.201s, 158.95/s (0.130s, 245.51/s) LR: 5.000e-04 Data: 0.001 (0.029) +2025-04-18 11:49:38,078 - train: [ INFO] - Train: 85 [ 200/461 ( 43%)] Loss: 0.666768 (0.6696) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.01/s (0.124s, 258.52/s) LR: 5.000e-04 Data: 0.000 (0.022) +2025-04-18 11:49:44,229 - train: [ INFO] - Train: 85 [ 250/461 ( 54%)] Loss: 0.669393 (0.6696) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.121s, 263.90/s (0.122s, 262.42/s) LR: 5.000e-04 Data: 0.007 (0.018) +2025-04-18 11:49:49,499 - train: [ INFO] - Train: 85 [ 300/461 ( 65%)] Loss: 0.690284 (0.6725) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 437.00/s (0.118s, 270.13/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-18 11:49:55,486 - train: [ INFO] - Train: 85 [ 350/461 ( 76%)] Loss: 0.663739 (0.6714) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.146s, 219.08/s (0.116s, 276.00/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-18 11:50:01,886 - train: [ INFO] - Train: 85 [ 400/461 ( 87%)] Loss: 0.668759 (0.6711) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.127s, 251.22/s (0.114s, 280.38/s) LR: 5.000e-04 Data: 0.001 (0.011) +2025-04-18 11:50:07,689 - train: [ INFO] - Train: 85 [ 450/461 ( 98%)] Loss: 0.670441 (0.6711) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.68/s (0.113s, 284.04/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 11:50:09,016 - train: [ INFO] - Train: 85 [ 460/461 (100%)] Loss: 0.663070 (0.6703) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.150s, 212.88/s (0.112s, 285.07/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 11:50:13,471 - train: [ INFO] - Eval : 85 Time: 4.138 (4.138) Loss: 2.0606 (2.0606) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:50:16,212 - train: [ INFO] - Eval : 85 Time: 0.061 (0.135) Loss: 1.8393 (1.9913) Acc@1: 56.2500 (51.1642)Acc@5: 71.8750 (75.5515) +2025-04-18 11:50:17,638 - train: [ INFO] - Eval : 85 Time: 0.018 (0.101) Loss: 3.1195 (1.9908) Acc@1: 0.0000 (50.6939)Acc@5: 50.0000 (75.4433) +2025-04-18 11:50:25,538 - train: [ INFO] - Train: 86 [ 0/461 ( 0%)] Loss: 0.687681 (0.6877) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.821s, 6.64/s (4.821s, 6.64/s) LR: 5.000e-04 Data: 4.702 (4.702) +2025-04-18 11:50:32,739 - train: [ INFO] - Train: 86 [ 50/461 ( 11%)] Loss: 0.661441 (0.6746) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.114s, 280.11/s (0.209s, 153.36/s) LR: 5.000e-04 Data: 0.000 (0.096) +2025-04-18 11:50:38,280 - train: [ INFO] - Train: 86 [ 100/461 ( 22%)] Loss: 0.690211 (0.6798) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 401.92/s (0.157s, 204.31/s) LR: 5.000e-04 Data: 0.001 (0.049) +2025-04-18 11:50:44,013 - train: [ INFO] - Train: 86 [ 150/461 ( 33%)] Loss: 0.670002 (0.6773) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 319.17/s (0.136s, 236.04/s) LR: 5.000e-04 Data: 0.001 (0.033) +2025-04-18 11:50:49,739 - train: [ INFO] - Train: 86 [ 200/461 ( 43%)] Loss: 0.664454 (0.6748) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.125s, 256.60/s (0.129s, 247.75/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-18 11:50:55,670 - train: [ INFO] - Train: 86 [ 250/461 ( 54%)] Loss: 0.664513 (0.6731) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.104s, 307.21/s (0.126s, 253.96/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:51:01,964 - train: [ INFO] - Train: 86 [ 300/461 ( 65%)] Loss: 0.666592 (0.6721) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.091s, 351.19/s (0.123s, 260.53/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 11:51:07,207 - train: [ INFO] - Train: 86 [ 350/461 ( 76%)] Loss: 0.662562 (0.6709) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.117s, 272.71/s (0.119s, 268.02/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:51:14,001 - train: [ INFO] - Train: 86 [ 400/461 ( 87%)] Loss: 0.667648 (0.6706) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.119s, 268.72/s (0.116s, 274.77/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-18 11:51:19,267 - train: [ INFO] - Train: 86 [ 450/461 ( 98%)] Loss: 0.667174 (0.6702) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 427.04/s (0.115s, 278.74/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:51:20,158 - train: [ INFO] - Train: 86 [ 460/461 (100%)] Loss: 0.664876 (0.6697) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.49/s (0.114s, 280.16/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:51:26,560 - train: [ INFO] - Eval : 86 Time: 6.022 (6.022) Loss: 2.0769 (2.0769) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:51:31,575 - train: [ INFO] - Eval : 86 Time: 0.053 (0.216) Loss: 1.8546 (2.0034) Acc@1: 56.2500 (50.7966)Acc@5: 75.0000 (75.6127) +2025-04-18 11:51:33,421 - train: [ INFO] - Eval : 86 Time: 0.014 (0.157) Loss: 3.1328 (2.0020) Acc@1: 0.0000 (50.5397)Acc@5: 0.0000 (75.2891) +2025-04-18 11:51:40,665 - train: [ INFO] - Train: 87 [ 0/461 ( 0%)] Loss: 0.666934 (0.6669) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.177s, 7.66/s (4.177s, 7.66/s) LR: 5.000e-04 Data: 4.045 (4.045) +2025-04-18 11:51:46,351 - train: [ INFO] - Train: 87 [ 50/461 ( 11%)] Loss: 0.683394 (0.6752) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 436.45/s (0.189s, 168.95/s) LR: 5.000e-04 Data: 0.001 (0.082) +2025-04-18 11:51:53,642 - train: [ INFO] - Train: 87 [ 100/461 ( 22%)] Loss: 0.677450 (0.6759) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.132s, 242.66/s (0.153s, 209.13/s) LR: 5.000e-04 Data: 0.001 (0.042) +2025-04-18 11:51:59,090 - train: [ INFO] - Train: 87 [ 150/461 ( 33%)] Loss: 0.673217 (0.6752) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.115s, 278.62/s (0.136s, 235.45/s) LR: 5.000e-04 Data: 0.001 (0.029) +2025-04-18 11:52:05,098 - train: [ INFO] - Train: 87 [ 200/461 ( 43%)] Loss: 0.661988 (0.6726) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 386.72/s (0.127s, 251.91/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-18 11:52:10,861 - train: [ INFO] - Train: 87 [ 250/461 ( 54%)] Loss: 0.673301 (0.6727) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 318.88/s (0.123s, 260.04/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-18 11:52:17,165 - train: [ INFO] - Train: 87 [ 300/461 ( 65%)] Loss: 0.663553 (0.6714) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 319.80/s (0.121s, 264.51/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-18 11:52:24,315 - train: [ INFO] - Train: 87 [ 350/461 ( 76%)] Loss: 0.680135 (0.6725) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 433.55/s (0.121s, 264.88/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-18 11:52:30,514 - train: [ INFO] - Train: 87 [ 400/461 ( 87%)] Loss: 0.664227 (0.6716) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 393.99/s (0.119s, 269.19/s) LR: 5.000e-04 Data: 0.001 (0.011) +2025-04-18 11:52:35,652 - train: [ INFO] - Train: 87 [ 450/461 ( 98%)] Loss: 0.662062 (0.6706) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.43/s (0.117s, 274.14/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 11:52:36,498 - train: [ INFO] - Train: 87 [ 460/461 (100%)] Loss: 0.666794 (0.6703) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.196s, 163.07/s (0.116s, 275.82/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 11:52:41,381 - train: [ INFO] - Eval : 87 Time: 4.595 (4.595) Loss: 2.0653 (2.0653) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:52:46,200 - train: [ INFO] - Eval : 87 Time: 0.071 (0.185) Loss: 1.8629 (1.9999) Acc@1: 56.2500 (50.9804)Acc@5: 75.0000 (75.3676) +2025-04-18 11:52:48,081 - train: [ INFO] - Eval : 87 Time: 0.019 (0.138) Loss: 3.0854 (1.9996) Acc@1: 0.0000 (50.4241)Acc@5: 50.0000 (75.5590) +2025-04-18 11:52:54,726 - train: [ INFO] - Train: 88 [ 0/461 ( 0%)] Loss: 0.670976 (0.6710) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 3.656s, 8.75/s (3.656s, 8.75/s) LR: 5.000e-04 Data: 3.563 (3.563) +2025-04-18 11:53:02,204 - train: [ INFO] - Train: 88 [ 50/461 ( 11%)] Loss: 0.666961 (0.6690) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 447.70/s (0.210s, 152.26/s) LR: 5.000e-04 Data: 0.001 (0.090) +2025-04-18 11:53:08,175 - train: [ INFO] - Train: 88 [ 100/461 ( 22%)] Loss: 0.664292 (0.6674) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.166s, 192.58/s (0.162s, 197.04/s) LR: 5.000e-04 Data: 0.001 (0.046) +2025-04-18 11:53:15,993 - train: [ INFO] - Train: 88 [ 150/461 ( 33%)] Loss: 0.664350 (0.6666) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.155s, 206.90/s (0.145s, 220.94/s) LR: 5.000e-04 Data: 0.001 (0.031) +2025-04-18 11:53:21,186 - train: [ INFO] - Train: 88 [ 200/461 ( 43%)] Loss: 0.677799 (0.6689) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.115s, 278.03/s (0.133s, 240.95/s) LR: 5.000e-04 Data: 0.001 (0.024) +2025-04-18 11:53:26,231 - train: [ INFO] - Train: 88 [ 250/461 ( 54%)] Loss: 0.663746 (0.6680) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 407.39/s (0.125s, 256.31/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-18 11:53:32,507 - train: [ INFO] - Train: 88 [ 300/461 ( 65%)] Loss: 0.686356 (0.6706) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 459.75/s (0.124s, 259.00/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:53:39,104 - train: [ INFO] - Train: 88 [ 350/461 ( 76%)] Loss: 0.669069 (0.6704) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.116s, 274.82/s (0.121s, 264.34/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 11:53:45,118 - train: [ INFO] - Train: 88 [ 400/461 ( 87%)] Loss: 0.671368 (0.6705) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 434.52/s (0.120s, 267.05/s) LR: 5.000e-04 Data: 0.001 (0.012) +2025-04-18 11:53:50,715 - train: [ INFO] - Train: 88 [ 450/461 ( 98%)] Loss: 0.671076 (0.6706) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.091s, 350.60/s (0.118s, 271.95/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:53:51,748 - train: [ INFO] - Train: 88 [ 460/461 (100%)] Loss: 0.698321 (0.6731) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 453.13/s (0.117s, 272.80/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:53:56,240 - train: [ INFO] - Eval : 88 Time: 4.232 (4.232) Loss: 2.0867 (2.0867) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 11:54:02,344 - train: [ INFO] - Eval : 88 Time: 0.056 (0.203) Loss: 1.8633 (2.0082) Acc@1: 56.2500 (50.9191)Acc@5: 75.0000 (75.7966) +2025-04-18 11:54:03,784 - train: [ INFO] - Eval : 88 Time: 0.018 (0.144) Loss: 3.0606 (2.0064) Acc@1: 0.0000 (50.3855)Acc@5: 0.0000 (75.5590) +2025-04-18 11:54:11,009 - train: [ INFO] - Train: 89 [ 0/461 ( 0%)] Loss: 0.668156 (0.6682) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.303s, 7.44/s (4.303s, 7.44/s) LR: 5.000e-04 Data: 4.137 (4.137) +2025-04-18 11:54:16,689 - train: [ INFO] - Train: 89 [ 50/461 ( 11%)] Loss: 0.668322 (0.6682) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 449.11/s (0.190s, 168.50/s) LR: 5.000e-04 Data: 0.000 (0.082) +2025-04-18 11:54:22,527 - train: [ INFO] - Train: 89 [ 100/461 ( 22%)] Loss: 0.720517 (0.6857) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.093s, 345.25/s (0.152s, 211.21/s) LR: 5.000e-04 Data: 0.001 (0.042) +2025-04-18 11:54:28,360 - train: [ INFO] - Train: 89 [ 150/461 ( 33%)] Loss: 0.669902 (0.6817) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.076s, 419.74/s (0.139s, 230.54/s) LR: 5.000e-04 Data: 0.001 (0.028) +2025-04-18 11:54:34,972 - train: [ INFO] - Train: 89 [ 200/461 ( 43%)] Loss: 0.664762 (0.6783) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.094s, 339.43/s (0.130s, 245.89/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-18 11:54:41,332 - train: [ INFO] - Train: 89 [ 250/461 ( 54%)] Loss: 0.663772 (0.6759) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.216s, 148.32/s (0.129s, 248.98/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-18 11:54:48,595 - train: [ INFO] - Train: 89 [ 300/461 ( 65%)] Loss: 0.662133 (0.6739) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.069s, 463.07/s (0.127s, 251.68/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-18 11:54:54,223 - train: [ INFO] - Train: 89 [ 350/461 ( 76%)] Loss: 0.662956 (0.6726) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.073s, 441.10/s (0.124s, 258.34/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:54:59,466 - train: [ INFO] - Train: 89 [ 400/461 ( 87%)] Loss: 0.709115 (0.6766) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.073s, 439.10/s (0.121s, 265.44/s) LR: 5.000e-04 Data: 0.001 (0.011) +2025-04-18 11:55:04,199 - train: [ INFO] - Train: 89 [ 450/461 ( 98%)] Loss: 0.714714 (0.6804) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.068s, 471.08/s (0.117s, 272.95/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 11:55:05,172 - train: [ INFO] - Train: 89 [ 460/461 (100%)] Loss: 0.663275 (0.6789) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.069s, 462.67/s (0.117s, 274.00/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 11:55:11,358 - train: [ INFO] - Eval : 89 Time: 5.773 (5.773) Loss: 2.0987 (2.0987) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:55:15,400 - train: [ INFO] - Eval : 89 Time: 0.077 (0.192) Loss: 1.8474 (2.0131) Acc@1: 59.3750 (50.7966)Acc@5: 75.0000 (75.1225) +2025-04-18 11:55:17,644 - train: [ INFO] - Eval : 89 Time: 0.015 (0.147) Loss: 2.9972 (2.0116) Acc@1: 0.0000 (50.2699)Acc@5: 50.0000 (75.0578) +2025-04-18 11:55:27,257 - train: [ INFO] - Train: 90 [ 0/461 ( 0%)] Loss: 0.664324 (0.6643) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.581s, 4.86/s (6.581s, 4.86/s) LR: 5.000e-04 Data: 6.444 (6.444) +2025-04-18 11:55:33,894 - train: [ INFO] - Train: 90 [ 50/461 ( 11%)] Loss: 0.671602 (0.6680) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.109s, 293.75/s (0.253s, 126.57/s) LR: 5.000e-04 Data: 0.000 (0.148) +2025-04-18 11:55:39,395 - train: [ INFO] - Train: 90 [ 100/461 ( 22%)] Loss: 0.687640 (0.6745) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 333.84/s (0.180s, 177.90/s) LR: 5.000e-04 Data: 0.000 (0.075) +2025-04-18 11:55:44,735 - train: [ INFO] - Train: 90 [ 150/461 ( 33%)] Loss: 0.662252 (0.6715) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 343.74/s (0.154s, 207.72/s) LR: 5.000e-04 Data: 0.001 (0.050) +2025-04-18 11:55:50,624 - train: [ INFO] - Train: 90 [ 200/461 ( 43%)] Loss: 0.666907 (0.6705) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 449.70/s (0.138s, 232.61/s) LR: 5.000e-04 Data: 0.000 (0.038) +2025-04-18 11:55:56,098 - train: [ INFO] - Train: 90 [ 250/461 ( 54%)] Loss: 0.664648 (0.6696) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.101s, 315.99/s (0.131s, 244.18/s) LR: 5.000e-04 Data: 0.001 (0.031) +2025-04-18 11:56:02,918 - train: [ INFO] - Train: 90 [ 300/461 ( 65%)] Loss: 0.667933 (0.6693) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.212s, 150.71/s (0.128s, 250.95/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-18 11:56:09,376 - train: [ INFO] - Train: 90 [ 350/461 ( 76%)] Loss: 0.665109 (0.6688) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.114s, 280.10/s (0.127s, 252.16/s) LR: 5.000e-04 Data: 0.000 (0.022) +2025-04-18 11:56:15,253 - train: [ INFO] - Train: 90 [ 400/461 ( 87%)] Loss: 0.687534 (0.6709) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.101s, 315.42/s (0.125s, 256.69/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:56:20,272 - train: [ INFO] - Train: 90 [ 450/461 ( 98%)] Loss: 0.688706 (0.6727) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 467.49/s (0.121s, 263.72/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-18 11:56:20,984 - train: [ INFO] - Train: 90 [ 460/461 (100%)] Loss: 0.693826 (0.6746) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.32/s (0.120s, 266.14/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 11:56:25,670 - train: [ INFO] - Eval : 90 Time: 4.439 (4.439) Loss: 2.1094 (2.1094) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:56:29,049 - train: [ INFO] - Eval : 90 Time: 0.022 (0.153) Loss: 1.8730 (2.0094) Acc@1: 59.3750 (50.7966)Acc@5: 71.8750 (75.2451) +2025-04-18 11:56:30,939 - train: [ INFO] - Eval : 90 Time: 0.014 (0.118) Loss: 3.0349 (2.0088) Acc@1: 0.0000 (50.3470)Acc@5: 50.0000 (75.2891) +2025-04-18 11:56:37,667 - train: [ INFO] - Train: 91 [ 0/461 ( 0%)] Loss: 0.660838 (0.6608) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 3.966s, 8.07/s (3.966s, 8.07/s) LR: 5.000e-04 Data: 3.799 (3.799) +2025-04-18 11:56:42,968 - train: [ INFO] - Train: 91 [ 50/461 ( 11%)] Loss: 0.665001 (0.6629) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 416.62/s (0.177s, 180.33/s) LR: 5.000e-04 Data: 0.001 (0.075) +2025-04-18 11:56:48,951 - train: [ INFO] - Train: 91 [ 100/461 ( 22%)] Loss: 0.662965 (0.6629) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 342.89/s (0.147s, 218.20/s) LR: 5.000e-04 Data: 0.001 (0.039) +2025-04-18 11:56:55,358 - train: [ INFO] - Train: 91 [ 150/461 ( 33%)] Loss: 0.736708 (0.6814) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.069s, 462.09/s (0.138s, 231.89/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-18 11:57:01,057 - train: [ INFO] - Train: 91 [ 200/461 ( 43%)] Loss: 0.662158 (0.6775) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.102s, 313.48/s (0.131s, 244.89/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:57:06,349 - train: [ INFO] - Train: 91 [ 250/461 ( 54%)] Loss: 0.666096 (0.6756) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.069s, 466.93/s (0.124s, 257.73/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:57:13,552 - train: [ INFO] - Train: 91 [ 300/461 ( 65%)] Loss: 0.662147 (0.6737) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.073s, 438.82/s (0.119s, 268.38/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 11:57:19,645 - train: [ INFO] - Train: 91 [ 350/461 ( 76%)] Loss: 0.661539 (0.6722) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.072s, 441.56/s (0.119s, 269.09/s) LR: 5.000e-04 Data: 0.001 (0.012) +2025-04-18 11:57:25,167 - train: [ INFO] - Train: 91 [ 400/461 ( 87%)] Loss: 0.672182 (0.6722) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.185s, 172.65/s (0.117s, 273.33/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 11:57:31,135 - train: [ INFO] - Train: 91 [ 450/461 ( 98%)] Loss: 0.665146 (0.6715) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.076s, 419.78/s (0.114s, 281.62/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 11:57:31,942 - train: [ INFO] - Train: 91 [ 460/461 (100%)] Loss: 0.674214 (0.6717) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.072s, 445.66/s (0.113s, 283.81/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 11:57:39,121 - train: [ INFO] - Eval : 91 Time: 6.807 (6.807) Loss: 2.1154 (2.1154) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:57:46,208 - train: [ INFO] - Eval : 91 Time: 0.050 (0.272) Loss: 1.8787 (2.0098) Acc@1: 56.2500 (50.7353)Acc@5: 75.0000 (75.7966) +2025-04-18 11:57:48,459 - train: [ INFO] - Eval : 91 Time: 0.014 (0.197) Loss: 3.0359 (2.0072) Acc@1: 0.0000 (50.5397)Acc@5: 50.0000 (75.7517) +2025-04-18 11:57:56,614 - train: [ INFO] - Train: 92 [ 0/461 ( 0%)] Loss: 0.667078 (0.6671) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.051s, 6.34/s (5.051s, 6.34/s) LR: 5.000e-04 Data: 4.908 (4.908) +2025-04-18 11:58:03,033 - train: [ INFO] - Train: 92 [ 50/461 ( 11%)] Loss: 0.661813 (0.6644) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.138s, 232.49/s (0.203s, 157.89/s) LR: 5.000e-04 Data: 0.001 (0.102) +2025-04-18 11:58:08,722 - train: [ INFO] - Train: 92 [ 100/461 ( 22%)] Loss: 0.674903 (0.6679) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 449.87/s (0.156s, 204.68/s) LR: 5.000e-04 Data: 0.001 (0.052) +2025-04-18 11:58:14,208 - train: [ INFO] - Train: 92 [ 150/461 ( 33%)] Loss: 0.668773 (0.6681) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.282s, 113.30/s (0.139s, 230.07/s) LR: 5.000e-04 Data: 0.001 (0.035) +2025-04-18 11:58:20,373 - train: [ INFO] - Train: 92 [ 200/461 ( 43%)] Loss: 0.672821 (0.6691) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 437.17/s (0.132s, 242.70/s) LR: 5.000e-04 Data: 0.001 (0.026) +2025-04-18 11:58:27,418 - train: [ INFO] - Train: 92 [ 250/461 ( 54%)] Loss: 0.675565 (0.6702) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 422.52/s (0.126s, 254.49/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-18 11:58:34,131 - train: [ INFO] - Train: 92 [ 300/461 ( 65%)] Loss: 0.663812 (0.6693) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.47/s (0.125s, 255.54/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-18 11:58:41,331 - train: [ INFO] - Train: 92 [ 350/461 ( 76%)] Loss: 0.662807 (0.6684) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.148s, 215.86/s (0.123s, 259.18/s) LR: 5.000e-04 Data: 0.001 (0.016) +2025-04-18 11:58:47,012 - train: [ INFO] - Train: 92 [ 400/461 ( 87%)] Loss: 0.662498 (0.6678) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 335.64/s (0.121s, 263.44/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 11:58:53,023 - train: [ INFO] - Train: 92 [ 450/461 ( 98%)] Loss: 0.666253 (0.6676) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 460.31/s (0.118s, 270.97/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:58:53,724 - train: [ INFO] - Train: 92 [ 460/461 (100%)] Loss: 0.674510 (0.6683) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 455.44/s (0.117s, 273.41/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:58:58,138 - train: [ INFO] - Eval : 92 Time: 4.141 (4.141) Loss: 2.1112 (2.1112) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 11:59:01,397 - train: [ INFO] - Eval : 92 Time: 0.063 (0.145) Loss: 1.8685 (2.0041) Acc@1: 56.2500 (50.6127)Acc@5: 75.0000 (76.2868) +2025-04-18 11:59:04,142 - train: [ INFO] - Eval : 92 Time: 0.017 (0.124) Loss: 3.0941 (2.0049) Acc@1: 0.0000 (50.2699)Acc@5: 50.0000 (75.7903) +2025-04-18 11:59:13,167 - train: [ INFO] - Train: 93 [ 0/461 ( 0%)] Loss: 0.695192 (0.6952) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.918s, 5.41/s (5.918s, 5.41/s) LR: 5.000e-04 Data: 5.807 (5.807) +2025-04-18 11:59:19,814 - train: [ INFO] - Train: 93 [ 50/461 ( 11%)] Loss: 0.724397 (0.7098) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.176s, 181.87/s (0.231s, 138.77/s) LR: 5.000e-04 Data: 0.001 (0.138) +2025-04-18 11:59:25,434 - train: [ INFO] - Train: 93 [ 100/461 ( 22%)] Loss: 0.679080 (0.6996) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 440.19/s (0.167s, 191.38/s) LR: 5.000e-04 Data: 0.001 (0.070) +2025-04-18 11:59:30,940 - train: [ INFO] - Train: 93 [ 150/461 ( 33%)] Loss: 0.670755 (0.6924) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.131s, 244.74/s (0.146s, 218.72/s) LR: 5.000e-04 Data: 0.001 (0.047) +2025-04-18 11:59:37,568 - train: [ INFO] - Train: 93 [ 200/461 ( 43%)] Loss: 0.662527 (0.6864) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.128s, 249.49/s (0.136s, 235.81/s) LR: 5.000e-04 Data: 0.001 (0.035) +2025-04-18 11:59:42,795 - train: [ INFO] - Train: 93 [ 250/461 ( 54%)] Loss: 0.724163 (0.6927) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.113s, 283.66/s (0.128s, 250.51/s) LR: 5.000e-04 Data: 0.001 (0.029) +2025-04-18 11:59:47,790 - train: [ INFO] - Train: 93 [ 300/461 ( 65%)] Loss: 0.667390 (0.6891) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.133s, 239.75/s (0.122s, 261.65/s) LR: 5.000e-04 Data: 0.000 (0.024) +2025-04-18 11:59:53,930 - train: [ INFO] - Train: 93 [ 350/461 ( 76%)] Loss: 0.675465 (0.6874) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 436.43/s (0.120s, 266.14/s) LR: 5.000e-04 Data: 0.001 (0.021) +2025-04-18 12:00:00,587 - train: [ INFO] - Train: 93 [ 400/461 ( 87%)] Loss: 0.693503 (0.6881) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.84/s (0.119s, 268.31/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-18 12:00:07,304 - train: [ INFO] - Train: 93 [ 450/461 ( 98%)] Loss: 0.727989 (0.6920) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 444.05/s (0.118s, 271.96/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 12:00:08,089 - train: [ INFO] - Train: 93 [ 460/461 (100%)] Loss: 0.668900 (0.6899) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 319.67/s (0.117s, 273.97/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 12:00:13,098 - train: [ INFO] - Eval : 93 Time: 4.771 (4.771) Loss: 2.1384 (2.1384) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 12:00:17,891 - train: [ INFO] - Eval : 93 Time: 0.328 (0.188) Loss: 1.8613 (2.0205) Acc@1: 59.3750 (50.5515)Acc@5: 68.7500 (74.8775) +2025-04-18 12:00:23,302 - train: [ INFO] - Eval : 93 Time: 0.020 (0.183) Loss: 3.1467 (2.0181) Acc@1: 0.0000 (50.3470)Acc@5: 0.0000 (75.2120) +2025-04-18 12:00:32,115 - train: [ INFO] - Train: 94 [ 0/461 ( 0%)] Loss: 0.670277 (0.6703) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.416s, 5.91/s (5.416s, 5.91/s) LR: 5.000e-04 Data: 5.298 (5.298) +2025-04-18 12:00:39,209 - train: [ INFO] - Train: 94 [ 50/461 ( 11%)] Loss: 0.673591 (0.6719) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.098s, 328.08/s (0.234s, 136.54/s) LR: 5.000e-04 Data: 0.000 (0.149) +2025-04-18 12:00:46,649 - train: [ INFO] - Train: 94 [ 100/461 ( 22%)] Loss: 0.663158 (0.6690) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.140s, 228.38/s (0.189s, 169.66/s) LR: 5.000e-04 Data: 0.001 (0.099) +2025-04-18 12:00:54,287 - train: [ INFO] - Train: 94 [ 150/461 ( 33%)] Loss: 0.680628 (0.6719) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.360s, 88.78/s (0.175s, 182.79/s) LR: 5.000e-04 Data: 0.265 (0.083) +2025-04-18 12:01:03,247 - train: [ INFO] - Train: 94 [ 200/461 ( 43%)] Loss: 0.664149 (0.6704) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.149s, 215.19/s (0.174s, 183.94/s) LR: 5.000e-04 Data: 0.000 (0.086) +2025-04-18 12:01:11,364 - train: [ INFO] - Train: 94 [ 250/461 ( 54%)] Loss: 0.672142 (0.6707) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 463.05/s (0.170s, 188.78/s) LR: 5.000e-04 Data: 0.000 (0.082) +2025-04-18 12:01:17,119 - train: [ INFO] - Train: 94 [ 300/461 ( 65%)] Loss: 0.663212 (0.6696) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 403.99/s (0.160s, 200.51/s) LR: 5.000e-04 Data: 0.001 (0.069) +2025-04-18 12:01:22,337 - train: [ INFO] - Train: 94 [ 350/461 ( 76%)] Loss: 0.663850 (0.6689) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.104s, 306.75/s (0.151s, 211.92/s) LR: 5.000e-04 Data: 0.001 (0.059) +2025-04-18 12:01:28,915 - train: [ INFO] - Train: 94 [ 400/461 ( 87%)] Loss: 0.673082 (0.6693) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.144s, 222.31/s (0.145s, 220.73/s) LR: 5.000e-04 Data: 0.001 (0.052) +2025-04-18 12:01:35,631 - train: [ INFO] - Train: 94 [ 450/461 ( 98%)] Loss: 0.661244 (0.6685) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 441.70/s (0.140s, 227.93/s) LR: 5.000e-04 Data: 0.000 (0.046) +2025-04-18 12:01:36,331 - train: [ INFO] - Train: 94 [ 460/461 (100%)] Loss: 0.666744 (0.6684) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 464.29/s (0.139s, 230.46/s) LR: 5.000e-04 Data: 0.000 (0.045) +2025-04-18 12:01:40,361 - train: [ INFO] - Eval : 94 Time: 3.573 (3.573) Loss: 2.1068 (2.1068) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 12:01:43,924 - train: [ INFO] - Eval : 94 Time: 0.088 (0.140) Loss: 1.8605 (2.0155) Acc@1: 59.3750 (50.9191)Acc@5: 68.7500 (75.3676) +2025-04-18 12:01:45,458 - train: [ INFO] - Eval : 94 Time: 0.018 (0.106) Loss: 3.0964 (2.0138) Acc@1: 0.0000 (50.5783)Acc@5: 0.0000 (75.2506) +2025-04-18 12:01:52,883 - train: [ INFO] - Train: 95 [ 0/461 ( 0%)] Loss: 0.665220 (0.6652) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.675s, 6.85/s (4.675s, 6.85/s) LR: 5.000e-04 Data: 4.562 (4.562) +2025-04-18 12:01:58,566 - train: [ INFO] - Train: 95 [ 50/461 ( 11%)] Loss: 0.753216 (0.7092) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (98.4375) Time: 0.096s, 334.84/s (0.198s, 161.67/s) LR: 5.000e-04 Data: 0.001 (0.096) +2025-04-18 12:02:03,693 - train: [ INFO] - Train: 95 [ 100/461 ( 22%)] Loss: 0.663666 (0.6940) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.071s, 450.49/s (0.150s, 213.10/s) LR: 5.000e-04 Data: 0.000 (0.049) +2025-04-18 12:02:10,189 - train: [ INFO] - Train: 95 [ 150/461 ( 33%)] Loss: 0.698775 (0.6952) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.099s, 324.84/s (0.133s, 241.34/s) LR: 5.000e-04 Data: 0.001 (0.033) +2025-04-18 12:02:15,351 - train: [ INFO] - Train: 95 [ 200/461 ( 43%)] Loss: 0.673404 (0.6909) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.099s, 322.78/s (0.124s, 257.73/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-18 12:02:20,733 - train: [ INFO] - Train: 95 [ 250/461 ( 54%)] Loss: 0.663135 (0.6862) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.069s, 465.19/s (0.119s, 267.81/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-18 12:02:25,966 - train: [ INFO] - Train: 95 [ 300/461 ( 65%)] Loss: 0.664989 (0.6832) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.076s, 420.27/s (0.116s, 275.16/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 12:02:30,994 - train: [ INFO] - Train: 95 [ 350/461 ( 76%)] Loss: 0.663940 (0.6808) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.070s, 456.69/s (0.113s, 282.20/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 12:02:35,939 - train: [ INFO] - Train: 95 [ 400/461 ( 87%)] Loss: 0.662704 (0.6788) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.073s, 440.08/s (0.111s, 289.41/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-18 12:02:42,067 - train: [ INFO] - Train: 95 [ 450/461 ( 98%)] Loss: 0.661243 (0.6770) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.070s, 453.92/s (0.109s, 294.42/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:02:42,903 - train: [ INFO] - Train: 95 [ 460/461 (100%)] Loss: 0.729779 (0.6818) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.068s, 469.61/s (0.108s, 295.94/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:02:46,738 - train: [ INFO] - Eval : 95 Time: 3.573 (3.573) Loss: 2.1179 (2.1179) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 12:02:49,645 - train: [ INFO] - Eval : 95 Time: 0.024 (0.127) Loss: 1.8580 (2.0224) Acc@1: 59.3750 (50.3676)Acc@5: 75.0000 (75.1225) +2025-04-18 12:02:51,491 - train: [ INFO] - Eval : 95 Time: 0.017 (0.102) Loss: 3.2128 (2.0203) Acc@1: 0.0000 (50.0000)Acc@5: 0.0000 (75.2506) +2025-04-18 12:02:58,944 - train: [ INFO] - Train: 96 [ 0/461 ( 0%)] Loss: 0.695003 (0.6950) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.607s, 6.95/s (4.607s, 6.95/s) LR: 5.000e-04 Data: 4.458 (4.458) +2025-04-18 12:03:04,120 - train: [ INFO] - Train: 96 [ 50/461 ( 11%)] Loss: 0.675579 (0.6853) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.103s, 309.51/s (0.186s, 171.96/s) LR: 5.000e-04 Data: 0.001 (0.088) +2025-04-18 12:03:09,677 - train: [ INFO] - Train: 96 [ 100/461 ( 22%)] Loss: 0.670055 (0.6802) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.085s, 375.74/s (0.146s, 218.94/s) LR: 5.000e-04 Data: 0.000 (0.045) +2025-04-18 12:03:16,056 - train: [ INFO] - Train: 96 [ 150/461 ( 33%)] Loss: 0.689965 (0.6827) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 450.35/s (0.130s, 246.21/s) LR: 5.000e-04 Data: 0.000 (0.031) +2025-04-18 12:03:21,164 - train: [ INFO] - Train: 96 [ 200/461 ( 43%)] Loss: 0.662514 (0.6786) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.110s, 289.93/s (0.122s, 262.36/s) LR: 5.000e-04 Data: 0.001 (0.023) +2025-04-18 12:03:25,919 - train: [ INFO] - Train: 96 [ 250/461 ( 54%)] Loss: 0.694858 (0.6813) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.179s, 178.29/s (0.116s, 276.50/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-18 12:03:31,269 - train: [ INFO] - Train: 96 [ 300/461 ( 65%)] Loss: 0.680786 (0.6813) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.32/s (0.113s, 282.60/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 12:03:36,767 - train: [ INFO] - Train: 96 [ 350/461 ( 76%)] Loss: 0.666402 (0.6794) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.139s, 230.81/s (0.112s, 286.37/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 12:03:41,626 - train: [ INFO] - Train: 96 [ 400/461 ( 87%)] Loss: 0.666760 (0.6780) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.091s, 350.92/s (0.110s, 292.23/s) LR: 5.000e-04 Data: 0.001 (0.012) +2025-04-18 12:03:47,347 - train: [ INFO] - Train: 96 [ 450/461 ( 98%)] Loss: 0.660474 (0.6762) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 459.84/s (0.107s, 299.47/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:03:48,083 - train: [ INFO] - Train: 96 [ 460/461 (100%)] Loss: 0.663142 (0.6750) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 455.15/s (0.106s, 301.57/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:03:52,890 - train: [ INFO] - Eval : 96 Time: 4.532 (4.532) Loss: 2.0835 (2.0835) Acc@1: 56.2500 (56.2500)Acc@5: 75.0000 (75.0000) +2025-04-18 12:03:57,367 - train: [ INFO] - Eval : 96 Time: 0.074 (0.177) Loss: 1.8643 (2.0214) Acc@1: 59.3750 (50.7353)Acc@5: 71.8750 (75.7966) +2025-04-18 12:03:59,241 - train: [ INFO] - Eval : 96 Time: 0.014 (0.133) Loss: 2.9524 (2.0198) Acc@1: 0.0000 (50.5012)Acc@5: 50.0000 (75.5590) +2025-04-18 12:04:09,052 - train: [ INFO] - Train: 97 [ 0/461 ( 0%)] Loss: 0.662470 (0.6625) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.576s, 6.99/s (4.576s, 6.99/s) LR: 5.000e-04 Data: 4.431 (4.431) +2025-04-18 12:04:13,978 - train: [ INFO] - Train: 97 [ 50/461 ( 11%)] Loss: 0.667376 (0.6649) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 346.61/s (0.183s, 174.44/s) LR: 5.000e-04 Data: 0.000 (0.087) +2025-04-18 12:04:20,076 - train: [ INFO] - Train: 97 [ 100/461 ( 22%)] Loss: 0.664482 (0.6648) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 430.99/s (0.147s, 217.74/s) LR: 5.000e-04 Data: 0.000 (0.045) +2025-04-18 12:04:26,323 - train: [ INFO] - Train: 97 [ 150/461 ( 33%)] Loss: 0.678756 (0.6683) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.099s, 323.00/s (0.133s, 240.74/s) LR: 5.000e-04 Data: 0.001 (0.030) +2025-04-18 12:04:31,253 - train: [ INFO] - Train: 97 [ 200/461 ( 43%)] Loss: 0.663245 (0.6673) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 348.96/s (0.122s, 261.71/s) LR: 5.000e-04 Data: 0.001 (0.023) +2025-04-18 12:04:36,662 - train: [ INFO] - Train: 97 [ 250/461 ( 54%)] Loss: 0.667860 (0.6674) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 432.89/s (0.119s, 269.99/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-18 12:04:42,076 - train: [ INFO] - Train: 97 [ 300/461 ( 65%)] Loss: 0.663567 (0.6668) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.102s, 315.05/s (0.116s, 274.93/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-18 12:04:47,491 - train: [ INFO] - Train: 97 [ 350/461 ( 76%)] Loss: 0.662532 (0.6663) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.161s, 199.35/s (0.114s, 280.26/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-18 12:04:53,277 - train: [ INFO] - Train: 97 [ 400/461 ( 87%)] Loss: 0.662155 (0.6658) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.073s, 435.55/s (0.112s, 284.45/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 12:04:59,339 - train: [ INFO] - Train: 97 [ 450/461 ( 98%)] Loss: 0.667428 (0.6660) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 446.40/s (0.110s, 290.82/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:05:00,303 - train: [ INFO] - Train: 97 [ 460/461 (100%)] Loss: 0.663484 (0.6658) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.071s, 452.06/s (0.110s, 291.65/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 12:05:03,795 - train: [ INFO] - Eval : 97 Time: 3.207 (3.207) Loss: 2.1172 (2.1172) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 12:05:06,956 - train: [ INFO] - Eval : 97 Time: 0.047 (0.125) Loss: 1.8709 (2.0265) Acc@1: 59.3750 (50.9191)Acc@5: 71.8750 (74.7549) +2025-04-18 12:05:08,118 - train: [ INFO] - Eval : 97 Time: 0.015 (0.092) Loss: 2.9258 (2.0242) Acc@1: 0.0000 (50.5397)Acc@5: 50.0000 (75.1349) +2025-04-18 12:05:15,077 - train: [ INFO] - Train: 98 [ 0/461 ( 0%)] Loss: 0.671618 (0.6716) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.187s, 7.64/s (4.187s, 7.64/s) LR: 5.000e-04 Data: 4.027 (4.027) +2025-04-18 12:05:21,995 - train: [ INFO] - Train: 98 [ 50/461 ( 11%)] Loss: 0.660422 (0.6660) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 342.19/s (0.191s, 167.98/s) LR: 5.000e-04 Data: 0.000 (0.083) +2025-04-18 12:05:28,411 - train: [ INFO] - Train: 98 [ 100/461 ( 22%)] Loss: 0.664463 (0.6655) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 457.46/s (0.148s, 216.05/s) LR: 5.000e-04 Data: 0.000 (0.043) +2025-04-18 12:05:34,523 - train: [ INFO] - Train: 98 [ 150/461 ( 33%)] Loss: 0.665501 (0.6655) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.176s, 182.02/s (0.137s, 232.82/s) LR: 5.000e-04 Data: 0.001 (0.029) +2025-04-18 12:05:40,038 - train: [ INFO] - Train: 98 [ 200/461 ( 43%)] Loss: 0.666771 (0.6658) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 426.80/s (0.126s, 253.16/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-18 12:05:45,909 - train: [ INFO] - Train: 98 [ 250/461 ( 54%)] Loss: 0.662171 (0.6652) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.141s, 227.71/s (0.121s, 265.30/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-18 12:05:51,836 - train: [ INFO] - Train: 98 [ 300/461 ( 65%)] Loss: 0.662461 (0.6648) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.197s, 162.08/s (0.120s, 267.67/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-18 12:05:57,062 - train: [ INFO] - Train: 98 [ 350/461 ( 76%)] Loss: 0.668915 (0.6653) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.127s, 252.58/s (0.117s, 273.55/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 12:06:01,957 - train: [ INFO] - Train: 98 [ 400/461 ( 87%)] Loss: 0.671098 (0.6659) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.099s, 323.79/s (0.114s, 280.90/s) LR: 5.000e-04 Data: 0.001 (0.011) +2025-04-18 12:06:08,095 - train: [ INFO] - Train: 98 [ 450/461 ( 98%)] Loss: 0.661640 (0.6655) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.069s, 466.44/s (0.112s, 286.77/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 12:06:08,794 - train: [ INFO] - Train: 98 [ 460/461 (100%)] Loss: 0.673856 (0.6663) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.068s, 471.54/s (0.111s, 289.19/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 12:06:13,460 - train: [ INFO] - Eval : 98 Time: 4.378 (4.378) Loss: 2.0918 (2.0918) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 12:06:21,355 - train: [ INFO] - Eval : 98 Time: 0.031 (0.241) Loss: 1.8801 (2.0238) Acc@1: 62.5000 (50.4289)Acc@5: 78.1250 (75.0613) +2025-04-18 12:06:27,231 - train: [ INFO] - Eval : 98 Time: 0.022 (0.221) Loss: 3.0845 (2.0212) Acc@1: 0.0000 (50.0386)Acc@5: 50.0000 (75.1735) +2025-04-18 12:06:34,886 - train: [ INFO] - Train: 99 [ 0/461 ( 0%)] Loss: 0.660796 (0.6608) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.709s, 6.79/s (4.709s, 6.79/s) LR: 5.000e-04 Data: 4.575 (4.575) +2025-04-18 12:06:42,123 - train: [ INFO] - Train: 99 [ 50/461 ( 11%)] Loss: 0.662496 (0.6616) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.124s, 258.79/s (0.215s, 148.92/s) LR: 5.000e-04 Data: 0.000 (0.100) +2025-04-18 12:06:48,315 - train: [ INFO] - Train: 99 [ 100/461 ( 22%)] Loss: 0.662108 (0.6618) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.074s, 432.05/s (0.162s, 197.70/s) LR: 5.000e-04 Data: 0.000 (0.051) +2025-04-18 12:06:53,536 - train: [ INFO] - Train: 99 [ 150/461 ( 33%)] Loss: 0.675923 (0.6653) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.147s, 217.66/s (0.141s, 226.61/s) LR: 5.000e-04 Data: 0.000 (0.034) +2025-04-18 12:07:00,734 - train: [ INFO] - Train: 99 [ 200/461 ( 43%)] Loss: 0.671100 (0.6665) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.108s, 296.21/s (0.132s, 242.84/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-18 12:07:06,749 - train: [ INFO] - Train: 99 [ 250/461 ( 54%)] Loss: 0.702737 (0.6725) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.113s, 283.14/s (0.128s, 249.59/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-18 12:07:12,952 - train: [ INFO] - Train: 99 [ 300/461 ( 65%)] Loss: 0.663913 (0.6713) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.124s, 258.80/s (0.126s, 253.09/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-18 12:07:19,004 - train: [ INFO] - Train: 99 [ 350/461 ( 76%)] Loss: 0.662880 (0.6702) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.15/s (0.125s, 255.81/s) LR: 5.000e-04 Data: 0.001 (0.016) +2025-04-18 12:07:25,108 - train: [ INFO] - Train: 99 [ 400/461 ( 87%)] Loss: 0.660658 (0.6692) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 342.95/s (0.122s, 261.94/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 12:07:32,516 - train: [ INFO] - Train: 99 [ 450/461 ( 98%)] Loss: 0.671157 (0.6694) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.072s, 445.19/s (0.120s, 267.23/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 12:07:33,458 - train: [ INFO] - Train: 99 [ 460/461 (100%)] Loss: 0.667517 (0.6692) Loss_single: 0.000000 (0.0000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.070s, 454.93/s (0.119s, 268.51/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 12:07:38,159 - train: [ INFO] - Eval : 99 Time: 4.312 (4.312) Loss: 2.0953 (2.0953) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 12:07:42,432 - train: [ INFO] - Eval : 99 Time: 0.023 (0.168) Loss: 1.8671 (2.0180) Acc@1: 56.2500 (50.9191)Acc@5: 75.0000 (74.8775) +2025-04-18 12:07:43,727 - train: [ INFO] - Eval : 99 Time: 0.015 (0.121) Loss: 3.1374 (2.0170) Acc@1: 0.0000 (50.5012)Acc@5: 0.0000 (75.0964) +2025-04-18 12:07:46,487 - train: [ INFO] - *** Best metric: 51.58057054741712 (epoch 23) diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/model_best.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/model_best.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..72f5420e6db6d21f40baddbc5f8686c2ed32b54d --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/model_best.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e37a7e4a985649da5c2ee3eb338970317ec8466040e0bc54a23d9d96e94dc97 +size 179373193 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/summary.csv b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/summary.csv new file mode 100644 index 0000000000000000000000000000000000000000..c1fc92690bf3ddc6e9428fe54415515ba64933da --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/summary.csv @@ -0,0 +1,101 @@ +epoch,train_loss,train_loss_single,train_loss_inverse,eval_loss,eval_top1,eval_top1_a,eval_top1_v +0,2.84503173828125,0,0,2.4356729096417804,30.724749421742484,2.158828064764842,2.197378565921357 +1,2.3694887377999048,0,0,2.8122676358189875,28.064764841942946,2.9683885890516577,1.1565150346954511 +2,2.1565536043860694,0,0,2.046155484345847,41.17193523515806,1.6191210485736314,2.5443330763299925 +3,1.9681163050911643,0,0,1.9930287789820522,44.79568234387047,2.5828835774865073,2.8527370855821124 +4,1.95731660452756,0,0,2.1865640749082074,38.858905165767155,1.6191210485736314,3.0454895913646878 +5,1.8815919377587058,0,0,1.935083419245394,44.83423284502698,2.3901310717039324,3.5080956052428682 +6,1.8242558674378828,0,0,2.073585390401236,43.87047031611411,1.6191210485736314,2.6599845797995374 +7,1.6322505257346414,0,0,1.9467310784133287,45.41249036237471,1.5034695451040863,2.428681572860447 +8,1.6926553140987048,0,0,1.8838076499580143,47.417116422513494,1.040863531225906,3.199691595990748 +9,1.541946898807179,0,0,2.1788414941903897,43.06090979182729,1.9660755589822667,3.623747108712413 +10,1.4783494472503662,0,0,1.9968265025727825,46.106399383191984,2.081727062451812,2.9683885890516577 +11,1.4341550306840376,0,0,1.903367721951734,47.10871241326137,2.7370855821125675,4.857363145720894 +12,1.1161095825108616,0,0,2.335887564818677,43.90902081727062,2.235929067077872,3.7779491133384733 +13,1.0882130752910266,0,0,2.07908983017356,46.26060138781804,2.5057825751734772,4.240555127216654 +14,0.9629263390194286,0,0,1.968355684346572,48.49653045489591,2.197378565921357,2.6599845797995374 +15,0.897862434387207,0,0,2.0055829440067616,46.72320740169622,2.6214340786430226,4.009252120277564 +16,0.8452200510285117,0,0,1.9178168904165533,49.92289899768697,1.9275250578257517,2.5443330763299925 +17,0.8071429025043141,0,0,1.9286873154945343,49.03623747108713,2.428681572860447,4.163454124903624 +18,0.8018280701203779,0,0,1.8817640207506825,49.73014649190439,2.5057825751734772,3.9321511179645334 +19,0.7431348508054559,0,0,1.8692893261346986,50.61680801850424,2.4672320740169624,3.9321511179645334 +20,0.7488561055876992,0,0,1.9402227703203305,48.03392444101773,2.3901310717039324,4.2020046260601385 +21,0.7464116595008157,0,0,1.8860773106400748,49.46029298380879,2.6599845797995374,3.276792598303778 +22,0.7589777978983793,0,0,1.8588327532468985,50.809560524286816,2.3901310717039324,3.8550501156515034 +23,0.7375390204516324,0,0,1.834703096905946,51.58057054741712,2.120277563608327,4.279105628373169 +24,0.7235157110474326,0,0,1.8571111029078617,50.84811102544333,2.8141865844255975,4.009252120277564 +25,0.7282718907703053,0,0,1.9045326055337028,50.0,2.158828064764842,3.9321511179645334 +26,0.7249117168513212,0,0,1.934991702173155,48.265227447956825,2.3130300693909023,3.7779491133384733 +27,0.7170815467834473,0,0,1.8986565024464885,50.809560524286816,2.081727062451812,4.124903623747109 +28,0.7267518639564514,0,0,1.9323314469689667,48.99768696993061,3.1611410948342327,3.8164996144949885 +29,0.7307774207808755,0,0,1.907023419576511,50.73245952197379,2.235929067077872,4.471858134155744 +30,0.7234120856631886,0,0,1.8932903774352652,51.00231303006939,2.428681572860447,4.587509637625289 +31,0.7121647054498846,0,0,1.9132159633092358,50.30840400925212,2.4672320740169624,3.7393986121819585 +32,0.717554737221111,0,0,1.8778468887899689,50.11565150346954,2.120277563608327,4.240555127216654 +33,0.7193075039170005,0,0,1.933656499858259,49.42174248265228,2.6599845797995374,4.2020046260601385 +34,0.7088963443582709,0,0,1.917556003505851,50.69390902081727,2.274479568234387,3.9707016191210487 +35,0.7105227329514243,0,0,1.9279127674279253,50.07710100231303,3.0840400925212026,4.587509637625289 +36,0.7185628576712175,0,0,1.9110201952911472,51.349267540478024,1.9660755589822667,3.8164996144949885 +37,0.7170974937352267,0,0,1.892678547934927,50.92521202775636,2.5828835774865073,4.7417116422513494 +38,0.7181021300229159,0,0,1.9402496645610519,49.46029298380879,2.043176561295297,4.2020046260601385 +39,0.7050957517190413,0,0,1.9436388714274904,49.15188897455667,1.9660755589822667,3.8936006168080186 +40,0.7154142260551453,0,0,1.9956428967904567,47.91827293754819,2.235929067077872,3.8550501156515034 +41,0.7271967963738875,0,0,1.9499217061327343,49.190439475713184,1.6962220508866614,4.394757131842714 +42,0.7188805504278704,0,0,1.952874204426797,50.53970701619121,2.081727062451812,4.471858134155744 +43,0.7167698578401045,0,0,1.9593764147394515,49.498843484965306,2.3901310717039324,3.353893600616808 +44,0.7061739997430281,0,0,1.9899023658234796,47.9568234387047,2.043176561295297,3.9707016191210487 +45,0.712029679255052,0,0,1.951217144934508,49.73014649190439,2.081727062451812,4.009252120277564 +46,0.7068618535995483,0,0,1.9516625058770456,48.4579799537394,2.3901310717039324,4.356206630686199 +47,0.7123134515502236,0,0,1.9463807610061046,50.11565150346954,2.004626060138782,3.700848111025443 +48,0.7261221300471913,0,0,1.9640198419345922,50.19275250578257,2.428681572860447,4.394757131842714 +49,0.7144224047660828,0,0,1.9756056315731616,49.42174248265228,2.5443330763299925,4.973014649190439 +50,0.7240266691554677,0,0,2.002313643854769,47.686969930609095,2.351580570547417,4.703161141094834 +51,0.7079346559264443,0,0,2.0168485358391894,49.07478797224364,3.0069390902081725,4.433307632999229 +52,0.704542029987682,0,0,1.9849119728679554,48.920585967617576,2.4672320740169624,4.009252120277564 +53,0.7049224972724915,0,0,1.9769741869377189,49.07478797224364,1.6962220508866614,5.088666152659985 +54,0.7113959301601757,0,0,1.972036603605554,49.61449498843485,1.9660755589822667,4.356206630686199 +55,0.7194026925347068,0,0,1.929792857114958,50.26985350809561,2.120277563608327,4.086353122590594 +56,0.7168085791847922,0,0,1.9944675268351157,48.88203546646106,3.0454895913646878,4.086353122590594 +57,0.7093271558934992,0,0,1.9509136568332692,49.113338473400155,2.197378565921357,3.8936006168080186 +58,0.7040835293856534,0,0,2.0025861290848614,47.14726291441789,2.274479568234387,4.124903623747109 +59,0.70566542040218,0,0,1.9888466498258028,49.15188897455667,2.8912875867386276,5.05011565150347 +60,0.7014055577191439,0,0,1.952616757030384,49.03623747108713,2.235929067077872,3.9321511179645334 +61,0.7207257043231617,0,0,1.9701330084569104,49.38319198149576,2.004626060138782,4.086353122590594 +62,0.7087216160514138,0,0,1.978608385084589,49.2289899768697,2.7370855821125675,4.587509637625289 +63,0.7110950459133495,0,0,1.9746223124707765,49.03623747108713,2.197378565921357,4.973014649190439 +64,0.7021869150075045,0,0,2.028183111523148,47.45566692367001,3.392444101773323,3.5851966075558983 +65,0.7081769650632684,0,0,2.0330357338339895,46.80030840400925,2.8527370855821124,3.8936006168080186 +66,0.7077403393658724,0,0,2.028001334544044,47.1858134155744,3.0454895913646878,4.471858134155744 +67,0.7116573615507646,0,0,1.995275044128724,49.07478797224364,2.5057825751734772,4.086353122590594 +68,0.6999574357813055,0,0,1.9978079214956361,48.188126445643796,2.5057825751734772,3.430994602929838 +69,0.7015819224444303,0,0,2.0715577633636406,46.22205088666153,3.0454895913646878,3.0454895913646878 +70,0.6959977637637745,0,0,1.9542799288250432,50.038550501156514,2.5057825751734772,3.8936006168080186 +71,0.6889803409576416,0,0,1.9396044842169298,50.65535851966076,2.3130300693909023,3.7393986121819585 +72,0.6849353584376249,0,0,1.9520756356423876,50.69390902081727,2.428681572860447,4.009252120277564 +73,0.6939813657240435,0,0,1.958347300336098,50.73245952197379,2.698535080956052,4.163454124903624 +74,0.6781938997181979,0,0,1.9602921382224643,50.809560524286816,2.428681572860447,3.9707016191210487 +75,0.6772383343089711,0,0,1.96580110077869,50.69390902081727,2.7370855821125675,4.510408635312259 +76,0.6841544996608387,0,0,1.9617228759833272,50.38550501156515,2.5828835774865073,4.2020046260601385 +77,0.672706739469008,0,0,1.9716180815729805,50.886661526599845,2.5828835774865073,4.317656129529684 +78,0.67627506906336,0,0,1.9800843243977613,50.96376252891287,2.6214340786430226,3.9707016191210487 +79,0.6769991787997159,0,0,1.981784750152388,50.57825751734772,2.7370855821125675,4.009252120277564 +80,0.6697457270188765,0,0,1.9825532362841605,51.11796453353894,2.7756360832690823,4.124903623747109 +81,0.6728830500082537,0,0,1.98822685545375,50.38550501156515,2.5057825751734772,4.163454124903624 +82,0.6793067888780073,0,0,1.9885198796080366,50.96376252891287,2.5828835774865073,4.433307632999229 +83,0.6716876246712424,0,0,1.9963799706770073,51.19506553585197,2.698535080956052,4.587509637625289 +84,0.6683548255400225,0,0,1.998742670303321,50.84811102544333,2.698535080956052,4.2020046260601385 +85,0.670335666699843,0,0,1.9908146990567974,50.69390902081727,2.7370855821125675,4.317656129529684 +86,0.669741234996102,0,0,2.0019844271351763,50.53970701619121,2.3901310717039324,4.356206630686199 +87,0.6702776442874562,0,0,1.999634550457839,50.424055512721665,2.5443330763299925,4.047802621434078 +88,0.673119458285245,0,0,2.0064249389798436,50.38550501156515,2.6214340786430226,4.2020046260601385 +89,0.6788747256452387,0,0,2.0116112706471885,50.26985350809561,2.5828835774865073,4.279105628373169 +90,0.6745892329649492,0,0,2.00881067605412,50.34695451040864,2.5828835774865073,4.394757131842714 +91,0.6717266494577582,0,0,2.0071605238991697,50.53970701619121,2.8527370855821124,4.279105628373169 +92,0.668257393620231,0,0,2.0048912540250496,50.26985350809561,2.7756360832690823,4.317656129529684 +93,0.6899418993429705,0,0,2.0180595345743453,50.34695451040864,2.5057825751734772,4.471858134155744 +94,0.6683707724918019,0,0,2.013797598061602,50.57825751734772,2.7370855821125675,4.240555127216654 +95,0.6818247220732949,0,0,2.020260846881381,50.0,2.698535080956052,4.356206630686199 +96,0.675048903985457,0,0,2.019830103736707,50.501156515034694,2.9298380878951424,4.356206630686199 +97,0.665759574283253,0,0,2.024168534010488,50.53970701619121,2.8527370855821124,4.587509637625289 +98,0.6662651246244257,0,0,2.0211983741754374,50.038550501156514,2.4672320740169624,3.9707016191210487 +99,0.6692075783556158,0,0,2.017012972600109,50.501156515034694,2.5828835774865073,4.510408635312259 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/args.yaml b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/args.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d8941b325763ed832983b19a6cc0641a65ad28da --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/args.yaml @@ -0,0 +1,162 @@ +aa: rand-m9-mstd0.5-inc1 +act_fun: QGateGrad +adam_epoch: 1000 +adaptation_info: false +adaptive_node: false +alpha: 0.8 +amp: false +apex_amp: false +audio_path: /mnt/home/hexiang/datasets/CREMA-D/AudioWAV/ +aug_splits: 0 +batch_size: 32 +bn_eps: null +bn_momentum: null +bn_tf: false +channels_last: false +clip_grad: null +color_jitter: 0.4 +conf_mat: false +conv_type: normal +cooldown_epochs: 10 +critical_loss: false +crop_pct: null +cut_mix: false +cutmix: 0.0 +cutmix_beta: 2.0 +cutmix_minmax: null +cutmix_noise: 0.0 +cutmix_num: 1 +cutmix_prob: 0.5 +dataset: KineticSound +decay_epochs: 70 +decay_rate: 0.1 +device: 0 +dist_bn: '' +drop: 0.0 +drop_block: null +drop_connect: null +drop_path: 0.1 +encode: direct +epochs: 100 +eval: false +eval_checkpoint: '' +eval_metric: top1 +event_mix: false +event_size: 48 +fps: 1 +fusion_method: concat +gaussian_n: 3 +gp: null +hflip: 0.5 +img_size: 224 +initial_checkpoint: '' +interpolation: '' +inverse: true +inverse_ends: 100 +inverse_starts: 0 +jsd: false +kernel_method: cuda +layer_by_layer: false +local_rank: 0 +log_interval: 50 +loss_fn: ce +lr: 0.005 +lr_cycle_limit: 1 +lr_cycle_mul: 1.0 +lr_noise: null +lr_noise_pct: 0.67 +lr_noise_std: 1.0 +mean: null +mem_dist: false +meta_ratio: -1.0 +min_lr: 1.0e-05 +mix_up: false +mixup: 0.0 +mixup_mode: batch +mixup_off_epoch: 0 +mixup_prob: 0.0 +mixup_switch_prob: 0.5 +modality: audio-visual +model: AVresnet18 +model_ema: false +model_ema_decay: 0.99996 +model_ema_force_cpu: false +modulation: Normal +modulation_ends: 50 +modulation_starts: 0 +momentum: 0.9 +n_encode_type: linear +n_groups: 1 +n_preact: false +native_amp: false +newton_maxiter: 20 +no_aug: false +no_prefetcher: false +no_resume_opt: false +node_resume: '' +node_type: LIFNode +noisy_grad: 0.0 +num_classes: 31 +num_gpu: 1 +opt: sgd +opt_betas: null +opt_eps: 1.0e-08 +output: ./exp_results +patience_epochs: 10 +pin_mem: false +power: 1 +pretrained: false +psai: 1.0 +rand_aug: false +rand_step: false +randaug_m: 15 +randaug_n: 3 +ratio: +- 0.75 +- 1.3333333333333333 +recount: 1 +recovery_interval: 0 +remode: pixel +reprob: 0.25 +requires_thres_grad: false +reset_drop: false +resplit: false +resume: '' +save_images: false +scale: +- 0.08 +- 1.0 +sched: step +seed: 2025 +sew_cnf: ADD +sigmoid_thres: false +smoothing: 0.1 +snr: -100 +snrModality: null +spike_output: false +spike_rate: false +split_bn: false +start_epoch: null +std: null +step: 4 +suffix: '' +sync_bn: false +tau: 2.0 +temporal_flatten: false +tensorboard_dir: ./exp_results +tet_loss: false +threshold: 0.5 +train_interpolation: random +train_portion: 0.9 +tsne: false +tta: 0 +use_multi_epochs_loader: false +use_video_frames: 3 +validation_batch_size_multiplier: 1 +vflip: 0.0 +visual_path: /mnt/home/hexiang/datasets/CREMA-D/ +visualize: false +warmup_epochs: 0 +warmup_lr: 1.0e-06 +weight_decay: 0.0005 +workers: 8 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-72.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-72.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..c340612837f697fbedfeb654bc84f41d0236562a --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-72.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24cb3180593213d5da34e5e4db609b0c7173396a1cd9ac9253be42749e72c26f +size 179501441 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/events.out.tfevents.1745049404.af1fd63cd999.1304306.0 b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/events.out.tfevents.1745049404.af1fd63cd999.1304306.0 new file mode 100644 index 0000000000000000000000000000000000000000..038b3e49da88094b6a6168089bd966fd80148034 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/events.out.tfevents.1745049404.af1fd63cd999.1304306.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc68609d01e486ef2c2d5a0276d80dfa89005df0b8683a02b0110bec6cbd03a2 +size 12954544 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/last.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/last.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..d02d5863546d76355204eb15eb4589e4bae0a469 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/last.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c3ceb72e9051580964cbb79bdf78153beaab8c57ef343e6be17867888eeccd +size 179501441 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/log.txt b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..f5c3f2bb7cff690c78c3865f4d9df72d779c99d8 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/log.txt @@ -0,0 +1,1434 @@ +2025-04-19 07:56:44,445 - train: [ INFO] - Training with a single process on 1 GPUs. +2025-04-19 07:56:49,566 - train: [ INFO] - AMP not enabled. Training in float32. +2025-04-19 07:56:49,569 - train: [ INFO] - Scheduled epochs: 100 +2025-04-19 07:57:04,255 - train: [ INFO] - Train: 0 [ 0/461 ( 0%)] Loss: 10.719982 (10.7200) Loss_single: 7.072478 (7.0725) Loss_inverse: 0.000000 (0.0000) Acc@1: 3.1250 ( 3.1250) Acc@5: 18.7500 (18.7500) Time: 14.670s, 2.18/s (14.670s, 2.18/s) LR: 5.000e-03 Data: 8.058 (8.058) +2025-04-19 07:57:23,503 - train: [ INFO] - Train: 0 [ 50/461 ( 11%)] Loss: 10.451446 (10.5857) Loss_single: 7.021874 (7.0472) Loss_inverse: 0.000000 (0.0000) Acc@1: 9.3750 ( 6.2500) Acc@5: 25.0000 (21.8750) Time: 0.568s, 56.32/s (0.664s, 48.20/s) LR: 5.000e-03 Data: 0.001 (0.159) +2025-04-19 07:57:42,938 - train: [ INFO] - Train: 0 [ 100/461 ( 22%)] Loss: 8.846096 (10.0058) Loss_single: 6.089304 (6.7279) Loss_inverse: 0.000000 (0.0000) Acc@1: 21.8750 (11.4583) Acc@5: 56.2500 (33.3333) Time: 0.359s, 89.07/s (0.527s, 60.70/s) LR: 5.000e-03 Data: 0.000 (0.081) +2025-04-19 07:58:02,798 - train: [ INFO] - Train: 0 [ 150/461 ( 33%)] Loss: 8.686634 (9.6760) Loss_single: 5.960189 (6.5360) Loss_inverse: 0.000000 (0.0000) Acc@1: 12.5000 (11.7188) Acc@5: 71.8750 (42.9688) Time: 0.343s, 93.37/s (0.484s, 66.18/s) LR: 5.000e-03 Data: 0.001 (0.055) +2025-04-19 07:58:20,808 - train: [ INFO] - Train: 0 [ 200/461 ( 43%)] Loss: 8.000007 (9.3408) Loss_single: 5.559431 (6.3407) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (17.5000) Acc@5: 75.0000 (49.3750) Time: 0.328s, 97.51/s (0.453s, 70.69/s) LR: 5.000e-03 Data: 0.000 (0.041) +2025-04-19 07:58:40,021 - train: [ INFO] - Train: 0 [ 250/461 ( 54%)] Loss: 8.469296 (9.1956) Loss_single: 5.957966 (6.2769) Loss_inverse: 0.000000 (0.0000) Acc@1: 31.2500 (19.7917) Acc@5: 75.0000 (53.6458) Time: 0.389s, 82.32/s (0.439s, 72.93/s) LR: 5.000e-03 Data: 0.001 (0.033) +2025-04-19 07:58:58,141 - train: [ INFO] - Train: 0 [ 300/461 ( 65%)] Loss: 8.358480 (9.0760) Loss_single: 5.757479 (6.2027) Loss_inverse: 0.000000 (0.0000) Acc@1: 28.1250 (20.9821) Acc@5: 65.6250 (55.3571) Time: 0.387s, 82.65/s (0.426s, 75.12/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-19 07:59:17,375 - train: [ INFO] - Train: 0 [ 350/461 ( 76%)] Loss: 8.706526 (9.0298) Loss_single: 5.981093 (6.1750) Loss_inverse: 0.000000 (0.0000) Acc@1: 28.1250 (21.8750) Acc@5: 62.5000 (56.2500) Time: 0.398s, 80.38/s (0.420s, 76.20/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 07:59:36,047 - train: [ INFO] - Train: 0 [ 400/461 ( 87%)] Loss: 8.928093 (9.0185) Loss_single: 6.069478 (6.1633) Loss_inverse: 0.000000 (0.0000) Acc@1: 21.8750 (21.8750) Acc@5: 59.3750 (56.5972) Time: 0.389s, 82.19/s (0.414s, 77.29/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 07:59:54,808 - train: [ INFO] - Train: 0 [ 450/461 ( 98%)] Loss: 8.570549 (8.9737) Loss_single: 5.881741 (6.1351) Loss_inverse: 0.000000 (0.0000) Acc@1: 25.0000 (22.1875) Acc@5: 65.6250 (57.5000) Time: 0.353s, 90.60/s (0.410s, 78.12/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 07:59:58,388 - train: [ INFO] - Train: 0 [ 460/461 (100%)] Loss: 8.310534 (8.9134) Loss_single: 5.748505 (6.1000) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (23.5795) Acc@5: 75.0000 (59.0909) Time: 0.336s, 95.34/s (0.408s, 78.35/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 08:00:04,765 - train: [ INFO] - Eval : 0 Time: 6.175 (6.175) Loss: 2.1978 (2.1978) Acc@1: 28.1250 (28.1250)Acc@5: 71.8750 (71.8750) +2025-04-19 08:00:16,438 - train: [ INFO] - Eval : 0 Time: 0.194 (0.351) Loss: 2.4398 (2.4123) Acc@1: 31.2500 (31.3113)Acc@5: 65.6250 (68.3211) +2025-04-19 08:00:23,785 - train: [ INFO] - Eval : 0 Time: 0.080 (0.308) Loss: 5.8908 (2.4186) Acc@1: 0.0000 (30.1465)Acc@5: 0.0000 (68.5428) +2025-04-19 08:00:34,378 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-0.pth.tar', 30.146491904394757) + +2025-04-19 08:00:40,061 - train: [ INFO] - Train: 1 [ 0/461 ( 0%)] Loss: 7.866621 (7.8666) Loss_single: 5.466396 (5.4664) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (37.5000) Acc@5: 71.8750 (71.8750) Time: 5.676s, 5.64/s (5.676s, 5.64/s) LR: 5.000e-03 Data: 5.092 (5.092) +2025-04-19 08:00:59,469 - train: [ INFO] - Train: 1 [ 50/461 ( 11%)] Loss: 8.753582 (8.3101) Loss_single: 6.025619 (5.7460) Loss_inverse: 0.000000 (0.0000) Acc@1: 31.2500 (34.3750) Acc@5: 65.6250 (68.7500) Time: 0.334s, 95.82/s (0.491s, 65.17/s) LR: 5.000e-03 Data: 0.001 (0.101) +2025-04-19 08:01:18,311 - train: [ INFO] - Train: 1 [ 100/461 ( 22%)] Loss: 7.773320 (8.1312) Loss_single: 5.396411 (5.6295) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (34.3750) Acc@5: 71.8750 (69.7917) Time: 0.409s, 78.30/s (0.434s, 73.73/s) LR: 5.000e-03 Data: 0.000 (0.052) +2025-04-19 08:01:36,998 - train: [ INFO] - Train: 1 [ 150/461 ( 33%)] Loss: 7.581175 (7.9937) Loss_single: 5.317683 (5.5515) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (35.9375) Acc@5: 78.1250 (71.8750) Time: 0.382s, 83.76/s (0.413s, 77.44/s) LR: 5.000e-03 Data: 0.001 (0.035) +2025-04-19 08:01:55,513 - train: [ INFO] - Train: 1 [ 200/461 ( 43%)] Loss: 7.426833 (7.8803) Loss_single: 5.243427 (5.4899) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (40.0000) Acc@5: 78.1250 (73.1250) Time: 0.396s, 80.79/s (0.402s, 79.53/s) LR: 5.000e-03 Data: 0.001 (0.026) +2025-04-19 08:02:13,881 - train: [ INFO] - Train: 1 [ 250/461 ( 54%)] Loss: 8.278015 (7.9466) Loss_single: 5.875004 (5.5541) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (40.6250) Acc@5: 68.7500 (72.3958) Time: 0.356s, 89.88/s (0.395s, 80.96/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 08:02:33,009 - train: [ INFO] - Train: 1 [ 300/461 ( 65%)] Loss: 7.952097 (7.9474) Loss_single: 5.559088 (5.5548) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (40.1786) Acc@5: 71.8750 (72.3214) Time: 0.486s, 65.88/s (0.393s, 81.43/s) LR: 5.000e-03 Data: 0.021 (0.018) +2025-04-19 08:02:51,813 - train: [ INFO] - Train: 1 [ 350/461 ( 76%)] Loss: 8.031414 (7.9579) Loss_single: 5.650450 (5.5668) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (40.2344) Acc@5: 75.0000 (72.6562) Time: 0.473s, 67.68/s (0.390s, 81.97/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 08:03:10,709 - train: [ INFO] - Train: 1 [ 400/461 ( 87%)] Loss: 8.381430 (8.0049) Loss_single: 5.955511 (5.6100) Loss_inverse: 0.000000 (0.0000) Acc@1: 31.2500 (39.2361) Acc@5: 71.8750 (72.5694) Time: 0.385s, 83.11/s (0.389s, 82.32/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 08:03:29,761 - train: [ INFO] - Train: 1 [ 450/461 ( 98%)] Loss: 8.106713 (8.0151) Loss_single: 5.547165 (5.6037) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (38.7500) Acc@5: 71.8750 (72.5000) Time: 0.397s, 80.70/s (0.388s, 82.54/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:03:33,384 - train: [ INFO] - Train: 1 [ 460/461 (100%)] Loss: 7.366877 (7.9562) Loss_single: 5.253183 (5.5718) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (39.4886) Acc@5: 75.0000 (72.7273) Time: 0.338s, 94.66/s (0.387s, 82.66/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:03:38,436 - train: [ INFO] - Eval : 1 Time: 4.690 (4.690) Loss: 2.4019 (2.4019) Acc@1: 34.3750 (34.3750)Acc@5: 75.0000 (75.0000) +2025-04-19 08:03:48,603 - train: [ INFO] - Eval : 1 Time: 0.161 (0.291) Loss: 2.3343 (2.2664) Acc@1: 40.6250 (37.1936)Acc@5: 62.5000 (69.9755) +2025-04-19 08:03:55,977 - train: [ INFO] - Eval : 1 Time: 0.053 (0.271) Loss: 5.7585 (2.2643) Acc@1: 0.0000 (37.3940)Acc@5: 0.0000 (70.1234) +2025-04-19 08:04:01,603 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-1.pth.tar', 37.39398612181958) + +2025-04-19 08:04:06,718 - train: [ INFO] - Train: 2 [ 0/461 ( 0%)] Loss: 7.181263 (7.1813) Loss_single: 5.053956 (5.0540) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (46.8750) Acc@5: 78.1250 (78.1250) Time: 5.079s, 6.30/s (5.079s, 6.30/s) LR: 5.000e-03 Data: 4.572 (4.572) +2025-04-19 08:04:25,586 - train: [ INFO] - Train: 2 [ 50/461 ( 11%)] Loss: 7.785999 (7.4836) Loss_single: 5.351480 (5.2027) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (40.6250) Acc@5: 75.0000 (76.5625) Time: 0.403s, 79.43/s (0.468s, 68.36/s) LR: 5.000e-03 Data: 0.000 (0.090) +2025-04-19 08:04:44,214 - train: [ INFO] - Train: 2 [ 100/461 ( 22%)] Loss: 7.293941 (7.4204) Loss_single: 5.168364 (5.1913) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (42.7083) Acc@5: 78.1250 (77.0833) Time: 0.357s, 89.64/s (0.420s, 76.11/s) LR: 5.000e-03 Data: 0.001 (0.046) +2025-04-19 08:05:02,786 - train: [ INFO] - Train: 2 [ 150/461 ( 33%)] Loss: 7.172987 (7.3585) Loss_single: 5.048332 (5.1555) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (43.7500) Acc@5: 75.0000 (76.5625) Time: 0.361s, 88.64/s (0.404s, 79.26/s) LR: 5.000e-03 Data: 0.001 (0.031) +2025-04-19 08:05:21,492 - train: [ INFO] - Train: 2 [ 200/461 ( 43%)] Loss: 7.348809 (7.3566) Loss_single: 5.220036 (5.1684) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (44.3750) Acc@5: 84.3750 (78.1250) Time: 0.361s, 88.69/s (0.396s, 80.78/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-19 08:05:40,243 - train: [ INFO] - Train: 2 [ 250/461 ( 54%)] Loss: 7.091031 (7.3123) Loss_single: 4.989704 (5.1386) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (43.7500) Acc@5: 81.2500 (78.6458) Time: 0.349s, 91.67/s (0.392s, 81.69/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 08:05:58,627 - train: [ INFO] - Train: 2 [ 300/461 ( 65%)] Loss: 8.029327 (7.4148) Loss_single: 5.653460 (5.2122) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (43.7500) Acc@5: 68.7500 (77.2321) Time: 0.367s, 87.23/s (0.388s, 82.56/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 08:06:17,671 - train: [ INFO] - Train: 2 [ 350/461 ( 76%)] Loss: 7.567821 (7.4339) Loss_single: 5.404396 (5.2362) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (42.9688) Acc@5: 84.3750 (78.1250) Time: 0.361s, 88.71/s (0.387s, 82.79/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 08:06:35,961 - train: [ INFO] - Train: 2 [ 400/461 ( 87%)] Loss: 7.060091 (7.3924) Loss_single: 4.972791 (5.2069) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (43.7500) Acc@5: 81.2500 (78.4722) Time: 0.426s, 75.06/s (0.384s, 83.39/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 08:06:54,086 - train: [ INFO] - Train: 2 [ 450/461 ( 98%)] Loss: 7.463734 (7.3995) Loss_single: 5.282918 (5.2145) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (43.7500) Acc@5: 84.3750 (79.0625) Time: 0.377s, 84.80/s (0.381s, 83.92/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 08:06:57,725 - train: [ INFO] - Train: 2 [ 460/461 (100%)] Loss: 7.700020 (7.4268) Loss_single: 5.364532 (5.2282) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (42.8977) Acc@5: 75.0000 (78.6932) Time: 0.330s, 97.07/s (0.381s, 84.01/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 08:07:03,398 - train: [ INFO] - Eval : 2 Time: 5.403 (5.403) Loss: 1.8477 (1.8477) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-19 08:07:14,890 - train: [ INFO] - Eval : 2 Time: 0.228 (0.331) Loss: 2.1688 (1.8963) Acc@1: 43.7500 (46.0784)Acc@5: 71.8750 (78.3701) +2025-04-19 08:07:21,219 - train: [ INFO] - Eval : 2 Time: 0.132 (0.281) Loss: 4.3711 (1.8896) Acc@1: 0.0000 (45.9907)Acc@5: 0.0000 (77.7564) +2025-04-19 08:07:25,082 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-2.pth.tar', 45.990747879722434) + +2025-04-19 08:07:29,856 - train: [ INFO] - Train: 3 [ 0/461 ( 0%)] Loss: 7.127790 (7.1278) Loss_single: 5.054474 (5.0545) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (43.7500) Acc@5: 84.3750 (84.3750) Time: 4.739s, 6.75/s (4.739s, 6.75/s) LR: 5.000e-03 Data: 4.062 (4.062) +2025-04-19 08:07:48,775 - train: [ INFO] - Train: 3 [ 50/461 ( 11%)] Loss: 6.569774 (6.8488) Loss_single: 4.757565 (4.9060) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (51.5625) Acc@5: 84.3750 (84.3750) Time: 0.344s, 93.09/s (0.461s, 69.42/s) LR: 5.000e-03 Data: 0.000 (0.081) +2025-04-19 08:08:06,579 - train: [ INFO] - Train: 3 [ 100/461 ( 22%)] Loss: 7.153086 (6.9502) Loss_single: 5.102788 (4.9716) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (51.0417) Acc@5: 75.0000 (81.2500) Time: 0.385s, 83.10/s (0.409s, 78.30/s) LR: 5.000e-03 Data: 0.001 (0.041) +2025-04-19 08:08:24,803 - train: [ INFO] - Train: 3 [ 150/461 ( 33%)] Loss: 6.735910 (6.8966) Loss_single: 4.871657 (4.9466) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (52.3438) Acc@5: 87.5000 (82.8125) Time: 0.389s, 82.26/s (0.394s, 81.25/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-19 08:08:42,830 - train: [ INFO] - Train: 3 [ 200/461 ( 43%)] Loss: 7.518188 (7.0209) Loss_single: 5.355463 (5.0284) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (51.2500) Acc@5: 81.2500 (82.5000) Time: 0.357s, 89.61/s (0.385s, 83.14/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 08:09:01,384 - train: [ INFO] - Train: 3 [ 250/461 ( 54%)] Loss: 6.941197 (7.0077) Loss_single: 4.959711 (5.0169) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (51.5625) Acc@5: 81.2500 (82.2917) Time: 0.334s, 95.95/s (0.382s, 83.78/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 08:09:19,905 - train: [ INFO] - Train: 3 [ 300/461 ( 65%)] Loss: 6.633842 (6.9543) Loss_single: 4.754072 (4.9794) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (51.7857) Acc@5: 81.2500 (82.1429) Time: 0.418s, 76.59/s (0.380s, 84.23/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 08:09:38,151 - train: [ INFO] - Train: 3 [ 350/461 ( 76%)] Loss: 6.102460 (6.8478) Loss_single: 4.493861 (4.9187) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (53.9062) Acc@5: 100.0000 (84.3750) Time: 0.403s, 79.38/s (0.378s, 84.73/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:09:56,013 - train: [ INFO] - Train: 3 [ 400/461 ( 87%)] Loss: 6.709568 (6.8324) Loss_single: 4.892616 (4.9158) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (53.8194) Acc@5: 84.3750 (84.3750) Time: 0.355s, 90.12/s (0.375s, 85.32/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 08:10:14,201 - train: [ INFO] - Train: 3 [ 450/461 ( 98%)] Loss: 7.570635 (6.9062) Loss_single: 5.300397 (4.9543) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (53.7500) Acc@5: 81.2500 (84.0625) Time: 0.367s, 87.31/s (0.374s, 85.65/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 08:10:17,645 - train: [ INFO] - Train: 3 [ 460/461 (100%)] Loss: 6.795628 (6.8962) Loss_single: 4.815098 (4.9416) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (54.5455) Acc@5: 78.1250 (83.5227) Time: 0.344s, 92.96/s (0.373s, 85.80/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 08:10:22,618 - train: [ INFO] - Eval : 3 Time: 4.649 (4.649) Loss: 1.9013 (1.9013) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-19 08:10:33,345 - train: [ INFO] - Eval : 3 Time: 0.170 (0.301) Loss: 1.7744 (1.9846) Acc@1: 46.8750 (42.4632)Acc@5: 78.1250 (75.6127) +2025-04-19 08:10:38,352 - train: [ INFO] - Eval : 3 Time: 0.051 (0.249) Loss: 4.3041 (1.9686) Acc@1: 0.0000 (43.0224)Acc@5: 0.0000 (75.6746) +2025-04-19 08:10:48,478 - train: [ INFO] - Train: 4 [ 0/461 ( 0%)] Loss: 5.916966 (5.9170) Loss_single: 4.285030 (4.2850) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (62.5000) Acc@5: 96.8750 (96.8750) Time: 5.139s, 6.23/s (5.139s, 6.23/s) LR: 5.000e-03 Data: 4.697 (4.697) +2025-04-19 08:11:06,361 - train: [ INFO] - Train: 4 [ 50/461 ( 11%)] Loss: 6.925436 (6.4212) Loss_single: 4.991133 (4.6381) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (57.8125) Acc@5: 93.7500 (95.3125) Time: 0.335s, 95.59/s (0.450s, 71.07/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-19 08:11:24,217 - train: [ INFO] - Train: 4 [ 100/461 ( 22%)] Loss: 6.599423 (6.4806) Loss_single: 4.741153 (4.6724) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (57.2917) Acc@5: 87.5000 (92.7083) Time: 0.356s, 90.00/s (0.403s, 79.31/s) LR: 5.000e-03 Data: 0.001 (0.047) +2025-04-19 08:11:42,356 - train: [ INFO] - Train: 4 [ 150/461 ( 33%)] Loss: 7.429860 (6.7179) Loss_single: 5.278492 (4.8240) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (55.4688) Acc@5: 84.3750 (90.6250) Time: 0.396s, 80.74/s (0.390s, 82.13/s) LR: 5.000e-03 Data: 0.001 (0.032) +2025-04-19 08:12:00,023 - train: [ INFO] - Train: 4 [ 200/461 ( 43%)] Loss: 7.481979 (6.8707) Loss_single: 5.245630 (4.9083) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (52.5000) Acc@5: 78.1250 (88.1250) Time: 0.364s, 87.84/s (0.380s, 84.12/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 08:12:18,318 - train: [ INFO] - Train: 4 [ 250/461 ( 54%)] Loss: 7.577086 (6.9885) Loss_single: 5.361179 (4.9838) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (52.6042) Acc@5: 75.0000 (85.9375) Time: 0.405s, 78.97/s (0.377s, 84.80/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 08:12:36,789 - train: [ INFO] - Train: 4 [ 300/461 ( 65%)] Loss: 6.821375 (6.9646) Loss_single: 4.898232 (4.9715) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (51.7857) Acc@5: 87.5000 (86.1607) Time: 0.385s, 83.18/s (0.376s, 85.15/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 08:12:55,013 - train: [ INFO] - Train: 4 [ 350/461 ( 76%)] Loss: 6.886101 (6.9548) Loss_single: 4.826712 (4.9534) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (51.1719) Acc@5: 81.2500 (85.5469) Time: 0.329s, 97.33/s (0.374s, 85.54/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 08:13:13,032 - train: [ INFO] - Train: 4 [ 400/461 ( 87%)] Loss: 6.815664 (6.9393) Loss_single: 4.873544 (4.9446) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (52.4306) Acc@5: 78.1250 (84.7222) Time: 0.360s, 88.97/s (0.372s, 85.96/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 08:15:10,272 - train: [ INFO] - Train: 4 [ 450/461 ( 98%)] Loss: 6.901834 (6.9356) Loss_single: 4.902820 (4.9404) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (52.1875) Acc@5: 81.2500 (84.3750) Time: 0.326s, 98.30/s (0.370s, 86.58/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 08:15:13,597 - train: [ INFO] - Train: 4 [ 460/461 (100%)] Loss: 6.190779 (6.8679) Loss_single: 4.499420 (4.9003) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (53.6932) Acc@5: 90.6250 (84.9432) Time: 0.317s, 101.01/s (0.369s, 86.77/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 08:15:18,525 - train: [ INFO] - Eval : 4 Time: 4.693 (4.693) Loss: 2.0000 (2.0000) Acc@1: 46.8750 (46.8750)Acc@5: 81.2500 (81.2500) +2025-04-19 08:15:28,953 - train: [ INFO] - Eval : 4 Time: 0.186 (0.297) Loss: 2.0938 (1.9335) Acc@1: 50.0000 (46.6299)Acc@5: 78.1250 (78.3701) +2025-04-19 08:15:34,593 - train: [ INFO] - Eval : 4 Time: 0.048 (0.253) Loss: 3.3410 (1.9175) Acc@1: 0.0000 (46.8003)Acc@5: 50.0000 (78.3732) +2025-04-19 08:15:39,634 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-4.pth.tar', 46.80030840400925) + +2025-04-19 08:15:43,904 - train: [ INFO] - Train: 5 [ 0/461 ( 0%)] Loss: 7.130038 (7.1300) Loss_single: 5.011151 (5.0112) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (53.1250) Acc@5: 78.1250 (78.1250) Time: 4.242s, 7.54/s (4.242s, 7.54/s) LR: 5.000e-03 Data: 3.710 (3.710) +2025-04-19 08:16:02,873 - train: [ INFO] - Train: 5 [ 50/461 ( 11%)] Loss: 6.434355 (6.7822) Loss_single: 4.528087 (4.7696) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (53.1250) Acc@5: 84.3750 (81.2500) Time: 0.431s, 74.19/s (0.454s, 70.45/s) LR: 5.000e-03 Data: 0.000 (0.073) +2025-04-19 08:16:21,781 - train: [ INFO] - Train: 5 [ 100/461 ( 22%)] Loss: 6.279892 (6.6148) Loss_single: 4.498487 (4.6792) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (58.3333) Acc@5: 90.6250 (84.3750) Time: 0.347s, 92.11/s (0.416s, 76.89/s) LR: 5.000e-03 Data: 0.000 (0.038) +2025-04-19 08:16:39,904 - train: [ INFO] - Train: 5 [ 150/461 ( 33%)] Loss: 5.693321 (6.3844) Loss_single: 4.227837 (4.5664) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (61.7188) Acc@5: 100.0000 (88.2812) Time: 0.364s, 87.99/s (0.398s, 80.37/s) LR: 5.000e-03 Data: 0.001 (0.026) +2025-04-19 08:16:58,550 - train: [ INFO] - Train: 5 [ 200/461 ( 43%)] Loss: 6.969082 (6.5013) Loss_single: 5.007816 (4.6547) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (60.6250) Acc@5: 81.2500 (86.8750) Time: 0.365s, 87.74/s (0.392s, 81.70/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 08:17:16,988 - train: [ INFO] - Train: 5 [ 250/461 ( 54%)] Loss: 6.552105 (6.5098) Loss_single: 4.641437 (4.6525) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (58.8542) Acc@5: 90.6250 (87.5000) Time: 0.366s, 87.37/s (0.387s, 82.70/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 08:17:35,866 - train: [ INFO] - Train: 5 [ 300/461 ( 65%)] Loss: 7.043552 (6.5860) Loss_single: 4.971847 (4.6981) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (57.1429) Acc@5: 75.0000 (85.7143) Time: 0.441s, 72.51/s (0.385s, 83.07/s) LR: 5.000e-03 Data: 0.004 (0.013) +2025-04-19 08:17:54,928 - train: [ INFO] - Train: 5 [ 350/461 ( 76%)] Loss: 6.535018 (6.5797) Loss_single: 4.712100 (4.6998) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (57.0312) Acc@5: 84.3750 (85.5469) Time: 0.348s, 91.87/s (0.385s, 83.22/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 08:18:12,816 - train: [ INFO] - Train: 5 [ 400/461 ( 87%)] Loss: 7.340433 (6.6642) Loss_single: 5.203409 (4.7558) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (55.5556) Acc@5: 78.1250 (84.7222) Time: 0.353s, 90.52/s (0.381s, 83.96/s) LR: 5.000e-03 Data: 0.001 (0.010) +2025-04-19 08:18:31,280 - train: [ INFO] - Train: 5 [ 450/461 ( 98%)] Loss: 6.901776 (6.6880) Loss_single: 4.963743 (4.7766) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (55.3125) Acc@5: 84.3750 (84.6875) Time: 0.319s, 100.42/s (0.380s, 84.28/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 08:18:34,599 - train: [ INFO] - Train: 5 [ 460/461 (100%)] Loss: 7.084498 (6.7240) Loss_single: 5.008656 (4.7977) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (54.2614) Acc@5: 78.1250 (84.0909) Time: 0.382s, 83.82/s (0.379s, 84.51/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 08:18:39,530 - train: [ INFO] - Eval : 5 Time: 4.676 (4.676) Loss: 1.7807 (1.7807) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 08:18:49,405 - train: [ INFO] - Eval : 5 Time: 0.150 (0.285) Loss: 1.7176 (1.7779) Acc@1: 62.5000 (49.6324)Acc@5: 81.2500 (80.7598) +2025-04-19 08:18:54,196 - train: [ INFO] - Eval : 5 Time: 0.050 (0.236) Loss: 4.2394 (1.8254) Acc@1: 0.0000 (48.7278)Acc@5: 0.0000 (79.3755) +2025-04-19 08:18:57,515 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-5.pth.tar', 48.727833461835004) + +2025-04-19 08:19:02,910 - train: [ INFO] - Train: 6 [ 0/461 ( 0%)] Loss: 6.788541 (6.7885) Loss_single: 4.836626 (4.8366) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (53.1250) Acc@5: 81.2500 (81.2500) Time: 5.366s, 5.96/s (5.366s, 5.96/s) LR: 5.000e-03 Data: 4.907 (4.907) +2025-04-19 08:19:21,150 - train: [ INFO] - Train: 6 [ 50/461 ( 11%)] Loss: 8.117075 (7.4528) Loss_single: 5.637614 (5.2371) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (46.8750) Acc@5: 68.7500 (75.0000) Time: 0.349s, 91.63/s (0.462s, 69.25/s) LR: 5.000e-03 Data: 0.000 (0.097) +2025-04-19 08:19:39,497 - train: [ INFO] - Train: 6 [ 100/461 ( 22%)] Loss: 5.792072 (6.8992) Loss_single: 4.235452 (4.9032) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (54.1667) Acc@5: 87.5000 (79.1667) Time: 0.329s, 97.20/s (0.415s, 77.20/s) LR: 5.000e-03 Data: 0.000 (0.049) +2025-04-19 08:19:57,313 - train: [ INFO] - Train: 6 [ 150/461 ( 33%)] Loss: 6.463147 (6.7902) Loss_single: 4.731339 (4.8603) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (57.0312) Acc@5: 87.5000 (81.2500) Time: 0.361s, 88.70/s (0.395s, 81.03/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-19 08:20:15,467 - train: [ INFO] - Train: 6 [ 200/461 ( 43%)] Loss: 6.855099 (6.8032) Loss_single: 4.851131 (4.8584) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (57.5000) Acc@5: 87.5000 (82.5000) Time: 0.467s, 68.47/s (0.387s, 82.74/s) LR: 5.000e-03 Data: 0.001 (0.025) +2025-04-19 08:20:38,077 - train: [ INFO] - Train: 6 [ 250/461 ( 54%)] Loss: 5.829837 (6.6410) Loss_single: 4.273876 (4.7610) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (58.8542) Acc@5: 93.7500 (84.3750) Time: 0.627s, 51.07/s (0.400s, 80.09/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 08:21:10,694 - train: [ INFO] - Train: 6 [ 300/461 ( 65%)] Loss: 6.960556 (6.6866) Loss_single: 4.804148 (4.7672) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (58.0357) Acc@5: 78.1250 (83.4821) Time: 0.698s, 45.85/s (0.441s, 72.53/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 08:21:43,788 - train: [ INFO] - Train: 6 [ 350/461 ( 76%)] Loss: 6.262389 (6.6336) Loss_single: 4.424915 (4.7244) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (58.9844) Acc@5: 87.5000 (83.9844) Time: 0.702s, 45.55/s (0.472s, 67.75/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 08:22:16,313 - train: [ INFO] - Train: 6 [ 400/461 ( 87%)] Loss: 5.581336 (6.5167) Loss_single: 4.149259 (4.6605) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (60.0694) Acc@5: 96.8750 (85.4167) Time: 0.544s, 58.85/s (0.494s, 64.74/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 08:22:50,036 - train: [ INFO] - Train: 6 [ 450/461 ( 98%)] Loss: 6.791943 (6.5442) Loss_single: 4.897241 (4.6842) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (60.0000) Acc@5: 87.5000 (85.6250) Time: 0.586s, 54.56/s (0.514s, 62.27/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:22:56,842 - train: [ INFO] - Train: 6 [ 460/461 (100%)] Loss: 5.836124 (6.4798) Loss_single: 4.230810 (4.6429) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (60.7955) Acc@5: 93.7500 (86.3636) Time: 0.872s, 36.70/s (0.517s, 61.84/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 08:23:03,148 - train: [ INFO] - Eval : 6 Time: 5.945 (5.945) Loss: 1.8175 (1.8175) Acc@1: 46.8750 (46.8750)Acc@5: 84.3750 (84.3750) +2025-04-19 08:23:16,645 - train: [ INFO] - Eval : 6 Time: 0.142 (0.381) Loss: 2.2657 (1.8124) Acc@1: 53.1250 (49.5711)Acc@5: 75.0000 (80.9436) +2025-04-19 08:23:22,770 - train: [ INFO] - Eval : 6 Time: 0.052 (0.312) Loss: 4.1647 (1.8014) Acc@1: 0.0000 (49.5374)Acc@5: 0.0000 (80.9175) +2025-04-19 08:23:26,054 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-6.pth.tar', 49.53739398612182) + +2025-04-19 08:23:29,638 - train: [ INFO] - Train: 7 [ 0/461 ( 0%)] Loss: 5.960217 (5.9602) Loss_single: 4.339715 (4.3397) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (68.7500) Acc@5: 90.6250 (90.6250) Time: 3.544s, 9.03/s (3.544s, 9.03/s) LR: 5.000e-03 Data: 3.034 (3.034) +2025-04-19 08:23:47,998 - train: [ INFO] - Train: 7 [ 50/461 ( 11%)] Loss: 5.955182 (5.9577) Loss_single: 4.327287 (4.3335) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (67.1875) Acc@5: 84.3750 (87.5000) Time: 0.374s, 85.67/s (0.428s, 74.70/s) LR: 5.000e-03 Data: 0.001 (0.060) +2025-04-19 08:24:07,050 - train: [ INFO] - Train: 7 [ 100/461 ( 22%)] Loss: 6.031383 (5.9823) Loss_single: 4.413013 (4.3600) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (65.6250) Acc@5: 93.7500 (89.5833) Time: 0.343s, 93.32/s (0.405s, 79.11/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 08:24:25,510 - train: [ INFO] - Train: 7 [ 150/461 ( 33%)] Loss: 6.553133 (6.1250) Loss_single: 4.675029 (4.4388) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (64.8438) Acc@5: 78.1250 (86.7188) Time: 0.337s, 95.09/s (0.392s, 81.54/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 08:24:48,045 - train: [ INFO] - Train: 7 [ 200/461 ( 43%)] Loss: 6.198823 (6.1397) Loss_single: 4.496533 (4.4503) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (66.2500) Acc@5: 87.5000 (86.8750) Time: 0.569s, 56.25/s (0.406s, 78.72/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 08:25:22,100 - train: [ INFO] - Train: 7 [ 250/461 ( 54%)] Loss: 5.485539 (6.0307) Loss_single: 3.944455 (4.3660) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (67.1875) Acc@5: 93.7500 (88.0208) Time: 0.631s, 50.70/s (0.461s, 69.44/s) LR: 5.000e-03 Data: 0.013 (0.013) +2025-04-19 08:26:02,601 - train: [ INFO] - Train: 7 [ 300/461 ( 65%)] Loss: 6.086329 (6.0387) Loss_single: 4.432632 (4.3755) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (66.9643) Acc@5: 96.8750 (89.2857) Time: 0.712s, 44.93/s (0.519s, 61.71/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 08:26:38,896 - train: [ INFO] - Train: 7 [ 350/461 ( 76%)] Loss: 6.205070 (6.0595) Loss_single: 4.554742 (4.3979) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (68.3594) Acc@5: 90.6250 (89.4531) Time: 0.708s, 45.17/s (0.548s, 58.40/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 08:27:17,850 - train: [ INFO] - Train: 7 [ 400/461 ( 87%)] Loss: 5.501691 (5.9975) Loss_single: 4.112236 (4.3662) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (69.4444) Acc@5: 96.8750 (90.2778) Time: 0.735s, 43.52/s (0.576s, 55.51/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 08:27:56,650 - train: [ INFO] - Train: 7 [ 450/461 ( 98%)] Loss: 6.011490 (5.9989) Loss_single: 4.414607 (4.3710) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (70.6250) Acc@5: 87.5000 (90.0000) Time: 0.765s, 41.81/s (0.598s, 53.48/s) LR: 5.000e-03 Data: 0.000 (0.008) +2025-04-19 08:28:04,066 - train: [ INFO] - Train: 7 [ 460/461 (100%)] Loss: 5.938564 (5.9934) Loss_single: 4.316225 (4.3660) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (70.1705) Acc@5: 87.5000 (89.7727) Time: 0.738s, 43.37/s (0.601s, 53.21/s) LR: 5.000e-03 Data: 0.000 (0.008) +2025-04-19 08:28:09,476 - train: [ INFO] - Eval : 7 Time: 5.039 (5.039) Loss: 1.8924 (1.8924) Acc@1: 53.1250 (53.1250)Acc@5: 78.1250 (78.1250) +2025-04-19 08:28:23,704 - train: [ INFO] - Eval : 7 Time: 0.243 (0.378) Loss: 2.1173 (1.7380) Acc@1: 53.1250 (53.1250)Acc@5: 71.8750 (80.6985) +2025-04-19 08:28:30,964 - train: [ INFO] - Eval : 7 Time: 0.069 (0.323) Loss: 4.7371 (1.7474) Acc@1: 0.0000 (51.3878)Acc@5: 0.0000 (81.6114) +2025-04-19 08:28:34,840 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-7.pth.tar', 51.38781804163454) + +2025-04-19 08:28:42,736 - train: [ INFO] - Train: 8 [ 0/461 ( 0%)] Loss: 5.388120 (5.3881) Loss_single: 3.981239 (3.9812) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (71.8750) Acc@5: 96.8750 (96.8750) Time: 7.824s, 4.09/s (7.824s, 4.09/s) LR: 5.000e-03 Data: 6.977 (6.977) +2025-04-19 08:29:20,207 - train: [ INFO] - Train: 8 [ 50/461 ( 11%)] Loss: 6.119821 (5.7540) Loss_single: 4.380947 (4.1811) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (73.4375) Acc@5: 84.3750 (90.6250) Time: 0.557s, 57.41/s (0.886s, 36.12/s) LR: 5.000e-03 Data: 0.000 (0.139) +2025-04-19 08:29:55,938 - train: [ INFO] - Train: 8 [ 100/461 ( 22%)] Loss: 5.234971 (5.5810) Loss_single: 3.999113 (4.1204) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (76.0417) Acc@5: 96.8750 (92.7083) Time: 0.623s, 51.38/s (0.800s, 39.98/s) LR: 5.000e-03 Data: 0.001 (0.071) +2025-04-19 08:30:32,031 - train: [ INFO] - Train: 8 [ 150/461 ( 33%)] Loss: 6.052136 (5.6988) Loss_single: 4.339602 (4.1752) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (72.6562) Acc@5: 90.6250 (92.1875) Time: 0.609s, 52.58/s (0.774s, 41.35/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-19 08:31:06,638 - train: [ INFO] - Train: 8 [ 200/461 ( 43%)] Loss: 5.935444 (5.7461) Loss_single: 4.312096 (4.2026) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (70.6250) Acc@5: 87.5000 (91.2500) Time: 0.698s, 45.86/s (0.753s, 42.48/s) LR: 5.000e-03 Data: 0.000 (0.037) +2025-04-19 08:31:46,241 - train: [ INFO] - Train: 8 [ 250/461 ( 54%)] Loss: 6.748180 (5.9131) Loss_single: 4.810965 (4.3040) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (66.6667) Acc@5: 87.5000 (90.6250) Time: 0.513s, 62.33/s (0.761s, 42.08/s) LR: 5.000e-03 Data: 0.004 (0.030) +2025-04-19 08:32:16,740 - train: [ INFO] - Train: 8 [ 300/461 ( 65%)] Loss: 5.996255 (5.9250) Loss_single: 4.476718 (4.3287) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (67.8571) Acc@5: 96.8750 (91.5179) Time: 0.531s, 60.23/s (0.735s, 43.52/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 08:32:45,597 - train: [ INFO] - Train: 8 [ 350/461 ( 76%)] Loss: 6.050463 (5.9407) Loss_single: 4.363173 (4.3330) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (67.1875) Acc@5: 93.7500 (91.7969) Time: 0.499s, 64.10/s (0.712s, 44.91/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 08:33:14,995 - train: [ INFO] - Train: 8 [ 400/461 ( 87%)] Loss: 7.231103 (6.0841) Loss_single: 5.018087 (4.4091) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (65.2778) Acc@5: 75.0000 (89.9306) Time: 0.837s, 38.21/s (0.697s, 45.93/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 08:33:54,643 - train: [ INFO] - Train: 8 [ 450/461 ( 98%)] Loss: 6.625731 (6.1382) Loss_single: 4.638073 (4.4320) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (64.0625) Acc@5: 81.2500 (89.0625) Time: 0.703s, 45.50/s (0.707s, 45.24/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 08:34:02,466 - train: [ INFO] - Train: 8 [ 460/461 (100%)] Loss: 6.250384 (6.1484) Loss_single: 4.474930 (4.4359) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (64.2045) Acc@5: 84.3750 (88.6364) Time: 0.697s, 45.94/s (0.709s, 45.14/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 08:34:09,332 - train: [ INFO] - Eval : 8 Time: 6.460 (6.460) Loss: 1.8392 (1.8392) Acc@1: 56.2500 (56.2500)Acc@5: 71.8750 (71.8750) +2025-04-19 08:34:23,901 - train: [ INFO] - Eval : 8 Time: 0.221 (0.412) Loss: 1.9803 (1.6292) Acc@1: 53.1250 (54.3505)Acc@5: 75.0000 (82.5368) +2025-04-19 08:34:31,943 - train: [ INFO] - Eval : 8 Time: 0.069 (0.355) Loss: 3.4509 (1.6256) Acc@1: 0.0000 (54.3562)Acc@5: 50.0000 (82.6137) +2025-04-19 08:34:36,579 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-8.pth.tar', 54.3562066306862) + +2025-04-19 08:34:43,324 - train: [ INFO] - Train: 9 [ 0/461 ( 0%)] Loss: 6.182666 (6.1827) Loss_single: 4.463579 (4.4636) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (68.7500) Acc@5: 87.5000 (87.5000) Time: 6.663s, 4.80/s (6.663s, 4.80/s) LR: 5.000e-03 Data: 5.737 (5.737) +2025-04-19 08:35:23,334 - train: [ INFO] - Train: 9 [ 50/461 ( 11%)] Loss: 5.898994 (6.0408) Loss_single: 4.329915 (4.3967) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (68.7500) Acc@5: 93.7500 (90.6250) Time: 0.768s, 41.65/s (0.914s, 35.02/s) LR: 5.000e-03 Data: 0.000 (0.113) +2025-04-19 08:35:59,044 - train: [ INFO] - Train: 9 [ 100/461 ( 22%)] Loss: 5.542518 (5.8747) Loss_single: 4.009240 (4.2676) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (71.8750) Acc@5: 90.6250 (90.6250) Time: 0.835s, 38.32/s (0.814s, 39.32/s) LR: 5.000e-03 Data: 0.000 (0.058) +2025-04-19 08:36:35,998 - train: [ INFO] - Train: 9 [ 150/461 ( 33%)] Loss: 5.495524 (5.7799) Loss_single: 4.046165 (4.2122) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (73.4375) Acc@5: 96.8750 (92.1875) Time: 0.561s, 57.01/s (0.788s, 40.59/s) LR: 5.000e-03 Data: 0.001 (0.039) +2025-04-19 08:37:08,332 - train: [ INFO] - Train: 9 [ 200/461 ( 43%)] Loss: 5.445080 (5.7130) Loss_single: 4.041679 (4.1781) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (73.1250) Acc@5: 96.8750 (93.1250) Time: 0.606s, 52.79/s (0.753s, 42.51/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 08:37:40,385 - train: [ INFO] - Train: 9 [ 250/461 ( 54%)] Loss: 5.459732 (5.6708) Loss_single: 4.039080 (4.1549) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (72.9167) Acc@5: 93.7500 (93.2292) Time: 0.762s, 41.99/s (0.730s, 43.82/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 08:38:13,832 - train: [ INFO] - Train: 9 [ 300/461 ( 65%)] Loss: 6.653950 (5.8112) Loss_single: 4.831197 (4.2516) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (70.9821) Acc@5: 93.7500 (93.3036) Time: 0.702s, 45.58/s (0.720s, 44.47/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 08:38:46,306 - train: [ INFO] - Train: 9 [ 350/461 ( 76%)] Loss: 5.362250 (5.7551) Loss_single: 3.967917 (4.2161) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (71.8750) Acc@5: 96.8750 (93.7500) Time: 0.593s, 53.97/s (0.709s, 45.10/s) LR: 5.000e-03 Data: 0.004 (0.017) +2025-04-19 08:39:17,185 - train: [ INFO] - Train: 9 [ 400/461 ( 87%)] Loss: 6.299184 (5.8155) Loss_single: 4.565492 (4.2549) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (70.8333) Acc@5: 87.5000 (93.0556) Time: 0.722s, 44.33/s (0.698s, 45.87/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 08:39:49,981 - train: [ INFO] - Train: 9 [ 450/461 ( 98%)] Loss: 6.085537 (5.8425) Loss_single: 4.403037 (4.2697) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (70.6250) Acc@5: 90.6250 (92.8125) Time: 0.783s, 40.89/s (0.693s, 46.19/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 08:39:55,951 - train: [ INFO] - Train: 9 [ 460/461 (100%)] Loss: 6.161352 (5.8715) Loss_single: 4.500867 (4.2907) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (70.4545) Acc@5: 96.8750 (93.1818) Time: 0.562s, 56.92/s (0.691s, 46.33/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 08:40:04,369 - train: [ INFO] - Eval : 9 Time: 8.047 (8.047) Loss: 1.7315 (1.7315) Acc@1: 43.7500 (43.7500)Acc@5: 84.3750 (84.3750) +2025-04-19 08:40:18,868 - train: [ INFO] - Eval : 9 Time: 0.197 (0.442) Loss: 1.8366 (1.6796) Acc@1: 62.5000 (52.4510)Acc@5: 78.1250 (80.7598) +2025-04-19 08:40:26,094 - train: [ INFO] - Eval : 9 Time: 0.058 (0.363) Loss: 3.9983 (1.7117) Acc@1: 0.0000 (51.6962)Acc@5: 50.0000 (80.5320) +2025-04-19 08:40:37,672 - train: [ INFO] - Train: 10 [ 0/461 ( 0%)] Loss: 5.578527 (5.5785) Loss_single: 4.218384 (4.2184) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (81.2500) Acc@5: 96.8750 (96.8750) Time: 7.388s, 4.33/s (7.388s, 4.33/s) LR: 5.000e-03 Data: 6.537 (6.537) +2025-04-19 08:41:10,925 - train: [ INFO] - Train: 10 [ 50/461 ( 11%)] Loss: 5.988016 (5.7833) Loss_single: 4.481531 (4.3500) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (78.1250) Acc@5: 90.6250 (93.7500) Time: 0.617s, 51.88/s (0.796s, 40.22/s) LR: 5.000e-03 Data: 0.001 (0.129) +2025-04-19 08:41:47,789 - train: [ INFO] - Train: 10 [ 100/461 ( 22%)] Loss: 5.462646 (5.6764) Loss_single: 4.007332 (4.2357) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (76.0417) Acc@5: 96.8750 (94.7917) Time: 0.599s, 53.45/s (0.766s, 41.77/s) LR: 5.000e-03 Data: 0.000 (0.065) +2025-04-19 08:42:22,583 - train: [ INFO] - Train: 10 [ 150/461 ( 33%)] Loss: 5.431932 (5.6153) Loss_single: 4.061519 (4.1922) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (75.7812) Acc@5: 93.7500 (94.5312) Time: 0.774s, 41.32/s (0.742s, 43.11/s) LR: 5.000e-03 Data: 0.001 (0.044) +2025-04-19 08:43:02,164 - train: [ INFO] - Train: 10 [ 200/461 ( 43%)] Loss: 5.817441 (5.6557) Loss_single: 4.375209 (4.2288) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (75.0000) Acc@5: 93.7500 (94.3750) Time: 0.752s, 42.57/s (0.754s, 42.43/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-19 08:43:35,829 - train: [ INFO] - Train: 10 [ 250/461 ( 54%)] Loss: 4.776661 (5.5092) Loss_single: 3.567299 (4.1185) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (76.0417) Acc@5: 96.8750 (94.7917) Time: 0.561s, 57.01/s (0.738s, 43.38/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 08:44:09,279 - train: [ INFO] - Train: 10 [ 300/461 ( 65%)] Loss: 5.777413 (5.5475) Loss_single: 4.175499 (4.1267) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (75.0000) Acc@5: 100.0000 (95.5357) Time: 0.491s, 65.15/s (0.726s, 44.09/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 08:44:39,720 - train: [ INFO] - Train: 10 [ 350/461 ( 76%)] Loss: 6.299998 (5.6416) Loss_single: 4.672723 (4.1949) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (73.4375) Acc@5: 90.6250 (94.9219) Time: 0.606s, 52.81/s (0.709s, 45.14/s) LR: 5.000e-03 Data: 0.001 (0.020) +2025-04-19 08:45:10,898 - train: [ INFO] - Train: 10 [ 400/461 ( 87%)] Loss: 5.823908 (5.6618) Loss_single: 4.381422 (4.2157) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (73.6111) Acc@5: 93.7500 (94.7917) Time: 0.477s, 67.12/s (0.698s, 45.84/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 08:45:42,698 - train: [ INFO] - Train: 10 [ 450/461 ( 98%)] Loss: 6.321147 (5.7278) Loss_single: 4.603419 (4.2544) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (72.1875) Acc@5: 84.3750 (93.7500) Time: 0.487s, 65.70/s (0.691s, 46.32/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 08:45:49,134 - train: [ INFO] - Train: 10 [ 460/461 (100%)] Loss: 5.904296 (5.7438) Loss_single: 4.366670 (4.2646) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (71.8750) Acc@5: 93.7500 (93.7500) Time: 0.614s, 52.09/s (0.690s, 46.39/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 08:45:54,140 - train: [ INFO] - Eval : 10 Time: 4.678 (4.678) Loss: 1.6774 (1.6774) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-19 08:46:07,521 - train: [ INFO] - Eval : 10 Time: 0.317 (0.354) Loss: 2.0018 (1.7277) Acc@1: 50.0000 (50.5515)Acc@5: 68.7500 (81.4338) +2025-04-19 08:46:13,827 - train: [ INFO] - Eval : 10 Time: 0.064 (0.297) Loss: 3.6384 (1.7374) Acc@1: 0.0000 (50.6939)Acc@5: 50.0000 (81.3030) +2025-04-19 08:46:23,282 - train: [ INFO] - Train: 11 [ 0/461 ( 0%)] Loss: 4.932510 (4.9325) Loss_single: 3.611113 (3.6111) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (78.1250) Acc@5: 100.0000 (100.0000) Time: 5.756s, 5.56/s (5.756s, 5.56/s) LR: 5.000e-03 Data: 5.054 (5.054) +2025-04-19 08:46:55,741 - train: [ INFO] - Train: 11 [ 50/461 ( 11%)] Loss: 5.375567 (5.1540) Loss_single: 4.139668 (3.8754) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (78.1250) Acc@5: 93.7500 (96.8750) Time: 0.674s, 47.50/s (0.747s, 42.83/s) LR: 5.000e-03 Data: 0.001 (0.100) +2025-04-19 08:47:34,147 - train: [ INFO] - Train: 11 [ 100/461 ( 22%)] Loss: 5.119301 (5.1425) Loss_single: 3.818448 (3.8564) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (77.0833) Acc@5: 93.7500 (95.8333) Time: 0.850s, 37.66/s (0.757s, 42.29/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-19 08:48:08,575 - train: [ INFO] - Train: 11 [ 150/461 ( 33%)] Loss: 5.427457 (5.2137) Loss_single: 4.079228 (3.9121) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (76.5625) Acc@5: 100.0000 (96.8750) Time: 0.458s, 69.88/s (0.733s, 43.64/s) LR: 5.000e-03 Data: 0.001 (0.035) +2025-04-19 08:48:43,177 - train: [ INFO] - Train: 11 [ 200/461 ( 43%)] Loss: 5.780743 (5.3271) Loss_single: 4.352798 (4.0003) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (75.6250) Acc@5: 96.8750 (96.8750) Time: 0.791s, 40.47/s (0.722s, 44.30/s) LR: 5.000e-03 Data: 0.001 (0.027) +2025-04-19 08:49:20,411 - train: [ INFO] - Train: 11 [ 250/461 ( 54%)] Loss: 5.593188 (5.3715) Loss_single: 4.069689 (4.0118) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (74.4792) Acc@5: 96.8750 (96.8750) Time: 0.595s, 53.76/s (0.726s, 44.05/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 08:49:58,079 - train: [ INFO] - Train: 11 [ 300/461 ( 65%)] Loss: 5.018520 (5.3210) Loss_single: 3.739665 (3.9729) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (76.3393) Acc@5: 90.6250 (95.9821) Time: 0.693s, 46.21/s (0.730s, 43.82/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 08:50:35,089 - train: [ INFO] - Train: 11 [ 350/461 ( 76%)] Loss: 5.785594 (5.3791) Loss_single: 4.247179 (4.0072) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (75.0000) Acc@5: 93.7500 (95.7031) Time: 0.843s, 37.97/s (0.731s, 43.75/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 08:51:11,173 - train: [ INFO] - Train: 11 [ 400/461 ( 87%)] Loss: 5.806432 (5.4266) Loss_single: 4.248322 (4.0340) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (74.6528) Acc@5: 93.7500 (95.4861) Time: 0.622s, 51.42/s (0.730s, 43.84/s) LR: 5.000e-03 Data: 0.003 (0.014) +2025-04-19 08:51:47,740 - train: [ INFO] - Train: 11 [ 450/461 ( 98%)] Loss: 4.893527 (5.3733) Loss_single: 3.714975 (4.0021) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (75.9375) Acc@5: 100.0000 (95.9375) Time: 1.038s, 30.84/s (0.730s, 43.84/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:51:55,596 - train: [ INFO] - Train: 11 [ 460/461 (100%)] Loss: 6.246730 (5.4527) Loss_single: 4.482846 (4.0458) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (73.8636) Acc@5: 93.7500 (95.7386) Time: 0.810s, 39.49/s (0.731s, 43.78/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:52:02,069 - train: [ INFO] - Eval : 11 Time: 5.821 (5.821) Loss: 2.1266 (2.1266) Acc@1: 46.8750 (46.8750)Acc@5: 68.7500 (68.7500) +2025-04-19 08:52:16,697 - train: [ INFO] - Eval : 11 Time: 0.199 (0.401) Loss: 2.0269 (1.7195) Acc@1: 50.0000 (52.3284)Acc@5: 71.8750 (80.3309) +2025-04-19 08:52:24,872 - train: [ INFO] - Eval : 11 Time: 0.080 (0.349) Loss: 2.3646 (1.7056) Acc@1: 0.0000 (52.0817)Acc@5: 50.0000 (80.8404) +2025-04-19 08:52:34,712 - train: [ INFO] - Train: 12 [ 0/461 ( 0%)] Loss: 4.642448 (4.6424) Loss_single: 3.520416 (3.5204) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (90.6250) Acc@5: 96.8750 (96.8750) Time: 6.120s, 5.23/s (6.120s, 5.23/s) LR: 5.000e-03 Data: 5.091 (5.091) +2025-04-19 08:53:10,718 - train: [ INFO] - Train: 12 [ 50/461 ( 11%)] Loss: 4.183132 (4.4128) Loss_single: 3.245133 (3.3828) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (92.1875) Acc@5: 100.0000 (98.4375) Time: 0.611s, 52.39/s (0.823s, 38.86/s) LR: 5.000e-03 Data: 0.002 (0.101) +2025-04-19 08:53:47,467 - train: [ INFO] - Train: 12 [ 100/461 ( 22%)] Loss: 5.059116 (4.6282) Loss_single: 3.808688 (3.5247) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (90.6250) Acc@5: 93.7500 (96.8750) Time: 0.941s, 34.02/s (0.778s, 41.11/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-19 08:54:26,637 - train: [ INFO] - Train: 12 [ 150/461 ( 33%)] Loss: 4.547534 (4.6081) Loss_single: 3.481535 (3.5139) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (90.6250) Acc@5: 100.0000 (97.6562) Time: 0.796s, 40.22/s (0.779s, 41.07/s) LR: 5.000e-03 Data: 0.004 (0.035) +2025-04-19 08:55:07,811 - train: [ INFO] - Train: 12 [ 200/461 ( 43%)] Loss: 4.275855 (4.5416) Loss_single: 3.315591 (3.4743) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (91.8750) Acc@5: 100.0000 (98.1250) Time: 0.889s, 36.00/s (0.790s, 40.52/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 08:55:47,564 - train: [ INFO] - Train: 12 [ 250/461 ( 54%)] Loss: 4.301764 (4.5016) Loss_single: 3.255333 (3.4378) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (92.1875) Acc@5: 96.8750 (97.9167) Time: 0.472s, 67.86/s (0.791s, 40.48/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 08:56:22,779 - train: [ INFO] - Train: 12 [ 300/461 ( 65%)] Loss: 4.522339 (4.5046) Loss_single: 3.426029 (3.4361) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (91.0714) Acc@5: 100.0000 (98.2143) Time: 0.577s, 55.49/s (0.776s, 41.24/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 08:56:57,007 - train: [ INFO] - Train: 12 [ 350/461 ( 76%)] Loss: 4.041733 (4.4467) Loss_single: 3.076327 (3.3911) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.4062) Acc@5: 100.0000 (98.4375) Time: 0.497s, 64.39/s (0.763s, 41.96/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 08:57:27,057 - train: [ INFO] - Train: 12 [ 400/461 ( 87%)] Loss: 5.024464 (4.5109) Loss_single: 3.862463 (3.4435) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (90.2778) Acc@5: 100.0000 (98.6111) Time: 0.865s, 36.98/s (0.742s, 43.11/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 08:58:00,533 - train: [ INFO] - Train: 12 [ 450/461 ( 98%)] Loss: 5.259326 (4.5858) Loss_single: 3.798205 (3.4790) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (88.4375) Acc@5: 93.7500 (98.1250) Time: 0.651s, 49.19/s (0.734s, 43.59/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:58:07,401 - train: [ INFO] - Train: 12 [ 460/461 (100%)] Loss: 5.055583 (4.6285) Loss_single: 3.904743 (3.5177) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (88.3523) Acc@5: 100.0000 (98.2955) Time: 0.605s, 52.91/s (0.733s, 43.66/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 08:58:13,641 - train: [ INFO] - Eval : 12 Time: 5.843 (5.843) Loss: 1.6923 (1.6923) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 08:58:27,246 - train: [ INFO] - Eval : 12 Time: 0.350 (0.381) Loss: 2.0247 (1.7912) Acc@1: 53.1250 (52.2672)Acc@5: 71.8750 (79.5956) +2025-04-19 08:58:34,747 - train: [ INFO] - Eval : 12 Time: 0.056 (0.329) Loss: 2.5947 (1.8054) Acc@1: 50.0000 (51.8119)Acc@5: 50.0000 (79.7224) +2025-04-19 08:58:43,884 - train: [ INFO] - Train: 13 [ 0/461 ( 0%)] Loss: 4.797266 (4.7973) Loss_single: 3.632388 (3.6324) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (87.5000) Acc@5: 100.0000 (100.0000) Time: 5.668s, 5.65/s (5.668s, 5.65/s) LR: 5.000e-03 Data: 4.953 (4.953) +2025-04-19 08:59:16,803 - train: [ INFO] - Train: 13 [ 50/461 ( 11%)] Loss: 4.426896 (4.6121) Loss_single: 3.404582 (3.5185) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (90.6250) Acc@5: 96.8750 (98.4375) Time: 0.615s, 52.02/s (0.755s, 42.36/s) LR: 5.000e-03 Data: 0.001 (0.098) +2025-04-19 08:59:50,074 - train: [ INFO] - Train: 13 [ 100/461 ( 22%)] Loss: 4.765571 (4.6632) Loss_single: 3.684249 (3.5737) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (89.5833) Acc@5: 100.0000 (98.9583) Time: 0.738s, 43.39/s (0.710s, 45.07/s) LR: 5.000e-03 Data: 0.000 (0.050) +2025-04-19 09:00:24,502 - train: [ INFO] - Train: 13 [ 150/461 ( 33%)] Loss: 4.292320 (4.5705) Loss_single: 3.396580 (3.5294) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (91.4062) Acc@5: 100.0000 (99.2188) Time: 0.909s, 35.21/s (0.702s, 45.56/s) LR: 5.000e-03 Data: 0.001 (0.034) +2025-04-19 09:00:58,404 - train: [ INFO] - Train: 13 [ 200/461 ( 43%)] Loss: 4.240652 (4.5045) Loss_single: 3.177931 (3.4591) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (90.6250) Acc@5: 96.8750 (98.7500) Time: 0.715s, 44.77/s (0.696s, 45.98/s) LR: 5.000e-03 Data: 0.001 (0.026) +2025-04-19 09:01:33,030 - train: [ INFO] - Train: 13 [ 250/461 ( 54%)] Loss: 4.261905 (4.4641) Loss_single: 3.325891 (3.4369) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.1458) Acc@5: 100.0000 (98.9583) Time: 0.733s, 43.66/s (0.695s, 46.04/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 09:02:07,730 - train: [ INFO] - Train: 13 [ 300/461 ( 65%)] Loss: 4.454655 (4.4628) Loss_single: 3.359050 (3.4258) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (91.0714) Acc@5: 100.0000 (99.1071) Time: 0.826s, 38.74/s (0.695s, 46.07/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 09:02:42,059 - train: [ INFO] - Train: 13 [ 350/461 ( 76%)] Loss: 4.509989 (4.4687) Loss_single: 3.484379 (3.4331) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.4062) Acc@5: 100.0000 (99.2188) Time: 0.825s, 38.81/s (0.693s, 46.16/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 09:03:15,349 - train: [ INFO] - Train: 13 [ 400/461 ( 87%)] Loss: 3.953017 (4.4114) Loss_single: 2.962928 (3.3809) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.6667) Acc@5: 100.0000 (99.3056) Time: 0.676s, 47.35/s (0.690s, 46.40/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:03:49,187 - train: [ INFO] - Train: 13 [ 450/461 ( 98%)] Loss: 4.472692 (4.4175) Loss_single: 3.447125 (3.3875) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.8750) Acc@5: 100.0000 (99.3750) Time: 0.672s, 47.65/s (0.688s, 46.51/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 09:03:56,482 - train: [ INFO] - Train: 13 [ 460/461 (100%)] Loss: 4.832087 (4.4552) Loss_single: 3.644785 (3.4109) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (90.6250) Acc@5: 96.8750 (99.1477) Time: 0.682s, 46.93/s (0.689s, 46.45/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 09:04:01,093 - train: [ INFO] - Eval : 13 Time: 4.218 (4.218) Loss: 1.8583 (1.8583) Acc@1: 56.2500 (56.2500)Acc@5: 81.2500 (81.2500) +2025-04-19 09:04:15,101 - train: [ INFO] - Eval : 13 Time: 0.227 (0.357) Loss: 1.8900 (1.7617) Acc@1: 43.7500 (53.6152)Acc@5: 78.1250 (79.2892) +2025-04-19 09:04:22,343 - train: [ INFO] - Eval : 13 Time: 0.064 (0.311) Loss: 2.5330 (1.7753) Acc@1: 0.0000 (53.1997)Acc@5: 50.0000 (79.4140) +2025-04-19 09:04:32,116 - train: [ INFO] - Train: 14 [ 0/461 ( 0%)] Loss: 4.534311 (4.5343) Loss_single: 3.460748 (3.4607) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (90.6250) Acc@5: 100.0000 (100.0000) Time: 5.066s, 6.32/s (5.066s, 6.32/s) LR: 5.000e-03 Data: 4.251 (4.251) +2025-04-19 09:05:05,302 - train: [ INFO] - Train: 14 [ 50/461 ( 11%)] Loss: 3.919429 (4.2269) Loss_single: 3.034095 (3.2474) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (93.7500) Acc@5: 100.0000 (100.0000) Time: 0.566s, 56.56/s (0.748s, 42.79/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-19 09:05:38,811 - train: [ INFO] - Train: 14 [ 100/461 ( 22%)] Loss: 4.677639 (4.3771) Loss_single: 3.575656 (3.3568) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (91.6667) Acc@5: 93.7500 (97.9167) Time: 0.593s, 53.99/s (0.708s, 45.17/s) LR: 5.000e-03 Data: 0.000 (0.043) +2025-04-19 09:06:13,334 - train: [ INFO] - Train: 14 [ 150/461 ( 33%)] Loss: 4.254154 (4.3464) Loss_single: 3.217347 (3.3220) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (91.4062) Acc@5: 93.7500 (96.8750) Time: 0.702s, 45.58/s (0.702s, 45.59/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 09:06:46,330 - train: [ INFO] - Train: 14 [ 200/461 ( 43%)] Loss: 4.294111 (4.3359) Loss_single: 3.325572 (3.3227) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.8750) Acc@5: 100.0000 (97.5000) Time: 0.665s, 48.11/s (0.691s, 46.32/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 09:07:19,943 - train: [ INFO] - Train: 14 [ 250/461 ( 54%)] Loss: 4.322253 (4.3336) Loss_single: 3.293243 (3.3178) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (92.7083) Acc@5: 100.0000 (97.9167) Time: 0.792s, 40.41/s (0.687s, 46.59/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 09:07:53,373 - train: [ INFO] - Train: 14 [ 300/461 ( 65%)] Loss: 3.699144 (4.2430) Loss_single: 2.883942 (3.2558) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (93.7500) Acc@5: 100.0000 (98.2143) Time: 0.714s, 44.79/s (0.684s, 46.81/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 09:08:23,133 - train: [ INFO] - Train: 14 [ 350/461 ( 76%)] Loss: 3.948689 (4.2062) Loss_single: 3.064025 (3.2318) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (94.1406) Acc@5: 100.0000 (98.4375) Time: 0.567s, 56.40/s (0.671s, 47.71/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:08:55,595 - train: [ INFO] - Train: 14 [ 400/461 ( 87%)] Loss: 3.983902 (4.1815) Loss_single: 3.167997 (3.2247) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (94.7917) Acc@5: 100.0000 (98.6111) Time: 0.626s, 51.10/s (0.668s, 47.92/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 09:09:28,027 - train: [ INFO] - Train: 14 [ 450/461 ( 98%)] Loss: 3.866891 (4.1501) Loss_single: 3.007355 (3.2030) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (95.3125) Acc@5: 100.0000 (98.7500) Time: 0.684s, 46.76/s (0.666s, 48.08/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:09:34,309 - train: [ INFO] - Train: 14 [ 460/461 (100%)] Loss: 3.643587 (4.1040) Loss_single: 2.768165 (3.1635) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (95.1705) Acc@5: 100.0000 (98.8636) Time: 0.627s, 51.05/s (0.665s, 48.14/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 09:09:39,776 - train: [ INFO] - Eval : 14 Time: 5.118 (5.118) Loss: 1.7431 (1.7431) Acc@1: 59.3750 (59.3750)Acc@5: 75.0000 (75.0000) +2025-04-19 09:09:52,435 - train: [ INFO] - Eval : 14 Time: 0.294 (0.349) Loss: 1.9344 (1.8114) Acc@1: 59.3750 (52.9412)Acc@5: 78.1250 (77.7574) +2025-04-19 09:09:59,113 - train: [ INFO] - Eval : 14 Time: 0.062 (0.298) Loss: 3.2486 (1.8292) Acc@1: 0.0000 (52.2359)Acc@5: 50.0000 (77.7949) +2025-04-19 09:10:09,199 - train: [ INFO] - Train: 15 [ 0/461 ( 0%)] Loss: 3.587583 (3.5876) Loss_single: 2.771078 (2.7711) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 6.109s, 5.24/s (6.109s, 5.24/s) LR: 5.000e-03 Data: 5.372 (5.372) +2025-04-19 09:10:45,091 - train: [ INFO] - Train: 15 [ 50/461 ( 11%)] Loss: 3.632601 (3.6101) Loss_single: 2.817130 (2.7941) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.756s, 42.31/s (0.822s, 38.95/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-19 09:11:16,995 - train: [ INFO] - Train: 15 [ 100/461 ( 22%)] Loss: 3.911602 (3.7106) Loss_single: 3.037109 (2.8751) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.9167) Acc@5: 96.8750 (98.9583) Time: 0.729s, 43.87/s (0.730s, 43.85/s) LR: 5.000e-03 Data: 0.000 (0.054) +2025-04-19 09:11:51,766 - train: [ INFO] - Train: 15 [ 150/461 ( 33%)] Loss: 3.916276 (3.7620) Loss_single: 2.989790 (2.9038) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (96.8750) Acc@5: 96.8750 (98.4375) Time: 0.679s, 47.15/s (0.718s, 44.57/s) LR: 5.000e-03 Data: 0.000 (0.037) +2025-04-19 09:12:24,067 - train: [ INFO] - Train: 15 [ 200/461 ( 43%)] Loss: 4.020301 (3.8137) Loss_single: 3.163985 (2.9558) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (98.7500) Time: 0.649s, 49.34/s (0.700s, 45.74/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-19 09:12:57,839 - train: [ INFO] - Train: 15 [ 250/461 ( 54%)] Loss: 3.859611 (3.8213) Loss_single: 2.998985 (2.9630) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (98.9583) Time: 0.685s, 46.75/s (0.695s, 46.08/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 09:13:31,097 - train: [ INFO] - Train: 15 [ 300/461 ( 65%)] Loss: 4.010444 (3.8483) Loss_single: 3.159203 (2.9910) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (99.1071) Time: 0.662s, 48.31/s (0.689s, 46.42/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 09:14:04,162 - train: [ INFO] - Train: 15 [ 350/461 ( 76%)] Loss: 4.082609 (3.8776) Loss_single: 3.193922 (3.0164) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (96.4844) Acc@5: 100.0000 (99.2188) Time: 0.687s, 46.60/s (0.685s, 46.70/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 09:14:37,331 - train: [ INFO] - Train: 15 [ 400/461 ( 87%)] Loss: 4.370549 (3.9324) Loss_single: 3.475484 (3.0674) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.5278) Acc@5: 96.8750 (98.9583) Time: 0.705s, 45.42/s (0.682s, 46.90/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 09:15:08,920 - train: [ INFO] - Train: 15 [ 450/461 ( 98%)] Loss: 3.873367 (3.9265) Loss_single: 3.007657 (3.0614) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.5625) Acc@5: 100.0000 (99.0625) Time: 0.608s, 52.62/s (0.676s, 47.31/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:15:15,480 - train: [ INFO] - Train: 15 [ 460/461 (100%)] Loss: 3.760440 (3.9114) Loss_single: 2.880473 (3.0450) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.5909) Acc@5: 100.0000 (99.1477) Time: 0.635s, 50.38/s (0.676s, 47.34/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:15:21,351 - train: [ INFO] - Eval : 15 Time: 5.484 (5.484) Loss: 2.4481 (2.4481) Acc@1: 46.8750 (46.8750)Acc@5: 68.7500 (68.7500) +2025-04-19 09:15:34,154 - train: [ INFO] - Eval : 15 Time: 0.235 (0.359) Loss: 2.0629 (1.8749) Acc@1: 50.0000 (50.5515)Acc@5: 75.0000 (77.4510) +2025-04-19 09:15:41,532 - train: [ INFO] - Eval : 15 Time: 0.054 (0.313) Loss: 2.9779 (1.8905) Acc@1: 50.0000 (49.7687)Acc@5: 50.0000 (77.3323) +2025-04-19 09:15:50,689 - train: [ INFO] - Train: 16 [ 0/461 ( 0%)] Loss: 3.472325 (3.4723) Loss_single: 2.709743 (2.7097) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.610s, 5.70/s (5.610s, 5.70/s) LR: 5.000e-03 Data: 4.741 (4.741) +2025-04-19 09:16:24,945 - train: [ INFO] - Train: 16 [ 50/461 ( 11%)] Loss: 3.455544 (3.4639) Loss_single: 2.637204 (2.6735) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.835s, 38.33/s (0.780s, 41.02/s) LR: 5.000e-03 Data: 0.001 (0.094) +2025-04-19 09:16:57,687 - train: [ INFO] - Train: 16 [ 100/461 ( 22%)] Loss: 4.126512 (3.6848) Loss_single: 3.347914 (2.8983) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.537s, 59.63/s (0.717s, 44.61/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-19 09:17:32,378 - train: [ INFO] - Train: 16 [ 150/461 ( 33%)] Loss: 3.810423 (3.7162) Loss_single: 3.008948 (2.9260) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.721s, 44.38/s (0.709s, 45.14/s) LR: 5.000e-03 Data: 0.001 (0.032) +2025-04-19 09:18:05,820 - train: [ INFO] - Train: 16 [ 200/461 ( 43%)] Loss: 3.766202 (3.7262) Loss_single: 2.944665 (2.9297) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.646s, 49.52/s (0.698s, 45.81/s) LR: 5.000e-03 Data: 0.001 (0.025) +2025-04-19 09:18:39,624 - train: [ INFO] - Train: 16 [ 250/461 ( 54%)] Loss: 3.733276 (3.7274) Loss_single: 2.913161 (2.9269) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.765s, 41.86/s (0.694s, 46.13/s) LR: 5.000e-03 Data: 0.007 (0.020) +2025-04-19 09:19:05,675 - train: [ INFO] - Train: 16 [ 300/461 ( 65%)] Loss: 3.846238 (3.7444) Loss_single: 3.005387 (2.9381) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.668s, 47.90/s (0.665s, 48.14/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 09:19:40,156 - train: [ INFO] - Train: 16 [ 350/461 ( 76%)] Loss: 3.639383 (3.7312) Loss_single: 2.894057 (2.9326) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.715s, 44.73/s (0.668s, 47.91/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 09:20:13,604 - train: [ INFO] - Train: 16 [ 400/461 ( 87%)] Loss: 3.840967 (3.7434) Loss_single: 3.045654 (2.9452) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.680s, 47.09/s (0.668s, 47.91/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 09:20:46,517 - train: [ INFO] - Train: 16 [ 450/461 ( 98%)] Loss: 3.202396 (3.6893) Loss_single: 2.435857 (2.8943) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.751s, 42.62/s (0.667s, 48.00/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:20:52,736 - train: [ INFO] - Train: 16 [ 460/461 (100%)] Loss: 3.770061 (3.6967) Loss_single: 2.870715 (2.8921) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (98.8636) Acc@5: 96.8750 (99.7159) Time: 0.621s, 51.57/s (0.666s, 48.08/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:21:00,718 - train: [ INFO] - Eval : 16 Time: 7.431 (7.431) Loss: 2.2195 (2.2195) Acc@1: 40.6250 (40.6250)Acc@5: 68.7500 (68.7500) +2025-04-19 09:21:13,547 - train: [ INFO] - Eval : 16 Time: 0.164 (0.397) Loss: 2.0762 (1.8589) Acc@1: 50.0000 (50.4902)Acc@5: 75.0000 (77.6961) +2025-04-19 09:21:21,060 - train: [ INFO] - Eval : 16 Time: 0.056 (0.339) Loss: 2.9111 (1.8673) Acc@1: 50.0000 (49.8072)Acc@5: 50.0000 (77.6022) +2025-04-19 09:21:29,053 - train: [ INFO] - Train: 17 [ 0/461 ( 0%)] Loss: 3.347519 (3.3475) Loss_single: 2.591084 (2.5911) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.399s, 7.27/s (4.399s, 7.27/s) LR: 5.000e-03 Data: 3.752 (3.752) +2025-04-19 09:22:04,384 - train: [ INFO] - Train: 17 [ 50/461 ( 11%)] Loss: 3.506082 (3.4268) Loss_single: 2.762614 (2.6768) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.647s, 49.50/s (0.777s, 41.18/s) LR: 5.000e-03 Data: 0.001 (0.075) +2025-04-19 09:22:37,344 - train: [ INFO] - Train: 17 [ 100/461 ( 22%)] Loss: 3.450306 (3.4346) Loss_single: 2.739443 (2.6977) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.591s, 54.11/s (0.718s, 44.56/s) LR: 5.000e-03 Data: 0.000 (0.038) +2025-04-19 09:23:12,798 - train: [ INFO] - Train: 17 [ 150/461 ( 33%)] Loss: 3.770505 (3.5186) Loss_single: 2.998149 (2.7728) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.562s, 56.93/s (0.714s, 44.80/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 09:23:46,622 - train: [ INFO] - Train: 17 [ 200/461 ( 43%)] Loss: 3.401097 (3.4951) Loss_single: 2.621914 (2.7426) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.545s, 58.69/s (0.704s, 45.44/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 09:24:19,853 - train: [ INFO] - Train: 17 [ 250/461 ( 54%)] Loss: 4.003915 (3.5799) Loss_single: 3.163048 (2.8127) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.649s, 49.34/s (0.696s, 45.98/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 09:24:55,468 - train: [ INFO] - Train: 17 [ 300/461 ( 65%)] Loss: 3.262418 (3.5345) Loss_single: 2.539777 (2.7737) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.463s, 69.15/s (0.699s, 45.81/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 09:25:28,712 - train: [ INFO] - Train: 17 [ 350/461 ( 76%)] Loss: 3.911555 (3.5817) Loss_single: 3.120032 (2.8170) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.587s, 54.47/s (0.694s, 46.14/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 09:25:56,750 - train: [ INFO] - Train: 17 [ 400/461 ( 87%)] Loss: 3.564487 (3.5798) Loss_single: 2.837677 (2.8193) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.695s, 46.08/s (0.677s, 47.28/s) LR: 5.000e-03 Data: 0.001 (0.010) +2025-04-19 09:26:32,354 - train: [ INFO] - Train: 17 [ 450/461 ( 98%)] Loss: 3.753113 (3.5971) Loss_single: 2.965449 (2.8339) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 100.0000 (100.0000) Time: 0.737s, 43.42/s (0.681s, 47.02/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-19 09:26:38,920 - train: [ INFO] - Train: 17 [ 460/461 (100%)] Loss: 3.984559 (3.6323) Loss_single: 3.157081 (2.8633) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8636) Acc@5: 100.0000 (100.0000) Time: 0.699s, 45.79/s (0.680s, 47.06/s) LR: 5.000e-03 Data: 0.001 (0.009) +2025-04-19 09:26:45,224 - train: [ INFO] - Eval : 17 Time: 5.881 (5.881) Loss: 2.0498 (2.0498) Acc@1: 46.8750 (46.8750)Acc@5: 81.2500 (81.2500) +2025-04-19 09:26:59,431 - train: [ INFO] - Eval : 17 Time: 0.254 (0.394) Loss: 1.7973 (1.7884) Acc@1: 53.1250 (53.2475)Acc@5: 78.1250 (77.8186) +2025-04-19 09:27:06,640 - train: [ INFO] - Eval : 17 Time: 0.071 (0.333) Loss: 3.8445 (1.7901) Acc@1: 50.0000 (53.3539)Acc@5: 50.0000 (78.2575) +2025-04-19 09:27:16,532 - train: [ INFO] - Train: 18 [ 0/461 ( 0%)] Loss: 3.267922 (3.2679) Loss_single: 2.544548 (2.5445) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.058s, 5.28/s (6.058s, 5.28/s) LR: 5.000e-03 Data: 5.247 (5.247) +2025-04-19 09:27:53,237 - train: [ INFO] - Train: 18 [ 50/461 ( 11%)] Loss: 3.873463 (3.5707) Loss_single: 3.118313 (2.8314) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.607s, 52.76/s (0.836s, 38.29/s) LR: 5.000e-03 Data: 0.000 (0.104) +2025-04-19 09:28:28,988 - train: [ INFO] - Train: 18 [ 100/461 ( 22%)] Loss: 3.868233 (3.6699) Loss_single: 2.973476 (2.8788) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 1.160s, 27.60/s (0.775s, 41.30/s) LR: 5.000e-03 Data: 0.000 (0.053) +2025-04-19 09:29:02,900 - train: [ INFO] - Train: 18 [ 150/461 ( 33%)] Loss: 3.558565 (3.6420) Loss_single: 2.794837 (2.8578) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.585s, 54.72/s (0.742s, 43.11/s) LR: 5.000e-03 Data: 0.000 (0.036) +2025-04-19 09:29:37,279 - train: [ INFO] - Train: 18 [ 200/461 ( 43%)] Loss: 3.625277 (3.6387) Loss_single: 2.887079 (2.8637) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.695s, 46.02/s (0.728s, 43.93/s) LR: 5.000e-03 Data: 0.001 (0.027) +2025-04-19 09:30:11,620 - train: [ INFO] - Train: 18 [ 250/461 ( 54%)] Loss: 3.560948 (3.6257) Loss_single: 2.832397 (2.8584) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.761s, 42.05/s (0.720s, 44.46/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 09:30:47,409 - train: [ INFO] - Train: 18 [ 300/461 ( 65%)] Loss: 4.163163 (3.7025) Loss_single: 3.167246 (2.9026) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (97.7679) Acc@5: 90.6250 (98.2143) Time: 0.828s, 38.64/s (0.719s, 44.52/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 09:31:22,643 - train: [ INFO] - Train: 18 [ 350/461 ( 76%)] Loss: 3.483876 (3.6752) Loss_single: 2.764672 (2.8853) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.0469) Acc@5: 100.0000 (98.4375) Time: 0.802s, 39.90/s (0.717s, 44.66/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 09:31:59,084 - train: [ INFO] - Train: 18 [ 400/461 ( 87%)] Loss: 3.547392 (3.6610) Loss_single: 2.832006 (2.8794) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.2639) Acc@5: 100.0000 (98.6111) Time: 0.677s, 47.27/s (0.718s, 44.58/s) LR: 5.000e-03 Data: 0.008 (0.014) +2025-04-19 09:32:32,005 - train: [ INFO] - Train: 18 [ 450/461 ( 98%)] Loss: 3.574079 (3.6523) Loss_single: 2.866893 (2.8781) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.7500) Time: 0.743s, 43.07/s (0.711s, 45.01/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:32:38,490 - train: [ INFO] - Train: 18 [ 460/461 (100%)] Loss: 3.510135 (3.6394) Loss_single: 2.788225 (2.8700) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.5795) Acc@5: 100.0000 (98.8636) Time: 0.695s, 46.04/s (0.710s, 45.09/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:32:44,444 - train: [ INFO] - Eval : 18 Time: 5.509 (5.509) Loss: 1.8360 (1.8360) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-19 09:32:57,558 - train: [ INFO] - Eval : 18 Time: 0.289 (0.365) Loss: 1.8362 (1.8266) Acc@1: 65.6250 (53.2475)Acc@5: 81.2500 (76.9608) +2025-04-19 09:33:04,244 - train: [ INFO] - Eval : 18 Time: 0.065 (0.309) Loss: 3.0843 (1.8416) Acc@1: 50.0000 (52.6214)Acc@5: 50.0000 (77.2167) +2025-04-19 09:33:13,423 - train: [ INFO] - Train: 19 [ 0/461 ( 0%)] Loss: 3.370380 (3.3704) Loss_single: 2.655162 (2.6552) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.208s, 6.14/s (5.208s, 6.14/s) LR: 5.000e-03 Data: 4.482 (4.482) +2025-04-19 09:33:47,207 - train: [ INFO] - Train: 19 [ 50/461 ( 11%)] Loss: 3.374659 (3.3725) Loss_single: 2.666821 (2.6610) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.693s, 46.18/s (0.763s, 41.96/s) LR: 5.000e-03 Data: 0.001 (0.089) +2025-04-19 09:34:21,066 - train: [ INFO] - Train: 19 [ 100/461 ( 22%)] Loss: 3.236012 (3.3270) Loss_single: 2.537131 (2.6197) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.659s, 48.53/s (0.720s, 44.46/s) LR: 5.000e-03 Data: 0.000 (0.045) +2025-04-19 09:34:55,728 - train: [ INFO] - Train: 19 [ 150/461 ( 33%)] Loss: 3.426269 (3.3518) Loss_single: 2.683277 (2.6356) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.867s, 36.92/s (0.710s, 45.05/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 09:35:29,720 - train: [ INFO] - Train: 19 [ 200/461 ( 43%)] Loss: 3.519286 (3.3853) Loss_single: 2.807690 (2.6700) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.655s, 48.87/s (0.702s, 45.56/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 09:36:02,135 - train: [ INFO] - Train: 19 [ 250/461 ( 54%)] Loss: 3.613440 (3.4233) Loss_single: 2.901217 (2.7085) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.661s, 48.44/s (0.691s, 46.28/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 09:36:35,606 - train: [ INFO] - Train: 19 [ 300/461 ( 65%)] Loss: 3.664028 (3.4577) Loss_single: 2.946713 (2.7426) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.624s, 51.25/s (0.688s, 46.54/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 09:37:09,520 - train: [ INFO] - Train: 19 [ 350/461 ( 76%)] Loss: 3.714161 (3.4898) Loss_single: 3.002819 (2.7751) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.745s, 42.94/s (0.686s, 46.64/s) LR: 5.000e-03 Data: 0.005 (0.014) +2025-04-19 09:37:45,688 - train: [ INFO] - Train: 19 [ 400/461 ( 87%)] Loss: 3.697937 (3.5129) Loss_single: 2.970193 (2.7968) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.576s, 55.59/s (0.691s, 46.34/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 09:38:20,094 - train: [ INFO] - Train: 19 [ 450/461 ( 98%)] Loss: 3.298456 (3.4915) Loss_single: 2.566093 (2.7737) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.610s, 52.50/s (0.690s, 46.37/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:38:26,756 - train: [ INFO] - Train: 19 [ 460/461 (100%)] Loss: 3.465129 (3.4891) Loss_single: 2.746953 (2.7713) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.511s, 62.65/s (0.690s, 46.40/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 09:38:33,407 - train: [ INFO] - Eval : 19 Time: 6.237 (6.237) Loss: 1.9666 (1.9666) Acc@1: 40.6250 (40.6250)Acc@5: 75.0000 (75.0000) +2025-04-19 09:38:45,953 - train: [ INFO] - Eval : 19 Time: 0.224 (0.368) Loss: 1.8715 (1.8644) Acc@1: 62.5000 (51.1029)Acc@5: 75.0000 (76.5319) +2025-04-19 09:38:53,594 - train: [ INFO] - Eval : 19 Time: 0.093 (0.322) Loss: 3.0868 (1.8804) Acc@1: 50.0000 (51.0023)Acc@5: 50.0000 (76.5227) +2025-04-19 09:39:02,625 - train: [ INFO] - Train: 20 [ 0/461 ( 0%)] Loss: 3.900748 (3.9007) Loss_single: 3.132719 (3.1327) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.934s, 6.49/s (4.934s, 6.49/s) LR: 5.000e-03 Data: 4.009 (4.009) +2025-04-19 09:39:36,448 - train: [ INFO] - Train: 20 [ 50/461 ( 11%)] Loss: 3.210500 (3.5556) Loss_single: 2.507071 (2.8199) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.696s, 45.96/s (0.759s, 42.17/s) LR: 5.000e-03 Data: 0.004 (0.079) +2025-04-19 09:40:09,011 - train: [ INFO] - Train: 20 [ 100/461 ( 22%)] Loss: 3.169667 (3.4270) Loss_single: 2.456501 (2.6988) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.637s, 50.22/s (0.705s, 45.40/s) LR: 5.000e-03 Data: 0.000 (0.040) +2025-04-19 09:40:42,680 - train: [ INFO] - Train: 20 [ 150/461 ( 33%)] Loss: 3.634691 (3.4789) Loss_single: 2.833322 (2.7324) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.584s, 54.83/s (0.694s, 46.10/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 09:41:16,760 - train: [ INFO] - Train: 20 [ 200/461 ( 43%)] Loss: 3.374378 (3.4580) Loss_single: 2.664552 (2.7188) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.575s, 55.67/s (0.691s, 46.34/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 09:41:49,735 - train: [ INFO] - Train: 20 [ 250/461 ( 54%)] Loss: 3.510047 (3.4667) Loss_single: 2.770988 (2.7275) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.668s, 47.94/s (0.684s, 46.78/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 09:42:24,289 - train: [ INFO] - Train: 20 [ 300/461 ( 65%)] Loss: 3.038565 (3.4055) Loss_single: 2.335673 (2.6715) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.623s, 51.33/s (0.685s, 46.71/s) LR: 5.000e-03 Data: 0.002 (0.014) +2025-04-19 09:42:54,710 - train: [ INFO] - Train: 20 [ 350/461 ( 76%)] Loss: 3.202094 (3.3801) Loss_single: 2.499599 (2.6501) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.772s, 41.46/s (0.674s, 47.48/s) LR: 5.000e-03 Data: 0.004 (0.012) +2025-04-19 09:43:26,649 - train: [ INFO] - Train: 20 [ 400/461 ( 87%)] Loss: 3.621579 (3.4069) Loss_single: 2.871050 (2.6746) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.590s, 54.26/s (0.669s, 47.80/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:43:58,822 - train: [ INFO] - Train: 20 [ 450/461 ( 98%)] Loss: 3.679858 (3.4342) Loss_single: 2.967687 (2.7039) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.630s, 50.76/s (0.666s, 48.01/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 09:44:05,022 - train: [ INFO] - Train: 20 [ 460/461 (100%)] Loss: 3.268947 (3.4192) Loss_single: 2.567071 (2.6915) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.736s, 43.48/s (0.665s, 48.09/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 09:44:10,208 - train: [ INFO] - Eval : 20 Time: 4.846 (4.846) Loss: 1.9969 (1.9969) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-19 09:44:23,708 - train: [ INFO] - Eval : 20 Time: 0.159 (0.360) Loss: 1.8947 (1.9007) Acc@1: 59.3750 (51.8382)Acc@5: 75.0000 (77.2672) +2025-04-19 09:44:30,460 - train: [ INFO] - Eval : 20 Time: 0.055 (0.306) Loss: 3.5805 (1.9175) Acc@1: 50.0000 (50.5783)Acc@5: 50.0000 (77.0625) +2025-04-19 09:44:39,689 - train: [ INFO] - Train: 21 [ 0/461 ( 0%)] Loss: 3.273484 (3.2735) Loss_single: 2.556193 (2.5562) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.521s, 5.80/s (5.521s, 5.80/s) LR: 5.000e-03 Data: 4.780 (4.780) +2025-04-19 09:45:10,631 - train: [ INFO] - Train: 21 [ 50/461 ( 11%)] Loss: 3.254451 (3.2640) Loss_single: 2.541785 (2.5490) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.612s, 52.28/s (0.713s, 44.85/s) LR: 5.000e-03 Data: 0.006 (0.100) +2025-04-19 09:45:41,977 - train: [ INFO] - Train: 21 [ 100/461 ( 22%)] Loss: 3.488227 (3.3387) Loss_single: 2.786325 (2.6281) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.569s, 56.24/s (0.669s, 47.82/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-19 09:46:19,013 - train: [ INFO] - Train: 21 [ 150/461 ( 33%)] Loss: 3.579334 (3.3989) Loss_single: 2.874239 (2.6896) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.591s, 54.15/s (0.692s, 46.21/s) LR: 5.000e-03 Data: 0.001 (0.034) +2025-04-19 09:46:53,304 - train: [ INFO] - Train: 21 [ 200/461 ( 43%)] Loss: 3.475479 (3.4142) Loss_single: 2.767394 (2.7052) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.571s, 56.01/s (0.690s, 46.36/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 09:47:26,252 - train: [ INFO] - Train: 21 [ 250/461 ( 54%)] Loss: 3.317160 (3.3980) Loss_single: 2.622167 (2.6914) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.698s, 45.83/s (0.684s, 46.80/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 09:47:59,544 - train: [ INFO] - Train: 21 [ 300/461 ( 65%)] Loss: 3.364683 (3.3933) Loss_single: 2.632567 (2.6830) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.678s, 47.19/s (0.680s, 47.03/s) LR: 5.000e-03 Data: 0.003 (0.018) +2025-04-19 09:48:34,690 - train: [ INFO] - Train: 21 [ 350/461 ( 76%)] Loss: 3.726121 (3.4349) Loss_single: 3.000955 (2.7227) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.550s, 58.18/s (0.683s, 46.82/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 09:49:07,374 - train: [ INFO] - Train: 21 [ 400/461 ( 87%)] Loss: 3.357679 (3.4263) Loss_single: 2.576796 (2.7065) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.564s, 56.76/s (0.680s, 47.09/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 09:49:40,702 - train: [ INFO] - Train: 21 [ 450/461 ( 98%)] Loss: 3.612259 (3.4449) Loss_single: 2.825030 (2.7183) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.761s, 42.02/s (0.678s, 47.20/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 09:49:47,453 - train: [ INFO] - Train: 21 [ 460/461 (100%)] Loss: 3.543470 (3.4538) Loss_single: 2.824735 (2.7280) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.756s, 42.35/s (0.678s, 47.21/s) LR: 5.000e-03 Data: 0.025 (0.012) +2025-04-19 09:49:53,241 - train: [ INFO] - Eval : 21 Time: 5.378 (5.378) Loss: 2.0261 (2.0261) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-19 09:50:06,877 - train: [ INFO] - Eval : 21 Time: 0.238 (0.373) Loss: 1.9621 (1.8897) Acc@1: 53.1250 (51.4706)Acc@5: 75.0000 (77.2672) +2025-04-19 09:50:14,385 - train: [ INFO] - Eval : 21 Time: 0.090 (0.323) Loss: 3.0740 (1.8991) Acc@1: 0.0000 (50.5783)Acc@5: 50.0000 (77.4094) +2025-04-19 09:50:23,305 - train: [ INFO] - Train: 22 [ 0/461 ( 0%)] Loss: 3.181329 (3.1813) Loss_single: 2.475126 (2.4751) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.498s, 5.82/s (5.498s, 5.82/s) LR: 5.000e-03 Data: 4.694 (4.694) +2025-04-19 09:50:57,894 - train: [ INFO] - Train: 22 [ 50/461 ( 11%)] Loss: 3.588313 (3.3848) Loss_single: 2.879588 (2.6774) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.740s, 43.22/s (0.785s, 40.78/s) LR: 5.000e-03 Data: 0.004 (0.093) +2025-04-19 09:51:28,971 - train: [ INFO] - Train: 22 [ 100/461 ( 22%)] Loss: 3.389965 (3.3865) Loss_single: 2.682369 (2.6790) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.603s, 53.10/s (0.703s, 45.51/s) LR: 5.000e-03 Data: 0.001 (0.047) +2025-04-19 09:52:00,963 - train: [ INFO] - Train: 22 [ 150/461 ( 33%)] Loss: 3.155594 (3.3288) Loss_single: 2.460384 (2.6244) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.784s, 40.82/s (0.682s, 46.93/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-19 09:52:36,927 - train: [ INFO] - Train: 22 [ 200/461 ( 43%)] Loss: 3.359861 (3.3350) Loss_single: 2.598485 (2.6192) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.816s, 39.20/s (0.691s, 46.33/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-19 09:53:11,195 - train: [ INFO] - Train: 22 [ 250/461 ( 54%)] Loss: 3.403286 (3.3464) Loss_single: 2.704008 (2.6333) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.815s, 39.27/s (0.689s, 46.42/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 09:53:44,610 - train: [ INFO] - Train: 22 [ 300/461 ( 65%)] Loss: 3.608054 (3.3838) Loss_single: 2.915969 (2.6737) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.690s, 46.36/s (0.686s, 46.68/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 09:54:17,808 - train: [ INFO] - Train: 22 [ 350/461 ( 76%)] Loss: 3.696637 (3.4229) Loss_single: 2.877728 (2.6992) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.6094) Time: 0.736s, 43.50/s (0.682s, 46.90/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 09:54:49,884 - train: [ INFO] - Train: 22 [ 400/461 ( 87%)] Loss: 3.340227 (3.4137) Loss_single: 2.649731 (2.6937) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.687s, 46.57/s (0.677s, 47.27/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 09:55:23,425 - train: [ INFO] - Train: 22 [ 450/461 ( 98%)] Loss: 3.549896 (3.4273) Loss_single: 2.849338 (2.7093) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.567s, 56.46/s (0.676s, 47.33/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:55:29,815 - train: [ INFO] - Train: 22 [ 460/461 (100%)] Loss: 4.103606 (3.4888) Loss_single: 3.212957 (2.7551) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (98.8636) Acc@5: 96.8750 (99.4318) Time: 0.662s, 48.36/s (0.675s, 47.39/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 09:55:34,466 - train: [ INFO] - Eval : 22 Time: 4.289 (4.289) Loss: 1.9968 (1.9968) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-19 09:55:47,640 - train: [ INFO] - Eval : 22 Time: 0.250 (0.342) Loss: 1.9586 (1.8943) Acc@1: 53.1250 (52.3284)Acc@5: 75.0000 (76.8382) +2025-04-19 09:55:55,353 - train: [ INFO] - Eval : 22 Time: 0.058 (0.307) Loss: 3.1810 (1.9077) Acc@1: 50.0000 (50.8867)Acc@5: 50.0000 (76.7926) +2025-04-19 09:56:04,622 - train: [ INFO] - Train: 23 [ 0/461 ( 0%)] Loss: 3.847893 (3.8479) Loss_single: 3.117740 (3.1177) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.533s, 5.78/s (5.533s, 5.78/s) LR: 5.000e-03 Data: 4.617 (4.617) +2025-04-19 09:56:36,774 - train: [ INFO] - Train: 23 [ 50/461 ( 11%)] Loss: 3.523985 (3.6859) Loss_single: 2.826900 (2.9723) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.581s, 55.07/s (0.737s, 43.41/s) LR: 5.000e-03 Data: 0.000 (0.092) +2025-04-19 09:57:10,816 - train: [ INFO] - Train: 23 [ 100/461 ( 22%)] Loss: 3.170280 (3.5141) Loss_single: 2.485441 (2.8100) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.853s, 37.51/s (0.709s, 45.16/s) LR: 5.000e-03 Data: 0.000 (0.047) +2025-04-19 09:57:43,421 - train: [ INFO] - Train: 23 [ 150/461 ( 33%)] Loss: 3.309030 (3.4628) Loss_single: 2.590676 (2.7552) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.572s, 55.97/s (0.689s, 46.42/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-19 09:58:17,992 - train: [ INFO] - Train: 23 [ 200/461 ( 43%)] Loss: 3.035401 (3.3773) Loss_single: 2.334287 (2.6710) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.719s, 44.49/s (0.689s, 46.42/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-19 09:58:51,269 - train: [ INFO] - Train: 23 [ 250/461 ( 54%)] Loss: 3.005875 (3.3154) Loss_single: 2.304755 (2.6100) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.747s, 42.85/s (0.684s, 46.76/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 09:59:25,538 - train: [ INFO] - Train: 23 [ 300/461 ( 65%)] Loss: 3.099770 (3.2846) Loss_single: 2.377264 (2.5767) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.630s, 50.76/s (0.684s, 46.77/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 09:59:56,340 - train: [ INFO] - Train: 23 [ 350/461 ( 76%)] Loss: 3.753016 (3.3432) Loss_single: 2.930430 (2.6209) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.820s, 39.01/s (0.674s, 47.45/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 10:00:30,330 - train: [ INFO] - Train: 23 [ 400/461 ( 87%)] Loss: 3.459146 (3.3560) Loss_single: 2.744787 (2.6347) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.565s, 56.65/s (0.675s, 47.42/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:01:05,808 - train: [ INFO] - Train: 23 [ 450/461 ( 98%)] Loss: 3.705762 (3.3910) Loss_single: 3.014156 (2.6726) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.824s, 38.84/s (0.679s, 47.16/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 10:01:12,376 - train: [ INFO] - Train: 23 [ 460/461 (100%)] Loss: 3.328316 (3.3853) Loss_single: 2.619650 (2.6678) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.601s, 53.27/s (0.678s, 47.20/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 10:01:18,403 - train: [ INFO] - Eval : 23 Time: 5.619 (5.619) Loss: 2.0824 (2.0824) Acc@1: 34.3750 (34.3750)Acc@5: 75.0000 (75.0000) +2025-04-19 10:01:32,213 - train: [ INFO] - Eval : 23 Time: 0.266 (0.381) Loss: 1.9615 (1.9117) Acc@1: 62.5000 (51.1029)Acc@5: 75.0000 (76.2868) +2025-04-19 10:01:40,070 - train: [ INFO] - Eval : 23 Time: 0.076 (0.333) Loss: 2.6425 (1.9234) Acc@1: 50.0000 (50.3855)Acc@5: 50.0000 (76.3685) +2025-04-19 10:01:49,539 - train: [ INFO] - Train: 24 [ 0/461 ( 0%)] Loss: 3.210778 (3.2108) Loss_single: 2.518312 (2.5183) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.843s, 5.48/s (5.843s, 5.48/s) LR: 5.000e-03 Data: 5.041 (5.041) +2025-04-19 10:02:25,980 - train: [ INFO] - Train: 24 [ 50/461 ( 11%)] Loss: 3.427584 (3.3192) Loss_single: 2.730572 (2.6244) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.695s, 46.07/s (0.828s, 38.67/s) LR: 5.000e-03 Data: 0.000 (0.100) +2025-04-19 10:02:59,672 - train: [ INFO] - Train: 24 [ 100/461 ( 22%)] Loss: 3.096246 (3.2449) Loss_single: 2.404520 (2.5511) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.623s, 51.32/s (0.750s, 42.65/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-19 10:03:34,615 - train: [ INFO] - Train: 24 [ 150/461 ( 33%)] Loss: 3.181630 (3.2291) Loss_single: 2.490749 (2.5360) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.818s, 39.14/s (0.733s, 43.68/s) LR: 5.000e-03 Data: 0.045 (0.035) +2025-04-19 10:04:07,163 - train: [ INFO] - Train: 24 [ 200/461 ( 43%)] Loss: 3.343192 (3.2519) Loss_single: 2.625623 (2.5540) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.358s, 89.43/s (0.712s, 44.95/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 10:04:41,288 - train: [ INFO] - Train: 24 [ 250/461 ( 54%)] Loss: 3.494213 (3.2923) Loss_single: 2.805955 (2.5960) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.634s, 50.50/s (0.706s, 45.34/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 10:05:14,592 - train: [ INFO] - Train: 24 [ 300/461 ( 65%)] Loss: 3.971069 (3.3892) Loss_single: 3.272268 (2.6926) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.700s, 45.70/s (0.699s, 45.79/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 10:05:47,739 - train: [ INFO] - Train: 24 [ 350/461 ( 76%)] Loss: 3.565014 (3.4112) Loss_single: 2.874563 (2.7153) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.577s, 55.46/s (0.693s, 46.15/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 10:06:21,362 - train: [ INFO] - Train: 24 [ 400/461 ( 87%)] Loss: 3.607524 (3.4330) Loss_single: 2.831095 (2.7282) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 96.8750 (99.6528) Time: 0.605s, 52.86/s (0.691s, 46.34/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 10:06:56,105 - train: [ INFO] - Train: 24 [ 450/461 ( 98%)] Loss: 3.454982 (3.4352) Loss_single: 2.763356 (2.7317) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.754s, 42.43/s (0.691s, 46.32/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:07:04,278 - train: [ INFO] - Train: 24 [ 460/461 (100%)] Loss: 3.261840 (3.4195) Loss_single: 2.555466 (2.7157) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.878s, 36.44/s (0.693s, 46.14/s) LR: 5.000e-03 Data: 0.010 (0.012) +2025-04-19 10:07:10,280 - train: [ INFO] - Eval : 24 Time: 5.385 (5.385) Loss: 1.8934 (1.8934) Acc@1: 53.1250 (53.1250)Acc@5: 81.2500 (81.2500) +2025-04-19 10:07:24,684 - train: [ INFO] - Eval : 24 Time: 0.312 (0.388) Loss: 1.8607 (1.8881) Acc@1: 56.2500 (53.1250)Acc@5: 78.1250 (77.2059) +2025-04-19 10:07:32,161 - train: [ INFO] - Eval : 24 Time: 0.057 (0.333) Loss: 2.9028 (1.9030) Acc@1: 50.0000 (51.7733)Acc@5: 50.0000 (76.2914) +2025-04-19 10:07:41,798 - train: [ INFO] - Train: 25 [ 0/461 ( 0%)] Loss: 3.540118 (3.5401) Loss_single: 2.776642 (2.7766) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 5.597s, 5.72/s (5.597s, 5.72/s) LR: 5.000e-03 Data: 4.862 (4.862) +2025-04-19 10:08:18,269 - train: [ INFO] - Train: 25 [ 50/461 ( 11%)] Loss: 3.208582 (3.3744) Loss_single: 2.504690 (2.6407) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.849s, 37.70/s (0.823s, 38.88/s) LR: 5.000e-03 Data: 0.000 (0.097) +2025-04-19 10:08:55,446 - train: [ INFO] - Train: 25 [ 100/461 ( 22%)] Loss: 3.088975 (3.2792) Loss_single: 2.392400 (2.5579) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.780s, 41.04/s (0.782s, 40.90/s) LR: 5.000e-03 Data: 0.000 (0.049) +2025-04-19 10:09:31,728 - train: [ INFO] - Train: 25 [ 150/461 ( 33%)] Loss: 3.280849 (3.2796) Loss_single: 2.587649 (2.5653) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.715s, 44.78/s (0.763s, 41.95/s) LR: 5.000e-03 Data: 0.008 (0.034) +2025-04-19 10:10:08,306 - train: [ INFO] - Train: 25 [ 200/461 ( 43%)] Loss: 3.370130 (3.2977) Loss_single: 2.678455 (2.5880) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.637s, 50.25/s (0.754s, 42.43/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 10:10:42,808 - train: [ INFO] - Train: 25 [ 250/461 ( 54%)] Loss: 3.274836 (3.2939) Loss_single: 2.493431 (2.5722) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (99.4792) Time: 0.647s, 49.46/s (0.741s, 43.17/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 10:11:17,819 - train: [ INFO] - Train: 25 [ 300/461 ( 65%)] Loss: 3.381765 (3.3065) Loss_single: 2.629375 (2.5804) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.6607) Acc@5: 100.0000 (99.5536) Time: 0.498s, 64.28/s (0.734s, 43.59/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 10:11:51,264 - train: [ INFO] - Train: 25 [ 350/461 ( 76%)] Loss: 3.321660 (3.3084) Loss_single: 2.539467 (2.5753) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (99.2188) Time: 0.615s, 52.07/s (0.725s, 44.17/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 10:12:26,100 - train: [ INFO] - Train: 25 [ 400/461 ( 87%)] Loss: 3.536615 (3.3337) Loss_single: 2.840002 (2.6047) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6111) Acc@5: 100.0000 (99.3056) Time: 0.589s, 54.31/s (0.721s, 44.39/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:13:00,228 - train: [ INFO] - Train: 25 [ 450/461 ( 98%)] Loss: 3.647356 (3.3651) Loss_single: 2.947925 (2.6390) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.739s, 43.33/s (0.716s, 44.67/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:13:07,364 - train: [ INFO] - Train: 25 [ 460/461 (100%)] Loss: 3.181682 (3.3484) Loss_single: 2.489573 (2.6254) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8636) Acc@5: 100.0000 (99.4318) Time: 0.586s, 54.57/s (0.716s, 44.67/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:13:12,557 - train: [ INFO] - Eval : 25 Time: 4.569 (4.569) Loss: 1.9517 (1.9517) Acc@1: 50.0000 (50.0000)Acc@5: 71.8750 (71.8750) +2025-04-19 10:13:23,846 - train: [ INFO] - Eval : 25 Time: 0.204 (0.311) Loss: 1.8167 (1.8797) Acc@1: 62.5000 (52.2672)Acc@5: 75.0000 (77.8799) +2025-04-19 10:13:29,636 - train: [ INFO] - Eval : 25 Time: 0.080 (0.264) Loss: 3.2835 (1.8944) Acc@1: 50.0000 (51.5420)Acc@5: 50.0000 (77.7564) +2025-04-19 10:13:38,739 - train: [ INFO] - Train: 26 [ 0/461 ( 0%)] Loss: 3.385718 (3.3857) Loss_single: 2.595061 (2.5951) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 5.606s, 5.71/s (5.606s, 5.71/s) LR: 5.000e-03 Data: 4.847 (4.847) +2025-04-19 10:14:12,196 - train: [ INFO] - Train: 26 [ 50/461 ( 11%)] Loss: 3.206723 (3.2962) Loss_single: 2.511662 (2.5534) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.690s, 46.35/s (0.765s, 41.86/s) LR: 5.000e-03 Data: 0.000 (0.097) +2025-04-19 10:14:46,643 - train: [ INFO] - Train: 26 [ 100/461 ( 22%)] Loss: 3.223022 (3.2718) Loss_single: 2.527157 (2.5446) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.586s, 54.60/s (0.726s, 44.06/s) LR: 5.000e-03 Data: 0.000 (0.050) +2025-04-19 10:15:20,612 - train: [ INFO] - Train: 26 [ 150/461 ( 33%)] Loss: 3.166764 (3.2456) Loss_single: 2.481664 (2.5289) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.782s, 40.92/s (0.710s, 45.05/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 10:15:53,140 - train: [ INFO] - Train: 26 [ 200/461 ( 43%)] Loss: 3.169403 (3.2303) Loss_single: 2.466522 (2.5164) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.541s, 59.19/s (0.695s, 46.05/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 10:16:25,720 - train: [ INFO] - Train: 26 [ 250/461 ( 54%)] Loss: 3.379676 (3.2552) Loss_single: 2.673548 (2.5426) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.676s, 47.33/s (0.686s, 46.65/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 10:16:59,189 - train: [ INFO] - Train: 26 [ 300/461 ( 65%)] Loss: 3.633385 (3.3092) Loss_single: 2.919531 (2.5964) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.587s, 54.49/s (0.683s, 46.86/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 10:17:33,001 - train: [ INFO] - Train: 26 [ 350/461 ( 76%)] Loss: 3.331450 (3.3120) Loss_single: 2.634414 (2.6012) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.606s, 52.80/s (0.682s, 46.94/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 10:18:03,184 - train: [ INFO] - Train: 26 [ 400/461 ( 87%)] Loss: 3.511503 (3.3342) Loss_single: 2.799193 (2.6232) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.543s, 58.90/s (0.672s, 47.63/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:18:36,213 - train: [ INFO] - Train: 26 [ 450/461 ( 98%)] Loss: 3.334938 (3.3343) Loss_single: 2.643867 (2.6253) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.760s, 42.09/s (0.670s, 47.73/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:18:43,197 - train: [ INFO] - Train: 26 [ 460/461 (100%)] Loss: 3.463927 (3.3460) Loss_single: 2.774795 (2.6389) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.768s, 41.65/s (0.671s, 47.69/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:18:48,316 - train: [ INFO] - Eval : 26 Time: 4.761 (4.761) Loss: 1.9584 (1.9584) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 10:19:01,954 - train: [ INFO] - Eval : 26 Time: 0.190 (0.361) Loss: 1.8777 (1.9089) Acc@1: 59.3750 (52.2672)Acc@5: 75.0000 (77.5123) +2025-04-19 10:19:09,770 - train: [ INFO] - Eval : 26 Time: 0.076 (0.320) Loss: 2.8212 (1.9282) Acc@1: 50.0000 (50.4626)Acc@5: 50.0000 (77.0239) +2025-04-19 10:19:19,924 - train: [ INFO] - Train: 27 [ 0/461 ( 0%)] Loss: 3.184779 (3.1848) Loss_single: 2.490891 (2.4909) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.579s, 5.74/s (5.579s, 5.74/s) LR: 5.000e-03 Data: 4.748 (4.748) +2025-04-19 10:20:00,488 - train: [ INFO] - Train: 27 [ 50/461 ( 11%)] Loss: 3.411792 (3.2983) Loss_single: 2.713349 (2.6021) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.792s, 40.42/s (0.903s, 35.43/s) LR: 5.000e-03 Data: 0.000 (0.094) +2025-04-19 10:20:40,757 - train: [ INFO] - Train: 27 [ 100/461 ( 22%)] Loss: 2.917460 (3.1713) Loss_single: 2.221643 (2.4753) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.786s, 40.72/s (0.854s, 37.48/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-19 10:21:19,774 - train: [ INFO] - Train: 27 [ 150/461 ( 33%)] Loss: 3.688254 (3.3006) Loss_single: 2.925236 (2.5878) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.774s, 41.34/s (0.829s, 38.61/s) LR: 5.000e-03 Data: 0.001 (0.032) +2025-04-19 10:21:59,757 - train: [ INFO] - Train: 27 [ 200/461 ( 43%)] Loss: 3.124024 (3.2653) Loss_single: 2.432850 (2.5568) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.676s, 47.31/s (0.821s, 38.96/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-19 10:22:43,416 - train: [ INFO] - Train: 27 [ 250/461 ( 54%)] Loss: 3.408600 (3.2892) Loss_single: 2.704574 (2.5814) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.708s, 45.22/s (0.831s, 38.50/s) LR: 5.000e-03 Data: 0.004 (0.020) +2025-04-19 10:23:26,776 - train: [ INFO] - Train: 27 [ 300/461 ( 65%)] Loss: 3.677746 (3.3447) Loss_single: 2.983511 (2.6389) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.594s, 53.84/s (0.837s, 38.23/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 10:24:07,196 - train: [ INFO] - Train: 27 [ 350/461 ( 76%)] Loss: 3.345841 (3.3448) Loss_single: 2.646667 (2.6398) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.585s, 54.69/s (0.833s, 38.42/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 10:24:47,349 - train: [ INFO] - Train: 27 [ 400/461 ( 87%)] Loss: 3.135496 (3.3216) Loss_single: 2.442030 (2.6179) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.672s, 47.59/s (0.829s, 38.60/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:25:28,193 - train: [ INFO] - Train: 27 [ 450/461 ( 98%)] Loss: 3.424789 (3.3319) Loss_single: 2.724961 (2.6286) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.838s, 38.20/s (0.827s, 38.67/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 10:25:35,532 - train: [ INFO] - Train: 27 [ 460/461 (100%)] Loss: 2.961983 (3.2983) Loss_single: 2.258459 (2.5949) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.903s, 35.44/s (0.825s, 38.77/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 10:25:40,700 - train: [ INFO] - Eval : 27 Time: 4.843 (4.843) Loss: 1.9308 (1.9308) Acc@1: 46.8750 (46.8750)Acc@5: 81.2500 (81.2500) +2025-04-19 10:25:53,605 - train: [ INFO] - Eval : 27 Time: 0.234 (0.348) Loss: 1.9636 (1.9406) Acc@1: 56.2500 (50.9804)Acc@5: 75.0000 (76.0417) +2025-04-19 10:26:01,202 - train: [ INFO] - Eval : 27 Time: 0.072 (0.309) Loss: 2.7848 (1.9507) Acc@1: 50.0000 (49.9229)Acc@5: 50.0000 (76.0601) +2025-04-19 10:26:11,416 - train: [ INFO] - Train: 28 [ 0/461 ( 0%)] Loss: 3.267337 (3.2673) Loss_single: 2.545724 (2.5457) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.982s, 5.35/s (5.982s, 5.35/s) LR: 5.000e-03 Data: 5.179 (5.179) +2025-04-19 10:26:52,706 - train: [ INFO] - Train: 28 [ 50/461 ( 11%)] Loss: 3.594593 (3.4310) Loss_single: 2.839602 (2.6927) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.697s, 45.93/s (0.925s, 34.59/s) LR: 5.000e-03 Data: 0.000 (0.103) +2025-04-19 10:27:32,405 - train: [ INFO] - Train: 28 [ 100/461 ( 22%)] Loss: 3.246476 (3.3695) Loss_single: 2.532017 (2.6391) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 1.005s, 31.85/s (0.860s, 37.23/s) LR: 5.000e-03 Data: 0.000 (0.052) +2025-04-19 10:28:14,025 - train: [ INFO] - Train: 28 [ 150/461 ( 33%)] Loss: 3.379778 (3.3720) Loss_single: 2.690587 (2.6520) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.706s, 45.31/s (0.850s, 37.64/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-19 10:28:54,759 - train: [ INFO] - Train: 28 [ 200/461 ( 43%)] Loss: 3.292974 (3.3562) Loss_single: 2.567356 (2.6351) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.806s, 39.72/s (0.841s, 38.06/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 10:29:34,285 - train: [ INFO] - Train: 28 [ 250/461 ( 54%)] Loss: 3.317902 (3.3498) Loss_single: 2.630154 (2.6342) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.696s, 45.94/s (0.831s, 38.53/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 10:30:15,335 - train: [ INFO] - Train: 28 [ 300/461 ( 65%)] Loss: 3.102317 (3.3145) Loss_single: 2.361341 (2.5953) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.699s, 45.80/s (0.829s, 38.61/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 10:30:55,748 - train: [ INFO] - Train: 28 [ 350/461 ( 76%)] Loss: 3.256860 (3.3073) Loss_single: 2.555646 (2.5903) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.758s, 42.21/s (0.826s, 38.76/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 10:31:36,474 - train: [ INFO] - Train: 28 [ 400/461 ( 87%)] Loss: 3.321855 (3.3089) Loss_single: 2.628757 (2.5946) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.962s, 33.27/s (0.824s, 38.83/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 10:32:18,299 - train: [ INFO] - Train: 28 [ 450/461 ( 98%)] Loss: 3.079650 (3.2860) Loss_single: 2.347997 (2.5699) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.719s, 44.48/s (0.825s, 38.78/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:32:26,347 - train: [ INFO] - Train: 28 [ 460/461 (100%)] Loss: 3.478240 (3.3035) Loss_single: 2.751047 (2.5864) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.807s, 39.67/s (0.825s, 38.80/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:32:32,028 - train: [ INFO] - Eval : 28 Time: 5.334 (5.334) Loss: 1.8462 (1.8462) Acc@1: 50.0000 (50.0000)Acc@5: 84.3750 (84.3750) +2025-04-19 10:32:45,277 - train: [ INFO] - Eval : 28 Time: 0.321 (0.364) Loss: 1.9339 (1.8899) Acc@1: 46.8750 (52.0833)Acc@5: 78.1250 (77.7574) +2025-04-19 10:32:52,386 - train: [ INFO] - Eval : 28 Time: 0.093 (0.313) Loss: 2.8374 (1.8950) Acc@1: 50.0000 (51.3107)Acc@5: 50.0000 (77.7949) +2025-04-19 10:33:01,972 - train: [ INFO] - Train: 29 [ 0/461 ( 0%)] Loss: 3.273845 (3.2738) Loss_single: 2.580293 (2.5803) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.383s, 5.94/s (5.383s, 5.94/s) LR: 5.000e-03 Data: 4.617 (4.617) +2025-04-19 10:33:43,762 - train: [ INFO] - Train: 29 [ 50/461 ( 11%)] Loss: 3.079873 (3.1769) Loss_single: 2.390693 (2.4855) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.174s, 27.26/s (0.924s, 34.65/s) LR: 5.000e-03 Data: 0.000 (0.091) +2025-04-19 10:34:23,428 - train: [ INFO] - Train: 29 [ 100/461 ( 22%)] Loss: 3.630825 (3.3282) Loss_single: 2.824734 (2.5986) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.645s, 49.65/s (0.858s, 37.29/s) LR: 5.000e-03 Data: 0.001 (0.047) +2025-04-19 10:35:04,508 - train: [ INFO] - Train: 29 [ 150/461 ( 33%)] Loss: 3.243194 (3.3069) Loss_single: 2.533152 (2.5822) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.873s, 36.67/s (0.846s, 37.85/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 10:35:44,932 - train: [ INFO] - Train: 29 [ 200/461 ( 43%)] Loss: 3.317482 (3.3090) Loss_single: 2.632638 (2.5923) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.576s, 55.59/s (0.836s, 38.28/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-19 10:36:25,964 - train: [ INFO] - Train: 29 [ 250/461 ( 54%)] Loss: 3.484733 (3.3383) Loss_single: 2.696876 (2.6097) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.771s, 41.49/s (0.833s, 38.43/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 10:37:06,296 - train: [ INFO] - Train: 29 [ 300/461 ( 65%)] Loss: 3.251101 (3.3259) Loss_single: 2.553231 (2.6017) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.1071) Time: 0.753s, 42.50/s (0.828s, 38.64/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 10:37:44,552 - train: [ INFO] - Train: 29 [ 350/461 ( 76%)] Loss: 3.268347 (3.3187) Loss_single: 2.502344 (2.5892) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8281) Acc@5: 96.8750 (98.8281) Time: 0.622s, 51.43/s (0.819s, 39.07/s) LR: 5.000e-03 Data: 0.003 (0.014) +2025-04-19 10:38:24,730 - train: [ INFO] - Train: 29 [ 400/461 ( 87%)] Loss: 3.597512 (3.3497) Loss_single: 2.865298 (2.6199) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.637s, 50.21/s (0.817s, 39.17/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:39:02,656 - train: [ INFO] - Train: 29 [ 450/461 ( 98%)] Loss: 3.493300 (3.3640) Loss_single: 2.806380 (2.6386) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.0625) Time: 0.588s, 54.45/s (0.810s, 39.49/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 10:39:10,041 - train: [ INFO] - Train: 29 [ 460/461 (100%)] Loss: 3.403141 (3.3676) Loss_single: 2.689287 (2.6432) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.1477) Time: 0.799s, 40.03/s (0.809s, 39.57/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 10:39:15,894 - train: [ INFO] - Eval : 29 Time: 5.493 (5.493) Loss: 2.0321 (2.0321) Acc@1: 40.6250 (40.6250)Acc@5: 84.3750 (84.3750) +2025-04-19 10:39:29,310 - train: [ INFO] - Eval : 29 Time: 0.293 (0.371) Loss: 1.9040 (1.9326) Acc@1: 62.5000 (51.5319)Acc@5: 78.1250 (76.1642) +2025-04-19 10:39:36,948 - train: [ INFO] - Eval : 29 Time: 0.073 (0.324) Loss: 3.1077 (1.9412) Acc@1: 0.0000 (50.6939)Acc@5: 50.0000 (76.2143) +2025-04-19 10:39:46,937 - train: [ INFO] - Train: 30 [ 0/461 ( 0%)] Loss: 2.920309 (2.9203) Loss_single: 2.218882 (2.2189) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.940s, 5.39/s (5.940s, 5.39/s) LR: 5.000e-03 Data: 5.136 (5.136) +2025-04-19 10:40:25,207 - train: [ INFO] - Train: 30 [ 50/461 ( 11%)] Loss: 3.265642 (3.0930) Loss_single: 2.573196 (2.3960) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.778s, 41.15/s (0.865s, 36.98/s) LR: 5.000e-03 Data: 0.000 (0.102) +2025-04-19 10:41:02,578 - train: [ INFO] - Train: 30 [ 100/461 ( 22%)] Loss: 3.230183 (3.1387) Loss_single: 2.538338 (2.4435) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.811s, 39.46/s (0.806s, 39.70/s) LR: 5.000e-03 Data: 0.001 (0.052) +2025-04-19 10:41:41,175 - train: [ INFO] - Train: 30 [ 150/461 ( 33%)] Loss: 3.306958 (3.1808) Loss_single: 2.609277 (2.4849) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.687s, 46.55/s (0.794s, 40.28/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-19 10:42:21,064 - train: [ INFO] - Train: 30 [ 200/461 ( 43%)] Loss: 2.989658 (3.1426) Loss_single: 2.302016 (2.4483) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.786s, 40.72/s (0.795s, 40.26/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 10:42:56,361 - train: [ INFO] - Train: 30 [ 250/461 ( 54%)] Loss: 3.310831 (3.1706) Loss_single: 2.576921 (2.4698) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.558s, 57.34/s (0.777s, 41.20/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 10:43:23,895 - train: [ INFO] - Train: 30 [ 300/461 ( 65%)] Loss: 3.243258 (3.1810) Loss_single: 2.474482 (2.4704) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.5536) Acc@5: 96.8750 (99.5536) Time: 0.521s, 61.39/s (0.739s, 43.30/s) LR: 5.000e-03 Data: 0.003 (0.018) +2025-04-19 10:43:56,004 - train: [ INFO] - Train: 30 [ 350/461 ( 76%)] Loss: 3.257895 (3.1906) Loss_single: 2.560174 (2.4817) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.621s, 51.53/s (0.725s, 44.14/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 10:44:35,995 - train: [ INFO] - Train: 30 [ 400/461 ( 87%)] Loss: 3.343582 (3.2076) Loss_single: 2.652508 (2.5006) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.670s, 47.77/s (0.734s, 43.59/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 10:45:13,110 - train: [ INFO] - Train: 30 [ 450/461 ( 98%)] Loss: 3.225767 (3.2094) Loss_single: 2.530177 (2.5036) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.784s, 40.83/s (0.735s, 43.54/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:45:21,757 - train: [ INFO] - Train: 30 [ 460/461 (100%)] Loss: 3.633976 (3.2480) Loss_single: 2.826781 (2.5330) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4318) Acc@5: 96.8750 (99.4318) Time: 0.685s, 46.71/s (0.738s, 43.38/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:45:27,232 - train: [ INFO] - Eval : 30 Time: 5.085 (5.085) Loss: 1.9455 (1.9455) Acc@1: 46.8750 (46.8750)Acc@5: 84.3750 (84.3750) +2025-04-19 10:45:41,232 - train: [ INFO] - Eval : 30 Time: 0.273 (0.374) Loss: 1.8427 (1.8896) Acc@1: 59.3750 (53.1250)Acc@5: 75.0000 (76.8995) +2025-04-19 10:45:48,881 - train: [ INFO] - Eval : 30 Time: 0.074 (0.326) Loss: 2.8433 (1.8963) Acc@1: 50.0000 (52.4672)Acc@5: 50.0000 (77.0625) +2025-04-19 10:45:59,013 - train: [ INFO] - Train: 31 [ 0/461 ( 0%)] Loss: 3.478415 (3.4784) Loss_single: 2.786016 (2.7860) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.879s, 5.44/s (5.879s, 5.44/s) LR: 5.000e-03 Data: 4.989 (4.989) +2025-04-19 10:46:40,974 - train: [ INFO] - Train: 31 [ 50/461 ( 11%)] Loss: 3.085022 (3.2817) Loss_single: 2.394756 (2.5904) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.760s, 42.09/s (0.936s, 34.19/s) LR: 5.000e-03 Data: 0.001 (0.098) +2025-04-19 10:47:22,700 - train: [ INFO] - Train: 31 [ 100/461 ( 22%)] Loss: 3.317948 (3.2938) Loss_single: 2.606206 (2.5957) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.783s, 40.86/s (0.885s, 36.15/s) LR: 5.000e-03 Data: 0.000 (0.050) +2025-04-19 10:48:03,564 - train: [ INFO] - Train: 31 [ 150/461 ( 33%)] Loss: 3.528376 (3.3524) Loss_single: 2.783805 (2.6427) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.956s, 33.46/s (0.862s, 37.12/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 10:48:44,041 - train: [ INFO] - Train: 31 [ 200/461 ( 43%)] Loss: 3.235216 (3.3290) Loss_single: 2.540024 (2.6222) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.963s, 33.23/s (0.849s, 37.71/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 10:49:26,293 - train: [ INFO] - Train: 31 [ 250/461 ( 54%)] Loss: 2.947599 (3.2654) Loss_single: 2.244744 (2.5593) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.822s, 38.93/s (0.848s, 37.75/s) LR: 5.000e-03 Data: 0.009 (0.021) +2025-04-19 10:50:07,911 - train: [ INFO] - Train: 31 [ 300/461 ( 65%)] Loss: 3.495238 (3.2983) Loss_single: 2.727451 (2.5833) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.831s, 38.51/s (0.845s, 37.87/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 10:50:50,397 - train: [ INFO] - Train: 31 [ 350/461 ( 76%)] Loss: 3.159357 (3.2809) Loss_single: 2.480353 (2.5704) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.695s, 46.03/s (0.845s, 37.85/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 10:51:30,036 - train: [ INFO] - Train: 31 [ 400/461 ( 87%)] Loss: 3.282495 (3.2811) Loss_single: 2.596993 (2.5734) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.604s, 53.02/s (0.839s, 38.15/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 10:52:09,644 - train: [ INFO] - Train: 31 [ 450/461 ( 98%)] Loss: 3.720548 (3.3250) Loss_single: 3.030483 (2.6191) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.879s, 36.42/s (0.833s, 38.40/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:52:17,498 - train: [ INFO] - Train: 31 [ 460/461 (100%)] Loss: 3.131702 (3.3074) Loss_single: 2.431826 (2.6021) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.706s, 45.30/s (0.832s, 38.45/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:52:23,618 - train: [ INFO] - Eval : 31 Time: 5.749 (5.749) Loss: 1.9871 (1.9871) Acc@1: 40.6250 (40.6250)Acc@5: 81.2500 (81.2500) +2025-04-19 10:52:36,663 - train: [ INFO] - Eval : 31 Time: 0.302 (0.369) Loss: 1.8558 (1.8717) Acc@1: 62.5000 (52.5735)Acc@5: 71.8750 (78.0025) +2025-04-19 10:52:44,056 - train: [ INFO] - Eval : 31 Time: 0.066 (0.319) Loss: 2.5706 (1.8822) Acc@1: 50.0000 (51.8504)Acc@5: 50.0000 (78.1419) +2025-04-19 10:52:54,044 - train: [ INFO] - Train: 32 [ 0/461 ( 0%)] Loss: 3.285013 (3.2850) Loss_single: 2.595976 (2.5960) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.008s, 5.33/s (6.008s, 5.33/s) LR: 5.000e-03 Data: 5.146 (5.146) +2025-04-19 10:53:35,275 - train: [ INFO] - Train: 32 [ 50/461 ( 11%)] Loss: 2.789610 (3.0373) Loss_single: 2.100912 (2.3484) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.45/s (0.925s, 34.61/s) LR: 5.000e-03 Data: 0.000 (0.102) +2025-04-19 10:54:15,726 - train: [ INFO] - Train: 32 [ 100/461 ( 22%)] Loss: 2.961624 (3.0121) Loss_single: 2.268425 (2.3218) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.797s, 40.16/s (0.866s, 36.94/s) LR: 5.000e-03 Data: 0.000 (0.052) +2025-04-19 10:54:57,718 - train: [ INFO] - Train: 32 [ 150/461 ( 33%)] Loss: 2.936615 (2.9932) Loss_single: 2.250943 (2.3041) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.852s, 37.54/s (0.857s, 37.35/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-19 10:55:37,999 - train: [ INFO] - Train: 32 [ 200/461 ( 43%)] Loss: 3.293986 (3.0534) Loss_single: 2.606492 (2.3645) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.736s, 43.50/s (0.844s, 37.93/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 10:56:18,857 - train: [ INFO] - Train: 32 [ 250/461 ( 54%)] Loss: 3.285300 (3.0920) Loss_single: 2.564352 (2.3978) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.716s, 44.71/s (0.838s, 38.18/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 10:56:58,713 - train: [ INFO] - Train: 32 [ 300/461 ( 65%)] Loss: 3.089195 (3.0916) Loss_single: 2.384500 (2.3959) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.501s, 63.88/s (0.831s, 38.50/s) LR: 5.000e-03 Data: 0.004 (0.018) +2025-04-19 10:57:36,517 - train: [ INFO] - Train: 32 [ 350/461 ( 76%)] Loss: 3.320652 (3.1202) Loss_single: 2.607036 (2.4223) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.713s, 44.90/s (0.820s, 39.02/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 10:58:17,332 - train: [ INFO] - Train: 32 [ 400/461 ( 87%)] Loss: 3.443992 (3.1562) Loss_single: 2.730777 (2.4566) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.811s, 39.45/s (0.819s, 39.05/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 10:58:57,376 - train: [ INFO] - Train: 32 [ 450/461 ( 98%)] Loss: 2.860806 (3.1267) Loss_single: 2.168654 (2.4278) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.683s, 46.83/s (0.817s, 39.16/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:59:04,540 - train: [ INFO] - Train: 32 [ 460/461 (100%)] Loss: 3.799029 (3.1878) Loss_single: 3.050695 (2.4844) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 96.8750 (99.7159) Time: 1.040s, 30.76/s (0.815s, 39.27/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 10:59:10,565 - train: [ INFO] - Eval : 32 Time: 5.641 (5.641) Loss: 2.0677 (2.0677) Acc@1: 34.3750 (34.3750)Acc@5: 87.5000 (87.5000) +2025-04-19 10:59:24,616 - train: [ INFO] - Eval : 32 Time: 0.282 (0.386) Loss: 1.8416 (1.8734) Acc@1: 53.1250 (53.6152)Acc@5: 75.0000 (78.0637) +2025-04-19 10:59:32,436 - train: [ INFO] - Eval : 32 Time: 0.070 (0.336) Loss: 2.7691 (1.8810) Acc@1: 50.0000 (52.9298)Acc@5: 50.0000 (78.2190) +2025-04-19 10:59:44,184 - train: [ INFO] - Train: 33 [ 0/461 ( 0%)] Loss: 3.418143 (3.4181) Loss_single: 2.633759 (2.6338) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 6.330s, 5.06/s (6.330s, 5.06/s) LR: 5.000e-03 Data: 5.690 (5.690) +2025-04-19 11:00:24,832 - train: [ INFO] - Train: 33 [ 50/461 ( 11%)] Loss: 3.211119 (3.3146) Loss_single: 2.445837 (2.5398) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 1.086s, 29.48/s (0.919s, 34.82/s) LR: 5.000e-03 Data: 0.000 (0.113) +2025-04-19 11:01:03,239 - train: [ INFO] - Train: 33 [ 100/461 ( 22%)] Loss: 3.438807 (3.3560) Loss_single: 2.637695 (2.5724) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (98.9583) Time: 0.667s, 47.97/s (0.843s, 37.94/s) LR: 5.000e-03 Data: 0.000 (0.057) +2025-04-19 11:01:42,748 - train: [ INFO] - Train: 33 [ 150/461 ( 33%)] Loss: 3.308387 (3.3441) Loss_single: 2.602795 (2.5800) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (97.6562) Acc@5: 100.0000 (99.2188) Time: 0.804s, 39.79/s (0.825s, 38.77/s) LR: 5.000e-03 Data: 0.000 (0.038) +2025-04-19 11:02:21,383 - train: [ INFO] - Train: 33 [ 200/461 ( 43%)] Loss: 3.284814 (3.3323) Loss_single: 2.602684 (2.5846) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.1250) Acc@5: 100.0000 (99.3750) Time: 0.851s, 37.62/s (0.812s, 39.41/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 11:03:02,476 - train: [ INFO] - Train: 33 [ 250/461 ( 54%)] Loss: 2.981858 (3.2739) Loss_single: 2.292980 (2.5360) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.4792) Time: 0.706s, 45.31/s (0.814s, 39.33/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-19 11:03:43,054 - train: [ INFO] - Train: 33 [ 300/461 ( 65%)] Loss: 3.231622 (3.2678) Loss_single: 2.507208 (2.5319) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.2143) Acc@5: 100.0000 (99.5536) Time: 0.768s, 41.66/s (0.813s, 39.36/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 11:04:25,659 - train: [ INFO] - Train: 33 [ 350/461 ( 76%)] Loss: 3.273470 (3.2685) Loss_single: 2.584805 (2.5385) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.6094) Time: 0.811s, 39.43/s (0.818s, 39.10/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 11:05:05,112 - train: [ INFO] - Train: 33 [ 400/461 ( 87%)] Loss: 3.366994 (3.2795) Loss_single: 2.677854 (2.5540) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6111) Acc@5: 100.0000 (99.6528) Time: 0.691s, 46.32/s (0.815s, 39.29/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 11:05:44,001 - train: [ INFO] - Train: 33 [ 450/461 ( 98%)] Loss: 2.917340 (3.2433) Loss_single: 2.182154 (2.5168) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.6875) Time: 0.689s, 46.47/s (0.810s, 39.49/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:05:51,492 - train: [ INFO] - Train: 33 [ 460/461 (100%)] Loss: 3.208918 (3.2401) Loss_single: 2.489980 (2.5143) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.5795) Acc@5: 100.0000 (99.7159) Time: 0.597s, 53.62/s (0.809s, 39.56/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:05:57,405 - train: [ INFO] - Eval : 33 Time: 5.539 (5.539) Loss: 2.0598 (2.0598) Acc@1: 43.7500 (43.7500)Acc@5: 81.2500 (81.2500) +2025-04-19 11:06:10,962 - train: [ INFO] - Eval : 33 Time: 0.274 (0.375) Loss: 1.9340 (1.8758) Acc@1: 62.5000 (53.0025)Acc@5: 71.8750 (78.6765) +2025-04-19 11:06:19,021 - train: [ INFO] - Eval : 33 Time: 0.092 (0.331) Loss: 2.8842 (1.8982) Acc@1: 50.0000 (51.6577)Acc@5: 50.0000 (78.4117) +2025-04-19 11:06:29,111 - train: [ INFO] - Train: 34 [ 0/461 ( 0%)] Loss: 2.785373 (2.7854) Loss_single: 2.101010 (2.1010) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.840s, 5.48/s (5.840s, 5.48/s) LR: 5.000e-03 Data: 5.185 (5.185) +2025-04-19 11:07:11,750 - train: [ INFO] - Train: 34 [ 50/461 ( 11%)] Loss: 3.336956 (3.0612) Loss_single: 2.659442 (2.3802) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.853s, 37.51/s (0.950s, 33.70/s) LR: 5.000e-03 Data: 0.000 (0.106) +2025-04-19 11:07:55,748 - train: [ INFO] - Train: 34 [ 100/461 ( 22%)] Loss: 3.103108 (3.0751) Loss_single: 2.397180 (2.3859) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.828s, 38.63/s (0.914s, 35.00/s) LR: 5.000e-03 Data: 0.000 (0.054) +2025-04-19 11:08:38,507 - train: [ INFO] - Train: 34 [ 150/461 ( 33%)] Loss: 3.156624 (3.0955) Loss_single: 2.450773 (2.4021) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.580s, 55.13/s (0.894s, 35.79/s) LR: 5.000e-03 Data: 0.000 (0.036) +2025-04-19 11:09:20,366 - train: [ INFO] - Train: 34 [ 200/461 ( 43%)] Loss: 3.289970 (3.1344) Loss_single: 2.526923 (2.4271) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 96.8750 (99.3750) Time: 0.833s, 38.41/s (0.880s, 36.38/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-19 11:10:03,880 - train: [ INFO] - Train: 34 [ 250/461 ( 54%)] Loss: 3.046554 (3.1198) Loss_single: 2.362565 (2.4163) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.786s, 40.72/s (0.877s, 36.47/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 11:10:45,708 - train: [ INFO] - Train: 34 [ 300/461 ( 65%)] Loss: 3.023094 (3.1060) Loss_single: 2.343026 (2.4058) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.788s, 40.62/s (0.870s, 36.76/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 11:11:28,634 - train: [ INFO] - Train: 34 [ 350/461 ( 76%)] Loss: 3.175725 (3.1147) Loss_single: 2.484204 (2.4156) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 1.135s, 28.20/s (0.869s, 36.84/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 11:12:10,562 - train: [ INFO] - Train: 34 [ 400/461 ( 87%)] Loss: 3.207304 (3.1250) Loss_single: 2.519278 (2.4272) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.893s, 35.85/s (0.865s, 37.01/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 11:12:50,639 - train: [ INFO] - Train: 34 [ 450/461 ( 98%)] Loss: 2.828798 (3.0954) Loss_single: 2.144622 (2.3989) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 1.053s, 30.38/s (0.857s, 37.32/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:12:58,867 - train: [ INFO] - Train: 34 [ 460/461 (100%)] Loss: 3.030817 (3.0895) Loss_single: 2.335851 (2.3932) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.818s, 39.11/s (0.857s, 37.36/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 11:13:06,506 - train: [ INFO] - Eval : 34 Time: 7.274 (7.274) Loss: 2.0547 (2.0547) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 11:13:20,850 - train: [ INFO] - Eval : 34 Time: 0.309 (0.424) Loss: 1.8041 (1.8827) Acc@1: 62.5000 (53.3088)Acc@5: 78.1250 (78.5539) +2025-04-19 11:13:28,647 - train: [ INFO] - Eval : 34 Time: 0.061 (0.359) Loss: 3.0539 (1.9031) Acc@1: 50.0000 (51.6962)Acc@5: 50.0000 (78.1804) +2025-04-19 11:13:39,723 - train: [ INFO] - Train: 35 [ 0/461 ( 0%)] Loss: 3.200356 (3.2004) Loss_single: 2.497457 (2.4975) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.996s, 5.34/s (5.996s, 5.34/s) LR: 5.000e-03 Data: 4.991 (4.991) +2025-04-19 11:14:24,240 - train: [ INFO] - Train: 35 [ 50/461 ( 11%)] Loss: 2.965712 (3.0830) Loss_single: 2.226197 (2.3618) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.821s, 39.00/s (0.989s, 32.37/s) LR: 5.000e-03 Data: 0.000 (0.099) +2025-04-19 11:15:06,627 - train: [ INFO] - Train: 35 [ 100/461 ( 22%)] Loss: 3.404088 (3.1901) Loss_single: 2.701720 (2.4751) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.068s, 29.97/s (0.918s, 34.85/s) LR: 5.000e-03 Data: 0.000 (0.050) +2025-04-19 11:15:47,850 - train: [ INFO] - Train: 35 [ 150/461 ( 33%)] Loss: 3.151625 (3.1804) Loss_single: 2.459817 (2.4713) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.798s, 40.09/s (0.887s, 36.09/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 11:16:30,523 - train: [ INFO] - Train: 35 [ 200/461 ( 43%)] Loss: 3.218907 (3.1881) Loss_single: 2.529871 (2.4830) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.980s, 32.66/s (0.878s, 36.45/s) LR: 5.000e-03 Data: 0.001 (0.026) +2025-04-19 11:17:12,666 - train: [ INFO] - Train: 35 [ 250/461 ( 54%)] Loss: 3.004702 (3.1576) Loss_single: 2.317767 (2.4555) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.650s, 49.24/s (0.871s, 36.76/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 11:17:54,435 - train: [ INFO] - Train: 35 [ 300/461 ( 65%)] Loss: 3.305858 (3.1787) Loss_single: 2.616466 (2.4785) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.861s, 37.17/s (0.864s, 37.02/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 11:18:37,489 - train: [ INFO] - Train: 35 [ 350/461 ( 76%)] Loss: 3.029356 (3.1601) Loss_single: 2.356156 (2.4632) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.922s, 34.70/s (0.864s, 37.05/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 11:19:19,362 - train: [ INFO] - Train: 35 [ 400/461 ( 87%)] Loss: 3.119192 (3.1555) Loss_single: 2.384986 (2.4545) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.862s, 37.14/s (0.860s, 37.20/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:19:55,156 - train: [ INFO] - Train: 35 [ 450/461 ( 98%)] Loss: 3.267918 (3.1668) Loss_single: 2.583890 (2.4674) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.019s, 31.39/s (0.844s, 37.91/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 11:20:03,727 - train: [ INFO] - Train: 35 [ 460/461 (100%)] Loss: 3.053632 (3.1565) Loss_single: 2.363826 (2.4580) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.734s, 43.58/s (0.844s, 37.90/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 11:20:10,277 - train: [ INFO] - Eval : 35 Time: 6.183 (6.183) Loss: 2.1163 (2.1163) Acc@1: 40.6250 (40.6250)Acc@5: 84.3750 (84.3750) +2025-04-19 11:20:23,947 - train: [ INFO] - Eval : 35 Time: 0.216 (0.390) Loss: 1.8680 (1.9170) Acc@1: 59.3750 (52.5735)Acc@5: 78.1250 (78.6152) +2025-04-19 11:20:31,912 - train: [ INFO] - Eval : 35 Time: 0.066 (0.340) Loss: 3.1477 (1.9317) Acc@1: 50.0000 (51.2336)Acc@5: 50.0000 (77.9491) +2025-04-19 11:20:42,144 - train: [ INFO] - Train: 36 [ 0/461 ( 0%)] Loss: 3.398562 (3.3986) Loss_single: 2.610815 (2.6108) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 6.318s, 5.06/s (6.318s, 5.06/s) LR: 5.000e-03 Data: 5.451 (5.451) +2025-04-19 11:21:22,957 - train: [ INFO] - Train: 36 [ 50/461 ( 11%)] Loss: 3.145881 (3.2722) Loss_single: 2.467597 (2.5392) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.846s, 37.84/s (0.923s, 34.68/s) LR: 5.000e-03 Data: 0.013 (0.108) +2025-04-19 11:22:03,186 - train: [ INFO] - Train: 36 [ 100/461 ( 22%)] Loss: 3.148311 (3.2309) Loss_single: 2.459813 (2.5127) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.738s, 43.33/s (0.863s, 37.07/s) LR: 5.000e-03 Data: 0.004 (0.055) +2025-04-19 11:22:43,441 - train: [ INFO] - Train: 36 [ 150/461 ( 33%)] Loss: 3.067304 (3.1900) Loss_single: 2.363711 (2.4755) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.668s, 47.93/s (0.843s, 37.96/s) LR: 5.000e-03 Data: 0.000 (0.037) +2025-04-19 11:23:24,842 - train: [ INFO] - Train: 36 [ 200/461 ( 43%)] Loss: 3.575017 (3.2670) Loss_single: 2.805537 (2.5415) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.742s, 43.14/s (0.839s, 38.15/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-19 11:24:06,084 - train: [ INFO] - Train: 36 [ 250/461 ( 54%)] Loss: 3.176629 (3.2520) Loss_single: 2.492504 (2.5333) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.516s, 61.97/s (0.836s, 38.29/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 11:24:33,608 - train: [ INFO] - Train: 36 [ 300/461 ( 65%)] Loss: 3.857041 (3.3384) Loss_single: 3.155571 (2.6222) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.587s, 54.55/s (0.788s, 40.60/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 11:25:16,853 - train: [ INFO] - Train: 36 [ 350/461 ( 76%)] Loss: 3.082442 (3.3064) Loss_single: 2.390183 (2.5932) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.711s, 45.02/s (0.799s, 40.06/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 11:25:59,145 - train: [ INFO] - Train: 36 [ 400/461 ( 87%)] Loss: 2.879771 (3.2590) Loss_single: 2.193640 (2.5488) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.718s, 44.55/s (0.805s, 39.77/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 11:26:40,853 - train: [ INFO] - Train: 36 [ 450/461 ( 98%)] Loss: 3.171833 (3.2503) Loss_single: 2.445360 (2.5385) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 100.0000 (99.6875) Time: 0.859s, 37.26/s (0.808s, 39.62/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:26:49,580 - train: [ INFO] - Train: 36 [ 460/461 (100%)] Loss: 3.354525 (3.2598) Loss_single: 2.646070 (2.5483) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.7159) Time: 1.045s, 30.61/s (0.809s, 39.56/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:26:55,596 - train: [ INFO] - Eval : 36 Time: 5.625 (5.625) Loss: 1.9419 (1.9419) Acc@1: 37.5000 (37.5000)Acc@5: 78.1250 (78.1250) +2025-04-19 11:27:08,976 - train: [ INFO] - Eval : 36 Time: 0.291 (0.373) Loss: 1.8241 (1.8950) Acc@1: 59.3750 (53.2475)Acc@5: 75.0000 (78.3088) +2025-04-19 11:27:16,684 - train: [ INFO] - Eval : 36 Time: 0.062 (0.326) Loss: 3.2865 (1.9167) Acc@1: 0.0000 (51.5806)Acc@5: 50.0000 (77.7564) +2025-04-19 11:27:27,958 - train: [ INFO] - Train: 37 [ 0/461 ( 0%)] Loss: 2.908086 (2.9081) Loss_single: 2.204576 (2.2046) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.954s, 4.60/s (6.954s, 4.60/s) LR: 5.000e-03 Data: 6.017 (6.017) +2025-04-19 11:28:12,252 - train: [ INFO] - Train: 37 [ 50/461 ( 11%)] Loss: 2.813424 (2.8608) Loss_single: 2.121000 (2.1628) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.805s, 39.77/s (1.004s, 31.89/s) LR: 5.000e-03 Data: 0.001 (0.119) +2025-04-19 11:28:54,931 - train: [ INFO] - Train: 37 [ 100/461 ( 22%)] Loss: 2.938321 (2.8866) Loss_single: 2.230050 (2.1852) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.243s, 25.75/s (0.929s, 34.46/s) LR: 5.000e-03 Data: 0.001 (0.061) +2025-04-19 11:29:35,905 - train: [ INFO] - Train: 37 [ 150/461 ( 33%)] Loss: 3.391119 (3.0127) Loss_single: 2.648524 (2.3010) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.703s, 45.52/s (0.892s, 35.88/s) LR: 5.000e-03 Data: 0.000 (0.041) +2025-04-19 11:30:21,768 - train: [ INFO] - Train: 37 [ 200/461 ( 43%)] Loss: 3.251005 (3.0604) Loss_single: 2.500561 (2.3409) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 96.8750 (99.3750) Time: 0.830s, 38.56/s (0.898s, 35.64/s) LR: 5.000e-03 Data: 0.001 (0.031) +2025-04-19 11:31:03,213 - train: [ INFO] - Train: 37 [ 250/461 ( 54%)] Loss: 3.039894 (3.0570) Loss_single: 2.354750 (2.3432) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 1.034s, 30.94/s (0.884s, 36.21/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 11:31:46,646 - train: [ INFO] - Train: 37 [ 300/461 ( 65%)] Loss: 3.103243 (3.0636) Loss_single: 2.414964 (2.3535) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.719s, 44.53/s (0.881s, 36.33/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 11:32:30,336 - train: [ INFO] - Train: 37 [ 350/461 ( 76%)] Loss: 3.318011 (3.0954) Loss_single: 2.616125 (2.3863) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.875s, 36.56/s (0.880s, 36.38/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 11:33:10,524 - train: [ INFO] - Train: 37 [ 400/461 ( 87%)] Loss: 3.157927 (3.1023) Loss_single: 2.476131 (2.3963) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.832s, 38.44/s (0.870s, 36.79/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 11:33:50,953 - train: [ INFO] - Train: 37 [ 450/461 ( 98%)] Loss: 3.194443 (3.1115) Loss_single: 2.510813 (2.4077) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.716s, 44.69/s (0.863s, 37.09/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 11:33:59,111 - train: [ INFO] - Train: 37 [ 460/461 (100%)] Loss: 3.506956 (3.1475) Loss_single: 2.820291 (2.4453) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.741s, 43.16/s (0.862s, 37.13/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 11:34:05,410 - train: [ INFO] - Eval : 37 Time: 5.925 (5.925) Loss: 2.0065 (2.0065) Acc@1: 37.5000 (37.5000)Acc@5: 81.2500 (81.2500) +2025-04-19 11:34:19,868 - train: [ INFO] - Eval : 37 Time: 0.282 (0.400) Loss: 1.8434 (1.8871) Acc@1: 68.7500 (52.7574)Acc@5: 78.1250 (78.4926) +2025-04-19 11:34:28,008 - train: [ INFO] - Eval : 37 Time: 0.062 (0.348) Loss: 3.2124 (1.9012) Acc@1: 0.0000 (51.9275)Acc@5: 50.0000 (77.9877) +2025-04-19 11:34:36,765 - train: [ INFO] - Train: 38 [ 0/461 ( 0%)] Loss: 3.166814 (3.1668) Loss_single: 2.475263 (2.4753) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.192s, 6.16/s (5.192s, 6.16/s) LR: 5.000e-03 Data: 4.444 (4.444) +2025-04-19 11:35:21,177 - train: [ INFO] - Train: 38 [ 50/461 ( 11%)] Loss: 3.023291 (3.0951) Loss_single: 2.330491 (2.4029) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.719s, 44.49/s (0.972s, 32.94/s) LR: 5.000e-03 Data: 0.000 (0.088) +2025-04-19 11:36:01,032 - train: [ INFO] - Train: 38 [ 100/461 ( 22%)] Loss: 3.743291 (3.3111) Loss_single: 2.937173 (2.5810) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.483s, 66.24/s (0.885s, 36.17/s) LR: 5.000e-03 Data: 0.001 (0.045) +2025-04-19 11:36:42,986 - train: [ INFO] - Train: 38 [ 150/461 ( 33%)] Loss: 3.033062 (3.2416) Loss_single: 2.338326 (2.5203) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 1.199s, 26.69/s (0.869s, 36.82/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-19 11:37:25,917 - train: [ INFO] - Train: 38 [ 200/461 ( 43%)] Loss: 3.364037 (3.2661) Loss_single: 2.668287 (2.5499) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.990s, 32.32/s (0.866s, 36.94/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 11:38:09,438 - train: [ INFO] - Train: 38 [ 250/461 ( 54%)] Loss: 3.816007 (3.3578) Loss_single: 3.034543 (2.6307) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.906s, 35.30/s (0.867s, 36.91/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 11:38:51,820 - train: [ INFO] - Train: 38 [ 300/461 ( 65%)] Loss: 3.007181 (3.3077) Loss_single: 2.328184 (2.5875) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.1071) Time: 0.672s, 47.59/s (0.863s, 37.07/s) LR: 5.000e-03 Data: 0.009 (0.016) +2025-04-19 11:39:34,793 - train: [ INFO] - Train: 38 [ 350/461 ( 76%)] Loss: 2.946945 (3.2626) Loss_single: 2.264145 (2.5471) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.725s, 44.13/s (0.863s, 37.10/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 11:40:17,290 - train: [ INFO] - Train: 38 [ 400/461 ( 87%)] Loss: 2.882173 (3.2203) Loss_single: 2.188764 (2.5072) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.3056) Time: 1.101s, 29.05/s (0.861s, 37.17/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 11:40:59,845 - train: [ INFO] - Train: 38 [ 450/461 ( 98%)] Loss: 3.140085 (3.2123) Loss_single: 2.455204 (2.5020) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.916s, 34.93/s (0.860s, 37.23/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 11:41:08,961 - train: [ INFO] - Train: 38 [ 460/461 (100%)] Loss: 3.023197 (3.1951) Loss_single: 2.333795 (2.4867) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.4318) Time: 0.849s, 37.67/s (0.861s, 37.18/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 11:41:16,075 - train: [ INFO] - Eval : 38 Time: 6.765 (6.765) Loss: 2.1600 (2.1600) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 11:41:29,692 - train: [ INFO] - Eval : 38 Time: 0.235 (0.399) Loss: 1.9748 (1.9200) Acc@1: 53.1250 (53.1250)Acc@5: 81.2500 (77.7574) +2025-04-19 11:41:37,141 - train: [ INFO] - Eval : 38 Time: 0.062 (0.339) Loss: 2.6230 (1.9307) Acc@1: 50.0000 (52.0046)Acc@5: 50.0000 (77.7564) +2025-04-19 11:41:47,150 - train: [ INFO] - Train: 39 [ 0/461 ( 0%)] Loss: 3.170997 (3.1710) Loss_single: 2.488612 (2.4886) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.867s, 5.45/s (5.867s, 5.45/s) LR: 5.000e-03 Data: 4.875 (4.875) +2025-04-19 11:42:29,148 - train: [ INFO] - Train: 39 [ 50/461 ( 11%)] Loss: 3.077402 (3.1242) Loss_single: 2.372520 (2.4306) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.008s, 31.73/s (0.937s, 34.15/s) LR: 5.000e-03 Data: 0.000 (0.097) +2025-04-19 11:43:10,707 - train: [ INFO] - Train: 39 [ 100/461 ( 22%)] Loss: 3.007019 (3.0851) Loss_single: 2.318426 (2.3932) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.791s, 40.45/s (0.884s, 36.19/s) LR: 5.000e-03 Data: 0.000 (0.049) +2025-04-19 11:43:53,991 - train: [ INFO] - Train: 39 [ 150/461 ( 33%)] Loss: 2.892361 (3.0369) Loss_single: 2.204539 (2.3460) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.664s, 48.16/s (0.878s, 36.46/s) LR: 5.000e-03 Data: 0.001 (0.033) +2025-04-19 11:44:35,892 - train: [ INFO] - Train: 39 [ 200/461 ( 43%)] Loss: 3.200331 (3.0696) Loss_single: 2.509182 (2.3787) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.773s, 41.38/s (0.867s, 36.89/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 11:45:19,597 - train: [ INFO] - Train: 39 [ 250/461 ( 54%)] Loss: 3.133976 (3.0803) Loss_single: 2.420731 (2.3857) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.782s, 40.94/s (0.868s, 36.85/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 11:46:00,382 - train: [ INFO] - Train: 39 [ 300/461 ( 65%)] Loss: 2.704410 (3.0266) Loss_single: 2.015901 (2.3328) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.650s, 49.21/s (0.859s, 37.23/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 11:46:42,128 - train: [ INFO] - Train: 39 [ 350/461 ( 76%)] Loss: 2.889913 (3.0096) Loss_single: 2.213509 (2.3179) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.845s, 37.87/s (0.856s, 37.39/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 11:47:25,547 - train: [ INFO] - Train: 39 [ 400/461 ( 87%)] Loss: 2.859543 (2.9929) Loss_single: 2.176340 (2.3022) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.768s, 41.65/s (0.857s, 37.33/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:48:07,628 - train: [ INFO] - Train: 39 [ 450/461 ( 98%)] Loss: 3.325414 (3.0261) Loss_single: 2.567407 (2.3287) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.992s, 32.27/s (0.855s, 37.41/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 11:48:15,348 - train: [ INFO] - Train: 39 [ 460/461 (100%)] Loss: 3.177633 (3.0399) Loss_single: 2.485399 (2.3430) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.688s, 46.48/s (0.853s, 37.50/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 11:48:21,473 - train: [ INFO] - Eval : 39 Time: 5.731 (5.731) Loss: 2.0552 (2.0552) Acc@1: 37.5000 (37.5000)Acc@5: 84.3750 (84.3750) +2025-04-19 11:48:35,885 - train: [ INFO] - Eval : 39 Time: 0.340 (0.396) Loss: 1.9441 (1.8980) Acc@1: 50.0000 (52.5735)Acc@5: 75.0000 (77.8799) +2025-04-19 11:48:43,084 - train: [ INFO] - Eval : 39 Time: 0.089 (0.334) Loss: 2.3148 (1.9121) Acc@1: 50.0000 (51.8119)Acc@5: 50.0000 (77.4480) +2025-04-19 11:48:53,094 - train: [ INFO] - Train: 40 [ 0/461 ( 0%)] Loss: 3.150948 (3.1509) Loss_single: 2.458973 (2.4590) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.640s, 5.67/s (5.640s, 5.67/s) LR: 5.000e-03 Data: 4.831 (4.831) +2025-04-19 11:49:31,873 - train: [ INFO] - Train: 40 [ 50/461 ( 11%)] Loss: 3.092241 (3.1216) Loss_single: 2.372159 (2.4156) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.494s, 64.72/s (0.869s, 36.80/s) LR: 5.000e-03 Data: 0.001 (0.096) +2025-04-19 11:50:13,554 - train: [ INFO] - Train: 40 [ 100/461 ( 22%)] Loss: 3.313493 (3.1856) Loss_single: 2.516414 (2.4492) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.464s, 68.93/s (0.851s, 37.61/s) LR: 5.000e-03 Data: 0.000 (0.049) +2025-04-19 11:50:54,743 - train: [ INFO] - Train: 40 [ 150/461 ( 33%)] Loss: 3.171713 (3.1821) Loss_single: 2.492103 (2.4599) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.965s, 33.16/s (0.841s, 38.03/s) LR: 5.000e-03 Data: 0.003 (0.033) +2025-04-19 11:51:36,484 - train: [ INFO] - Train: 40 [ 200/461 ( 43%)] Loss: 3.185367 (3.1828) Loss_single: 2.420495 (2.4520) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 96.8750 (98.7500) Time: 1.211s, 26.42/s (0.839s, 38.12/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 11:52:17,971 - train: [ INFO] - Train: 40 [ 250/461 ( 54%)] Loss: 3.037102 (3.1585) Loss_single: 2.352758 (2.4355) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.845s, 37.85/s (0.837s, 38.23/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 11:53:01,544 - train: [ INFO] - Train: 40 [ 300/461 ( 65%)] Loss: 3.046172 (3.1424) Loss_single: 2.356449 (2.4242) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.1071) Time: 0.804s, 39.78/s (0.842s, 37.99/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 11:53:44,213 - train: [ INFO] - Train: 40 [ 350/461 ( 76%)] Loss: 3.188838 (3.1482) Loss_single: 2.511612 (2.4351) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.661s, 48.43/s (0.844s, 37.92/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 11:54:23,572 - train: [ INFO] - Train: 40 [ 400/461 ( 87%)] Loss: 3.139128 (3.1472) Loss_single: 2.407754 (2.4321) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.3056) Time: 0.729s, 43.87/s (0.837s, 38.25/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 11:55:07,039 - train: [ INFO] - Train: 40 [ 450/461 ( 98%)] Loss: 3.311458 (3.1636) Loss_single: 2.602161 (2.4491) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.797s, 40.14/s (0.840s, 38.09/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 11:55:15,795 - train: [ INFO] - Train: 40 [ 460/461 (100%)] Loss: 3.119533 (3.1596) Loss_single: 2.435772 (2.4479) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.4318) Time: 0.835s, 38.30/s (0.841s, 38.06/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 11:55:22,300 - train: [ INFO] - Eval : 40 Time: 6.092 (6.092) Loss: 1.9346 (1.9346) Acc@1: 46.8750 (46.8750)Acc@5: 81.2500 (81.2500) +2025-04-19 11:55:36,074 - train: [ INFO] - Eval : 40 Time: 0.275 (0.390) Loss: 1.8825 (1.8982) Acc@1: 62.5000 (53.3088)Acc@5: 78.1250 (78.9216) +2025-04-19 11:55:44,051 - train: [ INFO] - Eval : 40 Time: 0.067 (0.340) Loss: 2.5024 (1.9091) Acc@1: 50.0000 (51.8504)Acc@5: 50.0000 (79.1056) +2025-04-19 11:55:56,016 - train: [ INFO] - Train: 41 [ 0/461 ( 0%)] Loss: 3.111473 (3.1115) Loss_single: 2.413622 (2.4136) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.804s, 4.70/s (6.804s, 4.70/s) LR: 5.000e-03 Data: 5.947 (5.947) +2025-04-19 11:56:39,005 - train: [ INFO] - Train: 41 [ 50/461 ( 11%)] Loss: 3.270086 (3.1908) Loss_single: 2.520988 (2.4673) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.764s, 41.89/s (0.975s, 32.81/s) LR: 5.000e-03 Data: 0.000 (0.118) +2025-04-19 11:57:21,659 - train: [ INFO] - Train: 41 [ 100/461 ( 22%)] Loss: 2.922731 (3.1014) Loss_single: 2.233481 (2.3894) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.938s, 34.12/s (0.914s, 35.01/s) LR: 5.000e-03 Data: 0.000 (0.060) +2025-04-19 11:58:06,548 - train: [ INFO] - Train: 41 [ 150/461 ( 33%)] Loss: 3.125752 (3.1075) Loss_single: 2.415064 (2.3958) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.901s, 35.50/s (0.908s, 35.23/s) LR: 5.000e-03 Data: 0.000 (0.041) +2025-04-19 11:58:46,732 - train: [ INFO] - Train: 41 [ 200/461 ( 43%)] Loss: 3.052032 (3.0964) Loss_single: 2.357464 (2.3881) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.937s, 34.16/s (0.882s, 36.29/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 11:59:29,733 - train: [ INFO] - Train: 41 [ 250/461 ( 54%)] Loss: 3.369655 (3.1420) Loss_single: 2.560963 (2.4169) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.745s, 42.95/s (0.877s, 36.48/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 12:00:11,528 - train: [ INFO] - Train: 41 [ 300/461 ( 65%)] Loss: 2.880028 (3.1045) Loss_single: 2.202326 (2.3863) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 1.180s, 27.12/s (0.870s, 36.78/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 12:00:53,829 - train: [ INFO] - Train: 41 [ 350/461 ( 76%)] Loss: 3.031720 (3.0954) Loss_single: 2.328439 (2.3790) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.801s, 39.96/s (0.866s, 36.93/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 12:01:38,628 - train: [ INFO] - Train: 41 [ 400/461 ( 87%)] Loss: 3.126301 (3.0989) Loss_single: 2.383829 (2.3796) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.920s, 34.80/s (0.870s, 36.79/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 12:02:17,734 - train: [ INFO] - Train: 41 [ 450/461 ( 98%)] Loss: 3.171190 (3.1061) Loss_single: 2.421432 (2.3838) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 100.0000 (100.0000) Time: 0.794s, 40.28/s (0.860s, 37.21/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:02:25,712 - train: [ INFO] - Train: 41 [ 460/461 (100%)] Loss: 3.243392 (3.1186) Loss_single: 2.494232 (2.3938) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (100.0000) Time: 0.848s, 37.75/s (0.858s, 37.28/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:02:32,394 - train: [ INFO] - Eval : 41 Time: 6.297 (6.297) Loss: 2.1073 (2.1073) Acc@1: 40.6250 (40.6250)Acc@5: 78.1250 (78.1250) +2025-04-19 12:02:46,300 - train: [ INFO] - Eval : 41 Time: 0.282 (0.396) Loss: 2.0888 (1.8893) Acc@1: 53.1250 (53.3088)Acc@5: 75.0000 (78.0025) +2025-04-19 12:02:53,909 - train: [ INFO] - Eval : 41 Time: 0.088 (0.339) Loss: 2.7607 (1.9005) Acc@1: 50.0000 (52.1588)Acc@5: 50.0000 (78.3732) +2025-04-19 12:03:06,476 - train: [ INFO] - Train: 42 [ 0/461 ( 0%)] Loss: 3.056961 (3.0570) Loss_single: 2.370455 (2.3705) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.597s, 4.85/s (6.597s, 4.85/s) LR: 5.000e-03 Data: 5.791 (5.791) +2025-04-19 12:03:49,453 - train: [ INFO] - Train: 42 [ 50/461 ( 11%)] Loss: 3.347011 (3.2020) Loss_single: 2.654933 (2.5127) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.773s, 41.41/s (0.970s, 32.98/s) LR: 5.000e-03 Data: 0.000 (0.114) +2025-04-19 12:04:30,983 - train: [ INFO] - Train: 42 [ 100/461 ( 22%)] Loss: 3.139827 (3.1813) Loss_single: 2.445693 (2.4904) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.722s, 44.34/s (0.901s, 35.53/s) LR: 5.000e-03 Data: 0.000 (0.059) +2025-04-19 12:05:11,424 - train: [ INFO] - Train: 42 [ 150/461 ( 33%)] Loss: 3.219723 (3.1909) Loss_single: 2.469784 (2.4852) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.884s, 36.20/s (0.870s, 36.79/s) LR: 5.000e-03 Data: 0.000 (0.039) +2025-04-19 12:05:50,050 - train: [ INFO] - Train: 42 [ 200/461 ( 43%)] Loss: 3.161777 (3.1851) Loss_single: 2.396268 (2.4674) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 96.8750 (99.3750) Time: 0.730s, 43.83/s (0.845s, 37.86/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-19 12:06:31,038 - train: [ INFO] - Train: 42 [ 250/461 ( 54%)] Loss: 2.812112 (3.1229) Loss_single: 2.133035 (2.4117) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.729s, 43.88/s (0.840s, 38.10/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 12:07:12,918 - train: [ INFO] - Train: 42 [ 300/461 ( 65%)] Loss: 3.231560 (3.1384) Loss_single: 2.456892 (2.4182) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.817s, 39.18/s (0.839s, 38.13/s) LR: 5.000e-03 Data: 0.002 (0.020) +2025-04-19 12:07:54,803 - train: [ INFO] - Train: 42 [ 350/461 ( 76%)] Loss: 3.218867 (3.1485) Loss_single: 2.430526 (2.4197) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8281) Acc@5: 96.8750 (99.2188) Time: 0.813s, 39.37/s (0.839s, 38.15/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 12:08:36,921 - train: [ INFO] - Train: 42 [ 400/461 ( 87%)] Loss: 2.824821 (3.1125) Loss_single: 2.141506 (2.3888) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.3056) Time: 0.811s, 39.47/s (0.839s, 38.14/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 12:09:20,393 - train: [ INFO] - Train: 42 [ 450/461 ( 98%)] Loss: 3.377130 (3.1390) Loss_single: 2.667524 (2.4167) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.3750) Time: 0.921s, 34.73/s (0.842s, 37.99/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:09:27,608 - train: [ INFO] - Train: 42 [ 460/461 (100%)] Loss: 2.962989 (3.1230) Loss_single: 2.275225 (2.4038) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.4318) Time: 0.462s, 69.33/s (0.840s, 38.12/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:09:33,706 - train: [ INFO] - Eval : 42 Time: 5.757 (5.757) Loss: 2.0625 (2.0625) Acc@1: 40.6250 (40.6250)Acc@5: 81.2500 (81.2500) +2025-04-19 12:09:46,975 - train: [ INFO] - Eval : 42 Time: 0.217 (0.373) Loss: 1.8324 (1.9127) Acc@1: 59.3750 (53.7377)Acc@5: 78.1250 (77.8186) +2025-04-19 12:09:54,365 - train: [ INFO] - Eval : 42 Time: 0.071 (0.322) Loss: 2.9835 (1.9237) Acc@1: 50.0000 (52.2745)Acc@5: 50.0000 (77.5636) +2025-04-19 12:10:05,860 - train: [ INFO] - Train: 43 [ 0/461 ( 0%)] Loss: 3.100519 (3.1005) Loss_single: 2.362463 (2.3625) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 6.854s, 4.67/s (6.854s, 4.67/s) LR: 5.000e-03 Data: 6.013 (6.013) +2025-04-19 12:10:46,529 - train: [ INFO] - Train: 43 [ 50/461 ( 11%)] Loss: 3.318018 (3.2093) Loss_single: 2.561873 (2.4622) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 0.610s, 52.46/s (0.930s, 34.41/s) LR: 5.000e-03 Data: 0.001 (0.119) +2025-04-19 12:11:27,977 - train: [ INFO] - Train: 43 [ 100/461 ( 22%)] Loss: 2.800857 (3.0731) Loss_single: 2.123421 (2.3493) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (97.9167) Acc@5: 100.0000 (100.0000) Time: 0.938s, 34.10/s (0.879s, 36.40/s) LR: 5.000e-03 Data: 0.000 (0.060) +2025-04-19 12:12:10,724 - train: [ INFO] - Train: 43 [ 150/461 ( 33%)] Loss: 3.040361 (3.0649) Loss_single: 2.356210 (2.3510) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.893s, 35.84/s (0.871s, 36.75/s) LR: 5.000e-03 Data: 0.000 (0.041) +2025-04-19 12:12:52,779 - train: [ INFO] - Train: 43 [ 200/461 ( 43%)] Loss: 3.118836 (3.0757) Loss_single: 2.355700 (2.3519) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.1250) Acc@5: 100.0000 (100.0000) Time: 0.770s, 41.58/s (0.863s, 37.08/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 12:13:34,116 - train: [ INFO] - Train: 43 [ 250/461 ( 54%)] Loss: 3.024499 (3.0672) Loss_single: 2.342425 (2.3503) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.804s, 39.79/s (0.855s, 37.41/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 12:14:14,520 - train: [ INFO] - Train: 43 [ 300/461 ( 65%)] Loss: 2.987886 (3.0559) Loss_single: 2.305445 (2.3439) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6607) Acc@5: 100.0000 (100.0000) Time: 0.801s, 39.93/s (0.847s, 37.77/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 12:14:56,074 - train: [ INFO] - Train: 43 [ 350/461 ( 76%)] Loss: 3.021924 (3.0516) Loss_single: 2.298598 (2.3383) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8281) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.46/s (0.845s, 37.88/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 12:15:37,159 - train: [ INFO] - Train: 43 [ 400/461 ( 87%)] Loss: 3.089562 (3.0558) Loss_single: 2.396897 (2.3448) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.801s, 39.96/s (0.842s, 38.02/s) LR: 5.000e-03 Data: 0.005 (0.016) +2025-04-19 12:16:20,444 - train: [ INFO] - Train: 43 [ 450/461 ( 98%)] Loss: 3.226902 (3.0729) Loss_single: 2.509520 (2.3613) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (100.0000) Time: 0.861s, 37.18/s (0.844s, 37.91/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:16:28,462 - train: [ INFO] - Train: 43 [ 460/461 (100%)] Loss: 2.985157 (3.0650) Loss_single: 2.290115 (2.3548) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (100.0000) Time: 0.913s, 35.05/s (0.843s, 37.95/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 12:16:34,038 - train: [ INFO] - Eval : 43 Time: 5.215 (5.215) Loss: 2.0523 (2.0523) Acc@1: 40.6250 (40.6250)Acc@5: 81.2500 (81.2500) +2025-04-19 12:16:47,386 - train: [ INFO] - Eval : 43 Time: 0.266 (0.364) Loss: 1.8840 (1.8806) Acc@1: 56.2500 (53.3701)Acc@5: 78.1250 (79.3505) +2025-04-19 12:16:55,256 - train: [ INFO] - Eval : 43 Time: 0.079 (0.322) Loss: 3.1813 (1.8935) Acc@1: 50.0000 (52.8142)Acc@5: 50.0000 (78.9900) +2025-04-19 12:17:05,698 - train: [ INFO] - Train: 44 [ 0/461 ( 0%)] Loss: 2.966125 (2.9661) Loss_single: 2.286140 (2.2861) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.000s, 5.33/s (6.000s, 5.33/s) LR: 5.000e-03 Data: 4.889 (4.889) +2025-04-19 12:17:44,603 - train: [ INFO] - Train: 44 [ 50/461 ( 11%)] Loss: 2.853490 (2.9098) Loss_single: 2.170408 (2.2283) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.771s, 41.48/s (0.878s, 36.43/s) LR: 5.000e-03 Data: 0.002 (0.097) +2025-04-19 12:18:24,252 - train: [ INFO] - Train: 44 [ 100/461 ( 22%)] Loss: 3.204661 (3.0081) Loss_single: 2.510402 (2.3223) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.758s, 42.20/s (0.835s, 38.31/s) LR: 5.000e-03 Data: 0.007 (0.049) +2025-04-19 12:19:05,740 - train: [ INFO] - Train: 44 [ 150/461 ( 33%)] Loss: 3.062930 (3.0218) Loss_single: 2.370288 (2.3343) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.797s, 40.15/s (0.833s, 38.42/s) LR: 5.000e-03 Data: 0.001 (0.034) +2025-04-19 12:19:46,660 - train: [ INFO] - Train: 44 [ 200/461 ( 43%)] Loss: 2.934272 (3.0043) Loss_single: 2.209904 (2.3094) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.852s, 37.56/s (0.829s, 38.61/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 12:20:27,844 - train: [ INFO] - Train: 44 [ 250/461 ( 54%)] Loss: 2.906182 (2.9879) Loss_single: 2.227699 (2.2958) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.841s, 38.06/s (0.828s, 38.67/s) LR: 5.000e-03 Data: 0.005 (0.021) +2025-04-19 12:21:09,312 - train: [ INFO] - Train: 44 [ 300/461 ( 65%)] Loss: 3.028786 (2.9938) Loss_single: 2.347590 (2.3032) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.787s, 40.66/s (0.828s, 38.67/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 12:21:49,319 - train: [ INFO] - Train: 44 [ 350/461 ( 76%)] Loss: 3.357330 (3.0392) Loss_single: 2.671747 (2.3493) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.959s, 33.38/s (0.823s, 38.86/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 12:22:30,745 - train: [ INFO] - Train: 44 [ 400/461 ( 87%)] Loss: 3.133402 (3.0497) Loss_single: 2.446467 (2.3601) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 1.062s, 30.13/s (0.824s, 38.85/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 12:23:11,442 - train: [ INFO] - Train: 44 [ 450/461 ( 98%)] Loss: 3.397771 (3.0845) Loss_single: 2.686280 (2.3927) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.805s, 39.77/s (0.823s, 38.90/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 12:23:20,080 - train: [ INFO] - Train: 44 [ 460/461 (100%)] Loss: 2.805812 (3.0592) Loss_single: 2.086352 (2.3648) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 1.014s, 31.55/s (0.823s, 38.87/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 12:23:26,404 - train: [ INFO] - Eval : 44 Time: 5.970 (5.970) Loss: 2.0340 (2.0340) Acc@1: 46.8750 (46.8750)Acc@5: 81.2500 (81.2500) +2025-04-19 12:23:40,436 - train: [ INFO] - Eval : 44 Time: 0.283 (0.392) Loss: 1.8776 (1.9169) Acc@1: 59.3750 (52.5735)Acc@5: 75.0000 (78.2475) +2025-04-19 12:23:48,351 - train: [ INFO] - Eval : 44 Time: 0.086 (0.340) Loss: 2.9649 (1.9311) Acc@1: 50.0000 (51.1180)Acc@5: 50.0000 (77.8720) +2025-04-19 12:23:59,254 - train: [ INFO] - Train: 45 [ 0/461 ( 0%)] Loss: 3.026524 (3.0265) Loss_single: 2.328193 (2.3282) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.034s, 5.30/s (6.034s, 5.30/s) LR: 5.000e-03 Data: 5.104 (5.104) +2025-04-19 12:24:42,212 - train: [ INFO] - Train: 45 [ 50/461 ( 11%)] Loss: 3.276932 (3.1517) Loss_single: 2.530985 (2.4296) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.850s, 37.66/s (0.959s, 33.38/s) LR: 5.000e-03 Data: 0.000 (0.101) +2025-04-19 12:25:25,029 - train: [ INFO] - Train: 45 [ 100/461 ( 22%)] Loss: 2.739551 (3.0143) Loss_single: 2.049173 (2.3028) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.843s, 37.95/s (0.907s, 35.27/s) LR: 5.000e-03 Data: 0.001 (0.051) +2025-04-19 12:26:05,940 - train: [ INFO] - Train: 45 [ 150/461 ( 33%)] Loss: 3.053051 (3.0240) Loss_single: 2.374678 (2.3208) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.624s, 51.32/s (0.877s, 36.47/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 12:26:47,480 - train: [ INFO] - Train: 45 [ 200/461 ( 43%)] Loss: 3.211861 (3.0616) Loss_single: 2.529555 (2.3625) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.924s, 34.65/s (0.865s, 36.98/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 12:27:29,773 - train: [ INFO] - Train: 45 [ 250/461 ( 54%)] Loss: 2.946006 (3.0423) Loss_single: 2.265109 (2.3463) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.712s, 44.94/s (0.861s, 37.16/s) LR: 5.000e-03 Data: 0.001 (0.021) +2025-04-19 12:28:07,608 - train: [ INFO] - Train: 45 [ 300/461 ( 65%)] Loss: 3.224042 (3.0683) Loss_single: 2.552030 (2.3757) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.610s, 52.45/s (0.844s, 37.93/s) LR: 5.000e-03 Data: 0.003 (0.018) +2025-04-19 12:28:45,413 - train: [ INFO] - Train: 45 [ 350/461 ( 76%)] Loss: 3.134722 (3.0766) Loss_single: 2.451868 (2.3852) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 1.010s, 31.67/s (0.831s, 38.51/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 12:29:25,548 - train: [ INFO] - Train: 45 [ 400/461 ( 87%)] Loss: 3.055808 (3.0743) Loss_single: 2.384493 (2.3851) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.802s, 39.92/s (0.827s, 38.69/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 12:30:07,901 - train: [ INFO] - Train: 45 [ 450/461 ( 98%)] Loss: 2.687542 (3.0356) Loss_single: 2.003680 (2.3470) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.780s, 41.02/s (0.829s, 38.59/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 12:30:16,448 - train: [ INFO] - Train: 45 [ 460/461 (100%)] Loss: 3.091005 (3.0406) Loss_single: 2.336658 (2.3460) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.567s, 56.47/s (0.830s, 38.57/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 12:30:21,862 - train: [ INFO] - Eval : 45 Time: 5.058 (5.058) Loss: 2.0544 (2.0544) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 12:30:36,129 - train: [ INFO] - Eval : 45 Time: 0.218 (0.379) Loss: 1.8829 (1.8889) Acc@1: 56.2500 (52.6348)Acc@5: 75.0000 (78.1250) +2025-04-19 12:30:44,331 - train: [ INFO] - Eval : 45 Time: 0.091 (0.336) Loss: 2.9206 (1.8959) Acc@1: 50.0000 (51.9275)Acc@5: 50.0000 (78.0648) +2025-04-19 12:30:54,222 - train: [ INFO] - Train: 46 [ 0/461 ( 0%)] Loss: 2.831533 (2.8315) Loss_single: 2.150925 (2.1509) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.649s, 5.66/s (5.649s, 5.66/s) LR: 5.000e-03 Data: 4.801 (4.801) +2025-04-19 12:31:36,775 - train: [ INFO] - Train: 46 [ 50/461 ( 11%)] Loss: 2.849167 (2.8404) Loss_single: 2.171161 (2.1610) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.47/s (0.943s, 33.93/s) LR: 5.000e-03 Data: 0.001 (0.095) +2025-04-19 12:32:19,392 - train: [ INFO] - Train: 46 [ 100/461 ( 22%)] Loss: 3.178234 (2.9530) Loss_single: 2.480435 (2.2675) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.040s, 30.77/s (0.897s, 35.68/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-19 12:32:56,582 - train: [ INFO] - Train: 46 [ 150/461 ( 33%)] Loss: 2.943479 (2.9506) Loss_single: 2.193357 (2.2490) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.779s, 41.10/s (0.846s, 37.85/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-19 12:33:38,020 - train: [ INFO] - Train: 46 [ 200/461 ( 43%)] Loss: 2.979177 (2.9563) Loss_single: 2.302623 (2.2597) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.793s, 40.35/s (0.841s, 38.05/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-19 12:34:18,959 - train: [ INFO] - Train: 46 [ 250/461 ( 54%)] Loss: 2.801891 (2.9306) Loss_single: 2.114724 (2.2355) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.830s, 38.54/s (0.836s, 38.27/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 12:35:02,020 - train: [ INFO] - Train: 46 [ 300/461 ( 65%)] Loss: 2.648927 (2.8903) Loss_single: 1.975949 (2.1985) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.842s, 37.99/s (0.840s, 38.09/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 12:35:44,156 - train: [ INFO] - Train: 46 [ 350/461 ( 76%)] Loss: 3.233622 (2.9333) Loss_single: 2.529005 (2.2398) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.722s, 44.31/s (0.840s, 38.08/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 12:36:25,762 - train: [ INFO] - Train: 46 [ 400/461 ( 87%)] Loss: 2.971603 (2.9375) Loss_single: 2.290141 (2.2454) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.759s, 42.18/s (0.839s, 38.14/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 12:37:09,334 - train: [ INFO] - Train: 46 [ 450/461 ( 98%)] Loss: 3.016781 (2.9454) Loss_single: 2.245371 (2.2454) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 96.8750 (99.6875) Time: 0.806s, 39.72/s (0.843s, 37.98/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 12:37:16,647 - train: [ INFO] - Train: 46 [ 460/461 (100%)] Loss: 2.765565 (2.9291) Loss_single: 2.086044 (2.2309) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.591s, 54.13/s (0.840s, 38.09/s) LR: 5.000e-03 Data: 0.003 (0.011) +2025-04-19 12:37:22,394 - train: [ INFO] - Eval : 46 Time: 5.375 (5.375) Loss: 1.9590 (1.9590) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 12:37:36,502 - train: [ INFO] - Eval : 46 Time: 0.315 (0.382) Loss: 1.8362 (1.8750) Acc@1: 62.5000 (53.6152)Acc@5: 71.8750 (77.3897) +2025-04-19 12:37:44,193 - train: [ INFO] - Eval : 46 Time: 0.083 (0.331) Loss: 2.5953 (1.8958) Acc@1: 50.0000 (51.8890)Acc@5: 50.0000 (77.3323) +2025-04-19 12:37:53,630 - train: [ INFO] - Train: 47 [ 0/461 ( 0%)] Loss: 3.328041 (3.3280) Loss_single: 2.498466 (2.4985) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 5.235s, 6.11/s (5.235s, 6.11/s) LR: 5.000e-03 Data: 4.345 (4.345) +2025-04-19 12:38:37,092 - train: [ INFO] - Train: 47 [ 50/461 ( 11%)] Loss: 2.912993 (3.1205) Loss_single: 2.219137 (2.3588) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 1.149s, 27.85/s (0.953s, 33.58/s) LR: 5.000e-03 Data: 0.000 (0.086) +2025-04-19 12:39:19,512 - train: [ INFO] - Train: 47 [ 100/461 ( 22%)] Loss: 2.803812 (3.0149) Loss_single: 2.122935 (2.2802) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.945s, 33.88/s (0.900s, 35.54/s) LR: 5.000e-03 Data: 0.000 (0.044) +2025-04-19 12:39:59,174 - train: [ INFO] - Train: 47 [ 150/461 ( 33%)] Loss: 2.892551 (2.9843) Loss_single: 2.190774 (2.2578) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.440s, 72.71/s (0.864s, 37.02/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-19 12:40:25,554 - train: [ INFO] - Train: 47 [ 200/461 ( 43%)] Loss: 3.116275 (3.0107) Loss_single: 2.434278 (2.2931) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.558s, 57.34/s (0.780s, 41.02/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 12:41:08,430 - train: [ INFO] - Train: 47 [ 250/461 ( 54%)] Loss: 3.118018 (3.0286) Loss_single: 2.434251 (2.3166) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.677s, 47.30/s (0.795s, 40.24/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 12:41:51,517 - train: [ INFO] - Train: 47 [ 300/461 ( 65%)] Loss: 3.073593 (3.0350) Loss_single: 2.334069 (2.3191) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.831s, 38.49/s (0.806s, 39.70/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-19 12:42:36,353 - train: [ INFO] - Train: 47 [ 350/461 ( 76%)] Loss: 2.967988 (3.0267) Loss_single: 2.285826 (2.3150) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.797s, 40.13/s (0.819s, 39.08/s) LR: 5.000e-03 Data: 0.003 (0.013) +2025-04-19 12:43:20,000 - train: [ INFO] - Train: 47 [ 400/461 ( 87%)] Loss: 3.075916 (3.0321) Loss_single: 2.392816 (2.3236) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.791s, 40.48/s (0.825s, 38.77/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 12:44:02,250 - train: [ INFO] - Train: 47 [ 450/461 ( 98%)] Loss: 2.719701 (3.0009) Loss_single: 2.043625 (2.2956) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.964s, 33.20/s (0.827s, 38.68/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 12:44:10,639 - train: [ INFO] - Train: 47 [ 460/461 (100%)] Loss: 3.315010 (3.0294) Loss_single: 2.624191 (2.3255) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 1.124s, 28.47/s (0.827s, 38.67/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 12:44:16,420 - train: [ INFO] - Eval : 47 Time: 5.407 (5.407) Loss: 1.9990 (1.9990) Acc@1: 37.5000 (37.5000)Acc@5: 84.3750 (84.3750) +2025-04-19 12:44:29,851 - train: [ INFO] - Eval : 47 Time: 0.213 (0.369) Loss: 1.7983 (1.8524) Acc@1: 56.2500 (54.0441)Acc@5: 81.2500 (78.8603) +2025-04-19 12:44:37,484 - train: [ INFO] - Eval : 47 Time: 0.064 (0.323) Loss: 2.5559 (1.8707) Acc@1: 50.0000 (52.5443)Acc@5: 50.0000 (79.0671) +2025-04-19 12:44:47,864 - train: [ INFO] - Train: 48 [ 0/461 ( 0%)] Loss: 2.776307 (2.7763) Loss_single: 2.087669 (2.0877) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.324s, 5.06/s (6.324s, 5.06/s) LR: 5.000e-03 Data: 5.663 (5.663) +2025-04-19 12:45:30,845 - train: [ INFO] - Train: 48 [ 50/461 ( 11%)] Loss: 3.132236 (2.9543) Loss_single: 2.440034 (2.2639) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.841s, 38.04/s (0.966s, 33.13/s) LR: 5.000e-03 Data: 0.001 (0.112) +2025-04-19 12:46:14,132 - train: [ INFO] - Train: 48 [ 100/461 ( 22%)] Loss: 3.178150 (3.0289) Loss_single: 2.494929 (2.3409) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.908s, 35.25/s (0.915s, 34.96/s) LR: 5.000e-03 Data: 0.000 (0.057) +2025-04-19 12:46:56,089 - train: [ INFO] - Train: 48 [ 150/461 ( 33%)] Loss: 3.200899 (3.0719) Loss_single: 2.526960 (2.3874) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.888s, 36.02/s (0.890s, 35.97/s) LR: 5.000e-03 Data: 0.001 (0.038) +2025-04-19 12:47:39,867 - train: [ INFO] - Train: 48 [ 200/461 ( 43%)] Loss: 3.134614 (3.0844) Loss_single: 2.254033 (2.3607) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (98.7500) Acc@5: 93.7500 (98.7500) Time: 1.211s, 26.42/s (0.886s, 36.13/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 12:48:24,897 - train: [ INFO] - Train: 48 [ 250/461 ( 54%)] Loss: 3.339657 (3.1270) Loss_single: 2.538577 (2.3904) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (97.9167) Acc@5: 100.0000 (98.9583) Time: 1.067s, 30.00/s (0.888s, 36.02/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-19 12:49:07,826 - train: [ INFO] - Train: 48 [ 300/461 ( 65%)] Loss: 3.362206 (3.1606) Loss_single: 2.655296 (2.4282) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.2143) Acc@5: 100.0000 (99.1071) Time: 0.716s, 44.67/s (0.883s, 36.23/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 12:49:51,371 - train: [ INFO] - Train: 48 [ 350/461 ( 76%)] Loss: 3.043048 (3.1459) Loss_single: 2.336189 (2.4167) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.2188) Time: 1.109s, 28.85/s (0.881s, 36.31/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 12:50:32,776 - train: [ INFO] - Train: 48 [ 400/461 ( 87%)] Loss: 3.282298 (3.1610) Loss_single: 2.600552 (2.4371) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6111) Acc@5: 100.0000 (99.3056) Time: 0.740s, 43.24/s (0.874s, 36.59/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 12:51:14,450 - train: [ INFO] - Train: 48 [ 450/461 ( 98%)] Loss: 2.907785 (3.1357) Loss_single: 2.224501 (2.4159) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 1.017s, 31.46/s (0.870s, 36.79/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 12:51:22,788 - train: [ INFO] - Train: 48 [ 460/461 (100%)] Loss: 3.091925 (3.1317) Loss_single: 2.306862 (2.4060) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8636) Acc@5: 100.0000 (99.4318) Time: 1.057s, 30.27/s (0.869s, 36.83/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 12:51:27,990 - train: [ INFO] - Eval : 48 Time: 4.853 (4.853) Loss: 1.9315 (1.9315) Acc@1: 40.6250 (40.6250)Acc@5: 81.2500 (81.2500) +2025-04-19 12:51:41,948 - train: [ INFO] - Eval : 48 Time: 0.287 (0.369) Loss: 1.8783 (1.8942) Acc@1: 59.3750 (53.4314)Acc@5: 78.1250 (77.4510) +2025-04-19 12:51:50,219 - train: [ INFO] - Eval : 48 Time: 0.099 (0.330) Loss: 2.5267 (1.9066) Acc@1: 50.0000 (52.4287)Acc@5: 50.0000 (77.9491) +2025-04-19 12:51:59,917 - train: [ INFO] - Train: 49 [ 0/461 ( 0%)] Loss: 3.070242 (3.0702) Loss_single: 2.307834 (2.3078) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 4.919s, 6.50/s (4.919s, 6.50/s) LR: 5.000e-03 Data: 4.053 (4.053) +2025-04-19 12:52:45,510 - train: [ INFO] - Train: 49 [ 50/461 ( 11%)] Loss: 2.619864 (2.8451) Loss_single: 1.936185 (2.1220) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.843s, 37.94/s (0.989s, 32.34/s) LR: 5.000e-03 Data: 0.000 (0.081) +2025-04-19 12:53:27,209 - train: [ INFO] - Train: 49 [ 100/461 ( 22%)] Loss: 2.980683 (2.8903) Loss_single: 2.289476 (2.1778) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 1.382s, 23.15/s (0.911s, 35.11/s) LR: 5.000e-03 Data: 0.000 (0.041) +2025-04-19 12:54:11,376 - train: [ INFO] - Train: 49 [ 150/461 ( 33%)] Loss: 3.088932 (2.9399) Loss_single: 2.343817 (2.2193) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.871s, 36.72/s (0.902s, 35.49/s) LR: 5.000e-03 Data: 0.004 (0.028) +2025-04-19 12:54:54,519 - train: [ INFO] - Train: 49 [ 200/461 ( 43%)] Loss: 2.805007 (2.9129) Loss_single: 2.116326 (2.1987) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.740s, 43.27/s (0.892s, 35.89/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 12:55:36,781 - train: [ INFO] - Train: 49 [ 250/461 ( 54%)] Loss: 2.922108 (2.9145) Loss_single: 2.244684 (2.2064) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 1.372s, 23.33/s (0.882s, 36.28/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 12:56:17,884 - train: [ INFO] - Train: 49 [ 300/461 ( 65%)] Loss: 3.258744 (2.9637) Loss_single: 2.565734 (2.2577) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.628s, 50.96/s (0.872s, 36.70/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 12:57:01,953 - train: [ INFO] - Train: 49 [ 350/461 ( 76%)] Loss: 3.143421 (2.9861) Loss_single: 2.463737 (2.2835) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.910s, 35.18/s (0.873s, 36.65/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-19 12:57:43,496 - train: [ INFO] - Train: 49 [ 400/461 ( 87%)] Loss: 2.808617 (2.9664) Loss_single: 2.128733 (2.2663) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.947s, 33.79/s (0.868s, 36.88/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 12:58:26,519 - train: [ INFO] - Train: 49 [ 450/461 ( 98%)] Loss: 3.060648 (2.9758) Loss_single: 2.381176 (2.2778) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.864s, 37.04/s (0.867s, 36.93/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 12:58:34,661 - train: [ INFO] - Train: 49 [ 460/461 (100%)] Loss: 2.819645 (2.9616) Loss_single: 2.142145 (2.2654) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.691s, 46.34/s (0.865s, 36.98/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 12:58:40,138 - train: [ INFO] - Eval : 49 Time: 5.138 (5.138) Loss: 1.9364 (1.9364) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-19 12:58:54,350 - train: [ INFO] - Eval : 49 Time: 0.227 (0.379) Loss: 1.8638 (1.8974) Acc@1: 59.3750 (53.9828)Acc@5: 78.1250 (78.0025) +2025-04-19 12:59:01,979 - train: [ INFO] - Eval : 49 Time: 0.065 (0.329) Loss: 2.9368 (1.8995) Acc@1: 50.0000 (53.0069)Acc@5: 50.0000 (78.3346) +2025-04-19 12:59:10,923 - train: [ INFO] - Train: 50 [ 0/461 ( 0%)] Loss: 2.960346 (2.9603) Loss_single: 2.262454 (2.2625) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.213s, 6.14/s (5.213s, 6.14/s) LR: 5.000e-03 Data: 4.212 (4.212) +2025-04-19 12:59:55,070 - train: [ INFO] - Train: 50 [ 50/461 ( 11%)] Loss: 3.118554 (3.0395) Loss_single: 2.348044 (2.3052) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (98.4375) Time: 0.895s, 35.74/s (0.967s, 33.11/s) LR: 5.000e-03 Data: 0.000 (0.084) +2025-04-19 13:00:37,276 - train: [ INFO] - Train: 50 [ 100/461 ( 22%)] Loss: 3.361137 (3.1467) Loss_single: 2.590559 (2.4004) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.9167) Acc@5: 100.0000 (98.9583) Time: 0.708s, 45.22/s (0.905s, 35.37/s) LR: 5.000e-03 Data: 0.000 (0.043) +2025-04-19 13:01:19,827 - train: [ INFO] - Train: 50 [ 150/461 ( 33%)] Loss: 3.097543 (3.1344) Loss_single: 2.387447 (2.3971) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.2188) Time: 1.074s, 29.81/s (0.887s, 36.09/s) LR: 5.000e-03 Data: 0.001 (0.029) +2025-04-19 13:02:02,720 - train: [ INFO] - Train: 50 [ 200/461 ( 43%)] Loss: 3.082507 (3.1240) Loss_single: 2.381559 (2.3940) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 1.051s, 30.46/s (0.879s, 36.40/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 13:02:48,344 - train: [ INFO] - Train: 50 [ 250/461 ( 54%)] Loss: 3.068270 (3.1147) Loss_single: 2.310085 (2.3800) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (98.9583) Time: 0.815s, 39.27/s (0.885s, 36.14/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 13:03:32,685 - train: [ INFO] - Train: 50 [ 300/461 ( 65%)] Loss: 3.008844 (3.0996) Loss_single: 2.271428 (2.3645) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.2143) Acc@5: 100.0000 (99.1071) Time: 1.038s, 30.83/s (0.885s, 36.14/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 13:04:15,424 - train: [ INFO] - Train: 50 [ 350/461 ( 76%)] Loss: 3.366144 (3.1329) Loss_single: 2.679921 (2.4039) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.722s, 44.34/s (0.881s, 36.34/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 13:05:00,721 - train: [ INFO] - Train: 50 [ 400/461 ( 87%)] Loss: 2.817111 (3.0978) Loss_single: 2.145051 (2.3752) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6111) Acc@5: 100.0000 (99.3056) Time: 0.839s, 38.15/s (0.884s, 36.21/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:05:42,843 - train: [ INFO] - Train: 50 [ 450/461 ( 98%)] Loss: 3.233117 (3.1114) Loss_single: 2.485640 (2.3862) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.3750) Time: 1.039s, 30.80/s (0.879s, 36.40/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 13:05:50,918 - train: [ INFO] - Train: 50 [ 460/461 (100%)] Loss: 3.487461 (3.1455) Loss_single: 2.787558 (2.4227) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.5795) Acc@5: 100.0000 (99.4318) Time: 0.472s, 67.86/s (0.877s, 36.47/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 13:05:56,426 - train: [ INFO] - Eval : 50 Time: 5.130 (5.130) Loss: 1.8996 (1.8996) Acc@1: 59.3750 (59.3750)Acc@5: 84.3750 (84.3750) +2025-04-19 13:06:10,386 - train: [ INFO] - Eval : 50 Time: 0.249 (0.374) Loss: 1.8931 (1.8736) Acc@1: 56.2500 (54.1054)Acc@5: 71.8750 (78.2475) +2025-04-19 13:06:18,521 - train: [ INFO] - Eval : 50 Time: 0.083 (0.332) Loss: 2.4859 (1.8829) Acc@1: 50.0000 (53.3153)Acc@5: 50.0000 (78.2961) +2025-04-19 13:06:29,312 - train: [ INFO] - Train: 51 [ 0/461 ( 0%)] Loss: 2.855382 (2.8554) Loss_single: 2.181492 (2.1815) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.971s, 5.36/s (5.971s, 5.36/s) LR: 5.000e-03 Data: 5.082 (5.082) +2025-04-19 13:07:12,123 - train: [ INFO] - Train: 51 [ 50/461 ( 11%)] Loss: 2.786402 (2.8209) Loss_single: 2.113085 (2.1473) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.843s, 37.97/s (0.955s, 33.51/s) LR: 5.000e-03 Data: 0.000 (0.101) +2025-04-19 13:07:51,004 - train: [ INFO] - Train: 51 [ 100/461 ( 22%)] Loss: 3.456415 (3.0327) Loss_single: 2.649227 (2.3146) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.512s, 62.55/s (0.866s, 36.93/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-19 13:08:29,456 - train: [ INFO] - Train: 51 [ 150/461 ( 33%)] Loss: 3.006866 (3.0263) Loss_single: 2.317158 (2.3152) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 1.327s, 24.11/s (0.834s, 38.38/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 13:09:11,477 - train: [ INFO] - Train: 51 [ 200/461 ( 43%)] Loss: 2.794887 (2.9800) Loss_single: 2.121048 (2.2764) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.725s, 44.13/s (0.835s, 38.33/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 13:09:52,633 - train: [ INFO] - Train: 51 [ 250/461 ( 54%)] Loss: 3.054872 (2.9925) Loss_single: 2.365583 (2.2913) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.817s, 39.18/s (0.832s, 38.45/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 13:10:31,253 - train: [ INFO] - Train: 51 [ 300/461 ( 65%)] Loss: 2.787160 (2.9631) Loss_single: 2.105324 (2.2647) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.684s, 46.75/s (0.822s, 38.93/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 13:11:12,807 - train: [ INFO] - Train: 51 [ 350/461 ( 76%)] Loss: 2.774105 (2.9395) Loss_single: 2.099336 (2.2440) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 1.107s, 28.90/s (0.823s, 38.88/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 13:11:56,100 - train: [ INFO] - Train: 51 [ 400/461 ( 87%)] Loss: 2.862944 (2.9310) Loss_single: 2.188635 (2.2379) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.708s, 45.20/s (0.828s, 38.64/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 13:12:34,759 - train: [ INFO] - Train: 51 [ 450/461 ( 98%)] Loss: 3.012780 (2.9392) Loss_single: 2.329719 (2.2471) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.698s, 45.86/s (0.822s, 38.93/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:12:42,300 - train: [ INFO] - Train: 51 [ 460/461 (100%)] Loss: 2.682658 (2.9159) Loss_single: 2.001805 (2.2248) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.631s, 50.67/s (0.820s, 39.00/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:12:46,976 - train: [ INFO] - Eval : 51 Time: 4.305 (4.305) Loss: 1.8635 (1.8635) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 13:13:00,261 - train: [ INFO] - Eval : 51 Time: 0.168 (0.345) Loss: 1.8769 (1.8676) Acc@1: 50.0000 (53.2475)Acc@5: 78.1250 (79.2892) +2025-04-19 13:13:07,940 - train: [ INFO] - Eval : 51 Time: 0.084 (0.308) Loss: 2.5024 (1.8807) Acc@1: 50.0000 (52.7371)Acc@5: 50.0000 (79.2984) +2025-04-19 13:13:17,812 - train: [ INFO] - Train: 52 [ 0/461 ( 0%)] Loss: 2.857202 (2.8572) Loss_single: 2.171954 (2.1720) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.406s, 5.92/s (5.406s, 5.92/s) LR: 5.000e-03 Data: 4.413 (4.413) +2025-04-19 13:14:00,620 - train: [ INFO] - Train: 52 [ 50/461 ( 11%)] Loss: 2.985147 (2.9212) Loss_single: 2.298373 (2.2352) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.824s, 38.85/s (0.944s, 33.90/s) LR: 5.000e-03 Data: 0.000 (0.087) +2025-04-19 13:14:39,960 - train: [ INFO] - Train: 52 [ 100/461 ( 22%)] Loss: 2.852107 (2.8982) Loss_single: 2.146008 (2.2054) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.842s, 38.02/s (0.865s, 36.98/s) LR: 5.000e-03 Data: 0.006 (0.045) +2025-04-19 13:15:21,227 - train: [ INFO] - Train: 52 [ 150/461 ( 33%)] Loss: 2.831432 (2.8815) Loss_single: 2.151681 (2.1920) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.653s, 49.00/s (0.852s, 37.58/s) LR: 5.000e-03 Data: 0.001 (0.030) +2025-04-19 13:16:03,589 - train: [ INFO] - Train: 52 [ 200/461 ( 43%)] Loss: 3.076870 (2.9206) Loss_single: 2.399255 (2.2335) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.734s, 43.60/s (0.850s, 37.64/s) LR: 5.000e-03 Data: 0.005 (0.023) +2025-04-19 13:16:46,861 - train: [ INFO] - Train: 52 [ 250/461 ( 54%)] Loss: 2.950096 (2.9255) Loss_single: 2.268853 (2.2394) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.756s, 42.30/s (0.853s, 37.53/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 13:17:28,174 - train: [ INFO] - Train: 52 [ 300/461 ( 65%)] Loss: 3.031546 (2.9406) Loss_single: 2.347749 (2.2548) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.868s, 36.86/s (0.848s, 37.73/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 13:18:10,720 - train: [ INFO] - Train: 52 [ 350/461 ( 76%)] Loss: 2.968019 (2.9441) Loss_single: 2.219598 (2.2504) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.943s, 33.95/s (0.848s, 37.72/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 13:18:52,527 - train: [ INFO] - Train: 52 [ 400/461 ( 87%)] Loss: 2.668783 (2.9135) Loss_single: 1.991110 (2.2216) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.803s, 39.83/s (0.847s, 37.79/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 13:19:37,784 - train: [ INFO] - Train: 52 [ 450/461 ( 98%)] Loss: 2.885950 (2.9107) Loss_single: 2.201964 (2.2197) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 1.354s, 23.64/s (0.853s, 37.51/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 13:19:46,528 - train: [ INFO] - Train: 52 [ 460/461 (100%)] Loss: 2.937180 (2.9131) Loss_single: 2.252202 (2.2226) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.931s, 34.39/s (0.853s, 37.50/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 13:19:52,835 - train: [ INFO] - Eval : 52 Time: 5.923 (5.923) Loss: 1.9701 (1.9701) Acc@1: 43.7500 (43.7500)Acc@5: 81.2500 (81.2500) +2025-04-19 13:20:05,917 - train: [ INFO] - Eval : 52 Time: 0.326 (0.373) Loss: 1.7370 (1.8742) Acc@1: 65.6250 (53.7990)Acc@5: 81.2500 (78.6152) +2025-04-19 13:20:14,389 - train: [ INFO] - Eval : 52 Time: 0.068 (0.335) Loss: 2.7556 (1.8805) Acc@1: 50.0000 (53.0069)Acc@5: 50.0000 (78.8743) +2025-04-19 13:20:23,670 - train: [ INFO] - Train: 53 [ 0/461 ( 0%)] Loss: 2.976391 (2.9764) Loss_single: 2.254433 (2.2544) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.516s, 5.80/s (5.516s, 5.80/s) LR: 5.000e-03 Data: 4.481 (4.481) +2025-04-19 13:21:07,434 - train: [ INFO] - Train: 53 [ 50/461 ( 11%)] Loss: 2.643788 (2.8101) Loss_single: 1.969267 (2.1118) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.949s, 33.73/s (0.964s, 33.19/s) LR: 5.000e-03 Data: 0.006 (0.089) +2025-04-19 13:21:50,693 - train: [ INFO] - Train: 53 [ 100/461 ( 22%)] Loss: 2.876140 (2.8321) Loss_single: 2.187404 (2.1370) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.986s, 32.45/s (0.914s, 35.01/s) LR: 5.000e-03 Data: 0.000 (0.045) +2025-04-19 13:22:35,452 - train: [ INFO] - Train: 53 [ 150/461 ( 33%)] Loss: 2.923187 (2.8549) Loss_single: 2.248852 (2.1650) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.308s, 24.47/s (0.907s, 35.26/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 13:23:17,052 - train: [ INFO] - Train: 53 [ 200/461 ( 43%)] Loss: 3.060106 (2.8959) Loss_single: 2.342225 (2.2004) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.755s, 42.36/s (0.888s, 36.02/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 13:23:56,629 - train: [ INFO] - Train: 53 [ 250/461 ( 54%)] Loss: 2.949541 (2.9049) Loss_single: 2.271295 (2.2122) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.920s, 34.77/s (0.869s, 36.84/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 13:24:38,501 - train: [ INFO] - Train: 53 [ 300/461 ( 65%)] Loss: 2.817237 (2.8923) Loss_single: 2.137557 (2.2016) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.016s, 31.51/s (0.863s, 37.07/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 13:25:22,167 - train: [ INFO] - Train: 53 [ 350/461 ( 76%)] Loss: 2.928928 (2.8969) Loss_single: 2.165135 (2.1970) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6094) Acc@5: 96.8750 (99.6094) Time: 1.041s, 30.73/s (0.864s, 37.02/s) LR: 5.000e-03 Data: 0.002 (0.014) +2025-04-19 13:26:02,799 - train: [ INFO] - Train: 53 [ 400/461 ( 87%)] Loss: 3.002290 (2.9086) Loss_single: 2.320696 (2.2108) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.651s, 49.15/s (0.858s, 37.31/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:26:46,354 - train: [ INFO] - Train: 53 [ 450/461 ( 98%)] Loss: 2.786457 (2.8964) Loss_single: 2.098709 (2.1996) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.692s, 46.24/s (0.859s, 37.26/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 13:26:54,557 - train: [ INFO] - Train: 53 [ 460/461 (100%)] Loss: 2.860619 (2.8932) Loss_single: 2.188841 (2.1986) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.825s, 38.79/s (0.858s, 37.30/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 13:27:00,101 - train: [ INFO] - Eval : 53 Time: 5.181 (5.181) Loss: 1.9908 (1.9908) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 13:27:13,920 - train: [ INFO] - Eval : 53 Time: 0.248 (0.373) Loss: 1.8864 (1.8565) Acc@1: 59.3750 (54.0441)Acc@5: 78.1250 (78.9828) +2025-04-19 13:27:21,952 - train: [ INFO] - Eval : 53 Time: 0.103 (0.330) Loss: 2.7271 (1.8661) Acc@1: 50.0000 (52.9684)Acc@5: 50.0000 (79.1827) +2025-04-19 13:27:30,930 - train: [ INFO] - Train: 54 [ 0/461 ( 0%)] Loss: 2.818661 (2.8187) Loss_single: 2.120224 (2.1202) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.804s, 6.66/s (4.804s, 6.66/s) LR: 5.000e-03 Data: 3.875 (3.875) +2025-04-19 13:28:16,422 - train: [ INFO] - Train: 54 [ 50/461 ( 11%)] Loss: 2.930056 (2.8744) Loss_single: 2.228940 (2.1746) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.106s, 28.94/s (0.984s, 32.51/s) LR: 5.000e-03 Data: 0.004 (0.077) +2025-04-19 13:28:58,261 - train: [ INFO] - Train: 54 [ 100/461 ( 22%)] Loss: 2.726141 (2.8250) Loss_single: 2.020253 (2.1231) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.841s, 38.06/s (0.910s, 35.15/s) LR: 5.000e-03 Data: 0.000 (0.040) +2025-04-19 13:29:42,460 - train: [ INFO] - Train: 54 [ 150/461 ( 33%)] Loss: 2.919769 (2.8487) Loss_single: 2.228601 (2.1495) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.860s, 37.19/s (0.901s, 35.50/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 13:30:22,826 - train: [ INFO] - Train: 54 [ 200/461 ( 43%)] Loss: 3.015722 (2.8821) Loss_single: 2.317739 (2.1832) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.734s, 43.61/s (0.877s, 36.47/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 13:31:04,382 - train: [ INFO] - Train: 54 [ 250/461 ( 54%)] Loss: 3.106961 (2.9196) Loss_single: 2.389812 (2.2176) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.784s, 40.80/s (0.868s, 36.88/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 13:31:46,154 - train: [ INFO] - Train: 54 [ 300/461 ( 65%)] Loss: 3.177571 (2.9564) Loss_single: 2.505338 (2.2587) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.846s, 37.84/s (0.862s, 37.12/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 13:32:28,621 - train: [ INFO] - Train: 54 [ 350/461 ( 76%)] Loss: 3.092552 (2.9734) Loss_single: 2.375093 (2.2732) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.932s, 34.33/s (0.860s, 37.21/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:33:13,157 - train: [ INFO] - Train: 54 [ 400/461 ( 87%)] Loss: 3.120456 (2.9898) Loss_single: 2.442499 (2.2921) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.019s, 31.40/s (0.864s, 37.05/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 13:33:54,670 - train: [ INFO] - Train: 54 [ 450/461 ( 98%)] Loss: 2.818799 (2.9727) Loss_single: 2.138907 (2.2767) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.919s, 34.81/s (0.860s, 37.22/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 13:34:03,387 - train: [ INFO] - Train: 54 [ 460/461 (100%)] Loss: 3.095046 (2.9838) Loss_single: 2.407183 (2.2886) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.906s, 35.32/s (0.860s, 37.21/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 13:34:09,129 - train: [ INFO] - Eval : 54 Time: 5.362 (5.362) Loss: 1.8886 (1.8886) Acc@1: 43.7500 (43.7500)Acc@5: 87.5000 (87.5000) +2025-04-19 13:34:23,145 - train: [ INFO] - Eval : 54 Time: 0.236 (0.380) Loss: 1.7559 (1.8573) Acc@1: 68.7500 (54.9632)Acc@5: 81.2500 (80.8824) +2025-04-19 13:34:30,802 - train: [ INFO] - Eval : 54 Time: 0.072 (0.330) Loss: 3.0579 (1.8810) Acc@1: 50.0000 (53.7008)Acc@5: 50.0000 (79.9537) +2025-04-19 13:34:41,826 - train: [ INFO] - Train: 55 [ 0/461 ( 0%)] Loss: 3.030969 (3.0310) Loss_single: 2.353578 (2.3536) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.799s, 4.71/s (6.799s, 4.71/s) LR: 5.000e-03 Data: 5.873 (5.873) +2025-04-19 13:35:24,613 - train: [ INFO] - Train: 55 [ 50/461 ( 11%)] Loss: 3.282639 (3.1568) Loss_single: 2.543320 (2.4484) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.809s, 39.58/s (0.971s, 32.96/s) LR: 5.000e-03 Data: 0.001 (0.116) +2025-04-19 13:36:06,663 - train: [ INFO] - Train: 55 [ 100/461 ( 22%)] Loss: 3.172977 (3.1622) Loss_single: 2.357530 (2.4181) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.46/s (0.906s, 35.33/s) LR: 5.000e-03 Data: 0.001 (0.059) +2025-04-19 13:36:50,230 - train: [ INFO] - Train: 55 [ 150/461 ( 33%)] Loss: 3.008116 (3.1237) Loss_single: 2.247309 (2.3754) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (99.2188) Time: 0.915s, 34.96/s (0.894s, 35.79/s) LR: 5.000e-03 Data: 0.001 (0.040) +2025-04-19 13:37:36,094 - train: [ INFO] - Train: 55 [ 200/461 ( 43%)] Loss: 2.760128 (3.0510) Loss_single: 1.999563 (2.3003) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.1250) Acc@5: 96.8750 (98.7500) Time: 0.778s, 41.11/s (0.899s, 35.58/s) LR: 5.000e-03 Data: 0.001 (0.030) +2025-04-19 13:38:20,631 - train: [ INFO] - Train: 55 [ 250/461 ( 54%)] Loss: 2.851246 (3.0177) Loss_single: 2.175068 (2.2794) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.9583) Time: 0.935s, 34.22/s (0.898s, 35.65/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 13:39:04,161 - train: [ INFO] - Train: 55 [ 300/461 ( 65%)] Loss: 2.810211 (2.9880) Loss_single: 2.123474 (2.2571) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6607) Acc@5: 100.0000 (99.1071) Time: 0.763s, 41.96/s (0.893s, 35.84/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 13:39:45,939 - train: [ INFO] - Train: 55 [ 350/461 ( 76%)] Loss: 3.074959 (2.9989) Loss_single: 2.386111 (2.2732) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8281) Acc@5: 100.0000 (99.2188) Time: 0.938s, 34.12/s (0.885s, 36.18/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 13:40:27,091 - train: [ INFO] - Train: 55 [ 400/461 ( 87%)] Loss: 2.680671 (2.9635) Loss_single: 2.003966 (2.2433) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.3056) Time: 0.780s, 41.02/s (0.877s, 36.50/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 13:41:10,158 - train: [ INFO] - Train: 55 [ 450/461 ( 98%)] Loss: 2.678889 (2.9351) Loss_single: 1.999793 (2.2190) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.3750) Time: 0.748s, 42.78/s (0.875s, 36.58/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 13:41:17,867 - train: [ INFO] - Train: 55 [ 460/461 (100%)] Loss: 2.936360 (2.9352) Loss_single: 2.260133 (2.2227) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.4318) Time: 0.577s, 55.45/s (0.873s, 36.67/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 13:41:23,484 - train: [ INFO] - Eval : 55 Time: 5.281 (5.281) Loss: 2.1029 (2.1029) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-19 13:41:37,971 - train: [ INFO] - Eval : 55 Time: 0.279 (0.388) Loss: 1.8751 (1.8699) Acc@1: 62.5000 (54.2279)Acc@5: 75.0000 (79.1667) +2025-04-19 13:41:45,596 - train: [ INFO] - Eval : 55 Time: 0.076 (0.334) Loss: 2.1303 (1.8819) Acc@1: 50.0000 (53.2382)Acc@5: 50.0000 (79.2213) +2025-04-19 13:41:55,959 - train: [ INFO] - Train: 56 [ 0/461 ( 0%)] Loss: 2.860941 (2.8609) Loss_single: 2.184165 (2.1842) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.489s, 4.93/s (6.489s, 4.93/s) LR: 5.000e-03 Data: 5.386 (5.386) +2025-04-19 13:42:40,182 - train: [ INFO] - Train: 56 [ 50/461 ( 11%)] Loss: 2.727611 (2.7943) Loss_single: 2.055558 (2.1199) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.816s, 39.20/s (0.993s, 32.23/s) LR: 5.000e-03 Data: 0.000 (0.106) +2025-04-19 13:43:24,015 - train: [ INFO] - Train: 56 [ 100/461 ( 22%)] Loss: 2.631615 (2.7401) Loss_single: 1.942701 (2.0608) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.790s, 40.49/s (0.935s, 34.24/s) LR: 5.000e-03 Data: 0.000 (0.054) +2025-04-19 13:44:06,287 - train: [ INFO] - Train: 56 [ 150/461 ( 33%)] Loss: 3.211280 (2.8579) Loss_single: 2.431338 (2.1534) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.737s, 43.44/s (0.904s, 35.38/s) LR: 5.000e-03 Data: 0.000 (0.037) +2025-04-19 13:44:45,939 - train: [ INFO] - Train: 56 [ 200/461 ( 43%)] Loss: 2.829484 (2.8522) Loss_single: 2.141384 (2.1510) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.911s, 35.13/s (0.876s, 36.52/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-19 13:45:27,535 - train: [ INFO] - Train: 56 [ 250/461 ( 54%)] Loss: 2.789579 (2.8418) Loss_single: 2.113693 (2.1448) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.829s, 38.59/s (0.867s, 36.91/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 13:46:11,104 - train: [ INFO] - Train: 56 [ 300/461 ( 65%)] Loss: 2.769419 (2.8314) Loss_single: 2.088396 (2.1367) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.706s, 45.34/s (0.868s, 36.89/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 13:46:53,997 - train: [ INFO] - Train: 56 [ 350/461 ( 76%)] Loss: 2.786810 (2.8258) Loss_single: 2.100083 (2.1322) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 1.191s, 26.87/s (0.866s, 36.95/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-19 13:47:36,268 - train: [ INFO] - Train: 56 [ 400/461 ( 87%)] Loss: 2.807895 (2.8238) Loss_single: 2.133487 (2.1323) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.972s, 32.93/s (0.863s, 37.07/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 13:48:18,794 - train: [ INFO] - Train: 56 [ 450/461 ( 98%)] Loss: 3.192245 (2.8607) Loss_single: 2.446528 (2.1637) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.838s, 38.18/s (0.862s, 37.14/s) LR: 5.000e-03 Data: 0.003 (0.013) +2025-04-19 13:48:27,174 - train: [ INFO] - Train: 56 [ 460/461 (100%)] Loss: 2.936854 (2.8676) Loss_single: 2.261700 (2.1726) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 1.232s, 25.97/s (0.861s, 37.16/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 13:48:33,241 - train: [ INFO] - Eval : 56 Time: 5.739 (5.739) Loss: 1.9408 (1.9408) Acc@1: 46.8750 (46.8750)Acc@5: 87.5000 (87.5000) +2025-04-19 13:48:47,017 - train: [ INFO] - Eval : 56 Time: 0.274 (0.383) Loss: 1.8696 (1.8339) Acc@1: 59.3750 (54.7794)Acc@5: 81.2500 (80.3309) +2025-04-19 13:48:54,833 - train: [ INFO] - Eval : 56 Time: 0.069 (0.333) Loss: 2.8153 (1.8480) Acc@1: 50.0000 (53.7779)Acc@5: 50.0000 (80.3007) +2025-04-19 13:49:04,829 - train: [ INFO] - Train: 57 [ 0/461 ( 0%)] Loss: 2.779975 (2.7800) Loss_single: 2.093842 (2.0938) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.777s, 5.54/s (5.777s, 5.54/s) LR: 5.000e-03 Data: 4.950 (4.950) +2025-04-19 13:49:45,221 - train: [ INFO] - Train: 57 [ 50/461 ( 11%)] Loss: 2.591883 (2.6859) Loss_single: 1.917898 (2.0059) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.474s, 67.50/s (0.904s, 35.41/s) LR: 5.000e-03 Data: 0.000 (0.098) +2025-04-19 13:50:27,784 - train: [ INFO] - Train: 57 [ 100/461 ( 22%)] Loss: 3.221156 (2.8643) Loss_single: 2.438097 (2.1499) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 1.388s, 23.06/s (0.877s, 36.50/s) LR: 5.000e-03 Data: 0.000 (0.050) +2025-04-19 13:51:13,044 - train: [ INFO] - Train: 57 [ 150/461 ( 33%)] Loss: 3.096453 (2.9224) Loss_single: 2.413408 (2.2158) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.737s, 43.40/s (0.885s, 36.16/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-19 13:51:52,239 - train: [ INFO] - Train: 57 [ 200/461 ( 43%)] Loss: 2.893356 (2.9166) Loss_single: 2.218383 (2.2163) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 1.115s, 28.69/s (0.860s, 37.23/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-19 13:52:34,316 - train: [ INFO] - Train: 57 [ 250/461 ( 54%)] Loss: 2.603243 (2.8643) Loss_single: 1.933063 (2.1691) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.672s, 47.62/s (0.856s, 37.40/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-19 13:53:19,939 - train: [ INFO] - Train: 57 [ 300/461 ( 65%)] Loss: 2.734475 (2.8458) Loss_single: 2.055707 (2.1529) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.837s, 38.22/s (0.865s, 37.00/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 13:54:03,186 - train: [ INFO] - Train: 57 [ 350/461 ( 76%)] Loss: 2.935503 (2.8570) Loss_single: 2.236847 (2.1634) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.783s, 40.86/s (0.865s, 37.01/s) LR: 5.000e-03 Data: 0.005 (0.015) +2025-04-19 13:54:45,810 - train: [ INFO] - Train: 57 [ 400/461 ( 87%)] Loss: 2.822852 (2.8532) Loss_single: 2.087644 (2.1550) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 100.0000 (99.6528) Time: 1.052s, 30.41/s (0.863s, 37.08/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 13:55:28,144 - train: [ INFO] - Train: 57 [ 450/461 ( 98%)] Loss: 3.185467 (2.8864) Loss_single: 2.502476 (2.1897) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.792s, 40.42/s (0.861s, 37.17/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:55:36,605 - train: [ INFO] - Train: 57 [ 460/461 (100%)] Loss: 2.817846 (2.8802) Loss_single: 2.131766 (2.1845) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.758s, 42.24/s (0.861s, 37.18/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 13:55:42,067 - train: [ INFO] - Eval : 57 Time: 5.082 (5.082) Loss: 2.0643 (2.0643) Acc@1: 37.5000 (37.5000)Acc@5: 71.8750 (71.8750) +2025-04-19 13:55:56,091 - train: [ INFO] - Eval : 57 Time: 0.222 (0.375) Loss: 1.8704 (1.8522) Acc@1: 56.2500 (53.4926)Acc@5: 78.1250 (79.0441) +2025-04-19 13:56:03,855 - train: [ INFO] - Eval : 57 Time: 0.060 (0.328) Loss: 2.6256 (1.8709) Acc@1: 50.0000 (52.6214)Acc@5: 50.0000 (78.9129) +2025-04-19 13:56:14,112 - train: [ INFO] - Train: 58 [ 0/461 ( 0%)] Loss: 2.783708 (2.7837) Loss_single: 2.104169 (2.1042) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.980s, 5.35/s (5.980s, 5.35/s) LR: 5.000e-03 Data: 4.636 (4.636) +2025-04-19 13:56:58,034 - train: [ INFO] - Train: 58 [ 50/461 ( 11%)] Loss: 2.617702 (2.7007) Loss_single: 1.945015 (2.0246) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.824s, 38.82/s (0.977s, 32.75/s) LR: 5.000e-03 Data: 0.000 (0.092) +2025-04-19 13:57:40,817 - train: [ INFO] - Train: 58 [ 100/461 ( 22%)] Loss: 2.844937 (2.7488) Loss_single: 2.169167 (2.0728) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.739s, 43.29/s (0.916s, 34.92/s) LR: 5.000e-03 Data: 0.000 (0.047) +2025-04-19 13:58:22,445 - train: [ INFO] - Train: 58 [ 150/461 ( 33%)] Loss: 2.801373 (2.7619) Loss_single: 2.115634 (2.0835) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.868s, 36.88/s (0.888s, 36.03/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 13:59:03,926 - train: [ INFO] - Train: 58 [ 200/461 ( 43%)] Loss: 2.956326 (2.8008) Loss_single: 2.281313 (2.1231) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.780s, 41.03/s (0.873s, 36.65/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 13:59:46,153 - train: [ INFO] - Train: 58 [ 250/461 ( 54%)] Loss: 2.898809 (2.8171) Loss_single: 2.221509 (2.1395) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.842s, 38.00/s (0.867s, 36.90/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 14:00:29,012 - train: [ INFO] - Train: 58 [ 300/461 ( 65%)] Loss: 3.091155 (2.8563) Loss_single: 2.403564 (2.1772) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.849s, 37.69/s (0.865s, 36.98/s) LR: 5.000e-03 Data: 0.007 (0.016) +2025-04-19 14:01:11,153 - train: [ INFO] - Train: 58 [ 350/461 ( 76%)] Loss: 2.688120 (2.8353) Loss_single: 2.003888 (2.1555) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.870s, 36.79/s (0.862s, 37.13/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 14:01:54,545 - train: [ INFO] - Train: 58 [ 400/461 ( 87%)] Loss: 2.801944 (2.8316) Loss_single: 2.125279 (2.1522) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.016s, 31.49/s (0.862s, 37.10/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:02:36,817 - train: [ INFO] - Train: 58 [ 450/461 ( 98%)] Loss: 2.912393 (2.8396) Loss_single: 2.222947 (2.1592) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.665s, 48.14/s (0.860s, 37.19/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:02:45,429 - train: [ INFO] - Train: 58 [ 460/461 (100%)] Loss: 3.019043 (2.8560) Loss_single: 2.328951 (2.1747) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.758s, 42.21/s (0.860s, 37.19/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:02:50,806 - train: [ INFO] - Eval : 58 Time: 4.995 (4.995) Loss: 1.9870 (1.9870) Acc@1: 53.1250 (53.1250)Acc@5: 84.3750 (84.3750) +2025-04-19 14:03:05,658 - train: [ INFO] - Eval : 58 Time: 0.341 (0.389) Loss: 1.7892 (1.8707) Acc@1: 62.5000 (53.0025)Acc@5: 78.1250 (79.9632) +2025-04-19 14:03:13,332 - train: [ INFO] - Eval : 58 Time: 0.113 (0.336) Loss: 2.7622 (1.8832) Acc@1: 50.0000 (52.0432)Acc@5: 50.0000 (79.9152) +2025-04-19 14:03:24,325 - train: [ INFO] - Train: 59 [ 0/461 ( 0%)] Loss: 2.852525 (2.8525) Loss_single: 2.101628 (2.1016) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 6.464s, 4.95/s (6.464s, 4.95/s) LR: 5.000e-03 Data: 5.539 (5.539) +2025-04-19 14:04:06,696 - train: [ INFO] - Train: 59 [ 50/461 ( 11%)] Loss: 3.089148 (2.9708) Loss_single: 2.411211 (2.2564) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.677s, 47.26/s (0.956s, 33.48/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-19 14:04:44,296 - train: [ INFO] - Train: 59 [ 100/461 ( 22%)] Loss: 3.017066 (2.9862) Loss_single: 2.322357 (2.2784) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 1.050s, 30.47/s (0.854s, 37.46/s) LR: 5.000e-03 Data: 0.000 (0.056) +2025-04-19 14:05:27,720 - train: [ INFO] - Train: 59 [ 150/461 ( 33%)] Loss: 2.764573 (2.9308) Loss_single: 2.080126 (2.2288) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 1.164s, 27.50/s (0.858s, 37.30/s) LR: 5.000e-03 Data: 0.001 (0.038) +2025-04-19 14:06:08,727 - train: [ INFO] - Train: 59 [ 200/461 ( 43%)] Loss: 2.852828 (2.9152) Loss_single: 2.141292 (2.2113) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.705s, 45.40/s (0.848s, 37.74/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 14:06:50,051 - train: [ INFO] - Train: 59 [ 250/461 ( 54%)] Loss: 3.202403 (2.9631) Loss_single: 2.515725 (2.2621) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.733s, 43.63/s (0.843s, 37.94/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 14:07:33,177 - train: [ INFO] - Train: 59 [ 300/461 ( 65%)] Loss: 2.887928 (2.9524) Loss_single: 2.189365 (2.2517) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 1.054s, 30.35/s (0.846s, 37.81/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 14:08:04,340 - train: [ INFO] - Train: 59 [ 350/461 ( 76%)] Loss: 2.726204 (2.9241) Loss_single: 2.054908 (2.2271) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.792s, 40.43/s (0.814s, 39.30/s) LR: 5.000e-03 Data: 0.007 (0.017) +2025-04-19 14:08:45,404 - train: [ INFO] - Train: 59 [ 400/461 ( 87%)] Loss: 2.642210 (2.8928) Loss_single: 1.964234 (2.1979) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.772s, 41.47/s (0.815s, 39.27/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 14:09:27,990 - train: [ INFO] - Train: 59 [ 450/461 ( 98%)] Loss: 2.984413 (2.9019) Loss_single: 2.303051 (2.2084) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.795s, 40.27/s (0.819s, 39.08/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:09:36,263 - train: [ INFO] - Train: 59 [ 460/461 (100%)] Loss: 2.589808 (2.8736) Loss_single: 1.910964 (2.1814) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.793s, 40.37/s (0.819s, 39.08/s) LR: 5.000e-03 Data: 0.006 (0.013) +2025-04-19 14:09:42,005 - train: [ INFO] - Eval : 59 Time: 5.399 (5.399) Loss: 1.9630 (1.9630) Acc@1: 46.8750 (46.8750)Acc@5: 84.3750 (84.3750) +2025-04-19 14:09:56,611 - train: [ INFO] - Eval : 59 Time: 0.262 (0.392) Loss: 1.8809 (1.9071) Acc@1: 59.3750 (52.8186)Acc@5: 78.1250 (79.5343) +2025-04-19 14:10:04,719 - train: [ INFO] - Eval : 59 Time: 0.069 (0.343) Loss: 3.0122 (1.9156) Acc@1: 50.0000 (52.4672)Acc@5: 50.0000 (79.3369) +2025-04-19 14:10:15,265 - train: [ INFO] - Train: 60 [ 0/461 ( 0%)] Loss: 2.707097 (2.7071) Loss_single: 2.034779 (2.0348) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.262s, 5.11/s (6.262s, 5.11/s) LR: 5.000e-03 Data: 5.239 (5.239) +2025-04-19 14:10:58,224 - train: [ INFO] - Train: 60 [ 50/461 ( 11%)] Loss: 3.153676 (2.9304) Loss_single: 2.461844 (2.2483) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.905s, 35.34/s (0.964s, 33.20/s) LR: 5.000e-03 Data: 0.000 (0.104) +2025-04-19 14:11:41,656 - train: [ INFO] - Train: 60 [ 100/461 ( 22%)] Loss: 2.695765 (2.8522) Loss_single: 1.980199 (2.1589) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.734s, 43.59/s (0.916s, 34.94/s) LR: 5.000e-03 Data: 0.001 (0.053) +2025-04-19 14:12:21,644 - train: [ INFO] - Train: 60 [ 150/461 ( 33%)] Loss: 2.794006 (2.8376) Loss_single: 2.119024 (2.1490) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.063s, 30.11/s (0.877s, 36.49/s) LR: 5.000e-03 Data: 0.000 (0.036) +2025-04-19 14:13:04,862 - train: [ INFO] - Train: 60 [ 200/461 ( 43%)] Loss: 2.992146 (2.8685) Loss_single: 2.309728 (2.1811) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.990s, 32.33/s (0.873s, 36.64/s) LR: 5.000e-03 Data: 0.002 (0.027) +2025-04-19 14:13:47,947 - train: [ INFO] - Train: 60 [ 250/461 ( 54%)] Loss: 2.880887 (2.8706) Loss_single: 2.206201 (2.1853) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.841s, 38.05/s (0.871s, 36.74/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 14:14:31,009 - train: [ INFO] - Train: 60 [ 300/461 ( 65%)] Loss: 2.884590 (2.8726) Loss_single: 2.210067 (2.1888) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.805s, 39.74/s (0.869s, 36.82/s) LR: 5.000e-03 Data: 0.006 (0.018) +2025-04-19 14:15:12,042 - train: [ INFO] - Train: 60 [ 350/461 ( 76%)] Loss: 2.903279 (2.8764) Loss_single: 2.227436 (2.1937) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.637s, 50.24/s (0.862s, 37.12/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 14:15:53,849 - train: [ INFO] - Train: 60 [ 400/461 ( 87%)] Loss: 2.910207 (2.8802) Loss_single: 2.227815 (2.1975) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.730s, 43.81/s (0.859s, 37.27/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 14:16:34,844 - train: [ INFO] - Train: 60 [ 450/461 ( 98%)] Loss: 2.924003 (2.8846) Loss_single: 2.236461 (2.2014) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.801s, 39.97/s (0.854s, 37.47/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:16:42,989 - train: [ INFO] - Train: 60 [ 460/461 (100%)] Loss: 2.913978 (2.8872) Loss_single: 2.194446 (2.2007) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.764s, 41.88/s (0.853s, 37.51/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 14:16:49,069 - train: [ INFO] - Eval : 60 Time: 5.757 (5.757) Loss: 1.9171 (1.9171) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 14:17:02,890 - train: [ INFO] - Eval : 60 Time: 0.362 (0.384) Loss: 1.7751 (1.8702) Acc@1: 59.3750 (55.1471)Acc@5: 78.1250 (78.6765) +2025-04-19 14:17:10,874 - train: [ INFO] - Eval : 60 Time: 0.063 (0.336) Loss: 2.5786 (1.8844) Acc@1: 50.0000 (54.3948)Acc@5: 50.0000 (78.2961) +2025-04-19 14:17:14,684 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-60.pth.tar', 54.39475713184272) + +2025-04-19 14:17:21,287 - train: [ INFO] - Train: 61 [ 0/461 ( 0%)] Loss: 2.982006 (2.9820) Loss_single: 2.307701 (2.3077) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.514s, 4.91/s (6.514s, 4.91/s) LR: 5.000e-03 Data: 5.689 (5.689) +2025-04-19 14:18:06,588 - train: [ INFO] - Train: 61 [ 50/461 ( 11%)] Loss: 2.593247 (2.7876) Loss_single: 1.924218 (2.1160) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.316s, 24.32/s (1.015s, 31.54/s) LR: 5.000e-03 Data: 0.003 (0.112) +2025-04-19 14:18:49,988 - train: [ INFO] - Train: 61 [ 100/461 ( 22%)] Loss: 2.553663 (2.7096) Loss_single: 1.874646 (2.0355) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.907s, 35.29/s (0.941s, 34.00/s) LR: 5.000e-03 Data: 0.000 (0.057) +2025-04-19 14:19:34,195 - train: [ INFO] - Train: 61 [ 150/461 ( 33%)] Loss: 2.763305 (2.7231) Loss_single: 2.090738 (2.0493) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.044s, 30.66/s (0.922s, 34.71/s) LR: 5.000e-03 Data: 0.001 (0.038) +2025-04-19 14:20:17,057 - train: [ INFO] - Train: 61 [ 200/461 ( 43%)] Loss: 2.832121 (2.7449) Loss_single: 2.154520 (2.0704) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.783s, 40.88/s (0.905s, 35.35/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 14:21:00,601 - train: [ INFO] - Train: 61 [ 250/461 ( 54%)] Loss: 3.031721 (2.7927) Loss_single: 2.258380 (2.1017) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 96.8750 (99.4792) Time: 0.891s, 35.93/s (0.898s, 35.63/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-19 14:21:43,004 - train: [ INFO] - Train: 61 [ 300/461 ( 65%)] Loss: 2.809774 (2.7951) Loss_single: 2.101638 (2.1017) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.922s, 34.72/s (0.890s, 35.97/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 14:22:25,677 - train: [ INFO] - Train: 61 [ 350/461 ( 76%)] Loss: 2.859003 (2.8031) Loss_single: 2.179495 (2.1114) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.927s, 34.50/s (0.884s, 36.19/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 14:23:09,739 - train: [ INFO] - Train: 61 [ 400/461 ( 87%)] Loss: 3.245754 (2.8523) Loss_single: 2.497181 (2.1543) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.845s, 37.88/s (0.884s, 36.21/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 14:23:50,941 - train: [ INFO] - Train: 61 [ 450/461 ( 98%)] Loss: 2.747509 (2.8418) Loss_single: 2.042919 (2.1431) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.667s, 47.96/s (0.877s, 36.49/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:23:59,661 - train: [ INFO] - Train: 61 [ 460/461 (100%)] Loss: 2.848648 (2.8424) Loss_single: 2.119955 (2.1410) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.976s, 32.79/s (0.877s, 36.50/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:24:05,482 - train: [ INFO] - Eval : 61 Time: 5.469 (5.469) Loss: 1.9666 (1.9666) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 14:24:19,370 - train: [ INFO] - Eval : 61 Time: 0.325 (0.380) Loss: 1.9635 (1.8796) Acc@1: 56.2500 (53.0637)Acc@5: 75.0000 (78.1250) +2025-04-19 14:24:27,332 - train: [ INFO] - Eval : 61 Time: 0.070 (0.333) Loss: 2.9361 (1.8908) Acc@1: 50.0000 (52.8142)Acc@5: 50.0000 (77.9877) +2025-04-19 14:24:36,780 - train: [ INFO] - Train: 62 [ 0/461 ( 0%)] Loss: 2.752539 (2.7525) Loss_single: 2.075013 (2.0750) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.422s, 5.90/s (5.422s, 5.90/s) LR: 5.000e-03 Data: 4.473 (4.473) +2025-04-19 14:25:18,308 - train: [ INFO] - Train: 62 [ 50/461 ( 11%)] Loss: 2.751665 (2.7521) Loss_single: 2.063606 (2.0693) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.851s, 37.62/s (0.919s, 34.84/s) LR: 5.000e-03 Data: 0.001 (0.090) +2025-04-19 14:25:59,475 - train: [ INFO] - Train: 62 [ 100/461 ( 22%)] Loss: 2.897256 (2.8005) Loss_single: 2.220672 (2.1198) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.536s, 59.66/s (0.871s, 36.75/s) LR: 5.000e-03 Data: 0.000 (0.046) +2025-04-19 14:26:43,301 - train: [ INFO] - Train: 62 [ 150/461 ( 33%)] Loss: 2.786566 (2.7970) Loss_single: 2.114987 (2.1186) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.709s, 45.11/s (0.872s, 36.69/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 14:27:26,917 - train: [ INFO] - Train: 62 [ 200/461 ( 43%)] Loss: 3.096460 (2.8569) Loss_single: 2.417448 (2.1783) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.731s, 43.77/s (0.872s, 36.71/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 14:28:08,684 - train: [ INFO] - Train: 62 [ 250/461 ( 54%)] Loss: 2.620107 (2.8174) Loss_single: 1.939396 (2.1385) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.951s, 33.63/s (0.864s, 37.03/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-19 14:28:50,748 - train: [ INFO] - Train: 62 [ 300/461 ( 65%)] Loss: 2.647291 (2.7931) Loss_single: 1.969065 (2.1143) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.862s, 37.11/s (0.860s, 37.20/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 14:29:32,801 - train: [ INFO] - Train: 62 [ 350/461 ( 76%)] Loss: 2.758528 (2.7888) Loss_single: 2.087046 (2.1109) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.754s, 42.47/s (0.857s, 37.33/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 14:30:15,697 - train: [ INFO] - Train: 62 [ 400/461 ( 87%)] Loss: 2.853315 (2.7960) Loss_single: 2.144100 (2.1146) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.774s, 41.33/s (0.857s, 37.33/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 14:30:56,984 - train: [ INFO] - Train: 62 [ 450/461 ( 98%)] Loss: 3.207650 (2.8371) Loss_single: 2.483864 (2.1515) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.998s, 32.08/s (0.854s, 37.49/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:31:04,813 - train: [ INFO] - Train: 62 [ 460/461 (100%)] Loss: 2.806645 (2.8344) Loss_single: 2.041303 (2.1415) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4318) Acc@5: 96.8750 (99.7159) Time: 0.842s, 37.99/s (0.852s, 37.56/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:31:10,817 - train: [ INFO] - Eval : 62 Time: 5.663 (5.663) Loss: 2.0395 (2.0395) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-19 14:31:25,320 - train: [ INFO] - Eval : 62 Time: 0.249 (0.395) Loss: 1.8933 (1.8908) Acc@1: 53.1250 (52.3284)Acc@5: 78.1250 (78.2475) +2025-04-19 14:31:33,256 - train: [ INFO] - Eval : 62 Time: 0.067 (0.343) Loss: 2.8066 (1.9012) Acc@1: 50.0000 (52.1588)Acc@5: 50.0000 (78.3346) +2025-04-19 14:31:43,245 - train: [ INFO] - Train: 63 [ 0/461 ( 0%)] Loss: 2.929043 (2.9290) Loss_single: 2.147775 (2.1478) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 5.855s, 5.47/s (5.855s, 5.47/s) LR: 5.000e-03 Data: 4.819 (4.819) +2025-04-19 14:32:26,292 - train: [ INFO] - Train: 63 [ 50/461 ( 11%)] Loss: 2.912174 (2.9206) Loss_single: 2.213493 (2.1806) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 1.087s, 29.44/s (0.957s, 33.43/s) LR: 5.000e-03 Data: 0.001 (0.095) +2025-04-19 14:33:09,713 - train: [ INFO] - Train: 63 [ 100/461 ( 22%)] Loss: 2.906382 (2.9159) Loss_single: 2.183355 (2.1815) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.765s, 41.84/s (0.912s, 35.07/s) LR: 5.000e-03 Data: 0.004 (0.049) +2025-04-19 14:33:51,082 - train: [ INFO] - Train: 63 [ 150/461 ( 33%)] Loss: 2.861217 (2.9022) Loss_single: 2.157321 (2.1755) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.656s, 48.81/s (0.884s, 36.22/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-19 14:34:32,866 - train: [ INFO] - Train: 63 [ 200/461 ( 43%)] Loss: 2.700737 (2.8619) Loss_single: 2.018186 (2.1440) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.924s, 34.62/s (0.871s, 36.72/s) LR: 5.000e-03 Data: 0.003 (0.025) +2025-04-19 14:35:14,536 - train: [ INFO] - Train: 63 [ 250/461 ( 54%)] Loss: 2.630697 (2.8234) Loss_single: 1.958262 (2.1131) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.847s, 37.77/s (0.863s, 37.06/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 14:35:59,445 - train: [ INFO] - Train: 63 [ 300/461 ( 65%)] Loss: 3.151447 (2.8702) Loss_single: 2.473639 (2.1646) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.784s, 40.80/s (0.869s, 36.83/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-19 14:36:43,640 - train: [ INFO] - Train: 63 [ 350/461 ( 76%)] Loss: 2.896917 (2.8736) Loss_single: 2.222540 (2.1718) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 1.219s, 26.24/s (0.871s, 36.75/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 14:37:26,823 - train: [ INFO] - Train: 63 [ 400/461 ( 87%)] Loss: 2.887439 (2.8751) Loss_single: 2.209559 (2.1760) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.781s, 40.99/s (0.870s, 36.79/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:38:08,381 - train: [ INFO] - Train: 63 [ 450/461 ( 98%)] Loss: 3.127761 (2.9004) Loss_single: 2.358201 (2.1942) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 96.8750 (99.3750) Time: 0.835s, 38.34/s (0.865s, 36.98/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 14:38:17,309 - train: [ INFO] - Train: 63 [ 460/461 (100%)] Loss: 2.945980 (2.9045) Loss_single: 2.273829 (2.2015) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.4318) Time: 1.224s, 26.14/s (0.866s, 36.96/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:38:22,773 - train: [ INFO] - Eval : 63 Time: 5.130 (5.130) Loss: 1.9613 (1.9613) Acc@1: 40.6250 (40.6250)Acc@5: 87.5000 (87.5000) +2025-04-19 14:38:36,705 - train: [ INFO] - Eval : 63 Time: 0.290 (0.374) Loss: 1.8349 (1.9008) Acc@1: 56.2500 (53.4314)Acc@5: 75.0000 (78.9216) +2025-04-19 14:38:44,542 - train: [ INFO] - Eval : 63 Time: 0.089 (0.328) Loss: 3.0400 (1.9071) Acc@1: 50.0000 (53.0455)Acc@5: 50.0000 (78.8743) +2025-04-19 14:38:55,279 - train: [ INFO] - Train: 64 [ 0/461 ( 0%)] Loss: 3.041381 (3.0414) Loss_single: 2.282570 (2.2826) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 6.331s, 5.05/s (6.331s, 5.05/s) LR: 5.000e-03 Data: 5.511 (5.511) +2025-04-19 14:39:38,949 - train: [ INFO] - Train: 64 [ 50/461 ( 11%)] Loss: 2.725830 (2.8836) Loss_single: 2.052917 (2.1677) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.986s, 32.44/s (0.979s, 32.70/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-19 14:40:23,377 - train: [ INFO] - Train: 64 [ 100/461 ( 22%)] Loss: 2.823804 (2.8637) Loss_single: 2.142036 (2.1592) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 1.073s, 29.83/s (0.933s, 34.29/s) LR: 5.000e-03 Data: 0.000 (0.055) +2025-04-19 14:41:04,221 - train: [ INFO] - Train: 64 [ 150/461 ( 33%)] Loss: 2.862525 (2.8634) Loss_single: 2.196445 (2.1685) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 1.087s, 29.45/s (0.894s, 35.78/s) LR: 5.000e-03 Data: 0.001 (0.037) +2025-04-19 14:41:47,998 - train: [ INFO] - Train: 64 [ 200/461 ( 43%)] Loss: 2.833009 (2.8573) Loss_single: 2.149983 (2.1648) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.804s, 39.81/s (0.889s, 35.99/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-19 14:42:23,881 - train: [ INFO] - Train: 64 [ 250/461 ( 54%)] Loss: 3.053257 (2.8900) Loss_single: 2.304637 (2.1881) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.783s, 40.87/s (0.855s, 37.44/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 14:43:07,785 - train: [ INFO] - Train: 64 [ 300/461 ( 65%)] Loss: 3.026599 (2.9095) Loss_single: 2.357882 (2.2124) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.870s, 36.78/s (0.858s, 37.28/s) LR: 5.000e-03 Data: 0.003 (0.019) +2025-04-19 14:43:50,575 - train: [ INFO] - Train: 64 [ 350/461 ( 76%)] Loss: 2.804351 (2.8963) Loss_single: 2.127538 (2.2018) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.615s, 52.02/s (0.858s, 37.31/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-19 14:44:33,399 - train: [ INFO] - Train: 64 [ 400/461 ( 87%)] Loss: 2.693626 (2.8738) Loss_single: 2.019662 (2.1815) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.702s, 45.56/s (0.857s, 37.32/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 14:45:14,008 - train: [ INFO] - Train: 64 [ 450/461 ( 98%)] Loss: 2.809670 (2.8674) Loss_single: 2.116890 (2.1751) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.862s, 37.11/s (0.852s, 37.55/s) LR: 5.000e-03 Data: 0.003 (0.013) +2025-04-19 14:45:21,664 - train: [ INFO] - Train: 64 [ 460/461 (100%)] Loss: 2.885056 (2.8690) Loss_single: 2.153129 (2.1731) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1477) Acc@5: 100.0000 (100.0000) Time: 0.803s, 39.86/s (0.850s, 37.63/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 14:45:27,824 - train: [ INFO] - Eval : 64 Time: 5.793 (5.793) Loss: 1.9214 (1.9214) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 14:45:41,608 - train: [ INFO] - Eval : 64 Time: 0.286 (0.384) Loss: 1.9813 (1.9056) Acc@1: 53.1250 (52.7574)Acc@5: 68.7500 (78.1250) +2025-04-19 14:45:49,266 - train: [ INFO] - Eval : 64 Time: 0.066 (0.332) Loss: 2.5296 (1.9148) Acc@1: 50.0000 (52.3130)Acc@5: 50.0000 (78.1419) +2025-04-19 14:45:58,455 - train: [ INFO] - Train: 65 [ 0/461 ( 0%)] Loss: 2.839249 (2.8392) Loss_single: 2.169026 (2.1690) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.680s, 6.84/s (4.680s, 6.84/s) LR: 5.000e-03 Data: 3.847 (3.847) +2025-04-19 14:46:42,784 - train: [ INFO] - Train: 65 [ 50/461 ( 11%)] Loss: 2.941306 (2.8903) Loss_single: 2.266523 (2.2178) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.806s, 39.69/s (0.960s, 33.35/s) LR: 5.000e-03 Data: 0.000 (0.076) +2025-04-19 14:47:25,210 - train: [ INFO] - Train: 65 [ 100/461 ( 22%)] Loss: 2.736241 (2.8389) Loss_single: 2.030281 (2.1553) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.704s, 45.47/s (0.904s, 35.41/s) LR: 5.000e-03 Data: 0.002 (0.039) +2025-04-19 14:48:06,716 - train: [ INFO] - Train: 65 [ 150/461 ( 33%)] Loss: 3.189538 (2.9266) Loss_single: 2.417963 (2.2209) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (99.2188) Time: 0.614s, 52.08/s (0.878s, 36.43/s) LR: 5.000e-03 Data: 0.001 (0.027) +2025-04-19 14:48:49,361 - train: [ INFO] - Train: 65 [ 200/461 ( 43%)] Loss: 2.641501 (2.8696) Loss_single: 1.959426 (2.1686) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.854s, 37.46/s (0.872s, 36.71/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-19 14:49:34,801 - train: [ INFO] - Train: 65 [ 250/461 ( 54%)] Loss: 2.612271 (2.8267) Loss_single: 1.935364 (2.1298) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 1.115s, 28.70/s (0.879s, 36.42/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 14:50:21,527 - train: [ INFO] - Train: 65 [ 300/461 ( 65%)] Loss: 2.893179 (2.8362) Loss_single: 2.201629 (2.1400) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.799s, 40.06/s (0.888s, 36.05/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 14:51:06,296 - train: [ INFO] - Train: 65 [ 350/461 ( 76%)] Loss: 2.964613 (2.8522) Loss_single: 2.277794 (2.1573) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.864s, 37.05/s (0.889s, 36.01/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 14:51:51,355 - train: [ INFO] - Train: 65 [ 400/461 ( 87%)] Loss: 2.845230 (2.8515) Loss_single: 2.170527 (2.1587) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.805s, 39.77/s (0.890s, 35.96/s) LR: 5.000e-03 Data: 0.001 (0.011) +2025-04-19 14:52:34,893 - train: [ INFO] - Train: 65 [ 450/461 ( 98%)] Loss: 3.024860 (2.8688) Loss_single: 2.352020 (2.1781) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.869s, 36.83/s (0.888s, 36.05/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 14:52:43,144 - train: [ INFO] - Train: 65 [ 460/461 (100%)] Loss: 3.213294 (2.9001) Loss_single: 2.499241 (2.2073) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.995s, 32.15/s (0.886s, 36.11/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 14:52:48,925 - train: [ INFO] - Eval : 65 Time: 5.379 (5.379) Loss: 1.8475 (1.8475) Acc@1: 46.8750 (46.8750)Acc@5: 87.5000 (87.5000) +2025-04-19 14:53:03,263 - train: [ INFO] - Eval : 65 Time: 0.293 (0.387) Loss: 1.8553 (1.8537) Acc@1: 59.3750 (53.4314)Acc@5: 75.0000 (79.7181) +2025-04-19 14:53:11,028 - train: [ INFO] - Eval : 65 Time: 0.065 (0.335) Loss: 2.8743 (1.8638) Acc@1: 50.0000 (53.1997)Acc@5: 50.0000 (79.2984) +2025-04-19 14:53:20,669 - train: [ INFO] - Train: 66 [ 0/461 ( 0%)] Loss: 2.739841 (2.7398) Loss_single: 2.075180 (2.0752) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.328s, 6.01/s (5.328s, 6.01/s) LR: 5.000e-03 Data: 4.485 (4.485) +2025-04-19 14:54:03,860 - train: [ INFO] - Train: 66 [ 50/461 ( 11%)] Loss: 2.675689 (2.7078) Loss_single: 2.000400 (2.0378) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.772s, 41.43/s (0.950s, 33.69/s) LR: 5.000e-03 Data: 0.000 (0.089) +2025-04-19 14:54:47,321 - train: [ INFO] - Train: 66 [ 100/461 ( 22%)] Loss: 2.698775 (2.7048) Loss_single: 2.016782 (2.0308) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.842s, 37.99/s (0.909s, 35.20/s) LR: 5.000e-03 Data: 0.000 (0.045) +2025-04-19 14:55:26,894 - train: [ INFO] - Train: 66 [ 150/461 ( 33%)] Loss: 2.808159 (2.7306) Loss_single: 2.134051 (2.0566) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.811s, 39.46/s (0.869s, 36.80/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-19 14:56:09,929 - train: [ INFO] - Train: 66 [ 200/461 ( 43%)] Loss: 2.871307 (2.7588) Loss_single: 2.187864 (2.0829) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.754s, 42.47/s (0.867s, 36.91/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-19 14:56:51,764 - train: [ INFO] - Train: 66 [ 250/461 ( 54%)] Loss: 2.895511 (2.7815) Loss_single: 2.217413 (2.1053) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.981s, 32.63/s (0.861s, 37.19/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 14:57:34,664 - train: [ INFO] - Train: 66 [ 300/461 ( 65%)] Loss: 2.698737 (2.7697) Loss_single: 2.022561 (2.0935) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.743s, 43.07/s (0.860s, 37.21/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 14:58:17,907 - train: [ INFO] - Train: 66 [ 350/461 ( 76%)] Loss: 3.062953 (2.8064) Loss_single: 2.366309 (2.1276) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.788s, 40.59/s (0.860s, 37.19/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-19 14:59:01,056 - train: [ INFO] - Train: 66 [ 400/461 ( 87%)] Loss: 2.720867 (2.7969) Loss_single: 2.047247 (2.1186) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.712s, 44.92/s (0.861s, 37.18/s) LR: 5.000e-03 Data: 0.004 (0.012) +2025-04-19 14:59:42,022 - train: [ INFO] - Train: 66 [ 450/461 ( 98%)] Loss: 2.853440 (2.8025) Loss_single: 2.117517 (2.1185) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.152s, 27.78/s (0.856s, 37.39/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:59:49,999 - train: [ INFO] - Train: 66 [ 460/461 (100%)] Loss: 2.840573 (2.8060) Loss_single: 2.167387 (2.1230) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.705s, 45.39/s (0.855s, 37.44/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-19 14:59:56,292 - train: [ INFO] - Eval : 66 Time: 5.906 (5.906) Loss: 2.0428 (2.0428) Acc@1: 40.6250 (40.6250)Acc@5: 75.0000 (75.0000) +2025-04-19 15:00:09,291 - train: [ INFO] - Eval : 66 Time: 0.214 (0.371) Loss: 1.8796 (1.8751) Acc@1: 59.3750 (53.2475)Acc@5: 71.8750 (79.9632) +2025-04-19 15:00:16,739 - train: [ INFO] - Eval : 66 Time: 0.065 (0.321) Loss: 2.6101 (1.8920) Acc@1: 50.0000 (52.5829)Acc@5: 50.0000 (79.9537) +2025-04-19 15:00:26,009 - train: [ INFO] - Train: 67 [ 0/461 ( 0%)] Loss: 2.948687 (2.9487) Loss_single: 2.249071 (2.2491) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.074s, 6.31/s (5.074s, 6.31/s) LR: 5.000e-03 Data: 4.245 (4.245) +2025-04-19 15:01:09,730 - train: [ INFO] - Train: 67 [ 50/461 ( 11%)] Loss: 2.663753 (2.8062) Loss_single: 1.986475 (2.1178) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.760s, 42.09/s (0.955s, 33.51/s) LR: 5.000e-03 Data: 0.000 (0.084) +2025-04-19 15:01:50,690 - train: [ INFO] - Train: 67 [ 100/461 ( 22%)] Loss: 2.674788 (2.7624) Loss_single: 2.005853 (2.0805) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.782s, 40.93/s (0.887s, 36.07/s) LR: 5.000e-03 Data: 0.004 (0.043) +2025-04-19 15:02:33,492 - train: [ INFO] - Train: 67 [ 150/461 ( 33%)] Loss: 2.833362 (2.7801) Loss_single: 2.118914 (2.0901) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 1.157s, 27.66/s (0.876s, 36.52/s) LR: 5.000e-03 Data: 0.000 (0.029) +2025-04-19 15:03:17,153 - train: [ INFO] - Train: 67 [ 200/461 ( 43%)] Loss: 2.559458 (2.7360) Loss_single: 1.880626 (2.0482) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.881s, 36.34/s (0.875s, 36.57/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 15:03:59,380 - train: [ INFO] - Train: 67 [ 250/461 ( 54%)] Loss: 2.838022 (2.7530) Loss_single: 2.157594 (2.0664) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.743s, 43.09/s (0.869s, 36.84/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-19 15:04:44,866 - train: [ INFO] - Train: 67 [ 300/461 ( 65%)] Loss: 2.891352 (2.7728) Loss_single: 2.208929 (2.0868) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.835s, 38.31/s (0.875s, 36.56/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-19 15:05:27,923 - train: [ INFO] - Train: 67 [ 350/461 ( 76%)] Loss: 2.752493 (2.7702) Loss_single: 2.078811 (2.0858) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.996s, 32.13/s (0.873s, 36.65/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 15:06:09,529 - train: [ INFO] - Train: 67 [ 400/461 ( 87%)] Loss: 3.280502 (2.8269) Loss_single: 2.385339 (2.1191) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (98.6111) Acc@5: 93.7500 (99.3056) Time: 0.729s, 43.92/s (0.868s, 36.88/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 15:06:54,404 - train: [ INFO] - Train: 67 [ 450/461 ( 98%)] Loss: 2.710917 (2.8153) Loss_single: 2.034797 (2.1106) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.971s, 32.94/s (0.871s, 36.74/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 15:07:03,677 - train: [ INFO] - Train: 67 [ 460/461 (100%)] Loss: 2.590438 (2.7949) Loss_single: 1.840044 (2.0860) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.5795) Acc@5: 96.8750 (99.1477) Time: 0.995s, 32.15/s (0.872s, 36.69/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-19 15:07:09,947 - train: [ INFO] - Eval : 67 Time: 5.901 (5.901) Loss: 1.9094 (1.9094) Acc@1: 50.0000 (50.0000)Acc@5: 84.3750 (84.3750) +2025-04-19 15:07:24,080 - train: [ INFO] - Eval : 67 Time: 0.264 (0.393) Loss: 1.8489 (1.8582) Acc@1: 62.5000 (55.0858)Acc@5: 78.1250 (79.1054) +2025-04-19 15:07:31,319 - train: [ INFO] - Eval : 67 Time: 0.070 (0.333) Loss: 2.7000 (1.8625) Acc@1: 50.0000 (53.8936)Acc@5: 50.0000 (79.6839) +2025-04-19 15:07:42,400 - train: [ INFO] - Train: 68 [ 0/461 ( 0%)] Loss: 2.773408 (2.7734) Loss_single: 2.102261 (2.1023) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.082s, 5.26/s (6.082s, 5.26/s) LR: 5.000e-03 Data: 5.146 (5.146) +2025-04-19 15:08:23,069 - train: [ INFO] - Train: 68 [ 50/461 ( 11%)] Loss: 2.543949 (2.6587) Loss_single: 1.875144 (1.9887) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.599s, 53.39/s (0.914s, 35.00/s) LR: 5.000e-03 Data: 0.000 (0.102) +2025-04-19 15:09:05,910 - train: [ INFO] - Train: 68 [ 100/461 ( 22%)] Loss: 2.895581 (2.7376) Loss_single: 2.214151 (2.0639) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.722s, 44.32/s (0.885s, 36.15/s) LR: 5.000e-03 Data: 0.001 (0.052) +2025-04-19 15:09:49,351 - train: [ INFO] - Train: 68 [ 150/461 ( 33%)] Loss: 3.086608 (2.8249) Loss_single: 2.419538 (2.1528) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.735s, 43.55/s (0.879s, 36.39/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-19 15:10:34,703 - train: [ INFO] - Train: 68 [ 200/461 ( 43%)] Loss: 3.138303 (2.8876) Loss_single: 2.438326 (2.2099) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.857s, 37.34/s (0.886s, 36.12/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-19 15:11:16,530 - train: [ INFO] - Train: 68 [ 250/461 ( 54%)] Loss: 2.667606 (2.8509) Loss_single: 1.999840 (2.1749) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.767s, 41.74/s (0.876s, 36.54/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 15:11:54,111 - train: [ INFO] - Train: 68 [ 300/461 ( 65%)] Loss: 2.687184 (2.8275) Loss_single: 1.994046 (2.1490) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.552s, 57.96/s (0.855s, 37.44/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-19 15:12:33,564 - train: [ INFO] - Train: 68 [ 350/461 ( 76%)] Loss: 2.793116 (2.8232) Loss_single: 2.080936 (2.1405) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.156s, 27.68/s (0.845s, 37.86/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 15:13:14,595 - train: [ INFO] - Train: 68 [ 400/461 ( 87%)] Loss: 2.883363 (2.8299) Loss_single: 2.215000 (2.1488) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.029s, 31.09/s (0.842s, 38.01/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 15:13:58,034 - train: [ INFO] - Train: 68 [ 450/461 ( 98%)] Loss: 2.811612 (2.8281) Loss_single: 2.139795 (2.1479) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.759s, 42.16/s (0.845s, 37.88/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 15:14:07,295 - train: [ INFO] - Train: 68 [ 460/461 (100%)] Loss: 2.729498 (2.8191) Loss_single: 2.057069 (2.1396) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.853s, 37.52/s (0.846s, 37.80/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-19 15:14:12,886 - train: [ INFO] - Eval : 68 Time: 5.204 (5.204) Loss: 1.8927 (1.8927) Acc@1: 53.1250 (53.1250)Acc@5: 81.2500 (81.2500) +2025-04-19 15:14:27,079 - train: [ INFO] - Eval : 68 Time: 0.262 (0.380) Loss: 1.8748 (1.8847) Acc@1: 56.2500 (52.2672)Acc@5: 71.8750 (79.4118) +2025-04-19 15:14:34,773 - train: [ INFO] - Eval : 68 Time: 0.062 (0.330) Loss: 3.3558 (1.9012) Acc@1: 0.0000 (51.8504)Acc@5: 50.0000 (79.2213) +2025-04-19 15:14:45,134 - train: [ INFO] - Train: 69 [ 0/461 ( 0%)] Loss: 2.667488 (2.6675) Loss_single: 1.998684 (1.9987) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.148s, 5.20/s (6.148s, 5.20/s) LR: 5.000e-03 Data: 5.322 (5.322) +2025-04-19 15:15:29,059 - train: [ INFO] - Train: 69 [ 50/461 ( 11%)] Loss: 2.595391 (2.6314) Loss_single: 1.930156 (1.9644) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.931s, 34.37/s (0.980s, 32.64/s) LR: 5.000e-03 Data: 0.001 (0.105) +2025-04-19 15:16:09,021 - train: [ INFO] - Train: 69 [ 100/461 ( 22%)] Loss: 2.856069 (2.7063) Loss_single: 2.175999 (2.0349) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.693s, 46.16/s (0.890s, 35.96/s) LR: 5.000e-03 Data: 0.000 (0.053) +2025-04-19 15:16:50,289 - train: [ INFO] - Train: 69 [ 150/461 ( 33%)] Loss: 2.846282 (2.7413) Loss_single: 2.169459 (2.0686) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.816s, 39.21/s (0.868s, 36.87/s) LR: 5.000e-03 Data: 0.001 (0.036) +2025-04-19 15:17:32,095 - train: [ INFO] - Train: 69 [ 200/461 ( 43%)] Loss: 2.765646 (2.7462) Loss_single: 2.088666 (2.0726) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.883s, 36.26/s (0.859s, 37.24/s) LR: 5.000e-03 Data: 0.012 (0.028) +2025-04-19 15:18:14,313 - train: [ INFO] - Train: 69 [ 250/461 ( 54%)] Loss: 2.767488 (2.7497) Loss_single: 2.065409 (2.0714) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.010s, 31.68/s (0.856s, 37.38/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-19 15:18:56,316 - train: [ INFO] - Train: 69 [ 300/461 ( 65%)] Loss: 2.761690 (2.7514) Loss_single: 2.083904 (2.0732) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.036s, 30.87/s (0.853s, 37.51/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-19 15:19:40,546 - train: [ INFO] - Train: 69 [ 350/461 ( 76%)] Loss: 2.670308 (2.7413) Loss_single: 1.995866 (2.0635) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.824s, 38.85/s (0.857s, 37.32/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-19 15:20:24,127 - train: [ INFO] - Train: 69 [ 400/461 ( 87%)] Loss: 2.887176 (2.7575) Loss_single: 2.223074 (2.0812) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.833s, 38.42/s (0.859s, 37.25/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-19 15:21:06,694 - train: [ INFO] - Train: 69 [ 450/461 ( 98%)] Loss: 2.786715 (2.7604) Loss_single: 2.097911 (2.0829) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.908s, 35.24/s (0.858s, 37.29/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-19 15:21:14,862 - train: [ INFO] - Train: 69 [ 460/461 (100%)] Loss: 2.888932 (2.7721) Loss_single: 2.219460 (2.0953) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.910s, 35.18/s (0.857s, 37.33/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-19 15:21:20,100 - train: [ INFO] - Eval : 69 Time: 4.866 (4.866) Loss: 1.9764 (1.9764) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-19 15:21:34,264 - train: [ INFO] - Eval : 69 Time: 0.299 (0.373) Loss: 1.8367 (1.8840) Acc@1: 59.3750 (53.4926)Acc@5: 81.2500 (78.9216) +2025-04-19 15:21:42,066 - train: [ INFO] - Eval : 69 Time: 0.081 (0.327) Loss: 2.9713 (1.8981) Acc@1: 0.0000 (52.6985)Acc@5: 50.0000 (78.3346) +2025-04-19 15:21:52,372 - train: [ INFO] - Train: 70 [ 0/461 ( 0%)] Loss: 2.877685 (2.8777) Loss_single: 2.195342 (2.1953) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.844s, 5.48/s (5.844s, 5.48/s) LR: 5.000e-04 Data: 4.853 (4.853) +2025-04-19 15:22:35,886 - train: [ INFO] - Train: 70 [ 50/461 ( 11%)] Loss: 2.639669 (2.7587) Loss_single: 1.975518 (2.0854) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.781s, 40.96/s (0.967s, 33.11/s) LR: 5.000e-04 Data: 0.000 (0.096) +2025-04-19 15:23:19,137 - train: [ INFO] - Train: 70 [ 100/461 ( 22%)] Loss: 2.777622 (2.7650) Loss_single: 2.092826 (2.0879) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.952s, 33.60/s (0.915s, 34.97/s) LR: 5.000e-04 Data: 0.000 (0.049) +2025-04-19 15:24:02,094 - train: [ INFO] - Train: 70 [ 150/461 ( 33%)] Loss: 2.449630 (2.6862) Loss_single: 1.784928 (2.0122) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.826s, 38.72/s (0.896s, 35.72/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-19 15:24:45,061 - train: [ INFO] - Train: 70 [ 200/461 ( 43%)] Loss: 2.545625 (2.6580) Loss_single: 1.879425 (1.9856) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.730s, 43.86/s (0.886s, 36.10/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-19 15:25:20,027 - train: [ INFO] - Train: 70 [ 250/461 ( 54%)] Loss: 2.599317 (2.6483) Loss_single: 1.903660 (1.9719) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.984s, 32.53/s (0.849s, 37.69/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-19 15:26:02,946 - train: [ INFO] - Train: 70 [ 300/461 ( 65%)] Loss: 2.432484 (2.6174) Loss_single: 1.768835 (1.9429) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.677s, 47.24/s (0.850s, 37.63/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 15:26:44,912 - train: [ INFO] - Train: 70 [ 350/461 ( 76%)] Loss: 2.415356 (2.5922) Loss_single: 1.753708 (1.9193) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.900s, 35.57/s (0.849s, 37.71/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 15:27:26,297 - train: [ INFO] - Train: 70 [ 400/461 ( 87%)] Loss: 2.624751 (2.5958) Loss_single: 1.943801 (1.9220) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.011s, 31.65/s (0.846s, 37.84/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:28:07,560 - train: [ INFO] - Train: 70 [ 450/461 ( 98%)] Loss: 2.512922 (2.5875) Loss_single: 1.839048 (1.9137) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.725s, 44.15/s (0.843s, 37.95/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 15:28:15,303 - train: [ INFO] - Train: 70 [ 460/461 (100%)] Loss: 2.633172 (2.5917) Loss_single: 1.886823 (1.9113) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 96.8750 (99.7159) Time: 0.587s, 54.47/s (0.842s, 38.02/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:28:20,897 - train: [ INFO] - Eval : 70 Time: 5.272 (5.272) Loss: 1.9819 (1.9819) Acc@1: 46.8750 (46.8750)Acc@5: 84.3750 (84.3750) +2025-04-19 15:28:34,934 - train: [ INFO] - Eval : 70 Time: 0.280 (0.379) Loss: 1.7714 (1.8724) Acc@1: 65.6250 (54.7794)Acc@5: 81.2500 (79.7181) +2025-04-19 15:28:42,926 - train: [ INFO] - Eval : 70 Time: 0.078 (0.333) Loss: 2.9308 (1.8891) Acc@1: 50.0000 (53.9322)Acc@5: 50.0000 (79.1056) +2025-04-19 15:28:53,577 - train: [ INFO] - Train: 71 [ 0/461 ( 0%)] Loss: 2.435403 (2.4354) Loss_single: 1.769016 (1.7690) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.931s, 5.40/s (5.931s, 5.40/s) LR: 5.000e-04 Data: 4.746 (4.746) +2025-04-19 15:29:35,676 - train: [ INFO] - Train: 71 [ 50/461 ( 11%)] Loss: 2.515505 (2.4755) Loss_single: 1.809073 (1.7890) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.856s, 37.38/s (0.940s, 34.03/s) LR: 5.000e-04 Data: 0.001 (0.094) +2025-04-19 15:30:17,213 - train: [ INFO] - Train: 71 [ 100/461 ( 22%)] Loss: 2.608616 (2.5198) Loss_single: 1.944847 (1.8410) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.716s, 44.68/s (0.885s, 36.15/s) LR: 5.000e-04 Data: 0.000 (0.048) +2025-04-19 15:30:59,690 - train: [ INFO] - Train: 71 [ 150/461 ( 33%)] Loss: 2.512690 (2.5181) Loss_single: 1.846034 (1.8422) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.836s, 38.29/s (0.873s, 36.66/s) LR: 5.000e-04 Data: 0.000 (0.032) +2025-04-19 15:31:41,338 - train: [ INFO] - Train: 71 [ 200/461 ( 43%)] Loss: 2.377393 (2.4899) Loss_single: 1.715384 (1.8169) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.102s, 29.03/s (0.863s, 37.10/s) LR: 5.000e-04 Data: 0.000 (0.024) +2025-04-19 15:32:24,680 - train: [ INFO] - Train: 71 [ 250/461 ( 54%)] Loss: 2.414207 (2.4773) Loss_single: 1.728586 (1.8022) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.739s, 43.29/s (0.863s, 37.08/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-19 15:33:07,323 - train: [ INFO] - Train: 71 [ 300/461 ( 65%)] Loss: 2.472768 (2.4767) Loss_single: 1.811263 (1.8035) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.992s, 32.25/s (0.861s, 37.16/s) LR: 5.000e-04 Data: 0.001 (0.017) +2025-04-19 15:33:50,653 - train: [ INFO] - Train: 71 [ 350/461 ( 76%)] Loss: 2.274328 (2.4514) Loss_single: 1.613949 (1.7798) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.737s, 43.40/s (0.862s, 37.13/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 15:34:34,271 - train: [ INFO] - Train: 71 [ 400/461 ( 87%)] Loss: 2.946005 (2.5063) Loss_single: 2.144946 (1.8203) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.946s, 33.84/s (0.863s, 37.08/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:35:17,972 - train: [ INFO] - Train: 71 [ 450/461 ( 98%)] Loss: 2.497031 (2.5054) Loss_single: 1.833913 (1.8217) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.673s, 47.55/s (0.864s, 37.04/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:35:26,372 - train: [ INFO] - Train: 71 [ 460/461 (100%)] Loss: 2.456802 (2.5010) Loss_single: 1.793133 (1.8191) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.766s, 41.79/s (0.863s, 37.06/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:35:32,357 - train: [ INFO] - Eval : 71 Time: 5.669 (5.669) Loss: 1.9596 (1.9596) Acc@1: 46.8750 (46.8750)Acc@5: 81.2500 (81.2500) +2025-04-19 15:35:46,058 - train: [ INFO] - Eval : 71 Time: 0.307 (0.380) Loss: 1.8348 (1.8612) Acc@1: 59.3750 (55.1471)Acc@5: 84.3750 (81.4951) +2025-04-19 15:35:53,942 - train: [ INFO] - Eval : 71 Time: 0.067 (0.332) Loss: 2.8516 (1.8770) Acc@1: 50.0000 (54.3562)Acc@5: 50.0000 (80.5320) +2025-04-19 15:36:04,052 - train: [ INFO] - Train: 72 [ 0/461 ( 0%)] Loss: 2.559281 (2.5593) Loss_single: 1.897653 (1.8977) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.566s, 5.75/s (5.566s, 5.75/s) LR: 5.000e-04 Data: 4.723 (4.723) +2025-04-19 15:36:48,117 - train: [ INFO] - Train: 72 [ 50/461 ( 11%)] Loss: 2.302281 (2.4308) Loss_single: 1.643376 (1.7705) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.092s, 29.32/s (0.971s, 32.96/s) LR: 5.000e-04 Data: 0.000 (0.093) +2025-04-19 15:37:29,155 - train: [ INFO] - Train: 72 [ 100/461 ( 22%)] Loss: 2.729562 (2.5304) Loss_single: 2.001590 (1.8475) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.766s, 41.78/s (0.896s, 35.71/s) LR: 5.000e-04 Data: 0.000 (0.048) +2025-04-19 15:38:05,262 - train: [ INFO] - Train: 72 [ 150/461 ( 33%)] Loss: 2.648889 (2.5600) Loss_single: 1.903655 (1.8616) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.757s, 42.30/s (0.838s, 38.18/s) LR: 5.000e-04 Data: 0.000 (0.032) +2025-04-19 15:38:50,272 - train: [ INFO] - Train: 72 [ 200/461 ( 43%)] Loss: 2.695737 (2.5871) Loss_single: 2.003726 (1.8900) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (100.0000) Time: 1.021s, 31.33/s (0.853s, 37.50/s) LR: 5.000e-04 Data: 0.001 (0.024) +2025-04-19 15:39:33,702 - train: [ INFO] - Train: 72 [ 250/461 ( 54%)] Loss: 2.620003 (2.5926) Loss_single: 1.922172 (1.8954) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.942s, 33.98/s (0.856s, 37.38/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 15:40:16,186 - train: [ INFO] - Train: 72 [ 300/461 ( 65%)] Loss: 2.497285 (2.5790) Loss_single: 1.837886 (1.8872) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.800s, 40.01/s (0.855s, 37.44/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 15:40:58,099 - train: [ INFO] - Train: 72 [ 350/461 ( 76%)] Loss: 2.293475 (2.5433) Loss_single: 1.633266 (1.8554) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.745s, 42.98/s (0.852s, 37.56/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 15:41:42,599 - train: [ INFO] - Train: 72 [ 400/461 ( 87%)] Loss: 2.516727 (2.5404) Loss_single: 1.854511 (1.8553) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 1.099s, 29.12/s (0.857s, 37.36/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:42:25,513 - train: [ INFO] - Train: 72 [ 450/461 ( 98%)] Loss: 2.591049 (2.5454) Loss_single: 1.928102 (1.8626) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.807s, 39.67/s (0.857s, 37.35/s) LR: 5.000e-04 Data: 0.001 (0.011) +2025-04-19 15:42:34,497 - train: [ INFO] - Train: 72 [ 460/461 (100%)] Loss: 2.396545 (2.5319) Loss_single: 1.728678 (1.8504) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.719s, 44.52/s (0.857s, 37.32/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:42:39,735 - train: [ INFO] - Eval : 72 Time: 4.864 (4.864) Loss: 2.0011 (2.0011) Acc@1: 46.8750 (46.8750)Acc@5: 81.2500 (81.2500) +2025-04-19 15:42:54,232 - train: [ INFO] - Eval : 72 Time: 0.272 (0.380) Loss: 1.8232 (1.8607) Acc@1: 62.5000 (56.1887)Acc@5: 78.1250 (80.3922) +2025-04-19 15:43:01,921 - train: [ INFO] - Eval : 72 Time: 0.083 (0.330) Loss: 2.7596 (1.8751) Acc@1: 50.0000 (55.4742)Acc@5: 50.0000 (80.0694) +2025-04-19 15:43:06,668 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/checkpoint-72.pth.tar', 55.47417116422513) + +2025-04-19 15:43:12,348 - train: [ INFO] - Train: 73 [ 0/461 ( 0%)] Loss: 2.443336 (2.4433) Loss_single: 1.777291 (1.7773) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.591s, 5.72/s (5.591s, 5.72/s) LR: 5.000e-04 Data: 4.768 (4.768) +2025-04-19 15:43:57,058 - train: [ INFO] - Train: 73 [ 50/461 ( 11%)] Loss: 2.536565 (2.4900) Loss_single: 1.876506 (1.8269) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.720s, 44.45/s (0.985s, 32.50/s) LR: 5.000e-04 Data: 0.000 (0.095) +2025-04-19 15:44:42,233 - train: [ INFO] - Train: 73 [ 100/461 ( 22%)] Loss: 2.492021 (2.4906) Loss_single: 1.828502 (1.8274) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.895s, 35.75/s (0.944s, 33.91/s) LR: 5.000e-04 Data: 0.000 (0.048) +2025-04-19 15:45:24,820 - train: [ INFO] - Train: 73 [ 150/461 ( 33%)] Loss: 2.375481 (2.4619) Loss_single: 1.715271 (1.7994) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.016s, 31.48/s (0.913s, 35.06/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-19 15:46:06,352 - train: [ INFO] - Train: 73 [ 200/461 ( 43%)] Loss: 2.827048 (2.5349) Loss_single: 2.032173 (1.8459) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (98.7500) Acc@5: 96.8750 (99.3750) Time: 0.851s, 37.60/s (0.892s, 35.87/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-19 15:46:48,236 - train: [ INFO] - Train: 73 [ 250/461 ( 54%)] Loss: 2.539690 (2.5357) Loss_single: 1.824891 (1.8424) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 1.019s, 31.39/s (0.881s, 36.33/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 15:47:29,952 - train: [ INFO] - Train: 73 [ 300/461 ( 65%)] Loss: 2.463369 (2.5254) Loss_single: 1.804390 (1.8370) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.736s, 43.46/s (0.873s, 36.66/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 15:48:13,645 - train: [ INFO] - Train: 73 [ 350/461 ( 76%)] Loss: 2.624377 (2.5377) Loss_single: 1.963380 (1.8528) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.923s, 34.69/s (0.873s, 36.66/s) LR: 5.000e-04 Data: 0.011 (0.014) +2025-04-19 15:48:56,593 - train: [ INFO] - Train: 73 [ 400/461 ( 87%)] Loss: 2.393540 (2.5217) Loss_single: 1.733305 (1.8395) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.960s, 33.32/s (0.871s, 36.74/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 15:49:39,711 - train: [ INFO] - Train: 73 [ 450/461 ( 98%)] Loss: 2.752642 (2.5448) Loss_single: 2.001884 (1.8558) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.779s, 41.06/s (0.870s, 36.79/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:49:47,608 - train: [ INFO] - Train: 73 [ 460/461 (100%)] Loss: 2.705797 (2.5594) Loss_single: 1.981063 (1.8672) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1477) Acc@5: 100.0000 (99.7159) Time: 0.718s, 44.60/s (0.868s, 36.87/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 15:49:53,116 - train: [ INFO] - Eval : 73 Time: 5.158 (5.158) Loss: 1.9289 (1.9289) Acc@1: 50.0000 (50.0000)Acc@5: 81.2500 (81.2500) +2025-04-19 15:50:07,343 - train: [ INFO] - Eval : 73 Time: 0.267 (0.380) Loss: 1.8131 (1.8622) Acc@1: 59.3750 (55.7598)Acc@5: 81.2500 (80.7598) +2025-04-19 15:50:15,443 - train: [ INFO] - Eval : 73 Time: 0.074 (0.335) Loss: 2.7800 (1.8776) Acc@1: 50.0000 (55.0116)Acc@5: 50.0000 (80.3007) +2025-04-19 15:50:25,661 - train: [ INFO] - Train: 74 [ 0/461 ( 0%)] Loss: 2.366094 (2.3661) Loss_single: 1.706444 (1.7064) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.033s, 5.30/s (6.033s, 5.30/s) LR: 5.000e-04 Data: 5.075 (5.075) +2025-04-19 15:51:07,901 - train: [ INFO] - Train: 74 [ 50/461 ( 11%)] Loss: 2.468256 (2.4172) Loss_single: 1.795985 (1.7512) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.668s, 47.90/s (0.944s, 33.88/s) LR: 5.000e-04 Data: 0.003 (0.100) +2025-04-19 15:51:47,771 - train: [ INFO] - Train: 74 [ 100/461 ( 22%)] Loss: 2.376946 (2.4038) Loss_single: 1.714161 (1.7389) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.167s, 27.43/s (0.871s, 36.74/s) LR: 5.000e-04 Data: 0.000 (0.051) +2025-04-19 15:52:30,779 - train: [ INFO] - Train: 74 [ 150/461 ( 33%)] Loss: 2.438623 (2.4125) Loss_single: 1.771557 (1.7470) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.833s, 38.40/s (0.867s, 36.91/s) LR: 5.000e-04 Data: 0.000 (0.035) +2025-04-19 15:53:11,989 - train: [ INFO] - Train: 74 [ 200/461 ( 43%)] Loss: 2.342917 (2.3986) Loss_single: 1.682419 (1.7341) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.794s, 40.31/s (0.856s, 37.39/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-19 15:53:54,551 - train: [ INFO] - Train: 74 [ 250/461 ( 54%)] Loss: 2.423759 (2.4028) Loss_single: 1.734379 (1.7342) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.818s, 39.10/s (0.855s, 37.44/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 15:54:39,553 - train: [ INFO] - Train: 74 [ 300/461 ( 65%)] Loss: 2.391421 (2.4011) Loss_single: 1.729682 (1.7335) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.796s, 40.18/s (0.862s, 37.12/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 15:55:24,408 - train: [ INFO] - Train: 74 [ 350/461 ( 76%)] Loss: 2.467454 (2.4094) Loss_single: 1.809240 (1.7430) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.920s, 34.77/s (0.867s, 36.92/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-19 15:56:06,345 - train: [ INFO] - Train: 74 [ 400/461 ( 87%)] Loss: 2.443058 (2.4132) Loss_single: 1.725561 (1.7410) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.761s, 42.03/s (0.863s, 37.07/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 15:56:48,764 - train: [ INFO] - Train: 74 [ 450/461 ( 98%)] Loss: 2.746475 (2.4465) Loss_single: 2.022912 (1.7692) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.003s, 31.90/s (0.861s, 37.16/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 15:56:57,211 - train: [ INFO] - Train: 74 [ 460/461 (100%)] Loss: 2.436346 (2.4456) Loss_single: 1.773417 (1.7696) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.735s, 43.54/s (0.861s, 37.17/s) LR: 5.000e-04 Data: 0.005 (0.012) +2025-04-19 15:57:03,107 - train: [ INFO] - Eval : 74 Time: 5.547 (5.547) Loss: 1.9857 (1.9857) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-19 15:57:17,350 - train: [ INFO] - Eval : 74 Time: 0.226 (0.388) Loss: 1.8408 (1.8700) Acc@1: 56.2500 (55.0245)Acc@5: 81.2500 (80.4534) +2025-04-19 15:57:25,089 - train: [ INFO] - Eval : 74 Time: 0.062 (0.336) Loss: 2.8719 (1.8860) Acc@1: 50.0000 (54.2020)Acc@5: 50.0000 (80.0694) +2025-04-19 15:57:35,009 - train: [ INFO] - Train: 75 [ 0/461 ( 0%)] Loss: 2.503353 (2.5034) Loss_single: 1.834616 (1.8346) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.576s, 5.74/s (5.576s, 5.74/s) LR: 5.000e-04 Data: 4.761 (4.761) +2025-04-19 15:58:15,946 - train: [ INFO] - Train: 75 [ 50/461 ( 11%)] Loss: 2.578986 (2.5412) Loss_single: 1.898567 (1.8666) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.078s, 29.68/s (0.911s, 35.13/s) LR: 5.000e-04 Data: 0.000 (0.095) +2025-04-19 15:58:58,326 - train: [ INFO] - Train: 75 [ 100/461 ( 22%)] Loss: 2.346641 (2.4763) Loss_single: 1.687679 (1.8070) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.670s, 47.75/s (0.879s, 36.41/s) LR: 5.000e-04 Data: 0.002 (0.048) +2025-04-19 15:59:40,332 - train: [ INFO] - Train: 75 [ 150/461 ( 33%)] Loss: 2.783145 (2.5530) Loss_single: 2.074092 (1.8737) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.811s, 39.44/s (0.866s, 36.97/s) LR: 5.000e-04 Data: 0.000 (0.032) +2025-04-19 16:00:22,127 - train: [ INFO] - Train: 75 [ 200/461 ( 43%)] Loss: 2.672195 (2.5769) Loss_single: 2.006746 (1.9003) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.809s, 39.57/s (0.858s, 37.31/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-19 16:01:04,890 - train: [ INFO] - Train: 75 [ 250/461 ( 54%)] Loss: 2.418769 (2.5505) Loss_single: 1.753447 (1.8759) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.824s, 38.84/s (0.857s, 37.35/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 16:01:46,532 - train: [ INFO] - Train: 75 [ 300/461 ( 65%)] Loss: 2.656459 (2.5656) Loss_single: 1.993276 (1.8926) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.765s, 41.81/s (0.853s, 37.53/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 16:02:25,901 - train: [ INFO] - Train: 75 [ 350/461 ( 76%)] Loss: 2.257840 (2.5272) Loss_single: 1.594639 (1.8554) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.795s, 40.28/s (0.843s, 37.96/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-19 16:03:08,455 - train: [ INFO] - Train: 75 [ 400/461 ( 87%)] Loss: 2.548268 (2.5295) Loss_single: 1.826554 (1.8522) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 100.0000 (100.0000) Time: 1.030s, 31.08/s (0.844s, 37.92/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:03:51,545 - train: [ INFO] - Train: 75 [ 450/461 ( 98%)] Loss: 2.442918 (2.5209) Loss_single: 1.782695 (1.8452) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.755s, 42.40/s (0.846s, 37.84/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 16:04:00,221 - train: [ INFO] - Train: 75 [ 460/461 (100%)] Loss: 2.399283 (2.5098) Loss_single: 1.733231 (1.8350) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.642s, 49.87/s (0.846s, 37.82/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 16:04:06,100 - train: [ INFO] - Eval : 75 Time: 5.507 (5.507) Loss: 1.9222 (1.9222) Acc@1: 50.0000 (50.0000)Acc@5: 84.3750 (84.3750) +2025-04-19 16:04:20,080 - train: [ INFO] - Eval : 75 Time: 0.300 (0.382) Loss: 1.8301 (1.8753) Acc@1: 59.3750 (55.6373)Acc@5: 78.1250 (80.2083) +2025-04-19 16:04:27,871 - train: [ INFO] - Eval : 75 Time: 0.071 (0.333) Loss: 2.9959 (1.8918) Acc@1: 50.0000 (54.5875)Acc@5: 50.0000 (80.1465) +2025-04-19 16:04:38,620 - train: [ INFO] - Train: 76 [ 0/461 ( 0%)] Loss: 2.460595 (2.4606) Loss_single: 1.795418 (1.7954) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.872s, 5.45/s (5.872s, 5.45/s) LR: 5.000e-04 Data: 5.082 (5.082) +2025-04-19 16:05:22,969 - train: [ INFO] - Train: 76 [ 50/461 ( 11%)] Loss: 2.678144 (2.5694) Loss_single: 1.940113 (1.8678) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (98.4375) Time: 0.972s, 32.91/s (0.983s, 32.54/s) LR: 5.000e-04 Data: 0.000 (0.100) +2025-04-19 16:06:07,260 - train: [ INFO] - Train: 76 [ 100/461 ( 22%)] Loss: 2.735947 (2.6249) Loss_single: 2.027523 (1.9210) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.786s, 40.71/s (0.934s, 34.25/s) LR: 5.000e-04 Data: 0.000 (0.051) +2025-04-19 16:06:46,686 - train: [ INFO] - Train: 76 [ 150/461 ( 33%)] Loss: 2.506512 (2.5953) Loss_single: 1.845020 (1.9020) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.905s, 35.35/s (0.885s, 36.14/s) LR: 5.000e-04 Data: 0.002 (0.034) +2025-04-19 16:07:29,383 - train: [ INFO] - Train: 76 [ 200/461 ( 43%)] Loss: 2.301838 (2.5366) Loss_single: 1.644946 (1.8506) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 1.198s, 26.70/s (0.877s, 36.48/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-19 16:08:13,976 - train: [ INFO] - Train: 76 [ 250/461 ( 54%)] Loss: 2.750070 (2.5722) Loss_single: 1.999651 (1.8754) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.798s, 40.09/s (0.880s, 36.37/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 16:08:57,665 - train: [ INFO] - Train: 76 [ 300/461 ( 65%)] Loss: 2.492197 (2.5608) Loss_single: 1.832891 (1.8694) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.1071) Time: 0.950s, 33.67/s (0.879s, 36.42/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 16:09:42,224 - train: [ INFO] - Train: 76 [ 350/461 ( 76%)] Loss: 2.456352 (2.5477) Loss_single: 1.770808 (1.8570) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 1.040s, 30.77/s (0.880s, 36.35/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 16:10:23,062 - train: [ INFO] - Train: 76 [ 400/461 ( 87%)] Loss: 2.461972 (2.5382) Loss_single: 1.799028 (1.8506) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.3056) Time: 0.353s, 90.74/s (0.872s, 36.69/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:10:58,733 - train: [ INFO] - Train: 76 [ 450/461 ( 98%)] Loss: 2.506607 (2.5350) Loss_single: 1.839829 (1.8495) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 1.366s, 23.43/s (0.854s, 37.45/s) LR: 5.000e-04 Data: 0.002 (0.012) +2025-04-19 16:11:06,785 - train: [ INFO] - Train: 76 [ 460/461 (100%)] Loss: 2.382365 (2.5211) Loss_single: 1.723683 (1.8381) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.4318) Time: 0.581s, 55.10/s (0.853s, 37.50/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:11:12,830 - train: [ INFO] - Eval : 76 Time: 5.738 (5.738) Loss: 1.9222 (1.9222) Acc@1: 53.1250 (53.1250)Acc@5: 81.2500 (81.2500) +2025-04-19 16:11:26,081 - train: [ INFO] - Eval : 76 Time: 0.292 (0.372) Loss: 1.8155 (1.8751) Acc@1: 62.5000 (55.7598)Acc@5: 78.1250 (80.3922) +2025-04-19 16:11:34,048 - train: [ INFO] - Eval : 76 Time: 0.057 (0.329) Loss: 2.9991 (1.8915) Acc@1: 50.0000 (54.5104)Acc@5: 50.0000 (80.1079) +2025-04-19 16:11:43,987 - train: [ INFO] - Train: 77 [ 0/461 ( 0%)] Loss: 2.382882 (2.3829) Loss_single: 1.704064 (1.7041) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.476s, 5.84/s (5.476s, 5.84/s) LR: 5.000e-04 Data: 4.711 (4.711) +2025-04-19 16:12:27,434 - train: [ INFO] - Train: 77 [ 50/461 ( 11%)] Loss: 2.563112 (2.4730) Loss_single: 1.869752 (1.7869) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.034s, 30.96/s (0.957s, 33.44/s) LR: 5.000e-04 Data: 0.005 (0.094) +2025-04-19 16:13:08,796 - train: [ INFO] - Train: 77 [ 100/461 ( 22%)] Loss: 2.317950 (2.4213) Loss_single: 1.660479 (1.7448) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.879s, 36.40/s (0.892s, 35.87/s) LR: 5.000e-04 Data: 0.000 (0.048) +2025-04-19 16:13:52,850 - train: [ INFO] - Train: 77 [ 150/461 ( 33%)] Loss: 2.318031 (2.3955) Loss_single: 1.660059 (1.7236) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.808s, 39.63/s (0.888s, 36.04/s) LR: 5.000e-04 Data: 0.000 (0.032) +2025-04-19 16:14:35,322 - train: [ INFO] - Train: 77 [ 200/461 ( 43%)] Loss: 2.390775 (2.3945) Loss_single: 1.726404 (1.7242) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.739s, 43.32/s (0.878s, 36.45/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-19 16:15:20,016 - train: [ INFO] - Train: 77 [ 250/461 ( 54%)] Loss: 2.329794 (2.3838) Loss_single: 1.670959 (1.7153) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.793s, 40.33/s (0.881s, 36.33/s) LR: 5.000e-04 Data: 0.006 (0.020) +2025-04-19 16:16:06,104 - train: [ INFO] - Train: 77 [ 300/461 ( 65%)] Loss: 2.599641 (2.4146) Loss_single: 1.939525 (1.7473) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.868s, 36.88/s (0.887s, 36.06/s) LR: 5.000e-04 Data: 0.004 (0.017) +2025-04-19 16:16:48,532 - train: [ INFO] - Train: 77 [ 350/461 ( 76%)] Loss: 2.541550 (2.4305) Loss_single: 1.836240 (1.7584) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.072s, 29.86/s (0.882s, 36.29/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 16:17:29,434 - train: [ INFO] - Train: 77 [ 400/461 ( 87%)] Loss: 2.459125 (2.4337) Loss_single: 1.801922 (1.7633) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.704s, 45.45/s (0.874s, 36.63/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:18:09,684 - train: [ INFO] - Train: 77 [ 450/461 ( 98%)] Loss: 2.743422 (2.4646) Loss_single: 2.082676 (1.7952) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.730s, 43.84/s (0.866s, 36.95/s) LR: 5.000e-04 Data: 0.005 (0.011) +2025-04-19 16:18:17,750 - train: [ INFO] - Train: 77 [ 460/461 (100%)] Loss: 2.494214 (2.4673) Loss_single: 1.834733 (1.7988) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.718s, 44.56/s (0.865s, 37.01/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 16:18:23,418 - train: [ INFO] - Eval : 77 Time: 5.292 (5.292) Loss: 1.9205 (1.9205) Acc@1: 53.1250 (53.1250)Acc@5: 81.2500 (81.2500) +2025-04-19 16:18:37,535 - train: [ INFO] - Eval : 77 Time: 0.280 (0.381) Loss: 1.8391 (1.8713) Acc@1: 62.5000 (55.8824)Acc@5: 78.1250 (80.0858) +2025-04-19 16:18:45,840 - train: [ INFO] - Eval : 77 Time: 0.078 (0.338) Loss: 2.6944 (1.8846) Acc@1: 50.0000 (54.9345)Acc@5: 50.0000 (80.0694) +2025-04-19 16:18:56,112 - train: [ INFO] - Train: 78 [ 0/461 ( 0%)] Loss: 2.547627 (2.5476) Loss_single: 1.816907 (1.8169) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 5.733s, 5.58/s (5.733s, 5.58/s) LR: 5.000e-04 Data: 4.799 (4.799) +2025-04-19 16:19:39,773 - train: [ INFO] - Train: 78 [ 50/461 ( 11%)] Loss: 2.574661 (2.5611) Loss_single: 1.914657 (1.8658) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.774s, 41.34/s (0.966s, 33.12/s) LR: 5.000e-04 Data: 0.001 (0.095) +2025-04-19 16:20:25,166 - train: [ INFO] - Train: 78 [ 100/461 ( 22%)] Loss: 2.611567 (2.5780) Loss_single: 1.951539 (1.8944) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.897s, 35.66/s (0.936s, 34.17/s) LR: 5.000e-04 Data: 0.004 (0.049) +2025-04-19 16:21:09,092 - train: [ INFO] - Train: 78 [ 150/461 ( 33%)] Loss: 2.578181 (2.5780) Loss_single: 1.912252 (1.8988) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.739s, 43.30/s (0.917s, 34.91/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-19 16:21:50,032 - train: [ INFO] - Train: 78 [ 200/461 ( 43%)] Loss: 2.561166 (2.5746) Loss_single: 1.904834 (1.9000) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.733s, 43.65/s (0.892s, 35.88/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-19 16:22:28,709 - train: [ INFO] - Train: 78 [ 250/461 ( 54%)] Loss: 2.358908 (2.5387) Loss_single: 1.700357 (1.8668) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.819s, 39.09/s (0.868s, 36.87/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 16:23:09,803 - train: [ INFO] - Train: 78 [ 300/461 ( 65%)] Loss: 2.366565 (2.5141) Loss_single: 1.686846 (1.8411) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.824s, 38.85/s (0.860s, 37.21/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 16:23:50,030 - train: [ INFO] - Train: 78 [ 350/461 ( 76%)] Loss: 2.668408 (2.5334) Loss_single: 1.996465 (1.8605) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.46/s (0.852s, 37.56/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 16:24:32,437 - train: [ INFO] - Train: 78 [ 400/461 ( 87%)] Loss: 2.444705 (2.5235) Loss_single: 1.770149 (1.8504) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.766s, 41.75/s (0.851s, 37.59/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 16:25:12,526 - train: [ INFO] - Train: 78 [ 450/461 ( 98%)] Loss: 2.378137 (2.5090) Loss_single: 1.720345 (1.8374) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.751s, 42.60/s (0.846s, 37.84/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:25:20,458 - train: [ INFO] - Train: 78 [ 460/461 (100%)] Loss: 2.690172 (2.5255) Loss_single: 2.023685 (1.8544) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.847s, 37.77/s (0.844s, 37.90/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:25:26,568 - train: [ INFO] - Eval : 78 Time: 5.796 (5.796) Loss: 1.9187 (1.9187) Acc@1: 46.8750 (46.8750)Acc@5: 84.3750 (84.3750) +2025-04-19 16:25:40,376 - train: [ INFO] - Eval : 78 Time: 0.274 (0.384) Loss: 1.8618 (1.8795) Acc@1: 59.3750 (55.2083)Acc@5: 75.0000 (80.2083) +2025-04-19 16:25:48,149 - train: [ INFO] - Eval : 78 Time: 0.061 (0.334) Loss: 2.8537 (1.8949) Acc@1: 50.0000 (54.3177)Acc@5: 50.0000 (80.1079) +2025-04-19 16:25:58,421 - train: [ INFO] - Train: 79 [ 0/461 ( 0%)] Loss: 2.369012 (2.3690) Loss_single: 1.710724 (1.7107) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.985s, 5.35/s (5.985s, 5.35/s) LR: 5.000e-04 Data: 5.145 (5.145) +2025-04-19 16:26:39,852 - train: [ INFO] - Train: 79 [ 50/461 ( 11%)] Loss: 2.507338 (2.4382) Loss_single: 1.849825 (1.7803) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.843s, 37.95/s (0.928s, 34.48/s) LR: 5.000e-04 Data: 0.000 (0.102) +2025-04-19 16:27:20,130 - train: [ INFO] - Train: 79 [ 100/461 ( 22%)] Loss: 2.493022 (2.4565) Loss_single: 1.830113 (1.7969) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.665s, 48.10/s (0.867s, 36.91/s) LR: 5.000e-04 Data: 0.000 (0.052) +2025-04-19 16:27:56,955 - train: [ INFO] - Train: 79 [ 150/461 ( 33%)] Loss: 2.511420 (2.4702) Loss_single: 1.854301 (1.8112) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.655s, 48.84/s (0.823s, 38.86/s) LR: 5.000e-04 Data: 0.001 (0.035) +2025-04-19 16:28:41,965 - train: [ INFO] - Train: 79 [ 200/461 ( 43%)] Loss: 2.412043 (2.4586) Loss_single: 1.749592 (1.7989) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.926s, 34.56/s (0.842s, 38.00/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-19 16:29:25,420 - train: [ INFO] - Train: 79 [ 250/461 ( 54%)] Loss: 2.389980 (2.4471) Loss_single: 1.723468 (1.7863) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.759s, 42.14/s (0.847s, 37.77/s) LR: 5.000e-04 Data: 0.000 (0.022) +2025-04-19 16:30:07,753 - train: [ INFO] - Train: 79 [ 300/461 ( 65%)] Loss: 2.323813 (2.4295) Loss_single: 1.665727 (1.7691) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.785s, 40.76/s (0.847s, 37.78/s) LR: 5.000e-04 Data: 0.005 (0.018) +2025-04-19 16:30:49,827 - train: [ INFO] - Train: 79 [ 350/461 ( 76%)] Loss: 2.469455 (2.4345) Loss_single: 1.809893 (1.7742) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.870s, 36.79/s (0.846s, 37.82/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 16:31:33,436 - train: [ INFO] - Train: 79 [ 400/461 ( 87%)] Loss: 2.664742 (2.4601) Loss_single: 1.907686 (1.7890) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 96.8750 (99.6528) Time: 0.870s, 36.80/s (0.849s, 37.68/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-19 16:32:14,963 - train: [ INFO] - Train: 79 [ 450/461 ( 98%)] Loss: 2.536409 (2.4677) Loss_single: 1.877047 (1.7978) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.708s, 45.22/s (0.847s, 37.78/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:32:23,057 - train: [ INFO] - Train: 79 [ 460/461 (100%)] Loss: 2.268678 (2.4496) Loss_single: 1.611290 (1.7809) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.836s, 38.26/s (0.846s, 37.82/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:32:29,594 - train: [ INFO] - Eval : 79 Time: 6.191 (6.191) Loss: 1.9254 (1.9254) Acc@1: 53.1250 (53.1250)Acc@5: 81.2500 (81.2500) +2025-04-19 16:32:43,828 - train: [ INFO] - Eval : 79 Time: 0.236 (0.400) Loss: 1.8676 (1.8799) Acc@1: 59.3750 (56.6176)Acc@5: 78.1250 (80.0245) +2025-04-19 16:32:51,545 - train: [ INFO] - Eval : 79 Time: 0.052 (0.343) Loss: 3.0307 (1.8943) Acc@1: 50.0000 (55.4356)Acc@5: 50.0000 (79.9537) +2025-04-19 16:33:02,431 - train: [ INFO] - Train: 80 [ 0/461 ( 0%)] Loss: 2.454198 (2.4542) Loss_single: 1.788235 (1.7882) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.828s, 4.69/s (6.828s, 4.69/s) LR: 5.000e-04 Data: 5.960 (5.960) +2025-04-19 16:33:42,311 - train: [ INFO] - Train: 80 [ 50/461 ( 11%)] Loss: 2.494534 (2.4744) Loss_single: 1.835588 (1.8119) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.591s, 54.17/s (0.914s, 35.02/s) LR: 5.000e-04 Data: 0.000 (0.118) +2025-04-19 16:34:23,141 - train: [ INFO] - Train: 80 [ 100/461 ( 22%)] Loss: 2.618933 (2.5226) Loss_single: 1.947739 (1.8572) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.722s, 44.34/s (0.865s, 37.00/s) LR: 5.000e-04 Data: 0.001 (0.060) +2025-04-19 16:35:05,844 - train: [ INFO] - Train: 80 [ 150/461 ( 33%)] Loss: 2.301388 (2.4673) Loss_single: 1.637806 (1.8023) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.884s, 36.21/s (0.861s, 37.18/s) LR: 5.000e-04 Data: 0.000 (0.040) +2025-04-19 16:35:48,470 - train: [ INFO] - Train: 80 [ 200/461 ( 43%)] Loss: 2.494380 (2.4727) Loss_single: 1.813292 (1.8045) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.769s, 41.63/s (0.858s, 37.29/s) LR: 5.000e-04 Data: 0.000 (0.030) +2025-04-19 16:36:33,145 - train: [ INFO] - Train: 80 [ 250/461 ( 54%)] Loss: 2.537277 (2.4835) Loss_single: 1.875650 (1.8164) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.809s, 39.58/s (0.865s, 37.00/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-19 16:37:16,989 - train: [ INFO] - Train: 80 [ 300/461 ( 65%)] Loss: 2.331760 (2.4618) Loss_single: 1.673850 (1.7960) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.918s, 34.86/s (0.867s, 36.93/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 16:37:58,673 - train: [ INFO] - Train: 80 [ 350/461 ( 76%)] Loss: 2.427511 (2.4575) Loss_single: 1.766517 (1.7923) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.825s, 38.79/s (0.862s, 37.14/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-19 16:38:41,492 - train: [ INFO] - Train: 80 [ 400/461 ( 87%)] Loss: 2.380288 (2.4489) Loss_single: 1.723197 (1.7847) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.895s, 35.74/s (0.861s, 37.17/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 16:39:21,793 - train: [ INFO] - Train: 80 [ 450/461 ( 98%)] Loss: 2.777256 (2.4818) Loss_single: 2.035005 (1.8097) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6875) Acc@5: 96.8750 (99.6875) Time: 0.619s, 51.70/s (0.855s, 37.44/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:39:30,867 - train: [ INFO] - Train: 80 [ 460/461 (100%)] Loss: 2.507576 (2.4841) Loss_single: 1.839121 (1.8124) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.886s, 36.11/s (0.856s, 37.40/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:39:37,010 - train: [ INFO] - Eval : 80 Time: 5.785 (5.785) Loss: 1.9474 (1.9474) Acc@1: 53.1250 (53.1250)Acc@5: 78.1250 (78.1250) +2025-04-19 16:39:51,564 - train: [ INFO] - Eval : 80 Time: 0.191 (0.399) Loss: 1.8604 (1.8751) Acc@1: 59.3750 (56.1887)Acc@5: 81.2500 (80.8211) +2025-04-19 16:39:59,282 - train: [ INFO] - Eval : 80 Time: 0.059 (0.342) Loss: 2.9918 (1.8878) Acc@1: 50.0000 (55.3585)Acc@5: 50.0000 (80.2621) +2025-04-19 16:40:10,577 - train: [ INFO] - Train: 81 [ 0/461 ( 0%)] Loss: 2.272584 (2.2726) Loss_single: 1.615818 (1.6158) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.061s, 4.53/s (7.061s, 4.53/s) LR: 5.000e-04 Data: 6.044 (6.044) +2025-04-19 16:40:51,650 - train: [ INFO] - Train: 81 [ 50/461 ( 11%)] Loss: 2.377352 (2.3250) Loss_single: 1.715056 (1.6654) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.029s, 31.09/s (0.943s, 33.95/s) LR: 5.000e-04 Data: 0.000 (0.119) +2025-04-19 16:41:33,372 - train: [ INFO] - Train: 81 [ 100/461 ( 22%)] Loss: 2.510242 (2.3867) Loss_single: 1.766140 (1.6990) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.907s, 35.28/s (0.888s, 36.02/s) LR: 5.000e-04 Data: 0.004 (0.061) +2025-04-19 16:42:15,742 - train: [ INFO] - Train: 81 [ 150/461 ( 33%)] Loss: 2.440262 (2.4001) Loss_single: 1.781701 (1.7197) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.749s, 42.71/s (0.874s, 36.61/s) LR: 5.000e-04 Data: 0.000 (0.041) +2025-04-19 16:42:56,663 - train: [ INFO] - Train: 81 [ 200/461 ( 43%)] Loss: 2.336404 (2.3874) Loss_single: 1.677446 (1.7112) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.730s, 43.81/s (0.860s, 37.21/s) LR: 5.000e-04 Data: 0.000 (0.031) +2025-04-19 16:43:39,508 - train: [ INFO] - Train: 81 [ 250/461 ( 54%)] Loss: 2.474424 (2.4019) Loss_single: 1.813889 (1.7283) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.911s, 35.12/s (0.859s, 37.25/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-19 16:44:22,400 - train: [ INFO] - Train: 81 [ 300/461 ( 65%)] Loss: 2.460469 (2.4102) Loss_single: 1.801194 (1.7387) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.785s, 40.76/s (0.859s, 37.27/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 16:45:03,132 - train: [ INFO] - Train: 81 [ 350/461 ( 76%)] Loss: 2.453374 (2.4156) Loss_single: 1.779326 (1.7438) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.784s, 40.81/s (0.852s, 37.56/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 16:45:42,926 - train: [ INFO] - Train: 81 [ 400/461 ( 87%)] Loss: 2.615759 (2.4379) Loss_single: 1.947398 (1.7664) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.820s, 39.03/s (0.845s, 37.88/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 16:46:23,612 - train: [ INFO] - Train: 81 [ 450/461 ( 98%)] Loss: 2.537703 (2.4479) Loss_single: 1.867916 (1.7766) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.821s, 39.00/s (0.841s, 38.04/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:46:30,951 - train: [ INFO] - Train: 81 [ 460/461 (100%)] Loss: 2.418402 (2.4452) Loss_single: 1.756408 (1.7748) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.549s, 58.31/s (0.839s, 38.15/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:46:36,945 - train: [ INFO] - Eval : 81 Time: 5.609 (5.609) Loss: 1.9384 (1.9384) Acc@1: 56.2500 (56.2500)Acc@5: 84.3750 (84.3750) +2025-04-19 16:46:51,329 - train: [ INFO] - Eval : 81 Time: 0.323 (0.392) Loss: 1.8656 (1.8888) Acc@1: 53.1250 (55.5760)Acc@5: 81.2500 (80.5147) +2025-04-19 16:46:59,223 - train: [ INFO] - Eval : 81 Time: 0.070 (0.340) Loss: 2.9527 (1.9026) Acc@1: 50.0000 (54.5490)Acc@5: 50.0000 (79.9152) +2025-04-19 16:47:08,191 - train: [ INFO] - Train: 82 [ 0/461 ( 0%)] Loss: 2.510936 (2.5109) Loss_single: 1.845891 (1.8459) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.551s, 7.03/s (4.551s, 7.03/s) LR: 5.000e-04 Data: 3.905 (3.905) +2025-04-19 16:47:49,248 - train: [ INFO] - Train: 82 [ 50/461 ( 11%)] Loss: 2.285940 (2.3984) Loss_single: 1.625146 (1.7355) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.890s, 35.95/s (0.893s, 35.83/s) LR: 5.000e-04 Data: 0.000 (0.078) +2025-04-19 16:48:31,968 - train: [ INFO] - Train: 82 [ 100/461 ( 22%)] Loss: 2.510074 (2.4357) Loss_single: 1.853968 (1.7750) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.883s, 36.23/s (0.873s, 36.65/s) LR: 5.000e-04 Data: 0.000 (0.040) +2025-04-19 16:49:12,220 - train: [ INFO] - Train: 82 [ 150/461 ( 33%)] Loss: 2.453752 (2.4402) Loss_single: 1.791035 (1.7790) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.602s, 53.15/s (0.850s, 37.63/s) LR: 5.000e-04 Data: 0.001 (0.027) +2025-04-19 16:49:51,828 - train: [ INFO] - Train: 82 [ 200/461 ( 43%)] Loss: 2.534206 (2.4590) Loss_single: 1.877238 (1.7987) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.764s, 41.88/s (0.836s, 38.30/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 16:50:32,697 - train: [ INFO] - Train: 82 [ 250/461 ( 54%)] Loss: 2.714671 (2.5016) Loss_single: 1.983046 (1.8294) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.764s, 41.89/s (0.832s, 38.48/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 16:51:17,766 - train: [ INFO] - Train: 82 [ 300/461 ( 65%)] Loss: 2.356869 (2.4809) Loss_single: 1.690221 (1.8095) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 1.032s, 31.01/s (0.843s, 37.96/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:52:00,786 - train: [ INFO] - Train: 82 [ 350/461 ( 76%)] Loss: 2.445033 (2.4764) Loss_single: 1.787371 (1.8067) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.967s, 33.10/s (0.845s, 37.86/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 16:52:42,409 - train: [ INFO] - Train: 82 [ 400/461 ( 87%)] Loss: 2.836983 (2.5165) Loss_single: 2.092708 (1.8385) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 100.0000 (100.0000) Time: 1.017s, 31.45/s (0.844s, 37.94/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 16:53:22,273 - train: [ INFO] - Train: 82 [ 450/461 ( 98%)] Loss: 2.523089 (2.5172) Loss_single: 1.863918 (1.8411) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.653s, 49.01/s (0.838s, 38.18/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-19 16:53:30,488 - train: [ INFO] - Train: 82 [ 460/461 (100%)] Loss: 2.669136 (2.5310) Loss_single: 1.915612 (1.8478) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1477) Acc@5: 96.8750 (99.7159) Time: 0.789s, 40.57/s (0.838s, 38.19/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-19 16:53:35,494 - train: [ INFO] - Eval : 82 Time: 4.645 (4.645) Loss: 1.9218 (1.9218) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-19 16:53:47,677 - train: [ INFO] - Eval : 82 Time: 0.318 (0.330) Loss: 1.8755 (1.8789) Acc@1: 59.3750 (55.9436)Acc@5: 75.0000 (80.9436) +2025-04-19 16:53:55,736 - train: [ INFO] - Eval : 82 Time: 0.064 (0.304) Loss: 3.0088 (1.8959) Acc@1: 50.0000 (54.7032)Acc@5: 50.0000 (80.3007) +2025-04-19 16:54:05,696 - train: [ INFO] - Train: 83 [ 0/461 ( 0%)] Loss: 2.377231 (2.3772) Loss_single: 1.705855 (1.7059) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.871s, 5.45/s (5.871s, 5.45/s) LR: 5.000e-04 Data: 4.691 (4.691) +2025-04-19 16:54:49,164 - train: [ INFO] - Train: 83 [ 50/461 ( 11%)] Loss: 2.507279 (2.4423) Loss_single: 1.848819 (1.7773) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.642s, 49.81/s (0.966s, 33.14/s) LR: 5.000e-04 Data: 0.000 (0.093) +2025-04-19 16:55:31,759 - train: [ INFO] - Train: 83 [ 100/461 ( 22%)] Loss: 2.585726 (2.4901) Loss_single: 1.854837 (1.8032) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.597s, 53.56/s (0.909s, 35.21/s) LR: 5.000e-04 Data: 0.001 (0.047) +2025-04-19 16:56:16,398 - train: [ INFO] - Train: 83 [ 150/461 ( 33%)] Loss: 2.551195 (2.5054) Loss_single: 1.893320 (1.8257) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.836s, 38.30/s (0.903s, 35.44/s) LR: 5.000e-04 Data: 0.001 (0.032) +2025-04-19 16:56:58,080 - train: [ INFO] - Train: 83 [ 200/461 ( 43%)] Loss: 2.362979 (2.4769) Loss_single: 1.705004 (1.8016) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.743s, 43.06/s (0.885s, 36.14/s) LR: 5.000e-04 Data: 0.000 (0.024) +2025-04-19 16:57:39,484 - train: [ INFO] - Train: 83 [ 250/461 ( 54%)] Loss: 2.331350 (2.4526) Loss_single: 1.673741 (1.7803) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.887s, 36.09/s (0.874s, 36.63/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 16:58:21,658 - train: [ INFO] - Train: 83 [ 300/461 ( 65%)] Loss: 2.375998 (2.4417) Loss_single: 1.704473 (1.7694) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.921s, 34.75/s (0.868s, 36.85/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 16:59:03,554 - train: [ INFO] - Train: 83 [ 350/461 ( 76%)] Loss: 2.420296 (2.4390) Loss_single: 1.746450 (1.7666) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.859s, 37.26/s (0.864s, 37.04/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 16:59:45,915 - train: [ INFO] - Train: 83 [ 400/461 ( 87%)] Loss: 2.307462 (2.4244) Loss_single: 1.645381 (1.7531) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.923s, 34.67/s (0.862s, 37.14/s) LR: 5.000e-04 Data: 0.002 (0.012) +2025-04-19 17:00:27,701 - train: [ INFO] - Train: 83 [ 450/461 ( 98%)] Loss: 2.505711 (2.4325) Loss_single: 1.849865 (1.7628) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.578s, 55.36/s (0.859s, 37.27/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 17:00:35,649 - train: [ INFO] - Train: 83 [ 460/461 (100%)] Loss: 2.560984 (2.4442) Loss_single: 1.867186 (1.7723) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.748s, 42.79/s (0.857s, 37.33/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 17:00:40,420 - train: [ INFO] - Eval : 83 Time: 4.398 (4.398) Loss: 1.9748 (1.9748) Acc@1: 46.8750 (46.8750)Acc@5: 84.3750 (84.3750) +2025-04-19 17:00:54,847 - train: [ INFO] - Eval : 83 Time: 0.228 (0.369) Loss: 1.8741 (1.8934) Acc@1: 56.2500 (55.8824)Acc@5: 78.1250 (79.5956) +2025-04-19 17:01:02,723 - train: [ INFO] - Eval : 83 Time: 0.062 (0.326) Loss: 2.7898 (1.9080) Acc@1: 50.0000 (54.7803)Acc@5: 50.0000 (79.6068) +2025-04-19 17:01:12,968 - train: [ INFO] - Train: 84 [ 0/461 ( 0%)] Loss: 2.379081 (2.3791) Loss_single: 1.722150 (1.7222) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.306s, 5.07/s (6.306s, 5.07/s) LR: 5.000e-04 Data: 5.371 (5.371) +2025-04-19 17:01:54,501 - train: [ INFO] - Train: 84 [ 50/461 ( 11%)] Loss: 2.381698 (2.3804) Loss_single: 1.712705 (1.7174) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.781s, 40.98/s (0.937s, 34.15/s) LR: 5.000e-04 Data: 0.000 (0.106) +2025-04-19 17:02:36,758 - train: [ INFO] - Train: 84 [ 100/461 ( 22%)] Loss: 2.433595 (2.3981) Loss_single: 1.763591 (1.7328) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.954s, 33.54/s (0.891s, 35.92/s) LR: 5.000e-04 Data: 0.001 (0.054) +2025-04-19 17:03:19,495 - train: [ INFO] - Train: 84 [ 150/461 ( 33%)] Loss: 2.273899 (2.3671) Loss_single: 1.616673 (1.7038) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.679s, 47.10/s (0.878s, 36.45/s) LR: 5.000e-04 Data: 0.000 (0.036) +2025-04-19 17:04:01,645 - train: [ INFO] - Train: 84 [ 200/461 ( 43%)] Loss: 2.313228 (2.3563) Loss_single: 1.653106 (1.6936) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.927s, 34.52/s (0.869s, 36.84/s) LR: 5.000e-04 Data: 0.000 (0.028) +2025-04-19 17:04:43,245 - train: [ INFO] - Train: 84 [ 250/461 ( 54%)] Loss: 2.477664 (2.3765) Loss_single: 1.815773 (1.7140) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.739s, 43.28/s (0.861s, 37.16/s) LR: 5.000e-04 Data: 0.000 (0.022) +2025-04-19 17:05:24,150 - train: [ INFO] - Train: 84 [ 300/461 ( 65%)] Loss: 2.657173 (2.4166) Loss_single: 1.995645 (1.7542) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.841s, 38.06/s (0.854s, 37.48/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-19 17:06:06,520 - train: [ INFO] - Train: 84 [ 350/461 ( 76%)] Loss: 2.767524 (2.4605) Loss_single: 2.075640 (1.7944) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.779s, 41.09/s (0.853s, 37.53/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 17:06:46,175 - train: [ INFO] - Train: 84 [ 400/461 ( 87%)] Loss: 2.447497 (2.4590) Loss_single: 1.789802 (1.7939) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.703s, 45.53/s (0.845s, 37.87/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 17:07:30,579 - train: [ INFO] - Train: 84 [ 450/461 ( 98%)] Loss: 2.416320 (2.4548) Loss_single: 1.758776 (1.7904) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.791s, 40.45/s (0.850s, 37.66/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 17:07:38,831 - train: [ INFO] - Train: 84 [ 460/461 (100%)] Loss: 2.267751 (2.4378) Loss_single: 1.609363 (1.7739) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.077s, 29.71/s (0.849s, 37.69/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:07:44,983 - train: [ INFO] - Eval : 84 Time: 5.820 (5.820) Loss: 1.9284 (1.9284) Acc@1: 53.1250 (53.1250)Acc@5: 84.3750 (84.3750) +2025-04-19 17:07:59,277 - train: [ INFO] - Eval : 84 Time: 0.325 (0.394) Loss: 1.8964 (1.8906) Acc@1: 56.2500 (55.5760)Acc@5: 78.1250 (79.9632) +2025-04-19 17:08:06,902 - train: [ INFO] - Eval : 84 Time: 0.095 (0.338) Loss: 2.8725 (1.9026) Acc@1: 50.0000 (54.8188)Acc@5: 50.0000 (79.7995) +2025-04-19 17:08:17,423 - train: [ INFO] - Train: 85 [ 0/461 ( 0%)] Loss: 2.474341 (2.4743) Loss_single: 1.815870 (1.8159) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.269s, 5.10/s (6.269s, 5.10/s) LR: 5.000e-04 Data: 5.301 (5.301) +2025-04-19 17:09:03,843 - train: [ INFO] - Train: 85 [ 50/461 ( 11%)] Loss: 2.455857 (2.4651) Loss_single: 1.769620 (1.7927) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.187s, 26.96/s (1.031s, 31.02/s) LR: 5.000e-04 Data: 0.001 (0.105) +2025-04-19 17:09:47,717 - train: [ INFO] - Train: 85 [ 100/461 ( 22%)] Loss: 2.432077 (2.4541) Loss_single: 1.770980 (1.7855) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.845s, 37.87/s (0.955s, 33.52/s) LR: 5.000e-04 Data: 0.004 (0.053) +2025-04-19 17:10:31,379 - train: [ INFO] - Train: 85 [ 150/461 ( 33%)] Loss: 2.451883 (2.4535) Loss_single: 1.777530 (1.7835) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.776s, 41.23/s (0.927s, 34.52/s) LR: 5.000e-04 Data: 0.000 (0.036) +2025-04-19 17:11:00,631 - train: [ INFO] - Train: 85 [ 200/461 ( 43%)] Loss: 2.377696 (2.4384) Loss_single: 1.695845 (1.7660) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.501s, 63.81/s (0.842s, 38.03/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-19 17:11:40,909 - train: [ INFO] - Train: 85 [ 250/461 ( 54%)] Loss: 2.326833 (2.4198) Loss_single: 1.670233 (1.7500) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.729s, 43.88/s (0.834s, 38.37/s) LR: 5.000e-04 Data: 0.000 (0.022) +2025-04-19 17:12:21,751 - train: [ INFO] - Train: 85 [ 300/461 ( 65%)] Loss: 2.562151 (2.4401) Loss_single: 1.842236 (1.7632) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.896s, 35.70/s (0.831s, 38.51/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 17:13:06,768 - train: [ INFO] - Train: 85 [ 350/461 ( 76%)] Loss: 2.420040 (2.4376) Loss_single: 1.763372 (1.7632) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.899s, 35.60/s (0.841s, 38.06/s) LR: 5.000e-04 Data: 0.014 (0.016) +2025-04-19 17:13:52,551 - train: [ INFO] - Train: 85 [ 400/461 ( 87%)] Loss: 2.345381 (2.4274) Loss_single: 1.681952 (1.7542) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.949s, 33.71/s (0.850s, 37.65/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-19 17:14:36,858 - train: [ INFO] - Train: 85 [ 450/461 ( 98%)] Loss: 2.526570 (2.4373) Loss_single: 1.850845 (1.7638) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.808s, 39.59/s (0.854s, 37.48/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 17:14:45,808 - train: [ INFO] - Train: 85 [ 460/461 (100%)] Loss: 2.468191 (2.4401) Loss_single: 1.812309 (1.7683) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 1.043s, 30.70/s (0.855s, 37.44/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:14:50,980 - train: [ INFO] - Eval : 85 Time: 4.770 (4.770) Loss: 1.9438 (1.9438) Acc@1: 46.8750 (46.8750)Acc@5: 84.3750 (84.3750) +2025-04-19 17:15:05,174 - train: [ INFO] - Eval : 85 Time: 0.252 (0.372) Loss: 1.8843 (1.8961) Acc@1: 59.3750 (55.5147)Acc@5: 78.1250 (79.9632) +2025-04-19 17:15:12,713 - train: [ INFO] - Eval : 85 Time: 0.071 (0.323) Loss: 2.9639 (1.9094) Acc@1: 50.0000 (54.5875)Acc@5: 50.0000 (79.9152) +2025-04-19 17:15:23,259 - train: [ INFO] - Train: 86 [ 0/461 ( 0%)] Loss: 2.624649 (2.6246) Loss_single: 1.875393 (1.8754) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 6.240s, 5.13/s (6.240s, 5.13/s) LR: 5.000e-04 Data: 5.224 (5.224) +2025-04-19 17:16:10,255 - train: [ INFO] - Train: 86 [ 50/461 ( 11%)] Loss: 2.489833 (2.5572) Loss_single: 1.831614 (1.8535) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.895s, 35.76/s (1.042s, 30.71/s) LR: 5.000e-04 Data: 0.003 (0.103) +2025-04-19 17:16:51,802 - train: [ INFO] - Train: 86 [ 100/461 ( 22%)] Loss: 2.878566 (2.6643) Loss_single: 2.164083 (1.9570) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.622s, 51.45/s (0.937s, 34.14/s) LR: 5.000e-04 Data: 0.000 (0.053) +2025-04-19 17:17:32,044 - train: [ INFO] - Train: 86 [ 150/461 ( 33%)] Loss: 2.438205 (2.6078) Loss_single: 1.763543 (1.9087) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 1.048s, 30.53/s (0.893s, 35.84/s) LR: 5.000e-04 Data: 0.001 (0.035) +2025-04-19 17:18:11,565 - train: [ INFO] - Train: 86 [ 200/461 ( 43%)] Loss: 2.458742 (2.5780) Loss_single: 1.797503 (1.8864) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.591s, 54.14/s (0.867s, 36.91/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-19 17:18:53,333 - train: [ INFO] - Train: 86 [ 250/461 ( 54%)] Loss: 2.275320 (2.5276) Loss_single: 1.615863 (1.8413) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.727s, 44.03/s (0.860s, 37.19/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-19 17:19:35,227 - train: [ INFO] - Train: 86 [ 300/461 ( 65%)] Loss: 2.467928 (2.5190) Loss_single: 1.810157 (1.8369) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.899s, 35.59/s (0.856s, 37.37/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 17:20:21,745 - train: [ INFO] - Train: 86 [ 350/461 ( 76%)] Loss: 2.434322 (2.5084) Loss_single: 1.773980 (1.8290) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.795s, 40.23/s (0.867s, 36.92/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 17:21:03,956 - train: [ INFO] - Train: 86 [ 400/461 ( 87%)] Loss: 2.708319 (2.5307) Loss_single: 2.048088 (1.8534) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.808s, 39.63/s (0.864s, 37.05/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 17:21:44,432 - train: [ INFO] - Train: 86 [ 450/461 ( 98%)] Loss: 2.338458 (2.5114) Loss_single: 1.647310 (1.8328) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.717s, 44.63/s (0.858s, 37.32/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:21:52,968 - train: [ INFO] - Train: 86 [ 460/461 (100%)] Loss: 2.364117 (2.4980) Loss_single: 1.705166 (1.8212) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.828s, 38.65/s (0.857s, 37.32/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:21:58,567 - train: [ INFO] - Eval : 86 Time: 5.255 (5.255) Loss: 1.9573 (1.9573) Acc@1: 53.1250 (53.1250)Acc@5: 84.3750 (84.3750) +2025-04-19 17:22:12,310 - train: [ INFO] - Eval : 86 Time: 0.298 (0.373) Loss: 1.8707 (1.8956) Acc@1: 59.3750 (55.0245)Acc@5: 78.1250 (79.5956) +2025-04-19 17:22:20,515 - train: [ INFO] - Eval : 86 Time: 0.065 (0.332) Loss: 3.0287 (1.9055) Acc@1: 50.0000 (54.3948)Acc@5: 50.0000 (79.3755) +2025-04-19 17:22:31,547 - train: [ INFO] - Train: 87 [ 0/461 ( 0%)] Loss: 2.438373 (2.4384) Loss_single: 1.777361 (1.7774) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.521s, 4.91/s (6.521s, 4.91/s) LR: 5.000e-04 Data: 5.500 (5.500) +2025-04-19 17:23:14,769 - train: [ INFO] - Train: 87 [ 50/461 ( 11%)] Loss: 2.669522 (2.5539) Loss_single: 1.999433 (1.8884) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.849s, 37.69/s (0.973s, 32.87/s) LR: 5.000e-04 Data: 0.000 (0.109) +2025-04-19 17:23:56,837 - train: [ INFO] - Train: 87 [ 100/461 ( 22%)] Loss: 2.597462 (2.5685) Loss_single: 1.915029 (1.8973) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.815s, 39.25/s (0.907s, 35.27/s) LR: 5.000e-04 Data: 0.000 (0.055) +2025-04-19 17:24:39,592 - train: [ INFO] - Train: 87 [ 150/461 ( 33%)] Loss: 2.723937 (2.6073) Loss_single: 2.019822 (1.9279) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.822s, 38.91/s (0.890s, 35.97/s) LR: 5.000e-04 Data: 0.001 (0.037) +2025-04-19 17:25:21,691 - train: [ INFO] - Train: 87 [ 200/461 ( 43%)] Loss: 2.202386 (2.5263) Loss_single: 1.545875 (1.8515) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.966s, 33.11/s (0.878s, 36.46/s) LR: 5.000e-04 Data: 0.000 (0.028) +2025-04-19 17:26:04,072 - train: [ INFO] - Train: 87 [ 250/461 ( 54%)] Loss: 2.267618 (2.4832) Loss_single: 1.604527 (1.8103) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.888s, 36.04/s (0.871s, 36.73/s) LR: 5.000e-04 Data: 0.000 (0.023) +2025-04-19 17:26:47,506 - train: [ INFO] - Train: 87 [ 300/461 ( 65%)] Loss: 2.296426 (2.4565) Loss_single: 1.636572 (1.7855) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.774s, 41.36/s (0.871s, 36.76/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 17:27:32,201 - train: [ INFO] - Train: 87 [ 350/461 ( 76%)] Loss: 2.625784 (2.4777) Loss_single: 1.917590 (1.8020) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.828s, 38.63/s (0.874s, 36.63/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 17:28:14,856 - train: [ INFO] - Train: 87 [ 400/461 ( 87%)] Loss: 2.618365 (2.4933) Loss_single: 1.914556 (1.8145) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.790s, 40.51/s (0.871s, 36.74/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 17:28:53,575 - train: [ INFO] - Train: 87 [ 450/461 ( 98%)] Loss: 2.351929 (2.4792) Loss_single: 1.695425 (1.8026) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.804s, 39.78/s (0.860s, 37.21/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 17:29:02,181 - train: [ INFO] - Train: 87 [ 460/461 (100%)] Loss: 2.561341 (2.4866) Loss_single: 1.893680 (1.8109) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.617s, 51.88/s (0.860s, 37.21/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 17:29:07,901 - train: [ INFO] - Eval : 87 Time: 5.369 (5.369) Loss: 1.9818 (1.9818) Acc@1: 43.7500 (43.7500)Acc@5: 81.2500 (81.2500) +2025-04-19 17:29:22,122 - train: [ INFO] - Eval : 87 Time: 0.335 (0.384) Loss: 1.8658 (1.8908) Acc@1: 53.1250 (56.0662)Acc@5: 78.1250 (80.2696) +2025-04-19 17:29:30,260 - train: [ INFO] - Eval : 87 Time: 0.064 (0.338) Loss: 2.9014 (1.9058) Acc@1: 50.0000 (54.8574)Acc@5: 50.0000 (79.9152) +2025-04-19 17:29:41,047 - train: [ INFO] - Train: 88 [ 0/461 ( 0%)] Loss: 2.413669 (2.4137) Loss_single: 1.754846 (1.7548) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.010s, 5.32/s (6.010s, 5.32/s) LR: 5.000e-04 Data: 5.136 (5.136) +2025-04-19 17:30:26,097 - train: [ INFO] - Train: 88 [ 50/461 ( 11%)] Loss: 2.575683 (2.4947) Loss_single: 1.916708 (1.8358) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.815s, 39.25/s (0.999s, 32.02/s) LR: 5.000e-04 Data: 0.001 (0.102) +2025-04-19 17:31:08,795 - train: [ INFO] - Train: 88 [ 100/461 ( 22%)] Loss: 2.289611 (2.4263) Loss_single: 1.632708 (1.7681) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.965s, 33.17/s (0.927s, 34.53/s) LR: 5.000e-04 Data: 0.000 (0.052) +2025-04-19 17:31:52,005 - train: [ INFO] - Train: 88 [ 150/461 ( 33%)] Loss: 2.397733 (2.4192) Loss_single: 1.739824 (1.7610) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.269s, 25.22/s (0.906s, 35.34/s) LR: 5.000e-04 Data: 0.001 (0.035) +2025-04-19 17:32:34,429 - train: [ INFO] - Train: 88 [ 200/461 ( 43%)] Loss: 2.382518 (2.4118) Loss_single: 1.714146 (1.7516) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.797s, 40.16/s (0.891s, 35.91/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-19 17:33:14,732 - train: [ INFO] - Train: 88 [ 250/461 ( 54%)] Loss: 2.498592 (2.4263) Loss_single: 1.840487 (1.7665) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.955s, 33.50/s (0.874s, 36.62/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 17:33:57,092 - train: [ INFO] - Train: 88 [ 300/461 ( 65%)] Loss: 2.461140 (2.4313) Loss_single: 1.718972 (1.7597) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.5536) Acc@5: 96.8750 (99.5536) Time: 1.038s, 30.84/s (0.869s, 36.82/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 17:34:40,765 - train: [ INFO] - Train: 88 [ 350/461 ( 76%)] Loss: 2.384976 (2.4255) Loss_single: 1.724605 (1.7553) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 1.055s, 30.34/s (0.870s, 36.80/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 17:35:23,184 - train: [ INFO] - Train: 88 [ 400/461 ( 87%)] Loss: 2.348009 (2.4169) Loss_single: 1.686253 (1.7476) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.693s, 46.15/s (0.867s, 36.92/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 17:36:02,892 - train: [ INFO] - Train: 88 [ 450/461 ( 98%)] Loss: 2.662789 (2.4415) Loss_single: 1.923204 (1.7652) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 96.8750 (99.3750) Time: 0.803s, 39.83/s (0.859s, 37.27/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:36:09,701 - train: [ INFO] - Train: 88 [ 460/461 (100%)] Loss: 2.789006 (2.4731) Loss_single: 2.049928 (1.7911) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1477) Acc@5: 96.8750 (99.1477) Time: 0.661s, 48.44/s (0.855s, 37.44/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:36:15,933 - train: [ INFO] - Eval : 88 Time: 5.855 (5.855) Loss: 1.9390 (1.9390) Acc@1: 56.2500 (56.2500)Acc@5: 84.3750 (84.3750) +2025-04-19 17:36:27,269 - train: [ INFO] - Eval : 88 Time: 0.237 (0.337) Loss: 1.8661 (1.8992) Acc@1: 59.3750 (55.0858)Acc@5: 78.1250 (80.5147) +2025-04-19 17:36:34,254 - train: [ INFO] - Eval : 88 Time: 0.054 (0.295) Loss: 3.0005 (1.9121) Acc@1: 50.0000 (54.3948)Acc@5: 50.0000 (80.0694) +2025-04-19 17:36:44,551 - train: [ INFO] - Train: 89 [ 0/461 ( 0%)] Loss: 2.400154 (2.4002) Loss_single: 1.737685 (1.7377) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.921s, 5.40/s (5.921s, 5.40/s) LR: 5.000e-04 Data: 5.180 (5.180) +2025-04-19 17:37:27,169 - train: [ INFO] - Train: 89 [ 50/461 ( 11%)] Loss: 2.618540 (2.5093) Loss_single: 1.906107 (1.8219) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.831s, 38.51/s (0.951s, 33.66/s) LR: 5.000e-04 Data: 0.001 (0.102) +2025-04-19 17:38:12,463 - train: [ INFO] - Train: 89 [ 100/461 ( 22%)] Loss: 2.649792 (2.5562) Loss_single: 1.909274 (1.8510) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.935s, 34.23/s (0.928s, 34.49/s) LR: 5.000e-04 Data: 0.000 (0.052) +2025-04-19 17:38:53,051 - train: [ INFO] - Train: 89 [ 150/461 ( 33%)] Loss: 2.362041 (2.5076) Loss_single: 1.699672 (1.8132) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.776s, 41.26/s (0.889s, 36.00/s) LR: 5.000e-04 Data: 0.000 (0.035) +2025-04-19 17:39:37,715 - train: [ INFO] - Train: 89 [ 200/461 ( 43%)] Loss: 2.314081 (2.4689) Loss_single: 1.656958 (1.7819) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.696s, 46.01/s (0.890s, 35.97/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-19 17:40:20,461 - train: [ INFO] - Train: 89 [ 250/461 ( 54%)] Loss: 2.401585 (2.4577) Loss_single: 1.743262 (1.7755) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.836s, 38.26/s (0.882s, 36.26/s) LR: 5.000e-04 Data: 0.000 (0.022) +2025-04-19 17:41:00,073 - train: [ INFO] - Train: 89 [ 300/461 ( 65%)] Loss: 2.308846 (2.4364) Loss_single: 1.651273 (1.7577) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 1.199s, 26.70/s (0.867s, 36.90/s) LR: 5.000e-04 Data: 0.006 (0.018) +2025-04-19 17:41:43,862 - train: [ INFO] - Train: 89 [ 350/461 ( 76%)] Loss: 2.326577 (2.4227) Loss_single: 1.671856 (1.7470) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.822s, 38.91/s (0.868s, 36.86/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 17:42:27,533 - train: [ INFO] - Train: 89 [ 400/461 ( 87%)] Loss: 2.524659 (2.4340) Loss_single: 1.784670 (1.7512) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 96.8750 (99.3056) Time: 0.854s, 37.46/s (0.869s, 36.84/s) LR: 5.000e-04 Data: 0.002 (0.014) +2025-04-19 17:43:09,445 - train: [ INFO] - Train: 89 [ 450/461 ( 98%)] Loss: 2.530946 (2.4437) Loss_single: 1.810151 (1.7571) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 100.0000 (99.3750) Time: 1.044s, 30.66/s (0.865s, 36.99/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:43:18,189 - train: [ INFO] - Train: 89 [ 460/461 (100%)] Loss: 2.414870 (2.4411) Loss_single: 1.757010 (1.7571) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.4318) Time: 0.737s, 43.45/s (0.865s, 36.98/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:43:23,917 - train: [ INFO] - Eval : 89 Time: 5.350 (5.350) Loss: 1.9136 (1.9136) Acc@1: 50.0000 (50.0000)Acc@5: 84.3750 (84.3750) +2025-04-19 17:43:38,123 - train: [ INFO] - Eval : 89 Time: 0.287 (0.383) Loss: 1.8737 (1.8964) Acc@1: 56.2500 (54.8407)Acc@5: 75.0000 (79.6569) +2025-04-19 17:43:45,846 - train: [ INFO] - Eval : 89 Time: 0.067 (0.333) Loss: 2.9855 (1.9127) Acc@1: 50.0000 (54.0093)Acc@5: 50.0000 (79.3369) +2025-04-19 17:43:56,023 - train: [ INFO] - Train: 90 [ 0/461 ( 0%)] Loss: 2.542407 (2.5424) Loss_single: 1.878087 (1.8781) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.798s, 5.52/s (5.798s, 5.52/s) LR: 5.000e-04 Data: 5.021 (5.021) +2025-04-19 17:44:41,148 - train: [ INFO] - Train: 90 [ 50/461 ( 11%)] Loss: 2.575766 (2.5591) Loss_single: 1.881575 (1.8798) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.198s, 26.72/s (0.997s, 32.08/s) LR: 5.000e-04 Data: 0.000 (0.100) +2025-04-19 17:45:26,110 - train: [ INFO] - Train: 90 [ 100/461 ( 22%)] Loss: 2.666452 (2.5949) Loss_single: 1.925982 (1.8952) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 1.004s, 31.88/s (0.948s, 33.74/s) LR: 5.000e-04 Data: 0.000 (0.051) +2025-04-19 17:46:10,326 - train: [ INFO] - Train: 90 [ 150/461 ( 33%)] Loss: 2.324507 (2.5273) Loss_single: 1.665929 (1.8379) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.805s, 39.75/s (0.926s, 34.54/s) LR: 5.000e-04 Data: 0.001 (0.034) +2025-04-19 17:46:52,882 - train: [ INFO] - Train: 90 [ 200/461 ( 43%)] Loss: 2.502433 (2.5223) Loss_single: 1.844908 (1.8393) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 1.034s, 30.95/s (0.907s, 35.27/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-19 17:47:35,758 - train: [ INFO] - Train: 90 [ 250/461 ( 54%)] Loss: 2.347502 (2.4932) Loss_single: 1.684496 (1.8135) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.861s, 37.19/s (0.897s, 35.67/s) LR: 5.000e-04 Data: 0.004 (0.021) +2025-04-19 17:48:19,044 - train: [ INFO] - Train: 90 [ 300/461 ( 65%)] Loss: 2.560867 (2.5028) Loss_single: 1.835280 (1.8166) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.828s, 38.64/s (0.892s, 35.89/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 17:49:05,669 - train: [ INFO] - Train: 90 [ 350/461 ( 76%)] Loss: 2.444000 (2.4955) Loss_single: 1.776923 (1.8116) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 1.122s, 28.52/s (0.897s, 35.66/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-19 17:49:50,922 - train: [ INFO] - Train: 90 [ 400/461 ( 87%)] Loss: 2.477839 (2.4935) Loss_single: 1.773812 (1.8074) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 1.379s, 23.21/s (0.898s, 35.63/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 17:50:35,202 - train: [ INFO] - Train: 90 [ 450/461 ( 98%)] Loss: 2.455482 (2.4897) Loss_single: 1.770818 (1.8038) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.770s, 41.54/s (0.896s, 35.69/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:50:43,814 - train: [ INFO] - Train: 90 [ 460/461 (100%)] Loss: 2.451124 (2.4862) Loss_single: 1.741077 (1.7981) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.838s, 38.19/s (0.896s, 35.73/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:50:49,665 - train: [ INFO] - Eval : 90 Time: 5.490 (5.490) Loss: 1.9391 (1.9391) Acc@1: 53.1250 (53.1250)Acc@5: 84.3750 (84.3750) +2025-04-19 17:51:03,576 - train: [ INFO] - Eval : 90 Time: 0.323 (0.380) Loss: 1.8852 (1.8822) Acc@1: 56.2500 (55.6373)Acc@5: 78.1250 (80.3309) +2025-04-19 17:51:11,678 - train: [ INFO] - Eval : 90 Time: 0.077 (0.335) Loss: 2.9391 (1.8990) Acc@1: 50.0000 (54.4719)Acc@5: 50.0000 (80.4549) +2025-04-19 17:51:21,895 - train: [ INFO] - Train: 91 [ 0/461 ( 0%)] Loss: 2.278419 (2.2784) Loss_single: 1.622338 (1.6223) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.278s, 5.10/s (6.278s, 5.10/s) LR: 5.000e-04 Data: 4.951 (4.951) +2025-04-19 17:52:04,328 - train: [ INFO] - Train: 91 [ 50/461 ( 11%)] Loss: 2.579186 (2.4288) Loss_single: 1.913173 (1.7678) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.791s, 40.46/s (0.954s, 33.56/s) LR: 5.000e-04 Data: 0.001 (0.098) +2025-04-19 17:52:47,440 - train: [ INFO] - Train: 91 [ 100/461 ( 22%)] Loss: 2.267730 (2.3751) Loss_single: 1.611708 (1.7157) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.835s, 38.34/s (0.908s, 35.25/s) LR: 5.000e-04 Data: 0.000 (0.050) +2025-04-19 17:53:31,591 - train: [ INFO] - Train: 91 [ 150/461 ( 33%)] Loss: 2.807076 (2.4831) Loss_single: 2.053393 (1.8002) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.849s, 37.68/s (0.899s, 35.59/s) LR: 5.000e-04 Data: 0.000 (0.034) +2025-04-19 17:54:13,677 - train: [ INFO] - Train: 91 [ 200/461 ( 43%)] Loss: 2.364206 (2.4593) Loss_single: 1.701542 (1.7804) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.836s, 38.28/s (0.885s, 36.18/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-19 17:54:55,321 - train: [ INFO] - Train: 91 [ 250/461 ( 54%)] Loss: 2.411127 (2.4513) Loss_single: 1.753005 (1.7759) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.755s, 42.38/s (0.874s, 36.62/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 17:55:35,672 - train: [ INFO] - Train: 91 [ 300/461 ( 65%)] Loss: 2.419166 (2.4467) Loss_single: 1.762295 (1.7739) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.814s, 39.30/s (0.863s, 37.10/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 17:56:18,881 - train: [ INFO] - Train: 91 [ 350/461 ( 76%)] Loss: 2.370184 (2.4371) Loss_single: 1.714269 (1.7665) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.820s, 39.00/s (0.863s, 37.10/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 17:57:02,075 - train: [ INFO] - Train: 91 [ 400/461 ( 87%)] Loss: 2.394320 (2.4324) Loss_single: 1.727739 (1.7622) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.812s, 39.41/s (0.862s, 37.10/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 17:57:43,780 - train: [ INFO] - Train: 91 [ 450/461 ( 98%)] Loss: 2.393992 (2.4285) Loss_single: 1.734484 (1.7594) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.679s, 47.12/s (0.859s, 37.25/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:57:52,049 - train: [ INFO] - Train: 91 [ 460/461 (100%)] Loss: 2.302287 (2.4171) Loss_single: 1.642025 (1.7487) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.733s, 43.66/s (0.858s, 37.28/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 17:57:58,353 - train: [ INFO] - Eval : 91 Time: 5.945 (5.945) Loss: 1.9188 (1.9188) Acc@1: 53.1250 (53.1250)Acc@5: 84.3750 (84.3750) +2025-04-19 17:58:11,982 - train: [ INFO] - Eval : 91 Time: 0.283 (0.384) Loss: 1.8834 (1.8999) Acc@1: 56.2500 (54.9020)Acc@5: 75.0000 (79.2279) +2025-04-19 17:58:19,466 - train: [ INFO] - Eval : 91 Time: 0.058 (0.330) Loss: 2.8914 (1.9122) Acc@1: 50.0000 (54.2020)Acc@5: 50.0000 (79.1056) +2025-04-19 17:58:30,448 - train: [ INFO] - Train: 92 [ 0/461 ( 0%)] Loss: 2.358606 (2.3586) Loss_single: 1.701345 (1.7013) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.431s, 4.98/s (6.431s, 4.98/s) LR: 5.000e-04 Data: 5.286 (5.286) +2025-04-19 17:59:12,369 - train: [ INFO] - Train: 92 [ 50/461 ( 11%)] Loss: 2.380791 (2.3697) Loss_single: 1.723828 (1.7126) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.787s, 40.66/s (0.946s, 33.83/s) LR: 5.000e-04 Data: 0.000 (0.104) +2025-04-19 17:59:55,350 - train: [ INFO] - Train: 92 [ 100/461 ( 22%)] Loss: 2.422547 (2.3873) Loss_single: 1.731589 (1.7189) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.859s, 37.25/s (0.903s, 35.46/s) LR: 5.000e-04 Data: 0.000 (0.053) +2025-04-19 18:00:37,995 - train: [ INFO] - Train: 92 [ 150/461 ( 33%)] Loss: 2.303301 (2.3663) Loss_single: 1.643465 (1.7001) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.857s, 37.32/s (0.886s, 36.13/s) LR: 5.000e-04 Data: 0.000 (0.036) +2025-04-19 18:01:22,789 - train: [ INFO] - Train: 92 [ 200/461 ( 43%)] Loss: 2.323192 (2.3577) Loss_single: 1.651157 (1.6903) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.118s, 28.62/s (0.888s, 36.04/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-19 18:02:01,292 - train: [ INFO] - Train: 92 [ 250/461 ( 54%)] Loss: 2.357968 (2.3577) Loss_single: 1.696054 (1.6912) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.591s, 54.19/s (0.864s, 37.03/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-19 18:02:41,150 - train: [ INFO] - Train: 92 [ 300/461 ( 65%)] Loss: 2.429229 (2.3679) Loss_single: 1.768198 (1.7022) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.890s, 35.96/s (0.853s, 37.53/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 18:03:24,447 - train: [ INFO] - Train: 92 [ 350/461 ( 76%)] Loss: 2.481253 (2.3821) Loss_single: 1.825123 (1.7176) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.951s, 33.66/s (0.854s, 37.46/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 18:04:06,260 - train: [ INFO] - Train: 92 [ 400/461 ( 87%)] Loss: 2.328682 (2.3762) Loss_single: 1.672928 (1.7126) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.874s, 36.63/s (0.852s, 37.57/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 18:04:49,173 - train: [ INFO] - Train: 92 [ 450/461 ( 98%)] Loss: 2.369388 (2.3755) Loss_single: 1.694402 (1.7108) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.804s, 39.80/s (0.852s, 37.54/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 18:04:57,477 - train: [ INFO] - Train: 92 [ 460/461 (100%)] Loss: 2.621626 (2.3979) Loss_single: 1.942428 (1.7319) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.727s, 44.03/s (0.852s, 37.57/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 18:05:03,445 - train: [ INFO] - Eval : 92 Time: 5.606 (5.606) Loss: 1.9126 (1.9126) Acc@1: 56.2500 (56.2500)Acc@5: 84.3750 (84.3750) +2025-04-19 18:05:17,352 - train: [ INFO] - Eval : 92 Time: 0.285 (0.383) Loss: 1.8457 (1.8891) Acc@1: 53.1250 (55.2083)Acc@5: 81.2500 (80.8824) +2025-04-19 18:05:25,425 - train: [ INFO] - Eval : 92 Time: 0.084 (0.336) Loss: 2.9750 (1.9051) Acc@1: 50.0000 (54.5490)Acc@5: 50.0000 (80.4163) +2025-04-19 18:05:36,643 - train: [ INFO] - Train: 93 [ 0/461 ( 0%)] Loss: 2.618326 (2.6183) Loss_single: 1.930096 (1.9301) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.675s, 4.79/s (6.675s, 4.79/s) LR: 5.000e-04 Data: 5.824 (5.824) +2025-04-19 18:06:14,477 - train: [ INFO] - Train: 93 [ 50/461 ( 11%)] Loss: 2.437607 (2.5280) Loss_single: 1.710015 (1.8201) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.820s, 39.03/s (0.871s, 36.72/s) LR: 5.000e-04 Data: 0.000 (0.115) +2025-04-19 18:06:58,100 - train: [ INFO] - Train: 93 [ 100/461 ( 22%)] Loss: 2.520439 (2.5255) Loss_single: 1.828705 (1.8229) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 1.031s, 31.05/s (0.871s, 36.73/s) LR: 5.000e-04 Data: 0.001 (0.059) +2025-04-19 18:07:41,284 - train: [ INFO] - Train: 93 [ 150/461 ( 33%)] Loss: 2.600015 (2.5441) Loss_single: 1.909172 (1.8445) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.645s, 49.63/s (0.868s, 36.86/s) LR: 5.000e-04 Data: 0.000 (0.039) +2025-04-19 18:08:26,016 - train: [ INFO] - Train: 93 [ 200/461 ( 43%)] Loss: 2.553592 (2.5460) Loss_single: 1.896546 (1.8549) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 1.236s, 25.89/s (0.874s, 36.61/s) LR: 5.000e-04 Data: 0.000 (0.030) +2025-04-19 18:09:08,847 - train: [ INFO] - Train: 93 [ 250/461 ( 54%)] Loss: 2.523108 (2.5422) Loss_single: 1.780282 (1.8425) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (99.4792) Time: 0.871s, 36.73/s (0.870s, 36.77/s) LR: 5.000e-04 Data: 0.012 (0.024) +2025-04-19 18:09:51,363 - train: [ INFO] - Train: 93 [ 300/461 ( 65%)] Loss: 2.468935 (2.5317) Loss_single: 1.797539 (1.8361) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.729s, 43.89/s (0.867s, 36.92/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 18:10:36,827 - train: [ INFO] - Train: 93 [ 350/461 ( 76%)] Loss: 2.525991 (2.5310) Loss_single: 1.838134 (1.8363) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 1.314s, 24.35/s (0.873s, 36.67/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 18:11:17,560 - train: [ INFO] - Train: 93 [ 400/461 ( 87%)] Loss: 2.567685 (2.5351) Loss_single: 1.867430 (1.8398) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.861s, 37.16/s (0.865s, 36.99/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 18:12:01,303 - train: [ INFO] - Train: 93 [ 450/461 ( 98%)] Loss: 2.843636 (2.5659) Loss_single: 2.091598 (1.8650) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 96.8750 (99.3750) Time: 0.870s, 36.77/s (0.866s, 36.95/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 18:12:10,152 - train: [ INFO] - Train: 93 [ 460/461 (100%)] Loss: 2.410492 (2.5518) Loss_single: 1.749968 (1.8545) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.4318) Time: 0.799s, 40.03/s (0.866s, 36.94/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 18:12:15,966 - train: [ INFO] - Eval : 93 Time: 5.447 (5.447) Loss: 1.9407 (1.9407) Acc@1: 53.1250 (53.1250)Acc@5: 84.3750 (84.3750) +2025-04-19 18:12:30,171 - train: [ INFO] - Eval : 93 Time: 0.332 (0.385) Loss: 1.8791 (1.8971) Acc@1: 59.3750 (55.5147)Acc@5: 78.1250 (79.9632) +2025-04-19 18:12:37,853 - train: [ INFO] - Eval : 93 Time: 0.071 (0.333) Loss: 2.7518 (1.9125) Acc@1: 50.0000 (54.3948)Acc@5: 50.0000 (79.2984) +2025-04-19 18:12:48,223 - train: [ INFO] - Train: 94 [ 0/461 ( 0%)] Loss: 2.441996 (2.4420) Loss_single: 1.765936 (1.7659) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.941s, 5.39/s (5.941s, 5.39/s) LR: 5.000e-04 Data: 5.123 (5.123) +2025-04-19 18:13:31,464 - train: [ INFO] - Train: 94 [ 50/461 ( 11%)] Loss: 2.501245 (2.4716) Loss_single: 1.837869 (1.8019) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.781s, 40.95/s (0.962s, 33.25/s) LR: 5.000e-04 Data: 0.000 (0.101) +2025-04-19 18:14:10,931 - train: [ INFO] - Train: 94 [ 100/461 ( 22%)] Loss: 2.316008 (2.4197) Loss_single: 1.658913 (1.7542) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.721s, 44.41/s (0.876s, 36.54/s) LR: 5.000e-04 Data: 0.000 (0.051) +2025-04-19 18:14:53,540 - train: [ INFO] - Train: 94 [ 150/461 ( 33%)] Loss: 2.451831 (2.4278) Loss_single: 1.771511 (1.7586) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.671s, 47.72/s (0.867s, 36.90/s) LR: 5.000e-04 Data: 0.000 (0.035) +2025-04-19 18:15:35,833 - train: [ INFO] - Train: 94 [ 200/461 ( 43%)] Loss: 2.421422 (2.4265) Loss_single: 1.761441 (1.7591) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.870s, 36.78/s (0.861s, 37.15/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-19 18:16:16,508 - train: [ INFO] - Train: 94 [ 250/461 ( 54%)] Loss: 2.356370 (2.4148) Loss_single: 1.695596 (1.7485) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.673s, 47.58/s (0.851s, 37.58/s) LR: 5.000e-04 Data: 0.001 (0.021) +2025-04-19 18:16:59,180 - train: [ INFO] - Train: 94 [ 300/461 ( 65%)] Loss: 2.310863 (2.4000) Loss_single: 1.653928 (1.7350) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.759s, 42.15/s (0.852s, 37.58/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 18:17:41,000 - train: [ INFO] - Train: 94 [ 350/461 ( 76%)] Loss: 2.200667 (2.3751) Loss_single: 1.542262 (1.7109) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.430s, 74.46/s (0.849s, 37.68/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 18:18:24,303 - train: [ INFO] - Train: 94 [ 400/461 ( 87%)] Loss: 2.707449 (2.4120) Loss_single: 2.043709 (1.7479) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.842s, 37.99/s (0.851s, 37.60/s) LR: 5.000e-04 Data: 0.010 (0.014) +2025-04-19 18:19:05,276 - train: [ INFO] - Train: 94 [ 450/461 ( 98%)] Loss: 2.332429 (2.4040) Loss_single: 1.675357 (1.7407) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.825s, 38.78/s (0.847s, 37.76/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 18:19:13,673 - train: [ INFO] - Train: 94 [ 460/461 (100%)] Loss: 2.567129 (2.4189) Loss_single: 1.908285 (1.7559) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.936s, 34.20/s (0.847s, 37.77/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 18:19:19,079 - train: [ INFO] - Eval : 94 Time: 5.040 (5.040) Loss: 1.9335 (1.9335) Acc@1: 56.2500 (56.2500)Acc@5: 81.2500 (81.2500) +2025-04-19 18:19:33,320 - train: [ INFO] - Eval : 94 Time: 0.176 (0.378) Loss: 1.8671 (1.9022) Acc@1: 56.2500 (54.9632)Acc@5: 78.1250 (79.1054) +2025-04-19 18:19:41,146 - train: [ INFO] - Eval : 94 Time: 0.062 (0.331) Loss: 2.8491 (1.9174) Acc@1: 50.0000 (53.9322)Acc@5: 50.0000 (78.3346) +2025-04-19 18:19:51,997 - train: [ INFO] - Train: 95 [ 0/461 ( 0%)] Loss: 2.187325 (2.1873) Loss_single: 1.528410 (1.5284) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.645s, 4.82/s (6.645s, 4.82/s) LR: 5.000e-04 Data: 5.715 (5.715) +2025-04-19 18:20:33,748 - train: [ INFO] - Train: 95 [ 50/461 ( 11%)] Loss: 2.630446 (2.4089) Loss_single: 1.877607 (1.7030) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (98.4375) Time: 0.822s, 38.94/s (0.948s, 33.77/s) LR: 5.000e-04 Data: 0.000 (0.113) +2025-04-19 18:21:14,971 - train: [ INFO] - Train: 95 [ 100/461 ( 22%)] Loss: 2.327412 (2.3817) Loss_single: 1.668490 (1.6915) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.703s, 45.54/s (0.886s, 36.12/s) LR: 5.000e-04 Data: 0.002 (0.057) +2025-04-19 18:21:56,324 - train: [ INFO] - Train: 95 [ 150/461 ( 33%)] Loss: 2.410990 (2.3890) Loss_single: 1.683375 (1.6895) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.836s, 38.26/s (0.866s, 36.96/s) LR: 5.000e-04 Data: 0.000 (0.039) +2025-04-19 18:22:39,482 - train: [ INFO] - Train: 95 [ 200/461 ( 43%)] Loss: 2.466542 (2.4045) Loss_single: 1.755659 (1.7027) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.1250) Acc@5: 100.0000 (99.3750) Time: 0.820s, 39.03/s (0.865s, 37.00/s) LR: 5.000e-04 Data: 0.004 (0.029) +2025-04-19 18:23:22,579 - train: [ INFO] - Train: 95 [ 250/461 ( 54%)] Loss: 2.470218 (2.4155) Loss_single: 1.813418 (1.7212) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.4792) Time: 0.733s, 43.64/s (0.864s, 37.04/s) LR: 5.000e-04 Data: 0.000 (0.024) +2025-04-19 18:24:05,966 - train: [ INFO] - Train: 95 [ 300/461 ( 65%)] Loss: 2.462265 (2.4222) Loss_single: 1.804379 (1.7330) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6607) Acc@5: 100.0000 (99.5536) Time: 0.893s, 35.85/s (0.864s, 37.02/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-19 18:24:44,975 - train: [ INFO] - Train: 95 [ 350/461 ( 76%)] Loss: 2.379601 (2.4168) Loss_single: 1.723069 (1.7318) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8281) Acc@5: 100.0000 (99.6094) Time: 0.938s, 34.13/s (0.852s, 37.55/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-19 18:25:28,749 - train: [ INFO] - Train: 95 [ 400/461 ( 87%)] Loss: 2.589170 (2.4360) Loss_single: 1.923680 (1.7531) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.6528) Time: 0.809s, 39.57/s (0.855s, 37.42/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-19 18:26:14,932 - train: [ INFO] - Train: 95 [ 450/461 ( 98%)] Loss: 2.322032 (2.4246) Loss_single: 1.666401 (1.7444) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.6875) Time: 0.968s, 33.05/s (0.863s, 37.10/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 18:26:22,840 - train: [ INFO] - Train: 95 [ 460/461 (100%)] Loss: 2.588090 (2.4395) Loss_single: 1.850529 (1.7541) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8636) Acc@5: 96.8750 (99.4318) Time: 1.012s, 31.63/s (0.861s, 37.17/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 18:26:28,603 - train: [ INFO] - Eval : 95 Time: 5.371 (5.371) Loss: 1.9448 (1.9448) Acc@1: 46.8750 (46.8750)Acc@5: 84.3750 (84.3750) +2025-04-19 18:26:42,495 - train: [ INFO] - Eval : 95 Time: 0.291 (0.378) Loss: 1.8692 (1.9001) Acc@1: 56.2500 (55.8211)Acc@5: 78.1250 (80.3309) +2025-04-19 18:26:50,020 - train: [ INFO] - Eval : 95 Time: 0.071 (0.327) Loss: 2.9485 (1.9160) Acc@1: 50.0000 (54.5490)Acc@5: 50.0000 (79.9537) +2025-04-19 18:26:59,710 - train: [ INFO] - Train: 96 [ 0/461 ( 0%)] Loss: 2.425312 (2.4253) Loss_single: 1.716347 (1.7163) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.220s, 6.13/s (5.220s, 6.13/s) LR: 5.000e-04 Data: 4.322 (4.322) +2025-04-19 18:27:43,056 - train: [ INFO] - Train: 96 [ 50/461 ( 11%)] Loss: 2.399920 (2.4126) Loss_single: 1.730822 (1.7236) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.077s, 29.71/s (0.951s, 33.66/s) LR: 5.000e-04 Data: 0.001 (0.086) +2025-04-19 18:28:27,096 - train: [ INFO] - Train: 96 [ 100/461 ( 22%)] Loss: 2.524334 (2.4499) Loss_single: 1.861999 (1.7697) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.952s, 33.60/s (0.915s, 34.95/s) LR: 5.000e-04 Data: 0.000 (0.044) +2025-04-19 18:29:08,860 - train: [ INFO] - Train: 96 [ 150/461 ( 33%)] Loss: 2.677108 (2.5067) Loss_single: 1.939863 (1.8123) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 1.024s, 31.24/s (0.889s, 36.01/s) LR: 5.000e-04 Data: 0.004 (0.030) +2025-04-19 18:29:54,465 - train: [ INFO] - Train: 96 [ 200/461 ( 43%)] Loss: 2.313176 (2.4680) Loss_single: 1.656475 (1.7811) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.879s, 36.39/s (0.894s, 35.79/s) LR: 5.000e-04 Data: 0.000 (0.023) +2025-04-19 18:30:37,545 - train: [ INFO] - Train: 96 [ 250/461 ( 54%)] Loss: 2.588481 (2.4881) Loss_single: 1.871103 (1.7961) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 1.242s, 25.76/s (0.887s, 36.06/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-19 18:31:18,307 - train: [ INFO] - Train: 96 [ 300/461 ( 65%)] Loss: 2.409419 (2.4768) Loss_single: 1.730423 (1.7867) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.775s, 41.30/s (0.875s, 36.56/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 18:32:00,958 - train: [ INFO] - Train: 96 [ 350/461 ( 76%)] Loss: 2.669428 (2.5009) Loss_single: 2.010626 (1.8147) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.771s, 41.51/s (0.872s, 36.70/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-19 18:32:45,166 - train: [ INFO] - Train: 96 [ 400/461 ( 87%)] Loss: 2.269396 (2.4752) Loss_single: 1.611545 (1.7921) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 1.124s, 28.47/s (0.873s, 36.65/s) LR: 5.000e-04 Data: 0.002 (0.012) +2025-04-19 18:33:28,800 - train: [ INFO] - Train: 96 [ 450/461 ( 98%)] Loss: 2.384460 (2.4661) Loss_single: 1.728380 (1.7858) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.743s, 43.05/s (0.873s, 36.65/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 18:33:37,306 - train: [ INFO] - Train: 96 [ 460/461 (100%)] Loss: 2.295691 (2.4506) Loss_single: 1.640832 (1.7726) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.848s, 37.71/s (0.872s, 36.68/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-19 18:33:42,916 - train: [ INFO] - Eval : 96 Time: 5.268 (5.268) Loss: 1.9130 (1.9130) Acc@1: 50.0000 (50.0000)Acc@5: 84.3750 (84.3750) +2025-04-19 18:33:56,904 - train: [ INFO] - Eval : 96 Time: 0.297 (0.378) Loss: 1.8686 (1.8815) Acc@1: 62.5000 (56.1275)Acc@5: 78.1250 (80.3309) +2025-04-19 18:34:04,734 - train: [ INFO] - Eval : 96 Time: 0.062 (0.330) Loss: 2.8446 (1.8954) Acc@1: 50.0000 (55.0887)Acc@5: 50.0000 (79.9923) +2025-04-19 18:34:15,485 - train: [ INFO] - Train: 97 [ 0/461 ( 0%)] Loss: 2.391752 (2.3918) Loss_single: 1.733309 (1.7333) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.532s, 5.78/s (5.532s, 5.78/s) LR: 5.000e-04 Data: 4.531 (4.531) +2025-04-19 18:34:59,331 - train: [ INFO] - Train: 97 [ 50/461 ( 11%)] Loss: 2.395359 (2.3936) Loss_single: 1.725099 (1.7292) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.840s, 38.09/s (0.966s, 33.13/s) LR: 5.000e-04 Data: 0.009 (0.090) +2025-04-19 18:35:43,730 - train: [ INFO] - Train: 97 [ 100/461 ( 22%)] Loss: 2.248418 (2.3452) Loss_single: 1.587432 (1.6819) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.893s, 35.83/s (0.927s, 34.53/s) LR: 5.000e-04 Data: 0.001 (0.046) +2025-04-19 18:36:27,894 - train: [ INFO] - Train: 97 [ 150/461 ( 33%)] Loss: 2.512898 (2.3871) Loss_single: 1.845836 (1.7229) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.791s, 40.46/s (0.912s, 35.09/s) LR: 5.000e-04 Data: 0.001 (0.031) +2025-04-19 18:37:12,422 - train: [ INFO] - Train: 97 [ 200/461 ( 43%)] Loss: 2.364300 (2.3825) Loss_single: 1.703591 (1.7191) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.945s, 33.85/s (0.906s, 35.31/s) LR: 5.000e-04 Data: 0.000 (0.024) +2025-04-19 18:37:54,113 - train: [ INFO] - Train: 97 [ 250/461 ( 54%)] Loss: 2.357823 (2.3784) Loss_single: 1.690547 (1.7143) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.023s, 31.28/s (0.892s, 35.89/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 18:38:36,559 - train: [ INFO] - Train: 97 [ 300/461 ( 65%)] Loss: 2.294987 (2.3665) Loss_single: 1.635257 (1.7030) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.48/s (0.884s, 36.19/s) LR: 5.000e-04 Data: 0.001 (0.016) +2025-04-19 18:39:19,627 - train: [ INFO] - Train: 97 [ 350/461 ( 76%)] Loss: 2.330904 (2.3621) Loss_single: 1.671824 (1.6991) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.064s, 30.09/s (0.881s, 36.33/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 18:40:02,109 - train: [ INFO] - Train: 97 [ 400/461 ( 87%)] Loss: 2.213284 (2.3455) Loss_single: 1.556606 (1.6833) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.693s, 46.15/s (0.877s, 36.49/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 18:40:43,780 - train: [ INFO] - Train: 97 [ 450/461 ( 98%)] Loss: 2.342573 (2.3452) Loss_single: 1.682986 (1.6832) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.744s, 43.03/s (0.872s, 36.70/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 18:40:52,428 - train: [ INFO] - Train: 97 [ 460/461 (100%)] Loss: 2.449519 (2.3547) Loss_single: 1.792088 (1.6931) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.819s, 39.09/s (0.872s, 36.71/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 18:40:58,402 - train: [ INFO] - Eval : 97 Time: 5.609 (5.609) Loss: 1.9829 (1.9829) Acc@1: 50.0000 (50.0000)Acc@5: 84.3750 (84.3750) +2025-04-19 18:41:12,719 - train: [ INFO] - Eval : 97 Time: 0.291 (0.391) Loss: 1.8897 (1.8999) Acc@1: 56.2500 (55.3922)Acc@5: 78.1250 (79.5956) +2025-04-19 18:41:20,447 - train: [ INFO] - Eval : 97 Time: 0.068 (0.337) Loss: 2.6286 (1.9127) Acc@1: 50.0000 (54.3948)Acc@5: 50.0000 (79.2598) +2025-04-19 18:41:31,653 - train: [ INFO] - Train: 98 [ 0/461 ( 0%)] Loss: 2.494175 (2.4942) Loss_single: 1.801554 (1.8016) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.019s, 5.32/s (6.019s, 5.32/s) LR: 5.000e-04 Data: 5.079 (5.079) +2025-04-19 18:42:11,130 - train: [ INFO] - Train: 98 [ 50/461 ( 11%)] Loss: 2.395969 (2.4451) Loss_single: 1.739971 (1.7708) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.732s, 43.72/s (0.891s, 35.91/s) LR: 5.000e-04 Data: 0.003 (0.100) +2025-04-19 18:42:52,054 - train: [ INFO] - Train: 98 [ 100/461 ( 22%)] Loss: 2.281637 (2.3906) Loss_single: 1.625112 (1.7222) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.742s, 43.11/s (0.854s, 37.46/s) LR: 5.000e-04 Data: 0.002 (0.051) +2025-04-19 18:43:34,353 - train: [ INFO] - Train: 98 [ 150/461 ( 33%)] Loss: 2.264430 (2.3591) Loss_single: 1.604782 (1.6929) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.737s, 43.44/s (0.851s, 37.60/s) LR: 5.000e-04 Data: 0.000 (0.035) +2025-04-19 18:44:20,478 - train: [ INFO] - Train: 98 [ 200/461 ( 43%)] Loss: 2.471859 (2.3816) Loss_single: 1.796016 (1.7135) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.863s, 37.08/s (0.869s, 36.84/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-19 18:45:04,152 - train: [ INFO] - Train: 98 [ 250/461 ( 54%)] Loss: 2.185571 (2.3489) Loss_single: 1.530157 (1.6829) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.089s, 29.40/s (0.869s, 36.81/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-19 18:45:48,618 - train: [ INFO] - Train: 98 [ 300/461 ( 65%)] Loss: 2.405988 (2.3571) Loss_single: 1.747326 (1.6921) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.040s, 30.77/s (0.873s, 36.68/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-19 18:46:30,916 - train: [ INFO] - Train: 98 [ 350/461 ( 76%)] Loss: 2.267846 (2.3459) Loss_single: 1.608830 (1.6817) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.901s, 35.50/s (0.869s, 36.84/s) LR: 5.000e-04 Data: 0.003 (0.015) +2025-04-19 18:47:14,199 - train: [ INFO] - Train: 98 [ 400/461 ( 87%)] Loss: 2.506130 (2.3637) Loss_single: 1.822138 (1.6973) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.311s, 24.40/s (0.868s, 36.87/s) LR: 5.000e-04 Data: 0.006 (0.013) +2025-04-19 18:47:53,704 - train: [ INFO] - Train: 98 [ 450/461 ( 98%)] Loss: 2.310369 (2.3584) Loss_single: 1.651096 (1.6927) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.48/s (0.859s, 37.25/s) LR: 5.000e-04 Data: 0.004 (0.012) +2025-04-19 18:48:02,504 - train: [ INFO] - Train: 98 [ 460/461 (100%)] Loss: 2.582496 (2.3788) Loss_single: 1.915685 (1.7130) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.855s, 37.45/s (0.859s, 37.23/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 18:48:08,188 - train: [ INFO] - Eval : 98 Time: 5.327 (5.327) Loss: 1.9216 (1.9216) Acc@1: 56.2500 (56.2500)Acc@5: 84.3750 (84.3750) +2025-04-19 18:48:22,476 - train: [ INFO] - Eval : 98 Time: 0.296 (0.385) Loss: 1.8934 (1.8921) Acc@1: 56.2500 (55.7598)Acc@5: 78.1250 (80.5760) +2025-04-19 18:48:29,944 - train: [ INFO] - Eval : 98 Time: 0.069 (0.330) Loss: 2.8663 (1.9081) Acc@1: 50.0000 (54.7417)Acc@5: 50.0000 (79.8766) +2025-04-19 18:48:39,871 - train: [ INFO] - Train: 99 [ 0/461 ( 0%)] Loss: 2.235826 (2.2358) Loss_single: 1.580282 (1.5803) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.201s, 6.15/s (5.201s, 6.15/s) LR: 5.000e-04 Data: 4.530 (4.530) +2025-04-19 18:49:22,049 - train: [ INFO] - Train: 99 [ 50/461 ( 11%)] Loss: 2.333473 (2.2846) Loss_single: 1.677624 (1.6290) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.904s, 35.40/s (0.927s, 34.53/s) LR: 5.000e-04 Data: 0.000 (0.090) +2025-04-19 18:50:03,579 - train: [ INFO] - Train: 99 [ 100/461 ( 22%)] Loss: 2.255991 (2.2751) Loss_single: 1.597569 (1.6185) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.832s, 38.44/s (0.879s, 36.43/s) LR: 5.000e-04 Data: 0.000 (0.046) +2025-04-19 18:50:40,519 - train: [ INFO] - Train: 99 [ 150/461 ( 33%)] Loss: 2.354414 (2.2949) Loss_single: 1.687525 (1.6357) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.752s, 42.53/s (0.832s, 38.47/s) LR: 5.000e-04 Data: 0.000 (0.031) +2025-04-19 18:51:24,767 - train: [ INFO] - Train: 99 [ 200/461 ( 43%)] Loss: 2.423699 (2.3207) Loss_single: 1.754422 (1.6595) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.726s, 44.06/s (0.845s, 37.88/s) LR: 5.000e-04 Data: 0.000 (0.023) +2025-04-19 18:52:07,146 - train: [ INFO] - Train: 99 [ 250/461 ( 54%)] Loss: 2.589243 (2.3654) Loss_single: 1.851599 (1.6915) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 100.0000 (100.0000) Time: 1.020s, 31.37/s (0.845s, 37.87/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-19 18:52:49,211 - train: [ INFO] - Train: 99 [ 300/461 ( 65%)] Loss: 2.466340 (2.3799) Loss_single: 1.808648 (1.7082) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.734s, 43.57/s (0.844s, 37.91/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-19 18:53:31,212 - train: [ INFO] - Train: 99 [ 350/461 ( 76%)] Loss: 2.442489 (2.3877) Loss_single: 1.786980 (1.7181) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 1.070s, 29.92/s (0.843s, 37.94/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-19 18:54:13,918 - train: [ INFO] - Train: 99 [ 400/461 ( 87%)] Loss: 2.238961 (2.3712) Loss_single: 1.583286 (1.7031) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.693s, 46.19/s (0.845s, 37.89/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-19 18:54:56,721 - train: [ INFO] - Train: 99 [ 450/461 ( 98%)] Loss: 2.446950 (2.3787) Loss_single: 1.786144 (1.7114) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.755s, 42.40/s (0.846s, 37.84/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-19 18:55:04,188 - train: [ INFO] - Train: 99 [ 460/461 (100%)] Loss: 2.684597 (2.4065) Loss_single: 1.962806 (1.7343) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.743s, 43.08/s (0.843s, 37.94/s) LR: 5.000e-04 Data: 0.001 (0.011) +2025-04-19 18:55:10,456 - train: [ INFO] - Eval : 99 Time: 5.901 (5.901) Loss: 1.9774 (1.9774) Acc@1: 50.0000 (50.0000)Acc@5: 84.3750 (84.3750) +2025-04-19 18:55:23,950 - train: [ INFO] - Eval : 99 Time: 0.258 (0.380) Loss: 1.8547 (1.8937) Acc@1: 62.5000 (55.6985)Acc@5: 78.1250 (80.0858) +2025-04-19 18:55:31,840 - train: [ INFO] - Eval : 99 Time: 0.070 (0.333) Loss: 2.9038 (1.9111) Acc@1: 50.0000 (54.3562)Acc@5: 50.0000 (79.6453) +2025-04-19 18:55:36,595 - train: [ INFO] - *** Best metric: 55.47417116422513 (epoch 72) diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/model_best.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/model_best.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..c340612837f697fbedfeb654bc84f41d0236562a --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/model_best.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24cb3180593213d5da34e5e4db609b0c7173396a1cd9ac9253be42749e72c26f +size 179501441 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/summary.csv b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/summary.csv new file mode 100644 index 0000000000000000000000000000000000000000..6163219268b54b8aa6bf31996717a2b853088cb7 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4/summary.csv @@ -0,0 +1,101 @@ +epoch,train_loss,train_loss_single,train_loss_inverse,eval_loss,eval_top1,eval_top1_a,eval_top1_v +0,8.913422064347701,6.0999579863114795,0.0,2.4186245882244597,30.146491904394757,23.323053199691596,16.345412490362374 +1,7.956188808787953,5.571812456304377,0.0,2.2643452720083266,37.39398612181958,28.79722436391673,18.889745566692365 +2,7.426820234818892,5.228178977966309,0.0,1.8895571652796972,45.990747879722434,31.071703932151117,25.636083269082498 +3,6.896188909357244,4.9416091658852315,0.0,1.968559294548417,43.02235929067078,34.04009252120277,25.250578257517347 +4,6.867864045229825,4.900304100730202,0.0,1.9174804566176744,46.80030840400925,36.43022359290671,26.060138781804163 +5,6.724006436087868,4.797688137401234,0.0,1.82541454582832,48.727833461835004,38.62760215882806,28.643022359290672 +6,6.4798290079290215,4.642946460030296,0.0,1.80135458179318,49.53739398612182,38.04934464148034,29.838087895142635 +7,5.993401917544278,4.3660430908203125,0.0,1.7473658622000525,51.38781804163454,37.62528912875867,31.033153430994602 +8,6.148419033397328,4.43590387431058,0.0,1.6255658770306072,54.3562066306862,39.707016191210485,34.96530454895914 +9,5.871526111255992,4.290742592378096,0.0,1.7117016254798578,51.69622205088666,36.19892058596762,34.734001542020046 +10,5.74381685256958,4.264637123454701,0.0,1.7374070306511777,50.69390902081727,36.700077101002314,35.8905165767155 +11,5.452688043767756,4.045811913230202,0.0,1.7055520404736262,52.08172706245181,37.12413261372398,37.27833461835004 +12,4.628481518138539,3.517678585919467,0.0,1.805424495394081,51.811873554356204,34.65690053970702,37.933693138010796 +13,4.455186367034912,3.410898880525069,0.0,1.7752763259934754,53.19969159599075,35.81341557440247,41.480339244410175 +14,4.104010061784224,3.163467688993974,0.0,1.829189393183959,52.23592906707787,37.548188126445645,37.933693138010796 +15,3.9113983891227027,3.044983213598078,0.0,1.8905051587265826,49.76869699306091,35.774865073245955,39.745566692367 +16,3.696666110645641,2.892118519002741,0.0,1.867321021021929,49.80724749421743,37.12413261372398,41.017733230531995 +17,3.6323231133547695,2.8632971156727183,0.0,1.7900664131735138,53.35389360061681,39.01310717039321,42.02004626060139 +18,3.6393686641346323,2.869971990585327,0.0,1.8415700799240549,52.62143407864302,40.24672320740169,40.70932922127988 +19,3.48906887661327,2.771279074928977,0.0,1.880367352398157,51.00231303006939,40.32382420971473,44.44872783346184 +20,3.4191886511715976,2.6914755647832695,0.0,1.9175427671386907,50.57825751734772,39.93831919814958,44.680030840400924 +21,3.4538497057828037,2.7280169400301846,0.0,1.8990509401584645,50.57825751734772,39.745566692367,44.64148033924441 +22,3.4887968843633477,2.755061994899403,0.0,1.9076726092865766,50.886661526599845,40.67077872012336,44.64148033924441 +23,3.385315851731734,2.6678260673176157,0.0,1.9233964123722214,50.38550501156515,39.745566692367,45.065535851966075 +24,3.419461033561013,2.715679948980158,0.0,1.902960644010957,51.77332305319969,40.24672320740169,47.57131842713955 +25,3.3484152880581943,2.625418923117898,0.0,1.8944436185802969,51.5420200462606,40.40092521202776,47.14726291441789 +26,3.346046296032992,2.638855804096569,0.0,1.9281684747547394,50.46260601387818,39.43716268311488,49.961449498843486 +27,3.2982512387362393,2.594924666664817,0.0,1.9507075506811797,49.92289899768697,40.28527370855821,48.188126445643796 +28,3.303452795202082,2.5863844481381504,0.0,1.8950384676042848,51.31071703932151,39.66846569005397,45.18118735543562 +29,3.367577487772161,2.643175081773238,0.0,1.9412081901532645,50.69390902081727,40.20817270624518,46.68465690053971 +30,3.2480053251439873,2.532977429303256,0.0,1.8963493973637142,52.46723207401696,40.13107170393215,47.57131842713955 +31,3.3074469566345215,2.6020596027374268,0.0,1.8821703823327833,51.85042405551272,39.39861218195836,47.10871241326137 +32,3.187801946293224,2.4844328490170566,0.0,1.8810275139584391,52.92983808789514,39.93831919814958,49.88434849653046 +33,3.2401338057084517,2.5143410726027056,0.0,1.8981733062952963,51.657671549730146,41.094834232845024,46.60755589822668 +34,3.0894840197129683,2.3931705301458184,0.0,1.9030943005105212,51.69622205088666,40.05397070161912,50.96376252891287 +35,3.156486056067727,2.458013881336559,0.0,1.931700356298901,51.23361603700848,40.555127216653815,49.38319198149576 +36,3.259755849838257,2.5482546632940117,0.0,1.9167086475154669,51.58057054741712,40.20817270624518,48.61218195836546 +37,3.147493449124423,2.4452531120993872,0.0,1.9012195858113474,51.927525057825754,39.745566692367,49.69159599074788 +38,3.195098400115967,2.4867431900717993,0.0,1.9306611038669772,52.00462606013878,39.55281418658443,50.038550501156514 +39,3.0399088859558105,2.3429606827822598,0.0,1.9120628173845773,51.811873554356204,39.629915188897456,49.30609097918273 +40,3.1596357388929888,2.447877515446056,0.0,1.9090616583548423,51.85042405551272,39.59136468774094,52.35158057054742 +41,3.118578217246316,2.393803661519831,0.0,1.9004772409808204,52.15882806476484,41.2875867386276,49.88434849653046 +42,3.1229797059839424,2.4038038470528345,0.0,1.9236741179949335,52.27447956823439,40.32382420971473,49.46029298380879 +43,3.064956534992565,2.354787913235751,0.0,1.893450268985863,52.8141865844256,39.97686969930609,49.80724749421743 +44,3.0591601675206963,2.364843498576771,0.0,1.9310902580446525,51.11796453353894,38.43484965304549,49.76869699306091 +45,3.040640419179743,2.3460383631966333,0.0,1.89587194035397,51.927525057825754,39.707016191210485,49.961449498843486 +46,2.9290889609943735,2.2308849638158623,0.0,1.8957584202059803,51.88897455666924,41.094834232845024,51.734772552043175 +47,3.0294453230771152,2.325488112189553,0.0,1.8707045902172785,52.54433307632999,39.97686969930609,52.27447956823439 +48,3.1317387494173916,2.405963897705078,0.0,1.9066181032126375,52.42868157286045,39.55281418658443,51.85042405551272 +49,2.9616283069957388,2.265440572391857,0.0,1.8994978067961306,53.00693909020817,40.555127216653815,51.5420200462606 +50,3.1455485820770264,2.4227043281901968,0.0,1.882923813351504,53.31534309946029,40.01542020046261,52.582883577486506 +51,2.9158610213886607,2.2247644771229136,0.0,1.8807359642493513,52.73708558211257,40.13107170393215,52.27447956823439 +52,2.9131210934032095,2.2226133671673862,0.0,1.8805447238725062,53.00693909020817,40.05397070161912,51.657671549730146 +53,2.893153017217463,2.1985829418355767,0.0,1.866078942577565,52.968388589051656,40.43947571318427,52.775636083269085 +54,2.983793995597146,2.2885990142822266,0.0,1.8809903658805853,53.700848111025444,40.747879722436394,53.39244410177332 +55,2.9351968331770464,2.222713134505532,0.0,1.8819090033276042,53.238242097147264,39.36006168080185,50.84811102544333 +56,2.867612058466131,2.1726393808018076,0.0,1.848045437723835,53.77794911333847,40.092521202775636,52.0431765612953 +57,2.88020075451244,2.1844664270227607,0.0,1.8708817611406101,52.62143407864302,40.82498072474942,52.0431765612953 +58,2.8559555357152764,2.1746761040254072,0.0,1.8831700686776096,52.0431765612953,39.55281418658443,51.927525057825754 +59,2.873554988340898,2.1813508814031426,0.0,1.9156408129789873,52.46723207401696,39.43716268311488,52.42868157286045 +60,2.8872393044558438,2.2007272135127676,0.0,1.8843953909098228,54.39475713184272,39.321511179645334,51.23361603700848 +61,2.8424318486993965,2.141035556793213,0.0,1.8908357570607017,52.8141865844256,40.13107170393215,52.390131071703934 +62,2.8343656930056484,2.14149995283647,0.0,1.9011504901953633,52.15882806476484,39.321511179645334,53.19969159599075 +63,2.904526775533503,2.201468998735601,0.0,1.9070615084610631,53.045489591364685,40.13107170393215,52.0431765612953 +64,2.869010014967485,2.1730627796866675,0.0,1.9148258545257169,52.313030069390905,39.09020817270625,51.927525057825754 +65,2.900116508657282,2.2072539112784644,0.0,1.8638444685807298,53.19969159599075,39.51426368542791,53.161141094834235 +66,2.8059865778142754,2.1229736588217993,0.0,1.8920320319320574,52.582883577486506,39.86121819583654,50.7710100231303 +67,2.7948883230035957,2.0860411904074927,0.0,1.862464604785834,53.893600616808016,39.707016191210485,54.43330763299923 +68,2.819111693989147,2.139646064151417,0.0,1.9011826450859663,51.85042405551272,40.362374710871244,51.19506553585197 +69,2.7721076878634365,2.095326152714816,0.0,1.8980726456770827,52.698535080956056,38.74325366229761,53.508095605242865 +70,2.5916575735265557,1.9112647555091165,0.0,1.8891348250572186,53.93215111796454,40.70932922127988,57.51734772552043 +71,2.5009771910580723,1.8191040754318237,0.0,1.877019375953292,54.3562066306862,41.017733230531995,57.97995373939861 +72,2.5318940336054023,1.8504195104945789,0.0,1.8751355013483382,55.47417116422513,40.747879722436394,58.28835774865073 +73,2.559442325071855,1.86715059930628,0.0,1.8776340866971217,55.011565150346954,40.32382420971473,58.09560524286816 +74,2.4455772096460517,1.7696142846887761,0.0,1.8859577449175056,54.20200462606014,40.40092521202776,57.170393215111794 +75,2.5098052241585473,1.8350491632114758,0.0,1.8917851683352669,54.58750963762529,40.24672320740169,57.20894371626831 +76,2.5211455171758477,1.8380828120491721,0.0,1.8915326236851324,54.51040863531226,40.632228218966844,57.20894371626831 +77,2.4673178412697534,1.7988011945377698,0.0,1.8845585563500844,54.934464148033925,40.13107170393215,57.90285273708558 +78,2.5254632993177935,1.8543669202110984,0.0,1.894946760274671,54.31765612952968,40.940632228218966,57.748650732459524 +79,2.4496282013979824,1.7808785221793435,0.0,1.894252816805402,55.43562066306862,41.210485736314574,56.55358519660756 +80,2.484100016680631,1.8123636787587947,0.0,1.887810735584868,55.35851966075559,41.17193523515806,58.018504240555124 +81,2.445179592479359,1.7747538523240523,0.0,1.9026271706833322,54.548959136468774,39.97686969930609,57.170393215111794 +82,2.530971787192605,1.8478322462602095,0.0,1.8959243119268483,54.70316114109483,40.940632228218966,58.134155744024675 +83,2.444200949235396,1.7722663662650369,0.0,1.908030605904396,54.78026214340787,40.40092521202776,57.24749421742483 +84,2.4377663785761055,1.7739294225519353,0.0,1.902572711431346,54.81881264456438,39.86121819583654,57.71010023130301 +85,2.4400927153500644,1.7682537165555088,0.0,1.9093585935297064,54.58750963762529,40.32382420971473,57.24749421742483 +86,2.498041716488925,1.8211543993516401,0.0,1.9054594642856806,54.39475713184272,40.28527370855821,56.6692367000771 +87,2.48664927482605,1.810897328636863,0.0,1.9057708282882466,54.857363145720896,40.90208172706245,56.93909020817271 +88,2.473065961490978,1.7910620407624678,0.0,1.9121413475380737,54.39475713184272,40.32382420971473,57.286044718581344 +89,2.4410992102189497,1.75708345933394,0.0,1.9126712123338498,54.009252120277566,40.362374710871244,56.36083269082498 +90,2.4862161549654873,1.7980807044289329,0.0,1.8990497668155266,54.471858134155745,40.40092521202776,57.170393215111794 +91,2.4170630411668257,1.7487245039506392,0.0,1.9122141334030751,54.20200462606014,40.32382420971473,56.245181187355435 +92,2.3978711691769687,1.7318652868270874,0.0,1.9051065198623316,54.548959136468774,40.20817270624518,57.093292212798765 +93,2.551802331751043,1.854498570615595,0.0,1.9124730269359274,54.39475713184272,40.43947571318427,56.245181187355435 +94,2.4188556454398413,1.7558914422988892,0.0,1.9174483050358875,53.93215111796454,40.32382420971473,56.36083269082498 +95,2.4394628784873267,1.75409244407307,0.0,1.915972285024368,54.548959136468774,40.632228218966844,56.51503469545104 +96,2.4506113962693648,1.772583159533414,0.0,1.895423756623691,55.08866615265998,40.362374710871244,56.86198920585968 +97,2.354710665616122,1.693143205209212,0.0,1.9127150442201355,54.39475713184272,40.28527370855821,56.51503469545104 +98,2.3787700696425005,1.712969801642678,0.0,1.908131160640496,54.741711642251346,40.555127216653815,57.24749421742483 +99,2.406543905084783,1.7342622171748767,0.0,1.9111042888511947,54.3562066306862,40.43947571318427,56.39938319198149 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5 b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5 new file mode 100644 index 0000000000000000000000000000000000000000..16c22a3dcc0ac603dc52811cc1d2d219d14e324c --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85e0279ce2e13be3567ac0a6d9930bbe1d046b40293096074be77a1c4916209f +size 179467884 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5_[-10.0,10.0,51]x[-10.0,10.0,51].h5 b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5_[-10.0,10.0,51]x[-10.0,10.0,51].h5 new file mode 100644 index 0000000000000000000000000000000000000000..4fd983bec99fb455b93ea0b6b0ff24e7fd3fd783 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/_weights_xignore=biasbn_xnorm=filter_yignore=biasbn_ynorm=filter.h5_[-10.0,10.0,51]x[-10.0,10.0,51].h5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:443db5c73240ab8e5d6ef2f156f74df05e26ce8e5a1b7b8a82f55a5d0fbfff39 +size 50640 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/args.yaml b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/args.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c48f9a495758df035d9d048f71e41bf491bdb5f9 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/args.yaml @@ -0,0 +1,162 @@ +aa: rand-m9-mstd0.5-inc1 +act_fun: QGateGrad +adam_epoch: 1000 +adaptation_info: false +adaptive_node: false +alpha: 0.8 +amp: false +apex_amp: false +audio_path: /mnt/home/hexiang/datasets/CREMA-D/AudioWAV/ +aug_splits: 0 +batch_size: 32 +bn_eps: null +bn_momentum: null +bn_tf: false +channels_last: false +clip_grad: null +color_jitter: 0.4 +conf_mat: false +conv_type: normal +cooldown_epochs: 10 +critical_loss: false +crop_pct: null +cut_mix: false +cutmix: 0.0 +cutmix_beta: 2.0 +cutmix_minmax: null +cutmix_noise: 0.0 +cutmix_num: 1 +cutmix_prob: 0.5 +dataset: KineticSound +decay_epochs: 70 +decay_rate: 0.1 +device: 0 +dist_bn: '' +drop: 0.0 +drop_block: null +drop_connect: null +drop_path: 0.1 +encode: direct +epochs: 100 +eval: false +eval_checkpoint: '' +eval_metric: top1 +event_mix: false +event_size: 48 +fps: 1 +fusion_method: concat +gaussian_n: 3 +gp: null +hflip: 0.5 +img_size: 224 +initial_checkpoint: '' +interpolation: '' +inverse: true +inverse_ends: 100 +inverse_starts: 0 +jsd: false +kernel_method: cuda +layer_by_layer: false +local_rank: 0 +log_interval: 50 +loss_fn: ce +lr: 0.005 +lr_cycle_limit: 1 +lr_cycle_mul: 1.0 +lr_noise: null +lr_noise_pct: 0.67 +lr_noise_std: 1.0 +mean: null +mem_dist: false +meta_ratio: -1.0 +min_lr: 1.0e-05 +mix_up: false +mixup: 0.0 +mixup_mode: batch +mixup_off_epoch: 0 +mixup_prob: 0.0 +mixup_switch_prob: 0.5 +modality: audio-visual +model: AVresnet18 +model_ema: false +model_ema_decay: 0.99996 +model_ema_force_cpu: false +modulation: Normal +modulation_ends: 50 +modulation_starts: 0 +momentum: 0.9 +n_encode_type: linear +n_groups: 1 +n_preact: false +native_amp: false +newton_maxiter: 20 +no_aug: false +no_prefetcher: false +no_resume_opt: false +node_resume: '' +node_type: ReLUNode +noisy_grad: 0.0 +num_classes: 31 +num_gpu: 1 +opt: sgd +opt_betas: null +opt_eps: 1.0e-08 +output: ./exp_results +patience_epochs: 10 +pin_mem: false +power: 1 +pretrained: false +psai: 1.0 +rand_aug: false +rand_step: false +randaug_m: 15 +randaug_n: 3 +ratio: +- 0.75 +- 1.3333333333333333 +recount: 1 +recovery_interval: 0 +remode: pixel +reprob: 0.25 +requires_thres_grad: false +reset_drop: false +resplit: false +resume: '' +save_images: false +scale: +- 0.08 +- 1.0 +sched: step +seed: 2025 +sew_cnf: ADD +sigmoid_thres: false +smoothing: 0.1 +snr: -100 +snrModality: null +spike_output: false +spike_rate: false +split_bn: false +start_epoch: null +std: null +step: 1 +suffix: '' +sync_bn: false +tau: 2.0 +temporal_flatten: false +tensorboard_dir: ./exp_results +tet_loss: false +threshold: 0.5 +train_interpolation: random +train_portion: 0.9 +tsne: false +tta: 0 +use_multi_epochs_loader: false +use_video_frames: 3 +validation_batch_size_multiplier: 1 +vflip: 0.0 +visual_path: /mnt/home/hexiang/datasets/CREMA-D/ +visualize: false +warmup_epochs: 0 +warmup_lr: 1.0e-06 +weight_decay: 0.0005 +workers: 8 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-74.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-74.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..99314478bb1e4b674b87fa035497fcb916a4c281 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-74.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a283adbc9717a11534fbe7859f2d754208cfde3c345f5d190e77e300706897f7 +size 179501441 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/events.out.tfevents.1744967800.af1fd63cd999.621246.0 b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/events.out.tfevents.1744967800.af1fd63cd999.621246.0 new file mode 100644 index 0000000000000000000000000000000000000000..6a2f0d1e13f0707df7c836e68a8114e7eda419a5 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/events.out.tfevents.1744967800.af1fd63cd999.621246.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1dcb17c1d35eb8a6b56bf5e078f4db34199784c8e72c35d0cde9e0f752e0de9 +size 12954544 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/last.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/last.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..0f7e8cb469d22b6859f3b28e571b880d0986250d --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/last.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaccc9ba71d70c66cd49d0ed6c68668006fd5bd48c0c5f1cfaffb8cfac78ae48 +size 179501441 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/log.txt b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..8d01e57be52532666aa0cb202c56cbea9a2967ea --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/log.txt @@ -0,0 +1,1452 @@ +2025-04-18 09:16:40,263 - train: [ INFO] - Training with a single process on 1 GPUs. +2025-04-18 09:16:44,527 - train: [ INFO] - AMP not enabled. Training in float32. +2025-04-18 09:16:44,528 - train: [ INFO] - Scheduled epochs: 100 +2025-04-18 09:16:58,160 - train: [ INFO] - Train: 0 [ 0/461 ( 0%)] Loss: 10.719982 (10.7200) Loss_single: 7.072478 (7.0725) Loss_inverse: 0.000000 (0.0000) Acc@1: 3.1250 ( 3.1250) Acc@5: 18.7500 (18.7500) Time: 13.623s, 2.35/s (13.623s, 2.35/s) LR: 5.000e-03 Data: 7.599 (7.599) +2025-04-18 09:17:06,114 - train: [ INFO] - Train: 0 [ 50/461 ( 11%)] Loss: 10.401055 (10.5605) Loss_single: 6.990743 (7.0316) Loss_inverse: 0.000000 (0.0000) Acc@1: 12.5000 ( 7.8125) Acc@5: 34.3750 (26.5625) Time: 0.102s, 314.77/s (0.422s, 75.75/s) LR: 5.000e-03 Data: 0.000 (0.215) +2025-04-18 09:17:21,181 - train: [ INFO] - Train: 0 [ 100/461 ( 22%)] Loss: 8.640416 (9.9205) Loss_single: 5.995893 (6.6864) Loss_inverse: 0.000000 (0.0000) Acc@1: 31.2500 (15.6250) Acc@5: 59.3750 (37.5000) Time: 0.080s, 397.68/s (0.362s, 88.38/s) LR: 5.000e-03 Data: 0.000 (0.208) +2025-04-18 09:17:37,489 - train: [ INFO] - Train: 0 [ 150/461 ( 33%)] Loss: 8.641858 (9.6008) Loss_single: 5.928420 (6.4969) Loss_inverse: 0.000000 (0.0000) Acc@1: 15.6250 (15.6250) Acc@5: 68.7500 (45.3125) Time: 1.182s, 27.07/s (0.350s, 91.45/s) LR: 5.000e-03 Data: 0.975 (0.213) +2025-04-18 09:17:52,220 - train: [ INFO] - Train: 0 [ 200/461 ( 43%)] Loss: 7.872415 (9.2551) Loss_single: 5.526597 (6.3028) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (21.8750) Acc@5: 78.1250 (51.8750) Time: 0.123s, 260.14/s (0.336s, 95.25/s) LR: 5.000e-03 Data: 0.000 (0.208) +2025-04-18 09:18:07,166 - train: [ INFO] - Train: 0 [ 250/461 ( 54%)] Loss: 8.627345 (9.1505) Loss_single: 6.017389 (6.2553) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (23.9583) Acc@5: 68.7500 (54.6875) Time: 0.081s, 394.58/s (0.328s, 97.46/s) LR: 5.000e-03 Data: 0.000 (0.207) +2025-04-18 09:18:41,519 - train: [ INFO] - Train: 0 [ 300/461 ( 65%)] Loss: 8.416099 (9.0456) Loss_single: 5.790589 (6.1889) Loss_inverse: 0.000000 (0.0000) Acc@1: 25.0000 (24.1071) Acc@5: 65.6250 (56.2500) Time: 0.082s, 391.12/s (0.373s, 85.82/s) LR: 5.000e-03 Data: 0.002 (0.255) +2025-04-18 09:18:59,323 - train: [ INFO] - Train: 0 [ 350/461 ( 76%)] Loss: 8.562950 (8.9853) Loss_single: 5.918099 (6.1550) Loss_inverse: 0.000000 (0.0000) Acc@1: 31.2500 (25.0000) Acc@5: 53.1250 (55.8594) Time: 0.079s, 403.76/s (0.370s, 86.55/s) LR: 5.000e-03 Data: 0.000 (0.255) +2025-04-18 09:19:13,593 - train: [ INFO] - Train: 0 [ 400/461 ( 87%)] Loss: 8.737133 (8.9577) Loss_single: 5.996840 (6.1374) Loss_inverse: 0.000000 (0.0000) Acc@1: 25.0000 (25.0000) Acc@5: 59.3750 (56.2500) Time: 0.083s, 383.83/s (0.359s, 89.11/s) LR: 5.000e-03 Data: 0.000 (0.247) +2025-04-18 09:19:29,816 - train: [ INFO] - Train: 0 [ 450/461 ( 98%)] Loss: 8.544861 (8.9164) Loss_single: 5.866578 (6.1104) Loss_inverse: 0.000000 (0.0000) Acc@1: 21.8750 (24.6875) Acc@5: 65.6250 (57.1875) Time: 0.092s, 349.26/s (0.355s, 90.11/s) LR: 5.000e-03 Data: 0.000 (0.245) +2025-04-18 09:19:31,126 - train: [ INFO] - Train: 0 [ 460/461 (100%)] Loss: 8.343237 (8.8643) Loss_single: 5.784344 (6.0807) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (26.1364) Acc@5: 65.6250 (57.9545) Time: 0.078s, 411.27/s (0.350s, 91.36/s) LR: 5.000e-03 Data: 0.000 (0.241) +2025-04-18 09:19:39,169 - train: [ INFO] - Eval : 0 Time: 7.863 (7.863) Loss: 2.3267 (2.3267) Acc@1: 31.2500 (31.2500)Acc@5: 59.3750 (59.3750) +2025-04-18 09:19:53,682 - train: [ INFO] - Eval : 0 Time: 0.239 (0.439) Loss: 2.6097 (2.4703) Acc@1: 25.0000 (28.6765)Acc@5: 62.5000 (65.5025) +2025-04-18 09:19:58,821 - train: [ INFO] - Eval : 0 Time: 0.018 (0.336) Loss: 5.1436 (2.4609) Acc@1: 0.0000 (28.7972)Acc@5: 0.0000 (66.0370) +2025-04-18 09:20:08,554 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-0.pth.tar', 28.79722436391673) + +2025-04-18 09:20:13,123 - train: [ INFO] - Train: 1 [ 0/461 ( 0%)] Loss: 7.815571 (7.8156) Loss_single: 5.419524 (5.4195) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (37.5000) Acc@5: 68.7500 (68.7500) Time: 4.522s, 7.08/s (4.522s, 7.08/s) LR: 5.000e-03 Data: 4.350 (4.350) +2025-04-18 09:20:20,396 - train: [ INFO] - Train: 1 [ 50/461 ( 11%)] Loss: 8.509930 (8.1628) Loss_single: 5.941968 (5.6807) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (35.9375) Acc@5: 62.5000 (65.6250) Time: 0.105s, 305.31/s (0.230s, 139.00/s) LR: 5.000e-03 Data: 0.001 (0.086) +2025-04-18 09:20:26,372 - train: [ INFO] - Train: 1 [ 100/461 ( 22%)] Loss: 7.807441 (8.0443) Loss_single: 5.392491 (5.5847) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (35.4167) Acc@5: 68.7500 (66.6667) Time: 0.180s, 177.82/s (0.175s, 182.82/s) LR: 5.000e-03 Data: 0.001 (0.044) +2025-04-18 09:20:32,313 - train: [ INFO] - Train: 1 [ 150/461 ( 33%)] Loss: 7.752483 (7.9714) Loss_single: 5.416879 (5.5427) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (35.1562) Acc@5: 75.0000 (68.7500) Time: 0.079s, 403.00/s (0.156s, 204.99/s) LR: 5.000e-03 Data: 0.001 (0.030) +2025-04-18 09:20:38,082 - train: [ INFO] - Train: 1 [ 200/461 ( 43%)] Loss: 7.227151 (7.8225) Loss_single: 5.113737 (5.4569) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (38.7500) Acc@5: 78.1250 (70.6250) Time: 0.114s, 280.66/s (0.146s, 219.56/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-18 09:20:44,080 - train: [ INFO] - Train: 1 [ 250/461 ( 54%)] Loss: 8.365211 (7.9130) Loss_single: 5.931273 (5.5360) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (38.0208) Acc@5: 75.0000 (71.3542) Time: 0.115s, 278.38/s (0.140s, 227.88/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 09:20:49,992 - train: [ INFO] - Train: 1 [ 300/461 ( 65%)] Loss: 7.991297 (7.9242) Loss_single: 5.570362 (5.5409) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (37.5000) Acc@5: 75.0000 (71.8750) Time: 0.134s, 238.88/s (0.135s, 236.94/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 09:20:56,129 - train: [ INFO] - Train: 1 [ 350/461 ( 76%)] Loss: 7.978827 (7.9310) Loss_single: 5.633933 (5.5525) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (38.2812) Acc@5: 81.2500 (73.0469) Time: 0.105s, 304.19/s (0.133s, 240.34/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-18 09:21:01,710 - train: [ INFO] - Train: 1 [ 400/461 ( 87%)] Loss: 8.481991 (7.9922) Loss_single: 6.029206 (5.6055) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (38.1944) Acc@5: 75.0000 (73.2639) Time: 0.079s, 407.43/s (0.130s, 245.55/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 09:21:06,627 - train: [ INFO] - Train: 1 [ 450/461 ( 98%)] Loss: 8.043344 (7.9973) Loss_single: 5.525559 (5.5975) Loss_inverse: 0.000000 (0.0000) Acc@1: 34.3750 (37.8125) Acc@5: 68.7500 (72.8125) Time: 0.080s, 399.83/s (0.127s, 252.52/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 09:21:07,454 - train: [ INFO] - Train: 1 [ 460/461 (100%)] Loss: 7.479002 (7.9502) Loss_single: 5.312485 (5.5716) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (38.3523) Acc@5: 75.0000 (73.0114) Time: 0.082s, 388.74/s (0.126s, 254.47/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 09:21:12,679 - train: [ INFO] - Eval : 1 Time: 4.941 (4.941) Loss: 2.8331 (2.8331) Acc@1: 28.1250 (28.1250)Acc@5: 53.1250 (53.1250) +2025-04-18 09:21:15,666 - train: [ INFO] - Eval : 1 Time: 0.063 (0.155) Loss: 2.7267 (2.5582) Acc@1: 34.3750 (32.4755)Acc@5: 62.5000 (64.4608) +2025-04-18 09:21:17,723 - train: [ INFO] - Eval : 1 Time: 0.015 (0.122) Loss: 5.9955 (2.5369) Acc@1: 0.0000 (32.9607)Acc@5: 0.0000 (64.5721) +2025-04-18 09:21:22,546 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-1.pth.tar', 32.960678488820356) + +2025-04-18 09:21:27,725 - train: [ INFO] - Train: 2 [ 0/461 ( 0%)] Loss: 7.138416 (7.1384) Loss_single: 5.019668 (5.0197) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (46.8750) Acc@5: 78.1250 (78.1250) Time: 5.155s, 6.21/s (5.155s, 6.21/s) LR: 5.000e-03 Data: 4.964 (4.964) +2025-04-18 09:21:34,230 - train: [ INFO] - Train: 2 [ 50/461 ( 11%)] Loss: 7.805411 (7.4719) Loss_single: 5.368176 (5.1939) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (45.3125) Acc@5: 75.0000 (76.5625) Time: 0.111s, 287.93/s (0.228s, 140.62/s) LR: 5.000e-03 Data: 0.000 (0.098) +2025-04-18 09:21:40,076 - train: [ INFO] - Train: 2 [ 100/461 ( 22%)] Loss: 7.292028 (7.4120) Loss_single: 5.147418 (5.1784) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (46.8750) Acc@5: 71.8750 (75.0000) Time: 0.092s, 347.70/s (0.172s, 185.59/s) LR: 5.000e-03 Data: 0.001 (0.050) +2025-04-18 09:21:45,533 - train: [ INFO] - Train: 2 [ 150/461 ( 33%)] Loss: 7.149941 (7.3464) Loss_single: 5.027510 (5.1407) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (47.6562) Acc@5: 78.1250 (75.7812) Time: 0.111s, 287.15/s (0.151s, 211.56/s) LR: 5.000e-03 Data: 0.000 (0.034) +2025-04-18 09:21:51,201 - train: [ INFO] - Train: 2 [ 200/461 ( 43%)] Loss: 7.310457 (7.3393) Loss_single: 5.180974 (5.1487) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (45.6250) Acc@5: 75.0000 (75.6250) Time: 0.165s, 193.88/s (0.142s, 225.88/s) LR: 5.000e-03 Data: 0.000 (0.026) +2025-04-18 09:21:56,810 - train: [ INFO] - Train: 2 [ 250/461 ( 54%)] Loss: 7.325401 (7.3369) Loss_single: 5.079297 (5.1372) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (44.7917) Acc@5: 81.2500 (76.5625) Time: 0.077s, 413.20/s (0.136s, 235.92/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-18 09:22:02,415 - train: [ INFO] - Train: 2 [ 300/461 ( 65%)] Loss: 8.229939 (7.4645) Loss_single: 5.748143 (5.2245) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (44.1964) Acc@5: 78.1250 (76.7857) Time: 0.082s, 390.64/s (0.132s, 243.12/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-18 09:22:08,475 - train: [ INFO] - Train: 2 [ 350/461 ( 76%)] Loss: 7.450753 (7.4628) Loss_single: 5.338310 (5.2387) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (44.9219) Acc@5: 90.6250 (78.5156) Time: 0.102s, 314.45/s (0.130s, 246.29/s) LR: 5.000e-03 Data: 0.001 (0.015) +2025-04-18 09:22:14,378 - train: [ INFO] - Train: 2 [ 400/461 ( 87%)] Loss: 7.256619 (7.4399) Loss_single: 5.069160 (5.2199) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (44.4444) Acc@5: 81.2500 (78.8194) Time: 0.116s, 276.54/s (0.128s, 249.31/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 09:22:20,745 - train: [ INFO] - Train: 2 [ 450/461 ( 98%)] Loss: 7.551278 (7.4510) Loss_single: 5.349144 (5.2328) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (44.0625) Acc@5: 84.3750 (79.3750) Time: 0.076s, 420.40/s (0.126s, 254.48/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 09:22:21,568 - train: [ INFO] - Train: 2 [ 460/461 (100%)] Loss: 7.613537 (7.4658) Loss_single: 5.355205 (5.2439) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (43.7500) Acc@5: 75.0000 (78.9773) Time: 0.081s, 395.45/s (0.125s, 256.43/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 09:22:25,758 - train: [ INFO] - Eval : 2 Time: 3.956 (3.956) Loss: 1.9075 (1.9075) Acc@1: 40.6250 (40.6250)Acc@5: 81.2500 (81.2500) +2025-04-18 09:22:31,772 - train: [ INFO] - Eval : 2 Time: 0.053 (0.195) Loss: 2.1929 (1.9822) Acc@1: 46.8750 (43.4436)Acc@5: 68.7500 (75.3064) +2025-04-18 09:22:33,525 - train: [ INFO] - Eval : 2 Time: 0.014 (0.143) Loss: 4.4288 (1.9738) Acc@1: 0.0000 (43.5621)Acc@5: 0.0000 (75.2120) +2025-04-18 09:22:36,402 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-2.pth.tar', 43.562066306861986) + +2025-04-18 09:22:42,546 - train: [ INFO] - Train: 3 [ 0/461 ( 0%)] Loss: 6.946611 (6.9466) Loss_single: 4.965800 (4.9658) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (50.0000) Acc@5: 87.5000 (87.5000) Time: 6.095s, 5.25/s (6.095s, 5.25/s) LR: 5.000e-03 Data: 5.933 (5.933) +2025-04-18 09:22:48,695 - train: [ INFO] - Train: 3 [ 50/461 ( 11%)] Loss: 6.790710 (6.8687) Loss_single: 4.879227 (4.9225) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (50.0000) Acc@5: 78.1250 (82.8125) Time: 0.124s, 258.00/s (0.239s, 133.75/s) LR: 5.000e-03 Data: 0.001 (0.117) +2025-04-18 09:22:54,945 - train: [ INFO] - Train: 3 [ 100/461 ( 22%)] Loss: 7.268330 (7.0019) Loss_single: 5.167965 (5.0043) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (50.0000) Acc@5: 75.0000 (80.2083) Time: 0.117s, 274.49/s (0.182s, 175.57/s) LR: 5.000e-03 Data: 0.001 (0.059) +2025-04-18 09:23:00,686 - train: [ INFO] - Train: 3 [ 150/461 ( 33%)] Loss: 6.893536 (6.9748) Loss_single: 4.980865 (4.9985) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (50.0000) Acc@5: 81.2500 (80.4688) Time: 0.093s, 343.85/s (0.160s, 200.49/s) LR: 5.000e-03 Data: 0.001 (0.040) +2025-04-18 09:23:06,597 - train: [ INFO] - Train: 3 [ 200/461 ( 43%)] Loss: 7.579701 (7.0958) Loss_single: 5.395156 (5.0778) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (47.5000) Acc@5: 81.2500 (80.6250) Time: 0.174s, 184.00/s (0.149s, 214.57/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-18 09:23:12,252 - train: [ INFO] - Train: 3 [ 250/461 ( 54%)] Loss: 6.633990 (7.0188) Loss_single: 4.786509 (5.0293) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (49.4792) Acc@5: 87.5000 (81.7708) Time: 0.143s, 223.22/s (0.142s, 225.73/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-18 09:23:17,857 - train: [ INFO] - Train: 3 [ 300/461 ( 65%)] Loss: 6.615726 (6.9612) Loss_single: 4.753306 (4.9898) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (50.4464) Acc@5: 87.5000 (82.5893) Time: 0.093s, 342.30/s (0.137s, 234.22/s) LR: 5.000e-03 Data: 0.001 (0.020) +2025-04-18 09:23:23,682 - train: [ INFO] - Train: 3 [ 350/461 ( 76%)] Loss: 6.021602 (6.8438) Loss_single: 4.466812 (4.9245) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (53.1250) Acc@5: 100.0000 (84.7656) Time: 0.111s, 287.94/s (0.134s, 239.63/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 09:23:30,432 - train: [ INFO] - Train: 3 [ 400/461 ( 87%)] Loss: 6.762699 (6.8348) Loss_single: 4.926628 (4.9247) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (53.8194) Acc@5: 84.3750 (84.7222) Time: 0.178s, 180.18/s (0.131s, 244.32/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-18 09:23:35,843 - train: [ INFO] - Train: 3 [ 450/461 ( 98%)] Loss: 7.561666 (6.9075) Loss_single: 5.291859 (4.9614) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (53.1250) Acc@5: 84.3750 (84.6875) Time: 0.080s, 399.33/s (0.128s, 249.48/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 09:23:36,762 - train: [ INFO] - Train: 3 [ 460/461 (100%)] Loss: 6.604880 (6.8800) Loss_single: 4.707539 (4.9383) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (53.6932) Acc@5: 81.2500 (84.3750) Time: 0.089s, 361.02/s (0.127s, 251.07/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 09:23:41,216 - train: [ INFO] - Eval : 3 Time: 4.146 (4.146) Loss: 1.8513 (1.8513) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-18 09:23:46,336 - train: [ INFO] - Eval : 3 Time: 0.052 (0.182) Loss: 1.8148 (1.9379) Acc@1: 56.2500 (45.1593)Acc@5: 75.0000 (76.6544) +2025-04-18 09:23:47,971 - train: [ INFO] - Eval : 3 Time: 0.018 (0.133) Loss: 4.7376 (1.9343) Acc@1: 0.0000 (45.6052)Acc@5: 0.0000 (76.7540) +2025-04-18 09:23:50,815 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-3.pth.tar', 45.60524286815728) + +2025-04-18 09:23:57,169 - train: [ INFO] - Train: 4 [ 0/461 ( 0%)] Loss: 6.019440 (6.0194) Loss_single: 4.333973 (4.3340) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (62.5000) Acc@5: 90.6250 (90.6250) Time: 6.310s, 5.07/s (6.310s, 5.07/s) LR: 5.000e-03 Data: 6.123 (6.123) +2025-04-18 09:24:03,207 - train: [ INFO] - Train: 4 [ 50/461 ( 11%)] Loss: 6.874726 (6.4471) Loss_single: 4.940449 (4.6372) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (56.2500) Acc@5: 93.7500 (92.1875) Time: 0.135s, 237.50/s (0.241s, 132.57/s) LR: 5.000e-03 Data: 0.000 (0.127) +2025-04-18 09:24:08,906 - train: [ INFO] - Train: 4 [ 100/461 ( 22%)] Loss: 6.588820 (6.4943) Loss_single: 4.740628 (4.6717) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (56.2500) Acc@5: 84.3750 (89.5833) Time: 0.092s, 346.38/s (0.178s, 179.92/s) LR: 5.000e-03 Data: 0.000 (0.064) +2025-04-18 09:24:14,873 - train: [ INFO] - Train: 4 [ 150/461 ( 33%)] Loss: 7.443413 (6.7316) Loss_single: 5.254763 (4.8175) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (52.3438) Acc@5: 75.0000 (85.9375) Time: 0.082s, 392.48/s (0.151s, 211.64/s) LR: 5.000e-03 Data: 0.001 (0.043) +2025-04-18 09:24:24,078 - train: [ INFO] - Train: 4 [ 200/461 ( 43%)] Loss: 7.578854 (6.9011) Loss_single: 5.287859 (4.9115) Loss_inverse: 0.000000 (0.0000) Acc@1: 37.5000 (49.3750) Acc@5: 81.2500 (85.0000) Time: 0.079s, 404.14/s (0.158s, 202.66/s) LR: 5.000e-03 Data: 0.000 (0.053) +2025-04-18 09:24:30,856 - train: [ INFO] - Train: 4 [ 250/461 ( 54%)] Loss: 7.341835 (6.9745) Loss_single: 5.222674 (4.9634) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (49.4792) Acc@5: 78.1250 (83.8542) Time: 0.076s, 419.33/s (0.152s, 210.81/s) LR: 5.000e-03 Data: 0.000 (0.047) +2025-04-18 09:24:45,961 - train: [ INFO] - Train: 4 [ 300/461 ( 65%)] Loss: 6.705892 (6.9361) Loss_single: 4.787405 (4.9383) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (50.4464) Acc@5: 78.1250 (83.0357) Time: 0.516s, 61.98/s (0.174s, 183.93/s) LR: 5.000e-03 Data: 0.327 (0.071) +2025-04-18 09:24:52,970 - train: [ INFO] - Train: 4 [ 350/461 ( 76%)] Loss: 7.011414 (6.9455) Loss_single: 4.936704 (4.9381) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (49.6094) Acc@5: 81.2500 (82.8125) Time: 0.075s, 424.32/s (0.169s, 189.39/s) LR: 5.000e-03 Data: 0.000 (0.064) +2025-04-18 09:25:00,593 - train: [ INFO] - Train: 4 [ 400/461 ( 87%)] Loss: 6.840940 (6.9339) Loss_single: 4.915912 (4.9356) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (51.0417) Acc@5: 75.0000 (81.9444) Time: 0.081s, 397.26/s (0.159s, 200.91/s) LR: 5.000e-03 Data: 0.000 (0.056) +2025-04-18 09:25:07,263 - train: [ INFO] - Train: 4 [ 450/461 ( 98%)] Loss: 6.830794 (6.9236) Loss_single: 4.912354 (4.9333) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (50.9375) Acc@5: 87.5000 (82.5000) Time: 0.090s, 355.22/s (0.156s, 205.66/s) LR: 5.000e-03 Data: 0.000 (0.053) +2025-04-18 09:25:08,319 - train: [ INFO] - Train: 4 [ 460/461 (100%)] Loss: 6.195561 (6.8574) Loss_single: 4.521687 (4.8959) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (51.7045) Acc@5: 93.7500 (83.5227) Time: 0.083s, 384.74/s (0.154s, 207.13/s) LR: 5.000e-03 Data: 0.000 (0.051) +2025-04-18 09:25:16,413 - train: [ INFO] - Eval : 4 Time: 7.841 (7.841) Loss: 2.0293 (2.0293) Acc@1: 40.6250 (40.6250)Acc@5: 78.1250 (78.1250) +2025-04-18 09:25:29,609 - train: [ INFO] - Eval : 4 Time: 0.764 (0.412) Loss: 2.0734 (2.0219) Acc@1: 50.0000 (44.0564)Acc@5: 78.1250 (77.6348) +2025-04-18 09:25:35,806 - train: [ INFO] - Eval : 4 Time: 0.016 (0.332) Loss: 4.9488 (1.9963) Acc@1: 0.0000 (43.6777)Acc@5: 50.0000 (77.9106) +2025-04-18 09:25:45,533 - train: [ INFO] - Train: 5 [ 0/461 ( 0%)] Loss: 7.095767 (7.0958) Loss_single: 4.995405 (4.9954) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (53.1250) Acc@5: 84.3750 (84.3750) Time: 6.951s, 4.60/s (6.951s, 4.60/s) LR: 5.000e-03 Data: 6.798 (6.798) +2025-04-18 09:25:55,109 - train: [ INFO] - Train: 5 [ 50/461 ( 11%)] Loss: 6.465457 (6.7806) Loss_single: 4.534131 (4.7648) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (57.8125) Acc@5: 87.5000 (85.9375) Time: 0.150s, 213.70/s (0.279s, 114.55/s) LR: 5.000e-03 Data: 0.000 (0.174) +2025-04-18 09:26:08,216 - train: [ INFO] - Train: 5 [ 100/461 ( 22%)] Loss: 6.231407 (6.5975) Loss_single: 4.468536 (4.6660) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (60.4167) Acc@5: 87.5000 (86.4583) Time: 0.142s, 224.88/s (0.262s, 121.98/s) LR: 5.000e-03 Data: 0.037 (0.162) +2025-04-18 09:26:14,038 - train: [ INFO] - Train: 5 [ 150/461 ( 33%)] Loss: 5.746527 (6.3848) Loss_single: 4.245544 (4.5609) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (61.7188) Acc@5: 100.0000 (89.8438) Time: 0.099s, 323.60/s (0.213s, 149.94/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 09:26:19,121 - train: [ INFO] - Train: 5 [ 200/461 ( 43%)] Loss: 6.709052 (6.4496) Loss_single: 4.873842 (4.6235) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (61.8750) Acc@5: 87.5000 (89.3750) Time: 0.076s, 418.30/s (0.185s, 172.53/s) LR: 5.000e-03 Data: 0.000 (0.082) +2025-04-18 09:26:24,358 - train: [ INFO] - Train: 5 [ 250/461 ( 54%)] Loss: 6.243452 (6.4153) Loss_single: 4.463791 (4.5969) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (62.5000) Acc@5: 90.6250 (89.5833) Time: 0.119s, 269.99/s (0.169s, 189.20/s) LR: 5.000e-03 Data: 0.001 (0.066) +2025-04-18 09:26:29,762 - train: [ INFO] - Train: 5 [ 300/461 ( 65%)] Loss: 6.867510 (6.4799) Loss_single: 4.861665 (4.6347) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (60.7143) Acc@5: 84.3750 (88.8393) Time: 0.080s, 402.26/s (0.159s, 201.44/s) LR: 5.000e-03 Data: 0.000 (0.055) +2025-04-18 09:26:36,040 - train: [ INFO] - Train: 5 [ 350/461 ( 76%)] Loss: 6.646693 (6.5007) Loss_single: 4.804171 (4.6559) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (60.1562) Acc@5: 84.3750 (88.2812) Time: 0.357s, 89.62/s (0.154s, 207.80/s) LR: 5.000e-03 Data: 0.268 (0.051) +2025-04-18 09:26:48,120 - train: [ INFO] - Train: 5 [ 400/461 ( 87%)] Loss: 7.213130 (6.5799) Loss_single: 5.136012 (4.7092) Loss_inverse: 0.000000 (0.0000) Acc@1: 40.6250 (57.9861) Acc@5: 81.2500 (87.5000) Time: 0.094s, 338.85/s (0.164s, 195.14/s) LR: 5.000e-03 Data: 0.000 (0.062) +2025-04-18 09:27:03,454 - train: [ INFO] - Train: 5 [ 450/461 ( 98%)] Loss: 6.981052 (6.6200) Loss_single: 4.985663 (4.7369) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (57.8125) Acc@5: 81.2500 (86.8750) Time: 0.081s, 394.60/s (0.177s, 180.83/s) LR: 5.000e-03 Data: 0.000 (0.077) +2025-04-18 09:27:06,245 - train: [ INFO] - Train: 5 [ 460/461 (100%)] Loss: 6.902294 (6.6457) Loss_single: 4.877906 (4.7497) Loss_inverse: 0.000000 (0.0000) Acc@1: 43.7500 (56.5341) Acc@5: 87.5000 (86.9318) Time: 0.080s, 397.87/s (0.178s, 179.28/s) LR: 5.000e-03 Data: 0.000 (0.078) +2025-04-18 09:27:15,327 - train: [ INFO] - Eval : 5 Time: 8.853 (8.853) Loss: 1.7317 (1.7317) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 09:27:31,846 - train: [ INFO] - Eval : 5 Time: 0.034 (0.497) Loss: 1.8167 (1.7854) Acc@1: 53.1250 (48.3456)Acc@5: 71.8750 (81.3113) +2025-04-18 09:27:40,423 - train: [ INFO] - Eval : 5 Time: 0.017 (0.414) Loss: 4.8233 (1.8240) Acc@1: 0.0000 (47.8797)Acc@5: 50.0000 (80.4163) +2025-04-18 09:27:44,353 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-5.pth.tar', 47.879722436391674) + +2025-04-18 09:27:52,045 - train: [ INFO] - Train: 6 [ 0/461 ( 0%)] Loss: 6.900502 (6.9005) Loss_single: 4.906857 (4.9069) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (56.2500) Acc@5: 84.3750 (84.3750) Time: 7.460s, 4.29/s (7.460s, 4.29/s) LR: 5.000e-03 Data: 7.313 (7.313) +2025-04-18 09:28:05,897 - train: [ INFO] - Train: 6 [ 50/461 ( 11%)] Loss: 8.024511 (7.4625) Loss_single: 5.617021 (5.2619) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (51.5625) Acc@5: 75.0000 (79.6875) Time: 0.086s, 372.77/s (0.366s, 87.47/s) LR: 5.000e-03 Data: 0.001 (0.277) +2025-04-18 09:28:19,788 - train: [ INFO] - Train: 6 [ 100/461 ( 22%)] Loss: 5.671633 (6.8655) Loss_single: 4.155028 (4.8930) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (58.3333) Acc@5: 90.6250 (83.3333) Time: 0.084s, 380.90/s (0.289s, 110.87/s) LR: 5.000e-03 Data: 0.001 (0.202) +2025-04-18 09:28:36,945 - train: [ INFO] - Train: 6 [ 150/461 ( 33%)] Loss: 6.444918 (6.7604) Loss_single: 4.732046 (4.8527) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (58.5938) Acc@5: 90.6250 (85.1562) Time: 0.083s, 383.25/s (0.278s, 115.14/s) LR: 5.000e-03 Data: 0.001 (0.191) +2025-04-18 09:28:54,128 - train: [ INFO] - Train: 6 [ 200/461 ( 43%)] Loss: 6.851816 (6.7787) Loss_single: 4.874578 (4.8571) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (58.1250) Acc@5: 87.5000 (85.6250) Time: 0.080s, 398.05/s (0.269s, 118.91/s) LR: 5.000e-03 Data: 0.000 (0.182) +2025-04-18 09:29:01,670 - train: [ INFO] - Train: 6 [ 250/461 ( 54%)] Loss: 5.794422 (6.6146) Loss_single: 4.237882 (4.7539) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (59.8958) Acc@5: 93.7500 (86.9792) Time: 0.081s, 397.20/s (0.244s, 130.91/s) LR: 5.000e-03 Data: 0.001 (0.159) +2025-04-18 09:29:13,463 - train: [ INFO] - Train: 6 [ 300/461 ( 65%)] Loss: 7.007553 (6.6708) Loss_single: 4.834503 (4.7654) Loss_inverse: 0.000000 (0.0000) Acc@1: 50.0000 (58.4821) Acc@5: 75.0000 (85.2679) Time: 0.100s, 321.22/s (0.236s, 135.86/s) LR: 5.000e-03 Data: 0.000 (0.150) +2025-04-18 09:29:30,469 - train: [ INFO] - Train: 6 [ 350/461 ( 76%)] Loss: 6.016671 (6.5890) Loss_single: 4.272753 (4.7038) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (59.3750) Acc@5: 84.3750 (85.1562) Time: 0.080s, 398.37/s (0.240s, 133.59/s) LR: 5.000e-03 Data: 0.001 (0.153) +2025-04-18 09:29:50,878 - train: [ INFO] - Train: 6 [ 400/461 ( 87%)] Loss: 5.798215 (6.5011) Loss_single: 4.292053 (4.6581) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (61.1111) Acc@5: 93.7500 (86.1111) Time: 3.842s, 8.33/s (0.248s, 129.24/s) LR: 5.000e-03 Data: 3.734 (0.161) +2025-04-18 09:30:05,314 - train: [ INFO] - Train: 6 [ 450/461 ( 98%)] Loss: 6.887175 (6.5397) Loss_single: 4.925197 (4.6848) Loss_inverse: 0.000000 (0.0000) Acc@1: 53.1250 (60.3125) Acc@5: 84.3750 (85.9375) Time: 0.079s, 403.18/s (0.245s, 130.75/s) LR: 5.000e-03 Data: 0.000 (0.158) +2025-04-18 09:30:06,129 - train: [ INFO] - Train: 6 [ 460/461 (100%)] Loss: 5.692831 (6.4627) Loss_single: 4.182261 (4.6391) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (61.9318) Acc@5: 93.7500 (86.6477) Time: 0.081s, 395.49/s (0.241s, 132.70/s) LR: 5.000e-03 Data: 0.000 (0.155) +2025-04-18 09:30:10,595 - train: [ INFO] - Eval : 6 Time: 4.245 (4.245) Loss: 2.0691 (2.0691) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-18 09:30:15,843 - train: [ INFO] - Eval : 6 Time: 0.107 (0.186) Loss: 2.2052 (1.9967) Acc@1: 50.0000 (46.7525)Acc@5: 71.8750 (77.4510) +2025-04-18 09:30:18,178 - train: [ INFO] - Eval : 6 Time: 0.016 (0.144) Loss: 3.7620 (1.9780) Acc@1: 0.0000 (46.4919)Acc@5: 50.0000 (77.5251) +2025-04-18 09:30:28,351 - train: [ INFO] - Train: 7 [ 0/461 ( 0%)] Loss: 5.813516 (5.8135) Loss_single: 4.243446 (4.2434) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (62.5000) Acc@5: 93.7500 (93.7500) Time: 7.324s, 4.37/s (7.324s, 4.37/s) LR: 5.000e-03 Data: 7.194 (7.194) +2025-04-18 09:30:45,279 - train: [ INFO] - Train: 7 [ 50/461 ( 11%)] Loss: 5.889990 (5.8518) Loss_single: 4.267707 (4.2556) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (67.1875) Acc@5: 87.5000 (90.6250) Time: 0.165s, 193.96/s (0.395s, 81.11/s) LR: 5.000e-03 Data: 0.000 (0.300) +2025-04-18 09:30:57,377 - train: [ INFO] - Train: 7 [ 100/461 ( 22%)] Loss: 6.155669 (5.9531) Loss_single: 4.501505 (4.3376) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (69.7917) Acc@5: 93.7500 (91.6667) Time: 0.163s, 196.04/s (0.293s, 109.11/s) LR: 5.000e-03 Data: 0.034 (0.200) +2025-04-18 09:31:14,292 - train: [ INFO] - Train: 7 [ 150/461 ( 33%)] Loss: 6.490442 (6.0874) Loss_single: 4.604568 (4.4043) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (66.4062) Acc@5: 84.3750 (89.8438) Time: 0.084s, 381.57/s (0.290s, 110.52/s) LR: 5.000e-03 Data: 0.000 (0.195) +2025-04-18 09:31:30,646 - train: [ INFO] - Train: 7 [ 200/461 ( 43%)] Loss: 6.197998 (6.1095) Loss_single: 4.507295 (4.4249) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (65.0000) Acc@5: 87.5000 (89.3750) Time: 0.093s, 344.88/s (0.288s, 111.27/s) LR: 5.000e-03 Data: 0.001 (0.192) +2025-04-18 09:31:43,222 - train: [ INFO] - Train: 7 [ 250/461 ( 54%)] Loss: 5.470828 (6.0031) Loss_single: 3.957538 (4.3470) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (66.1458) Acc@5: 93.7500 (90.1042) Time: 0.078s, 407.92/s (0.273s, 117.17/s) LR: 5.000e-03 Data: 0.000 (0.178) +2025-04-18 09:31:53,198 - train: [ INFO] - Train: 7 [ 300/461 ( 65%)] Loss: 6.296985 (6.0451) Loss_single: 4.582132 (4.3806) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (65.6250) Acc@5: 96.8750 (91.0714) Time: 0.136s, 234.98/s (0.260s, 123.04/s) LR: 5.000e-03 Data: 0.001 (0.164) +2025-04-18 09:32:00,620 - train: [ INFO] - Train: 7 [ 350/461 ( 76%)] Loss: 6.114400 (6.0537) Loss_single: 4.487041 (4.3939) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (66.0156) Acc@5: 93.7500 (91.4062) Time: 0.090s, 357.34/s (0.241s, 133.01/s) LR: 5.000e-03 Data: 0.001 (0.141) +2025-04-18 09:32:07,184 - train: [ INFO] - Train: 7 [ 400/461 ( 87%)] Loss: 5.402871 (5.9814) Loss_single: 4.034716 (4.3540) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (66.6667) Acc@5: 96.8750 (92.0139) Time: 0.082s, 390.32/s (0.224s, 142.69/s) LR: 5.000e-03 Data: 0.001 (0.123) +2025-04-18 09:32:21,092 - train: [ INFO] - Train: 7 [ 450/461 ( 98%)] Loss: 5.775197 (5.9608) Loss_single: 4.266332 (4.3452) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (67.8125) Acc@5: 90.6250 (91.8750) Time: 0.429s, 74.62/s (0.225s, 142.41/s) LR: 5.000e-03 Data: 0.331 (0.125) +2025-04-18 09:32:22,877 - train: [ INFO] - Train: 7 [ 460/461 (100%)] Loss: 5.837229 (5.9496) Loss_single: 4.272438 (4.3386) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (67.6136) Acc@5: 90.6250 (91.7614) Time: 0.080s, 401.21/s (0.223s, 143.39/s) LR: 5.000e-03 Data: 0.000 (0.123) +2025-04-18 09:32:28,360 - train: [ INFO] - Eval : 7 Time: 5.177 (5.177) Loss: 1.8939 (1.8939) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-18 09:32:38,733 - train: [ INFO] - Eval : 7 Time: 0.027 (0.305) Loss: 2.0029 (1.7845) Acc@1: 56.2500 (49.8162)Acc@5: 78.1250 (81.3113) +2025-04-18 09:32:48,127 - train: [ INFO] - Eval : 7 Time: 0.014 (0.304) Loss: 5.3132 (1.8037) Acc@1: 0.0000 (48.8820)Acc@5: 0.0000 (80.8790) +2025-04-18 09:32:52,882 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-7.pth.tar', 48.88203546646106) + +2025-04-18 09:32:58,637 - train: [ INFO] - Train: 8 [ 0/461 ( 0%)] Loss: 5.436306 (5.4363) Loss_single: 4.001596 (4.0016) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (75.0000) Acc@5: 96.8750 (96.8750) Time: 5.722s, 5.59/s (5.722s, 5.59/s) LR: 5.000e-03 Data: 5.549 (5.549) +2025-04-18 09:33:06,079 - train: [ INFO] - Train: 8 [ 50/461 ( 11%)] Loss: 6.134310 (5.7853) Loss_single: 4.369385 (4.1855) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (76.5625) Acc@5: 81.2500 (89.0625) Time: 0.164s, 195.49/s (0.238s, 134.35/s) LR: 5.000e-03 Data: 0.000 (0.121) +2025-04-18 09:33:11,727 - train: [ INFO] - Train: 8 [ 100/461 ( 22%)] Loss: 5.541430 (5.7040) Loss_single: 4.176641 (4.1825) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (75.0000) Acc@5: 96.8750 (91.6667) Time: 0.112s, 284.85/s (0.169s, 188.83/s) LR: 5.000e-03 Data: 0.000 (0.061) +2025-04-18 09:33:18,697 - train: [ INFO] - Train: 8 [ 150/461 ( 33%)] Loss: 5.943470 (5.7639) Loss_single: 4.328197 (4.2190) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (72.6562) Acc@5: 90.6250 (91.4062) Time: 0.080s, 398.51/s (0.154s, 208.43/s) LR: 5.000e-03 Data: 0.001 (0.041) +2025-04-18 09:33:30,712 - train: [ INFO] - Train: 8 [ 200/461 ( 43%)] Loss: 6.201310 (5.8514) Loss_single: 4.492652 (4.2737) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (70.6250) Acc@5: 87.5000 (90.6250) Time: 0.086s, 371.54/s (0.154s, 207.55/s) LR: 5.000e-03 Data: 0.000 (0.046) +2025-04-18 09:33:46,831 - train: [ INFO] - Train: 8 [ 250/461 ( 54%)] Loss: 6.728534 (5.9976) Loss_single: 4.875470 (4.3740) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (68.7500) Acc@5: 90.6250 (90.6250) Time: 0.114s, 281.75/s (0.184s, 173.63/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 09:34:00,916 - train: [ INFO] - Train: 8 [ 300/461 ( 65%)] Loss: 6.001633 (5.9981) Loss_single: 4.500758 (4.3921) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (70.5357) Acc@5: 93.7500 (91.0714) Time: 1.017s, 31.47/s (0.199s, 160.46/s) LR: 5.000e-03 Data: 0.940 (0.096) +2025-04-18 09:34:13,572 - train: [ INFO] - Train: 8 [ 350/461 ( 76%)] Loss: 5.946046 (5.9916) Loss_single: 4.236115 (4.3726) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (69.1406) Acc@5: 87.5000 (90.6250) Time: 0.177s, 181.23/s (0.205s, 156.12/s) LR: 5.000e-03 Data: 0.095 (0.103) +2025-04-18 09:34:26,074 - train: [ INFO] - Train: 8 [ 400/461 ( 87%)] Loss: 7.386850 (6.1467) Loss_single: 5.161228 (4.4602) Loss_inverse: 0.000000 (0.0000) Acc@1: 56.2500 (67.7083) Acc@5: 81.2500 (89.5833) Time: 0.090s, 356.54/s (0.208s, 153.57/s) LR: 5.000e-03 Data: 0.001 (0.106) +2025-04-18 09:34:39,011 - train: [ INFO] - Train: 8 [ 450/461 ( 98%)] Loss: 6.788081 (6.2108) Loss_single: 4.737130 (4.4879) Loss_inverse: 0.000000 (0.0000) Acc@1: 46.8750 (65.6250) Acc@5: 87.5000 (89.3750) Time: 0.077s, 416.15/s (0.212s, 150.98/s) LR: 5.000e-03 Data: 0.000 (0.111) +2025-04-18 09:34:44,194 - train: [ INFO] - Train: 8 [ 460/461 (100%)] Loss: 6.251084 (6.2145) Loss_single: 4.510487 (4.4900) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (65.6250) Acc@5: 90.6250 (89.4886) Time: 0.082s, 389.55/s (0.218s, 146.97/s) LR: 5.000e-03 Data: 0.000 (0.117) +2025-04-18 09:34:52,214 - train: [ INFO] - Eval : 8 Time: 7.761 (7.761) Loss: 1.9937 (1.9937) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 09:35:01,026 - train: [ INFO] - Eval : 8 Time: 0.053 (0.325) Loss: 2.1569 (1.7707) Acc@1: 46.8750 (51.3480)Acc@5: 71.8750 (81.0049) +2025-04-18 09:35:02,654 - train: [ INFO] - Eval : 8 Time: 0.016 (0.222) Loss: 3.3632 (1.7482) Acc@1: 0.0000 (51.0794)Acc@5: 50.0000 (81.1488) +2025-04-18 09:35:06,252 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-8.pth.tar', 51.079414032382424) + +2025-04-18 09:35:13,988 - train: [ INFO] - Train: 9 [ 0/461 ( 0%)] Loss: 5.956565 (5.9566) Loss_single: 4.353933 (4.3539) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (71.8750) Acc@5: 90.6250 (90.6250) Time: 7.709s, 4.15/s (7.709s, 4.15/s) LR: 5.000e-03 Data: 7.558 (7.558) +2025-04-18 09:35:30,241 - train: [ INFO] - Train: 9 [ 50/461 ( 11%)] Loss: 5.847625 (5.9021) Loss_single: 4.283331 (4.3186) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (71.8750) Acc@5: 96.8750 (93.7500) Time: 0.136s, 235.34/s (0.441s, 72.49/s) LR: 5.000e-03 Data: 0.001 (0.347) +2025-04-18 09:35:40,450 - train: [ INFO] - Train: 9 [ 100/461 ( 22%)] Loss: 5.509825 (5.7713) Loss_single: 4.069036 (4.2354) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (70.8333) Acc@5: 93.7500 (93.7500) Time: 0.085s, 376.61/s (0.314s, 101.77/s) LR: 5.000e-03 Data: 0.001 (0.209) +2025-04-18 09:35:47,347 - train: [ INFO] - Train: 9 [ 150/461 ( 33%)] Loss: 5.408840 (5.6807) Loss_single: 3.952830 (4.1648) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (71.8750) Acc@5: 96.8750 (94.5312) Time: 0.077s, 416.63/s (0.248s, 129.18/s) LR: 5.000e-03 Data: 0.000 (0.140) +2025-04-18 09:36:01,226 - train: [ INFO] - Train: 9 [ 200/461 ( 43%)] Loss: 5.237538 (5.5921) Loss_single: 3.961833 (4.1242) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (75.0000) Acc@5: 96.8750 (95.0000) Time: 0.207s, 154.27/s (0.247s, 129.66/s) LR: 5.000e-03 Data: 0.119 (0.142) +2025-04-18 09:36:15,031 - train: [ INFO] - Train: 9 [ 250/461 ( 54%)] Loss: 5.329964 (5.5484) Loss_single: 3.994656 (4.1026) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (75.5208) Acc@5: 96.8750 (95.3125) Time: 0.108s, 295.28/s (0.250s, 127.94/s) LR: 5.000e-03 Data: 0.000 (0.148) +2025-04-18 09:36:26,050 - train: [ INFO] - Train: 9 [ 300/461 ( 65%)] Loss: 6.452797 (5.6776) Loss_single: 4.734587 (4.1929) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (73.2143) Acc@5: 96.8750 (95.5357) Time: 0.146s, 218.63/s (0.244s, 131.18/s) LR: 5.000e-03 Data: 0.001 (0.141) +2025-04-18 09:36:34,048 - train: [ INFO] - Train: 9 [ 350/461 ( 76%)] Loss: 4.992311 (5.5919) Loss_single: 3.723192 (4.1342) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (74.6094) Acc@5: 93.7500 (95.3125) Time: 0.094s, 340.91/s (0.226s, 141.66/s) LR: 5.000e-03 Data: 0.001 (0.121) +2025-04-18 09:36:47,200 - train: [ INFO] - Train: 9 [ 400/461 ( 87%)] Loss: 5.927938 (5.6293) Loss_single: 4.371450 (4.1605) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (74.6528) Acc@5: 96.8750 (95.4861) Time: 0.328s, 97.66/s (0.222s, 144.05/s) LR: 5.000e-03 Data: 0.191 (0.117) +2025-04-18 09:36:58,887 - train: [ INFO] - Train: 9 [ 450/461 ( 98%)] Loss: 5.971939 (5.6635) Loss_single: 4.300575 (4.1745) Loss_inverse: 0.000000 (0.0000) Acc@1: 65.6250 (73.7500) Acc@5: 87.5000 (94.6875) Time: 0.126s, 254.25/s (0.221s, 144.80/s) LR: 5.000e-03 Data: 0.000 (0.117) +2025-04-18 09:36:59,988 - train: [ INFO] - Train: 9 [ 460/461 (100%)] Loss: 6.214610 (5.7136) Loss_single: 4.493366 (4.2035) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (72.4432) Acc@5: 90.6250 (94.3182) Time: 0.079s, 403.68/s (0.218s, 146.71/s) LR: 5.000e-03 Data: 0.000 (0.115) +2025-04-18 09:37:04,628 - train: [ INFO] - Eval : 9 Time: 4.332 (4.332) Loss: 2.1735 (2.1735) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-18 09:37:08,649 - train: [ INFO] - Eval : 9 Time: 0.176 (0.164) Loss: 2.4126 (2.1207) Acc@1: 53.1250 (46.5686)Acc@5: 65.6250 (74.8775) +2025-04-18 09:37:11,832 - train: [ INFO] - Eval : 9 Time: 0.015 (0.141) Loss: 3.5081 (2.1416) Acc@1: 0.0000 (45.9907)Acc@5: 50.0000 (74.2868) +2025-04-18 09:37:22,793 - train: [ INFO] - Train: 10 [ 0/461 ( 0%)] Loss: 5.570330 (5.5703) Loss_single: 4.222802 (4.2228) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (78.1250) Acc@5: 96.8750 (96.8750) Time: 8.044s, 3.98/s (8.044s, 3.98/s) LR: 5.000e-03 Data: 7.919 (7.919) +2025-04-18 09:37:36,345 - train: [ INFO] - Train: 10 [ 50/461 ( 11%)] Loss: 5.840055 (5.7052) Loss_single: 4.359903 (4.2914) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (78.1250) Acc@5: 93.7500 (95.3125) Time: 0.107s, 299.66/s (0.390s, 82.05/s) LR: 5.000e-03 Data: 0.001 (0.293) +2025-04-18 09:37:52,202 - train: [ INFO] - Train: 10 [ 100/461 ( 22%)] Loss: 5.196199 (5.5355) Loss_single: 3.857318 (4.1467) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (77.0833) Acc@5: 96.8750 (95.8333) Time: 0.082s, 391.56/s (0.339s, 94.45/s) LR: 5.000e-03 Data: 0.000 (0.247) +2025-04-18 09:38:06,123 - train: [ INFO] - Train: 10 [ 150/461 ( 33%)] Loss: 5.510208 (5.5292) Loss_single: 4.109567 (4.1374) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (77.3438) Acc@5: 96.8750 (96.0938) Time: 0.080s, 399.32/s (0.298s, 107.41/s) LR: 5.000e-03 Data: 0.000 (0.205) +2025-04-18 09:38:19,542 - train: [ INFO] - Train: 10 [ 200/461 ( 43%)] Loss: 5.749707 (5.5733) Loss_single: 4.349674 (4.1799) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (76.8750) Acc@5: 90.6250 (95.0000) Time: 0.086s, 373.58/s (0.284s, 112.52/s) LR: 5.000e-03 Data: 0.000 (0.190) +2025-04-18 09:38:25,522 - train: [ INFO] - Train: 10 [ 250/461 ( 54%)] Loss: 4.960348 (5.4711) Loss_single: 3.683738 (4.0972) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (77.6042) Acc@5: 100.0000 (95.8333) Time: 0.083s, 384.76/s (0.251s, 127.30/s) LR: 5.000e-03 Data: 0.000 (0.152) +2025-04-18 09:38:34,354 - train: [ INFO] - Train: 10 [ 300/461 ( 65%)] Loss: 5.930599 (5.5368) Loss_single: 4.359101 (4.1346) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (76.3393) Acc@5: 96.8750 (95.9821) Time: 0.084s, 379.62/s (0.225s, 142.07/s) LR: 5.000e-03 Data: 0.000 (0.127) +2025-04-18 09:38:47,518 - train: [ INFO] - Train: 10 [ 350/461 ( 76%)] Loss: 6.446428 (5.6505) Loss_single: 4.719720 (4.2077) Loss_inverse: 0.000000 (0.0000) Acc@1: 62.5000 (74.6094) Acc@5: 93.7500 (95.7031) Time: 0.083s, 387.56/s (0.228s, 140.12/s) LR: 5.000e-03 Data: 0.000 (0.130) +2025-04-18 09:38:59,568 - train: [ INFO] - Train: 10 [ 400/461 ( 87%)] Loss: 5.495386 (5.6333) Loss_single: 4.114191 (4.1973) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (73.9583) Acc@5: 90.6250 (95.1389) Time: 0.132s, 242.42/s (0.229s, 139.76/s) LR: 5.000e-03 Data: 0.001 (0.129) +2025-04-18 09:39:04,918 - train: [ INFO] - Train: 10 [ 450/461 ( 98%)] Loss: 6.320864 (5.7020) Loss_single: 4.647235 (4.2423) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (73.7500) Acc@5: 84.3750 (94.0625) Time: 0.075s, 424.28/s (0.215s, 148.59/s) LR: 5.000e-03 Data: 0.000 (0.115) +2025-04-18 09:39:05,730 - train: [ INFO] - Train: 10 [ 460/461 (100%)] Loss: 5.687356 (5.7007) Loss_single: 4.239741 (4.2421) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (74.1477) Acc@5: 96.8750 (94.3182) Time: 0.075s, 426.96/s (0.212s, 150.63/s) LR: 5.000e-03 Data: 0.000 (0.112) +2025-04-18 09:39:13,584 - train: [ INFO] - Eval : 10 Time: 7.522 (7.522) Loss: 1.8678 (1.8678) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 09:39:23,824 - train: [ INFO] - Eval : 10 Time: 0.059 (0.348) Loss: 2.1328 (1.8846) Acc@1: 53.1250 (48.4069)Acc@5: 62.5000 (80.2696) +2025-04-18 09:39:31,473 - train: [ INFO] - Eval : 10 Time: 0.014 (0.310) Loss: 4.3825 (1.8843) Acc@1: 0.0000 (48.7664)Acc@5: 0.0000 (80.1079) +2025-04-18 09:39:44,602 - train: [ INFO] - Train: 11 [ 0/461 ( 0%)] Loss: 5.025867 (5.0259) Loss_single: 3.684556 (3.6846) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (78.1250) Acc@5: 100.0000 (100.0000) Time: 8.654s, 3.70/s (8.654s, 3.70/s) LR: 5.000e-03 Data: 8.519 (8.519) +2025-04-18 09:39:54,107 - train: [ INFO] - Train: 11 [ 50/461 ( 11%)] Loss: 5.592324 (5.3091) Loss_single: 4.194963 (3.9398) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (73.4375) Acc@5: 96.8750 (98.4375) Time: 0.150s, 214.03/s (0.332s, 96.32/s) LR: 5.000e-03 Data: 0.001 (0.223) +2025-04-18 09:40:05,335 - train: [ INFO] - Train: 11 [ 100/461 ( 22%)] Loss: 5.005015 (5.2077) Loss_single: 3.749601 (3.8764) Loss_inverse: 0.000000 (0.0000) Acc@1: 78.1250 (75.0000) Acc@5: 100.0000 (98.9583) Time: 0.160s, 199.91/s (0.235s, 136.29/s) LR: 5.000e-03 Data: 0.001 (0.134) +2025-04-18 09:40:11,338 - train: [ INFO] - Train: 11 [ 150/461 ( 33%)] Loss: 5.489965 (5.2783) Loss_single: 4.114563 (3.9359) Loss_inverse: 0.000000 (0.0000) Acc@1: 68.7500 (73.4375) Acc@5: 96.8750 (98.4375) Time: 0.112s, 286.16/s (0.197s, 162.80/s) LR: 5.000e-03 Data: 0.000 (0.090) +2025-04-18 09:40:16,925 - train: [ INFO] - Train: 11 [ 200/461 ( 43%)] Loss: 5.649273 (5.3525) Loss_single: 4.197281 (3.9882) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (73.1250) Acc@5: 90.6250 (96.8750) Time: 0.114s, 280.52/s (0.175s, 182.56/s) LR: 5.000e-03 Data: 0.001 (0.068) +2025-04-18 09:40:22,668 - train: [ INFO] - Train: 11 [ 250/461 ( 54%)] Loss: 4.794432 (5.2595) Loss_single: 3.555445 (3.9161) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (74.4792) Acc@5: 100.0000 (97.3958) Time: 0.106s, 302.86/s (0.163s, 196.32/s) LR: 5.000e-03 Data: 0.000 (0.054) +2025-04-18 09:40:30,402 - train: [ INFO] - Train: 11 [ 300/461 ( 65%)] Loss: 5.073546 (5.2329) Loss_single: 3.791437 (3.8983) Loss_inverse: 0.000000 (0.0000) Acc@1: 81.2500 (75.4464) Acc@5: 93.7500 (96.8750) Time: 0.278s, 115.05/s (0.154s, 207.73/s) LR: 5.000e-03 Data: 0.000 (0.046) +2025-04-18 09:40:45,199 - train: [ INFO] - Train: 11 [ 350/461 ( 76%)] Loss: 5.678465 (5.2886) Loss_single: 4.208208 (3.9370) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (75.0000) Acc@5: 96.8750 (96.8750) Time: 0.099s, 324.21/s (0.167s, 192.11/s) LR: 5.000e-03 Data: 0.000 (0.060) +2025-04-18 09:41:00,164 - train: [ INFO] - Train: 11 [ 400/461 ( 87%)] Loss: 5.440841 (5.3055) Loss_single: 4.084882 (3.9534) Loss_inverse: 0.000000 (0.0000) Acc@1: 71.8750 (74.6528) Acc@5: 100.0000 (97.2222) Time: 0.100s, 318.55/s (0.181s, 176.83/s) LR: 5.000e-03 Data: 0.000 (0.076) +2025-04-18 09:41:10,032 - train: [ INFO] - Train: 11 [ 450/461 ( 98%)] Loss: 4.751537 (5.2501) Loss_single: 3.585528 (3.9166) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (75.9375) Acc@5: 100.0000 (97.5000) Time: 0.102s, 314.89/s (0.182s, 175.68/s) LR: 5.000e-03 Data: 0.000 (0.077) +2025-04-18 09:41:12,020 - train: [ INFO] - Train: 11 [ 460/461 (100%)] Loss: 6.299869 (5.3456) Loss_single: 4.548589 (3.9741) Loss_inverse: 0.000000 (0.0000) Acc@1: 59.3750 (74.4318) Acc@5: 90.6250 (96.8750) Time: 0.113s, 283.43/s (0.182s, 176.14/s) LR: 5.000e-03 Data: 0.001 (0.077) +2025-04-18 09:41:17,715 - train: [ INFO] - Eval : 11 Time: 5.366 (5.366) Loss: 2.4717 (2.4717) Acc@1: 37.5000 (37.5000)Acc@5: 62.5000 (62.5000) +2025-04-18 09:41:21,439 - train: [ INFO] - Eval : 11 Time: 0.067 (0.178) Loss: 2.1417 (1.8535) Acc@1: 53.1250 (51.4093)Acc@5: 71.8750 (79.5343) +2025-04-18 09:41:25,924 - train: [ INFO] - Eval : 11 Time: 0.014 (0.166) Loss: 3.3165 (1.8489) Acc@1: 0.0000 (50.8096)Acc@5: 50.0000 (79.4911) +2025-04-18 09:41:38,535 - train: [ INFO] - Train: 12 [ 0/461 ( 0%)] Loss: 4.439084 (4.4391) Loss_single: 3.385864 (3.3859) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (87.5000) Acc@5: 100.0000 (100.0000) Time: 7.254s, 4.41/s (7.254s, 4.41/s) LR: 5.000e-03 Data: 7.121 (7.121) +2025-04-18 09:41:46,929 - train: [ INFO] - Train: 12 [ 50/461 ( 11%)] Loss: 4.123111 (4.2811) Loss_single: 3.177869 (3.2819) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (90.6250) Acc@5: 100.0000 (100.0000) Time: 0.111s, 288.99/s (0.296s, 108.02/s) LR: 5.000e-03 Data: 0.000 (0.195) +2025-04-18 09:42:02,089 - train: [ INFO] - Train: 12 [ 100/461 ( 22%)] Loss: 4.857931 (4.4734) Loss_single: 3.736727 (3.4335) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (90.6250) Acc@5: 96.8750 (98.9583) Time: 0.084s, 381.97/s (0.287s, 111.42/s) LR: 5.000e-03 Data: 0.000 (0.187) +2025-04-18 09:42:15,260 - train: [ INFO] - Train: 12 [ 150/461 ( 33%)] Loss: 4.477859 (4.4745) Loss_single: 3.461451 (3.4405) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (90.6250) Acc@5: 100.0000 (99.2188) Time: 0.085s, 377.73/s (0.259s, 123.66/s) LR: 5.000e-03 Data: 0.000 (0.161) +2025-04-18 09:42:21,258 - train: [ INFO] - Train: 12 [ 200/461 ( 43%)] Loss: 4.083486 (4.3963) Loss_single: 3.159483 (3.3843) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (91.8750) Acc@5: 100.0000 (99.3750) Time: 0.075s, 424.25/s (0.224s, 142.82/s) LR: 5.000e-03 Data: 0.000 (0.124) +2025-04-18 09:42:27,234 - train: [ INFO] - Train: 12 [ 250/461 ( 54%)] Loss: 4.596776 (4.4297) Loss_single: 3.427427 (3.3915) Loss_inverse: 0.000000 (0.0000) Acc@1: 84.3750 (90.6250) Acc@5: 93.7500 (98.4375) Time: 0.102s, 314.12/s (0.200s, 159.66/s) LR: 5.000e-03 Data: 0.000 (0.099) +2025-04-18 09:42:34,948 - train: [ INFO] - Train: 12 [ 300/461 ( 65%)] Loss: 4.412025 (4.4272) Loss_single: 3.342471 (3.3845) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.0714) Acc@5: 100.0000 (98.6607) Time: 0.097s, 331.16/s (0.184s, 174.32/s) LR: 5.000e-03 Data: 0.001 (0.083) +2025-04-18 09:42:52,708 - train: [ INFO] - Train: 12 [ 350/461 ( 76%)] Loss: 3.910460 (4.3626) Loss_single: 2.921353 (3.3266) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.4062) Acc@5: 100.0000 (98.8281) Time: 0.104s, 306.87/s (0.207s, 154.65/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-18 09:43:04,326 - train: [ INFO] - Train: 12 [ 400/461 ( 87%)] Loss: 4.994489 (4.4328) Loss_single: 3.887897 (3.3889) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (91.3194) Acc@5: 96.8750 (98.6111) Time: 0.078s, 411.02/s (0.205s, 156.18/s) LR: 5.000e-03 Data: 0.000 (0.106) +2025-04-18 09:43:14,563 - train: [ INFO] - Train: 12 [ 450/461 ( 98%)] Loss: 5.613014 (4.5508) Loss_single: 4.118885 (3.4619) Loss_inverse: 0.000000 (0.0000) Acc@1: 75.0000 (89.6875) Acc@5: 90.6250 (97.8125) Time: 0.084s, 379.48/s (0.202s, 158.75/s) LR: 5.000e-03 Data: 0.000 (0.103) +2025-04-18 09:43:18,110 - train: [ INFO] - Train: 12 [ 460/461 (100%)] Loss: 5.086546 (4.5995) Loss_single: 3.908812 (3.5026) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (89.7727) Acc@5: 100.0000 (98.0114) Time: 0.111s, 288.22/s (0.204s, 156.54/s) LR: 5.000e-03 Data: 0.000 (0.106) +2025-04-18 09:43:23,148 - train: [ INFO] - Eval : 12 Time: 4.721 (4.721) Loss: 2.5517 (2.5517) Acc@1: 40.6250 (40.6250)Acc@5: 68.7500 (68.7500) +2025-04-18 09:43:29,350 - train: [ INFO] - Eval : 12 Time: 0.498 (0.214) Loss: 2.6436 (2.2183) Acc@1: 43.7500 (45.0368)Acc@5: 68.7500 (74.3260) +2025-04-18 09:43:34,132 - train: [ INFO] - Eval : 12 Time: 0.018 (0.192) Loss: 3.2061 (2.2225) Acc@1: 50.0000 (44.7957)Acc@5: 50.0000 (74.2097) +2025-04-18 09:43:46,492 - train: [ INFO] - Train: 13 [ 0/461 ( 0%)] Loss: 4.842314 (4.8423) Loss_single: 3.694397 (3.6944) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (87.5000) Acc@5: 96.8750 (96.8750) Time: 8.020s, 3.99/s (8.020s, 3.99/s) LR: 5.000e-03 Data: 7.893 (7.893) +2025-04-18 09:44:01,234 - train: [ INFO] - Train: 13 [ 50/461 ( 11%)] Loss: 4.407600 (4.6250) Loss_single: 3.398998 (3.5467) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (92.1875) Acc@5: 96.8750 (96.8750) Time: 0.104s, 308.97/s (0.401s, 79.73/s) LR: 5.000e-03 Data: 0.000 (0.304) +2025-04-18 09:44:11,845 - train: [ INFO] - Train: 13 [ 100/461 ( 22%)] Loss: 4.554745 (4.6016) Loss_single: 3.588721 (3.5607) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (92.7083) Acc@5: 100.0000 (97.9167) Time: 0.084s, 381.55/s (0.286s, 111.88/s) LR: 5.000e-03 Data: 0.000 (0.192) +2025-04-18 09:44:17,834 - train: [ INFO] - Train: 13 [ 150/461 ( 33%)] Loss: 4.415332 (4.5550) Loss_single: 3.362127 (3.5111) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (91.4062) Acc@5: 96.8750 (97.6562) Time: 0.081s, 396.60/s (0.226s, 141.57/s) LR: 5.000e-03 Data: 0.000 (0.130) +2025-04-18 09:44:23,825 - train: [ INFO] - Train: 13 [ 200/461 ( 43%)] Loss: 4.323798 (4.5088) Loss_single: 3.229133 (3.4547) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (91.2500) Acc@5: 96.8750 (97.5000) Time: 0.086s, 371.16/s (0.199s, 160.57/s) LR: 5.000e-03 Data: 0.000 (0.098) +2025-04-18 09:44:29,190 - train: [ INFO] - Train: 13 [ 250/461 ( 54%)] Loss: 4.279045 (4.4705) Loss_single: 3.339252 (3.4354) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (92.1875) Acc@5: 100.0000 (97.9167) Time: 0.087s, 369.75/s (0.181s, 177.06/s) LR: 5.000e-03 Data: 0.000 (0.078) +2025-04-18 09:44:34,624 - train: [ INFO] - Train: 13 [ 300/461 ( 65%)] Loss: 4.183255 (4.4294) Loss_single: 3.182051 (3.3992) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (91.5179) Acc@5: 100.0000 (98.2143) Time: 0.143s, 224.12/s (0.169s, 189.74/s) LR: 5.000e-03 Data: 0.000 (0.065) +2025-04-18 09:44:44,586 - train: [ INFO] - Train: 13 [ 350/461 ( 76%)] Loss: 4.404757 (4.4264) Loss_single: 3.356382 (3.3939) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (91.7969) Acc@5: 100.0000 (98.4375) Time: 0.116s, 275.37/s (0.158s, 202.39/s) LR: 5.000e-03 Data: 0.031 (0.056) +2025-04-18 09:44:58,112 - train: [ INFO] - Train: 13 [ 400/461 ( 87%)] Loss: 3.785639 (4.3552) Loss_single: 2.818991 (3.3300) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (92.0139) Acc@5: 100.0000 (98.6111) Time: 0.080s, 399.45/s (0.172s, 186.56/s) LR: 5.000e-03 Data: 0.002 (0.071) +2025-04-18 09:45:09,615 - train: [ INFO] - Train: 13 [ 450/461 ( 98%)] Loss: 4.367107 (4.3564) Loss_single: 3.380062 (3.3350) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (92.5000) Acc@5: 100.0000 (98.7500) Time: 0.122s, 263.28/s (0.175s, 182.84/s) LR: 5.000e-03 Data: 0.042 (0.075) +2025-04-18 09:45:12,264 - train: [ INFO] - Train: 13 [ 460/461 (100%)] Loss: 4.751781 (4.3923) Loss_single: 3.601549 (3.3592) Loss_inverse: 0.000000 (0.0000) Acc@1: 87.5000 (92.0455) Acc@5: 96.8750 (98.5795) Time: 0.082s, 391.82/s (0.177s, 180.99/s) LR: 5.000e-03 Data: 0.000 (0.077) +2025-04-18 09:45:21,005 - train: [ INFO] - Eval : 13 Time: 8.479 (8.479) Loss: 1.8548 (1.8548) Acc@1: 59.3750 (59.3750)Acc@5: 71.8750 (71.8750) +2025-04-18 09:45:32,539 - train: [ INFO] - Eval : 13 Time: 0.027 (0.392) Loss: 1.9448 (1.8373) Acc@1: 53.1250 (51.5931)Acc@5: 71.8750 (78.4314) +2025-04-18 09:45:41,144 - train: [ INFO] - Eval : 13 Time: 0.016 (0.349) Loss: 3.6798 (1.8433) Acc@1: 0.0000 (51.8504)Acc@5: 50.0000 (77.8720) +2025-04-18 09:45:45,608 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-13.pth.tar', 51.85042405551272) + +2025-04-18 09:45:53,758 - train: [ INFO] - Train: 14 [ 0/461 ( 0%)] Loss: 4.281870 (4.2819) Loss_single: 3.313104 (3.3131) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (93.7500) Acc@5: 100.0000 (100.0000) Time: 7.953s, 4.02/s (7.953s, 4.02/s) LR: 5.000e-03 Data: 7.797 (7.797) +2025-04-18 09:46:01,480 - train: [ INFO] - Train: 14 [ 50/461 ( 11%)] Loss: 3.788745 (4.0353) Loss_single: 2.938587 (3.1258) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (96.8750) Acc@5: 100.0000 (100.0000) Time: 0.138s, 231.82/s (0.306s, 104.58/s) LR: 5.000e-03 Data: 0.017 (0.208) +2025-04-18 09:46:12,289 - train: [ INFO] - Train: 14 [ 100/461 ( 22%)] Loss: 4.676615 (4.2491) Loss_single: 3.578448 (3.2767) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (95.8333) Acc@5: 93.7500 (97.9167) Time: 0.108s, 296.57/s (0.241s, 132.52/s) LR: 5.000e-03 Data: 0.001 (0.145) +2025-04-18 09:46:19,889 - train: [ INFO] - Train: 14 [ 150/461 ( 33%)] Loss: 4.229682 (4.2442) Loss_single: 3.191085 (3.2553) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (94.5312) Acc@5: 96.8750 (97.6562) Time: 0.148s, 216.30/s (0.207s, 154.47/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-18 09:46:25,580 - train: [ INFO] - Train: 14 [ 200/461 ( 43%)] Loss: 4.091220 (4.2136) Loss_single: 3.177892 (3.2398) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (95.6250) Acc@5: 100.0000 (98.1250) Time: 0.086s, 373.64/s (0.183s, 174.40/s) LR: 5.000e-03 Data: 0.001 (0.080) +2025-04-18 09:46:31,597 - train: [ INFO] - Train: 14 [ 250/461 ( 54%)] Loss: 4.249740 (4.2196) Loss_single: 3.283346 (3.2471) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (95.8333) Acc@5: 100.0000 (98.4375) Time: 0.081s, 393.65/s (0.167s, 191.83/s) LR: 5.000e-03 Data: 0.000 (0.064) +2025-04-18 09:46:42,049 - train: [ INFO] - Train: 14 [ 300/461 ( 65%)] Loss: 3.670344 (4.1412) Loss_single: 2.838476 (3.1887) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (95.9821) Acc@5: 100.0000 (98.6607) Time: 0.200s, 160.40/s (0.170s, 188.33/s) LR: 5.000e-03 Data: 0.000 (0.068) +2025-04-18 09:46:56,990 - train: [ INFO] - Train: 14 [ 350/461 ( 76%)] Loss: 4.039183 (4.1284) Loss_single: 3.161776 (3.1853) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (96.4844) Acc@5: 100.0000 (98.8281) Time: 0.083s, 383.43/s (0.184s, 173.56/s) LR: 5.000e-03 Data: 0.001 (0.084) +2025-04-18 09:47:12,167 - train: [ INFO] - Train: 14 [ 400/461 ( 87%)] Loss: 3.870861 (4.0998) Loss_single: 3.044807 (3.1697) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (96.8750) Acc@5: 100.0000 (98.9583) Time: 0.081s, 394.33/s (0.196s, 163.27/s) LR: 5.000e-03 Data: 0.000 (0.096) +2025-04-18 09:47:25,106 - train: [ INFO] - Train: 14 [ 450/461 ( 98%)] Loss: 3.608583 (4.0507) Loss_single: 2.775252 (3.1303) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (99.0625) Time: 0.081s, 394.77/s (0.199s, 160.97/s) LR: 5.000e-03 Data: 0.000 (0.099) +2025-04-18 09:47:28,633 - train: [ INFO] - Train: 14 [ 460/461 (100%)] Loss: 3.681998 (4.0172) Loss_single: 2.827293 (3.1027) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (97.1591) Acc@5: 100.0000 (99.1477) Time: 0.080s, 401.01/s (0.202s, 158.46/s) LR: 5.000e-03 Data: 0.000 (0.103) +2025-04-18 09:47:36,316 - train: [ INFO] - Eval : 14 Time: 7.460 (7.460) Loss: 2.1497 (2.1497) Acc@1: 53.1250 (53.1250)Acc@5: 71.8750 (71.8750) +2025-04-18 09:47:50,343 - train: [ INFO] - Eval : 14 Time: 0.046 (0.421) Loss: 1.9088 (1.9407) Acc@1: 53.1250 (50.0000)Acc@5: 71.8750 (75.8578) +2025-04-18 09:47:53,588 - train: [ INFO] - Eval : 14 Time: 0.015 (0.302) Loss: 3.9644 (1.9643) Acc@1: 0.0000 (49.5759)Acc@5: 50.0000 (75.0964) +2025-04-18 09:48:02,951 - train: [ INFO] - Train: 15 [ 0/461 ( 0%)] Loss: 3.511650 (3.5116) Loss_single: 2.696790 (2.6968) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.548s, 5.77/s (5.548s, 5.77/s) LR: 5.000e-03 Data: 5.421 (5.421) +2025-04-18 09:48:10,086 - train: [ INFO] - Train: 15 [ 50/461 ( 11%)] Loss: 3.480730 (3.4962) Loss_single: 2.710502 (2.7036) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.136s, 234.64/s (0.247s, 129.35/s) LR: 5.000e-03 Data: 0.000 (0.150) +2025-04-18 09:48:19,909 - train: [ INFO] - Train: 15 [ 100/461 ( 22%)] Loss: 3.979661 (3.6573) Loss_single: 3.087050 (2.8314) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.081s, 393.78/s (0.207s, 154.91/s) LR: 5.000e-03 Data: 0.001 (0.109) +2025-04-18 09:48:27,148 - train: [ INFO] - Train: 15 [ 150/461 ( 33%)] Loss: 3.778078 (3.6875) Loss_single: 2.888745 (2.8458) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (98.4375) Time: 0.083s, 387.82/s (0.186s, 172.15/s) LR: 5.000e-03 Data: 0.001 (0.090) +2025-04-18 09:48:32,961 - train: [ INFO] - Train: 15 [ 200/461 ( 43%)] Loss: 3.845302 (3.7191) Loss_single: 2.981608 (2.8729) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.1250) Acc@5: 96.8750 (98.1250) Time: 0.167s, 191.44/s (0.168s, 190.06/s) LR: 5.000e-03 Data: 0.001 (0.068) +2025-04-18 09:48:38,641 - train: [ INFO] - Train: 15 [ 250/461 ( 54%)] Loss: 3.780367 (3.7293) Loss_single: 2.953236 (2.8863) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.9167) Acc@5: 100.0000 (98.4375) Time: 0.078s, 407.69/s (0.157s, 203.60/s) LR: 5.000e-03 Data: 0.000 (0.055) +2025-04-18 09:48:44,220 - train: [ INFO] - Train: 15 [ 300/461 ( 65%)] Loss: 3.998856 (3.7678) Loss_single: 3.144939 (2.9233) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.2143) Acc@5: 100.0000 (98.6607) Time: 0.105s, 305.17/s (0.149s, 214.08/s) LR: 5.000e-03 Data: 0.001 (0.046) +2025-04-18 09:48:50,883 - train: [ INFO] - Train: 15 [ 350/461 ( 76%)] Loss: 4.030441 (3.8006) Loss_single: 3.192733 (2.9570) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.8281) Time: 0.103s, 309.89/s (0.144s, 222.82/s) LR: 5.000e-03 Data: 0.000 (0.039) +2025-04-18 09:48:56,019 - train: [ INFO] - Train: 15 [ 400/461 ( 87%)] Loss: 4.258664 (3.8515) Loss_single: 3.373101 (3.0032) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.2639) Acc@5: 96.8750 (98.6111) Time: 0.080s, 401.48/s (0.138s, 231.15/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-18 09:49:01,267 - train: [ INFO] - Train: 15 [ 450/461 ( 98%)] Loss: 3.760864 (3.8425) Loss_single: 2.942972 (2.9972) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.7500) Time: 0.084s, 382.07/s (0.135s, 237.65/s) LR: 5.000e-03 Data: 0.000 (0.031) +2025-04-18 09:49:02,094 - train: [ INFO] - Train: 15 [ 460/461 (100%)] Loss: 3.828905 (3.8412) Loss_single: 2.935562 (2.9916) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.2955) Acc@5: 100.0000 (98.8636) Time: 0.077s, 417.04/s (0.134s, 239.69/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-18 09:49:07,156 - train: [ INFO] - Eval : 15 Time: 4.819 (4.819) Loss: 2.4335 (2.4335) Acc@1: 34.3750 (34.3750)Acc@5: 62.5000 (62.5000) +2025-04-18 09:49:10,804 - train: [ INFO] - Eval : 15 Time: 0.048 (0.167) Loss: 1.8701 (1.8981) Acc@1: 46.8750 (49.3873)Acc@5: 71.8750 (76.8995) +2025-04-18 09:49:13,219 - train: [ INFO] - Eval : 15 Time: 0.016 (0.133) Loss: 3.2059 (1.9269) Acc@1: 0.0000 (48.8435)Acc@5: 50.0000 (76.0216) +2025-04-18 09:49:24,967 - train: [ INFO] - Train: 16 [ 0/461 ( 0%)] Loss: 3.546958 (3.5470) Loss_single: 2.776558 (2.7766) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.634s, 4.19/s (7.634s, 4.19/s) LR: 5.000e-03 Data: 7.471 (7.471) +2025-04-18 09:49:36,376 - train: [ INFO] - Train: 16 [ 50/461 ( 11%)] Loss: 3.430984 (3.4890) Loss_single: 2.601207 (2.6889) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 382.70/s (0.360s, 88.87/s) LR: 5.000e-03 Data: 0.000 (0.253) +2025-04-18 09:49:53,207 - train: [ INFO] - Train: 16 [ 100/461 ( 22%)] Loss: 4.298402 (3.7588) Loss_single: 3.514239 (2.9640) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.160s, 199.45/s (0.302s, 105.82/s) LR: 5.000e-03 Data: 0.000 (0.202) +2025-04-18 09:50:09,319 - train: [ INFO] - Train: 16 [ 150/461 ( 33%)] Loss: 3.868292 (3.7862) Loss_single: 3.051799 (2.9860) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.083s, 384.25/s (0.286s, 111.78/s) LR: 5.000e-03 Data: 0.000 (0.189) +2025-04-18 09:50:19,712 - train: [ INFO] - Train: 16 [ 200/461 ( 43%)] Loss: 3.620821 (3.7531) Loss_single: 2.846242 (2.9580) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.079s, 404.68/s (0.259s, 123.48/s) LR: 5.000e-03 Data: 0.000 (0.163) +2025-04-18 09:50:37,131 - train: [ INFO] - Train: 16 [ 250/461 ( 54%)] Loss: 3.887760 (3.7755) Loss_single: 3.068873 (2.9765) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.081s, 395.58/s (0.261s, 122.79/s) LR: 5.000e-03 Data: 0.000 (0.166) +2025-04-18 09:50:55,165 - train: [ INFO] - Train: 16 [ 300/461 ( 65%)] Loss: 3.637418 (3.7558) Loss_single: 2.833313 (2.9560) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.083s, 385.38/s (0.264s, 121.26/s) LR: 5.000e-03 Data: 0.000 (0.171) +2025-04-18 09:51:05,746 - train: [ INFO] - Train: 16 [ 350/461 ( 76%)] Loss: 3.644844 (3.7419) Loss_single: 2.876593 (2.9461) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.081s, 395.39/s (0.248s, 129.13/s) LR: 5.000e-03 Data: 0.000 (0.155) +2025-04-18 09:51:19,600 - train: [ INFO] - Train: 16 [ 400/461 ( 87%)] Loss: 3.812999 (3.7498) Loss_single: 3.022382 (2.9546) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.691s, 46.33/s (0.246s, 129.92/s) LR: 5.000e-03 Data: 0.595 (0.154) +2025-04-18 09:51:36,541 - train: [ INFO] - Train: 16 [ 450/461 ( 98%)] Loss: 3.205189 (3.6954) Loss_single: 2.436531 (2.9028) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.106s, 300.93/s (0.250s, 127.97/s) LR: 5.000e-03 Data: 0.001 (0.158) +2025-04-18 09:51:37,925 - train: [ INFO] - Train: 16 [ 460/461 (100%)] Loss: 3.615397 (3.6881) Loss_single: 2.766101 (2.8903) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1477) Acc@5: 96.8750 (99.7159) Time: 0.080s, 402.43/s (0.246s, 129.89/s) LR: 5.000e-03 Data: 0.000 (0.154) +2025-04-18 09:51:45,850 - train: [ INFO] - Eval : 16 Time: 7.688 (7.688) Loss: 2.1197 (2.1197) Acc@1: 53.1250 (53.1250)Acc@5: 71.8750 (71.8750) +2025-04-18 09:51:56,447 - train: [ INFO] - Eval : 16 Time: 0.040 (0.359) Loss: 1.7001 (1.8091) Acc@1: 62.5000 (52.4510)Acc@5: 78.1250 (78.1250) +2025-04-18 09:52:03,993 - train: [ INFO] - Eval : 16 Time: 0.015 (0.315) Loss: 3.6828 (1.8440) Acc@1: 0.0000 (51.6962)Acc@5: 50.0000 (77.3323) +2025-04-18 09:52:17,275 - train: [ INFO] - Train: 17 [ 0/461 ( 0%)] Loss: 3.353337 (3.3533) Loss_single: 2.610287 (2.6103) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.778s, 4.11/s (7.778s, 4.11/s) LR: 5.000e-03 Data: 7.655 (7.655) +2025-04-18 09:52:30,481 - train: [ INFO] - Train: 17 [ 50/461 ( 11%)] Loss: 3.397919 (3.3756) Loss_single: 2.661419 (2.6359) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 336.68/s (0.383s, 83.51/s) LR: 5.000e-03 Data: 0.000 (0.290) +2025-04-18 09:52:44,952 - train: [ INFO] - Train: 17 [ 100/461 ( 22%)] Loss: 3.418197 (3.3898) Loss_single: 2.680570 (2.6508) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 408.58/s (0.319s, 100.36/s) LR: 5.000e-03 Data: 0.000 (0.228) +2025-04-18 09:52:59,650 - train: [ INFO] - Train: 17 [ 150/461 ( 33%)] Loss: 3.673807 (3.4608) Loss_single: 2.923953 (2.7191) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.76/s (0.286s, 111.83/s) LR: 5.000e-03 Data: 0.000 (0.195) +2025-04-18 09:53:14,729 - train: [ INFO] - Train: 17 [ 200/461 ( 43%)] Loss: 3.318196 (3.4323) Loss_single: 2.544904 (2.6842) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 404.51/s (0.276s, 116.05/s) LR: 5.000e-03 Data: 0.000 (0.185) +2025-04-18 09:53:29,813 - train: [ INFO] - Train: 17 [ 250/461 ( 54%)] Loss: 4.030136 (3.5319) Loss_single: 3.241377 (2.7771) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.107s, 298.44/s (0.274s, 116.79/s) LR: 5.000e-03 Data: 0.003 (0.182) +2025-04-18 09:53:40,876 - train: [ INFO] - Train: 17 [ 300/461 ( 65%)] Loss: 3.273750 (3.4950) Loss_single: 2.549084 (2.7445) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.120s, 266.92/s (0.263s, 121.79/s) LR: 5.000e-03 Data: 0.000 (0.167) +2025-04-18 09:53:47,717 - train: [ INFO] - Train: 17 [ 350/461 ( 76%)] Loss: 3.881367 (3.5433) Loss_single: 3.092359 (2.7880) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.167s, 191.24/s (0.241s, 132.84/s) LR: 5.000e-03 Data: 0.000 (0.144) +2025-04-18 09:53:54,443 - train: [ INFO] - Train: 17 [ 400/461 ( 87%)] Loss: 3.353858 (3.5223) Loss_single: 2.635056 (2.7710) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.085s, 375.16/s (0.223s, 143.24/s) LR: 5.000e-03 Data: 0.000 (0.126) +2025-04-18 09:54:06,734 - train: [ INFO] - Train: 17 [ 450/461 ( 98%)] Loss: 3.773139 (3.5474) Loss_single: 2.986264 (2.7925) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 100.0000 (100.0000) Time: 0.312s, 102.47/s (0.223s, 143.37/s) LR: 5.000e-03 Data: 0.174 (0.126) +2025-04-18 09:54:09,673 - train: [ INFO] - Train: 17 [ 460/461 (100%)] Loss: 3.764758 (3.5671) Loss_single: 2.982666 (2.8098) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8636) Acc@5: 100.0000 (100.0000) Time: 0.080s, 398.89/s (0.224s, 142.60/s) LR: 5.000e-03 Data: 0.000 (0.128) +2025-04-18 09:54:18,477 - train: [ INFO] - Eval : 17 Time: 8.472 (8.472) Loss: 2.2719 (2.2719) Acc@1: 53.1250 (53.1250)Acc@5: 62.5000 (62.5000) +2025-04-18 09:54:31,754 - train: [ INFO] - Eval : 17 Time: 1.513 (0.427) Loss: 1.8974 (1.8317) Acc@1: 59.3750 (52.5735)Acc@5: 71.8750 (77.8186) +2025-04-18 09:54:40,729 - train: [ INFO] - Eval : 17 Time: 0.014 (0.375) Loss: 4.1483 (1.8459) Acc@1: 0.0000 (51.5035)Acc@5: 0.0000 (78.0262) +2025-04-18 09:54:52,784 - train: [ INFO] - Train: 18 [ 0/461 ( 0%)] Loss: 3.202409 (3.2024) Loss_single: 2.480682 (2.4807) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.656s, 4.18/s (7.656s, 4.18/s) LR: 5.000e-03 Data: 7.532 (7.532) +2025-04-18 09:55:08,397 - train: [ INFO] - Train: 18 [ 50/461 ( 11%)] Loss: 3.777193 (3.4898) Loss_single: 3.009080 (2.7449) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 331.83/s (0.427s, 74.91/s) LR: 5.000e-03 Data: 0.000 (0.327) +2025-04-18 09:55:18,135 - train: [ INFO] - Train: 18 [ 100/461 ( 22%)] Loss: 3.784266 (3.5880) Loss_single: 2.908296 (2.7994) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.084s, 380.57/s (0.303s, 105.60/s) LR: 5.000e-03 Data: 0.000 (0.208) +2025-04-18 09:55:23,553 - train: [ INFO] - Train: 18 [ 150/461 ( 33%)] Loss: 3.508118 (3.5680) Loss_single: 2.747550 (2.7864) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.077s, 415.84/s (0.238s, 134.25/s) LR: 5.000e-03 Data: 0.000 (0.139) +2025-04-18 09:55:34,324 - train: [ INFO] - Train: 18 [ 200/461 ( 43%)] Loss: 3.508099 (3.5560) Loss_single: 2.789218 (2.7870) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.079s, 403.07/s (0.202s, 158.33/s) LR: 5.000e-03 Data: 0.000 (0.105) +2025-04-18 09:55:48,580 - train: [ INFO] - Train: 18 [ 250/461 ( 54%)] Loss: 3.534131 (3.5524) Loss_single: 2.783356 (2.7864) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.077s, 417.04/s (0.213s, 150.34/s) LR: 5.000e-03 Data: 0.000 (0.115) +2025-04-18 09:56:01,667 - train: [ INFO] - Train: 18 [ 300/461 ( 65%)] Loss: 4.242179 (3.6509) Loss_single: 3.260142 (2.8540) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (97.7679) Acc@5: 93.7500 (98.6607) Time: 0.094s, 340.51/s (0.214s, 149.82/s) LR: 5.000e-03 Data: 0.000 (0.115) +2025-04-18 09:56:11,299 - train: [ INFO] - Train: 18 [ 350/461 ( 76%)] Loss: 3.589304 (3.6432) Loss_single: 2.855596 (2.8542) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.0469) Acc@5: 100.0000 (98.8281) Time: 0.081s, 395.32/s (0.210s, 152.24/s) LR: 5.000e-03 Data: 0.000 (0.112) +2025-04-18 09:56:17,925 - train: [ INFO] - Train: 18 [ 400/461 ( 87%)] Loss: 3.667586 (3.6459) Loss_single: 2.929854 (2.8626) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.9167) Acc@5: 100.0000 (98.9583) Time: 0.106s, 301.76/s (0.197s, 162.42/s) LR: 5.000e-03 Data: 0.001 (0.098) +2025-04-18 09:56:22,806 - train: [ INFO] - Train: 18 [ 450/461 ( 98%)] Loss: 3.646302 (3.6460) Loss_single: 2.931782 (2.8696) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.1250) Acc@5: 100.0000 (99.0625) Time: 0.079s, 407.18/s (0.186s, 172.15/s) LR: 5.000e-03 Data: 0.000 (0.087) +2025-04-18 09:56:23,590 - train: [ INFO] - Train: 18 [ 460/461 (100%)] Loss: 3.475438 (3.6305) Loss_single: 2.753742 (2.8590) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.2955) Acc@5: 100.0000 (99.1477) Time: 0.080s, 399.99/s (0.184s, 174.35/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-18 09:56:30,802 - train: [ INFO] - Eval : 18 Time: 6.961 (6.961) Loss: 2.1475 (2.1475) Acc@1: 40.6250 (40.6250)Acc@5: 71.8750 (71.8750) +2025-04-18 09:56:44,584 - train: [ INFO] - Eval : 18 Time: 0.028 (0.407) Loss: 1.8957 (1.8193) Acc@1: 59.3750 (52.3897)Acc@5: 71.8750 (76.9608) +2025-04-18 09:56:51,039 - train: [ INFO] - Eval : 18 Time: 0.014 (0.332) Loss: 2.9784 (1.8357) Acc@1: 0.0000 (52.0046)Acc@5: 50.0000 (76.9854) +2025-04-18 09:56:55,755 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-18.pth.tar', 52.00462606013878) + +2025-04-18 09:57:04,931 - train: [ INFO] - Train: 19 [ 0/461 ( 0%)] Loss: 3.517375 (3.5174) Loss_single: 2.802338 (2.8023) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 9.037s, 3.54/s (9.037s, 3.54/s) LR: 5.000e-03 Data: 8.902 (8.902) +2025-04-18 09:57:20,075 - train: [ INFO] - Train: 19 [ 50/461 ( 11%)] Loss: 3.490422 (3.5039) Loss_single: 2.787348 (2.7948) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.097s, 330.58/s (0.412s, 77.71/s) LR: 5.000e-03 Data: 0.001 (0.320) +2025-04-18 09:57:30,107 - train: [ INFO] - Train: 19 [ 100/461 ( 22%)] Loss: 3.178274 (3.3954) Loss_single: 2.476447 (2.6887) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.087s, 367.41/s (0.288s, 111.20/s) LR: 5.000e-03 Data: 0.001 (0.193) +2025-04-18 09:57:42,446 - train: [ INFO] - Train: 19 [ 150/461 ( 33%)] Loss: 3.557234 (3.4358) Loss_single: 2.803953 (2.7175) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 392.02/s (0.265s, 120.65/s) LR: 5.000e-03 Data: 0.000 (0.171) +2025-04-18 09:57:51,726 - train: [ INFO] - Train: 19 [ 200/461 ( 43%)] Loss: 3.466590 (3.4420) Loss_single: 2.753153 (2.7246) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 391.42/s (0.240s, 133.39/s) LR: 5.000e-03 Data: 0.000 (0.142) +2025-04-18 09:57:57,389 - train: [ INFO] - Train: 19 [ 250/461 ( 54%)] Loss: 3.537520 (3.4579) Loss_single: 2.813978 (2.7395) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.087s, 368.62/s (0.213s, 150.39/s) LR: 5.000e-03 Data: 0.001 (0.114) +2025-04-18 09:58:03,010 - train: [ INFO] - Train: 19 [ 300/461 ( 65%)] Loss: 3.528384 (3.4680) Loss_single: 2.821631 (2.7513) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.089s, 358.01/s (0.196s, 163.61/s) LR: 5.000e-03 Data: 0.000 (0.095) +2025-04-18 09:58:09,735 - train: [ INFO] - Train: 19 [ 350/461 ( 76%)] Loss: 3.589811 (3.4832) Loss_single: 2.882022 (2.7676) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 402.07/s (0.186s, 172.29/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-18 09:58:26,206 - train: [ INFO] - Train: 19 [ 400/461 ( 87%)] Loss: 3.615514 (3.4979) Loss_single: 2.882930 (2.7804) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.112s, 284.78/s (0.202s, 158.23/s) LR: 5.000e-03 Data: 0.001 (0.103) +2025-04-18 09:58:37,918 - train: [ INFO] - Train: 19 [ 450/461 ( 98%)] Loss: 3.272059 (3.4753) Loss_single: 2.561954 (2.7586) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.132s, 242.05/s (0.206s, 155.72/s) LR: 5.000e-03 Data: 0.000 (0.106) +2025-04-18 09:58:38,839 - train: [ INFO] - Train: 19 [ 460/461 (100%)] Loss: 3.513002 (3.4787) Loss_single: 2.798600 (2.7622) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 387.08/s (0.203s, 157.62/s) LR: 5.000e-03 Data: 0.000 (0.104) +2025-04-18 09:58:45,108 - train: [ INFO] - Eval : 19 Time: 6.009 (6.009) Loss: 2.1160 (2.1160) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 09:58:53,833 - train: [ INFO] - Eval : 19 Time: 0.027 (0.289) Loss: 1.8225 (1.9787) Acc@1: 59.3750 (47.9779)Acc@5: 71.8750 (74.3260) +2025-04-18 09:59:03,898 - train: [ INFO] - Eval : 19 Time: 0.016 (0.302) Loss: 3.0733 (1.9979) Acc@1: 50.0000 (47.6870)Acc@5: 50.0000 (74.2483) +2025-04-18 09:59:16,768 - train: [ INFO] - Train: 20 [ 0/461 ( 0%)] Loss: 3.859391 (3.8594) Loss_single: 3.095436 (3.0954) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 8.001s, 4.00/s (8.001s, 4.00/s) LR: 5.000e-03 Data: 7.833 (7.833) +2025-04-18 09:59:28,096 - train: [ INFO] - Train: 20 [ 50/461 ( 11%)] Loss: 3.220924 (3.5402) Loss_single: 2.512156 (2.8038) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.120s, 266.87/s (0.347s, 92.33/s) LR: 5.000e-03 Data: 0.000 (0.252) +2025-04-18 09:59:33,922 - train: [ INFO] - Train: 20 [ 100/461 ( 22%)] Loss: 3.194603 (3.4250) Loss_single: 2.481061 (2.6962) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.167s, 191.18/s (0.232s, 137.92/s) LR: 5.000e-03 Data: 0.001 (0.128) +2025-04-18 09:59:39,816 - train: [ INFO] - Train: 20 [ 150/461 ( 33%)] Loss: 3.748576 (3.5059) Loss_single: 2.936405 (2.7563) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (99.2188) Time: 0.100s, 320.77/s (0.193s, 165.50/s) LR: 5.000e-03 Data: 0.001 (0.086) +2025-04-18 09:59:51,612 - train: [ INFO] - Train: 20 [ 200/461 ( 43%)] Loss: 3.436120 (3.4919) Loss_single: 2.715257 (2.7481) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 1.274s, 25.11/s (0.191s, 167.41/s) LR: 5.000e-03 Data: 1.164 (0.088) +2025-04-18 10:00:03,074 - train: [ INFO] - Train: 20 [ 250/461 ( 54%)] Loss: 3.515152 (3.4958) Loss_single: 2.774654 (2.7525) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.207s, 154.72/s (0.196s, 163.06/s) LR: 5.000e-03 Data: 0.092 (0.094) +2025-04-18 10:00:13,600 - train: [ INFO] - Train: 20 [ 300/461 ( 65%)] Loss: 3.132705 (3.4439) Loss_single: 2.429294 (2.7063) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.133s, 240.70/s (0.198s, 161.38/s) LR: 5.000e-03 Data: 0.001 (0.097) +2025-04-18 10:00:28,047 - train: [ INFO] - Train: 20 [ 350/461 ( 76%)] Loss: 3.087110 (3.3993) Loss_single: 2.391032 (2.6669) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.076s, 418.52/s (0.211s, 151.73/s) LR: 5.000e-03 Data: 0.000 (0.111) +2025-04-18 10:00:39,933 - train: [ INFO] - Train: 20 [ 400/461 ( 87%)] Loss: 3.566789 (3.4179) Loss_single: 2.829793 (2.6850) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.109s, 293.79/s (0.214s, 149.46/s) LR: 5.000e-03 Data: 0.000 (0.113) +2025-04-18 10:00:45,548 - train: [ INFO] - Train: 20 [ 450/461 ( 98%)] Loss: 3.784358 (3.4546) Loss_single: 3.044337 (2.7209) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.094s, 339.82/s (0.201s, 158.97/s) LR: 5.000e-03 Data: 0.000 (0.100) +2025-04-18 10:00:46,900 - train: [ INFO] - Train: 20 [ 460/461 (100%)] Loss: 3.243385 (3.4354) Loss_single: 2.539747 (2.7045) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.085s, 375.88/s (0.199s, 160.99/s) LR: 5.000e-03 Data: 0.000 (0.098) +2025-04-18 10:00:51,009 - train: [ INFO] - Eval : 20 Time: 3.836 (3.836) Loss: 2.2223 (2.2223) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 10:00:59,670 - train: [ INFO] - Eval : 20 Time: 0.731 (0.245) Loss: 1.7826 (1.9166) Acc@1: 59.3750 (50.6127)Acc@5: 78.1250 (76.8382) +2025-04-18 10:01:08,726 - train: [ INFO] - Eval : 20 Time: 0.015 (0.263) Loss: 3.2559 (1.9600) Acc@1: 50.0000 (49.6145)Acc@5: 50.0000 (75.4048) +2025-04-18 10:01:21,488 - train: [ INFO] - Train: 21 [ 0/461 ( 0%)] Loss: 3.125787 (3.1258) Loss_single: 2.408363 (2.4084) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.820s, 4.09/s (7.820s, 4.09/s) LR: 5.000e-03 Data: 7.645 (7.645) +2025-04-18 10:01:37,414 - train: [ INFO] - Train: 21 [ 50/461 ( 11%)] Loss: 3.215032 (3.1704) Loss_single: 2.510351 (2.4594) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.130s, 245.82/s (0.413s, 77.43/s) LR: 5.000e-03 Data: 0.001 (0.312) +2025-04-18 10:01:53,298 - train: [ INFO] - Train: 21 [ 100/461 ( 22%)] Loss: 3.338780 (3.2265) Loss_single: 2.635204 (2.5180) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.112s, 284.79/s (0.346s, 92.52/s) LR: 5.000e-03 Data: 0.000 (0.246) +2025-04-18 10:02:01,805 - train: [ INFO] - Train: 21 [ 150/461 ( 33%)] Loss: 3.515919 (3.2989) Loss_single: 2.803966 (2.5895) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.169s, 189.86/s (0.286s, 111.84/s) LR: 5.000e-03 Data: 0.001 (0.184) +2025-04-18 10:02:08,228 - train: [ INFO] - Train: 21 [ 200/461 ( 43%)] Loss: 3.372732 (3.3136) Loss_single: 2.669408 (2.6055) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 409.90/s (0.240s, 133.28/s) LR: 5.000e-03 Data: 0.000 (0.138) +2025-04-18 10:02:22,315 - train: [ INFO] - Train: 21 [ 250/461 ( 54%)] Loss: 3.343629 (3.3186) Loss_single: 2.637627 (2.6108) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 401.09/s (0.243s, 131.46/s) LR: 5.000e-03 Data: 0.000 (0.145) +2025-04-18 10:02:38,607 - train: [ INFO] - Train: 21 [ 300/461 ( 65%)] Loss: 3.285812 (3.3140) Loss_single: 2.559056 (2.6034) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.106s, 302.79/s (0.255s, 125.49/s) LR: 5.000e-03 Data: 0.000 (0.157) +2025-04-18 10:02:50,239 - train: [ INFO] - Train: 21 [ 350/461 ( 76%)] Loss: 3.651363 (3.3561) Loss_single: 2.939804 (2.6455) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.143s, 224.21/s (0.247s, 129.39/s) LR: 5.000e-03 Data: 0.000 (0.148) +2025-04-18 10:02:56,602 - train: [ INFO] - Train: 21 [ 400/461 ( 87%)] Loss: 3.384932 (3.3593) Loss_single: 2.617871 (2.6424) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.115s, 278.80/s (0.229s, 139.61/s) LR: 5.000e-03 Data: 0.001 (0.130) +2025-04-18 10:03:09,871 - train: [ INFO] - Train: 21 [ 450/461 ( 98%)] Loss: 3.620839 (3.3855) Loss_single: 2.842091 (2.6624) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.081s, 392.95/s (0.228s, 140.52/s) LR: 5.000e-03 Data: 0.000 (0.129) +2025-04-18 10:03:11,107 - train: [ INFO] - Train: 21 [ 460/461 (100%)] Loss: 3.505513 (3.3964) Loss_single: 2.800737 (2.6750) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.078s, 412.41/s (0.225s, 141.99/s) LR: 5.000e-03 Data: 0.000 (0.126) +2025-04-18 10:03:17,692 - train: [ INFO] - Eval : 21 Time: 6.246 (6.246) Loss: 2.0954 (2.0954) Acc@1: 50.0000 (50.0000)Acc@5: 68.7500 (68.7500) +2025-04-18 10:03:32,812 - train: [ INFO] - Eval : 21 Time: 0.076 (0.419) Loss: 1.9161 (1.8801) Acc@1: 56.2500 (51.6544)Acc@5: 71.8750 (78.5539) +2025-04-18 10:03:34,791 - train: [ INFO] - Eval : 21 Time: 0.016 (0.285) Loss: 3.1221 (1.8979) Acc@1: 0.0000 (51.3107)Acc@5: 50.0000 (77.4480) +2025-04-18 10:03:41,854 - train: [ INFO] - Train: 22 [ 0/461 ( 0%)] Loss: 3.170148 (3.1701) Loss_single: 2.470814 (2.4708) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.072s, 7.86/s (4.072s, 7.86/s) LR: 5.000e-03 Data: 3.888 (3.888) +2025-04-18 10:03:53,758 - train: [ INFO] - Train: 22 [ 50/461 ( 11%)] Loss: 3.586802 (3.3785) Loss_single: 2.873041 (2.6719) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.143s, 224.34/s (0.259s, 123.50/s) LR: 5.000e-03 Data: 0.001 (0.156) +2025-04-18 10:04:05,499 - train: [ INFO] - Train: 22 [ 100/461 ( 22%)] Loss: 3.355108 (3.3707) Loss_single: 2.647319 (2.6637) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 410.50/s (0.224s, 142.64/s) LR: 5.000e-03 Data: 0.000 (0.126) +2025-04-18 10:04:24,562 - train: [ INFO] - Train: 22 [ 150/461 ( 33%)] Loss: 3.196601 (3.3272) Loss_single: 2.498233 (2.6224) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 388.56/s (0.254s, 125.98/s) LR: 5.000e-03 Data: 0.001 (0.158) +2025-04-18 10:04:32,199 - train: [ INFO] - Train: 22 [ 200/461 ( 43%)] Loss: 3.374629 (3.3367) Loss_single: 2.619817 (2.6218) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.077s, 417.61/s (0.221s, 144.83/s) LR: 5.000e-03 Data: 0.000 (0.125) +2025-04-18 10:04:42,369 - train: [ INFO] - Train: 22 [ 250/461 ( 54%)] Loss: 3.446987 (3.3550) Loss_single: 2.747896 (2.6429) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.078s, 409.93/s (0.205s, 156.21/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 10:04:50,548 - train: [ INFO] - Train: 22 [ 300/461 ( 65%)] Loss: 3.658118 (3.3983) Loss_single: 2.964295 (2.6888) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.079s, 405.01/s (0.195s, 163.88/s) LR: 5.000e-03 Data: 0.000 (0.097) +2025-04-18 10:04:56,981 - train: [ INFO] - Train: 22 [ 350/461 ( 76%)] Loss: 3.533914 (3.4153) Loss_single: 2.737992 (2.6949) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.6094) Time: 0.129s, 248.84/s (0.184s, 174.24/s) LR: 5.000e-03 Data: 0.000 (0.083) +2025-04-18 10:05:02,301 - train: [ INFO] - Train: 22 [ 400/461 ( 87%)] Loss: 3.379128 (3.4113) Loss_single: 2.692223 (2.6946) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.109s, 293.84/s (0.174s, 183.96/s) LR: 5.000e-03 Data: 0.000 (0.073) +2025-04-18 10:05:08,259 - train: [ INFO] - Train: 22 [ 450/461 ( 98%)] Loss: 3.577997 (3.4279) Loss_single: 2.874192 (2.7126) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.085s, 377.44/s (0.166s, 192.27/s) LR: 5.000e-03 Data: 0.000 (0.065) +2025-04-18 10:05:09,155 - train: [ INFO] - Train: 22 [ 460/461 (100%)] Loss: 4.149915 (3.4936) Loss_single: 3.281341 (2.7643) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (98.8636) Acc@5: 96.8750 (99.4318) Time: 0.077s, 417.77/s (0.165s, 194.23/s) LR: 5.000e-03 Data: 0.000 (0.063) +2025-04-18 10:05:16,361 - train: [ INFO] - Eval : 22 Time: 6.982 (6.982) Loss: 2.3136 (2.3136) Acc@1: 37.5000 (37.5000)Acc@5: 68.7500 (68.7500) +2025-04-18 10:05:33,807 - train: [ INFO] - Eval : 22 Time: 0.058 (0.479) Loss: 2.0177 (1.9234) Acc@1: 59.3750 (51.1642)Acc@5: 71.8750 (77.2672) +2025-04-18 10:05:43,135 - train: [ INFO] - Eval : 22 Time: 0.016 (0.412) Loss: 2.7856 (1.9375) Acc@1: 50.0000 (50.5397)Acc@5: 50.0000 (76.5998) +2025-04-18 10:05:54,958 - train: [ INFO] - Train: 23 [ 0/461 ( 0%)] Loss: 3.903476 (3.9035) Loss_single: 3.166374 (3.1664) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.396s, 3.81/s (8.396s, 3.81/s) LR: 5.000e-03 Data: 8.238 (8.238) +2025-04-18 10:06:10,384 - train: [ INFO] - Train: 23 [ 50/461 ( 11%)] Loss: 3.578325 (3.7409) Loss_single: 2.861442 (3.0139) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 335.43/s (0.407s, 78.70/s) LR: 5.000e-03 Data: 0.000 (0.314) +2025-04-18 10:06:22,898 - train: [ INFO] - Train: 23 [ 100/461 ( 22%)] Loss: 3.135798 (3.5392) Loss_single: 2.439182 (2.8223) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 409.37/s (0.321s, 99.72/s) LR: 5.000e-03 Data: 0.000 (0.228) +2025-04-18 10:06:31,998 - train: [ INFO] - Train: 23 [ 150/461 ( 33%)] Loss: 3.294105 (3.4779) Loss_single: 2.568216 (2.7588) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.138s, 231.99/s (0.268s, 119.33/s) LR: 5.000e-03 Data: 0.001 (0.167) +2025-04-18 10:06:38,590 - train: [ INFO] - Train: 23 [ 200/461 ( 43%)] Loss: 3.107352 (3.4038) Loss_single: 2.401101 (2.6873) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.116s, 275.92/s (0.228s, 140.06/s) LR: 5.000e-03 Data: 0.000 (0.126) +2025-04-18 10:06:44,353 - train: [ INFO] - Train: 23 [ 250/461 ( 54%)] Loss: 3.008531 (3.3379) Loss_single: 2.308379 (2.6241) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.075s, 427.54/s (0.206s, 155.52/s) LR: 5.000e-03 Data: 0.000 (0.101) +2025-04-18 10:06:51,349 - train: [ INFO] - Train: 23 [ 300/461 ( 65%)] Loss: 3.003926 (3.2902) Loss_single: 2.274178 (2.5741) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.107s, 299.21/s (0.187s, 170.74/s) LR: 5.000e-03 Data: 0.000 (0.084) +2025-04-18 10:07:00,855 - train: [ INFO] - Train: 23 [ 350/461 ( 76%)] Loss: 3.681302 (3.3391) Loss_single: 2.876915 (2.6120) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.149s, 214.75/s (0.183s, 175.32/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 10:07:09,841 - train: [ INFO] - Train: 23 [ 400/461 ( 87%)] Loss: 3.472577 (3.3539) Loss_single: 2.758305 (2.6282) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.084s, 382.67/s (0.181s, 177.05/s) LR: 5.000e-03 Data: 0.001 (0.077) +2025-04-18 10:07:25,777 - train: [ INFO] - Train: 23 [ 450/461 ( 98%)] Loss: 3.564717 (3.3750) Loss_single: 2.871742 (2.6526) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.083s, 383.50/s (0.190s, 168.01/s) LR: 5.000e-03 Data: 0.000 (0.087) +2025-04-18 10:07:26,613 - train: [ INFO] - Train: 23 [ 460/461 (100%)] Loss: 3.154651 (3.3550) Loss_single: 2.451922 (2.6343) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.078s, 412.83/s (0.188s, 170.10/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-18 10:07:30,467 - train: [ INFO] - Eval : 23 Time: 3.636 (3.636) Loss: 2.1567 (2.1567) Acc@1: 43.7500 (43.7500)Acc@5: 68.7500 (68.7500) +2025-04-18 10:07:33,328 - train: [ INFO] - Eval : 23 Time: 0.054 (0.127) Loss: 2.0086 (1.8898) Acc@1: 50.0000 (50.7966)Acc@5: 75.0000 (77.2672) +2025-04-18 10:07:34,720 - train: [ INFO] - Eval : 23 Time: 0.015 (0.096) Loss: 3.5008 (1.9079) Acc@1: 0.0000 (50.5783)Acc@5: 50.0000 (76.6384) +2025-04-18 10:07:41,527 - train: [ INFO] - Train: 24 [ 0/461 ( 0%)] Loss: 3.319911 (3.3199) Loss_single: 2.616370 (2.6164) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 3.937s, 8.13/s (3.937s, 8.13/s) LR: 5.000e-03 Data: 3.767 (3.767) +2025-04-18 10:07:56,791 - train: [ INFO] - Train: 24 [ 50/461 ( 11%)] Loss: 3.247169 (3.2835) Loss_single: 2.556383 (2.5864) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 387.87/s (0.307s, 104.30/s) LR: 5.000e-03 Data: 0.000 (0.209) +2025-04-18 10:08:10,565 - train: [ INFO] - Train: 24 [ 100/461 ( 22%)] Loss: 3.178756 (3.2486) Loss_single: 2.472794 (2.5485) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.086s, 373.76/s (0.268s, 119.46/s) LR: 5.000e-03 Data: 0.001 (0.175) +2025-04-18 10:08:17,438 - train: [ INFO] - Train: 24 [ 150/461 ( 33%)] Loss: 3.139208 (3.2213) Loss_single: 2.449294 (2.5237) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 392.90/s (0.223s, 143.71/s) LR: 5.000e-03 Data: 0.001 (0.130) +2025-04-18 10:08:33,456 - train: [ INFO] - Train: 24 [ 200/461 ( 43%)] Loss: 3.418931 (3.2608) Loss_single: 2.682730 (2.5555) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.113s, 283.65/s (0.230s, 138.98/s) LR: 5.000e-03 Data: 0.000 (0.137) +2025-04-18 10:08:47,692 - train: [ INFO] - Train: 24 [ 250/461 ( 54%)] Loss: 3.619081 (3.3205) Loss_single: 2.930337 (2.6180) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 389.84/s (0.234s, 136.67/s) LR: 5.000e-03 Data: 0.000 (0.142) +2025-04-18 10:08:57,914 - train: [ INFO] - Train: 24 [ 300/461 ( 65%)] Loss: 4.160106 (3.4405) Loss_single: 3.459924 (2.7383) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.101s, 316.92/s (0.223s, 143.76/s) LR: 5.000e-03 Data: 0.001 (0.129) +2025-04-18 10:09:10,530 - train: [ INFO] - Train: 24 [ 350/461 ( 76%)] Loss: 3.553198 (3.4545) Loss_single: 2.857494 (2.7532) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.132s, 242.96/s (0.225s, 142.38/s) LR: 5.000e-03 Data: 0.001 (0.130) +2025-04-18 10:09:16,473 - train: [ INFO] - Train: 24 [ 400/461 ( 87%)] Loss: 3.576450 (3.4681) Loss_single: 2.811810 (2.7597) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 96.8750 (99.6528) Time: 0.107s, 298.10/s (0.211s, 151.33/s) LR: 5.000e-03 Data: 0.001 (0.114) +2025-04-18 10:09:22,198 - train: [ INFO] - Train: 24 [ 450/461 ( 98%)] Loss: 3.370332 (3.4583) Loss_single: 2.673952 (2.7511) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.109s, 294.31/s (0.200s, 160.15/s) LR: 5.000e-03 Data: 0.001 (0.102) +2025-04-18 10:09:23,109 - train: [ INFO] - Train: 24 [ 460/461 (100%)] Loss: 3.469479 (3.4593) Loss_single: 2.774472 (2.7532) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.079s, 403.36/s (0.197s, 162.08/s) LR: 5.000e-03 Data: 0.000 (0.099) +2025-04-18 10:09:27,832 - train: [ INFO] - Eval : 24 Time: 4.490 (4.490) Loss: 1.9670 (1.9670) Acc@1: 56.2500 (56.2500)Acc@5: 75.0000 (75.0000) +2025-04-18 10:09:40,783 - train: [ INFO] - Eval : 24 Time: 0.062 (0.342) Loss: 1.9442 (1.8823) Acc@1: 56.2500 (51.8382)Acc@5: 75.0000 (76.6544) +2025-04-18 10:09:48,734 - train: [ INFO] - Eval : 24 Time: 0.016 (0.310) Loss: 2.7654 (1.9024) Acc@1: 50.0000 (51.1951)Acc@5: 50.0000 (75.9830) +2025-04-18 10:10:01,941 - train: [ INFO] - Train: 25 [ 0/461 ( 0%)] Loss: 3.668925 (3.6689) Loss_single: 2.891674 (2.8917) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 8.943s, 3.58/s (8.943s, 3.58/s) LR: 5.000e-03 Data: 8.838 (8.838) +2025-04-18 10:10:15,979 - train: [ INFO] - Train: 25 [ 50/461 ( 11%)] Loss: 3.076987 (3.3730) Loss_single: 2.390512 (2.6411) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.123s, 260.63/s (0.396s, 80.87/s) LR: 5.000e-03 Data: 0.000 (0.291) +2025-04-18 10:10:21,937 - train: [ INFO] - Train: 25 [ 100/461 ( 22%)] Loss: 3.136981 (3.2943) Loss_single: 2.439878 (2.5740) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.119s, 268.58/s (0.258s, 123.81/s) LR: 5.000e-03 Data: 0.000 (0.147) +2025-04-18 10:10:32,594 - train: [ INFO] - Train: 25 [ 150/461 ( 33%)] Loss: 3.331391 (3.3036) Loss_single: 2.641842 (2.5910) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.740s, 43.25/s (0.216s, 148.30/s) LR: 5.000e-03 Data: 0.615 (0.113) +2025-04-18 10:10:43,104 - train: [ INFO] - Train: 25 [ 200/461 ( 43%)] Loss: 3.377471 (3.3184) Loss_single: 2.682428 (2.6093) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.088s, 365.42/s (0.213s, 150.26/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 10:10:55,395 - train: [ INFO] - Train: 25 [ 250/461 ( 54%)] Loss: 3.309072 (3.3168) Loss_single: 2.530339 (2.5961) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (99.4792) Time: 0.085s, 374.68/s (0.201s, 159.21/s) LR: 5.000e-03 Data: 0.000 (0.096) +2025-04-18 10:11:04,201 - train: [ INFO] - Train: 25 [ 300/461 ( 65%)] Loss: 3.392923 (3.3277) Loss_single: 2.617062 (2.5991) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.6607) Acc@5: 96.8750 (99.1071) Time: 0.109s, 293.57/s (0.187s, 171.41/s) LR: 5.000e-03 Data: 0.000 (0.080) +2025-04-18 10:11:15,670 - train: [ INFO] - Train: 25 [ 350/461 ( 76%)] Loss: 3.333211 (3.3284) Loss_single: 2.560296 (2.5943) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (98.8281) Time: 0.200s, 159.71/s (0.182s, 175.83/s) LR: 5.000e-03 Data: 0.051 (0.077) +2025-04-18 10:11:26,551 - train: [ INFO] - Train: 25 [ 400/461 ( 87%)] Loss: 3.410234 (3.3375) Loss_single: 2.723348 (2.6086) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6111) Acc@5: 100.0000 (98.9583) Time: 0.134s, 238.00/s (0.183s, 174.41/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 10:11:39,700 - train: [ INFO] - Train: 25 [ 450/461 ( 98%)] Loss: 3.727428 (3.3765) Loss_single: 3.030701 (2.6508) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.0625) Time: 0.075s, 425.09/s (0.187s, 171.04/s) LR: 5.000e-03 Data: 0.000 (0.083) +2025-04-18 10:11:40,539 - train: [ INFO] - Train: 25 [ 460/461 (100%)] Loss: 3.095139 (3.3509) Loss_single: 2.409583 (2.6289) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8636) Acc@5: 100.0000 (99.1477) Time: 0.079s, 406.18/s (0.185s, 173.16/s) LR: 5.000e-03 Data: 0.000 (0.081) +2025-04-18 10:11:48,715 - train: [ INFO] - Eval : 25 Time: 7.927 (7.927) Loss: 2.0297 (2.0297) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-18 10:11:59,576 - train: [ INFO] - Eval : 25 Time: 0.059 (0.368) Loss: 1.9069 (1.9297) Acc@1: 59.3750 (50.7966)Acc@5: 75.0000 (77.2672) +2025-04-18 10:12:03,014 - train: [ INFO] - Eval : 25 Time: 0.016 (0.271) Loss: 3.2446 (1.9512) Acc@1: 50.0000 (50.2699)Acc@5: 50.0000 (76.4842) +2025-04-18 10:12:10,856 - train: [ INFO] - Train: 26 [ 0/461 ( 0%)] Loss: 3.504507 (3.5045) Loss_single: 2.723959 (2.7240) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 5.023s, 6.37/s (5.023s, 6.37/s) LR: 5.000e-03 Data: 4.863 (4.863) +2025-04-18 10:12:18,481 - train: [ INFO] - Train: 26 [ 50/461 ( 11%)] Loss: 3.329690 (3.4171) Loss_single: 2.643768 (2.6839) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.085s, 375.85/s (0.212s, 151.08/s) LR: 5.000e-03 Data: 0.001 (0.096) +2025-04-18 10:12:31,269 - train: [ INFO] - Train: 26 [ 100/461 ( 22%)] Loss: 3.190830 (3.3417) Loss_single: 2.489290 (2.6190) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.095s, 335.30/s (0.223s, 143.38/s) LR: 5.000e-03 Data: 0.000 (0.116) +2025-04-18 10:12:43,390 - train: [ INFO] - Train: 26 [ 150/461 ( 33%)] Loss: 2.989401 (3.2536) Loss_single: 2.303435 (2.5401) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.088s, 362.74/s (0.220s, 145.25/s) LR: 5.000e-03 Data: 0.000 (0.115) +2025-04-18 10:12:52,882 - train: [ INFO] - Train: 26 [ 200/461 ( 43%)] Loss: 3.230292 (3.2489) Loss_single: 2.534354 (2.5390) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.079s, 404.64/s (0.212s, 151.17/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 10:13:00,716 - train: [ INFO] - Train: 26 [ 250/461 ( 54%)] Loss: 3.361588 (3.2677) Loss_single: 2.660635 (2.5592) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.106s, 301.16/s (0.198s, 161.34/s) LR: 5.000e-03 Data: 0.001 (0.094) +2025-04-18 10:13:09,413 - train: [ INFO] - Train: 26 [ 300/461 ( 65%)] Loss: 3.583936 (3.3129) Loss_single: 2.868696 (2.6034) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.173s, 184.72/s (0.183s, 175.03/s) LR: 5.000e-03 Data: 0.001 (0.078) +2025-04-18 10:13:17,086 - train: [ INFO] - Train: 26 [ 350/461 ( 76%)] Loss: 3.313353 (3.3129) Loss_single: 2.622250 (2.6058) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.166s, 192.69/s (0.173s, 185.08/s) LR: 5.000e-03 Data: 0.001 (0.069) +2025-04-18 10:13:28,442 - train: [ INFO] - Train: 26 [ 400/461 ( 87%)] Loss: 3.537455 (3.3379) Loss_single: 2.843630 (2.6322) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.080s, 398.38/s (0.176s, 182.01/s) LR: 5.000e-03 Data: 0.001 (0.073) +2025-04-18 10:13:44,983 - train: [ INFO] - Train: 26 [ 450/461 ( 98%)] Loss: 3.261585 (3.3303) Loss_single: 2.566623 (2.6257) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.084s, 381.34/s (0.191s, 167.91/s) LR: 5.000e-03 Data: 0.000 (0.089) +2025-04-18 10:13:46,514 - train: [ INFO] - Train: 26 [ 460/461 (100%)] Loss: 3.375429 (3.3344) Loss_single: 2.688759 (2.6314) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.079s, 403.00/s (0.190s, 168.74/s) LR: 5.000e-03 Data: 0.000 (0.088) +2025-04-18 10:13:52,004 - train: [ INFO] - Eval : 26 Time: 5.166 (5.166) Loss: 2.1344 (2.1344) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 10:14:02,361 - train: [ INFO] - Eval : 26 Time: 0.027 (0.304) Loss: 1.9924 (1.9530) Acc@1: 50.0000 (49.9387)Acc@5: 75.0000 (77.8186) +2025-04-18 10:14:04,204 - train: [ INFO] - Eval : 26 Time: 0.017 (0.212) Loss: 3.1933 (1.9888) Acc@1: 0.0000 (49.1519)Acc@5: 50.0000 (76.5998) +2025-04-18 10:14:15,930 - train: [ INFO] - Train: 27 [ 0/461 ( 0%)] Loss: 3.209921 (3.2099) Loss_single: 2.510824 (2.5108) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.768s, 3.65/s (8.768s, 3.65/s) LR: 5.000e-03 Data: 8.563 (8.563) +2025-04-18 10:14:31,334 - train: [ INFO] - Train: 27 [ 50/461 ( 11%)] Loss: 3.369139 (3.2895) Loss_single: 2.674407 (2.5926) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.112s, 286.55/s (0.405s, 78.98/s) LR: 5.000e-03 Data: 0.001 (0.307) +2025-04-18 10:14:45,963 - train: [ INFO] - Train: 27 [ 100/461 ( 22%)] Loss: 2.893779 (3.1576) Loss_single: 2.196532 (2.4606) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.105s, 304.87/s (0.316s, 101.28/s) LR: 5.000e-03 Data: 0.000 (0.221) +2025-04-18 10:14:52,693 - train: [ INFO] - Train: 27 [ 150/461 ( 33%)] Loss: 3.682902 (3.2889) Loss_single: 2.908229 (2.5725) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.092s, 345.96/s (0.253s, 126.48/s) LR: 5.000e-03 Data: 0.000 (0.153) +2025-04-18 10:15:01,311 - train: [ INFO] - Train: 27 [ 200/461 ( 43%)] Loss: 3.048722 (3.2409) Loss_single: 2.364228 (2.5308) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.112s, 285.40/s (0.218s, 146.65/s) LR: 5.000e-03 Data: 0.001 (0.121) +2025-04-18 10:15:13,739 - train: [ INFO] - Train: 27 [ 250/461 ( 54%)] Loss: 3.381153 (3.2643) Loss_single: 2.667532 (2.5536) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.083s, 384.03/s (0.221s, 144.62/s) LR: 5.000e-03 Data: 0.001 (0.123) +2025-04-18 10:15:25,715 - train: [ INFO] - Train: 27 [ 300/461 ( 65%)] Loss: 3.630607 (3.3166) Loss_single: 2.927575 (2.6070) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.103s, 309.35/s (0.218s, 147.02/s) LR: 5.000e-03 Data: 0.000 (0.120) +2025-04-18 10:15:36,482 - train: [ INFO] - Train: 27 [ 350/461 ( 76%)] Loss: 3.400908 (3.3271) Loss_single: 2.685899 (2.6169) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.112s, 284.92/s (0.217s, 147.52/s) LR: 5.000e-03 Data: 0.000 (0.117) +2025-04-18 10:15:43,279 - train: [ INFO] - Train: 27 [ 400/461 ( 87%)] Loss: 3.143947 (3.3068) Loss_single: 2.434175 (2.5966) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.086s, 372.42/s (0.202s, 158.16/s) LR: 5.000e-03 Data: 0.001 (0.103) +2025-04-18 10:15:54,876 - train: [ INFO] - Train: 27 [ 450/461 ( 98%)] Loss: 3.447300 (3.3208) Loss_single: 2.744608 (2.6114) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.078s, 409.62/s (0.204s, 157.09/s) LR: 5.000e-03 Data: 0.000 (0.105) +2025-04-18 10:15:58,804 - train: [ INFO] - Train: 27 [ 460/461 (100%)] Loss: 2.993572 (3.2911) Loss_single: 2.300448 (2.5831) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.62/s (0.207s, 154.40/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 10:16:05,563 - train: [ INFO] - Eval : 27 Time: 6.433 (6.433) Loss: 2.1997 (2.1997) Acc@1: 43.7500 (43.7500)Acc@5: 68.7500 (68.7500) +2025-04-18 10:16:08,532 - train: [ INFO] - Eval : 27 Time: 0.046 (0.184) Loss: 2.0055 (1.9325) Acc@1: 43.7500 (51.0417)Acc@5: 75.0000 (75.7353) +2025-04-18 10:16:10,313 - train: [ INFO] - Eval : 27 Time: 0.018 (0.136) Loss: 3.0882 (1.9503) Acc@1: 0.0000 (50.4626)Acc@5: 50.0000 (74.9807) +2025-04-18 10:16:20,486 - train: [ INFO] - Train: 28 [ 0/461 ( 0%)] Loss: 3.267232 (3.2672) Loss_single: 2.549075 (2.5491) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.307s, 4.38/s (7.307s, 4.38/s) LR: 5.000e-03 Data: 7.151 (7.151) +2025-04-18 10:16:35,238 - train: [ INFO] - Train: 28 [ 50/461 ( 11%)] Loss: 3.528165 (3.3977) Loss_single: 2.759521 (2.6543) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.277s, 115.41/s (0.390s, 82.01/s) LR: 5.000e-03 Data: 0.177 (0.296) +2025-04-18 10:16:53,691 - train: [ INFO] - Train: 28 [ 100/461 ( 22%)] Loss: 3.150569 (3.3153) Loss_single: 2.442079 (2.5836) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.085s, 375.28/s (0.336s, 95.25/s) LR: 5.000e-03 Data: 0.000 (0.240) +2025-04-18 10:17:07,259 - train: [ INFO] - Train: 28 [ 150/461 ( 33%)] Loss: 3.421101 (3.3418) Loss_single: 2.733513 (2.6210) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.216s, 148.15/s (0.303s, 105.69/s) LR: 5.000e-03 Data: 0.128 (0.208) +2025-04-18 10:17:17,477 - train: [ INFO] - Train: 28 [ 200/461 ( 43%)] Loss: 3.363149 (3.3460) Loss_single: 2.627242 (2.6223) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.081s, 395.50/s (0.275s, 116.50/s) LR: 5.000e-03 Data: 0.001 (0.181) +2025-04-18 10:17:26,670 - train: [ INFO] - Train: 28 [ 250/461 ( 54%)] Loss: 3.338581 (3.3448) Loss_single: 2.653268 (2.6274) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.127s, 252.43/s (0.242s, 132.21/s) LR: 5.000e-03 Data: 0.001 (0.145) +2025-04-18 10:17:37,432 - train: [ INFO] - Train: 28 [ 300/461 ( 65%)] Loss: 3.098207 (3.3096) Loss_single: 2.346873 (2.5874) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.085s, 375.23/s (0.236s, 135.63/s) LR: 5.000e-03 Data: 0.000 (0.138) +2025-04-18 10:17:52,516 - train: [ INFO] - Train: 28 [ 350/461 ( 76%)] Loss: 3.254970 (3.3027) Loss_single: 2.561929 (2.5842) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.079s, 405.69/s (0.243s, 131.81/s) LR: 5.000e-03 Data: 0.000 (0.147) +2025-04-18 10:18:02,637 - train: [ INFO] - Train: 28 [ 400/461 ( 87%)] Loss: 3.240689 (3.2959) Loss_single: 2.550354 (2.5804) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.106s, 300.53/s (0.236s, 135.55/s) LR: 5.000e-03 Data: 0.001 (0.140) +2025-04-18 10:18:09,723 - train: [ INFO] - Train: 28 [ 450/461 ( 98%)] Loss: 3.084051 (3.2747) Loss_single: 2.344654 (2.5569) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.080s, 400.95/s (0.225s, 141.93/s) LR: 5.000e-03 Data: 0.000 (0.126) +2025-04-18 10:18:10,578 - train: [ INFO] - Train: 28 [ 460/461 (100%)] Loss: 3.345385 (3.2811) Loss_single: 2.612478 (2.5619) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.078s, 409.39/s (0.222s, 143.89/s) LR: 5.000e-03 Data: 0.000 (0.123) +2025-04-18 10:18:15,250 - train: [ INFO] - Eval : 28 Time: 4.427 (4.427) Loss: 2.2077 (2.2077) Acc@1: 37.5000 (37.5000)Acc@5: 71.8750 (71.8750) +2025-04-18 10:18:20,265 - train: [ INFO] - Eval : 28 Time: 0.281 (0.181) Loss: 1.9829 (1.9826) Acc@1: 50.0000 (46.8137)Acc@5: 68.7500 (75.8578) +2025-04-18 10:18:27,813 - train: [ INFO] - Eval : 28 Time: 0.014 (0.207) Loss: 2.8265 (1.9949) Acc@1: 50.0000 (46.6076)Acc@5: 50.0000 (74.9807) +2025-04-18 10:18:40,978 - train: [ INFO] - Train: 29 [ 0/461 ( 0%)] Loss: 3.206530 (3.2065) Loss_single: 2.513584 (2.5136) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.790s, 3.64/s (8.790s, 3.64/s) LR: 5.000e-03 Data: 8.641 (8.641) +2025-04-18 10:18:53,634 - train: [ INFO] - Train: 29 [ 50/461 ( 11%)] Loss: 3.013035 (3.1098) Loss_single: 2.317446 (2.4155) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.090s, 354.10/s (0.392s, 81.69/s) LR: 5.000e-03 Data: 0.000 (0.291) +2025-04-18 10:19:05,016 - train: [ INFO] - Train: 29 [ 100/461 ( 22%)] Loss: 3.584563 (3.2680) Loss_single: 2.783638 (2.5382) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.077s, 415.44/s (0.299s, 107.04/s) LR: 5.000e-03 Data: 0.001 (0.205) +2025-04-18 10:19:19,514 - train: [ INFO] - Train: 29 [ 150/461 ( 33%)] Loss: 3.361475 (3.2914) Loss_single: 2.649561 (2.5661) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.085s, 376.50/s (0.281s, 113.87/s) LR: 5.000e-03 Data: 0.000 (0.189) +2025-04-18 10:19:27,766 - train: [ INFO] - Train: 29 [ 200/461 ( 43%)] Loss: 3.287423 (3.2906) Loss_single: 2.576972 (2.5682) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.116s, 276.92/s (0.246s, 130.30/s) LR: 5.000e-03 Data: 0.000 (0.149) +2025-04-18 10:19:34,705 - train: [ INFO] - Train: 29 [ 250/461 ( 54%)] Loss: 3.544105 (3.3329) Loss_single: 2.754460 (2.5993) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.082s, 392.09/s (0.219s, 145.96/s) LR: 5.000e-03 Data: 0.000 (0.119) +2025-04-18 10:19:43,418 - train: [ INFO] - Train: 29 [ 300/461 ( 65%)] Loss: 3.197873 (3.3136) Loss_single: 2.500060 (2.5851) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.1071) Time: 0.079s, 403.31/s (0.199s, 160.77/s) LR: 5.000e-03 Data: 0.001 (0.100) +2025-04-18 10:19:58,318 - train: [ INFO] - Train: 29 [ 350/461 ( 76%)] Loss: 3.261880 (3.3071) Loss_single: 2.481637 (2.5722) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8281) Acc@5: 96.8750 (98.8281) Time: 0.585s, 54.74/s (0.212s, 151.20/s) LR: 5.000e-03 Data: 0.505 (0.114) +2025-04-18 10:20:13,766 - train: [ INFO] - Train: 29 [ 400/461 ( 87%)] Loss: 3.532425 (3.3321) Loss_single: 2.823728 (2.6001) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.135s, 236.42/s (0.224s, 143.17/s) LR: 5.000e-03 Data: 0.056 (0.126) +2025-04-18 10:20:28,998 - train: [ INFO] - Train: 29 [ 450/461 ( 98%)] Loss: 3.457657 (3.3447) Loss_single: 2.770898 (2.6172) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.0625) Time: 0.079s, 407.24/s (0.232s, 137.86/s) LR: 5.000e-03 Data: 0.000 (0.135) +2025-04-18 10:20:31,524 - train: [ INFO] - Train: 29 [ 460/461 (100%)] Loss: 3.352497 (3.3454) Loss_single: 2.648401 (2.6200) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.1477) Time: 0.082s, 390.13/s (0.232s, 137.73/s) LR: 5.000e-03 Data: 0.000 (0.136) +2025-04-18 10:20:38,617 - train: [ INFO] - Eval : 29 Time: 6.861 (6.861) Loss: 2.2373 (2.2373) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 10:20:42,178 - train: [ INFO] - Eval : 29 Time: 0.062 (0.204) Loss: 1.9206 (1.9506) Acc@1: 56.2500 (49.5098)Acc@5: 75.0000 (76.8382) +2025-04-18 10:20:44,084 - train: [ INFO] - Eval : 29 Time: 0.015 (0.150) Loss: 2.8722 (1.9683) Acc@1: 50.0000 (48.8435)Acc@5: 50.0000 (75.7903) +2025-04-18 10:20:52,208 - train: [ INFO] - Train: 30 [ 0/461 ( 0%)] Loss: 2.905569 (2.9056) Loss_single: 2.213292 (2.2133) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.083s, 6.30/s (5.083s, 6.30/s) LR: 5.000e-03 Data: 4.914 (4.914) +2025-04-18 10:21:09,453 - train: [ INFO] - Train: 30 [ 50/461 ( 11%)] Loss: 3.279928 (3.0927) Loss_single: 2.595177 (2.4042) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.166s, 193.32/s (0.372s, 85.98/s) LR: 5.000e-03 Data: 0.000 (0.279) +2025-04-18 10:21:18,989 - train: [ INFO] - Train: 30 [ 100/461 ( 22%)] Loss: 3.220208 (3.1352) Loss_single: 2.522037 (2.4435) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 343.94/s (0.263s, 121.74/s) LR: 5.000e-03 Data: 0.000 (0.168) +2025-04-18 10:21:34,884 - train: [ INFO] - Train: 30 [ 150/461 ( 33%)] Loss: 3.290980 (3.1742) Loss_single: 2.595372 (2.4815) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.522s, 61.33/s (0.264s, 121.38/s) LR: 5.000e-03 Data: 0.390 (0.167) +2025-04-18 10:21:47,424 - train: [ INFO] - Train: 30 [ 200/461 ( 43%)] Loss: 2.923805 (3.1241) Loss_single: 2.225460 (2.4303) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 413.21/s (0.254s, 126.02/s) LR: 5.000e-03 Data: 0.000 (0.158) +2025-04-18 10:21:55,255 - train: [ INFO] - Train: 30 [ 250/461 ( 54%)] Loss: 3.263391 (3.1473) Loss_single: 2.530462 (2.4470) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.102s, 314.27/s (0.231s, 138.26/s) LR: 5.000e-03 Data: 0.000 (0.133) +2025-04-18 10:22:03,323 - train: [ INFO] - Train: 30 [ 300/461 ( 65%)] Loss: 3.219280 (3.1576) Loss_single: 2.447828 (2.4471) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.5536) Acc@5: 96.8750 (99.5536) Time: 0.086s, 370.77/s (0.209s, 152.83/s) LR: 5.000e-03 Data: 0.001 (0.112) +2025-04-18 10:22:16,850 - train: [ INFO] - Train: 30 [ 350/461 ( 76%)] Loss: 3.207757 (3.1639) Loss_single: 2.510438 (2.4550) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.083s, 384.66/s (0.215s, 148.60/s) LR: 5.000e-03 Data: 0.001 (0.117) +2025-04-18 10:22:28,340 - train: [ INFO] - Train: 30 [ 400/461 ( 87%)] Loss: 3.351580 (3.1847) Loss_single: 2.649825 (2.4767) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.248s, 129.07/s (0.215s, 148.64/s) LR: 5.000e-03 Data: 0.166 (0.118) +2025-04-18 10:22:41,366 - train: [ INFO] - Train: 30 [ 450/461 ( 98%)] Loss: 3.243361 (3.1906) Loss_single: 2.551818 (2.4842) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.154s, 207.20/s (0.220s, 145.60/s) LR: 5.000e-03 Data: 0.006 (0.122) +2025-04-18 10:22:42,320 - train: [ INFO] - Train: 30 [ 460/461 (100%)] Loss: 3.622351 (3.2298) Loss_single: 2.797035 (2.5126) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4318) Acc@5: 96.8750 (99.4318) Time: 0.085s, 374.38/s (0.217s, 147.43/s) LR: 5.000e-03 Data: 0.000 (0.119) +2025-04-18 10:22:47,758 - train: [ INFO] - Eval : 30 Time: 5.176 (5.176) Loss: 2.1051 (2.1051) Acc@1: 50.0000 (50.0000)Acc@5: 71.8750 (71.8750) +2025-04-18 10:22:51,371 - train: [ INFO] - Eval : 30 Time: 0.057 (0.172) Loss: 1.9298 (1.8911) Acc@1: 62.5000 (52.3897)Acc@5: 78.1250 (77.5735) +2025-04-18 10:22:54,690 - train: [ INFO] - Eval : 30 Time: 0.014 (0.148) Loss: 3.5260 (1.9181) Acc@1: 0.0000 (51.4649)Acc@5: 50.0000 (76.8311) +2025-04-18 10:23:06,711 - train: [ INFO] - Train: 31 [ 0/461 ( 0%)] Loss: 3.521098 (3.5211) Loss_single: 2.828527 (2.8285) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.805s, 3.63/s (8.805s, 3.63/s) LR: 5.000e-03 Data: 8.681 (8.681) +2025-04-18 10:23:22,187 - train: [ INFO] - Train: 31 [ 50/461 ( 11%)] Loss: 3.025640 (3.2734) Loss_single: 2.331931 (2.5802) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.121s, 265.55/s (0.412s, 77.72/s) LR: 5.000e-03 Data: 0.000 (0.318) +2025-04-18 10:23:33,958 - train: [ INFO] - Train: 31 [ 100/461 ( 22%)] Loss: 3.394976 (3.3139) Loss_single: 2.674264 (2.6116) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.124s, 259.09/s (0.311s, 102.79/s) LR: 5.000e-03 Data: 0.000 (0.213) +2025-04-18 10:23:50,103 - train: [ INFO] - Train: 31 [ 150/461 ( 33%)] Loss: 3.515918 (3.3644) Loss_single: 2.774647 (2.6523) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.077s, 416.46/s (0.303s, 105.62/s) LR: 5.000e-03 Data: 0.000 (0.206) +2025-04-18 10:24:01,857 - train: [ INFO] - Train: 31 [ 200/461 ( 43%)] Loss: 3.235163 (3.3386) Loss_single: 2.539171 (2.6297) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.085s, 377.12/s (0.280s, 114.40/s) LR: 5.000e-03 Data: 0.000 (0.185) +2025-04-18 10:24:15,115 - train: [ INFO] - Train: 31 [ 250/461 ( 54%)] Loss: 2.804435 (3.2495) Loss_single: 2.126790 (2.5459) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.215s, 148.90/s (0.269s, 118.96/s) LR: 5.000e-03 Data: 0.134 (0.172) +2025-04-18 10:24:29,765 - train: [ INFO] - Train: 31 [ 300/461 ( 65%)] Loss: 3.365077 (3.2660) Loss_single: 2.637609 (2.5590) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.080s, 400.44/s (0.269s, 119.07/s) LR: 5.000e-03 Data: 0.000 (0.172) +2025-04-18 10:24:42,279 - train: [ INFO] - Train: 31 [ 350/461 ( 76%)] Loss: 3.169647 (3.2540) Loss_single: 2.482667 (2.5495) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.090s, 355.63/s (0.260s, 122.93/s) LR: 5.000e-03 Data: 0.000 (0.164) +2025-04-18 10:24:53,806 - train: [ INFO] - Train: 31 [ 400/461 ( 87%)] Loss: 3.438997 (3.2746) Loss_single: 2.751308 (2.5719) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.295s, 108.53/s (0.255s, 125.67/s) LR: 5.000e-03 Data: 0.218 (0.159) +2025-04-18 10:25:03,960 - train: [ INFO] - Train: 31 [ 450/461 ( 98%)] Loss: 3.770491 (3.3241) Loss_single: 3.073500 (2.6220) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.083s, 385.42/s (0.249s, 128.63/s) LR: 5.000e-03 Data: 0.000 (0.152) +2025-04-18 10:25:04,862 - train: [ INFO] - Train: 31 [ 460/461 (100%)] Loss: 3.201097 (3.3130) Loss_single: 2.508509 (2.6117) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.081s, 393.63/s (0.245s, 130.48/s) LR: 5.000e-03 Data: 0.000 (0.148) +2025-04-18 10:25:09,943 - train: [ INFO] - Eval : 31 Time: 4.719 (4.719) Loss: 2.1904 (2.1904) Acc@1: 46.8750 (46.8750)Acc@5: 68.7500 (68.7500) +2025-04-18 10:25:21,404 - train: [ INFO] - Eval : 31 Time: 0.036 (0.317) Loss: 1.9640 (1.8504) Acc@1: 62.5000 (54.2279)Acc@5: 71.8750 (80.0245) +2025-04-18 10:25:32,306 - train: [ INFO] - Eval : 31 Time: 0.015 (0.330) Loss: 2.8587 (1.8701) Acc@1: 50.0000 (53.1997)Acc@5: 50.0000 (79.1442) +2025-04-18 10:25:37,615 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-31.pth.tar', 53.19969159599075) + +2025-04-18 10:25:48,188 - train: [ INFO] - Train: 32 [ 0/461 ( 0%)] Loss: 3.310794 (3.3108) Loss_single: 2.615953 (2.6160) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 10.459s, 3.06/s (10.459s, 3.06/s) LR: 5.000e-03 Data: 10.346 (10.346) +2025-04-18 10:26:05,933 - train: [ INFO] - Train: 32 [ 50/461 ( 11%)] Loss: 2.795421 (3.0531) Loss_single: 2.117784 (2.3669) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.090s, 354.10/s (0.483s, 66.19/s) LR: 5.000e-03 Data: 0.000 (0.388) +2025-04-18 10:26:17,598 - train: [ INFO] - Train: 32 [ 100/461 ( 22%)] Loss: 2.894702 (3.0003) Loss_single: 2.208826 (2.3142) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 362.88/s (0.352s, 90.78/s) LR: 5.000e-03 Data: 0.000 (0.258) +2025-04-18 10:26:37,404 - train: [ INFO] - Train: 32 [ 150/461 ( 33%)] Loss: 3.043116 (3.0110) Loss_single: 2.346814 (2.3223) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 386.90/s (0.329s, 97.41/s) LR: 5.000e-03 Data: 0.000 (0.235) +2025-04-18 10:26:53,796 - train: [ INFO] - Train: 32 [ 200/461 ( 43%)] Loss: 3.355114 (3.0798) Loss_single: 2.655717 (2.3890) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 394.35/s (0.308s, 104.01/s) LR: 5.000e-03 Data: 0.000 (0.214) +2025-04-18 10:27:11,391 - train: [ INFO] - Train: 32 [ 250/461 ( 54%)] Loss: 3.339909 (3.1232) Loss_single: 2.616775 (2.4270) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 379.36/s (0.299s, 107.20/s) LR: 5.000e-03 Data: 0.000 (0.204) +2025-04-18 10:27:21,702 - train: [ INFO] - Train: 32 [ 300/461 ( 65%)] Loss: 3.205593 (3.1349) Loss_single: 2.516649 (2.4398) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 397.89/s (0.281s, 113.82/s) LR: 5.000e-03 Data: 0.000 (0.187) +2025-04-18 10:27:38,320 - train: [ INFO] - Train: 32 [ 350/461 ( 76%)] Loss: 3.501212 (3.1807) Loss_single: 2.782823 (2.4827) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 392.10/s (0.276s, 116.11/s) LR: 5.000e-03 Data: 0.001 (0.182) +2025-04-18 10:27:58,620 - train: [ INFO] - Train: 32 [ 400/461 ( 87%)] Loss: 3.507123 (3.2170) Loss_single: 2.781415 (2.5159) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 2.509s, 12.76/s (0.279s, 114.68/s) LR: 5.000e-03 Data: 2.404 (0.185) +2025-04-18 10:28:15,743 - train: [ INFO] - Train: 32 [ 450/461 ( 98%)] Loss: 2.893975 (3.1847) Loss_single: 2.193630 (2.4836) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.103s, 310.17/s (0.278s, 115.27/s) LR: 5.000e-03 Data: 0.000 (0.184) +2025-04-18 10:28:17,240 - train: [ INFO] - Train: 32 [ 460/461 (100%)] Loss: 3.755671 (3.2366) Loss_single: 3.002964 (2.5308) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 96.8750 (99.7159) Time: 0.078s, 411.88/s (0.274s, 116.87/s) LR: 5.000e-03 Data: 0.000 (0.180) +2025-04-18 10:28:27,683 - train: [ INFO] - Eval : 32 Time: 10.111 (10.111) Loss: 2.3378 (2.3378) Acc@1: 43.7500 (43.7500)Acc@5: 62.5000 (62.5000) +2025-04-18 10:28:46,035 - train: [ INFO] - Eval : 32 Time: 0.029 (0.558) Loss: 1.8964 (1.8936) Acc@1: 62.5000 (51.5319)Acc@5: 71.8750 (78.4926) +2025-04-18 10:28:55,925 - train: [ INFO] - Eval : 32 Time: 0.014 (0.468) Loss: 3.2465 (1.9120) Acc@1: 50.0000 (51.2336)Acc@5: 50.0000 (78.0262) +2025-04-18 10:29:09,765 - train: [ INFO] - Train: 33 [ 0/461 ( 0%)] Loss: 3.476375 (3.4764) Loss_single: 2.683011 (2.6830) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 10.080s, 3.17/s (10.080s, 3.17/s) LR: 5.000e-03 Data: 9.973 (9.973) +2025-04-18 10:29:25,618 - train: [ INFO] - Train: 33 [ 50/461 ( 11%)] Loss: 3.289655 (3.3830) Loss_single: 2.528051 (2.6055) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 0.087s, 367.16/s (0.426s, 75.14/s) LR: 5.000e-03 Data: 0.001 (0.338) +2025-04-18 10:29:41,024 - train: [ INFO] - Train: 33 [ 100/461 ( 22%)] Loss: 3.357194 (3.3744) Loss_single: 2.554667 (2.5886) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (98.9583) Time: 0.086s, 370.09/s (0.324s, 98.87/s) LR: 5.000e-03 Data: 0.000 (0.233) +2025-04-18 10:29:56,514 - train: [ INFO] - Train: 33 [ 150/461 ( 33%)] Loss: 3.345742 (3.3672) Loss_single: 2.652354 (2.6045) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (97.6562) Acc@5: 100.0000 (99.2188) Time: 0.081s, 397.33/s (0.292s, 109.64/s) LR: 5.000e-03 Data: 0.001 (0.202) +2025-04-18 10:30:08,969 - train: [ INFO] - Train: 33 [ 200/461 ( 43%)] Loss: 3.181759 (3.3301) Loss_single: 2.501203 (2.5839) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.1250) Acc@5: 100.0000 (99.3750) Time: 0.081s, 395.64/s (0.269s, 119.12/s) LR: 5.000e-03 Data: 0.000 (0.178) +2025-04-18 10:30:24,548 - train: [ INFO] - Train: 33 [ 250/461 ( 54%)] Loss: 3.036467 (3.2812) Loss_single: 2.343920 (2.5439) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.4792) Time: 0.077s, 417.51/s (0.263s, 121.46/s) LR: 5.000e-03 Data: 0.000 (0.172) +2025-04-18 10:30:43,452 - train: [ INFO] - Train: 33 [ 300/461 ( 65%)] Loss: 3.298854 (3.2837) Loss_single: 2.581862 (2.5493) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.2143) Acc@5: 100.0000 (99.5536) Time: 0.081s, 393.59/s (0.264s, 121.34/s) LR: 5.000e-03 Data: 0.000 (0.173) +2025-04-18 10:30:59,542 - train: [ INFO] - Train: 33 [ 350/461 ( 76%)] Loss: 3.361067 (3.2934) Loss_single: 2.664347 (2.5637) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.6094) Time: 0.076s, 420.18/s (0.260s, 123.10/s) LR: 5.000e-03 Data: 0.000 (0.169) +2025-04-18 10:31:10,103 - train: [ INFO] - Train: 33 [ 400/461 ( 87%)] Loss: 3.279631 (3.2919) Loss_single: 2.584589 (2.5660) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6111) Acc@5: 100.0000 (99.6528) Time: 1.939s, 16.51/s (0.249s, 128.43/s) LR: 5.000e-03 Data: 1.781 (0.157) +2025-04-18 10:31:26,564 - train: [ INFO] - Train: 33 [ 450/461 ( 98%)] Loss: 3.059257 (3.2686) Loss_single: 2.334753 (2.5429) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.6875) Time: 0.076s, 419.03/s (0.249s, 128.28/s) LR: 5.000e-03 Data: 0.000 (0.158) +2025-04-18 10:31:27,522 - train: [ INFO] - Train: 33 [ 460/461 (100%)] Loss: 3.143449 (3.2572) Loss_single: 2.413593 (2.5311) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.5795) Acc@5: 100.0000 (99.7159) Time: 0.082s, 392.58/s (0.246s, 130.19/s) LR: 5.000e-03 Data: 0.000 (0.154) +2025-04-18 10:31:36,081 - train: [ INFO] - Eval : 33 Time: 8.293 (8.293) Loss: 2.3409 (2.3409) Acc@1: 40.6250 (40.6250)Acc@5: 75.0000 (75.0000) +2025-04-18 10:31:44,827 - train: [ INFO] - Eval : 33 Time: 0.031 (0.334) Loss: 1.9812 (1.8896) Acc@1: 59.3750 (52.4510)Acc@5: 65.6250 (78.7990) +2025-04-18 10:31:52,836 - train: [ INFO] - Eval : 33 Time: 0.015 (0.305) Loss: 2.9639 (1.9110) Acc@1: 50.0000 (52.0432)Acc@5: 50.0000 (77.7564) +2025-04-18 10:32:06,955 - train: [ INFO] - Train: 34 [ 0/461 ( 0%)] Loss: 2.696986 (2.6970) Loss_single: 2.006644 (2.0066) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 9.159s, 3.49/s (9.159s, 3.49/s) LR: 5.000e-03 Data: 9.048 (9.048) +2025-04-18 10:32:19,119 - train: [ INFO] - Train: 34 [ 50/461 ( 11%)] Loss: 3.334650 (3.0158) Loss_single: 2.657582 (2.3321) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.097s, 329.60/s (0.376s, 85.11/s) LR: 5.000e-03 Data: 0.000 (0.288) +2025-04-18 10:32:34,523 - train: [ INFO] - Train: 34 [ 100/461 ( 22%)] Loss: 3.196906 (3.0762) Loss_single: 2.487621 (2.3839) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 408.34/s (0.302s, 106.00/s) LR: 5.000e-03 Data: 0.000 (0.211) +2025-04-18 10:32:51,235 - train: [ INFO] - Train: 34 [ 150/461 ( 33%)] Loss: 3.271713 (3.1251) Loss_single: 2.580419 (2.4331) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 397.25/s (0.272s, 117.70/s) LR: 5.000e-03 Data: 0.000 (0.181) +2025-04-18 10:33:00,811 - train: [ INFO] - Train: 34 [ 200/461 ( 43%)] Loss: 3.321821 (3.1644) Loss_single: 2.553515 (2.4572) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 96.8750 (99.3750) Time: 0.083s, 383.62/s (0.245s, 130.78/s) LR: 5.000e-03 Data: 0.000 (0.153) +2025-04-18 10:33:07,036 - train: [ INFO] - Train: 34 [ 250/461 ( 54%)] Loss: 3.130603 (3.1588) Loss_single: 2.445561 (2.4552) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.088s, 363.04/s (0.221s, 145.08/s) LR: 5.000e-03 Data: 0.000 (0.124) +2025-04-18 10:33:17,667 - train: [ INFO] - Train: 34 [ 300/461 ( 65%)] Loss: 3.259776 (3.1732) Loss_single: 2.576439 (2.4725) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.081s, 395.36/s (0.201s, 159.32/s) LR: 5.000e-03 Data: 0.000 (0.103) +2025-04-18 10:33:30,970 - train: [ INFO] - Train: 34 [ 350/461 ( 76%)] Loss: 3.149217 (3.1702) Loss_single: 2.452343 (2.4700) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.080s, 402.27/s (0.208s, 153.51/s) LR: 5.000e-03 Data: 0.000 (0.111) +2025-04-18 10:33:44,491 - train: [ INFO] - Train: 34 [ 400/461 ( 87%)] Loss: 3.101950 (3.1626) Loss_single: 2.414885 (2.4639) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.075s, 425.10/s (0.214s, 149.22/s) LR: 5.000e-03 Data: 0.000 (0.118) +2025-04-18 10:33:55,248 - train: [ INFO] - Train: 34 [ 450/461 ( 98%)] Loss: 2.783357 (3.1247) Loss_single: 2.101643 (2.4277) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.110s, 291.43/s (0.214s, 149.43/s) LR: 5.000e-03 Data: 0.000 (0.114) +2025-04-18 10:33:56,191 - train: [ INFO] - Train: 34 [ 460/461 (100%)] Loss: 2.891762 (3.1035) Loss_single: 2.200250 (2.4070) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.084s, 380.77/s (0.212s, 151.27/s) LR: 5.000e-03 Data: 0.000 (0.112) +2025-04-18 10:34:01,985 - train: [ INFO] - Eval : 34 Time: 5.359 (5.359) Loss: 2.2836 (2.2836) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 10:34:11,244 - train: [ INFO] - Eval : 34 Time: 0.062 (0.287) Loss: 1.9099 (1.8970) Acc@1: 59.3750 (53.4314)Acc@5: 71.8750 (78.0025) +2025-04-18 10:34:18,309 - train: [ INFO] - Eval : 34 Time: 0.015 (0.264) Loss: 2.9434 (1.9203) Acc@1: 50.0000 (52.1203)Acc@5: 50.0000 (77.3709) +2025-04-18 10:34:32,207 - train: [ INFO] - Train: 35 [ 0/461 ( 0%)] Loss: 3.206851 (3.2069) Loss_single: 2.498829 (2.4988) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 9.738s, 3.29/s (9.738s, 3.29/s) LR: 5.000e-03 Data: 9.601 (9.601) +2025-04-18 10:34:48,677 - train: [ INFO] - Train: 35 [ 50/461 ( 11%)] Loss: 3.003282 (3.1051) Loss_single: 2.265286 (2.3821) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.120s, 265.88/s (0.437s, 73.30/s) LR: 5.000e-03 Data: 0.000 (0.341) +2025-04-18 10:35:02,580 - train: [ INFO] - Train: 35 [ 100/461 ( 22%)] Loss: 3.602143 (3.2708) Loss_single: 2.911066 (2.5584) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.087s, 366.24/s (0.318s, 100.49/s) LR: 5.000e-03 Data: 0.000 (0.218) +2025-04-18 10:35:11,349 - train: [ INFO] - Train: 35 [ 150/461 ( 33%)] Loss: 3.224048 (3.2591) Loss_single: 2.537771 (2.5532) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.38/s (0.257s, 124.32/s) LR: 5.000e-03 Data: 0.000 (0.158) +2025-04-18 10:35:26,717 - train: [ INFO] - Train: 35 [ 200/461 ( 43%)] Loss: 3.267283 (3.2607) Loss_single: 2.579799 (2.5585) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.092s, 347.92/s (0.255s, 125.30/s) LR: 5.000e-03 Data: 0.001 (0.159) +2025-04-18 10:35:39,548 - train: [ INFO] - Train: 35 [ 250/461 ( 54%)] Loss: 2.953830 (3.2096) Loss_single: 2.266451 (2.5099) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.188s, 170.52/s (0.253s, 126.48/s) LR: 5.000e-03 Data: 0.000 (0.156) +2025-04-18 10:35:46,286 - train: [ INFO] - Train: 35 [ 300/461 ( 65%)] Loss: 3.359943 (3.2311) Loss_single: 2.664509 (2.5320) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.115s, 277.64/s (0.231s, 138.56/s) LR: 5.000e-03 Data: 0.001 (0.130) +2025-04-18 10:35:58,348 - train: [ INFO] - Train: 35 [ 350/461 ( 76%)] Loss: 3.049112 (3.2083) Loss_single: 2.362583 (2.5108) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 1.377s, 23.24/s (0.216s, 148.34/s) LR: 5.000e-03 Data: 1.270 (0.115) +2025-04-18 10:36:10,343 - train: [ INFO] - Train: 35 [ 400/461 ( 87%)] Loss: 3.093493 (3.1956) Loss_single: 2.340250 (2.4918) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.144s, 221.62/s (0.212s, 151.13/s) LR: 5.000e-03 Data: 0.065 (0.111) +2025-04-18 10:36:24,312 - train: [ INFO] - Train: 35 [ 450/461 ( 98%)] Loss: 3.320138 (3.2080) Loss_single: 2.617249 (2.5044) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.090s, 354.23/s (0.216s, 148.06/s) LR: 5.000e-03 Data: 0.000 (0.115) +2025-04-18 10:36:26,411 - train: [ INFO] - Train: 35 [ 460/461 (100%)] Loss: 3.219872 (3.2091) Loss_single: 2.518974 (2.5057) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.079s, 406.65/s (0.216s, 148.22/s) LR: 5.000e-03 Data: 0.000 (0.116) +2025-04-18 10:36:32,097 - train: [ INFO] - Eval : 35 Time: 5.361 (5.361) Loss: 2.2140 (2.2140) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 10:36:36,990 - train: [ INFO] - Eval : 35 Time: 0.422 (0.201) Loss: 1.9941 (1.9288) Acc@1: 59.3750 (52.1446)Acc@5: 65.6250 (78.3088) +2025-04-18 10:36:39,181 - train: [ INFO] - Eval : 35 Time: 0.178 (0.150) Loss: 3.3771 (1.9533) Acc@1: 50.0000 (51.7733)Acc@5: 50.0000 (77.4094) +2025-04-18 10:36:54,885 - train: [ INFO] - Train: 36 [ 0/461 ( 0%)] Loss: 3.344144 (3.3441) Loss_single: 2.564523 (2.5645) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 11.723s, 2.73/s (11.723s, 2.73/s) LR: 5.000e-03 Data: 11.558 (11.558) +2025-04-18 10:37:10,190 - train: [ INFO] - Train: 36 [ 50/461 ( 11%)] Loss: 3.277020 (3.3106) Loss_single: 2.592180 (2.5784) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.198s, 161.27/s (0.473s, 67.59/s) LR: 5.000e-03 Data: 0.102 (0.378) +2025-04-18 10:37:25,133 - train: [ INFO] - Train: 36 [ 100/461 ( 22%)] Loss: 3.204004 (3.2751) Loss_single: 2.503744 (2.5535) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.081s, 394.92/s (0.361s, 88.57/s) LR: 5.000e-03 Data: 0.000 (0.271) +2025-04-18 10:37:33,777 - train: [ INFO] - Train: 36 [ 150/461 ( 33%)] Loss: 3.138121 (3.2408) Loss_single: 2.440057 (2.5251) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.106s, 303.11/s (0.296s, 108.02/s) LR: 5.000e-03 Data: 0.000 (0.203) +2025-04-18 10:37:40,755 - train: [ INFO] - Train: 36 [ 200/461 ( 43%)] Loss: 3.657103 (3.3241) Loss_single: 2.904957 (2.6011) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.108s, 295.52/s (0.254s, 125.84/s) LR: 5.000e-03 Data: 0.001 (0.156) +2025-04-18 10:37:48,519 - train: [ INFO] - Train: 36 [ 250/461 ( 54%)] Loss: 3.063275 (3.2806) Loss_single: 2.371887 (2.5629) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.095s, 336.90/s (0.228s, 140.28/s) LR: 5.000e-03 Data: 0.001 (0.127) +2025-04-18 10:38:01,857 - train: [ INFO] - Train: 36 [ 300/461 ( 65%)] Loss: 3.667444 (3.3359) Loss_single: 2.971213 (2.6212) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.080s, 397.96/s (0.225s, 142.02/s) LR: 5.000e-03 Data: 0.000 (0.125) +2025-04-18 10:38:12,202 - train: [ INFO] - Train: 36 [ 350/461 ( 76%)] Loss: 3.028223 (3.2974) Loss_single: 2.341398 (2.5862) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.079s, 403.06/s (0.217s, 147.57/s) LR: 5.000e-03 Data: 0.000 (0.118) +2025-04-18 10:38:26,020 - train: [ INFO] - Train: 36 [ 400/461 ( 87%)] Loss: 2.794728 (3.2416) Loss_single: 2.116742 (2.5341) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.332s, 96.37/s (0.220s, 145.37/s) LR: 5.000e-03 Data: 0.250 (0.121) +2025-04-18 10:38:33,727 - train: [ INFO] - Train: 36 [ 450/461 ( 98%)] Loss: 3.250271 (3.2424) Loss_single: 2.497723 (2.5304) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 100.0000 (99.6875) Time: 0.079s, 406.34/s (0.213s, 150.55/s) LR: 5.000e-03 Data: 0.000 (0.112) +2025-04-18 10:38:34,634 - train: [ INFO] - Train: 36 [ 460/461 (100%)] Loss: 3.413803 (3.2580) Loss_single: 2.707733 (2.5466) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.7159) Time: 0.077s, 415.67/s (0.210s, 152.46/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 10:38:40,236 - train: [ INFO] - Eval : 36 Time: 5.337 (5.337) Loss: 2.1663 (2.1663) Acc@1: 50.0000 (50.0000)Acc@5: 68.7500 (68.7500) +2025-04-18 10:38:51,570 - train: [ INFO] - Eval : 36 Time: 0.044 (0.327) Loss: 1.9263 (1.9232) Acc@1: 56.2500 (51.4706)Acc@5: 71.8750 (77.4510) +2025-04-18 10:39:02,098 - train: [ INFO] - Eval : 36 Time: 0.018 (0.332) Loss: 2.8826 (1.9498) Acc@1: 50.0000 (50.1928)Acc@5: 50.0000 (76.7926) +2025-04-18 10:39:15,104 - train: [ INFO] - Train: 37 [ 0/461 ( 0%)] Loss: 2.879513 (2.8795) Loss_single: 2.187407 (2.1874) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.423s, 3.80/s (8.423s, 3.80/s) LR: 5.000e-03 Data: 8.283 (8.283) +2025-04-18 10:39:24,100 - train: [ INFO] - Train: 37 [ 50/461 ( 11%)] Loss: 2.868283 (2.8739) Loss_single: 2.183740 (2.1856) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 405.26/s (0.316s, 101.27/s) LR: 5.000e-03 Data: 0.000 (0.210) +2025-04-18 10:39:30,170 - train: [ INFO] - Train: 37 [ 100/461 ( 22%)] Loss: 2.939574 (2.8958) Loss_single: 2.222154 (2.1978) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 410.16/s (0.213s, 150.37/s) LR: 5.000e-03 Data: 0.000 (0.106) +2025-04-18 10:39:35,780 - train: [ INFO] - Train: 37 [ 150/461 ( 33%)] Loss: 3.520872 (3.0521) Loss_single: 2.786252 (2.3449) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.130s, 245.31/s (0.179s, 178.72/s) LR: 5.000e-03 Data: 0.000 (0.071) +2025-04-18 10:39:42,985 - train: [ INFO] - Train: 37 [ 200/461 ( 43%)] Loss: 3.359435 (3.1135) Loss_single: 2.613294 (2.3986) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.079s, 403.60/s (0.160s, 199.66/s) LR: 5.000e-03 Data: 0.001 (0.054) +2025-04-18 10:39:54,572 - train: [ INFO] - Train: 37 [ 250/461 ( 54%)] Loss: 2.859251 (3.0712) Loss_single: 2.165704 (2.3598) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.144s, 222.74/s (0.165s, 193.50/s) LR: 5.000e-03 Data: 0.001 (0.060) +2025-04-18 10:40:02,656 - train: [ INFO] - Train: 37 [ 300/461 ( 65%)] Loss: 3.148026 (3.0821) Loss_single: 2.463130 (2.3745) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.083s, 385.93/s (0.162s, 197.13/s) LR: 5.000e-03 Data: 0.000 (0.057) +2025-04-18 10:40:16,185 - train: [ INFO] - Train: 37 [ 350/461 ( 76%)] Loss: 3.323538 (3.1123) Loss_single: 2.611651 (2.4042) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.081s, 394.39/s (0.176s, 181.36/s) LR: 5.000e-03 Data: 0.001 (0.073) +2025-04-18 10:40:31,511 - train: [ INFO] - Train: 37 [ 400/461 ( 87%)] Loss: 3.064545 (3.1070) Loss_single: 2.379561 (2.4014) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.563s, 56.86/s (0.191s, 167.43/s) LR: 5.000e-03 Data: 0.475 (0.089) +2025-04-18 10:40:44,469 - train: [ INFO] - Train: 37 [ 450/461 ( 98%)] Loss: 3.223677 (3.1187) Loss_single: 2.543908 (2.4157) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.499s, 64.14/s (0.198s, 161.43/s) LR: 5.000e-03 Data: 0.407 (0.097) +2025-04-18 10:40:47,097 - train: [ INFO] - Train: 37 [ 460/461 (100%)] Loss: 3.454563 (3.1492) Loss_single: 2.772868 (2.4482) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.09/s (0.200s, 160.32/s) LR: 5.000e-03 Data: 0.000 (0.099) +2025-04-18 10:40:55,234 - train: [ INFO] - Eval : 37 Time: 7.799 (7.799) Loss: 2.2456 (2.2456) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 10:41:10,139 - train: [ INFO] - Eval : 37 Time: 0.214 (0.445) Loss: 1.9142 (1.9071) Acc@1: 62.5000 (52.6348)Acc@5: 71.8750 (78.4926) +2025-04-18 10:41:11,894 - train: [ INFO] - Eval : 37 Time: 0.017 (0.298) Loss: 3.3659 (1.9257) Acc@1: 0.0000 (51.7733)Acc@5: 50.0000 (77.2938) +2025-04-18 10:41:24,923 - train: [ INFO] - Train: 38 [ 0/461 ( 0%)] Loss: 3.243713 (3.2437) Loss_single: 2.560241 (2.5602) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 9.521s, 3.36/s (9.521s, 3.36/s) LR: 5.000e-03 Data: 9.360 (9.360) +2025-04-18 10:41:38,256 - train: [ INFO] - Train: 38 [ 50/461 ( 11%)] Loss: 3.068219 (3.1560) Loss_single: 2.359446 (2.4598) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.204s, 156.99/s (0.405s, 79.06/s) LR: 5.000e-03 Data: 0.088 (0.305) +2025-04-18 10:41:46,260 - train: [ INFO] - Train: 38 [ 100/461 ( 22%)] Loss: 3.694319 (3.3354) Loss_single: 2.887995 (2.6026) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.118s, 272.25/s (0.271s, 118.19/s) LR: 5.000e-03 Data: 0.000 (0.168) +2025-04-18 10:42:00,314 - train: [ INFO] - Train: 38 [ 150/461 ( 33%)] Loss: 3.115887 (3.2805) Loss_single: 2.429026 (2.5592) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.123s, 260.55/s (0.256s, 125.17/s) LR: 5.000e-03 Data: 0.041 (0.157) +2025-04-18 10:42:12,787 - train: [ INFO] - Train: 38 [ 200/461 ( 43%)] Loss: 3.248478 (3.2741) Loss_single: 2.554957 (2.5583) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.083s, 385.64/s (0.249s, 128.70/s) LR: 5.000e-03 Data: 0.000 (0.151) +2025-04-18 10:42:25,816 - train: [ INFO] - Train: 38 [ 250/461 ( 54%)] Loss: 3.595511 (3.3277) Loss_single: 2.822371 (2.6023) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.379s, 84.44/s (0.243s, 131.78/s) LR: 5.000e-03 Data: 0.274 (0.147) +2025-04-18 10:42:41,095 - train: [ INFO] - Train: 38 [ 300/461 ( 65%)] Loss: 2.993852 (3.2800) Loss_single: 2.313501 (2.5611) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.1071) Time: 0.078s, 408.30/s (0.250s, 127.98/s) LR: 5.000e-03 Data: 0.000 (0.155) +2025-04-18 10:43:00,236 - train: [ INFO] - Train: 38 [ 350/461 ( 76%)] Loss: 2.879090 (3.2299) Loss_single: 2.199221 (2.5158) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.081s, 396.08/s (0.261s, 122.59/s) LR: 5.000e-03 Data: 0.000 (0.167) +2025-04-18 10:43:14,849 - train: [ INFO] - Train: 38 [ 400/461 ( 87%)] Loss: 2.734236 (3.1748) Loss_single: 2.048967 (2.4640) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.3056) Time: 1.676s, 19.10/s (0.263s, 121.57/s) LR: 5.000e-03 Data: 1.536 (0.169) +2025-04-18 10:43:33,486 - train: [ INFO] - Train: 38 [ 450/461 ( 98%)] Loss: 3.094803 (3.1668) Loss_single: 2.403806 (2.4580) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.086s, 370.03/s (0.272s, 117.81/s) LR: 5.000e-03 Data: 0.000 (0.178) +2025-04-18 10:43:35,896 - train: [ INFO] - Train: 38 [ 460/461 (100%)] Loss: 2.953798 (3.1474) Loss_single: 2.268831 (2.4408) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.4318) Time: 0.079s, 407.50/s (0.271s, 118.22/s) LR: 5.000e-03 Data: 0.000 (0.178) +2025-04-18 10:43:44,548 - train: [ INFO] - Eval : 38 Time: 8.286 (8.286) Loss: 2.3577 (2.3577) Acc@1: 43.7500 (43.7500)Acc@5: 62.5000 (62.5000) +2025-04-18 10:43:54,676 - train: [ INFO] - Eval : 38 Time: 0.051 (0.361) Loss: 2.0920 (1.9274) Acc@1: 53.1250 (52.0833)Acc@5: 68.7500 (77.2059) +2025-04-18 10:44:04,945 - train: [ INFO] - Eval : 38 Time: 0.016 (0.350) Loss: 2.8695 (1.9456) Acc@1: 50.0000 (51.5806)Acc@5: 50.0000 (76.3300) +2025-04-18 10:44:19,052 - train: [ INFO] - Train: 39 [ 0/461 ( 0%)] Loss: 3.183985 (3.1840) Loss_single: 2.499187 (2.4992) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 10.064s, 3.18/s (10.064s, 3.18/s) LR: 5.000e-03 Data: 9.938 (9.938) +2025-04-18 10:44:31,434 - train: [ INFO] - Train: 39 [ 50/461 ( 11%)] Loss: 3.078552 (3.1313) Loss_single: 2.371642 (2.4354) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 333.10/s (0.396s, 80.82/s) LR: 5.000e-03 Data: 0.000 (0.298) +2025-04-18 10:44:48,623 - train: [ INFO] - Train: 39 [ 100/461 ( 22%)] Loss: 2.968271 (3.0769) Loss_single: 2.271106 (2.3806) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.101s, 316.83/s (0.334s, 95.74/s) LR: 5.000e-03 Data: 0.001 (0.236) +2025-04-18 10:44:57,916 - train: [ INFO] - Train: 39 [ 150/461 ( 33%)] Loss: 2.886595 (3.0294) Loss_single: 2.209870 (2.3380) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.119s, 269.76/s (0.279s, 114.74/s) LR: 5.000e-03 Data: 0.000 (0.177) +2025-04-18 10:45:03,096 - train: [ INFO] - Train: 39 [ 200/461 ( 43%)] Loss: 3.285134 (3.0805) Loss_single: 2.589495 (2.3883) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.110s, 291.18/s (0.235s, 136.10/s) LR: 5.000e-03 Data: 0.000 (0.133) +2025-04-18 10:45:08,792 - train: [ INFO] - Train: 39 [ 250/461 ( 54%)] Loss: 3.298124 (3.1168) Loss_single: 2.578834 (2.4200) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.118s, 271.04/s (0.211s, 151.85/s) LR: 5.000e-03 Data: 0.000 (0.106) +2025-04-18 10:45:16,510 - train: [ INFO] - Train: 39 [ 300/461 ( 65%)] Loss: 2.807681 (3.0726) Loss_single: 2.117707 (2.3768) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 397.82/s (0.193s, 166.21/s) LR: 5.000e-03 Data: 0.000 (0.089) +2025-04-18 10:45:31,689 - train: [ INFO] - Train: 39 [ 350/461 ( 76%)] Loss: 3.033796 (3.0678) Loss_single: 2.356361 (2.3743) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.169s, 189.41/s (0.205s, 155.95/s) LR: 5.000e-03 Data: 0.085 (0.103) +2025-04-18 10:45:46,829 - train: [ INFO] - Train: 39 [ 400/461 ( 87%)] Loss: 2.848661 (3.0434) Loss_single: 2.167942 (2.3513) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 335.84/s (0.217s, 147.30/s) LR: 5.000e-03 Data: 0.001 (0.117) +2025-04-18 10:45:59,700 - train: [ INFO] - Train: 39 [ 450/461 ( 98%)] Loss: 3.231095 (3.0622) Loss_single: 2.466100 (2.3628) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.735s, 43.56/s (0.221s, 144.75/s) LR: 5.000e-03 Data: 0.630 (0.122) +2025-04-18 10:46:01,708 - train: [ INFO] - Train: 39 [ 460/461 (100%)] Loss: 2.958109 (3.0527) Loss_single: 2.270408 (2.3544) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.085s, 378.10/s (0.221s, 145.12/s) LR: 5.000e-03 Data: 0.000 (0.122) +2025-04-18 10:46:12,395 - train: [ INFO] - Eval : 39 Time: 10.272 (10.272) Loss: 2.2805 (2.2805) Acc@1: 40.6250 (40.6250)Acc@5: 71.8750 (71.8750) +2025-04-18 10:46:26,507 - train: [ INFO] - Eval : 39 Time: 0.658 (0.478) Loss: 2.1027 (1.9070) Acc@1: 53.1250 (53.0637)Acc@5: 65.6250 (78.1250) +2025-04-18 10:46:30,076 - train: [ INFO] - Eval : 39 Time: 0.017 (0.341) Loss: 2.6986 (1.9285) Acc@1: 50.0000 (51.8119)Acc@5: 50.0000 (77.2167) +2025-04-18 10:46:43,154 - train: [ INFO] - Train: 40 [ 0/461 ( 0%)] Loss: 3.173249 (3.1732) Loss_single: 2.482688 (2.4827) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.325s, 4.37/s (7.325s, 4.37/s) LR: 5.000e-03 Data: 7.153 (7.153) +2025-04-18 10:46:49,257 - train: [ INFO] - Train: 40 [ 50/461 ( 11%)] Loss: 3.125940 (3.1496) Loss_single: 2.395372 (2.4390) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 419.87/s (0.263s, 121.84/s) LR: 5.000e-03 Data: 0.000 (0.141) +2025-04-18 10:47:00,825 - train: [ INFO] - Train: 40 [ 100/461 ( 22%)] Loss: 3.357604 (3.2189) Loss_single: 2.556505 (2.4782) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.079s, 402.90/s (0.218s, 146.88/s) LR: 5.000e-03 Data: 0.000 (0.111) +2025-04-18 10:47:10,941 - train: [ INFO] - Train: 40 [ 150/461 ( 33%)] Loss: 3.194721 (3.2129) Loss_single: 2.506910 (2.4854) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.083s, 384.52/s (0.199s, 160.97/s) LR: 5.000e-03 Data: 0.000 (0.094) +2025-04-18 10:47:26,715 - train: [ INFO] - Train: 40 [ 200/461 ( 43%)] Loss: 3.170608 (3.2044) Loss_single: 2.406253 (2.4695) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 96.8750 (99.3750) Time: 0.116s, 276.49/s (0.223s, 143.52/s) LR: 5.000e-03 Data: 0.001 (0.121) +2025-04-18 10:47:42,059 - train: [ INFO] - Train: 40 [ 250/461 ( 54%)] Loss: 3.014210 (3.1727) Loss_single: 2.331349 (2.4465) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.138s, 232.68/s (0.235s, 136.26/s) LR: 5.000e-03 Data: 0.001 (0.133) +2025-04-18 10:47:48,581 - train: [ INFO] - Train: 40 [ 300/461 ( 65%)] Loss: 2.892098 (3.1326) Loss_single: 2.208339 (2.4125) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.088s, 363.05/s (0.215s, 148.72/s) LR: 5.000e-03 Data: 0.000 (0.111) +2025-04-18 10:47:58,825 - train: [ INFO] - Train: 40 [ 350/461 ( 76%)] Loss: 3.227304 (3.1445) Loss_single: 2.539361 (2.4283) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.082s, 389.61/s (0.198s, 161.42/s) LR: 5.000e-03 Data: 0.001 (0.095) +2025-04-18 10:48:13,733 - train: [ INFO] - Train: 40 [ 400/461 ( 87%)] Loss: 3.063710 (3.1355) Loss_single: 2.320462 (2.4164) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.098s, 326.65/s (0.206s, 155.21/s) LR: 5.000e-03 Data: 0.000 (0.104) +2025-04-18 10:48:25,137 - train: [ INFO] - Train: 40 [ 450/461 ( 98%)] Loss: 3.290407 (3.1510) Loss_single: 2.585602 (2.4333) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.547s, 58.54/s (0.204s, 156.54/s) LR: 5.000e-03 Data: 0.452 (0.102) +2025-04-18 10:48:27,081 - train: [ INFO] - Train: 40 [ 460/461 (100%)] Loss: 3.014090 (3.1385) Loss_single: 2.328023 (2.4237) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.076s, 420.31/s (0.204s, 156.82/s) LR: 5.000e-03 Data: 0.000 (0.102) +2025-04-18 10:48:33,520 - train: [ INFO] - Eval : 40 Time: 6.161 (6.161) Loss: 2.1074 (2.1074) Acc@1: 53.1250 (53.1250)Acc@5: 71.8750 (71.8750) +2025-04-18 10:48:39,221 - train: [ INFO] - Eval : 40 Time: 0.028 (0.233) Loss: 1.8394 (1.8964) Acc@1: 53.1250 (52.7574)Acc@5: 78.1250 (78.7990) +2025-04-18 10:48:47,960 - train: [ INFO] - Eval : 40 Time: 0.020 (0.251) Loss: 2.8790 (1.9084) Acc@1: 50.0000 (52.0817)Acc@5: 50.0000 (77.8335) +2025-04-18 10:48:58,697 - train: [ INFO] - Train: 41 [ 0/461 ( 0%)] Loss: 3.161740 (3.1617) Loss_single: 2.458972 (2.4590) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.477s, 4.94/s (6.477s, 4.94/s) LR: 5.000e-03 Data: 6.327 (6.327) +2025-04-18 10:49:12,599 - train: [ INFO] - Train: 41 [ 50/461 ( 11%)] Loss: 3.164976 (3.1634) Loss_single: 2.398090 (2.4285) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.083s, 384.60/s (0.344s, 93.14/s) LR: 5.000e-03 Data: 0.000 (0.242) +2025-04-18 10:49:19,622 - train: [ INFO] - Train: 41 [ 100/461 ( 22%)] Loss: 2.922112 (3.0829) Loss_single: 2.240824 (2.3660) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.118s, 270.27/s (0.240s, 133.30/s) LR: 5.000e-03 Data: 0.000 (0.127) +2025-04-18 10:49:25,249 - train: [ INFO] - Train: 41 [ 150/461 ( 33%)] Loss: 3.212909 (3.1154) Loss_single: 2.497047 (2.3987) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.103s, 309.48/s (0.198s, 161.93/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-18 10:49:33,110 - train: [ INFO] - Train: 41 [ 200/461 ( 43%)] Loss: 2.907319 (3.0738) Loss_single: 2.225475 (2.3641) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.110s, 291.76/s (0.172s, 186.48/s) LR: 5.000e-03 Data: 0.000 (0.064) +2025-04-18 10:49:41,763 - train: [ INFO] - Train: 41 [ 250/461 ( 54%)] Loss: 3.432936 (3.1337) Loss_single: 2.628374 (2.4081) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.080s, 401.93/s (0.168s, 190.37/s) LR: 5.000e-03 Data: 0.000 (0.063) +2025-04-18 10:49:52,751 - train: [ INFO] - Train: 41 [ 300/461 ( 65%)] Loss: 3.000177 (3.1146) Loss_single: 2.323565 (2.3960) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.127s, 252.85/s (0.172s, 185.97/s) LR: 5.000e-03 Data: 0.005 (0.066) +2025-04-18 10:50:09,389 - train: [ INFO] - Train: 41 [ 350/461 ( 76%)] Loss: 3.172126 (3.1218) Loss_single: 2.462853 (2.4044) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.177s, 180.73/s (0.190s, 168.84/s) LR: 5.000e-03 Data: 0.095 (0.086) +2025-04-18 10:50:19,134 - train: [ INFO] - Train: 41 [ 400/461 ( 87%)] Loss: 3.189365 (3.1293) Loss_single: 2.433305 (2.4076) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (99.6528) Time: 0.078s, 411.40/s (0.190s, 168.79/s) LR: 5.000e-03 Data: 0.000 (0.086) +2025-04-18 10:50:30,116 - train: [ INFO] - Train: 41 [ 450/461 ( 98%)] Loss: 3.170088 (3.1334) Loss_single: 2.415498 (2.4084) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (99.6875) Time: 0.084s, 379.08/s (0.188s, 170.39/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-18 10:50:31,200 - train: [ INFO] - Train: 41 [ 460/461 (100%)] Loss: 3.386046 (3.1563) Loss_single: 2.630002 (2.4285) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8636) Acc@5: 100.0000 (99.7159) Time: 0.078s, 412.38/s (0.186s, 172.48/s) LR: 5.000e-03 Data: 0.000 (0.083) +2025-04-18 10:50:40,281 - train: [ INFO] - Eval : 41 Time: 8.719 (8.719) Loss: 2.2204 (2.2204) Acc@1: 46.8750 (46.8750)Acc@5: 81.2500 (81.2500) +2025-04-18 10:50:45,216 - train: [ INFO] - Eval : 41 Time: 0.366 (0.260) Loss: 1.9952 (1.9122) Acc@1: 56.2500 (51.3480)Acc@5: 71.8750 (77.6348) +2025-04-18 10:50:50,376 - train: [ INFO] - Eval : 41 Time: 0.016 (0.229) Loss: 3.3414 (1.9166) Acc@1: 50.0000 (51.1565)Acc@5: 50.0000 (77.1010) +2025-04-18 10:51:05,069 - train: [ INFO] - Train: 42 [ 0/461 ( 0%)] Loss: 3.000298 (3.0003) Loss_single: 2.326801 (2.3268) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 11.948s, 2.68/s (11.948s, 2.68/s) LR: 5.000e-03 Data: 11.780 (11.780) +2025-04-18 10:51:23,010 - train: [ INFO] - Train: 42 [ 50/461 ( 11%)] Loss: 3.296025 (3.1482) Loss_single: 2.604154 (2.4655) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 341.79/s (0.508s, 63.01/s) LR: 5.000e-03 Data: 0.000 (0.408) +2025-04-18 10:51:34,008 - train: [ INFO] - Train: 42 [ 100/461 ( 22%)] Loss: 3.332999 (3.2098) Loss_single: 2.634690 (2.5219) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.085s, 375.37/s (0.350s, 91.41/s) LR: 5.000e-03 Data: 0.001 (0.253) +2025-04-18 10:51:48,646 - train: [ INFO] - Train: 42 [ 150/461 ( 33%)] Loss: 3.217755 (3.2118) Loss_single: 2.450182 (2.5040) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.082s, 389.91/s (0.319s, 100.41/s) LR: 5.000e-03 Data: 0.001 (0.225) +2025-04-18 10:51:57,336 - train: [ INFO] - Train: 42 [ 200/461 ( 43%)] Loss: 3.186127 (3.2066) Loss_single: 2.410526 (2.4853) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 96.8750 (98.7500) Time: 0.103s, 310.92/s (0.277s, 115.57/s) LR: 5.000e-03 Data: 0.000 (0.178) +2025-04-18 10:52:02,757 - train: [ INFO] - Train: 42 [ 250/461 ( 54%)] Loss: 2.924524 (3.1596) Loss_single: 2.251901 (2.4464) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.111s, 287.33/s (0.243s, 131.58/s) LR: 5.000e-03 Data: 0.000 (0.143) +2025-04-18 10:52:08,478 - train: [ INFO] - Train: 42 [ 300/461 ( 65%)] Loss: 3.251896 (3.1728) Loss_single: 2.461358 (2.4485) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.1071) Time: 0.168s, 190.45/s (0.222s, 144.35/s) LR: 5.000e-03 Data: 0.000 (0.119) +2025-04-18 10:52:14,416 - train: [ INFO] - Train: 42 [ 350/461 ( 76%)] Loss: 3.218282 (3.1785) Loss_single: 2.431888 (2.4464) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8281) Acc@5: 96.8750 (98.8281) Time: 0.132s, 241.92/s (0.207s, 154.65/s) LR: 5.000e-03 Data: 0.000 (0.102) +2025-04-18 10:52:19,851 - train: [ INFO] - Train: 42 [ 400/461 ( 87%)] Loss: 2.976081 (3.1560) Loss_single: 2.282400 (2.4282) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.105s, 305.41/s (0.195s, 164.48/s) LR: 5.000e-03 Data: 0.000 (0.090) +2025-04-18 10:52:25,384 - train: [ INFO] - Train: 42 [ 450/461 ( 98%)] Loss: 3.360457 (3.1764) Loss_single: 2.666360 (2.4520) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.0625) Time: 0.094s, 338.87/s (0.185s, 172.81/s) LR: 5.000e-03 Data: 0.000 (0.080) +2025-04-18 10:52:26,433 - train: [ INFO] - Train: 42 [ 460/461 (100%)] Loss: 2.765256 (3.1391) Loss_single: 2.088832 (2.4190) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.1477) Time: 0.084s, 379.78/s (0.183s, 174.52/s) LR: 5.000e-03 Data: 0.000 (0.078) +2025-04-18 10:52:34,422 - train: [ INFO] - Eval : 42 Time: 7.705 (7.705) Loss: 2.1109 (2.1109) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 10:52:39,466 - train: [ INFO] - Eval : 42 Time: 0.046 (0.250) Loss: 1.9947 (1.9093) Acc@1: 59.3750 (52.5735)Acc@5: 75.0000 (78.4314) +2025-04-18 10:52:41,410 - train: [ INFO] - Eval : 42 Time: 0.014 (0.179) Loss: 3.3089 (1.9317) Acc@1: 50.0000 (51.8504)Acc@5: 50.0000 (77.7564) +2025-04-18 10:52:48,921 - train: [ INFO] - Train: 43 [ 0/461 ( 0%)] Loss: 3.158286 (3.1583) Loss_single: 2.403079 (2.4031) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 4.589s, 6.97/s (4.589s, 6.97/s) LR: 5.000e-03 Data: 4.383 (4.383) +2025-04-18 10:52:56,141 - train: [ INFO] - Train: 43 [ 50/461 ( 11%)] Loss: 3.221929 (3.1901) Loss_single: 2.492616 (2.4478) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.089s, 358.17/s (0.199s, 160.98/s) LR: 5.000e-03 Data: 0.001 (0.092) +2025-04-18 10:53:02,187 - train: [ INFO] - Train: 43 [ 100/461 ( 22%)] Loss: 2.756407 (3.0455) Loss_single: 2.078436 (2.3247) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.082s, 391.62/s (0.160s, 200.56/s) LR: 5.000e-03 Data: 0.000 (0.047) +2025-04-18 10:53:07,594 - train: [ INFO] - Train: 43 [ 150/461 ( 33%)] Loss: 3.128505 (3.0663) Loss_single: 2.439888 (2.3535) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.117s, 273.51/s (0.142s, 224.82/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-18 10:53:13,414 - train: [ INFO] - Train: 43 [ 200/461 ( 43%)] Loss: 3.324791 (3.1180) Loss_single: 2.569883 (2.3968) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.207s, 154.26/s (0.136s, 235.79/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-18 10:53:18,686 - train: [ INFO] - Train: 43 [ 250/461 ( 54%)] Loss: 3.184645 (3.1291) Loss_single: 2.480669 (2.4108) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.139s, 230.57/s (0.129s, 247.31/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-18 10:53:24,514 - train: [ INFO] - Train: 43 [ 300/461 ( 65%)] Loss: 2.927204 (3.1003) Loss_single: 2.242383 (2.3867) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.137s, 234.17/s (0.127s, 252.05/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-18 10:53:30,023 - train: [ INFO] - Train: 43 [ 350/461 ( 76%)] Loss: 2.962204 (3.0830) Loss_single: 2.238631 (2.3682) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.103s, 311.69/s (0.124s, 257.05/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 10:53:35,683 - train: [ INFO] - Train: 43 [ 400/461 ( 87%)] Loss: 3.088157 (3.0836) Loss_single: 2.403589 (2.3721) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.118s, 270.97/s (0.123s, 260.29/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:53:41,673 - train: [ INFO] - Train: 43 [ 450/461 ( 98%)] Loss: 3.063819 (3.0816) Loss_single: 2.362583 (2.3712) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.076s, 418.81/s (0.120s, 265.79/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 10:53:42,527 - train: [ INFO] - Train: 43 [ 460/461 (100%)] Loss: 2.996897 (3.0739) Loss_single: 2.307963 (2.3654) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.088s, 363.55/s (0.120s, 267.51/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 10:53:52,278 - train: [ INFO] - Eval : 43 Time: 9.285 (9.285) Loss: 2.1332 (2.1332) Acc@1: 43.7500 (43.7500)Acc@5: 68.7500 (68.7500) +2025-04-18 10:53:57,383 - train: [ INFO] - Eval : 43 Time: 0.067 (0.282) Loss: 1.9049 (1.8843) Acc@1: 50.0000 (51.8995)Acc@5: 68.7500 (79.4118) +2025-04-18 10:53:59,694 - train: [ INFO] - Eval : 43 Time: 0.017 (0.204) Loss: 3.4247 (1.9050) Acc@1: 50.0000 (51.8504)Acc@5: 50.0000 (78.4117) +2025-04-18 10:54:07,713 - train: [ INFO] - Train: 44 [ 0/461 ( 0%)] Loss: 3.073564 (3.0736) Loss_single: 2.383953 (2.3840) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.838s, 6.61/s (4.838s, 6.61/s) LR: 5.000e-03 Data: 4.580 (4.580) +2025-04-18 10:54:13,782 - train: [ INFO] - Train: 44 [ 50/461 ( 11%)] Loss: 2.882547 (2.9781) Loss_single: 2.194268 (2.2891) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 382.31/s (0.212s, 150.76/s) LR: 5.000e-03 Data: 0.000 (0.093) +2025-04-18 10:54:19,335 - train: [ INFO] - Train: 44 [ 100/461 ( 22%)] Loss: 3.187039 (3.0477) Loss_single: 2.493531 (2.3573) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.096s, 334.81/s (0.162s, 197.73/s) LR: 5.000e-03 Data: 0.000 (0.047) +2025-04-18 10:54:24,604 - train: [ INFO] - Train: 44 [ 150/461 ( 33%)] Loss: 3.071042 (3.0535) Loss_single: 2.378847 (2.3626) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.104s, 308.65/s (0.143s, 223.85/s) LR: 5.000e-03 Data: 0.001 (0.032) +2025-04-18 10:54:30,387 - train: [ INFO] - Train: 44 [ 200/461 ( 43%)] Loss: 2.998492 (3.0425) Loss_single: 2.279357 (2.3460) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.095s, 335.91/s (0.136s, 235.36/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-18 10:54:35,858 - train: [ INFO] - Train: 44 [ 250/461 ( 54%)] Loss: 2.951995 (3.0274) Loss_single: 2.276319 (2.3344) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.119s, 269.07/s (0.130s, 245.52/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-18 10:54:41,477 - train: [ INFO] - Train: 44 [ 300/461 ( 65%)] Loss: 3.095709 (3.0372) Loss_single: 2.398376 (2.3435) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.110s, 290.76/s (0.127s, 251.52/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-18 10:54:48,463 - train: [ INFO] - Train: 44 [ 350/461 ( 76%)] Loss: 3.343640 (3.0755) Loss_single: 2.645900 (2.3813) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.081s, 394.09/s (0.125s, 255.01/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-18 10:54:54,338 - train: [ INFO] - Train: 44 [ 400/461 ( 87%)] Loss: 3.165992 (3.0856) Loss_single: 2.489204 (2.3933) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.109s, 293.35/s (0.124s, 257.38/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-18 10:54:59,903 - train: [ INFO] - Train: 44 [ 450/461 ( 98%)] Loss: 3.346898 (3.1117) Loss_single: 2.645444 (2.4185) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.079s, 405.24/s (0.123s, 260.58/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 10:55:01,632 - train: [ INFO] - Train: 44 [ 460/461 (100%)] Loss: 2.862845 (3.0891) Loss_single: 2.141445 (2.3933) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.086s, 373.29/s (0.122s, 262.47/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 10:55:07,080 - train: [ INFO] - Eval : 44 Time: 5.147 (5.147) Loss: 2.0212 (2.0212) Acc@1: 40.6250 (40.6250)Acc@5: 71.8750 (71.8750) +2025-04-18 10:55:14,240 - train: [ INFO] - Eval : 44 Time: 0.023 (0.241) Loss: 1.8732 (1.8958) Acc@1: 62.5000 (52.5123)Acc@5: 78.1250 (79.5956) +2025-04-18 10:55:15,865 - train: [ INFO] - Eval : 44 Time: 0.028 (0.170) Loss: 3.1045 (1.9251) Acc@1: 50.0000 (51.8504)Acc@5: 50.0000 (78.2190) +2025-04-18 10:55:23,906 - train: [ INFO] - Train: 45 [ 0/461 ( 0%)] Loss: 2.999830 (2.9998) Loss_single: 2.300524 (2.3005) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.165s, 6.20/s (5.165s, 6.20/s) LR: 5.000e-03 Data: 5.013 (5.013) +2025-04-18 10:55:30,493 - train: [ INFO] - Train: 45 [ 50/461 ( 11%)] Loss: 3.291313 (3.1456) Loss_single: 2.547827 (2.4242) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.129s, 249.01/s (0.230s, 139.31/s) LR: 5.000e-03 Data: 0.000 (0.105) +2025-04-18 10:55:36,399 - train: [ INFO] - Train: 45 [ 100/461 ( 22%)] Loss: 2.720538 (3.0039) Loss_single: 2.037049 (2.2951) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.099s, 322.41/s (0.174s, 183.84/s) LR: 5.000e-03 Data: 0.000 (0.053) +2025-04-18 10:55:41,903 - train: [ INFO] - Train: 45 [ 150/461 ( 33%)] Loss: 2.980816 (2.9981) Loss_single: 2.300982 (2.2966) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.080s, 400.92/s (0.153s, 209.60/s) LR: 5.000e-03 Data: 0.000 (0.036) +2025-04-18 10:55:47,966 - train: [ INFO] - Train: 45 [ 200/461 ( 43%)] Loss: 3.078129 (3.0141) Loss_single: 2.390497 (2.3154) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.111s, 288.05/s (0.145s, 221.19/s) LR: 5.000e-03 Data: 0.001 (0.027) +2025-04-18 10:55:53,542 - train: [ INFO] - Train: 45 [ 250/461 ( 54%)] Loss: 2.866840 (2.9896) Loss_single: 2.186774 (2.2939) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.093s, 343.29/s (0.138s, 232.01/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-18 10:56:00,318 - train: [ INFO] - Train: 45 [ 300/461 ( 65%)] Loss: 3.159136 (3.0138) Loss_single: 2.483777 (2.3211) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.137s, 233.32/s (0.134s, 239.65/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 10:56:05,844 - train: [ INFO] - Train: 45 [ 350/461 ( 76%)] Loss: 3.142010 (3.0298) Loss_single: 2.466582 (2.3393) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.125s, 255.90/s (0.130s, 246.14/s) LR: 5.000e-03 Data: 0.001 (0.016) +2025-04-18 10:56:11,742 - train: [ INFO] - Train: 45 [ 400/461 ( 87%)] Loss: 3.063305 (3.0335) Loss_single: 2.389149 (2.3448) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.188s, 170.20/s (0.128s, 249.23/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 10:56:18,834 - train: [ INFO] - Train: 45 [ 450/461 ( 98%)] Loss: 2.740809 (3.0043) Loss_single: 2.048810 (2.3152) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.086s, 372.94/s (0.127s, 251.80/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:56:19,740 - train: [ INFO] - Train: 45 [ 460/461 (100%)] Loss: 3.197226 (3.0218) Loss_single: 2.436257 (2.3262) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.141s, 227.19/s (0.126s, 253.42/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:56:25,674 - train: [ INFO] - Eval : 45 Time: 5.526 (5.526) Loss: 2.1516 (2.1516) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 10:56:32,004 - train: [ INFO] - Eval : 45 Time: 0.028 (0.232) Loss: 1.9746 (1.8882) Acc@1: 56.2500 (53.3701)Acc@5: 71.8750 (78.4314) +2025-04-18 10:56:34,250 - train: [ INFO] - Eval : 45 Time: 0.030 (0.172) Loss: 3.2435 (1.9026) Acc@1: 0.0000 (52.7756)Acc@5: 50.0000 (77.6022) +2025-04-18 10:56:41,683 - train: [ INFO] - Train: 46 [ 0/461 ( 0%)] Loss: 2.799030 (2.7990) Loss_single: 2.103563 (2.1036) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.554s, 7.03/s (4.554s, 7.03/s) LR: 5.000e-03 Data: 4.348 (4.348) +2025-04-18 10:56:47,811 - train: [ INFO] - Train: 46 [ 50/461 ( 11%)] Loss: 2.812925 (2.8060) Loss_single: 2.121658 (2.1126) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 401.34/s (0.209s, 153.47/s) LR: 5.000e-03 Data: 0.001 (0.088) +2025-04-18 10:56:53,355 - train: [ INFO] - Train: 46 [ 100/461 ( 22%)] Loss: 3.155650 (2.9225) Loss_single: 2.457698 (2.2276) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.145s, 221.37/s (0.160s, 200.27/s) LR: 5.000e-03 Data: 0.000 (0.045) +2025-04-18 10:56:59,178 - train: [ INFO] - Train: 46 [ 150/461 ( 33%)] Loss: 3.047128 (2.9537) Loss_single: 2.294683 (2.2444) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.087s, 366.30/s (0.145s, 220.99/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-18 10:57:05,045 - train: [ INFO] - Train: 46 [ 200/461 ( 43%)] Loss: 3.049511 (2.9728) Loss_single: 2.353692 (2.2663) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.120s, 267.71/s (0.138s, 232.25/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-18 10:57:12,385 - train: [ INFO] - Train: 46 [ 250/461 ( 54%)] Loss: 2.745588 (2.9350) Loss_single: 2.065133 (2.2327) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.165s, 194.22/s (0.135s, 237.09/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-18 10:57:17,934 - train: [ INFO] - Train: 46 [ 300/461 ( 65%)] Loss: 2.713770 (2.9034) Loss_single: 2.036197 (2.2047) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.092s, 348.85/s (0.131s, 244.50/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 10:57:23,243 - train: [ INFO] - Train: 46 [ 350/461 ( 76%)] Loss: 3.144448 (2.9335) Loss_single: 2.445912 (2.2348) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.087s, 367.55/s (0.127s, 251.44/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-18 10:57:30,020 - train: [ INFO] - Train: 46 [ 400/461 ( 87%)] Loss: 2.985557 (2.9393) Loss_single: 2.305392 (2.2427) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.168s, 190.09/s (0.125s, 255.61/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:57:35,090 - train: [ INFO] - Train: 46 [ 450/461 ( 98%)] Loss: 2.987850 (2.9441) Loss_single: 2.228376 (2.2412) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 96.8750 (99.6875) Time: 0.079s, 404.83/s (0.122s, 261.67/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 10:57:35,890 - train: [ INFO] - Train: 46 [ 460/461 (100%)] Loss: 2.724842 (2.9242) Loss_single: 2.038913 (2.2228) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.084s, 381.19/s (0.121s, 263.68/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 10:57:42,885 - train: [ INFO] - Eval : 46 Time: 6.676 (6.676) Loss: 2.1330 (2.1330) Acc@1: 50.0000 (50.0000)Acc@5: 71.8750 (71.8750) +2025-04-18 10:57:46,871 - train: [ INFO] - Eval : 46 Time: 0.645 (0.209) Loss: 1.8698 (1.8998) Acc@1: 53.1250 (51.9608)Acc@5: 75.0000 (80.2696) +2025-04-18 10:57:49,880 - train: [ INFO] - Eval : 46 Time: 0.017 (0.167) Loss: 3.0377 (1.9298) Acc@1: 50.0000 (50.7710)Acc@5: 50.0000 (78.6816) +2025-04-18 10:57:57,315 - train: [ INFO] - Train: 47 [ 0/461 ( 0%)] Loss: 3.327984 (3.3280) Loss_single: 2.488853 (2.4889) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (93.7500) Acc@5: 96.8750 (96.8750) Time: 4.140s, 7.73/s (4.140s, 7.73/s) LR: 5.000e-03 Data: 3.931 (3.931) +2025-04-18 10:58:03,444 - train: [ INFO] - Train: 47 [ 50/461 ( 11%)] Loss: 2.872988 (3.1005) Loss_single: 2.184157 (2.3365) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (96.8750) Acc@5: 100.0000 (98.4375) Time: 0.109s, 294.90/s (0.201s, 159.55/s) LR: 5.000e-03 Data: 0.001 (0.087) +2025-04-18 10:58:08,941 - train: [ INFO] - Train: 47 [ 100/461 ( 22%)] Loss: 2.757944 (2.9863) Loss_single: 2.065026 (2.2460) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (97.9167) Acc@5: 100.0000 (98.9583) Time: 0.113s, 283.66/s (0.155s, 205.97/s) LR: 5.000e-03 Data: 0.001 (0.044) +2025-04-18 10:58:14,191 - train: [ INFO] - Train: 47 [ 150/461 ( 33%)] Loss: 2.872566 (2.9579) Loss_single: 2.183082 (2.2303) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.138s, 231.09/s (0.138s, 231.40/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-18 10:58:20,558 - train: [ INFO] - Train: 47 [ 200/461 ( 43%)] Loss: 2.910979 (2.9485) Loss_single: 2.232085 (2.2306) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.084s, 381.44/s (0.130s, 247.06/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-18 10:58:26,413 - train: [ INFO] - Train: 47 [ 250/461 ( 54%)] Loss: 3.158484 (2.9835) Loss_single: 2.468525 (2.2703) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.123s, 259.11/s (0.127s, 252.18/s) LR: 5.000e-03 Data: 0.001 (0.018) +2025-04-18 10:58:31,993 - train: [ INFO] - Train: 47 [ 300/461 ( 65%)] Loss: 3.096644 (2.9997) Loss_single: 2.351493 (2.2819) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.137s, 233.79/s (0.124s, 257.71/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 10:58:38,802 - train: [ INFO] - Train: 47 [ 350/461 ( 76%)] Loss: 3.212981 (3.0263) Loss_single: 2.523548 (2.3121) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.111s, 287.70/s (0.123s, 261.21/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-18 10:58:45,193 - train: [ INFO] - Train: 47 [ 400/461 ( 87%)] Loss: 3.096311 (3.0341) Loss_single: 2.415633 (2.3236) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.083s, 384.73/s (0.123s, 260.16/s) LR: 5.000e-03 Data: 0.001 (0.012) +2025-04-18 10:58:50,618 - train: [ INFO] - Train: 47 [ 450/461 ( 98%)] Loss: 2.778608 (3.0085) Loss_single: 2.091164 (2.3004) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.085s, 375.17/s (0.121s, 264.04/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 10:58:51,513 - train: [ INFO] - Train: 47 [ 460/461 (100%)] Loss: 3.212354 (3.0271) Loss_single: 2.532847 (2.3215) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.092s, 349.48/s (0.120s, 265.59/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 10:58:59,049 - train: [ INFO] - Eval : 47 Time: 7.241 (7.241) Loss: 2.0407 (2.0407) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 10:59:02,463 - train: [ INFO] - Eval : 47 Time: 0.058 (0.209) Loss: 1.8441 (1.8850) Acc@1: 56.2500 (52.0221)Acc@5: 75.0000 (78.7990) +2025-04-18 10:59:03,998 - train: [ INFO] - Eval : 47 Time: 0.019 (0.149) Loss: 3.0738 (1.9030) Acc@1: 50.0000 (51.8119)Acc@5: 50.0000 (77.6022) +2025-04-18 10:59:10,949 - train: [ INFO] - Train: 48 [ 0/461 ( 0%)] Loss: 2.679873 (2.6799) Loss_single: 2.002614 (2.0026) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.082s, 7.84/s (4.082s, 7.84/s) LR: 5.000e-03 Data: 3.884 (3.884) +2025-04-18 10:59:17,970 - train: [ INFO] - Train: 48 [ 50/461 ( 11%)] Loss: 3.194426 (2.9371) Loss_single: 2.507442 (2.2550) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.117s, 273.66/s (0.217s, 147.67/s) LR: 5.000e-03 Data: 0.001 (0.079) +2025-04-18 10:59:23,689 - train: [ INFO] - Train: 48 [ 100/461 ( 22%)] Loss: 3.151925 (3.0087) Loss_single: 2.459626 (2.3232) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.125s, 256.63/s (0.166s, 193.02/s) LR: 5.000e-03 Data: 0.000 (0.040) +2025-04-18 10:59:30,568 - train: [ INFO] - Train: 48 [ 150/461 ( 33%)] Loss: 3.226543 (3.0632) Loss_single: 2.542221 (2.3780) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.148s, 216.25/s (0.148s, 216.61/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-18 10:59:36,875 - train: [ INFO] - Train: 48 [ 200/461 ( 43%)] Loss: 3.211274 (3.0928) Loss_single: 2.345381 (2.3715) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (98.7500) Acc@5: 93.7500 (98.7500) Time: 0.095s, 336.93/s (0.142s, 225.19/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-18 10:59:42,457 - train: [ INFO] - Train: 48 [ 250/461 ( 54%)] Loss: 3.374499 (3.1398) Loss_single: 2.564079 (2.4036) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (97.9167) Acc@5: 96.8750 (98.4375) Time: 0.091s, 351.33/s (0.136s, 235.49/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-18 10:59:48,971 - train: [ INFO] - Train: 48 [ 300/461 ( 65%)] Loss: 3.276506 (3.1593) Loss_single: 2.578568 (2.4286) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.2143) Acc@5: 100.0000 (98.6607) Time: 0.169s, 189.83/s (0.131s, 244.41/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-18 10:59:54,581 - train: [ INFO] - Train: 48 [ 350/461 ( 76%)] Loss: 3.043258 (3.1448) Loss_single: 2.337426 (2.4172) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.8281) Time: 0.124s, 257.54/s (0.128s, 250.29/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 10:59:59,996 - train: [ INFO] - Train: 48 [ 400/461 ( 87%)] Loss: 3.249170 (3.1564) Loss_single: 2.568871 (2.4340) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6111) Acc@5: 100.0000 (98.9583) Time: 0.085s, 377.37/s (0.125s, 255.47/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 11:00:05,337 - train: [ INFO] - Train: 48 [ 450/461 ( 98%)] Loss: 2.843675 (3.1251) Loss_single: 2.157402 (2.4064) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.0625) Time: 0.081s, 392.66/s (0.123s, 259.88/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 11:00:06,244 - train: [ INFO] - Train: 48 [ 460/461 (100%)] Loss: 3.026441 (3.1161) Loss_single: 2.252421 (2.3924) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.5795) Acc@5: 100.0000 (99.1477) Time: 0.097s, 329.45/s (0.122s, 261.41/s) LR: 5.000e-03 Data: 0.000 (0.009) +2025-04-18 11:00:11,905 - train: [ INFO] - Eval : 48 Time: 5.154 (5.154) Loss: 2.0378 (2.0378) Acc@1: 59.3750 (59.3750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:00:17,901 - train: [ INFO] - Eval : 48 Time: 0.052 (0.219) Loss: 2.0079 (1.8842) Acc@1: 53.1250 (53.6152)Acc@5: 75.0000 (79.5343) +2025-04-18 11:00:19,744 - train: [ INFO] - Eval : 48 Time: 0.022 (0.158) Loss: 2.8496 (1.9094) Acc@1: 50.0000 (53.2382)Acc@5: 50.0000 (78.2961) +2025-04-18 11:00:22,877 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-48.pth.tar', 53.238242097147264) + +2025-04-18 11:00:26,962 - train: [ INFO] - Train: 49 [ 0/461 ( 0%)] Loss: 3.053994 (3.0540) Loss_single: 2.282130 (2.2821) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 4.060s, 7.88/s (4.060s, 7.88/s) LR: 5.000e-03 Data: 3.935 (3.935) +2025-04-18 11:00:33,512 - train: [ INFO] - Train: 49 [ 50/461 ( 11%)] Loss: 2.716145 (2.8851) Loss_single: 2.039348 (2.1607) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.126s, 253.80/s (0.207s, 154.83/s) LR: 5.000e-03 Data: 0.000 (0.083) +2025-04-18 11:00:39,780 - train: [ INFO] - Train: 49 [ 100/461 ( 22%)] Loss: 3.007899 (2.9260) Loss_single: 2.298739 (2.2067) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.121s, 263.69/s (0.155s, 205.92/s) LR: 5.000e-03 Data: 0.000 (0.043) +2025-04-18 11:00:45,945 - train: [ INFO] - Train: 49 [ 150/461 ( 33%)] Loss: 3.088152 (2.9665) Loss_single: 2.344769 (2.2412) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.106s, 301.10/s (0.141s, 227.72/s) LR: 5.000e-03 Data: 0.001 (0.029) +2025-04-18 11:00:51,635 - train: [ INFO] - Train: 49 [ 200/461 ( 43%)] Loss: 2.693943 (2.9120) Loss_single: 2.005100 (2.1940) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.111s, 287.90/s (0.134s, 239.35/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-18 11:00:57,775 - train: [ INFO] - Train: 49 [ 250/461 ( 54%)] Loss: 2.809186 (2.8949) Loss_single: 2.127873 (2.1830) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.121s, 265.36/s (0.131s, 243.64/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-18 11:01:04,683 - train: [ INFO] - Train: 49 [ 300/461 ( 65%)] Loss: 3.377935 (2.9639) Loss_single: 2.687730 (2.2551) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.114s, 281.90/s (0.128s, 249.27/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 11:01:10,681 - train: [ INFO] - Train: 49 [ 350/461 ( 76%)] Loss: 3.105039 (2.9815) Loss_single: 2.424762 (2.2763) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.110s, 291.87/s (0.127s, 251.89/s) LR: 5.000e-03 Data: 0.001 (0.013) +2025-04-18 11:01:16,778 - train: [ INFO] - Train: 49 [ 400/461 ( 87%)] Loss: 2.751601 (2.9560) Loss_single: 2.063430 (2.2527) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.122s, 262.56/s (0.126s, 254.96/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 11:01:22,333 - train: [ INFO] - Train: 49 [ 450/461 ( 98%)] Loss: 2.943947 (2.9548) Loss_single: 2.257778 (2.2532) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.082s, 392.22/s (0.124s, 258.45/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 11:01:23,192 - train: [ INFO] - Train: 49 [ 460/461 (100%)] Loss: 2.808496 (2.9415) Loss_single: 2.131642 (2.2421) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.087s, 365.86/s (0.123s, 260.22/s) LR: 5.000e-03 Data: 0.000 (0.010) +2025-04-18 11:01:28,861 - train: [ INFO] - Eval : 49 Time: 5.378 (5.378) Loss: 1.9516 (1.9516) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:01:33,969 - train: [ INFO] - Eval : 49 Time: 0.082 (0.206) Loss: 1.8468 (1.8681) Acc@1: 59.3750 (53.1250)Acc@5: 75.0000 (78.3088) +2025-04-18 11:01:35,638 - train: [ INFO] - Eval : 49 Time: 0.021 (0.148) Loss: 2.8609 (1.8754) Acc@1: 0.0000 (52.2359)Acc@5: 50.0000 (78.1419) +2025-04-18 11:01:45,657 - train: [ INFO] - Train: 50 [ 0/461 ( 0%)] Loss: 2.892950 (2.8930) Loss_single: 2.212682 (2.2127) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.064s, 4.53/s (7.064s, 4.53/s) LR: 5.000e-03 Data: 6.890 (6.890) +2025-04-18 11:01:52,896 - train: [ INFO] - Train: 50 [ 50/461 ( 11%)] Loss: 3.023603 (2.9583) Loss_single: 2.256718 (2.2347) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.117s, 273.28/s (0.280s, 114.49/s) LR: 5.000e-03 Data: 0.000 (0.141) +2025-04-18 11:01:59,442 - train: [ INFO] - Train: 50 [ 100/461 ( 22%)] Loss: 3.242807 (3.0531) Loss_single: 2.489946 (2.3198) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (97.9167) Acc@5: 96.8750 (98.9583) Time: 0.105s, 305.71/s (0.204s, 156.99/s) LR: 5.000e-03 Data: 0.000 (0.071) +2025-04-18 11:02:05,153 - train: [ INFO] - Train: 50 [ 150/461 ( 33%)] Loss: 2.981297 (3.0352) Loss_single: 2.272413 (2.3079) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.123s, 260.40/s (0.174s, 183.96/s) LR: 5.000e-03 Data: 0.000 (0.048) +2025-04-18 11:02:11,202 - train: [ INFO] - Train: 50 [ 200/461 ( 43%)] Loss: 3.108391 (3.0498) Loss_single: 2.408107 (2.3280) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.077s, 416.67/s (0.161s, 199.28/s) LR: 5.000e-03 Data: 0.000 (0.037) +2025-04-18 11:02:17,817 - train: [ INFO] - Train: 50 [ 250/461 ( 54%)] Loss: 3.098902 (3.0580) Loss_single: 2.358714 (2.3331) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.4792) Time: 0.144s, 221.76/s (0.150s, 213.47/s) LR: 5.000e-03 Data: 0.000 (0.030) +2025-04-18 11:02:23,867 - train: [ INFO] - Train: 50 [ 300/461 ( 65%)] Loss: 2.941001 (3.0413) Loss_single: 2.214983 (2.3162) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6607) Acc@5: 100.0000 (99.5536) Time: 0.150s, 213.22/s (0.145s, 220.75/s) LR: 5.000e-03 Data: 0.001 (0.025) +2025-04-18 11:02:29,850 - train: [ INFO] - Train: 50 [ 350/461 ( 76%)] Loss: 3.334950 (3.0780) Loss_single: 2.648176 (2.3577) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8281) Acc@5: 100.0000 (99.6094) Time: 0.102s, 314.80/s (0.141s, 226.58/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-18 11:02:35,927 - train: [ INFO] - Train: 50 [ 400/461 ( 87%)] Loss: 2.764693 (3.0432) Loss_single: 2.091938 (2.3282) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.6528) Time: 0.151s, 212.14/s (0.139s, 230.96/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-18 11:02:41,170 - train: [ INFO] - Train: 50 [ 450/461 ( 98%)] Loss: 3.169431 (3.0558) Loss_single: 2.428837 (2.3383) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.7500) Acc@5: 100.0000 (99.6875) Time: 0.084s, 382.79/s (0.135s, 237.60/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-18 11:02:42,071 - train: [ INFO] - Train: 50 [ 460/461 (100%)] Loss: 3.331317 (3.0808) Loss_single: 2.633806 (2.3651) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8636) Acc@5: 100.0000 (99.7159) Time: 0.088s, 364.53/s (0.134s, 239.34/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 11:02:48,774 - train: [ INFO] - Eval : 50 Time: 6.170 (6.170) Loss: 2.1340 (2.1340) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:03:01,663 - train: [ INFO] - Eval : 50 Time: 0.213 (0.374) Loss: 1.9106 (1.9019) Acc@1: 59.3750 (52.3284)Acc@5: 78.1250 (78.9216) +2025-04-18 11:03:05,196 - train: [ INFO] - Eval : 50 Time: 0.017 (0.276) Loss: 2.7109 (1.9230) Acc@1: 50.0000 (51.6577)Acc@5: 50.0000 (78.3732) +2025-04-18 11:03:15,587 - train: [ INFO] - Train: 51 [ 0/461 ( 0%)] Loss: 2.870959 (2.8710) Loss_single: 2.191243 (2.1912) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.548s, 4.89/s (6.548s, 4.89/s) LR: 5.000e-03 Data: 6.398 (6.398) +2025-04-18 11:03:22,744 - train: [ INFO] - Train: 51 [ 50/461 ( 11%)] Loss: 2.713617 (2.7923) Loss_single: 2.033561 (2.1124) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 385.75/s (0.268s, 119.42/s) LR: 5.000e-03 Data: 0.001 (0.163) +2025-04-18 11:03:29,941 - train: [ INFO] - Train: 51 [ 100/461 ( 22%)] Loss: 3.460960 (3.0152) Loss_single: 2.639287 (2.2880) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (97.9167) Acc@5: 96.8750 (98.9583) Time: 0.081s, 393.05/s (0.206s, 155.37/s) LR: 5.000e-03 Data: 0.001 (0.097) +2025-04-18 11:03:37,466 - train: [ INFO] - Train: 51 [ 150/461 ( 33%)] Loss: 3.168418 (3.0535) Loss_single: 2.473210 (2.3343) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.269s, 119.04/s (0.180s, 177.50/s) LR: 5.000e-03 Data: 0.001 (0.065) +2025-04-18 11:03:43,309 - train: [ INFO] - Train: 51 [ 200/461 ( 43%)] Loss: 2.810762 (3.0049) Loss_single: 2.134865 (2.2944) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.108s, 296.56/s (0.164s, 194.74/s) LR: 5.000e-03 Data: 0.000 (0.049) +2025-04-18 11:03:48,801 - train: [ INFO] - Train: 51 [ 250/461 ( 54%)] Loss: 3.145717 (3.0284) Loss_single: 2.449110 (2.3202) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.139s, 230.87/s (0.153s, 208.89/s) LR: 5.000e-03 Data: 0.000 (0.039) +2025-04-18 11:03:54,275 - train: [ INFO] - Train: 51 [ 300/461 ( 65%)] Loss: 2.726584 (2.9853) Loss_single: 2.048748 (2.2814) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.123s, 259.23/s (0.146s, 219.57/s) LR: 5.000e-03 Data: 0.001 (0.033) +2025-04-18 11:03:59,883 - train: [ INFO] - Train: 51 [ 350/461 ( 76%)] Loss: 2.729550 (2.9533) Loss_single: 2.054280 (2.2530) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.113s, 284.06/s (0.141s, 227.17/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-18 11:04:05,499 - train: [ INFO] - Train: 51 [ 400/461 ( 87%)] Loss: 2.729749 (2.9285) Loss_single: 2.052725 (2.2308) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.107s, 298.51/s (0.137s, 233.22/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-18 11:04:12,197 - train: [ INFO] - Train: 51 [ 450/461 ( 98%)] Loss: 3.081037 (2.9437) Loss_single: 2.396985 (2.2474) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.082s, 389.03/s (0.134s, 238.06/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-18 11:04:13,122 - train: [ INFO] - Train: 51 [ 460/461 (100%)] Loss: 2.746437 (2.9258) Loss_single: 2.071931 (2.2314) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.086s, 373.40/s (0.133s, 239.71/s) LR: 5.000e-03 Data: 0.000 (0.022) +2025-04-18 11:04:19,308 - train: [ INFO] - Eval : 51 Time: 5.779 (5.779) Loss: 2.0398 (2.0398) Acc@1: 50.0000 (50.0000)Acc@5: 84.3750 (84.3750) +2025-04-18 11:04:24,267 - train: [ INFO] - Eval : 51 Time: 0.081 (0.211) Loss: 1.9308 (1.9355) Acc@1: 56.2500 (51.1029)Acc@5: 78.1250 (78.7990) +2025-04-18 11:04:26,622 - train: [ INFO] - Eval : 51 Time: 0.015 (0.160) Loss: 3.0030 (1.9578) Acc@1: 50.0000 (50.5783)Acc@5: 50.0000 (77.7564) +2025-04-18 11:04:34,588 - train: [ INFO] - Train: 52 [ 0/461 ( 0%)] Loss: 2.991759 (2.9918) Loss_single: 2.302579 (2.3026) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.844s, 6.61/s (4.844s, 6.61/s) LR: 5.000e-03 Data: 4.646 (4.646) +2025-04-18 11:04:41,458 - train: [ INFO] - Train: 52 [ 50/461 ( 11%)] Loss: 3.044251 (3.0180) Loss_single: 2.354077 (2.3283) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.120s, 265.68/s (0.205s, 155.86/s) LR: 5.000e-03 Data: 0.001 (0.096) +2025-04-18 11:04:47,490 - train: [ INFO] - Train: 52 [ 100/461 ( 22%)] Loss: 2.739309 (2.9251) Loss_single: 2.030497 (2.2291) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.128s, 249.71/s (0.163s, 196.53/s) LR: 5.000e-03 Data: 0.000 (0.049) +2025-04-18 11:04:52,967 - train: [ INFO] - Train: 52 [ 150/461 ( 33%)] Loss: 2.801276 (2.8941) Loss_single: 2.118529 (2.2014) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 410.22/s (0.145s, 220.71/s) LR: 5.000e-03 Data: 0.001 (0.033) +2025-04-18 11:04:59,130 - train: [ INFO] - Train: 52 [ 200/461 ( 43%)] Loss: 3.022732 (2.9199) Loss_single: 2.348888 (2.2309) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 396.87/s (0.138s, 231.91/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-18 11:05:04,884 - train: [ INFO] - Train: 52 [ 250/461 ( 54%)] Loss: 2.981183 (2.9301) Loss_single: 2.289696 (2.2407) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.114s, 280.69/s (0.133s, 240.08/s) LR: 5.000e-03 Data: 0.001 (0.020) +2025-04-18 11:05:10,433 - train: [ INFO] - Train: 52 [ 300/461 ( 65%)] Loss: 3.086438 (2.9524) Loss_single: 2.406869 (2.2644) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.110s, 291.99/s (0.129s, 247.19/s) LR: 5.000e-03 Data: 0.000 (0.017) +2025-04-18 11:05:16,614 - train: [ INFO] - Train: 52 [ 350/461 ( 76%)] Loss: 2.902762 (2.9462) Loss_single: 2.157282 (2.2511) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6094) Acc@5: 96.8750 (99.6094) Time: 0.119s, 268.46/s (0.128s, 249.16/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 11:05:23,039 - train: [ INFO] - Train: 52 [ 400/461 ( 87%)] Loss: 2.745473 (2.9239) Loss_single: 2.059020 (2.2297) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.085s, 374.80/s (0.126s, 254.93/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:05:28,593 - train: [ INFO] - Train: 52 [ 450/461 ( 98%)] Loss: 2.890933 (2.9206) Loss_single: 2.207989 (2.2275) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.090s, 356.89/s (0.124s, 258.38/s) LR: 5.000e-03 Data: 0.000 (0.012) +2025-04-18 11:05:29,450 - train: [ INFO] - Train: 52 [ 460/461 (100%)] Loss: 3.077968 (2.9349) Loss_single: 2.395690 (2.2428) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.080s, 401.30/s (0.123s, 260.16/s) LR: 5.000e-03 Data: 0.000 (0.011) +2025-04-18 11:05:34,625 - train: [ INFO] - Eval : 52 Time: 4.896 (4.896) Loss: 2.1829 (2.1829) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 11:05:37,630 - train: [ INFO] - Eval : 52 Time: 0.047 (0.154) Loss: 1.7584 (1.8887) Acc@1: 59.3750 (52.8799)Acc@5: 78.1250 (80.0858) +2025-04-18 11:05:40,030 - train: [ INFO] - Eval : 52 Time: 0.016 (0.126) Loss: 3.1562 (1.9068) Acc@1: 50.0000 (52.1588)Acc@5: 50.0000 (79.3755) +2025-04-18 11:05:51,121 - train: [ INFO] - Train: 53 [ 0/461 ( 0%)] Loss: 2.978291 (2.9783) Loss_single: 2.250697 (2.2507) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.950s, 4.03/s (7.950s, 4.03/s) LR: 5.000e-03 Data: 7.756 (7.756) +2025-04-18 11:05:57,648 - train: [ INFO] - Train: 53 [ 50/461 ( 11%)] Loss: 2.567972 (2.7731) Loss_single: 1.900858 (2.0758) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.090s, 355.98/s (0.269s, 118.93/s) LR: 5.000e-03 Data: 0.000 (0.156) +2025-04-18 11:06:04,268 - train: [ INFO] - Train: 53 [ 100/461 ( 22%)] Loss: 2.780745 (2.7757) Loss_single: 2.083324 (2.0783) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.117s, 272.98/s (0.201s, 159.30/s) LR: 5.000e-03 Data: 0.000 (0.079) +2025-04-18 11:06:09,890 - train: [ INFO] - Train: 53 [ 150/461 ( 33%)] Loss: 2.726670 (2.7634) Loss_single: 2.041291 (2.0690) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.146s, 218.57/s (0.171s, 186.76/s) LR: 5.000e-03 Data: 0.000 (0.053) +2025-04-18 11:06:16,314 - train: [ INFO] - Train: 53 [ 200/461 ( 43%)] Loss: 2.983503 (2.8074) Loss_single: 2.263413 (2.1079) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.143s, 223.46/s (0.157s, 203.46/s) LR: 5.000e-03 Data: 0.001 (0.040) +2025-04-18 11:06:22,666 - train: [ INFO] - Train: 53 [ 250/461 ( 54%)] Loss: 3.027857 (2.8442) Loss_single: 2.347321 (2.1478) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.154s, 207.76/s (0.151s, 211.84/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-18 11:06:28,829 - train: [ INFO] - Train: 53 [ 300/461 ( 65%)] Loss: 2.713652 (2.8255) Loss_single: 2.037737 (2.1321) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 408.70/s (0.144s, 222.17/s) LR: 5.000e-03 Data: 0.001 (0.027) +2025-04-18 11:06:35,404 - train: [ INFO] - Train: 53 [ 350/461 ( 76%)] Loss: 3.018916 (2.8497) Loss_single: 2.250575 (2.1469) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6094) Acc@5: 96.8750 (99.6094) Time: 0.123s, 260.39/s (0.140s, 227.95/s) LR: 5.000e-03 Data: 0.001 (0.023) +2025-04-18 11:06:41,040 - train: [ INFO] - Train: 53 [ 400/461 ( 87%)] Loss: 2.929764 (2.8586) Loss_single: 2.248826 (2.1582) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.157s, 204.23/s (0.137s, 233.84/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-18 11:06:46,815 - train: [ INFO] - Train: 53 [ 450/461 ( 98%)] Loss: 2.815720 (2.8543) Loss_single: 2.123932 (2.1548) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.077s, 414.31/s (0.134s, 238.18/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-18 11:06:48,750 - train: [ INFO] - Train: 53 [ 460/461 (100%)] Loss: 2.820701 (2.8513) Loss_single: 2.145956 (2.1540) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.077s, 416.60/s (0.133s, 240.28/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-18 11:06:55,498 - train: [ INFO] - Eval : 53 Time: 6.407 (6.407) Loss: 2.0680 (2.0680) Acc@1: 53.1250 (53.1250)Acc@5: 71.8750 (71.8750) +2025-04-18 11:07:00,733 - train: [ INFO] - Eval : 53 Time: 0.039 (0.228) Loss: 1.8705 (1.8635) Acc@1: 59.3750 (53.4926)Acc@5: 71.8750 (80.3309) +2025-04-18 11:07:02,129 - train: [ INFO] - Eval : 53 Time: 0.015 (0.159) Loss: 2.3051 (1.8867) Acc@1: 50.0000 (52.5829)Acc@5: 50.0000 (79.4911) +2025-04-18 11:07:12,460 - train: [ INFO] - Train: 54 [ 0/461 ( 0%)] Loss: 2.675276 (2.6753) Loss_single: 1.986334 (1.9863) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.136s, 4.48/s (7.136s, 4.48/s) LR: 5.000e-03 Data: 6.908 (6.908) +2025-04-18 11:07:18,628 - train: [ INFO] - Train: 54 [ 50/461 ( 11%)] Loss: 2.968754 (2.8220) Loss_single: 2.263374 (2.1249) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.133s, 240.69/s (0.259s, 123.71/s) LR: 5.000e-03 Data: 0.001 (0.136) +2025-04-18 11:07:24,424 - train: [ INFO] - Train: 54 [ 100/461 ( 22%)] Loss: 2.766403 (2.8035) Loss_single: 2.054394 (2.1014) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.169s, 189.39/s (0.188s, 170.51/s) LR: 5.000e-03 Data: 0.000 (0.069) +2025-04-18 11:07:29,919 - train: [ INFO] - Train: 54 [ 150/461 ( 33%)] Loss: 2.910993 (2.8304) Loss_single: 2.215714 (2.1300) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.107s, 299.32/s (0.162s, 197.86/s) LR: 5.000e-03 Data: 0.000 (0.046) +2025-04-18 11:07:35,516 - train: [ INFO] - Train: 54 [ 200/461 ( 43%)] Loss: 2.926682 (2.8496) Loss_single: 2.245426 (2.1530) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.140s, 229.12/s (0.149s, 214.52/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-18 11:07:41,872 - train: [ INFO] - Train: 54 [ 250/461 ( 54%)] Loss: 3.058864 (2.8845) Loss_single: 2.339122 (2.1841) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 393.56/s (0.141s, 226.84/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-18 11:07:48,296 - train: [ INFO] - Train: 54 [ 300/461 ( 65%)] Loss: 3.293038 (2.9429) Loss_single: 2.616877 (2.2459) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.116s, 274.76/s (0.138s, 232.16/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-18 11:07:54,234 - train: [ INFO] - Train: 54 [ 350/461 ( 76%)] Loss: 3.150320 (2.9688) Loss_single: 2.417183 (2.2673) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.145s, 220.63/s (0.134s, 238.34/s) LR: 5.000e-03 Data: 0.001 (0.020) +2025-04-18 11:08:00,272 - train: [ INFO] - Train: 54 [ 400/461 ( 87%)] Loss: 2.951988 (2.9669) Loss_single: 2.267476 (2.2673) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.095s, 335.17/s (0.132s, 243.30/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-18 11:08:07,089 - train: [ INFO] - Train: 54 [ 450/461 ( 98%)] Loss: 2.889394 (2.9592) Loss_single: 2.206090 (2.2612) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.083s, 387.02/s (0.129s, 247.47/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 11:08:07,956 - train: [ INFO] - Train: 54 [ 460/461 (100%)] Loss: 2.940977 (2.9575) Loss_single: 2.259215 (2.2610) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.078s, 410.46/s (0.128s, 249.51/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 11:08:12,999 - train: [ INFO] - Eval : 54 Time: 4.758 (4.758) Loss: 2.0148 (2.0148) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 11:08:16,760 - train: [ INFO] - Eval : 54 Time: 0.132 (0.166) Loss: 1.8942 (1.8771) Acc@1: 59.3750 (54.4118)Acc@5: 71.8750 (79.7794) +2025-04-18 11:08:18,883 - train: [ INFO] - Eval : 54 Time: 0.014 (0.130) Loss: 3.5118 (1.9031) Acc@1: 0.0000 (52.9684)Acc@5: 50.0000 (78.9514) +2025-04-18 11:08:26,855 - train: [ INFO] - Train: 55 [ 0/461 ( 0%)] Loss: 2.957053 (2.9571) Loss_single: 2.277540 (2.2775) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.076s, 6.30/s (5.076s, 6.30/s) LR: 5.000e-03 Data: 4.863 (4.863) +2025-04-18 11:08:34,298 - train: [ INFO] - Train: 55 [ 50/461 ( 11%)] Loss: 3.173013 (3.0650) Loss_single: 2.441675 (2.3596) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 395.50/s (0.236s, 135.38/s) LR: 5.000e-03 Data: 0.001 (0.107) +2025-04-18 11:08:41,235 - train: [ INFO] - Train: 55 [ 100/461 ( 22%)] Loss: 3.084178 (3.0714) Loss_single: 2.265042 (2.3281) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.106s, 301.80/s (0.187s, 170.71/s) LR: 5.000e-03 Data: 0.000 (0.055) +2025-04-18 11:08:46,980 - train: [ INFO] - Train: 55 [ 150/461 ( 33%)] Loss: 2.983568 (3.0495) Loss_single: 2.241538 (2.3064) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.098s, 325.22/s (0.163s, 196.10/s) LR: 5.000e-03 Data: 0.000 (0.037) +2025-04-18 11:08:53,254 - train: [ INFO] - Train: 55 [ 200/461 ( 43%)] Loss: 2.939468 (3.0275) Loss_single: 2.177211 (2.2806) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.1250) Acc@5: 96.8750 (99.3750) Time: 0.077s, 413.69/s (0.151s, 211.99/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-18 11:08:59,451 - train: [ INFO] - Train: 55 [ 250/461 ( 54%)] Loss: 2.816339 (2.9923) Loss_single: 2.138878 (2.2570) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.4792) Time: 0.079s, 406.55/s (0.143s, 224.08/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-18 11:09:05,243 - train: [ INFO] - Train: 55 [ 300/461 ( 65%)] Loss: 2.733785 (2.9553) Loss_single: 2.051657 (2.2276) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6607) Acc@5: 100.0000 (99.5536) Time: 0.088s, 364.09/s (0.138s, 231.60/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-18 11:09:10,706 - train: [ INFO] - Train: 55 [ 350/461 ( 76%)] Loss: 2.995128 (2.9603) Loss_single: 2.308815 (2.2378) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8281) Acc@5: 100.0000 (99.6094) Time: 0.109s, 293.17/s (0.134s, 238.86/s) LR: 5.000e-03 Data: 0.001 (0.017) +2025-04-18 11:09:17,273 - train: [ INFO] - Train: 55 [ 400/461 ( 87%)] Loss: 2.921686 (2.9560) Loss_single: 2.246202 (2.2387) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.6528) Time: 0.083s, 384.17/s (0.130s, 245.32/s) LR: 5.000e-03 Data: 0.000 (0.015) +2025-04-18 11:09:24,056 - train: [ INFO] - Train: 55 [ 450/461 ( 98%)] Loss: 2.509889 (2.9114) Loss_single: 1.831909 (2.1980) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.6875) Time: 0.096s, 332.60/s (0.129s, 248.39/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:09:24,892 - train: [ INFO] - Train: 55 [ 460/461 (100%)] Loss: 3.035284 (2.9227) Loss_single: 2.363106 (2.2131) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.7159) Time: 0.089s, 361.54/s (0.128s, 250.33/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:09:31,174 - train: [ INFO] - Eval : 55 Time: 5.981 (5.981) Loss: 2.1458 (2.1458) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-18 11:09:36,014 - train: [ INFO] - Eval : 55 Time: 0.068 (0.212) Loss: 1.8465 (1.8328) Acc@1: 62.5000 (55.4534)Acc@5: 78.1250 (81.8015) +2025-04-18 11:09:38,096 - train: [ INFO] - Eval : 55 Time: 0.014 (0.157) Loss: 2.9681 (1.8550) Acc@1: 0.0000 (54.4333)Acc@5: 50.0000 (80.8019) +2025-04-18 11:09:40,921 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-55.pth.tar', 54.43330763299923) + +2025-04-18 11:09:46,717 - train: [ INFO] - Train: 56 [ 0/461 ( 0%)] Loss: 2.684247 (2.6842) Loss_single: 2.002451 (2.0025) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.752s, 5.56/s (5.752s, 5.56/s) LR: 5.000e-03 Data: 5.593 (5.593) +2025-04-18 11:09:52,883 - train: [ INFO] - Train: 56 [ 50/461 ( 11%)] Loss: 2.761998 (2.7231) Loss_single: 2.090407 (2.0464) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.098s, 325.70/s (0.232s, 137.77/s) LR: 5.000e-03 Data: 0.000 (0.110) +2025-04-18 11:09:58,658 - train: [ INFO] - Train: 56 [ 100/461 ( 22%)] Loss: 2.603364 (2.6832) Loss_single: 1.922982 (2.0053) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.189s, 169.09/s (0.174s, 183.97/s) LR: 5.000e-03 Data: 0.001 (0.056) +2025-04-18 11:10:05,105 - train: [ INFO] - Train: 56 [ 150/461 ( 33%)] Loss: 3.220515 (2.8175) Loss_single: 2.450378 (2.1166) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.130s, 245.75/s (0.159s, 201.59/s) LR: 5.000e-03 Data: 0.001 (0.038) +2025-04-18 11:10:12,030 - train: [ INFO] - Train: 56 [ 200/461 ( 43%)] Loss: 2.821430 (2.8183) Loss_single: 2.141730 (2.1216) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.146s, 219.63/s (0.147s, 218.05/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-18 11:10:17,773 - train: [ INFO] - Train: 56 [ 250/461 ( 54%)] Loss: 2.803853 (2.8159) Loss_single: 2.119495 (2.1212) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.085s, 377.84/s (0.140s, 228.12/s) LR: 5.000e-03 Data: 0.000 (0.023) +2025-04-18 11:10:23,543 - train: [ INFO] - Train: 56 [ 300/461 ( 65%)] Loss: 2.756289 (2.8074) Loss_single: 2.060505 (2.1126) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.109s, 293.04/s (0.136s, 235.24/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-18 11:10:29,842 - train: [ INFO] - Train: 56 [ 350/461 ( 76%)] Loss: 2.796559 (2.8060) Loss_single: 2.114143 (2.1128) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.134s, 239.12/s (0.131s, 244.13/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 11:10:35,350 - train: [ INFO] - Train: 56 [ 400/461 ( 87%)] Loss: 2.916667 (2.8183) Loss_single: 2.224456 (2.1252) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.090s, 354.34/s (0.128s, 249.26/s) LR: 5.000e-03 Data: 0.000 (0.014) +2025-04-18 11:10:41,713 - train: [ INFO] - Train: 56 [ 450/461 ( 98%)] Loss: 3.040228 (2.8405) Loss_single: 2.297610 (2.1424) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.087s, 366.21/s (0.126s, 254.96/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:10:42,576 - train: [ INFO] - Train: 56 [ 460/461 (100%)] Loss: 2.959196 (2.8513) Loss_single: 2.291053 (2.1559) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.088s, 364.10/s (0.125s, 256.74/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:10:49,481 - train: [ INFO] - Eval : 56 Time: 6.523 (6.523) Loss: 2.1164 (2.1164) Acc@1: 43.7500 (43.7500)Acc@5: 81.2500 (81.2500) +2025-04-18 11:10:54,220 - train: [ INFO] - Eval : 56 Time: 0.039 (0.221) Loss: 1.9024 (1.8597) Acc@1: 59.3750 (53.2475)Acc@5: 75.0000 (79.5343) +2025-04-18 11:10:56,411 - train: [ INFO] - Eval : 56 Time: 0.014 (0.164) Loss: 3.4376 (1.8837) Acc@1: 50.0000 (52.9684)Acc@5: 50.0000 (79.0671) +2025-04-18 11:11:04,758 - train: [ INFO] - Train: 57 [ 0/461 ( 0%)] Loss: 2.718004 (2.7180) Loss_single: 2.030412 (2.0304) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.256s, 6.09/s (5.256s, 6.09/s) LR: 5.000e-03 Data: 5.087 (5.087) +2025-04-18 11:11:11,618 - train: [ INFO] - Train: 57 [ 50/461 ( 11%)] Loss: 2.687315 (2.7027) Loss_single: 2.001309 (2.0159) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.122s, 263.23/s (0.236s, 135.57/s) LR: 5.000e-03 Data: 0.001 (0.107) +2025-04-18 11:11:19,238 - train: [ INFO] - Train: 57 [ 100/461 ( 22%)] Loss: 3.144210 (2.8498) Loss_single: 2.357970 (2.1299) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.157s, 203.95/s (0.174s, 184.16/s) LR: 5.000e-03 Data: 0.000 (0.054) +2025-04-18 11:11:24,924 - train: [ INFO] - Train: 57 [ 150/461 ( 33%)] Loss: 3.091412 (2.9102) Loss_single: 2.403910 (2.1984) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.094s, 340.43/s (0.153s, 208.56/s) LR: 5.000e-03 Data: 0.001 (0.036) +2025-04-18 11:11:30,505 - train: [ INFO] - Train: 57 [ 200/461 ( 43%)] Loss: 2.950114 (2.9182) Loss_single: 2.269781 (2.2127) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.094s, 341.52/s (0.143s, 224.21/s) LR: 5.000e-03 Data: 0.001 (0.028) +2025-04-18 11:11:37,810 - train: [ INFO] - Train: 57 [ 250/461 ( 54%)] Loss: 2.665536 (2.8761) Loss_single: 1.985692 (2.1748) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.103s, 311.60/s (0.139s, 230.72/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-18 11:11:43,678 - train: [ INFO] - Train: 57 [ 300/461 ( 65%)] Loss: 2.649539 (2.8437) Loss_single: 1.960339 (2.1442) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.124s, 258.64/s (0.135s, 237.11/s) LR: 5.000e-03 Data: 0.001 (0.019) +2025-04-18 11:11:49,645 - train: [ INFO] - Train: 57 [ 350/461 ( 76%)] Loss: 2.984717 (2.8614) Loss_single: 2.285594 (2.1619) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.107s, 299.14/s (0.133s, 241.29/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 11:11:56,597 - train: [ INFO] - Train: 57 [ 400/461 ( 87%)] Loss: 2.734886 (2.8473) Loss_single: 1.991264 (2.1429) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.172s, 185.67/s (0.130s, 245.87/s) LR: 5.000e-03 Data: 0.001 (0.014) +2025-04-18 11:12:02,289 - train: [ INFO] - Train: 57 [ 450/461 ( 98%)] Loss: 3.050847 (2.8677) Loss_single: 2.374016 (2.1660) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.080s, 401.16/s (0.128s, 249.67/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:12:03,155 - train: [ INFO] - Train: 57 [ 460/461 (100%)] Loss: 2.638207 (2.8468) Loss_single: 1.950610 (2.1464) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.084s, 382.98/s (0.127s, 251.48/s) LR: 5.000e-03 Data: 0.000 (0.013) +2025-04-18 11:12:08,126 - train: [ INFO] - Eval : 57 Time: 4.641 (4.641) Loss: 2.0690 (2.0690) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:12:11,869 - train: [ INFO] - Eval : 57 Time: 0.057 (0.164) Loss: 1.8156 (1.8496) Acc@1: 56.2500 (54.3505)Acc@5: 78.1250 (80.3309) +2025-04-18 11:12:12,960 - train: [ INFO] - Eval : 57 Time: 0.014 (0.116) Loss: 3.0755 (1.8789) Acc@1: 50.0000 (53.4310)Acc@5: 50.0000 (78.8358) +2025-04-18 11:12:22,640 - train: [ INFO] - Train: 58 [ 0/461 ( 0%)] Loss: 2.806853 (2.8069) Loss_single: 2.123705 (2.1237) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.841s, 4.68/s (6.841s, 4.68/s) LR: 5.000e-03 Data: 6.666 (6.666) +2025-04-18 11:12:30,740 - train: [ INFO] - Train: 58 [ 50/461 ( 11%)] Loss: 2.699113 (2.7530) Loss_single: 2.030086 (2.0769) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.103s, 310.78/s (0.271s, 117.89/s) LR: 5.000e-03 Data: 0.000 (0.138) +2025-04-18 11:12:36,664 - train: [ INFO] - Train: 58 [ 100/461 ( 22%)] Loss: 2.733845 (2.7466) Loss_single: 2.054440 (2.0694) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 348.97/s (0.195s, 163.78/s) LR: 5.000e-03 Data: 0.001 (0.070) +2025-04-18 11:12:42,656 - train: [ INFO] - Train: 58 [ 150/461 ( 33%)] Loss: 2.858160 (2.7745) Loss_single: 2.178256 (2.0966) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.118s, 270.56/s (0.170s, 188.32/s) LR: 5.000e-03 Data: 0.001 (0.047) +2025-04-18 11:12:49,330 - train: [ INFO] - Train: 58 [ 200/461 ( 43%)] Loss: 2.733987 (2.7664) Loss_single: 2.060125 (2.0893) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 409.37/s (0.155s, 206.41/s) LR: 5.000e-03 Data: 0.000 (0.035) +2025-04-18 11:12:55,207 - train: [ INFO] - Train: 58 [ 250/461 ( 54%)] Loss: 3.110219 (2.8237) Loss_single: 2.418188 (2.1441) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.111s, 289.30/s (0.147s, 217.06/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-18 11:13:00,715 - train: [ INFO] - Train: 58 [ 300/461 ( 65%)] Loss: 3.006876 (2.8499) Loss_single: 2.318779 (2.1691) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 341.73/s (0.141s, 226.74/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-18 11:13:06,165 - train: [ INFO] - Train: 58 [ 350/461 ( 76%)] Loss: 2.632933 (2.8227) Loss_single: 1.943758 (2.1409) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.124s, 257.69/s (0.136s, 234.50/s) LR: 5.000e-03 Data: 0.000 (0.021) +2025-04-18 11:13:13,432 - train: [ INFO] - Train: 58 [ 400/461 ( 87%)] Loss: 2.688170 (2.8078) Loss_single: 2.004810 (2.1258) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.085s, 377.80/s (0.134s, 238.08/s) LR: 5.000e-03 Data: 0.000 (0.018) +2025-04-18 11:13:19,183 - train: [ INFO] - Train: 58 [ 450/461 ( 98%)] Loss: 2.968382 (2.8239) Loss_single: 2.285665 (2.1418) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 365.27/s (0.132s, 242.12/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 11:13:20,056 - train: [ INFO] - Train: 58 [ 460/461 (100%)] Loss: 3.101995 (2.8491) Loss_single: 2.409679 (2.1661) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.137s, 232.94/s (0.131s, 243.95/s) LR: 5.000e-03 Data: 0.000 (0.016) +2025-04-18 11:13:25,973 - train: [ INFO] - Eval : 58 Time: 5.556 (5.556) Loss: 2.0824 (2.0824) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-18 11:13:29,790 - train: [ INFO] - Eval : 58 Time: 0.072 (0.184) Loss: 1.7496 (1.8747) Acc@1: 59.3750 (52.2672)Acc@5: 78.1250 (79.7181) +2025-04-18 11:13:32,032 - train: [ INFO] - Eval : 58 Time: 0.015 (0.142) Loss: 2.6077 (1.9000) Acc@1: 50.0000 (51.7348)Acc@5: 50.0000 (79.2598) +2025-04-18 11:13:44,128 - train: [ INFO] - Train: 59 [ 0/461 ( 0%)] Loss: 2.884233 (2.8842) Loss_single: 2.135391 (2.1354) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 8.605s, 3.72/s (8.605s, 3.72/s) LR: 5.000e-03 Data: 8.422 (8.422) +2025-04-18 11:13:54,603 - train: [ INFO] - Train: 59 [ 50/461 ( 11%)] Loss: 3.253294 (3.0688) Loss_single: 2.572427 (2.3539) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.143s, 223.92/s (0.354s, 90.48/s) LR: 5.000e-03 Data: 0.000 (0.256) +2025-04-18 11:14:01,902 - train: [ INFO] - Train: 59 [ 100/461 ( 22%)] Loss: 2.848682 (2.9954) Loss_single: 2.164515 (2.2908) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.080s, 398.29/s (0.248s, 129.22/s) LR: 5.000e-03 Data: 0.001 (0.146) +2025-04-18 11:14:18,580 - train: [ INFO] - Train: 59 [ 150/461 ( 33%)] Loss: 2.936864 (2.9808) Loss_single: 2.252477 (2.2812) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.302s, 106.06/s (0.239s, 133.83/s) LR: 5.000e-03 Data: 0.210 (0.138) +2025-04-18 11:14:39,017 - train: [ INFO] - Train: 59 [ 200/461 ( 43%)] Loss: 2.880341 (2.9607) Loss_single: 2.171520 (2.2593) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.078s, 409.44/s (0.260s, 123.09/s) LR: 5.000e-03 Data: 0.000 (0.161) +2025-04-18 11:15:00,155 - train: [ INFO] - Train: 59 [ 250/461 ( 54%)] Loss: 3.156076 (2.9932) Loss_single: 2.472643 (2.2948) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.080s, 400.26/s (0.272s, 117.78/s) LR: 5.000e-03 Data: 0.000 (0.173) +2025-04-18 11:15:20,728 - train: [ INFO] - Train: 59 [ 300/461 ( 65%)] Loss: 2.796423 (2.9651) Loss_single: 2.103592 (2.2675) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.087s, 368.19/s (0.276s, 115.86/s) LR: 5.000e-03 Data: 0.001 (0.179) +2025-04-18 11:15:37,111 - train: [ INFO] - Train: 59 [ 350/461 ( 76%)] Loss: 2.743587 (2.9374) Loss_single: 2.058090 (2.2413) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.094s, 341.28/s (0.271s, 117.97/s) LR: 5.000e-03 Data: 0.001 (0.174) +2025-04-18 11:16:01,268 - train: [ INFO] - Train: 59 [ 400/461 ( 87%)] Loss: 2.649325 (2.9054) Loss_single: 1.972910 (2.2115) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 2.562s, 12.49/s (0.289s, 110.90/s) LR: 5.000e-03 Data: 2.407 (0.192) +2025-04-18 11:16:18,251 - train: [ INFO] - Train: 59 [ 450/461 ( 98%)] Loss: 3.044463 (2.9193) Loss_single: 2.349321 (2.2253) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.148s, 216.83/s (0.285s, 112.13/s) LR: 5.000e-03 Data: 0.000 (0.189) +2025-04-18 11:16:19,614 - train: [ INFO] - Train: 59 [ 460/461 (100%)] Loss: 2.586279 (2.8891) Loss_single: 1.897959 (2.1955) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.075s, 424.46/s (0.281s, 113.90/s) LR: 5.000e-03 Data: 0.000 (0.185) +2025-04-18 11:16:29,228 - train: [ INFO] - Eval : 59 Time: 9.270 (9.270) Loss: 2.0305 (2.0305) Acc@1: 59.3750 (59.3750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:16:42,711 - train: [ INFO] - Eval : 59 Time: 0.028 (0.446) Loss: 1.8980 (1.8618) Acc@1: 56.2500 (53.3701)Acc@5: 68.7500 (80.5147) +2025-04-18 11:16:55,302 - train: [ INFO] - Eval : 59 Time: 0.016 (0.431) Loss: 2.9207 (1.8858) Acc@1: 50.0000 (53.0069)Acc@5: 50.0000 (79.2984) +2025-04-18 11:17:10,283 - train: [ INFO] - Train: 60 [ 0/461 ( 0%)] Loss: 2.544673 (2.5447) Loss_single: 1.873240 (1.8732) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 9.724s, 3.29/s (9.724s, 3.29/s) LR: 5.000e-03 Data: 9.540 (9.540) +2025-04-18 11:17:27,215 - train: [ INFO] - Train: 60 [ 50/461 ( 11%)] Loss: 2.897582 (2.7211) Loss_single: 2.210773 (2.0420) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 1.325s, 24.15/s (0.483s, 66.25/s) LR: 5.000e-03 Data: 1.232 (0.389) +2025-04-18 11:17:40,919 - train: [ INFO] - Train: 60 [ 100/461 ( 22%)] Loss: 2.740715 (2.7277) Loss_single: 2.023447 (2.0358) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 395.59/s (0.361s, 88.60/s) LR: 5.000e-03 Data: 0.000 (0.271) +2025-04-18 11:17:55,281 - train: [ INFO] - Train: 60 [ 150/461 ( 33%)] Loss: 2.783537 (2.7416) Loss_single: 2.110267 (2.0544) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 389.34/s (0.320s, 100.06/s) LR: 5.000e-03 Data: 0.000 (0.229) +2025-04-18 11:18:05,518 - train: [ INFO] - Train: 60 [ 200/461 ( 43%)] Loss: 3.032157 (2.7997) Loss_single: 2.343946 (2.1123) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 406.12/s (0.289s, 110.79/s) LR: 5.000e-03 Data: 0.000 (0.199) +2025-04-18 11:18:13,614 - train: [ INFO] - Train: 60 [ 250/461 ( 54%)] Loss: 2.914118 (2.8188) Loss_single: 2.235332 (2.1328) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 385.15/s (0.261s, 122.50/s) LR: 5.000e-03 Data: 0.000 (0.173) +2025-04-18 11:18:20,469 - train: [ INFO] - Train: 60 [ 300/461 ( 65%)] Loss: 2.929899 (2.8347) Loss_single: 2.251703 (2.1498) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 416.19/s (0.241s, 133.05/s) LR: 5.000e-03 Data: 0.000 (0.152) +2025-04-18 11:18:28,159 - train: [ INFO] - Train: 60 [ 350/461 ( 76%)] Loss: 2.724665 (2.8209) Loss_single: 2.046770 (2.1369) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.105s, 305.77/s (0.228s, 140.31/s) LR: 5.000e-03 Data: 0.000 (0.140) +2025-04-18 11:18:36,543 - train: [ INFO] - Train: 60 [ 400/461 ( 87%)] Loss: 2.977128 (2.8383) Loss_single: 2.291850 (2.1541) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.563s, 56.80/s (0.217s, 147.35/s) LR: 5.000e-03 Data: 0.430 (0.126) +2025-04-18 11:18:42,096 - train: [ INFO] - Train: 60 [ 450/461 ( 98%)] Loss: 3.083172 (2.8628) Loss_single: 2.402010 (2.1789) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.102s, 313.46/s (0.205s, 155.88/s) LR: 5.000e-03 Data: 0.000 (0.112) +2025-04-18 11:18:43,001 - train: [ INFO] - Train: 60 [ 460/461 (100%)] Loss: 2.897198 (2.8659) Loss_single: 2.168659 (2.1780) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 393.50/s (0.203s, 157.82/s) LR: 5.000e-03 Data: 0.000 (0.109) +2025-04-18 11:18:47,516 - train: [ INFO] - Eval : 60 Time: 4.209 (4.209) Loss: 2.0036 (2.0036) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 11:18:52,901 - train: [ INFO] - Eval : 60 Time: 0.076 (0.188) Loss: 1.7899 (1.8532) Acc@1: 62.5000 (54.2892)Acc@5: 78.1250 (80.3922) +2025-04-18 11:18:55,364 - train: [ INFO] - Eval : 60 Time: 0.014 (0.147) Loss: 2.9358 (1.8707) Acc@1: 50.0000 (53.7394)Acc@5: 50.0000 (79.6839) +2025-04-18 11:19:07,627 - train: [ INFO] - Train: 61 [ 0/461 ( 0%)] Loss: 2.843726 (2.8437) Loss_single: 2.168535 (2.1685) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.796s, 4.71/s (6.796s, 4.71/s) LR: 5.000e-03 Data: 6.633 (6.633) +2025-04-18 11:19:18,590 - train: [ INFO] - Train: 61 [ 50/461 ( 11%)] Loss: 2.520462 (2.6821) Loss_single: 1.846804 (2.0077) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.112s, 285.07/s (0.322s, 99.23/s) LR: 5.000e-03 Data: 0.001 (0.225) +2025-04-18 11:19:29,155 - train: [ INFO] - Train: 61 [ 100/461 ( 22%)] Loss: 2.607579 (2.6573) Loss_single: 1.928687 (1.9813) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 413.00/s (0.237s, 134.89/s) LR: 5.000e-03 Data: 0.000 (0.143) +2025-04-18 11:19:38,635 - train: [ INFO] - Train: 61 [ 150/461 ( 33%)] Loss: 2.809084 (2.6952) Loss_single: 2.133093 (2.0193) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.77/s (0.218s, 146.70/s) LR: 5.000e-03 Data: 0.000 (0.125) +2025-04-18 11:19:48,173 - train: [ INFO] - Train: 61 [ 200/461 ( 43%)] Loss: 2.891865 (2.7345) Loss_single: 2.210868 (2.0576) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.077s, 414.13/s (0.210s, 152.67/s) LR: 5.000e-03 Data: 0.000 (0.117) +2025-04-18 11:19:59,573 - train: [ INFO] - Train: 61 [ 250/461 ( 54%)] Loss: 3.124310 (2.7995) Loss_single: 2.350143 (2.1064) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 96.8750 (99.4792) Time: 0.079s, 404.75/s (0.209s, 153.33/s) LR: 5.000e-03 Data: 0.000 (0.116) +2025-04-18 11:20:07,625 - train: [ INFO] - Train: 61 [ 300/461 ( 65%)] Loss: 2.796003 (2.7990) Loss_single: 2.091686 (2.1043) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.091s, 352.21/s (0.201s, 159.60/s) LR: 5.000e-03 Data: 0.001 (0.106) +2025-04-18 11:20:15,751 - train: [ INFO] - Train: 61 [ 350/461 ( 76%)] Loss: 2.848732 (2.8052) Loss_single: 2.157971 (2.1110) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.111s, 288.30/s (0.195s, 164.10/s) LR: 5.000e-03 Data: 0.001 (0.100) +2025-04-18 11:20:22,917 - train: [ INFO] - Train: 61 [ 400/461 ( 87%)] Loss: 3.220558 (2.8514) Loss_single: 2.465450 (2.1504) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.239s, 133.92/s (0.188s, 169.82/s) LR: 5.000e-03 Data: 0.124 (0.092) +2025-04-18 11:20:30,057 - train: [ INFO] - Train: 61 [ 450/461 ( 98%)] Loss: 2.747069 (2.8409) Loss_single: 2.043029 (2.1396) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.075s, 427.16/s (0.183s, 174.79/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-18 11:20:31,034 - train: [ INFO] - Train: 61 [ 460/461 (100%)] Loss: 2.930056 (2.8490) Loss_single: 2.215817 (2.1466) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.077s, 415.34/s (0.181s, 176.61/s) LR: 5.000e-03 Data: 0.000 (0.083) +2025-04-18 11:20:37,710 - train: [ INFO] - Eval : 61 Time: 6.216 (6.216) Loss: 2.1748 (2.1748) Acc@1: 40.6250 (40.6250)Acc@5: 78.1250 (78.1250) +2025-04-18 11:20:43,362 - train: [ INFO] - Eval : 61 Time: 0.063 (0.233) Loss: 1.9207 (1.9099) Acc@1: 53.1250 (52.9412)Acc@5: 78.1250 (78.3701) +2025-04-18 11:20:47,352 - train: [ INFO] - Eval : 61 Time: 0.016 (0.193) Loss: 3.3355 (1.9296) Acc@1: 50.0000 (52.1203)Acc@5: 50.0000 (78.0648) +2025-04-18 11:20:59,964 - train: [ INFO] - Train: 62 [ 0/461 ( 0%)] Loss: 2.665666 (2.6657) Loss_single: 1.988889 (1.9889) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 9.644s, 3.32/s (9.644s, 3.32/s) LR: 5.000e-03 Data: 9.477 (9.477) +2025-04-18 11:21:08,621 - train: [ INFO] - Train: 62 [ 50/461 ( 11%)] Loss: 2.724797 (2.6952) Loss_single: 2.037753 (2.0133) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 410.08/s (0.336s, 95.25/s) LR: 5.000e-03 Data: 0.000 (0.243) +2025-04-18 11:21:17,685 - train: [ INFO] - Train: 62 [ 100/461 ( 22%)] Loss: 2.987938 (2.7928) Loss_single: 2.308540 (2.1117) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.169s, 189.70/s (0.259s, 123.56/s) LR: 5.000e-03 Data: 0.001 (0.167) +2025-04-18 11:21:27,501 - train: [ INFO] - Train: 62 [ 150/461 ( 33%)] Loss: 2.814764 (2.7983) Loss_single: 2.144175 (2.1198) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 391.96/s (0.238s, 134.69/s) LR: 5.000e-03 Data: 0.000 (0.146) +2025-04-18 11:21:34,725 - train: [ INFO] - Train: 62 [ 200/461 ( 43%)] Loss: 3.336102 (2.9059) Loss_single: 2.642110 (2.2243) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.094s, 339.13/s (0.214s, 149.37/s) LR: 5.000e-03 Data: 0.000 (0.121) +2025-04-18 11:21:42,324 - train: [ INFO] - Train: 62 [ 250/461 ( 54%)] Loss: 2.627260 (2.8594) Loss_single: 1.952463 (2.1790) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.110s, 290.53/s (0.202s, 158.68/s) LR: 5.000e-03 Data: 0.001 (0.105) +2025-04-18 11:21:48,335 - train: [ INFO] - Train: 62 [ 300/461 ( 65%)] Loss: 2.614024 (2.8244) Loss_single: 1.936670 (2.1444) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 405.84/s (0.188s, 170.24/s) LR: 5.000e-03 Data: 0.000 (0.089) +2025-04-18 11:21:55,504 - train: [ INFO] - Train: 62 [ 350/461 ( 76%)] Loss: 2.718832 (2.8112) Loss_single: 2.049646 (2.1325) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.114s, 281.13/s (0.182s, 176.30/s) LR: 5.000e-03 Data: 0.001 (0.082) +2025-04-18 11:22:02,484 - train: [ INFO] - Train: 62 [ 400/461 ( 87%)] Loss: 2.841359 (2.8145) Loss_single: 2.123218 (2.1315) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.157s, 203.76/s (0.176s, 181.64/s) LR: 5.000e-03 Data: 0.000 (0.077) +2025-04-18 11:22:09,260 - train: [ INFO] - Train: 62 [ 450/461 ( 98%)] Loss: 2.880377 (2.8211) Loss_single: 2.179258 (2.1363) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 406.80/s (0.169s, 189.45/s) LR: 5.000e-03 Data: 0.000 (0.069) +2025-04-18 11:22:10,190 - train: [ INFO] - Train: 62 [ 460/461 (100%)] Loss: 2.797151 (2.8189) Loss_single: 2.041149 (2.1276) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 96.8750 (99.7159) Time: 0.081s, 394.73/s (0.167s, 191.35/s) LR: 5.000e-03 Data: 0.000 (0.068) +2025-04-18 11:22:15,805 - train: [ INFO] - Eval : 62 Time: 5.339 (5.339) Loss: 2.0467 (2.0467) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:22:23,907 - train: [ INFO] - Eval : 62 Time: 0.075 (0.264) Loss: 1.8126 (1.8760) Acc@1: 62.5000 (54.2279)Acc@5: 71.8750 (78.7377) +2025-04-18 11:22:26,184 - train: [ INFO] - Eval : 62 Time: 0.015 (0.192) Loss: 3.5380 (1.9070) Acc@1: 50.0000 (53.0840)Acc@5: 50.0000 (77.6793) +2025-04-18 11:22:37,256 - train: [ INFO] - Train: 63 [ 0/461 ( 0%)] Loss: 2.904201 (2.9042) Loss_single: 2.134255 (2.1343) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 7.901s, 4.05/s (7.901s, 4.05/s) LR: 5.000e-03 Data: 7.777 (7.777) +2025-04-18 11:22:45,067 - train: [ INFO] - Train: 63 [ 50/461 ( 11%)] Loss: 3.028482 (2.9663) Loss_single: 2.327591 (2.2309) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.132s, 243.04/s (0.305s, 104.81/s) LR: 5.000e-03 Data: 0.003 (0.208) +2025-04-18 11:22:52,435 - train: [ INFO] - Train: 63 [ 100/461 ( 22%)] Loss: 3.001862 (2.9782) Loss_single: 2.273635 (2.2452) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.080s, 399.76/s (0.226s, 141.31/s) LR: 5.000e-03 Data: 0.000 (0.136) +2025-04-18 11:22:59,421 - train: [ INFO] - Train: 63 [ 150/461 ( 33%)] Loss: 2.843843 (2.9446) Loss_single: 2.144482 (2.2200) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.085s, 374.32/s (0.197s, 162.07/s) LR: 5.000e-03 Data: 0.001 (0.106) +2025-04-18 11:23:05,534 - train: [ INFO] - Train: 63 [ 200/461 ( 43%)] Loss: 2.668478 (2.8894) Loss_single: 1.988702 (2.1737) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.114s, 279.96/s (0.178s, 179.55/s) LR: 5.000e-03 Data: 0.000 (0.082) +2025-04-18 11:23:11,498 - train: [ INFO] - Train: 63 [ 250/461 ( 54%)] Loss: 2.600359 (2.8412) Loss_single: 1.918476 (2.1312) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.103s, 311.96/s (0.166s, 192.40/s) LR: 5.000e-03 Data: 0.000 (0.069) +2025-04-18 11:23:17,803 - train: [ INFO] - Train: 63 [ 300/461 ( 65%)] Loss: 3.092710 (2.8771) Loss_single: 2.411809 (2.1713) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.127s, 252.20/s (0.159s, 200.91/s) LR: 5.000e-03 Data: 0.001 (0.058) +2025-04-18 11:23:24,026 - train: [ INFO] - Train: 63 [ 350/461 ( 76%)] Loss: 2.990219 (2.8913) Loss_single: 2.315826 (2.1893) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.129s, 247.57/s (0.152s, 210.60/s) LR: 5.000e-03 Data: 0.001 (0.050) +2025-04-18 11:23:35,546 - train: [ INFO] - Train: 63 [ 400/461 ( 87%)] Loss: 2.719301 (2.8722) Loss_single: 2.045860 (2.1734) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 1.066s, 30.01/s (0.160s, 200.35/s) LR: 5.000e-03 Data: 0.950 (0.058) +2025-04-18 11:23:43,179 - train: [ INFO] - Train: 63 [ 450/461 ( 98%)] Loss: 3.101415 (2.8951) Loss_single: 2.329660 (2.1890) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 96.8750 (99.3750) Time: 0.082s, 391.11/s (0.157s, 203.96/s) LR: 5.000e-03 Data: 0.000 (0.054) +2025-04-18 11:23:44,009 - train: [ INFO] - Train: 63 [ 460/461 (100%)] Loss: 3.058688 (2.9100) Loss_single: 2.376378 (2.2061) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.4318) Time: 0.082s, 388.31/s (0.155s, 206.10/s) LR: 5.000e-03 Data: 0.000 (0.053) +2025-04-18 11:23:49,373 - train: [ INFO] - Eval : 63 Time: 5.100 (5.100) Loss: 2.0936 (2.0936) Acc@1: 40.6250 (40.6250)Acc@5: 78.1250 (78.1250) +2025-04-18 11:24:00,081 - train: [ INFO] - Eval : 63 Time: 0.056 (0.310) Loss: 1.9255 (1.8722) Acc@1: 59.3750 (54.7181)Acc@5: 78.1250 (78.4314) +2025-04-18 11:24:06,147 - train: [ INFO] - Eval : 63 Time: 0.017 (0.267) Loss: 2.6279 (1.8959) Acc@1: 50.0000 (53.7779)Acc@5: 50.0000 (77.4865) +2025-04-18 11:24:18,820 - train: [ INFO] - Train: 64 [ 0/461 ( 0%)] Loss: 2.938547 (2.9385) Loss_single: 2.189938 (2.1899) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 96.8750 (96.8750) Time: 9.129s, 3.51/s (9.129s, 3.51/s) LR: 5.000e-03 Data: 8.956 (8.956) +2025-04-18 11:24:29,387 - train: [ INFO] - Train: 64 [ 50/461 ( 11%)] Loss: 2.831810 (2.8852) Loss_single: 2.157152 (2.1735) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (98.4375) Time: 0.106s, 302.45/s (0.370s, 86.57/s) LR: 5.000e-03 Data: 0.000 (0.269) +2025-04-18 11:24:36,641 - train: [ INFO] - Train: 64 [ 100/461 ( 22%)] Loss: 2.781175 (2.8505) Loss_single: 2.095521 (2.1475) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.112s, 284.56/s (0.258s, 124.04/s) LR: 5.000e-03 Data: 0.000 (0.152) +2025-04-18 11:24:43,415 - train: [ INFO] - Train: 64 [ 150/461 ( 33%)] Loss: 2.841566 (2.8483) Loss_single: 2.173271 (2.1540) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.089s, 359.13/s (0.217s, 147.60/s) LR: 5.000e-03 Data: 0.001 (0.110) +2025-04-18 11:24:49,860 - train: [ INFO] - Train: 64 [ 200/461 ( 43%)] Loss: 2.842944 (2.8472) Loss_single: 2.168608 (2.1569) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.078s, 410.73/s (0.195s, 164.36/s) LR: 5.000e-03 Data: 0.000 (0.086) +2025-04-18 11:24:55,879 - train: [ INFO] - Train: 64 [ 250/461 ( 54%)] Loss: 3.070166 (2.8844) Loss_single: 2.294287 (2.1798) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.192s, 167.03/s (0.179s, 178.44/s) LR: 5.000e-03 Data: 0.000 (0.069) +2025-04-18 11:25:01,884 - train: [ INFO] - Train: 64 [ 300/461 ( 65%)] Loss: 3.099883 (2.9152) Loss_single: 2.423257 (2.2146) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.1071) Time: 0.171s, 186.64/s (0.169s, 189.03/s) LR: 5.000e-03 Data: 0.003 (0.058) +2025-04-18 11:25:07,972 - train: [ INFO] - Train: 64 [ 350/461 ( 76%)] Loss: 2.691380 (2.8872) Loss_single: 2.018497 (2.1901) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.140s, 228.64/s (0.162s, 197.13/s) LR: 5.000e-03 Data: 0.000 (0.050) +2025-04-18 11:25:15,189 - train: [ INFO] - Train: 64 [ 400/461 ( 87%)] Loss: 2.635427 (2.8592) Loss_single: 1.965504 (2.1651) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.3056) Time: 0.111s, 288.27/s (0.155s, 206.30/s) LR: 5.000e-03 Data: 0.001 (0.044) +2025-04-18 11:25:21,438 - train: [ INFO] - Train: 64 [ 450/461 ( 98%)] Loss: 2.846067 (2.8579) Loss_single: 2.156315 (2.1642) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.223s, 143.60/s (0.152s, 211.06/s) LR: 5.000e-03 Data: 0.083 (0.039) +2025-04-18 11:25:22,937 - train: [ INFO] - Train: 64 [ 460/461 (100%)] Loss: 3.017732 (2.8724) Loss_single: 2.277531 (2.1745) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1477) Acc@5: 100.0000 (99.4318) Time: 0.089s, 360.27/s (0.152s, 211.16/s) LR: 5.000e-03 Data: 0.000 (0.039) +2025-04-18 11:25:28,228 - train: [ INFO] - Eval : 64 Time: 4.811 (4.811) Loss: 2.2076 (2.2076) Acc@1: 34.3750 (34.3750)Acc@5: 78.1250 (78.1250) +2025-04-18 11:25:33,748 - train: [ INFO] - Eval : 64 Time: 0.075 (0.203) Loss: 1.9202 (1.8859) Acc@1: 56.2500 (52.2672)Acc@5: 71.8750 (78.6152) +2025-04-18 11:25:36,313 - train: [ INFO] - Eval : 64 Time: 0.015 (0.157) Loss: 2.9478 (1.9073) Acc@1: 0.0000 (51.5806)Acc@5: 50.0000 (78.2575) +2025-04-18 11:25:48,443 - train: [ INFO] - Train: 65 [ 0/461 ( 0%)] Loss: 2.744979 (2.7450) Loss_single: 2.073462 (2.0735) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.154s, 5.20/s (6.154s, 5.20/s) LR: 5.000e-03 Data: 5.913 (5.913) +2025-04-18 11:25:57,253 - train: [ INFO] - Train: 65 [ 50/461 ( 11%)] Loss: 2.858140 (2.8016) Loss_single: 2.175712 (2.1246) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.140s, 228.44/s (0.292s, 109.56/s) LR: 5.000e-03 Data: 0.027 (0.196) +2025-04-18 11:26:05,306 - train: [ INFO] - Train: 65 [ 100/461 ( 22%)] Loss: 2.641592 (2.7482) Loss_single: 1.934763 (2.0613) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.086s, 373.53/s (0.227s, 141.10/s) LR: 5.000e-03 Data: 0.000 (0.134) +2025-04-18 11:26:12,692 - train: [ INFO] - Train: 65 [ 150/461 ( 33%)] Loss: 3.276427 (2.8803) Loss_single: 2.503200 (2.1718) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.081s, 397.04/s (0.200s, 159.77/s) LR: 5.000e-03 Data: 0.000 (0.107) +2025-04-18 11:26:18,787 - train: [ INFO] - Train: 65 [ 200/461 ( 43%)] Loss: 2.616875 (2.8276) Loss_single: 1.937757 (2.1250) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.080s, 401.38/s (0.181s, 177.21/s) LR: 5.000e-03 Data: 0.000 (0.085) +2025-04-18 11:26:25,324 - train: [ INFO] - Train: 65 [ 250/461 ( 54%)] Loss: 2.784249 (2.8204) Loss_single: 2.112386 (2.1229) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.115s, 278.97/s (0.170s, 187.70/s) LR: 5.000e-03 Data: 0.000 (0.068) +2025-04-18 11:26:32,301 - train: [ INFO] - Train: 65 [ 300/461 ( 65%)] Loss: 2.854750 (2.8253) Loss_single: 2.157527 (2.1278) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.121s, 264.33/s (0.165s, 193.74/s) LR: 5.000e-03 Data: 0.000 (0.057) +2025-04-18 11:26:40,410 - train: [ INFO] - Train: 65 [ 350/461 ( 76%)] Loss: 2.984348 (2.8452) Loss_single: 2.301528 (2.1495) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.223s, 143.43/s (0.158s, 203.08/s) LR: 5.000e-03 Data: 0.060 (0.051) +2025-04-18 11:26:50,011 - train: [ INFO] - Train: 65 [ 400/461 ( 87%)] Loss: 2.856324 (2.8464) Loss_single: 2.186821 (2.1537) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.127s, 252.78/s (0.161s, 198.32/s) LR: 5.000e-03 Data: 0.000 (0.055) +2025-04-18 11:26:57,415 - train: [ INFO] - Train: 65 [ 450/461 ( 98%)] Loss: 2.710100 (2.8328) Loss_single: 2.039435 (2.1423) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.078s, 410.60/s (0.160s, 200.53/s) LR: 5.000e-03 Data: 0.000 (0.053) +2025-04-18 11:26:58,596 - train: [ INFO] - Train: 65 [ 460/461 (100%)] Loss: 3.399511 (2.8843) Loss_single: 2.689218 (2.1920) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.078s, 409.99/s (0.158s, 202.80/s) LR: 5.000e-03 Data: 0.000 (0.052) +2025-04-18 11:27:05,822 - train: [ INFO] - Eval : 65 Time: 6.893 (6.893) Loss: 2.0446 (2.0446) Acc@1: 40.6250 (40.6250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:27:15,139 - train: [ INFO] - Eval : 65 Time: 0.095 (0.318) Loss: 1.9064 (1.8739) Acc@1: 50.0000 (52.6961)Acc@5: 75.0000 (79.8407) +2025-04-18 11:27:20,887 - train: [ INFO] - Eval : 65 Time: 0.019 (0.268) Loss: 2.6172 (1.8860) Acc@1: 50.0000 (52.6214)Acc@5: 50.0000 (78.9514) +2025-04-18 11:27:30,366 - train: [ INFO] - Train: 66 [ 0/461 ( 0%)] Loss: 2.832588 (2.8326) Loss_single: 2.160146 (2.1601) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.121s, 7.76/s (4.121s, 7.76/s) LR: 5.000e-03 Data: 3.941 (3.941) +2025-04-18 11:27:37,826 - train: [ INFO] - Train: 66 [ 50/461 ( 11%)] Loss: 2.676209 (2.7544) Loss_single: 1.999987 (2.0801) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.162s, 197.61/s (0.226s, 141.55/s) LR: 5.000e-03 Data: 0.000 (0.116) +2025-04-18 11:27:43,488 - train: [ INFO] - Train: 66 [ 100/461 ( 22%)] Loss: 2.714345 (2.7410) Loss_single: 2.038090 (2.0661) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 386.05/s (0.170s, 188.67/s) LR: 5.000e-03 Data: 0.001 (0.064) +2025-04-18 11:27:49,806 - train: [ INFO] - Train: 66 [ 150/461 ( 33%)] Loss: 2.751912 (2.7438) Loss_single: 2.076264 (2.0686) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.152s, 211.13/s (0.155s, 206.48/s) LR: 5.000e-03 Data: 0.001 (0.043) +2025-04-18 11:27:55,580 - train: [ INFO] - Train: 66 [ 200/461 ( 43%)] Loss: 2.739341 (2.7429) Loss_single: 2.065518 (2.0680) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.120s, 266.09/s (0.145s, 220.94/s) LR: 5.000e-03 Data: 0.000 (0.033) +2025-04-18 11:28:01,637 - train: [ INFO] - Train: 66 [ 250/461 ( 54%)] Loss: 2.796467 (2.7518) Loss_single: 2.123351 (2.0772) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.157s, 203.79/s (0.140s, 228.65/s) LR: 5.000e-03 Data: 0.000 (0.027) +2025-04-18 11:28:08,989 - train: [ INFO] - Train: 66 [ 300/461 ( 65%)] Loss: 2.669583 (2.7401) Loss_single: 1.989880 (2.0647) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.259s, 123.75/s (0.134s, 238.15/s) LR: 5.000e-03 Data: 0.124 (0.023) +2025-04-18 11:28:16,356 - train: [ INFO] - Train: 66 [ 350/461 ( 76%)] Loss: 3.198905 (2.7974) Loss_single: 2.488781 (2.1178) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.173s, 185.29/s (0.136s, 235.16/s) LR: 5.000e-03 Data: 0.001 (0.024) +2025-04-18 11:28:23,190 - train: [ INFO] - Train: 66 [ 400/461 ( 87%)] Loss: 2.740681 (2.7911) Loss_single: 2.067495 (2.1122) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.172s, 186.14/s (0.136s, 235.22/s) LR: 5.000e-03 Data: 0.001 (0.022) +2025-04-18 11:28:29,709 - train: [ INFO] - Train: 66 [ 450/461 ( 98%)] Loss: 3.038695 (2.8159) Loss_single: 2.299202 (2.1309) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 382.10/s (0.134s, 238.90/s) LR: 5.000e-03 Data: 0.000 (0.020) +2025-04-18 11:28:30,555 - train: [ INFO] - Train: 66 [ 460/461 (100%)] Loss: 2.931302 (2.8264) Loss_single: 2.259207 (2.1425) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 397.66/s (0.133s, 240.86/s) LR: 5.000e-03 Data: 0.000 (0.019) +2025-04-18 11:28:37,895 - train: [ INFO] - Eval : 66 Time: 7.017 (7.017) Loss: 2.1916 (2.1916) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 11:28:53,190 - train: [ INFO] - Eval : 66 Time: 0.050 (0.437) Loss: 1.7708 (1.8847) Acc@1: 65.6250 (52.3284)Acc@5: 71.8750 (79.7181) +2025-04-18 11:29:01,737 - train: [ INFO] - Eval : 66 Time: 0.018 (0.376) Loss: 2.5183 (1.9078) Acc@1: 50.0000 (51.5806)Acc@5: 50.0000 (79.0285) +2025-04-18 11:29:14,362 - train: [ INFO] - Train: 67 [ 0/461 ( 0%)] Loss: 3.056406 (3.0564) Loss_single: 2.354783 (2.3548) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 8.657s, 3.70/s (8.657s, 3.70/s) LR: 5.000e-03 Data: 8.548 (8.548) +2025-04-18 11:29:27,548 - train: [ INFO] - Train: 67 [ 50/461 ( 11%)] Loss: 2.790791 (2.9236) Loss_single: 2.108419 (2.2316) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.109s, 293.22/s (0.391s, 81.87/s) LR: 5.000e-03 Data: 0.000 (0.302) +2025-04-18 11:29:40,319 - train: [ INFO] - Train: 67 [ 100/461 ( 22%)] Loss: 2.728307 (2.8585) Loss_single: 2.058467 (2.1739) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 362.54/s (0.304s, 105.23/s) LR: 5.000e-03 Data: 0.000 (0.215) +2025-04-18 11:29:50,397 - train: [ INFO] - Train: 67 [ 150/461 ( 33%)] Loss: 2.784527 (2.8400) Loss_single: 2.078484 (2.1500) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.080s, 398.22/s (0.265s, 120.95/s) LR: 5.000e-03 Data: 0.000 (0.176) +2025-04-18 11:29:58,930 - train: [ INFO] - Train: 67 [ 200/461 ( 43%)] Loss: 2.487651 (2.7695) Loss_single: 1.810907 (2.0822) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.081s, 393.38/s (0.240s, 133.18/s) LR: 5.000e-03 Data: 0.000 (0.152) +2025-04-18 11:30:06,228 - train: [ INFO] - Train: 67 [ 250/461 ( 54%)] Loss: 2.858450 (2.7844) Loss_single: 2.163113 (2.0957) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.079s, 403.44/s (0.221s, 144.58/s) LR: 5.000e-03 Data: 0.000 (0.134) +2025-04-18 11:30:14,503 - train: [ INFO] - Train: 67 [ 300/461 ( 65%)] Loss: 2.840702 (2.7924) Loss_single: 2.139085 (2.1019) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.080s, 398.37/s (0.205s, 156.04/s) LR: 5.000e-03 Data: 0.000 (0.113) +2025-04-18 11:30:25,486 - train: [ INFO] - Train: 67 [ 350/461 ( 76%)] Loss: 2.963422 (2.8138) Loss_single: 2.282024 (2.1244) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.078s, 410.00/s (0.205s, 156.22/s) LR: 5.000e-03 Data: 0.000 (0.112) +2025-04-18 11:30:38,439 - train: [ INFO] - Train: 67 [ 400/461 ( 87%)] Loss: 3.250114 (2.8623) Loss_single: 2.352975 (2.1498) Loss_inverse: 0.000000 (0.0000) Acc@1: 90.6250 (98.6111) Acc@5: 93.7500 (99.3056) Time: 1.390s, 23.02/s (0.211s, 151.90/s) LR: 5.000e-03 Data: 1.309 (0.117) +2025-04-18 11:30:50,312 - train: [ INFO] - Train: 67 [ 450/461 ( 98%)] Loss: 2.673273 (2.8434) Loss_single: 1.996464 (2.1345) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (99.3750) Time: 0.098s, 327.18/s (0.213s, 150.33/s) LR: 5.000e-03 Data: 0.000 (0.119) +2025-04-18 11:30:51,652 - train: [ INFO] - Train: 67 [ 460/461 (100%)] Loss: 2.712812 (2.8315) Loss_single: 1.968002 (2.1193) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.5795) Acc@5: 100.0000 (99.4318) Time: 0.081s, 395.97/s (0.211s, 151.61/s) LR: 5.000e-03 Data: 0.000 (0.118) +2025-04-18 11:30:58,816 - train: [ INFO] - Eval : 67 Time: 6.888 (6.888) Loss: 2.1984 (2.1984) Acc@1: 43.7500 (43.7500)Acc@5: 71.8750 (71.8750) +2025-04-18 11:31:14,617 - train: [ INFO] - Eval : 67 Time: 0.029 (0.445) Loss: 1.8070 (1.8840) Acc@1: 59.3750 (53.1250)Acc@5: 84.3750 (80.0245) +2025-04-18 11:31:20,971 - train: [ INFO] - Eval : 67 Time: 0.024 (0.354) Loss: 2.7633 (1.9043) Acc@1: 50.0000 (52.3516)Acc@5: 50.0000 (79.1056) +2025-04-18 11:31:29,999 - train: [ INFO] - Train: 68 [ 0/461 ( 0%)] Loss: 2.725630 (2.7256) Loss_single: 2.048272 (2.0483) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.440s, 5.88/s (5.440s, 5.88/s) LR: 5.000e-03 Data: 5.297 (5.297) +2025-04-18 11:31:37,255 - train: [ INFO] - Train: 68 [ 50/461 ( 11%)] Loss: 2.515558 (2.6206) Loss_single: 1.833119 (1.9407) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 393.20/s (0.248s, 129.21/s) LR: 5.000e-03 Data: 0.000 (0.157) +2025-04-18 11:31:45,387 - train: [ INFO] - Train: 68 [ 100/461 ( 22%)] Loss: 2.984548 (2.7419) Loss_single: 2.289004 (2.0568) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.085s, 377.29/s (0.205s, 155.94/s) LR: 5.000e-03 Data: 0.000 (0.114) +2025-04-18 11:31:53,613 - train: [ INFO] - Train: 68 [ 150/461 ( 33%)] Loss: 2.946934 (2.7932) Loss_single: 2.273995 (2.1111) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 387.44/s (0.191s, 167.75/s) LR: 5.000e-03 Data: 0.000 (0.101) +2025-04-18 11:32:00,903 - train: [ INFO] - Train: 68 [ 200/461 ( 43%)] Loss: 3.166340 (2.8678) Loss_single: 2.447984 (2.1785) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.112s, 284.96/s (0.179s, 178.43/s) LR: 5.000e-03 Data: 0.001 (0.085) +2025-04-18 11:32:07,525 - train: [ INFO] - Train: 68 [ 250/461 ( 54%)] Loss: 2.647762 (2.8311) Loss_single: 1.971815 (2.1440) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.132s, 241.94/s (0.170s, 188.49/s) LR: 5.000e-03 Data: 0.001 (0.068) +2025-04-18 11:32:13,019 - train: [ INFO] - Train: 68 [ 300/461 ( 65%)] Loss: 2.707280 (2.8134) Loss_single: 2.007651 (2.1245) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 400.24/s (0.160s, 200.38/s) LR: 5.000e-03 Data: 0.001 (0.057) +2025-04-18 11:32:18,872 - train: [ INFO] - Train: 68 [ 350/461 ( 76%)] Loss: 2.898436 (2.8241) Loss_single: 2.173419 (2.1307) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.108s, 295.25/s (0.153s, 208.47/s) LR: 5.000e-03 Data: 0.000 (0.049) +2025-04-18 11:32:24,165 - train: [ INFO] - Train: 68 [ 400/461 ( 87%)] Loss: 3.041996 (2.8483) Loss_single: 2.361694 (2.1563) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.155s, 206.41/s (0.147s, 216.97/s) LR: 5.000e-03 Data: 0.001 (0.043) +2025-04-18 11:32:31,546 - train: [ INFO] - Train: 68 [ 450/461 ( 98%)] Loss: 3.045766 (2.8680) Loss_single: 2.373635 (2.1781) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.109s, 294.34/s (0.143s, 223.74/s) LR: 5.000e-03 Data: 0.000 (0.039) +2025-04-18 11:32:32,646 - train: [ INFO] - Train: 68 [ 460/461 (100%)] Loss: 2.584492 (2.8422) Loss_single: 1.913082 (2.1540) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.087s, 368.50/s (0.142s, 225.42/s) LR: 5.000e-03 Data: 0.000 (0.038) +2025-04-18 11:32:38,468 - train: [ INFO] - Eval : 68 Time: 5.487 (5.487) Loss: 2.3370 (2.3370) Acc@1: 43.7500 (43.7500)Acc@5: 68.7500 (68.7500) +2025-04-18 11:32:52,572 - train: [ INFO] - Eval : 68 Time: 0.056 (0.384) Loss: 1.8902 (1.8990) Acc@1: 56.2500 (52.7574)Acc@5: 75.0000 (77.6348) +2025-04-18 11:32:59,166 - train: [ INFO] - Eval : 68 Time: 0.021 (0.319) Loss: 3.2981 (1.9130) Acc@1: 0.0000 (52.0046)Acc@5: 50.0000 (77.4094) +2025-04-18 11:33:08,746 - train: [ INFO] - Train: 69 [ 0/461 ( 0%)] Loss: 2.802751 (2.8028) Loss_single: 2.122055 (2.1221) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.752s, 5.56/s (5.752s, 5.56/s) LR: 5.000e-03 Data: 5.609 (5.609) +2025-04-18 11:33:17,049 - train: [ INFO] - Train: 69 [ 50/461 ( 11%)] Loss: 2.586034 (2.6944) Loss_single: 1.895596 (2.0088) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 380.32/s (0.275s, 116.41/s) LR: 5.000e-03 Data: 0.000 (0.185) +2025-04-18 11:33:24,008 - train: [ INFO] - Train: 69 [ 100/461 ( 22%)] Loss: 2.814513 (2.7344) Loss_single: 2.129245 (2.0490) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.189s, 169.21/s (0.207s, 154.44/s) LR: 5.000e-03 Data: 0.001 (0.107) +2025-04-18 11:33:29,917 - train: [ INFO] - Train: 69 [ 150/461 ( 33%)] Loss: 2.803779 (2.7518) Loss_single: 2.118635 (2.0664) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.121s, 264.28/s (0.177s, 180.57/s) LR: 5.000e-03 Data: 0.001 (0.072) +2025-04-18 11:33:35,490 - train: [ INFO] - Train: 69 [ 200/461 ( 43%)] Loss: 2.613239 (2.7241) Loss_single: 1.937589 (2.0406) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 403.62/s (0.161s, 199.14/s) LR: 5.000e-03 Data: 0.000 (0.054) +2025-04-18 11:33:40,916 - train: [ INFO] - Train: 69 [ 250/461 ( 54%)] Loss: 2.787379 (2.7346) Loss_single: 2.068890 (2.0453) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.091s, 353.06/s (0.150s, 213.11/s) LR: 5.000e-03 Data: 0.001 (0.043) +2025-04-18 11:33:46,447 - train: [ INFO] - Train: 69 [ 300/461 ( 65%)] Loss: 2.773789 (2.7402) Loss_single: 2.103093 (2.0536) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 343.70/s (0.143s, 223.03/s) LR: 5.000e-03 Data: 0.000 (0.036) +2025-04-18 11:33:51,876 - train: [ INFO] - Train: 69 [ 350/461 ( 76%)] Loss: 2.797572 (2.7474) Loss_single: 2.119609 (2.0618) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.108s, 297.35/s (0.138s, 231.17/s) LR: 5.000e-03 Data: 0.000 (0.032) +2025-04-18 11:33:57,332 - train: [ INFO] - Train: 69 [ 400/461 ( 87%)] Loss: 2.881825 (2.7623) Loss_single: 2.210744 (2.0784) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 405.10/s (0.135s, 237.58/s) LR: 5.000e-03 Data: 0.000 (0.028) +2025-04-18 11:34:03,844 - train: [ INFO] - Train: 69 [ 450/461 ( 98%)] Loss: 2.841842 (2.7703) Loss_single: 2.158307 (2.0864) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 363.49/s (0.132s, 242.93/s) LR: 5.000e-03 Data: 0.000 (0.025) +2025-04-18 11:34:05,023 - train: [ INFO] - Train: 69 [ 460/461 (100%)] Loss: 2.852816 (2.7778) Loss_single: 2.173810 (2.0943) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 385.53/s (0.131s, 245.04/s) LR: 5.000e-03 Data: 0.000 (0.024) +2025-04-18 11:34:09,359 - train: [ INFO] - Eval : 69 Time: 3.967 (3.967) Loss: 2.0912 (2.0912) Acc@1: 43.7500 (43.7500)Acc@5: 68.7500 (68.7500) +2025-04-18 11:34:14,830 - train: [ INFO] - Eval : 69 Time: 0.051 (0.185) Loss: 1.8902 (1.9027) Acc@1: 56.2500 (52.8186)Acc@5: 78.1250 (77.4510) +2025-04-18 11:34:16,720 - train: [ INFO] - Eval : 69 Time: 0.015 (0.138) Loss: 3.2016 (1.9147) Acc@1: 50.0000 (52.2745)Acc@5: 50.0000 (76.9468) +2025-04-18 11:34:24,524 - train: [ INFO] - Train: 70 [ 0/461 ( 0%)] Loss: 2.996381 (2.9964) Loss_single: 2.315875 (2.3159) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.953s, 6.46/s (4.953s, 6.46/s) LR: 5.000e-04 Data: 4.811 (4.811) +2025-04-18 11:34:30,271 - train: [ INFO] - Train: 70 [ 50/461 ( 11%)] Loss: 2.704257 (2.8503) Loss_single: 2.029003 (2.1724) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.132s, 243.32/s (0.209s, 153.02/s) LR: 5.000e-04 Data: 0.000 (0.095) +2025-04-18 11:34:36,099 - train: [ INFO] - Train: 70 [ 100/461 ( 22%)] Loss: 2.839777 (2.8468) Loss_single: 2.145573 (2.1635) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.169s, 188.81/s (0.163s, 196.37/s) LR: 5.000e-04 Data: 0.000 (0.049) +2025-04-18 11:34:41,887 - train: [ INFO] - Train: 70 [ 150/461 ( 33%)] Loss: 2.498643 (2.7598) Loss_single: 1.829447 (2.0800) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.104s, 308.85/s (0.147s, 217.62/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-18 11:34:47,934 - train: [ INFO] - Train: 70 [ 200/461 ( 43%)] Loss: 2.563586 (2.7205) Loss_single: 1.894874 (2.0430) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.122s, 262.35/s (0.140s, 228.01/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-18 11:34:53,566 - train: [ INFO] - Train: 70 [ 250/461 ( 54%)] Loss: 2.780140 (2.7305) Loss_single: 2.077095 (2.0486) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.109s, 294.20/s (0.135s, 237.57/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:34:59,802 - train: [ INFO] - Train: 70 [ 300/461 ( 65%)] Loss: 2.591259 (2.7106) Loss_single: 1.914922 (2.0295) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 338.40/s (0.130s, 246.01/s) LR: 5.000e-04 Data: 0.001 (0.017) +2025-04-18 11:35:05,398 - train: [ INFO] - Train: 70 [ 350/461 ( 76%)] Loss: 2.472688 (2.6808) Loss_single: 1.798553 (2.0007) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 411.12/s (0.127s, 251.49/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-18 11:35:12,771 - train: [ INFO] - Train: 70 [ 400/461 ( 87%)] Loss: 2.630015 (2.6752) Loss_single: 1.952008 (1.9953) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 388.99/s (0.124s, 257.36/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-18 11:35:18,437 - train: [ INFO] - Train: 70 [ 450/461 ( 98%)] Loss: 2.439664 (2.6516) Loss_single: 1.771979 (1.9729) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 409.49/s (0.123s, 260.07/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:35:19,285 - train: [ INFO] - Train: 70 [ 460/461 (100%)] Loss: 2.564150 (2.6437) Loss_single: 1.812800 (1.9584) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 96.8750 (99.7159) Time: 0.112s, 285.28/s (0.122s, 261.88/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:35:23,643 - train: [ INFO] - Eval : 70 Time: 4.076 (4.076) Loss: 2.0224 (2.0224) Acc@1: 50.0000 (50.0000)Acc@5: 71.8750 (71.8750) +2025-04-18 11:35:26,796 - train: [ INFO] - Eval : 70 Time: 0.064 (0.142) Loss: 1.7527 (1.8142) Acc@1: 62.5000 (57.1078)Acc@5: 81.2500 (81.4338) +2025-04-18 11:35:29,264 - train: [ INFO] - Eval : 70 Time: 0.017 (0.118) Loss: 3.0755 (1.8350) Acc@1: 50.0000 (55.9753)Acc@5: 50.0000 (81.0717) +2025-04-18 11:35:32,400 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-70.pth.tar', 55.97532767925983) + +2025-04-18 11:35:37,127 - train: [ INFO] - Train: 71 [ 0/461 ( 0%)] Loss: 2.444843 (2.4448) Loss_single: 1.773254 (1.7733) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.684s, 6.83/s (4.684s, 6.83/s) LR: 5.000e-04 Data: 4.486 (4.486) +2025-04-18 11:35:43,250 - train: [ INFO] - Train: 71 [ 50/461 ( 11%)] Loss: 2.438141 (2.4415) Loss_single: 1.729870 (1.7516) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.124s, 258.29/s (0.211s, 151.69/s) LR: 5.000e-04 Data: 0.000 (0.089) +2025-04-18 11:35:48,633 - train: [ INFO] - Train: 71 [ 100/461 ( 22%)] Loss: 2.674390 (2.5191) Loss_single: 1.992833 (1.8320) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 362.04/s (0.159s, 201.10/s) LR: 5.000e-04 Data: 0.001 (0.046) +2025-04-18 11:35:54,267 - train: [ INFO] - Train: 71 [ 150/461 ( 33%)] Loss: 2.520658 (2.5195) Loss_single: 1.844481 (1.8351) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 387.14/s (0.143s, 223.24/s) LR: 5.000e-04 Data: 0.000 (0.031) +2025-04-18 11:35:59,574 - train: [ INFO] - Train: 71 [ 200/461 ( 43%)] Loss: 2.511743 (2.5180) Loss_single: 1.846262 (1.8373) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.089s, 357.89/s (0.134s, 238.93/s) LR: 5.000e-04 Data: 0.000 (0.024) +2025-04-18 11:36:05,076 - train: [ INFO] - Train: 71 [ 250/461 ( 54%)] Loss: 2.445960 (2.5060) Loss_single: 1.743474 (1.8217) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 396.29/s (0.129s, 248.24/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-18 11:36:10,598 - train: [ INFO] - Train: 71 [ 300/461 ( 65%)] Loss: 2.420778 (2.4938) Loss_single: 1.759531 (1.8128) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.108s, 296.60/s (0.126s, 254.68/s) LR: 5.000e-04 Data: 0.024 (0.016) +2025-04-18 11:36:17,942 - train: [ INFO] - Train: 71 [ 350/461 ( 76%)] Loss: 2.304281 (2.4701) Loss_single: 1.637401 (1.7909) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.108s, 296.84/s (0.123s, 259.53/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 11:36:24,229 - train: [ INFO] - Train: 71 [ 400/461 ( 87%)] Loss: 3.098309 (2.5399) Loss_single: 2.274420 (1.8446) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.093s, 342.85/s (0.123s, 260.19/s) LR: 5.000e-04 Data: 0.001 (0.012) +2025-04-18 11:36:29,620 - train: [ INFO] - Train: 71 [ 450/461 ( 98%)] Loss: 2.548995 (2.5408) Loss_single: 1.872963 (1.8474) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.082s, 390.73/s (0.121s, 263.96/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:36:30,447 - train: [ INFO] - Train: 71 [ 460/461 (100%)] Loss: 2.490383 (2.5362) Loss_single: 1.823684 (1.8453) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.53/s (0.120s, 265.82/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:36:36,302 - train: [ INFO] - Eval : 71 Time: 5.597 (5.597) Loss: 2.0164 (2.0164) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:36:41,303 - train: [ INFO] - Eval : 71 Time: 0.159 (0.208) Loss: 1.7927 (1.8101) Acc@1: 59.3750 (56.6789)Acc@5: 78.1250 (81.8015) +2025-04-18 11:36:43,670 - train: [ INFO] - Eval : 71 Time: 0.016 (0.158) Loss: 2.9314 (1.8323) Acc@1: 50.0000 (56.0910)Acc@5: 50.0000 (81.3801) +2025-04-18 11:36:46,414 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-71.pth.tar', 56.09097918272938) + +2025-04-18 11:36:50,437 - train: [ INFO] - Train: 72 [ 0/461 ( 0%)] Loss: 2.422350 (2.4224) Loss_single: 1.753721 (1.7537) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 3.990s, 8.02/s (3.990s, 8.02/s) LR: 5.000e-04 Data: 3.816 (3.816) +2025-04-18 11:36:56,680 - train: [ INFO] - Train: 72 [ 50/461 ( 11%)] Loss: 2.424214 (2.4233) Loss_single: 1.761661 (1.7577) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.10/s (0.200s, 160.12/s) LR: 5.000e-04 Data: 0.001 (0.075) +2025-04-18 11:37:02,128 - train: [ INFO] - Train: 72 [ 100/461 ( 22%)] Loss: 2.636696 (2.4944) Loss_single: 1.898501 (1.8046) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.133s, 240.48/s (0.154s, 207.26/s) LR: 5.000e-04 Data: 0.000 (0.039) +2025-04-18 11:37:07,751 - train: [ INFO] - Train: 72 [ 150/461 ( 33%)] Loss: 2.678652 (2.5405) Loss_single: 1.927186 (1.8353) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.145s, 220.65/s (0.140s, 228.17/s) LR: 5.000e-04 Data: 0.001 (0.026) +2025-04-18 11:37:13,759 - train: [ INFO] - Train: 72 [ 200/461 ( 43%)] Loss: 2.678280 (2.5680) Loss_single: 1.974820 (1.8632) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.7500) Acc@5: 100.0000 (100.0000) Time: 0.132s, 241.62/s (0.135s, 236.90/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:37:19,640 - train: [ INFO] - Train: 72 [ 250/461 ( 54%)] Loss: 2.620256 (2.5767) Loss_single: 1.913077 (1.8715) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.086s, 369.98/s (0.131s, 243.57/s) LR: 5.000e-04 Data: 0.001 (0.016) +2025-04-18 11:37:27,159 - train: [ INFO] - Train: 72 [ 300/461 ( 65%)] Loss: 2.416818 (2.5539) Loss_single: 1.755226 (1.8549) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (100.0000) Time: 0.125s, 256.25/s (0.127s, 252.02/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 11:37:32,770 - train: [ INFO] - Train: 72 [ 350/461 ( 76%)] Loss: 2.329019 (2.5258) Loss_single: 1.665212 (1.8312) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.093s, 343.79/s (0.125s, 256.45/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:37:38,129 - train: [ INFO] - Train: 72 [ 400/461 ( 87%)] Loss: 2.609512 (2.5351) Loss_single: 1.946926 (1.8440) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.131s, 243.80/s (0.123s, 261.19/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 11:37:43,393 - train: [ INFO] - Train: 72 [ 450/461 ( 98%)] Loss: 2.632678 (2.5448) Loss_single: 1.965193 (1.8562) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.081s, 396.02/s (0.120s, 265.61/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 11:37:44,177 - train: [ INFO] - Train: 72 [ 460/461 (100%)] Loss: 2.458405 (2.5370) Loss_single: 1.790231 (1.8502) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.076s, 421.06/s (0.120s, 267.66/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 11:37:47,704 - train: [ INFO] - Eval : 72 Time: 3.294 (3.294) Loss: 2.0363 (2.0363) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:37:52,265 - train: [ INFO] - Eval : 72 Time: 0.055 (0.153) Loss: 1.7942 (1.8148) Acc@1: 62.5000 (56.3725)Acc@5: 78.1250 (82.4755) +2025-04-18 11:37:54,956 - train: [ INFO] - Eval : 72 Time: 0.014 (0.129) Loss: 2.9492 (1.8352) Acc@1: 50.0000 (55.7055)Acc@5: 50.0000 (81.8427) +2025-04-18 11:38:03,787 - train: [ INFO] - Train: 73 [ 0/461 ( 0%)] Loss: 2.445140 (2.4451) Loss_single: 1.772680 (1.7727) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.668s, 5.65/s (5.668s, 5.65/s) LR: 5.000e-04 Data: 5.505 (5.505) +2025-04-18 11:38:09,592 - train: [ INFO] - Train: 73 [ 50/461 ( 11%)] Loss: 2.538617 (2.4919) Loss_single: 1.878612 (1.8256) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.087s, 369.07/s (0.224s, 143.06/s) LR: 5.000e-04 Data: 0.000 (0.108) +2025-04-18 11:38:14,869 - train: [ INFO] - Train: 73 [ 100/461 ( 22%)] Loss: 2.477625 (2.4871) Loss_single: 1.814555 (1.8219) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 405.87/s (0.165s, 194.40/s) LR: 5.000e-04 Data: 0.000 (0.055) +2025-04-18 11:38:19,977 - train: [ INFO] - Train: 73 [ 150/461 ( 33%)] Loss: 2.383609 (2.4612) Loss_single: 1.716735 (1.7956) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.099s, 322.10/s (0.144s, 222.64/s) LR: 5.000e-04 Data: 0.001 (0.037) +2025-04-18 11:38:25,042 - train: [ INFO] - Train: 73 [ 200/461 ( 43%)] Loss: 2.841574 (2.5373) Loss_single: 2.055438 (1.8476) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (98.7500) Acc@5: 96.8750 (99.3750) Time: 0.139s, 229.61/s (0.133s, 240.53/s) LR: 5.000e-04 Data: 0.000 (0.028) +2025-04-18 11:38:32,393 - train: [ INFO] - Train: 73 [ 250/461 ( 54%)] Loss: 2.533976 (2.5368) Loss_single: 1.808179 (1.8410) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.099s, 322.08/s (0.127s, 251.57/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-18 11:38:38,304 - train: [ INFO] - Train: 73 [ 300/461 ( 65%)] Loss: 2.556341 (2.5396) Loss_single: 1.895474 (1.8488) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.119s, 268.66/s (0.125s, 255.86/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-18 11:38:44,187 - train: [ INFO] - Train: 73 [ 350/461 ( 76%)] Loss: 2.623787 (2.5501) Loss_single: 1.956527 (1.8623) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.083s, 383.44/s (0.123s, 260.05/s) LR: 5.000e-04 Data: 0.001 (0.016) +2025-04-18 11:38:49,835 - train: [ INFO] - Train: 73 [ 400/461 ( 87%)] Loss: 2.394275 (2.5328) Loss_single: 1.727205 (1.8473) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.084s, 379.28/s (0.122s, 263.00/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 11:38:54,973 - train: [ INFO] - Train: 73 [ 450/461 ( 98%)] Loss: 2.696312 (2.5491) Loss_single: 1.950616 (1.8576) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.080s, 399.56/s (0.119s, 267.81/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:38:55,795 - train: [ INFO] - Train: 73 [ 460/461 (100%)] Loss: 2.607295 (2.5544) Loss_single: 1.882514 (1.8599) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1477) Acc@5: 100.0000 (99.7159) Time: 0.079s, 402.81/s (0.119s, 269.68/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:39:00,490 - train: [ INFO] - Eval : 73 Time: 4.420 (4.420) Loss: 1.9930 (1.9930) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:39:04,546 - train: [ INFO] - Eval : 73 Time: 0.149 (0.166) Loss: 1.8128 (1.8153) Acc@1: 59.3750 (56.5564)Acc@5: 78.1250 (81.7402) +2025-04-18 11:39:06,862 - train: [ INFO] - Eval : 73 Time: 0.016 (0.132) Loss: 2.9001 (1.8371) Acc@1: 50.0000 (56.1295)Acc@5: 50.0000 (81.2645) +2025-04-18 11:39:09,797 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-73.pth.tar', 56.12952968388589) + +2025-04-18 11:39:14,746 - train: [ INFO] - Train: 74 [ 0/461 ( 0%)] Loss: 2.395595 (2.3956) Loss_single: 1.729470 (1.7295) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.915s, 6.51/s (4.915s, 6.51/s) LR: 5.000e-04 Data: 4.664 (4.664) +2025-04-18 11:39:20,602 - train: [ INFO] - Train: 74 [ 50/461 ( 11%)] Loss: 2.509920 (2.4528) Loss_single: 1.822677 (1.7761) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 364.56/s (0.210s, 152.36/s) LR: 5.000e-04 Data: 0.000 (0.092) +2025-04-18 11:39:26,637 - train: [ INFO] - Train: 74 [ 100/461 ( 22%)] Loss: 2.420587 (2.4420) Loss_single: 1.755695 (1.7693) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 336.25/s (0.165s, 193.47/s) LR: 5.000e-04 Data: 0.000 (0.047) +2025-04-18 11:39:31,806 - train: [ INFO] - Train: 74 [ 150/461 ( 33%)] Loss: 2.457859 (2.4460) Loss_single: 1.790348 (1.7745) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 411.15/s (0.145s, 221.20/s) LR: 5.000e-04 Data: 0.000 (0.032) +2025-04-18 11:39:38,589 - train: [ INFO] - Train: 74 [ 200/461 ( 43%)] Loss: 2.336503 (2.4241) Loss_single: 1.669846 (1.7536) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 388.25/s (0.137s, 234.10/s) LR: 5.000e-04 Data: 0.000 (0.024) +2025-04-18 11:39:44,780 - train: [ INFO] - Train: 74 [ 250/461 ( 54%)] Loss: 2.444434 (2.4275) Loss_single: 1.757822 (1.7543) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.101s, 316.53/s (0.130s, 246.12/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-18 11:39:50,011 - train: [ INFO] - Train: 74 [ 300/461 ( 65%)] Loss: 2.405293 (2.4243) Loss_single: 1.742214 (1.7526) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 419.50/s (0.126s, 254.57/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:39:55,695 - train: [ INFO] - Train: 74 [ 350/461 ( 76%)] Loss: 2.468794 (2.4299) Loss_single: 1.806477 (1.7593) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.117s, 273.36/s (0.124s, 258.31/s) LR: 5.000e-04 Data: 0.009 (0.014) +2025-04-18 11:40:01,144 - train: [ INFO] - Train: 74 [ 400/461 ( 87%)] Loss: 2.491078 (2.4367) Loss_single: 1.768099 (1.7603) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.079s, 406.77/s (0.122s, 262.92/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:40:06,678 - train: [ INFO] - Train: 74 [ 450/461 ( 98%)] Loss: 2.548651 (2.4479) Loss_single: 1.830448 (1.7673) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.081s, 393.15/s (0.120s, 265.79/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:40:07,548 - train: [ INFO] - Train: 74 [ 460/461 (100%)] Loss: 2.402759 (2.4438) Loss_single: 1.737181 (1.7646) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.076s, 418.57/s (0.120s, 267.46/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:40:13,751 - train: [ INFO] - Eval : 74 Time: 5.778 (5.778) Loss: 2.0332 (2.0332) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:40:17,699 - train: [ INFO] - Eval : 74 Time: 0.050 (0.191) Loss: 1.8052 (1.8199) Acc@1: 62.5000 (56.8015)Acc@5: 81.2500 (81.8627) +2025-04-18 11:40:19,814 - train: [ INFO] - Eval : 74 Time: 0.014 (0.144) Loss: 2.7944 (1.8419) Acc@1: 50.0000 (56.1681)Acc@5: 50.0000 (81.3416) +2025-04-18 11:40:22,661 - timm.utils.checkpoint_saver: [ INFO] - Current checkpoints: + ('./exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/checkpoint-74.pth.tar', 56.168080185042406) + +2025-04-18 11:40:26,747 - train: [ INFO] - Train: 75 [ 0/461 ( 0%)] Loss: 2.433314 (2.4333) Loss_single: 1.762517 (1.7625) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.025s, 7.95/s (4.025s, 7.95/s) LR: 5.000e-04 Data: 3.857 (3.857) +2025-04-18 11:40:32,098 - train: [ INFO] - Train: 75 [ 50/461 ( 11%)] Loss: 2.523793 (2.4786) Loss_single: 1.848298 (1.8054) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.097s, 329.39/s (0.183s, 174.59/s) LR: 5.000e-04 Data: 0.000 (0.076) +2025-04-18 11:40:37,251 - train: [ INFO] - Train: 75 [ 100/461 ( 22%)] Loss: 2.393970 (2.4504) Loss_single: 1.731745 (1.7809) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.125s, 255.77/s (0.143s, 223.37/s) LR: 5.000e-04 Data: 0.001 (0.039) +2025-04-18 11:40:44,738 - train: [ INFO] - Train: 75 [ 150/461 ( 33%)] Loss: 2.805823 (2.5392) Loss_single: 2.094241 (1.8592) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.105s, 304.54/s (0.137s, 233.06/s) LR: 5.000e-04 Data: 0.001 (0.026) +2025-04-18 11:40:51,565 - train: [ INFO] - Train: 75 [ 200/461 ( 43%)] Loss: 2.592066 (2.5498) Loss_single: 1.925244 (1.8724) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.107s, 298.56/s (0.130s, 245.45/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:40:57,384 - train: [ INFO] - Train: 75 [ 250/461 ( 54%)] Loss: 2.332512 (2.5136) Loss_single: 1.667621 (1.8383) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 337.20/s (0.127s, 251.22/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:41:02,678 - train: [ INFO] - Train: 75 [ 300/461 ( 65%)] Loss: 2.586895 (2.5241) Loss_single: 1.916199 (1.8494) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.109s, 292.32/s (0.124s, 258.71/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 11:41:08,082 - train: [ INFO] - Train: 75 [ 350/461 ( 76%)] Loss: 2.241271 (2.4887) Loss_single: 1.574511 (1.8150) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.114s, 281.06/s (0.121s, 263.91/s) LR: 5.000e-04 Data: 0.001 (0.012) +2025-04-18 11:41:13,248 - train: [ INFO] - Train: 75 [ 400/461 ( 87%)] Loss: 2.812593 (2.5247) Loss_single: 2.023170 (1.8382) Loss_inverse: 0.000000 (0.0000) Acc@1: 93.7500 (99.3056) Acc@5: 100.0000 (100.0000) Time: 0.093s, 343.96/s (0.119s, 269.03/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 11:41:18,329 - train: [ INFO] - Train: 75 [ 450/461 ( 98%)] Loss: 2.429691 (2.5152) Loss_single: 1.771056 (1.8315) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.081s, 397.48/s (0.117s, 273.63/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 11:41:19,146 - train: [ INFO] - Train: 75 [ 460/461 (100%)] Loss: 2.394097 (2.5042) Loss_single: 1.728535 (1.8221) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.081s, 396.91/s (0.116s, 275.47/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 11:41:24,213 - train: [ INFO] - Eval : 75 Time: 4.804 (4.804) Loss: 2.0281 (2.0281) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:41:28,888 - train: [ INFO] - Eval : 75 Time: 0.082 (0.186) Loss: 1.8162 (1.8273) Acc@1: 59.3750 (56.3725)Acc@5: 81.2500 (82.0466) +2025-04-18 11:41:31,537 - train: [ INFO] - Eval : 75 Time: 0.015 (0.148) Loss: 2.9207 (1.8496) Acc@1: 50.0000 (55.7055)Acc@5: 50.0000 (81.4572) +2025-04-18 11:41:39,460 - train: [ INFO] - Train: 76 [ 0/461 ( 0%)] Loss: 2.362910 (2.3629) Loss_single: 1.698092 (1.6981) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.854s, 6.59/s (4.854s, 6.59/s) LR: 5.000e-04 Data: 4.655 (4.655) +2025-04-18 11:41:44,871 - train: [ INFO] - Train: 76 [ 50/461 ( 11%)] Loss: 2.686224 (2.5246) Loss_single: 1.950114 (1.8241) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.148s, 215.78/s (0.200s, 159.86/s) LR: 5.000e-04 Data: 0.001 (0.092) +2025-04-18 11:41:51,470 - train: [ INFO] - Train: 76 [ 100/461 ( 22%)] Loss: 2.823315 (2.6241) Loss_single: 2.107483 (1.9186) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.080s, 399.54/s (0.155s, 206.89/s) LR: 5.000e-04 Data: 0.000 (0.047) +2025-04-18 11:41:57,814 - train: [ INFO] - Train: 76 [ 150/461 ( 33%)] Loss: 2.389127 (2.5654) Loss_single: 1.728599 (1.8711) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.103s, 309.87/s (0.138s, 232.69/s) LR: 5.000e-04 Data: 0.000 (0.031) +2025-04-18 11:42:03,068 - train: [ INFO] - Train: 76 [ 200/461 ( 43%)] Loss: 2.266687 (2.5057) Loss_single: 1.608137 (1.8185) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.078s, 412.41/s (0.129s, 247.52/s) LR: 5.000e-04 Data: 0.000 (0.024) +2025-04-18 11:42:08,898 - train: [ INFO] - Train: 76 [ 250/461 ( 54%)] Loss: 2.660604 (2.5315) Loss_single: 1.898270 (1.8318) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (99.4792) Time: 0.172s, 185.53/s (0.127s, 252.79/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-18 11:42:14,650 - train: [ INFO] - Train: 76 [ 300/461 ( 65%)] Loss: 2.495733 (2.5264) Loss_single: 1.833970 (1.8321) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.143s, 223.36/s (0.125s, 256.94/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:42:20,567 - train: [ INFO] - Train: 76 [ 350/461 ( 76%)] Loss: 2.426455 (2.5139) Loss_single: 1.741680 (1.8208) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.103s, 311.45/s (0.123s, 259.27/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:42:25,904 - train: [ INFO] - Train: 76 [ 400/461 ( 87%)] Loss: 2.495887 (2.5119) Loss_single: 1.831257 (1.8220) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.113s, 282.46/s (0.121s, 263.90/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:42:31,563 - train: [ INFO] - Train: 76 [ 450/461 ( 98%)] Loss: 2.446864 (2.5054) Loss_single: 1.779590 (1.8177) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.084s, 381.07/s (0.119s, 268.78/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:42:32,375 - train: [ INFO] - Train: 76 [ 460/461 (100%)] Loss: 2.344054 (2.4907) Loss_single: 1.684189 (1.8056) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.076s, 418.49/s (0.118s, 270.68/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:42:37,279 - train: [ INFO] - Eval : 76 Time: 4.657 (4.657) Loss: 2.0137 (2.0137) Acc@1: 53.1250 (53.1250)Acc@5: 71.8750 (71.8750) +2025-04-18 11:42:39,644 - train: [ INFO] - Eval : 76 Time: 0.024 (0.138) Loss: 1.7805 (1.8185) Acc@1: 62.5000 (56.6789)Acc@5: 81.2500 (81.9853) +2025-04-18 11:42:41,702 - train: [ INFO] - Eval : 76 Time: 0.014 (0.111) Loss: 2.7843 (1.8432) Acc@1: 50.0000 (55.7440)Acc@5: 50.0000 (81.2259) +2025-04-18 11:42:49,356 - train: [ INFO] - Train: 77 [ 0/461 ( 0%)] Loss: 2.438427 (2.4384) Loss_single: 1.758869 (1.7589) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.827s, 6.63/s (4.827s, 6.63/s) LR: 5.000e-04 Data: 4.606 (4.606) +2025-04-18 11:42:57,955 - train: [ INFO] - Train: 77 [ 50/461 ( 11%)] Loss: 2.582647 (2.5105) Loss_single: 1.890892 (1.8249) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 394.81/s (0.232s, 138.17/s) LR: 5.000e-04 Data: 0.001 (0.102) +2025-04-18 11:43:08,842 - train: [ INFO] - Train: 77 [ 100/461 ( 22%)] Loss: 2.370025 (2.4637) Loss_single: 1.709575 (1.7864) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.127s, 252.39/s (0.204s, 156.62/s) LR: 5.000e-04 Data: 0.000 (0.090) +2025-04-18 11:43:19,818 - train: [ INFO] - Train: 77 [ 150/461 ( 33%)] Loss: 2.261427 (2.4131) Loss_single: 1.601685 (1.7403) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.105s, 303.47/s (0.209s, 153.06/s) LR: 5.000e-04 Data: 0.000 (0.102) +2025-04-18 11:43:29,934 - train: [ INFO] - Train: 77 [ 200/461 ( 43%)] Loss: 2.371843 (2.4049) Loss_single: 1.706614 (1.7335) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.102s, 313.45/s (0.207s, 154.47/s) LR: 5.000e-04 Data: 0.000 (0.103) +2025-04-18 11:43:39,433 - train: [ INFO] - Train: 77 [ 250/461 ( 54%)] Loss: 2.311785 (2.3894) Loss_single: 1.651655 (1.7199) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 362.06/s (0.202s, 158.35/s) LR: 5.000e-04 Data: 0.000 (0.099) +2025-04-18 11:43:50,431 - train: [ INFO] - Train: 77 [ 300/461 ( 65%)] Loss: 2.500825 (2.4053) Loss_single: 1.837533 (1.7367) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.087s, 367.13/s (0.204s, 156.90/s) LR: 5.000e-04 Data: 0.000 (0.100) +2025-04-18 11:44:00,342 - train: [ INFO] - Train: 77 [ 350/461 ( 76%)] Loss: 2.569187 (2.4258) Loss_single: 1.858853 (1.7520) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.118s, 271.45/s (0.202s, 158.18/s) LR: 5.000e-04 Data: 0.000 (0.100) +2025-04-18 11:44:09,621 - train: [ INFO] - Train: 77 [ 400/461 ( 87%)] Loss: 2.486058 (2.4325) Loss_single: 1.825444 (1.7601) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 364.70/s (0.200s, 159.93/s) LR: 5.000e-04 Data: 0.001 (0.100) +2025-04-18 11:44:19,118 - train: [ INFO] - Train: 77 [ 450/461 ( 98%)] Loss: 2.679791 (2.4572) Loss_single: 2.017134 (1.7858) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 343.82/s (0.199s, 160.90/s) LR: 5.000e-04 Data: 0.000 (0.098) +2025-04-18 11:44:20,372 - train: [ INFO] - Train: 77 [ 460/461 (100%)] Loss: 2.523787 (2.4633) Loss_single: 1.861762 (1.7927) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 423.30/s (0.197s, 162.27/s) LR: 5.000e-04 Data: 0.000 (0.096) +2025-04-18 11:44:28,678 - train: [ INFO] - Eval : 77 Time: 7.955 (7.955) Loss: 2.0411 (2.0411) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:44:40,491 - train: [ INFO] - Eval : 77 Time: 0.051 (0.388) Loss: 1.8068 (1.8280) Acc@1: 59.3750 (55.8824)Acc@5: 81.2500 (82.1078) +2025-04-18 11:44:46,520 - train: [ INFO] - Eval : 77 Time: 0.021 (0.315) Loss: 2.7464 (1.8504) Acc@1: 50.0000 (55.3585)Acc@5: 50.0000 (81.0717) +2025-04-18 11:44:56,996 - train: [ INFO] - Train: 78 [ 0/461 ( 0%)] Loss: 2.534285 (2.5343) Loss_single: 1.807825 (1.8078) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 6.898s, 4.64/s (6.898s, 4.64/s) LR: 5.000e-04 Data: 6.728 (6.728) +2025-04-18 11:45:09,487 - train: [ INFO] - Train: 78 [ 50/461 ( 11%)] Loss: 2.561224 (2.5478) Loss_single: 1.898772 (1.8533) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.096s, 334.87/s (0.346s, 92.49/s) LR: 5.000e-04 Data: 0.000 (0.251) +2025-04-18 11:45:18,432 - train: [ INFO] - Train: 78 [ 100/461 ( 22%)] Loss: 2.566719 (2.5541) Loss_single: 1.905883 (1.8708) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.084s, 382.98/s (0.261s, 122.63/s) LR: 5.000e-04 Data: 0.000 (0.167) +2025-04-18 11:45:24,099 - train: [ INFO] - Train: 78 [ 150/461 ( 33%)] Loss: 2.502289 (2.5411) Loss_single: 1.834496 (1.8617) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.079s, 402.89/s (0.212s, 151.07/s) LR: 5.000e-04 Data: 0.000 (0.112) +2025-04-18 11:45:29,862 - train: [ INFO] - Train: 78 [ 200/461 ( 43%)] Loss: 2.547463 (2.5424) Loss_single: 1.886030 (1.8666) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.080s, 397.99/s (0.188s, 170.58/s) LR: 5.000e-04 Data: 0.000 (0.089) +2025-04-18 11:45:35,764 - train: [ INFO] - Train: 78 [ 250/461 ( 54%)] Loss: 2.304891 (2.5028) Loss_single: 1.646316 (1.8299) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.085s, 376.94/s (0.174s, 184.36/s) LR: 5.000e-04 Data: 0.001 (0.075) +2025-04-18 11:45:42,262 - train: [ INFO] - Train: 78 [ 300/461 ( 65%)] Loss: 2.416162 (2.4904) Loss_single: 1.737246 (1.8167) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.081s, 395.83/s (0.166s, 192.75/s) LR: 5.000e-04 Data: 0.001 (0.064) +2025-04-18 11:45:50,366 - train: [ INFO] - Train: 78 [ 350/461 ( 76%)] Loss: 2.703379 (2.5171) Loss_single: 2.027359 (1.8430) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.138s, 232.36/s (0.159s, 200.92/s) LR: 5.000e-04 Data: 0.001 (0.055) +2025-04-18 11:45:56,693 - train: [ INFO] - Train: 78 [ 400/461 ( 87%)] Loss: 2.449479 (2.5095) Loss_single: 1.778418 (1.8358) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.286s, 111.70/s (0.155s, 206.39/s) LR: 5.000e-04 Data: 0.000 (0.048) +2025-04-18 11:46:02,881 - train: [ INFO] - Train: 78 [ 450/461 ( 98%)] Loss: 2.497567 (2.5083) Loss_single: 1.835090 (1.8357) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.084s, 382.81/s (0.150s, 213.30/s) LR: 5.000e-04 Data: 0.000 (0.043) +2025-04-18 11:46:04,102 - train: [ INFO] - Train: 78 [ 460/461 (100%)] Loss: 2.728673 (2.5284) Loss_single: 2.058472 (1.8560) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.104s, 307.99/s (0.149s, 214.21/s) LR: 5.000e-04 Data: 0.000 (0.042) +2025-04-18 11:46:12,761 - train: [ INFO] - Eval : 78 Time: 8.174 (8.174) Loss: 2.0131 (2.0131) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:46:15,447 - train: [ INFO] - Eval : 78 Time: 0.054 (0.213) Loss: 1.7958 (1.8326) Acc@1: 59.3750 (56.4338)Acc@5: 81.2500 (82.1078) +2025-04-18 11:46:16,755 - train: [ INFO] - Eval : 78 Time: 0.014 (0.148) Loss: 2.7401 (1.8559) Acc@1: 50.0000 (55.6669)Acc@5: 50.0000 (81.1103) +2025-04-18 11:46:29,984 - train: [ INFO] - Train: 79 [ 0/461 ( 0%)] Loss: 2.394159 (2.3942) Loss_single: 1.735084 (1.7351) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.236s, 4.42/s (7.236s, 4.42/s) LR: 5.000e-04 Data: 7.051 (7.051) +2025-04-18 11:46:37,736 - train: [ INFO] - Train: 79 [ 50/461 ( 11%)] Loss: 2.489601 (2.4419) Loss_single: 1.829650 (1.7824) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.146s, 219.80/s (0.274s, 116.81/s) LR: 5.000e-04 Data: 0.000 (0.139) +2025-04-18 11:46:44,134 - train: [ INFO] - Train: 79 [ 100/461 ( 22%)] Loss: 2.427866 (2.4372) Loss_single: 1.763357 (1.7760) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.091s, 350.51/s (0.201s, 158.98/s) LR: 5.000e-04 Data: 0.000 (0.071) +2025-04-18 11:46:50,725 - train: [ INFO] - Train: 79 [ 150/461 ( 33%)] Loss: 2.440593 (2.4381) Loss_single: 1.782940 (1.7778) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.220s, 145.38/s (0.169s, 189.24/s) LR: 5.000e-04 Data: 0.001 (0.048) +2025-04-18 11:46:56,807 - train: [ INFO] - Train: 79 [ 200/461 ( 43%)] Loss: 2.396721 (2.4298) Loss_single: 1.735316 (1.7693) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.137s, 234.43/s (0.157s, 203.94/s) LR: 5.000e-04 Data: 0.001 (0.036) +2025-04-18 11:47:03,036 - train: [ INFO] - Train: 79 [ 250/461 ( 54%)] Loss: 2.424469 (2.4289) Loss_single: 1.756450 (1.7671) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.164s, 194.77/s (0.150s, 213.00/s) LR: 5.000e-04 Data: 0.001 (0.029) +2025-04-18 11:47:09,416 - train: [ INFO] - Train: 79 [ 300/461 ( 65%)] Loss: 2.395087 (2.4241) Loss_single: 1.731684 (1.7621) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.091s, 350.64/s (0.146s, 218.68/s) LR: 5.000e-04 Data: 0.003 (0.024) +2025-04-18 11:47:14,975 - train: [ INFO] - Train: 79 [ 350/461 ( 76%)] Loss: 2.394365 (2.4204) Loss_single: 1.734271 (1.7586) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.147s, 216.97/s (0.141s, 226.59/s) LR: 5.000e-04 Data: 0.001 (0.021) +2025-04-18 11:47:20,776 - train: [ INFO] - Train: 79 [ 400/461 ( 87%)] Loss: 2.602994 (2.4407) Loss_single: 1.848556 (1.7686) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6528) Acc@5: 96.8750 (99.6528) Time: 0.096s, 334.57/s (0.138s, 231.91/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-18 11:47:26,709 - train: [ INFO] - Train: 79 [ 450/461 ( 98%)] Loss: 2.669865 (2.4636) Loss_single: 2.005023 (1.7922) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.089s, 360.36/s (0.136s, 235.88/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:47:27,745 - train: [ INFO] - Train: 79 [ 460/461 (100%)] Loss: 2.183046 (2.4381) Loss_single: 1.524807 (1.7679) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.078s, 408.07/s (0.135s, 237.13/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:47:32,712 - train: [ INFO] - Eval : 79 Time: 4.546 (4.546) Loss: 2.0382 (2.0382) Acc@1: 46.8750 (46.8750)Acc@5: 75.0000 (75.0000) +2025-04-18 11:47:38,310 - train: [ INFO] - Eval : 79 Time: 0.410 (0.190) Loss: 1.8170 (1.8334) Acc@1: 59.3750 (56.5564)Acc@5: 78.1250 (82.5980) +2025-04-18 11:47:41,251 - train: [ INFO] - Eval : 79 Time: 0.019 (0.160) Loss: 2.8459 (1.8562) Acc@1: 50.0000 (55.6669)Acc@5: 50.0000 (81.5343) +2025-04-18 11:47:53,267 - train: [ INFO] - Train: 80 [ 0/461 ( 0%)] Loss: 2.466027 (2.4660) Loss_single: 1.804814 (1.8048) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 7.750s, 4.13/s (7.750s, 4.13/s) LR: 5.000e-04 Data: 7.545 (7.545) +2025-04-18 11:47:59,713 - train: [ INFO] - Train: 80 [ 50/461 ( 11%)] Loss: 2.554066 (2.5100) Loss_single: 1.895003 (1.8499) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.103s, 310.61/s (0.278s, 115.27/s) LR: 5.000e-04 Data: 0.001 (0.149) +2025-04-18 11:48:05,881 - train: [ INFO] - Train: 80 [ 100/461 ( 22%)] Loss: 2.582475 (2.5342) Loss_single: 1.908337 (1.8694) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.254s, 126.05/s (0.201s, 159.27/s) LR: 5.000e-04 Data: 0.001 (0.076) +2025-04-18 11:48:12,645 - train: [ INFO] - Train: 80 [ 150/461 ( 33%)] Loss: 2.286773 (2.4723) Loss_single: 1.622247 (1.8076) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.117s, 273.24/s (0.170s, 187.87/s) LR: 5.000e-04 Data: 0.001 (0.051) +2025-04-18 11:48:18,698 - train: [ INFO] - Train: 80 [ 200/461 ( 43%)] Loss: 2.501235 (2.4781) Loss_single: 1.816697 (1.8094) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.121s, 264.88/s (0.158s, 202.79/s) LR: 5.000e-04 Data: 0.001 (0.038) +2025-04-18 11:48:24,609 - train: [ INFO] - Train: 80 [ 250/461 ( 54%)] Loss: 2.481268 (2.4786) Loss_single: 1.820658 (1.8113) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.149s, 214.09/s (0.150s, 213.64/s) LR: 5.000e-04 Data: 0.001 (0.031) +2025-04-18 11:48:30,969 - train: [ INFO] - Train: 80 [ 300/461 ( 65%)] Loss: 2.360117 (2.4617) Loss_single: 1.700455 (1.7955) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.104s, 307.96/s (0.146s, 219.28/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-18 11:48:36,664 - train: [ INFO] - Train: 80 [ 350/461 ( 76%)] Loss: 2.500802 (2.4666) Loss_single: 1.838066 (1.8008) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.135s, 237.43/s (0.141s, 226.49/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-18 11:48:42,034 - train: [ INFO] - Train: 80 [ 400/461 ( 87%)] Loss: 2.394675 (2.4586) Loss_single: 1.735971 (1.7936) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.134s, 238.29/s (0.137s, 233.71/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:48:50,385 - train: [ INFO] - Train: 80 [ 450/461 ( 98%)] Loss: 2.688646 (2.4816) Loss_single: 1.959771 (1.8102) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.083s, 384.38/s (0.133s, 239.83/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 11:48:51,550 - train: [ INFO] - Train: 80 [ 460/461 (100%)] Loss: 2.678849 (2.4995) Loss_single: 1.999356 (1.8274) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.132s, 242.47/s (0.133s, 240.67/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 11:48:57,443 - train: [ INFO] - Eval : 80 Time: 5.635 (5.635) Loss: 2.0147 (2.0147) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:49:02,524 - train: [ INFO] - Eval : 80 Time: 0.031 (0.210) Loss: 1.8129 (1.8255) Acc@1: 59.3750 (56.7402)Acc@5: 81.2500 (81.9240) +2025-04-18 11:49:04,096 - train: [ INFO] - Eval : 80 Time: 0.014 (0.150) Loss: 2.7604 (1.8483) Acc@1: 50.0000 (55.9753)Acc@5: 50.0000 (81.1488) +2025-04-18 11:49:15,635 - train: [ INFO] - Train: 81 [ 0/461 ( 0%)] Loss: 2.230113 (2.2301) Loss_single: 1.572081 (1.5721) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.009s, 6.39/s (5.009s, 6.39/s) LR: 5.000e-04 Data: 4.834 (4.834) +2025-04-18 11:49:21,998 - train: [ INFO] - Train: 81 [ 50/461 ( 11%)] Loss: 2.433956 (2.3320) Loss_single: 1.772070 (1.6721) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.177s, 180.69/s (0.222s, 144.47/s) LR: 5.000e-04 Data: 0.000 (0.095) +2025-04-18 11:49:28,603 - train: [ INFO] - Train: 81 [ 100/461 ( 22%)] Loss: 2.600702 (2.4216) Loss_single: 1.867199 (1.7371) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.083s, 387.50/s (0.171s, 186.95/s) LR: 5.000e-04 Data: 0.000 (0.049) +2025-04-18 11:49:34,951 - train: [ INFO] - Train: 81 [ 150/461 ( 33%)] Loss: 2.470466 (2.4338) Loss_single: 1.811493 (1.7557) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.089s, 357.58/s (0.156s, 204.82/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-18 11:49:41,180 - train: [ INFO] - Train: 81 [ 200/461 ( 43%)] Loss: 2.396436 (2.4263) Loss_single: 1.730736 (1.7507) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.146s, 219.56/s (0.144s, 221.65/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-18 11:49:47,206 - train: [ INFO] - Train: 81 [ 250/461 ( 54%)] Loss: 2.451337 (2.4305) Loss_single: 1.787568 (1.7569) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.104s, 306.23/s (0.139s, 229.43/s) LR: 5.000e-04 Data: 0.000 (0.020) +2025-04-18 11:49:53,938 - train: [ INFO] - Train: 81 [ 300/461 ( 65%)] Loss: 2.429713 (2.4304) Loss_single: 1.768717 (1.7586) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.111s, 288.51/s (0.137s, 234.40/s) LR: 5.000e-04 Data: 0.001 (0.017) +2025-04-18 11:50:00,360 - train: [ INFO] - Train: 81 [ 350/461 ( 76%)] Loss: 2.490110 (2.4379) Loss_single: 1.812632 (1.7653) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.079s, 406.43/s (0.134s, 239.02/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:50:06,938 - train: [ INFO] - Train: 81 [ 400/461 ( 87%)] Loss: 2.516644 (2.4466) Loss_single: 1.843400 (1.7740) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.093s, 343.92/s (0.131s, 244.28/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:50:14,267 - train: [ INFO] - Train: 81 [ 450/461 ( 98%)] Loss: 2.469937 (2.4489) Loss_single: 1.798047 (1.7764) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.200s, 160.35/s (0.130s, 247.00/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:50:15,074 - train: [ INFO] - Train: 81 [ 460/461 (100%)] Loss: 2.430598 (2.4473) Loss_single: 1.769553 (1.7758) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.078s, 412.19/s (0.128s, 249.06/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:50:22,074 - train: [ INFO] - Eval : 81 Time: 6.725 (6.725) Loss: 2.0243 (2.0243) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:50:25,164 - train: [ INFO] - Eval : 81 Time: 0.074 (0.192) Loss: 1.8131 (1.8422) Acc@1: 59.3750 (55.6373)Acc@5: 81.2500 (81.8015) +2025-04-18 11:50:27,597 - train: [ INFO] - Eval : 81 Time: 0.016 (0.149) Loss: 2.6480 (1.8656) Acc@1: 50.0000 (55.3971)Acc@5: 50.0000 (80.9561) +2025-04-18 11:50:35,773 - train: [ INFO] - Train: 82 [ 0/461 ( 0%)] Loss: 2.442305 (2.4423) Loss_single: 1.774189 (1.7742) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.202s, 6.15/s (5.202s, 6.15/s) LR: 5.000e-04 Data: 5.039 (5.039) +2025-04-18 11:50:42,523 - train: [ INFO] - Train: 82 [ 50/461 ( 11%)] Loss: 2.373171 (2.4077) Loss_single: 1.713124 (1.7437) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 411.14/s (0.234s, 136.96/s) LR: 5.000e-04 Data: 0.000 (0.104) +2025-04-18 11:50:49,785 - train: [ INFO] - Train: 82 [ 100/461 ( 22%)] Loss: 2.508391 (2.4413) Loss_single: 1.850605 (1.7793) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.204s, 157.02/s (0.184s, 174.24/s) LR: 5.000e-04 Data: 0.000 (0.053) +2025-04-18 11:50:55,682 - train: [ INFO] - Train: 82 [ 150/461 ( 33%)] Loss: 2.509753 (2.4584) Loss_single: 1.844620 (1.7956) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.136s, 235.43/s (0.162s, 197.93/s) LR: 5.000e-04 Data: 0.000 (0.036) +2025-04-18 11:51:01,883 - train: [ INFO] - Train: 82 [ 200/461 ( 43%)] Loss: 2.571480 (2.4810) Loss_single: 1.913283 (1.8192) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.120s, 266.16/s (0.149s, 215.47/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-18 11:51:07,973 - train: [ INFO] - Train: 82 [ 250/461 ( 54%)] Loss: 2.692195 (2.5162) Loss_single: 1.962700 (1.8431) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.155s, 207.12/s (0.143s, 223.71/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-18 11:51:15,562 - train: [ INFO] - Train: 82 [ 300/461 ( 65%)] Loss: 2.397937 (2.4993) Loss_single: 1.728670 (1.8267) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.171s, 187.51/s (0.140s, 228.76/s) LR: 5.000e-04 Data: 0.000 (0.018) +2025-04-18 11:51:21,531 - train: [ INFO] - Train: 82 [ 350/461 ( 76%)] Loss: 2.468460 (2.4955) Loss_single: 1.808294 (1.8244) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.107s, 298.64/s (0.137s, 233.81/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:51:28,589 - train: [ INFO] - Train: 82 [ 400/461 ( 87%)] Loss: 2.759331 (2.5248) Loss_single: 1.999045 (1.8438) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 385.74/s (0.133s, 240.36/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 11:51:35,275 - train: [ INFO] - Train: 82 [ 450/461 ( 98%)] Loss: 2.582880 (2.5306) Loss_single: 1.922029 (1.8517) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.105s, 304.68/s (0.132s, 242.24/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:51:36,839 - train: [ INFO] - Train: 82 [ 460/461 (100%)] Loss: 2.648840 (2.5413) Loss_single: 1.901235 (1.8562) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.7159) Acc@5: 96.8750 (99.7159) Time: 0.204s, 157.03/s (0.131s, 243.66/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:51:42,900 - train: [ INFO] - Eval : 82 Time: 5.750 (5.750) Loss: 2.0199 (2.0199) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:51:46,792 - train: [ INFO] - Eval : 82 Time: 0.030 (0.189) Loss: 1.8302 (1.8428) Acc@1: 59.3750 (56.1887)Acc@5: 81.2500 (81.9240) +2025-04-18 11:51:48,959 - train: [ INFO] - Eval : 82 Time: 0.016 (0.144) Loss: 2.7661 (1.8671) Acc@1: 50.0000 (55.5898)Acc@5: 50.0000 (81.1103) +2025-04-18 11:51:56,840 - train: [ INFO] - Train: 83 [ 0/461 ( 0%)] Loss: 2.390685 (2.3907) Loss_single: 1.719758 (1.7198) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.031s, 6.36/s (5.031s, 6.36/s) LR: 5.000e-04 Data: 4.841 (4.841) +2025-04-18 11:52:03,662 - train: [ INFO] - Train: 83 [ 50/461 ( 11%)] Loss: 2.557716 (2.4742) Loss_single: 1.898766 (1.8093) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.133s, 240.31/s (0.225s, 142.28/s) LR: 5.000e-04 Data: 0.001 (0.098) +2025-04-18 11:52:10,124 - train: [ INFO] - Train: 83 [ 100/461 ( 22%)] Loss: 2.675380 (2.5413) Loss_single: 1.946687 (1.8551) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.193s, 165.61/s (0.177s, 180.61/s) LR: 5.000e-04 Data: 0.000 (0.049) +2025-04-18 11:52:15,828 - train: [ INFO] - Train: 83 [ 150/461 ( 33%)] Loss: 2.479473 (2.5258) Loss_single: 1.821003 (1.8466) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.110s, 292.21/s (0.156s, 205.22/s) LR: 5.000e-04 Data: 0.006 (0.033) +2025-04-18 11:52:22,473 - train: [ INFO] - Train: 83 [ 200/461 ( 43%)] Loss: 2.399228 (2.5005) Loss_single: 1.738041 (1.8249) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.121s, 263.99/s (0.147s, 217.56/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-18 11:52:29,566 - train: [ INFO] - Train: 83 [ 250/461 ( 54%)] Loss: 2.374760 (2.4795) Loss_single: 1.715196 (1.8066) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.129s, 249.00/s (0.143s, 224.16/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 11:52:35,768 - train: [ INFO] - Train: 83 [ 300/461 ( 65%)] Loss: 2.288346 (2.4522) Loss_single: 1.621807 (1.7802) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.105s, 304.84/s (0.140s, 229.32/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 11:52:41,392 - train: [ INFO] - Train: 83 [ 350/461 ( 76%)] Loss: 2.445729 (2.4514) Loss_single: 1.767350 (1.7786) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.138s, 231.86/s (0.136s, 235.98/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-18 11:52:48,251 - train: [ INFO] - Train: 83 [ 400/461 ( 87%)] Loss: 2.260635 (2.4302) Loss_single: 1.595190 (1.7582) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.123s, 259.64/s (0.133s, 240.92/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:52:55,255 - train: [ INFO] - Train: 83 [ 450/461 ( 98%)] Loss: 2.446433 (2.4318) Loss_single: 1.787816 (1.7612) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.080s, 398.30/s (0.130s, 245.22/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:52:56,766 - train: [ INFO] - Train: 83 [ 460/461 (100%)] Loss: 2.515249 (2.4394) Loss_single: 1.816588 (1.7662) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.087s, 366.94/s (0.130s, 245.71/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:53:03,401 - train: [ INFO] - Eval : 83 Time: 6.133 (6.133) Loss: 2.0592 (2.0592) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 11:53:08,455 - train: [ INFO] - Eval : 83 Time: 0.062 (0.219) Loss: 1.8368 (1.8519) Acc@1: 59.3750 (55.8211)Acc@5: 81.2500 (81.6789) +2025-04-18 11:53:11,635 - train: [ INFO] - Eval : 83 Time: 0.023 (0.175) Loss: 2.6738 (1.8754) Acc@1: 50.0000 (55.2429)Acc@5: 50.0000 (80.9175) +2025-04-18 11:53:19,920 - train: [ INFO] - Train: 84 [ 0/461 ( 0%)] Loss: 2.309103 (2.3091) Loss_single: 1.650576 (1.6506) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.270s, 6.07/s (5.270s, 6.07/s) LR: 5.000e-04 Data: 5.135 (5.135) +2025-04-18 11:53:26,092 - train: [ INFO] - Train: 84 [ 50/461 ( 11%)] Loss: 2.432830 (2.3710) Loss_single: 1.754067 (1.7023) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 363.48/s (0.223s, 143.60/s) LR: 5.000e-04 Data: 0.000 (0.102) +2025-04-18 11:53:32,170 - train: [ INFO] - Train: 84 [ 100/461 ( 22%)] Loss: 2.426952 (2.3896) Loss_single: 1.753330 (1.7193) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 321.05/s (0.172s, 185.99/s) LR: 5.000e-04 Data: 0.000 (0.052) +2025-04-18 11:53:38,642 - train: [ INFO] - Train: 84 [ 150/461 ( 33%)] Loss: 2.285604 (2.3636) Loss_single: 1.628017 (1.6965) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.190s, 168.75/s (0.150s, 213.15/s) LR: 5.000e-04 Data: 0.001 (0.035) +2025-04-18 11:53:44,777 - train: [ INFO] - Train: 84 [ 200/461 ( 43%)] Loss: 2.329937 (2.3569) Loss_single: 1.669421 (1.6911) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 383.60/s (0.143s, 224.08/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-18 11:53:51,604 - train: [ INFO] - Train: 84 [ 250/461 ( 54%)] Loss: 2.615275 (2.3999) Loss_single: 1.952828 (1.7347) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.200s, 159.94/s (0.141s, 227.32/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-18 11:53:57,861 - train: [ INFO] - Train: 84 [ 300/461 ( 65%)] Loss: 2.494519 (2.4135) Loss_single: 1.831917 (1.7486) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 407.04/s (0.137s, 233.14/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-18 11:54:04,396 - train: [ INFO] - Train: 84 [ 350/461 ( 76%)] Loss: 2.787775 (2.4602) Loss_single: 2.083171 (1.7904) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.126s, 254.82/s (0.134s, 238.91/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 11:54:10,733 - train: [ INFO] - Train: 84 [ 400/461 ( 87%)] Loss: 2.420360 (2.4558) Loss_single: 1.760599 (1.7871) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.112s, 285.63/s (0.130s, 245.58/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:54:16,528 - train: [ INFO] - Train: 84 [ 450/461 ( 98%)] Loss: 2.437482 (2.4540) Loss_single: 1.779716 (1.7864) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 407.55/s (0.129s, 248.76/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:54:17,577 - train: [ INFO] - Train: 84 [ 460/461 (100%)] Loss: 2.306068 (2.4405) Loss_single: 1.647566 (1.7737) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 387.65/s (0.128s, 249.79/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:54:23,356 - train: [ INFO] - Eval : 84 Time: 5.466 (5.466) Loss: 2.0171 (2.0171) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-18 11:54:26,671 - train: [ INFO] - Eval : 84 Time: 0.053 (0.172) Loss: 1.8234 (1.8476) Acc@1: 59.3750 (56.1887)Acc@5: 81.2500 (81.8015) +2025-04-18 11:54:28,378 - train: [ INFO] - Eval : 84 Time: 0.014 (0.128) Loss: 2.7882 (1.8709) Acc@1: 50.0000 (55.2043)Acc@5: 50.0000 (81.0332) +2025-04-18 11:54:37,154 - train: [ INFO] - Train: 85 [ 0/461 ( 0%)] Loss: 2.320357 (2.3204) Loss_single: 1.663183 (1.6632) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.600s, 5.71/s (5.600s, 5.71/s) LR: 5.000e-04 Data: 5.422 (5.422) +2025-04-18 11:54:44,580 - train: [ INFO] - Train: 85 [ 50/461 ( 11%)] Loss: 2.536384 (2.4284) Loss_single: 1.854823 (1.7590) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 342.26/s (0.254s, 125.75/s) LR: 5.000e-04 Data: 0.000 (0.107) +2025-04-18 11:54:52,554 - train: [ INFO] - Train: 85 [ 100/461 ( 22%)] Loss: 2.476743 (2.4445) Loss_single: 1.810498 (1.7762) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.111s, 288.88/s (0.198s, 161.90/s) LR: 5.000e-04 Data: 0.000 (0.054) +2025-04-18 11:54:58,033 - train: [ INFO] - Train: 85 [ 150/461 ( 33%)] Loss: 2.418468 (2.4380) Loss_single: 1.734889 (1.7658) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.126s, 253.94/s (0.168s, 190.17/s) LR: 5.000e-04 Data: 0.000 (0.037) +2025-04-18 11:55:03,368 - train: [ INFO] - Train: 85 [ 200/461 ( 43%)] Loss: 2.360157 (2.4224) Loss_single: 1.688021 (1.7503) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.145s, 221.32/s (0.153s, 209.41/s) LR: 5.000e-04 Data: 0.000 (0.028) +2025-04-18 11:55:10,254 - train: [ INFO] - Train: 85 [ 250/461 ( 54%)] Loss: 2.240618 (2.3921) Loss_single: 1.582290 (1.7223) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.184s, 173.88/s (0.146s, 218.65/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-18 11:55:17,276 - train: [ INFO] - Train: 85 [ 300/461 ( 65%)] Loss: 2.517530 (2.4100) Loss_single: 1.799921 (1.7334) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.109s, 292.81/s (0.145s, 221.27/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-18 11:55:24,918 - train: [ INFO] - Train: 85 [ 350/461 ( 76%)] Loss: 2.367599 (2.4047) Loss_single: 1.708950 (1.7303) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.132s, 242.73/s (0.141s, 226.74/s) LR: 5.000e-04 Data: 0.003 (0.016) +2025-04-18 11:55:31,350 - train: [ INFO] - Train: 85 [ 400/461 ( 87%)] Loss: 2.371947 (2.4011) Loss_single: 1.706931 (1.7277) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.096s, 333.13/s (0.138s, 231.84/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 11:55:37,397 - train: [ INFO] - Train: 85 [ 450/461 ( 98%)] Loss: 2.589120 (2.4199) Loss_single: 1.903621 (1.7453) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.084s, 380.28/s (0.136s, 235.21/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:55:38,221 - train: [ INFO] - Train: 85 [ 460/461 (100%)] Loss: 2.419912 (2.4199) Loss_single: 1.762453 (1.7469) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.078s, 411.61/s (0.135s, 237.26/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:55:43,273 - train: [ INFO] - Eval : 85 Time: 4.626 (4.626) Loss: 2.0481 (2.0481) Acc@1: 53.1250 (53.1250)Acc@5: 78.1250 (78.1250) +2025-04-18 11:55:46,689 - train: [ INFO] - Eval : 85 Time: 0.050 (0.158) Loss: 1.8118 (1.8454) Acc@1: 59.3750 (56.1275)Acc@5: 78.1250 (81.9853) +2025-04-18 11:55:47,913 - train: [ INFO] - Eval : 85 Time: 0.016 (0.113) Loss: 2.8782 (1.8689) Acc@1: 0.0000 (55.0501)Acc@5: 50.0000 (81.2259) +2025-04-18 11:55:56,548 - train: [ INFO] - Train: 86 [ 0/461 ( 0%)] Loss: 2.594810 (2.5948) Loss_single: 1.835515 (1.8355) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (96.8750) Acc@5: 100.0000 (100.0000) Time: 5.835s, 5.48/s (5.835s, 5.48/s) LR: 5.000e-04 Data: 5.631 (5.631) +2025-04-18 11:56:03,624 - train: [ INFO] - Train: 86 [ 50/461 ( 11%)] Loss: 2.406298 (2.5006) Loss_single: 1.747055 (1.7913) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.091s, 351.12/s (0.233s, 137.31/s) LR: 5.000e-04 Data: 0.000 (0.112) +2025-04-18 11:56:10,186 - train: [ INFO] - Train: 86 [ 100/461 ( 22%)] Loss: 2.734648 (2.5786) Loss_single: 2.020800 (1.8678) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.089s, 357.79/s (0.182s, 175.57/s) LR: 5.000e-04 Data: 0.000 (0.057) +2025-04-18 11:56:17,374 - train: [ INFO] - Train: 86 [ 150/461 ( 33%)] Loss: 2.400509 (2.5341) Loss_single: 1.721197 (1.8311) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.102s, 312.80/s (0.169s, 189.70/s) LR: 5.000e-04 Data: 0.005 (0.038) +2025-04-18 11:56:23,440 - train: [ INFO] - Train: 86 [ 200/461 ( 43%)] Loss: 2.401059 (2.5075) Loss_single: 1.742197 (1.8134) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.083s, 386.95/s (0.154s, 207.53/s) LR: 5.000e-04 Data: 0.001 (0.029) +2025-04-18 11:56:30,403 - train: [ INFO] - Train: 86 [ 250/461 ( 54%)] Loss: 2.331154 (2.4781) Loss_single: 1.672155 (1.7898) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (100.0000) Time: 0.090s, 356.45/s (0.149s, 215.15/s) LR: 5.000e-04 Data: 0.001 (0.023) +2025-04-18 11:56:37,606 - train: [ INFO] - Train: 86 [ 300/461 ( 65%)] Loss: 2.413901 (2.4689) Loss_single: 1.755422 (1.7849) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (100.0000) Time: 0.079s, 403.05/s (0.145s, 220.26/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-18 11:56:43,547 - train: [ INFO] - Train: 86 [ 350/461 ( 76%)] Loss: 2.355075 (2.4547) Loss_single: 1.695741 (1.7738) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.090s, 354.62/s (0.141s, 226.28/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 11:56:49,306 - train: [ INFO] - Train: 86 [ 400/461 ( 87%)] Loss: 2.622615 (2.4733) Loss_single: 1.961787 (1.7947) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.123s, 259.15/s (0.138s, 231.78/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-18 11:56:55,625 - train: [ INFO] - Train: 86 [ 450/461 ( 98%)] Loss: 2.473747 (2.4734) Loss_single: 1.754311 (1.7906) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.077s, 415.76/s (0.137s, 234.09/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:56:56,763 - train: [ INFO] - Train: 86 [ 460/461 (100%)] Loss: 2.301982 (2.4578) Loss_single: 1.643671 (1.7773) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (100.0000) Time: 0.138s, 232.61/s (0.136s, 234.98/s) LR: 5.000e-04 Data: 0.001 (0.013) +2025-04-18 11:57:02,975 - train: [ INFO] - Eval : 86 Time: 5.928 (5.928) Loss: 2.0449 (2.0449) Acc@1: 53.1250 (53.1250)Acc@5: 75.0000 (75.0000) +2025-04-18 11:57:07,604 - train: [ INFO] - Eval : 86 Time: 0.029 (0.207) Loss: 1.8356 (1.8539) Acc@1: 59.3750 (56.1275)Acc@5: 81.2500 (81.4338) +2025-04-18 11:57:10,850 - train: [ INFO] - Eval : 86 Time: 0.027 (0.168) Loss: 2.8334 (1.8767) Acc@1: 0.0000 (55.1658)Acc@5: 50.0000 (80.8019) +2025-04-18 11:57:18,800 - train: [ INFO] - Train: 87 [ 0/461 ( 0%)] Loss: 2.452991 (2.4530) Loss_single: 1.789457 (1.7895) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.185s, 6.17/s (5.185s, 6.17/s) LR: 5.000e-04 Data: 5.001 (5.001) +2025-04-18 11:57:24,901 - train: [ INFO] - Train: 87 [ 50/461 ( 11%)] Loss: 2.680219 (2.5666) Loss_single: 2.008967 (1.8992) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.098s, 327.36/s (0.221s, 144.99/s) LR: 5.000e-04 Data: 0.000 (0.099) +2025-04-18 11:57:32,160 - train: [ INFO] - Train: 87 [ 100/461 ( 22%)] Loss: 2.550125 (2.5611) Loss_single: 1.862234 (1.8869) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.206s, 155.07/s (0.172s, 185.86/s) LR: 5.000e-04 Data: 0.001 (0.050) +2025-04-18 11:57:39,838 - train: [ INFO] - Train: 87 [ 150/461 ( 33%)] Loss: 2.670628 (2.5885) Loss_single: 1.969293 (1.9075) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.107s, 298.81/s (0.156s, 204.51/s) LR: 5.000e-04 Data: 0.000 (0.034) +2025-04-18 11:57:46,577 - train: [ INFO] - Train: 87 [ 200/461 ( 43%)] Loss: 2.263348 (2.5235) Loss_single: 1.604142 (1.8468) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.083s, 383.51/s (0.149s, 215.35/s) LR: 5.000e-04 Data: 0.001 (0.026) +2025-04-18 11:57:53,793 - train: [ INFO] - Train: 87 [ 250/461 ( 54%)] Loss: 2.345838 (2.4939) Loss_single: 1.681571 (1.8193) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.124s, 258.23/s (0.145s, 221.20/s) LR: 5.000e-04 Data: 0.001 (0.021) +2025-04-18 11:58:00,046 - train: [ INFO] - Train: 87 [ 300/461 ( 65%)] Loss: 2.224690 (2.4554) Loss_single: 1.565418 (1.7830) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 397.24/s (0.141s, 226.46/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 11:58:06,544 - train: [ INFO] - Train: 87 [ 350/461 ( 76%)] Loss: 2.699500 (2.4859) Loss_single: 1.985911 (1.8084) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.6094) Acc@5: 100.0000 (100.0000) Time: 0.087s, 366.66/s (0.138s, 231.51/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-18 11:58:11,659 - train: [ INFO] - Train: 87 [ 400/461 ( 87%)] Loss: 2.528911 (2.4907) Loss_single: 1.820307 (1.8097) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (100.0000) Time: 0.078s, 411.62/s (0.134s, 239.41/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:58:18,179 - train: [ INFO] - Train: 87 [ 450/461 ( 98%)] Loss: 2.267927 (2.4684) Loss_single: 1.609486 (1.7897) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (100.0000) Time: 0.079s, 403.09/s (0.133s, 240.32/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:58:19,252 - train: [ INFO] - Train: 87 [ 460/461 (100%)] Loss: 2.482324 (2.4697) Loss_single: 1.816788 (1.7921) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (100.0000) Time: 0.118s, 271.16/s (0.133s, 241.37/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:58:26,224 - train: [ INFO] - Eval : 87 Time: 6.617 (6.617) Loss: 2.0720 (2.0720) Acc@1: 53.1250 (53.1250)Acc@5: 71.8750 (71.8750) +2025-04-18 11:58:31,093 - train: [ INFO] - Eval : 87 Time: 0.387 (0.225) Loss: 1.8211 (1.8469) Acc@1: 59.3750 (56.4951)Acc@5: 81.2500 (81.8627) +2025-04-18 11:58:33,149 - train: [ INFO] - Eval : 87 Time: 0.014 (0.165) Loss: 2.8098 (1.8707) Acc@1: 50.0000 (55.5127)Acc@5: 50.0000 (81.1103) +2025-04-18 11:58:41,317 - train: [ INFO] - Train: 88 [ 0/461 ( 0%)] Loss: 2.376579 (2.3766) Loss_single: 1.714629 (1.7146) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.120s, 6.25/s (5.120s, 6.25/s) LR: 5.000e-04 Data: 4.990 (4.990) +2025-04-18 11:58:47,872 - train: [ INFO] - Train: 88 [ 50/461 ( 11%)] Loss: 2.621953 (2.4993) Loss_single: 1.962184 (1.8384) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.129s, 248.43/s (0.228s, 140.18/s) LR: 5.000e-04 Data: 0.001 (0.098) +2025-04-18 11:58:54,858 - train: [ INFO] - Train: 88 [ 100/461 ( 22%)] Loss: 2.236419 (2.4117) Loss_single: 1.578897 (1.7519) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 382.66/s (0.175s, 182.76/s) LR: 5.000e-04 Data: 0.001 (0.050) +2025-04-18 11:59:00,798 - train: [ INFO] - Train: 88 [ 150/461 ( 33%)] Loss: 2.328972 (2.3910) Loss_single: 1.671500 (1.7318) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 389.36/s (0.156s, 204.87/s) LR: 5.000e-04 Data: 0.001 (0.034) +2025-04-18 11:59:07,968 - train: [ INFO] - Train: 88 [ 200/461 ( 43%)] Loss: 2.285667 (2.3699) Loss_single: 1.620772 (1.7096) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.140s, 229.20/s (0.148s, 215.85/s) LR: 5.000e-04 Data: 0.000 (0.025) +2025-04-18 11:59:14,948 - train: [ INFO] - Train: 88 [ 250/461 ( 54%)] Loss: 2.451669 (2.3835) Loss_single: 1.791687 (1.7233) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.160s, 200.59/s (0.146s, 218.82/s) LR: 5.000e-04 Data: 0.001 (0.021) +2025-04-18 11:59:21,938 - train: [ INFO] - Train: 88 [ 300/461 ( 65%)] Loss: 2.538524 (2.4057) Loss_single: 1.797702 (1.7339) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.5536) Acc@5: 96.8750 (99.5536) Time: 0.140s, 227.90/s (0.144s, 222.68/s) LR: 5.000e-04 Data: 0.004 (0.017) +2025-04-18 11:59:27,832 - train: [ INFO] - Train: 88 [ 350/461 ( 76%)] Loss: 2.366697 (2.4008) Loss_single: 1.704324 (1.7302) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.086s, 370.72/s (0.140s, 229.00/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-18 11:59:34,427 - train: [ INFO] - Train: 88 [ 400/461 ( 87%)] Loss: 2.276065 (2.3869) Loss_single: 1.614692 (1.7174) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.199s, 160.87/s (0.137s, 234.23/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 11:59:40,848 - train: [ INFO] - Train: 88 [ 450/461 ( 98%)] Loss: 2.611839 (2.4094) Loss_single: 1.880209 (1.7337) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.155s, 206.41/s (0.136s, 235.92/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 11:59:41,777 - train: [ INFO] - Train: 88 [ 460/461 (100%)] Loss: 2.739064 (2.4394) Loss_single: 1.998001 (1.7577) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1477) Acc@5: 96.8750 (99.4318) Time: 0.130s, 246.95/s (0.135s, 237.57/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 11:59:46,611 - train: [ INFO] - Eval : 88 Time: 4.584 (4.584) Loss: 2.0478 (2.0478) Acc@1: 43.7500 (43.7500)Acc@5: 75.0000 (75.0000) +2025-04-18 11:59:50,694 - train: [ INFO] - Eval : 88 Time: 0.074 (0.170) Loss: 1.8337 (1.8533) Acc@1: 59.3750 (56.1887)Acc@5: 78.1250 (81.3725) +2025-04-18 11:59:52,305 - train: [ INFO] - Eval : 88 Time: 0.015 (0.125) Loss: 2.9112 (1.8784) Acc@1: 0.0000 (55.2429)Acc@5: 50.0000 (80.5320) +2025-04-18 12:00:01,668 - train: [ INFO] - Train: 89 [ 0/461 ( 0%)] Loss: 2.359069 (2.3591) Loss_single: 1.697016 (1.6970) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.355s, 5.04/s (6.355s, 5.04/s) LR: 5.000e-04 Data: 6.189 (6.189) +2025-04-18 12:00:09,168 - train: [ INFO] - Train: 89 [ 50/461 ( 11%)] Loss: 2.678580 (2.5188) Loss_single: 1.959119 (1.8281) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.106s, 301.21/s (0.254s, 126.03/s) LR: 5.000e-04 Data: 0.001 (0.122) +2025-04-18 12:00:15,188 - train: [ INFO] - Train: 89 [ 100/461 ( 22%)] Loss: 2.596900 (2.5448) Loss_single: 1.852934 (1.8364) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.080s, 401.20/s (0.187s, 170.70/s) LR: 5.000e-04 Data: 0.000 (0.062) +2025-04-18 12:00:21,124 - train: [ INFO] - Train: 89 [ 150/461 ( 33%)] Loss: 2.471643 (2.5265) Loss_single: 1.805203 (1.8286) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.085s, 374.60/s (0.162s, 197.39/s) LR: 5.000e-04 Data: 0.001 (0.048) +2025-04-18 12:00:32,176 - train: [ INFO] - Train: 89 [ 200/461 ( 43%)] Loss: 2.322983 (2.4858) Loss_single: 1.663231 (1.7955) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.089s, 361.28/s (0.176s, 181.62/s) LR: 5.000e-04 Data: 0.000 (0.064) +2025-04-18 12:00:39,788 - train: [ INFO] - Train: 89 [ 250/461 ( 54%)] Loss: 2.429731 (2.4765) Loss_single: 1.766775 (1.7907) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.080s, 398.45/s (0.171s, 187.03/s) LR: 5.000e-04 Data: 0.000 (0.058) +2025-04-18 12:00:47,281 - train: [ INFO] - Train: 89 [ 300/461 ( 65%)] Loss: 2.313327 (2.4532) Loss_single: 1.655150 (1.7713) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.077s, 417.69/s (0.167s, 191.14/s) LR: 5.000e-04 Data: 0.000 (0.057) +2025-04-18 12:00:55,021 - train: [ INFO] - Train: 89 [ 350/461 ( 76%)] Loss: 2.280365 (2.4316) Loss_single: 1.624773 (1.7530) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.147s, 217.62/s (0.166s, 193.35/s) LR: 5.000e-04 Data: 0.000 (0.055) +2025-04-18 12:01:04,063 - train: [ INFO] - Train: 89 [ 400/461 ( 87%)] Loss: 2.496239 (2.4388) Loss_single: 1.757592 (1.7535) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.3056) Acc@5: 96.8750 (99.3056) Time: 0.080s, 397.99/s (0.166s, 192.28/s) LR: 5.000e-04 Data: 0.001 (0.056) +2025-04-18 12:01:12,540 - train: [ INFO] - Train: 89 [ 450/461 ( 98%)] Loss: 2.592702 (2.4542) Loss_single: 1.866236 (1.7648) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 100.0000 (99.3750) Time: 0.084s, 379.08/s (0.165s, 193.49/s) LR: 5.000e-04 Data: 0.000 (0.056) +2025-04-18 12:01:13,612 - train: [ INFO] - Train: 89 [ 460/461 (100%)] Loss: 2.352209 (2.4449) Loss_single: 1.695299 (1.7585) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.4318) Time: 0.099s, 324.00/s (0.164s, 195.01/s) LR: 5.000e-04 Data: 0.000 (0.055) +2025-04-18 12:01:18,769 - train: [ INFO] - Eval : 89 Time: 4.833 (4.833) Loss: 2.0586 (2.0586) Acc@1: 50.0000 (50.0000)Acc@5: 75.0000 (75.0000) +2025-04-18 12:01:22,508 - train: [ INFO] - Eval : 89 Time: 0.047 (0.168) Loss: 1.8372 (1.8581) Acc@1: 56.2500 (56.1275)Acc@5: 78.1250 (81.3725) +2025-04-18 12:01:24,628 - train: [ INFO] - Eval : 89 Time: 0.022 (0.130) Loss: 2.8241 (1.8813) Acc@1: 50.0000 (55.2814)Acc@5: 50.0000 (80.6476) +2025-04-18 12:01:34,122 - train: [ INFO] - Train: 90 [ 0/461 ( 0%)] Loss: 2.446237 (2.4462) Loss_single: 1.784343 (1.7843) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 6.544s, 4.89/s (6.544s, 4.89/s) LR: 5.000e-04 Data: 6.414 (6.414) +2025-04-18 12:01:40,766 - train: [ INFO] - Train: 90 [ 50/461 ( 11%)] Loss: 2.555913 (2.5011) Loss_single: 1.856110 (1.8202) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.143s, 224.07/s (0.257s, 124.35/s) LR: 5.000e-04 Data: 0.000 (0.127) +2025-04-18 12:01:46,718 - train: [ INFO] - Train: 90 [ 100/461 ( 22%)] Loss: 2.622712 (2.5416) Loss_single: 1.873774 (1.8381) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (98.9583) Time: 0.080s, 397.85/s (0.187s, 171.45/s) LR: 5.000e-04 Data: 0.001 (0.064) +2025-04-18 12:01:53,773 - train: [ INFO] - Train: 90 [ 150/461 ( 33%)] Loss: 2.423231 (2.5120) Loss_single: 1.764285 (1.8196) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.2188) Time: 0.082s, 389.73/s (0.168s, 190.96/s) LR: 5.000e-04 Data: 0.000 (0.043) +2025-04-18 12:01:59,540 - train: [ INFO] - Train: 90 [ 200/461 ( 43%)] Loss: 2.538467 (2.5173) Loss_single: 1.878411 (1.8314) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.121s, 264.68/s (0.154s, 207.22/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-18 12:02:05,116 - train: [ INFO] - Train: 90 [ 250/461 ( 54%)] Loss: 2.311358 (2.4830) Loss_single: 1.648440 (1.8009) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.100s, 319.46/s (0.146s, 219.56/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-18 12:02:11,820 - train: [ INFO] - Train: 90 [ 300/461 ( 65%)] Loss: 2.465441 (2.4805) Loss_single: 1.733512 (1.7913) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.211s, 151.85/s (0.140s, 228.86/s) LR: 5.000e-04 Data: 0.001 (0.022) +2025-04-18 12:02:18,240 - train: [ INFO] - Train: 90 [ 350/461 ( 76%)] Loss: 2.364749 (2.4660) Loss_single: 1.698922 (1.7797) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.099s, 322.77/s (0.138s, 231.77/s) LR: 5.000e-04 Data: 0.001 (0.019) +2025-04-18 12:02:24,864 - train: [ INFO] - Train: 90 [ 400/461 ( 87%)] Loss: 2.536320 (2.4738) Loss_single: 1.831096 (1.7854) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.080s, 397.81/s (0.137s, 233.20/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 12:02:30,138 - train: [ INFO] - Train: 90 [ 450/461 ( 98%)] Loss: 2.422509 (2.4687) Loss_single: 1.732432 (1.7801) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.078s, 412.54/s (0.134s, 239.55/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-18 12:02:30,985 - train: [ INFO] - Train: 90 [ 460/461 (100%)] Loss: 2.413459 (2.4637) Loss_single: 1.706813 (1.7735) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.083s, 386.38/s (0.133s, 241.49/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-18 12:02:36,027 - train: [ INFO] - Eval : 90 Time: 4.697 (4.697) Loss: 2.0381 (2.0381) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-18 12:02:41,343 - train: [ INFO] - Eval : 90 Time: 0.022 (0.196) Loss: 1.8444 (1.8515) Acc@1: 59.3750 (57.0466)Acc@5: 81.2500 (82.4755) +2025-04-18 12:02:42,852 - train: [ INFO] - Eval : 90 Time: 0.014 (0.141) Loss: 2.7804 (1.8763) Acc@1: 50.0000 (55.7826)Acc@5: 50.0000 (81.5343) +2025-04-18 12:02:50,449 - train: [ INFO] - Train: 91 [ 0/461 ( 0%)] Loss: 2.231249 (2.2312) Loss_single: 1.574049 (1.5740) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.861s, 6.58/s (4.861s, 6.58/s) LR: 5.000e-04 Data: 4.725 (4.725) +2025-04-18 12:02:57,485 - train: [ INFO] - Train: 91 [ 50/461 ( 11%)] Loss: 2.578604 (2.4049) Loss_single: 1.911346 (1.7427) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.116s, 276.91/s (0.210s, 152.63/s) LR: 5.000e-04 Data: 0.000 (0.094) +2025-04-18 12:03:03,204 - train: [ INFO] - Train: 91 [ 100/461 ( 22%)] Loss: 2.350008 (2.3866) Loss_single: 1.691318 (1.7256) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.126s, 253.43/s (0.162s, 197.35/s) LR: 5.000e-04 Data: 0.000 (0.048) +2025-04-18 12:03:09,081 - train: [ INFO] - Train: 91 [ 150/461 ( 33%)] Loss: 2.823588 (2.4959) Loss_single: 2.074041 (1.8127) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.096s, 334.62/s (0.147s, 217.43/s) LR: 5.000e-04 Data: 0.001 (0.032) +2025-04-18 12:03:16,344 - train: [ INFO] - Train: 91 [ 200/461 ( 43%)] Loss: 2.357143 (2.4681) Loss_single: 1.695780 (1.7893) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.112s, 286.89/s (0.142s, 224.72/s) LR: 5.000e-04 Data: 0.000 (0.024) +2025-04-18 12:03:21,990 - train: [ INFO] - Train: 91 [ 250/461 ( 54%)] Loss: 2.473216 (2.4690) Loss_single: 1.813630 (1.7934) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4792) Acc@5: 100.0000 (99.4792) Time: 0.120s, 267.19/s (0.136s, 234.96/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-18 12:03:27,536 - train: [ INFO] - Train: 91 [ 300/461 ( 65%)] Loss: 2.397645 (2.4588) Loss_single: 1.740267 (1.7858) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.082s, 390.50/s (0.132s, 242.65/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 12:03:33,879 - train: [ INFO] - Train: 91 [ 350/461 ( 76%)] Loss: 2.364535 (2.4470) Loss_single: 1.708879 (1.7762) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.161s, 199.35/s (0.131s, 244.16/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 12:03:39,648 - train: [ INFO] - Train: 91 [ 400/461 ( 87%)] Loss: 2.473743 (2.4500) Loss_single: 1.804655 (1.7793) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.127s, 251.33/s (0.129s, 247.97/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 12:03:46,455 - train: [ INFO] - Train: 91 [ 450/461 ( 98%)] Loss: 2.316905 (2.4367) Loss_single: 1.657913 (1.7672) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.078s, 410.57/s (0.127s, 251.47/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:03:47,418 - train: [ INFO] - Train: 91 [ 460/461 (100%)] Loss: 2.378379 (2.4314) Loss_single: 1.717376 (1.7627) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.079s, 407.54/s (0.127s, 252.83/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:03:52,934 - train: [ INFO] - Eval : 91 Time: 5.250 (5.250) Loss: 2.0437 (2.0437) Acc@1: 50.0000 (50.0000)Acc@5: 71.8750 (71.8750) +2025-04-18 12:03:57,320 - train: [ INFO] - Eval : 91 Time: 0.078 (0.189) Loss: 1.8495 (1.8601) Acc@1: 59.3750 (56.3725)Acc@5: 81.2500 (81.9853) +2025-04-18 12:03:59,341 - train: [ INFO] - Eval : 91 Time: 0.014 (0.142) Loss: 2.8609 (1.8844) Acc@1: 50.0000 (55.2429)Acc@5: 50.0000 (80.8790) +2025-04-18 12:04:08,862 - train: [ INFO] - Train: 92 [ 0/461 ( 0%)] Loss: 2.363977 (2.3640) Loss_single: 1.705521 (1.7055) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.221s, 7.58/s (4.221s, 7.58/s) LR: 5.000e-04 Data: 4.106 (4.106) +2025-04-18 12:04:14,594 - train: [ INFO] - Train: 92 [ 50/461 ( 11%)] Loss: 2.260679 (2.3123) Loss_single: 1.602843 (1.6542) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.106s, 302.22/s (0.194s, 164.61/s) LR: 5.000e-04 Data: 0.000 (0.081) +2025-04-18 12:04:20,723 - train: [ INFO] - Train: 92 [ 100/461 ( 22%)] Loss: 2.440424 (2.3550) Loss_single: 1.750355 (1.6862) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 382.85/s (0.151s, 211.29/s) LR: 5.000e-04 Data: 0.001 (0.041) +2025-04-18 12:04:27,522 - train: [ INFO] - Train: 92 [ 150/461 ( 33%)] Loss: 2.242582 (2.3269) Loss_single: 1.583027 (1.6604) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.086s, 374.15/s (0.143s, 223.49/s) LR: 5.000e-04 Data: 0.001 (0.028) +2025-04-18 12:04:33,887 - train: [ INFO] - Train: 92 [ 200/461 ( 43%)] Loss: 2.276198 (2.3168) Loss_single: 1.601876 (1.6487) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.090s, 357.33/s (0.139s, 230.31/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-18 12:04:40,001 - train: [ INFO] - Train: 92 [ 250/461 ( 54%)] Loss: 2.360757 (2.3241) Loss_single: 1.698686 (1.6571) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.088s, 365.49/s (0.135s, 236.19/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 12:04:45,446 - train: [ INFO] - Train: 92 [ 300/461 ( 65%)] Loss: 2.516298 (2.3516) Loss_single: 1.855183 (1.6854) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.098s, 325.94/s (0.131s, 244.40/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 12:04:52,095 - train: [ INFO] - Train: 92 [ 350/461 ( 76%)] Loss: 2.541415 (2.3753) Loss_single: 1.883259 (1.7101) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.150s, 212.68/s (0.130s, 246.45/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 12:04:59,087 - train: [ INFO] - Train: 92 [ 400/461 ( 87%)] Loss: 2.309053 (2.3679) Loss_single: 1.652121 (1.7037) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.152s, 210.65/s (0.129s, 248.00/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:05:04,247 - train: [ INFO] - Train: 92 [ 450/461 ( 98%)] Loss: 2.510897 (2.3822) Loss_single: 1.834248 (1.7167) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.082s, 389.00/s (0.126s, 253.74/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 12:05:05,167 - train: [ INFO] - Train: 92 [ 460/461 (100%)] Loss: 2.636429 (2.4053) Loss_single: 1.941832 (1.7372) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.079s, 405.38/s (0.125s, 255.28/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 12:05:11,883 - train: [ INFO] - Eval : 92 Time: 6.441 (6.441) Loss: 2.0315 (2.0315) Acc@1: 53.1250 (53.1250)Acc@5: 78.1250 (78.1250) +2025-04-18 12:05:14,879 - train: [ INFO] - Eval : 92 Time: 0.031 (0.185) Loss: 1.8225 (1.8506) Acc@1: 59.3750 (56.2500)Acc@5: 81.2500 (82.4142) +2025-04-18 12:05:16,363 - train: [ INFO] - Eval : 92 Time: 0.016 (0.133) Loss: 2.8433 (1.8752) Acc@1: 50.0000 (55.3200)Acc@5: 50.0000 (81.1874) +2025-04-18 12:05:24,489 - train: [ INFO] - Train: 93 [ 0/461 ( 0%)] Loss: 2.574171 (2.5742) Loss_single: 1.878769 (1.8788) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 5.274s, 6.07/s (5.274s, 6.07/s) LR: 5.000e-04 Data: 5.118 (5.118) +2025-04-18 12:05:31,309 - train: [ INFO] - Train: 93 [ 50/461 ( 11%)] Loss: 2.391876 (2.4830) Loss_single: 1.665868 (1.7723) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (100.0000) Time: 0.104s, 307.60/s (0.221s, 144.73/s) LR: 5.000e-04 Data: 0.001 (0.101) +2025-04-18 12:05:36,761 - train: [ INFO] - Train: 93 [ 100/461 ( 22%)] Loss: 2.578536 (2.5149) Loss_single: 1.885582 (1.8101) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (100.0000) Time: 0.107s, 297.92/s (0.165s, 193.62/s) LR: 5.000e-04 Data: 0.000 (0.051) +2025-04-18 12:05:42,954 - train: [ INFO] - Train: 93 [ 150/461 ( 33%)] Loss: 2.529817 (2.5186) Loss_single: 1.832847 (1.8158) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (100.0000) Time: 0.106s, 302.85/s (0.147s, 217.12/s) LR: 5.000e-04 Data: 0.000 (0.034) +2025-04-18 12:05:49,634 - train: [ INFO] - Train: 93 [ 200/461 ( 43%)] Loss: 2.478380 (2.5106) Loss_single: 1.820127 (1.8166) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (100.0000) Time: 0.079s, 406.27/s (0.142s, 225.90/s) LR: 5.000e-04 Data: 0.000 (0.026) +2025-04-18 12:05:55,738 - train: [ INFO] - Train: 93 [ 250/461 ( 54%)] Loss: 2.496668 (2.5082) Loss_single: 1.756595 (1.8066) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 96.8750 (99.4792) Time: 0.124s, 258.43/s (0.138s, 232.50/s) LR: 5.000e-04 Data: 0.000 (0.021) +2025-04-18 12:06:00,815 - train: [ INFO] - Train: 93 [ 300/461 ( 65%)] Loss: 2.505972 (2.5079) Loss_single: 1.841231 (1.8116) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.087s, 367.55/s (0.132s, 243.25/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 12:06:07,342 - train: [ INFO] - Train: 93 [ 350/461 ( 76%)] Loss: 2.423024 (2.4973) Loss_single: 1.736652 (1.8022) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.080s, 398.60/s (0.128s, 249.40/s) LR: 5.000e-04 Data: 0.001 (0.015) +2025-04-18 12:06:13,120 - train: [ INFO] - Train: 93 [ 400/461 ( 87%)] Loss: 2.510019 (2.4987) Loss_single: 1.791390 (1.8010) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.149s, 215.40/s (0.127s, 252.65/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 12:06:19,316 - train: [ INFO] - Train: 93 [ 450/461 ( 98%)] Loss: 2.722770 (2.5211) Loss_single: 1.966657 (1.8176) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.0625) Acc@5: 96.8750 (99.3750) Time: 0.084s, 380.38/s (0.126s, 253.53/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 12:06:20,800 - train: [ INFO] - Train: 93 [ 460/461 (100%)] Loss: 2.371534 (2.5075) Loss_single: 1.708866 (1.8077) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1477) Acc@5: 100.0000 (99.4318) Time: 0.091s, 350.54/s (0.127s, 252.67/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 12:06:26,919 - train: [ INFO] - Eval : 93 Time: 5.815 (5.815) Loss: 2.0735 (2.0735) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-18 12:06:34,978 - train: [ INFO] - Eval : 93 Time: 0.050 (0.272) Loss: 1.8310 (1.8624) Acc@1: 59.3750 (56.3725)Acc@5: 78.1250 (81.3725) +2025-04-18 12:06:37,813 - train: [ INFO] - Eval : 93 Time: 0.015 (0.204) Loss: 2.8604 (1.8878) Acc@1: 0.0000 (55.3200)Acc@5: 50.0000 (80.6476) +2025-04-18 12:06:45,366 - train: [ INFO] - Train: 94 [ 0/461 ( 0%)] Loss: 2.413727 (2.4137) Loss_single: 1.745022 (1.7450) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.720s, 6.78/s (4.720s, 6.78/s) LR: 5.000e-04 Data: 4.558 (4.558) +2025-04-18 12:06:51,672 - train: [ INFO] - Train: 94 [ 50/461 ( 11%)] Loss: 2.443100 (2.4284) Loss_single: 1.775845 (1.7604) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 378.96/s (0.214s, 149.21/s) LR: 5.000e-04 Data: 0.001 (0.090) +2025-04-18 12:06:58,496 - train: [ INFO] - Train: 94 [ 100/461 ( 22%)] Loss: 2.342173 (2.3997) Loss_single: 1.684435 (1.7351) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.130s, 246.00/s (0.162s, 197.94/s) LR: 5.000e-04 Data: 0.001 (0.046) +2025-04-18 12:07:05,893 - train: [ INFO] - Train: 94 [ 150/461 ( 33%)] Loss: 2.480467 (2.4199) Loss_single: 1.787336 (1.7482) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.120s, 266.66/s (0.157s, 204.29/s) LR: 5.000e-04 Data: 0.000 (0.032) +2025-04-18 12:07:12,589 - train: [ INFO] - Train: 94 [ 200/461 ( 43%)] Loss: 2.445133 (2.4249) Loss_single: 1.787311 (1.7560) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.128s, 250.71/s (0.151s, 212.23/s) LR: 5.000e-04 Data: 0.001 (0.024) +2025-04-18 12:07:18,346 - train: [ INFO] - Train: 94 [ 250/461 ( 54%)] Loss: 2.315385 (2.4067) Loss_single: 1.654564 (1.7391) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 380.38/s (0.144s, 222.90/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-18 12:07:25,841 - train: [ INFO] - Train: 94 [ 300/461 ( 65%)] Loss: 2.290894 (2.3901) Loss_single: 1.632689 (1.7239) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.095s, 335.96/s (0.142s, 225.31/s) LR: 5.000e-04 Data: 0.001 (0.016) +2025-04-18 12:07:33,669 - train: [ INFO] - Train: 94 [ 350/461 ( 76%)] Loss: 2.243706 (2.3718) Loss_single: 1.583032 (1.7063) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.167s, 191.71/s (0.140s, 228.65/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 12:07:39,483 - train: [ INFO] - Train: 94 [ 400/461 ( 87%)] Loss: 2.640302 (2.4017) Loss_single: 1.973688 (1.7360) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.084s, 379.47/s (0.137s, 233.72/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 12:07:47,137 - train: [ INFO] - Train: 94 [ 450/461 ( 98%)] Loss: 2.242506 (2.3857) Loss_single: 1.584602 (1.7209) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.147s, 216.96/s (0.137s, 233.66/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:07:48,081 - train: [ INFO] - Train: 94 [ 460/461 (100%)] Loss: 2.528140 (2.3987) Loss_single: 1.868186 (1.7342) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.078s, 408.10/s (0.136s, 235.26/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:07:53,822 - train: [ INFO] - Eval : 94 Time: 5.464 (5.464) Loss: 2.0362 (2.0362) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-18 12:07:58,774 - train: [ INFO] - Eval : 94 Time: 0.056 (0.204) Loss: 1.8421 (1.8596) Acc@1: 62.5000 (56.1275)Acc@5: 78.1250 (82.0466) +2025-04-18 12:08:00,090 - train: [ INFO] - Eval : 94 Time: 0.016 (0.143) Loss: 2.7685 (1.8853) Acc@1: 0.0000 (55.2043)Acc@5: 50.0000 (80.9175) +2025-04-18 12:08:06,863 - train: [ INFO] - Train: 95 [ 0/461 ( 0%)] Loss: 2.191771 (2.1918) Loss_single: 1.534822 (1.5348) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.071s, 7.86/s (4.071s, 7.86/s) LR: 5.000e-04 Data: 3.724 (3.724) +2025-04-18 12:08:14,119 - train: [ INFO] - Train: 95 [ 50/461 ( 11%)] Loss: 2.582604 (2.3872) Loss_single: 1.829123 (1.6820) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 96.8750 (98.4375) Time: 0.092s, 346.56/s (0.221s, 144.83/s) LR: 5.000e-04 Data: 0.000 (0.073) +2025-04-18 12:08:20,536 - train: [ INFO] - Train: 95 [ 100/461 ( 22%)] Loss: 2.291831 (2.3554) Loss_single: 1.632694 (1.6655) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (98.9583) Time: 0.100s, 321.15/s (0.175s, 183.01/s) LR: 5.000e-04 Data: 0.001 (0.037) +2025-04-18 12:08:26,214 - train: [ INFO] - Train: 95 [ 150/461 ( 33%)] Loss: 2.408813 (2.3688) Loss_single: 1.683792 (1.6701) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.4375) Acc@5: 100.0000 (99.2188) Time: 0.098s, 326.09/s (0.154s, 207.31/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-18 12:08:33,200 - train: [ INFO] - Train: 95 [ 200/461 ( 43%)] Loss: 2.425400 (2.3801) Loss_single: 1.710451 (1.6782) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.1250) Acc@5: 100.0000 (99.3750) Time: 0.082s, 388.40/s (0.151s, 212.54/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-18 12:08:40,495 - train: [ INFO] - Train: 95 [ 250/461 ( 54%)] Loss: 2.459918 (2.3934) Loss_single: 1.802533 (1.6989) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.4375) Acc@5: 100.0000 (99.4792) Time: 0.093s, 344.82/s (0.145s, 220.33/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-18 12:08:46,500 - train: [ INFO] - Train: 95 [ 300/461 ( 65%)] Loss: 2.479115 (2.4056) Loss_single: 1.821177 (1.7164) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.6607) Acc@5: 100.0000 (99.5536) Time: 0.113s, 282.58/s (0.139s, 229.55/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 12:08:52,266 - train: [ INFO] - Train: 95 [ 350/461 ( 76%)] Loss: 2.355835 (2.3994) Loss_single: 1.696988 (1.7139) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.8281) Acc@5: 100.0000 (99.6094) Time: 0.083s, 384.74/s (0.136s, 235.66/s) LR: 5.000e-04 Data: 0.001 (0.011) +2025-04-18 12:08:58,806 - train: [ INFO] - Train: 95 [ 400/461 ( 87%)] Loss: 2.582156 (2.4197) Loss_single: 1.917725 (1.7366) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (98.9583) Acc@5: 100.0000 (99.6528) Time: 0.211s, 151.32/s (0.135s, 236.98/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 12:09:05,612 - train: [ INFO] - Train: 95 [ 450/461 ( 98%)] Loss: 2.378849 (2.4156) Loss_single: 1.720922 (1.7350) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.0625) Acc@5: 100.0000 (99.6875) Time: 0.136s, 235.94/s (0.134s, 238.39/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 12:09:06,995 - train: [ INFO] - Train: 95 [ 460/461 (100%)] Loss: 2.569270 (2.4296) Loss_single: 1.833822 (1.7440) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.8636) Acc@5: 100.0000 (99.7159) Time: 0.103s, 309.68/s (0.134s, 239.46/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 12:09:10,754 - train: [ INFO] - Eval : 95 Time: 3.474 (3.474) Loss: 2.0566 (2.0566) Acc@1: 53.1250 (53.1250)Acc@5: 78.1250 (78.1250) +2025-04-18 12:09:13,790 - train: [ INFO] - Eval : 95 Time: 0.049 (0.128) Loss: 1.8449 (1.8645) Acc@1: 59.3750 (56.3725)Acc@5: 81.2500 (82.0466) +2025-04-18 12:09:14,996 - train: [ INFO] - Eval : 95 Time: 0.014 (0.094) Loss: 2.8727 (1.8894) Acc@1: 0.0000 (55.3971)Acc@5: 50.0000 (80.7247) +2025-04-18 12:09:21,873 - train: [ INFO] - Train: 96 [ 0/461 ( 0%)] Loss: 2.523894 (2.5239) Loss_single: 1.812797 (1.8128) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 4.077s, 7.85/s (4.077s, 7.85/s) LR: 5.000e-04 Data: 3.919 (3.919) +2025-04-18 12:09:29,095 - train: [ INFO] - Train: 96 [ 50/461 ( 11%)] Loss: 2.432706 (2.4783) Loss_single: 1.766107 (1.7895) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.093s, 344.41/s (0.220s, 145.13/s) LR: 5.000e-04 Data: 0.000 (0.078) +2025-04-18 12:09:35,276 - train: [ INFO] - Train: 96 [ 100/461 ( 22%)] Loss: 2.458125 (2.4716) Loss_single: 1.796636 (1.7918) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.090s, 354.90/s (0.172s, 185.74/s) LR: 5.000e-04 Data: 0.000 (0.040) +2025-04-18 12:09:41,925 - train: [ INFO] - Train: 96 [ 150/461 ( 33%)] Loss: 2.655720 (2.5176) Loss_single: 1.918605 (1.8235) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.2188) Acc@5: 96.8750 (99.2188) Time: 0.115s, 278.58/s (0.154s, 207.16/s) LR: 5.000e-04 Data: 0.000 (0.027) +2025-04-18 12:09:48,742 - train: [ INFO] - Train: 96 [ 200/461 ( 43%)] Loss: 2.337493 (2.4816) Loss_single: 1.679467 (1.7947) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.3750) Time: 0.223s, 143.20/s (0.150s, 213.63/s) LR: 5.000e-04 Data: 0.001 (0.020) +2025-04-18 12:09:55,347 - train: [ INFO] - Train: 96 [ 250/461 ( 54%)] Loss: 2.560809 (2.4948) Loss_single: 1.834518 (1.8014) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (98.9583) Acc@5: 100.0000 (99.4792) Time: 0.079s, 404.84/s (0.146s, 219.48/s) LR: 5.000e-04 Data: 0.000 (0.016) +2025-04-18 12:10:01,876 - train: [ INFO] - Train: 96 [ 300/461 ( 65%)] Loss: 2.480187 (2.4927) Loss_single: 1.792405 (1.8001) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.1071) Acc@5: 100.0000 (99.5536) Time: 0.145s, 220.28/s (0.142s, 225.86/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 12:10:07,753 - train: [ INFO] - Train: 96 [ 350/461 ( 76%)] Loss: 2.690739 (2.5175) Loss_single: 2.031295 (1.8290) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.2188) Acc@5: 100.0000 (99.6094) Time: 0.081s, 393.34/s (0.138s, 231.62/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 12:10:15,058 - train: [ INFO] - Train: 96 [ 400/461 ( 87%)] Loss: 2.170194 (2.4789) Loss_single: 1.512883 (1.7939) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3056) Acc@5: 100.0000 (99.6528) Time: 0.107s, 297.85/s (0.139s, 230.09/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:10:21,289 - train: [ INFO] - Train: 96 [ 450/461 ( 98%)] Loss: 2.351153 (2.4661) Loss_single: 1.695879 (1.7841) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.3750) Acc@5: 100.0000 (99.6875) Time: 0.077s, 416.70/s (0.137s, 234.16/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 12:10:22,520 - train: [ INFO] - Train: 96 [ 460/461 (100%)] Loss: 2.296530 (2.4507) Loss_single: 1.639954 (1.7710) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.4318) Acc@5: 100.0000 (99.7159) Time: 0.153s, 209.28/s (0.136s, 235.12/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 12:10:25,949 - train: [ INFO] - Eval : 96 Time: 3.158 (3.158) Loss: 2.0665 (2.0665) Acc@1: 43.7500 (43.7500)Acc@5: 78.1250 (78.1250) +2025-04-18 12:10:29,184 - train: [ INFO] - Eval : 96 Time: 0.026 (0.125) Loss: 1.8496 (1.8552) Acc@1: 59.3750 (56.4338)Acc@5: 75.0000 (81.9240) +2025-04-18 12:10:30,677 - train: [ INFO] - Eval : 96 Time: 0.014 (0.096) Loss: 2.8772 (1.8789) Acc@1: 50.0000 (55.4742)Acc@5: 50.0000 (80.8404) +2025-04-18 12:10:36,958 - train: [ INFO] - Train: 97 [ 0/461 ( 0%)] Loss: 2.362727 (2.3627) Loss_single: 1.704221 (1.7042) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 3.671s, 8.72/s (3.671s, 8.72/s) LR: 5.000e-04 Data: 3.486 (3.486) +2025-04-18 12:10:46,484 - train: [ INFO] - Train: 97 [ 50/461 ( 11%)] Loss: 2.406262 (2.3845) Loss_single: 1.724228 (1.7142) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.186s, 172.40/s (0.218s, 146.57/s) LR: 5.000e-04 Data: 0.001 (0.072) +2025-04-18 12:10:52,786 - train: [ INFO] - Train: 97 [ 100/461 ( 22%)] Loss: 2.196670 (2.3219) Loss_single: 1.536218 (1.6549) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.086s, 373.33/s (0.167s, 191.35/s) LR: 5.000e-04 Data: 0.000 (0.037) +2025-04-18 12:10:58,062 - train: [ INFO] - Train: 97 [ 150/461 ( 33%)] Loss: 2.458276 (2.3560) Loss_single: 1.790972 (1.6889) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.103s, 310.23/s (0.147s, 218.30/s) LR: 5.000e-04 Data: 0.001 (0.025) +2025-04-18 12:11:05,293 - train: [ INFO] - Train: 97 [ 200/461 ( 43%)] Loss: 2.315818 (2.3480) Loss_single: 1.656415 (1.6824) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.102s, 313.37/s (0.146s, 219.27/s) LR: 5.000e-04 Data: 0.000 (0.019) +2025-04-18 12:11:12,392 - train: [ INFO] - Train: 97 [ 250/461 ( 54%)] Loss: 2.297926 (2.3396) Loss_single: 1.628491 (1.6734) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 348.42/s (0.145s, 220.61/s) LR: 5.000e-04 Data: 0.000 (0.015) +2025-04-18 12:11:18,102 - train: [ INFO] - Train: 97 [ 300/461 ( 65%)] Loss: 2.311152 (2.3355) Loss_single: 1.650623 (1.6702) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 392.99/s (0.140s, 228.84/s) LR: 5.000e-04 Data: 0.000 (0.013) +2025-04-18 12:11:23,904 - train: [ INFO] - Train: 97 [ 350/461 ( 76%)] Loss: 2.277936 (2.3283) Loss_single: 1.617592 (1.6636) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.102s, 312.94/s (0.136s, 234.77/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:11:31,116 - train: [ INFO] - Train: 97 [ 400/461 ( 87%)] Loss: 2.336021 (2.3292) Loss_single: 1.679248 (1.6653) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 420.15/s (0.137s, 233.20/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 12:11:37,603 - train: [ INFO] - Train: 97 [ 450/461 ( 98%)] Loss: 2.291030 (2.3254) Loss_single: 1.631790 (1.6620) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.137s, 234.00/s (0.136s, 235.80/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 12:11:38,811 - train: [ INFO] - Train: 97 [ 460/461 (100%)] Loss: 2.293986 (2.3225) Loss_single: 1.636928 (1.6597) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.174s, 183.92/s (0.135s, 236.38/s) LR: 5.000e-04 Data: 0.000 (0.008) +2025-04-18 12:11:42,945 - train: [ INFO] - Eval : 97 Time: 3.851 (3.851) Loss: 2.0777 (2.0777) Acc@1: 46.8750 (46.8750)Acc@5: 78.1250 (78.1250) +2025-04-18 12:11:47,176 - train: [ INFO] - Eval : 97 Time: 0.084 (0.158) Loss: 1.8631 (1.8673) Acc@1: 59.3750 (56.6789)Acc@5: 78.1250 (81.8627) +2025-04-18 12:11:48,905 - train: [ INFO] - Eval : 97 Time: 0.018 (0.120) Loss: 2.7301 (1.8906) Acc@1: 50.0000 (55.3971)Acc@5: 50.0000 (80.8790) +2025-04-18 12:11:55,069 - train: [ INFO] - Train: 98 [ 0/461 ( 0%)] Loss: 2.483130 (2.4831) Loss_single: 1.799634 (1.7996) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 3.468s, 9.23/s (3.468s, 9.23/s) LR: 5.000e-04 Data: 3.301 (3.301) +2025-04-18 12:12:02,453 - train: [ INFO] - Train: 98 [ 50/461 ( 11%)] Loss: 2.470697 (2.4769) Loss_single: 1.811739 (1.8057) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 400.66/s (0.207s, 154.35/s) LR: 5.000e-04 Data: 0.000 (0.068) +2025-04-18 12:12:08,543 - train: [ INFO] - Train: 98 [ 100/461 ( 22%)] Loss: 2.354369 (2.4361) Loss_single: 1.696618 (1.7693) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.107s, 299.27/s (0.159s, 201.30/s) LR: 5.000e-04 Data: 0.000 (0.035) +2025-04-18 12:12:14,495 - train: [ INFO] - Train: 98 [ 150/461 ( 33%)] Loss: 2.308755 (2.4042) Loss_single: 1.649317 (1.7393) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.402s, 79.53/s (0.144s, 221.59/s) LR: 5.000e-04 Data: 0.002 (0.023) +2025-04-18 12:12:21,759 - train: [ INFO] - Train: 98 [ 200/461 ( 43%)] Loss: 2.458240 (2.4150) Loss_single: 1.786024 (1.7487) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.080s, 397.89/s (0.144s, 221.47/s) LR: 5.000e-04 Data: 0.001 (0.018) +2025-04-18 12:12:29,208 - train: [ INFO] - Train: 98 [ 250/461 ( 54%)] Loss: 2.166502 (2.3736) Loss_single: 1.511700 (1.7092) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.099s, 322.81/s (0.145s, 220.28/s) LR: 5.000e-04 Data: 0.001 (0.014) +2025-04-18 12:12:34,710 - train: [ INFO] - Train: 98 [ 300/461 ( 65%)] Loss: 2.359470 (2.3716) Loss_single: 1.701678 (1.7081) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.100s, 321.08/s (0.139s, 229.68/s) LR: 5.000e-04 Data: 0.000 (0.012) +2025-04-18 12:12:39,880 - train: [ INFO] - Train: 98 [ 350/461 ( 76%)] Loss: 2.240075 (2.3552) Loss_single: 1.581805 (1.6923) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.089s, 359.89/s (0.134s, 238.56/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 12:12:46,856 - train: [ INFO] - Train: 98 [ 400/461 ( 87%)] Loss: 2.487567 (2.3699) Loss_single: 1.797567 (1.7040) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.092s, 348.42/s (0.135s, 237.49/s) LR: 5.000e-04 Data: 0.000 (0.009) +2025-04-18 12:12:54,195 - train: [ INFO] - Train: 98 [ 450/461 ( 98%)] Loss: 2.260108 (2.3589) Loss_single: 1.597426 (1.6934) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.076s, 419.27/s (0.134s, 238.95/s) LR: 5.000e-04 Data: 0.000 (0.008) +2025-04-18 12:12:55,219 - train: [ INFO] - Train: 98 [ 460/461 (100%)] Loss: 2.618950 (2.3825) Loss_single: 1.947633 (1.7165) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.133s, 239.85/s (0.133s, 240.20/s) LR: 5.000e-04 Data: 0.000 (0.008) +2025-04-18 12:13:00,457 - train: [ INFO] - Eval : 98 Time: 5.009 (5.009) Loss: 2.0708 (2.0708) Acc@1: 50.0000 (50.0000)Acc@5: 78.1250 (78.1250) +2025-04-18 12:13:03,109 - train: [ INFO] - Eval : 98 Time: 0.059 (0.150) Loss: 1.8610 (1.8651) Acc@1: 59.3750 (56.5564)Acc@5: 81.2500 (81.8015) +2025-04-18 12:13:04,235 - train: [ INFO] - Eval : 98 Time: 0.014 (0.107) Loss: 2.9345 (1.8880) Acc@1: 0.0000 (55.4742)Acc@5: 50.0000 (80.8019) +2025-04-18 12:13:09,949 - train: [ INFO] - Train: 99 [ 0/461 ( 0%)] Loss: 2.283158 (2.2832) Loss_single: 1.626796 (1.6268) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 3.085s, 10.37/s (3.085s, 10.37/s) LR: 5.000e-04 Data: 2.937 (2.937) +2025-04-18 12:13:17,434 - train: [ INFO] - Train: 99 [ 50/461 ( 11%)] Loss: 2.404971 (2.3441) Loss_single: 1.747005 (1.6869) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.104s, 306.98/s (0.206s, 155.12/s) LR: 5.000e-04 Data: 0.000 (0.065) +2025-04-18 12:13:22,896 - train: [ INFO] - Train: 99 [ 100/461 ( 22%)] Loss: 2.251063 (2.3131) Loss_single: 1.592763 (1.6555) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.091s, 349.76/s (0.158s, 202.52/s) LR: 5.000e-04 Data: 0.000 (0.033) +2025-04-18 12:13:27,826 - train: [ INFO] - Train: 99 [ 150/461 ( 33%)] Loss: 2.437341 (2.3441) Loss_single: 1.767299 (1.6835) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.085s, 377.38/s (0.138s, 231.57/s) LR: 5.000e-04 Data: 0.000 (0.022) +2025-04-18 12:13:32,952 - train: [ INFO] - Train: 99 [ 200/461 ( 43%)] Loss: 2.513685 (2.3780) Loss_single: 1.837565 (1.7143) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (100.0000) Acc@5: 100.0000 (100.0000) Time: 0.081s, 396.84/s (0.129s, 248.07/s) LR: 5.000e-04 Data: 0.000 (0.017) +2025-04-18 12:13:38,098 - train: [ INFO] - Train: 99 [ 250/461 ( 54%)] Loss: 2.586888 (2.4129) Loss_single: 1.842111 (1.7356) Loss_inverse: 0.000000 (0.0000) Acc@1: 96.8750 (99.4792) Acc@5: 96.8750 (99.4792) Time: 0.083s, 384.56/s (0.124s, 258.91/s) LR: 5.000e-04 Data: 0.000 (0.014) +2025-04-18 12:13:43,315 - train: [ INFO] - Train: 99 [ 300/461 ( 65%)] Loss: 2.403600 (2.4115) Loss_single: 1.744586 (1.7369) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.5536) Acc@5: 100.0000 (99.5536) Time: 0.087s, 365.84/s (0.120s, 266.31/s) LR: 5.000e-04 Data: 0.000 (0.011) +2025-04-18 12:13:48,285 - train: [ INFO] - Train: 99 [ 350/461 ( 76%)] Loss: 2.426534 (2.4134) Loss_single: 1.768847 (1.7409) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6094) Acc@5: 100.0000 (99.6094) Time: 0.097s, 331.49/s (0.117s, 273.18/s) LR: 5.000e-04 Data: 0.000 (0.010) +2025-04-18 12:13:53,428 - train: [ INFO] - Train: 99 [ 400/461 ( 87%)] Loss: 2.225606 (2.3925) Loss_single: 1.570514 (1.7219) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6528) Acc@5: 100.0000 (99.6528) Time: 0.108s, 295.59/s (0.115s, 277.70/s) LR: 5.000e-04 Data: 0.001 (0.009) +2025-04-18 12:13:58,232 - train: [ INFO] - Train: 99 [ 450/461 ( 98%)] Loss: 2.450655 (2.3984) Loss_single: 1.786029 (1.7284) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.6875) Acc@5: 100.0000 (99.6875) Time: 0.079s, 403.90/s (0.113s, 283.05/s) LR: 5.000e-04 Data: 0.000 (0.008) +2025-04-18 12:13:59,049 - train: [ INFO] - Train: 99 [ 460/461 (100%)] Loss: 2.625385 (2.4190) Loss_single: 1.903249 (1.7443) Loss_inverse: 0.000000 (0.0000) Acc@1: 100.0000 (99.7159) Acc@5: 100.0000 (99.7159) Time: 0.079s, 404.26/s (0.112s, 284.79/s) LR: 5.000e-04 Data: 0.000 (0.008) +2025-04-18 12:14:03,159 - train: [ INFO] - Eval : 99 Time: 3.873 (3.873) Loss: 2.1146 (2.1146) Acc@1: 46.8750 (46.8750)Acc@5: 71.8750 (71.8750) +2025-04-18 12:14:06,052 - train: [ INFO] - Eval : 99 Time: 0.052 (0.133) Loss: 1.8463 (1.8665) Acc@1: 62.5000 (56.5564)Acc@5: 78.1250 (81.7402) +2025-04-18 12:14:07,156 - train: [ INFO] - Eval : 99 Time: 0.012 (0.096) Loss: 3.0631 (1.8918) Acc@1: 0.0000 (55.4742)Acc@5: 50.0000 (80.8019) +2025-04-18 12:14:09,879 - train: [ INFO] - *** Best metric: 56.168080185042406 (epoch 74) diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/model_best.pth.tar b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/model_best.pth.tar new file mode 100644 index 0000000000000000000000000000000000000000..99314478bb1e4b674b87fa035497fcb916a4c281 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/model_best.pth.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a283adbc9717a11534fbe7859f2d754208cfde3c345f5d190e77e300706897f7 +size 179501441 diff --git a/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/summary.csv b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/summary.csv new file mode 100644 index 0000000000000000000000000000000000000000..c0e979cd1bae8a15a4bb5209946f08db34cada76 --- /dev/null +++ b/Audio Visual Classification/exp_results/AVresnet18-KineticSound-audio-visual-Normal-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1/summary.csv @@ -0,0 +1,101 @@ +epoch,train_loss,train_loss_single,train_loss_inverse,eval_loss,eval_top1,eval_top1_a,eval_top1_v +0,8.864304672588002,6.08072449944236,0.0,2.4609338110377443,28.79722436391673,20.470316114109483,16.499614494988435 +1,7.950204502452504,5.571583401073109,0.0,2.5369057806069426,32.960678488820356,23.053199691595992,18.272937548188125 +2,7.465798247944225,5.2439094456759365,0.0,1.9737686717519414,43.562066306861986,29.02852737085582,23.708558211256747 +3,6.879950046539307,4.938333164561879,0.0,1.934290700631594,45.60524286815728,32.22821896684657,25.79028527370856 +4,6.857426296580922,4.895855253393,0.0,1.9962589374945177,43.677717810331536,36.77717810331534,25.096376252891286 +5,6.64566724950617,4.749696904962713,0.0,1.8239913012490607,47.879722436391674,36.969930609097915,26.522744795682343 +6,6.462749784643,4.6391071839766065,0.0,1.9780334705743958,46.491904394757135,35.92906707787201,28.95142636854279 +7,5.949556827545166,4.33861069245772,0.0,1.8036506596949804,48.88203546646106,34.811102544333075,33.0763299922899 +8,6.214459592645818,4.489969036795876,0.0,1.7482086602963203,51.079414032382424,37.50963762528913,32.035466461064 +9,5.713632020083341,4.203526193445379,0.0,2.1416370473463164,45.990747879722434,31.5343099460293,31.727062451811875 +10,5.700679822401567,4.24209003014998,0.0,1.8843012444313068,48.76638396299152,32.99922898997687,34.11719352351581 +11,5.345557733015581,3.97409573468295,0.0,1.8489470847680556,50.809560524286816,31.84271395528142,37.74094063222822 +12,4.599525473334572,3.502567182887684,0.0,2.222502092076157,44.79568234387047,31.84271395528142,32.845026985350806 +13,4.392306696284901,3.359241984107278,0.0,1.8432699939151314,51.85042405551272,33.26908249807248,38.7047031611411 +14,4.017167394811457,3.1027332219210537,0.0,1.9642711887933146,49.575944487278335,36.00616808018504,37.4325366229761 +15,3.8412289402701636,2.991567026485096,0.0,1.9268970074061715,48.84348496530455,36.46877409406322,36.00616808018504 +16,3.688096588308161,2.890348954634233,0.0,1.84404759013662,51.69622205088666,38.04934464148034,41.403238242097146 +17,3.567133079875599,2.809812545776367,0.0,1.8459300803697007,51.50346954510409,39.629915188897456,38.16499614494988 +18,3.63045672936873,2.8590270172465932,0.0,1.8357023385826587,52.00462606013878,40.169622205088665,42.21279876638396 +19,3.478744246742942,2.7622139670632104,0.0,1.9979014415049792,47.686969930609095,38.396299151888975,39.55281418658443 +20,3.435373826460405,2.704470157623291,0.0,1.9600261314703853,49.61449498843485,40.67077872012336,42.17424826522745 +21,3.3963942527770996,2.6749524636702104,0.0,1.8978821540117816,51.31071703932151,39.66846569005397,40.28527370855821 +22,3.4935771118510854,2.764287666840987,0.0,1.937524498106428,50.53970701619121,39.97686969930609,40.5165767154973 +23,3.3549781279130415,2.6343413266268643,0.0,1.9078881617408583,50.57825751734772,39.784117193523514,44.79568234387047 +24,3.4593291716142134,2.7532327391884546,0.0,1.9024209023992558,51.19506553585197,40.01542020046261,44.29452582883577 +25,3.350887493653731,2.6288786151192407,0.0,1.951225899142675,50.26985350809561,41.480339244410175,41.981495759444876 +26,3.334369811144742,2.6313998915932397,0.0,1.9888019819119938,49.15188897455667,38.35774865073246,46.1449498843485 +27,3.291086348620328,2.583132570440119,0.0,1.9502920466564946,50.46260601387818,40.01542020046261,46.18350038550501 +28,3.2810999263416636,2.5619078549471768,0.0,1.994886975152362,46.60755589822668,37.39398612181958,36.160370084811106 +29,3.3454058170318604,2.620034868066961,0.0,1.9683376987254335,48.84348496530455,39.51426368542791,44.75713184271395 +30,3.2298372008583764,2.512613144787875,0.0,1.9181220057199988,51.464919043947575,40.43947571318427,45.913646877409406 +31,3.3129579587416216,2.611720323562622,0.0,1.870143467955343,53.19969159599075,40.32382420971473,42.13569776407093 +32,3.2366027615287085,2.5308499986475166,0.0,1.9119959745208575,51.23361603700848,40.20817270624518,46.761757902852736 +33,3.2572227608073843,2.5311226628043433,0.0,1.9109867598887307,52.0431765612953,39.93831919814958,46.26060138781804 +34,3.10352180220864,2.40699104829268,0.0,1.9203283924641017,52.120277563608326,39.66846569005397,47.031611410948344 +35,3.2090905146165327,2.5057059851559726,0.0,1.9533046666897529,51.77332305319969,41.017733230531995,40.555127216653815 +36,3.2580124248157847,2.546559767289595,0.0,1.9498492386493669,50.19275250578257,39.82266769468003,46.68465690053971 +37,3.1492070934989234,2.4481518268585205,0.0,1.9257320449640867,51.77332305319969,40.32382420971473,46.60755589822668 +38,3.1474460688504307,2.4407600706273858,0.0,1.945646116525831,51.58057054741712,40.82498072474942,43.79336931380108 +39,3.0527275042100386,2.3544228727167305,0.0,1.9284831297425187,51.811873554356204,39.707016191210485,46.18350038550501 +40,3.1385399861769243,2.4237148978493432,0.0,1.9083975874283907,52.08172706245181,40.43947571318427,48.49653045489591 +41,3.1563447388735684,2.4285459301688452,0.0,1.9166246578154789,51.15651503469545,39.59136468774094,46.68465690053971 +42,3.139063683423129,2.419008320028132,0.0,1.931701413833277,51.85042405551272,40.169622205088665,46.26060138781804 +43,3.073895064267245,2.3654291196302935,0.0,1.9050379573333787,51.85042405551272,39.321511179645334,46.18350038550501 +44,3.0890694098039106,2.393331462686712,0.0,1.9250956267325254,51.85042405551272,38.858905165767155,47.031611410948344 +45,3.0218137827786533,2.32620247927579,0.0,1.9026443897620844,52.775636083269085,39.43716268311488,48.342328450269854 +46,2.9242090528661553,2.222837903282859,0.0,1.9298404046178508,50.7710100231303,38.35774865073246,47.49421742482652 +47,3.0270766778425737,2.321492065082897,0.0,1.9029926213284318,51.811873554356204,38.66615265998458,49.73014649190439 +48,3.1161446137861772,2.392368294975974,0.0,1.909401678175033,53.238242097147264,40.59367771781033,48.22667694680031 +49,2.94148512320085,2.242118250239979,0.0,1.8753940750289717,52.23592906707787,39.93831919814958,50.7710100231303 +50,3.080849300731312,2.3651200207796963,0.0,1.9229632420271474,51.657671549730146,39.39861218195836,48.727833461835004 +51,2.925799109719016,2.2314494956623423,0.0,1.957751393593911,50.57825751734772,39.321511179645334,48.03392444101773 +52,2.934916778044267,2.2428288893266157,0.0,1.906772012239984,52.15882806476484,39.16730917501928,48.57363145720895 +53,2.8512535962191494,2.1539934765208852,0.0,1.886652306032438,52.582883577486506,40.47802621434079,48.03392444101773 +54,2.957517060366544,2.261018688028509,0.0,1.903125951358145,52.968388589051656,40.59367771781033,48.072474942174246 +55,2.9226718599146064,2.213052207773382,0.0,1.8549808779402521,54.43330763299923,39.93831919814958,51.61912104857363 +56,2.8513040976090864,2.155928308313543,0.0,1.8836915241173808,52.968388589051656,39.82266769468003,50.07710100231303 +57,2.8467988751151343,2.1464450359344482,0.0,1.8788552984606788,53.430994602929836,39.16730917501928,50.61680801850424 +58,2.8491393436085093,2.1661354953592475,0.0,1.9000250405316732,51.734772552043175,38.62760215882806,48.84348496530455 +59,2.8890515890988437,2.1955313465811988,0.0,1.885846688366892,53.00693909020817,39.86121819583654,52.50578257517348 +60,2.8658947294408623,2.1779997565529565,0.0,1.8707261260142212,53.73939861218196,39.86121819583654,49.26754047802621 +61,2.849040313200517,2.1465529636903242,0.0,1.9295746870195305,52.120277563608326,40.28527370855821,49.46029298380879 +62,2.8189338554035532,2.1276246200908315,0.0,1.906982354044271,53.0840400925212,40.47802621434079,52.659984579799534 +63,2.909959749741988,2.206061428243464,0.0,1.8958956412195516,53.77794911333847,40.555127216653815,50.19275250578257 +64,2.872427073392001,2.1745346134359185,0.0,1.907307339155775,51.58057054741712,40.092521202775636,51.657671549730146 +65,2.8842995817011055,2.191982475194064,0.0,1.885983072985294,52.62143407864302,40.20817270624518,49.498843484965306 +66,2.8263662078163843,2.1425382007252085,0.0,1.9078462031959293,51.58057054741712,39.707016191210485,49.07478797224364 +67,2.831496065313166,2.1193384365601973,0.0,1.9043025220460679,52.35158057054742,39.51426368542791,49.498843484965306 +68,2.8422492850910532,2.1539700356396763,0.0,1.9129531686822543,52.00462606013878,38.396299151888975,51.96607555898227 +69,2.7777761112559927,2.094324762170965,0.0,1.914720185279111,52.27447956823439,38.58905165767155,49.80724749421743 +70,2.643687508322976,1.95837524804202,0.0,1.8350490071540073,55.97532767925983,40.5165767154973,57.093292212798765 +71,2.536225535652854,1.8452885367653586,0.0,1.8322941990383974,56.09097918272938,41.017733230531995,57.05474171164225 +72,2.5369892553849653,1.8501596667549827,0.0,1.8352445920063334,55.70547417116423,40.70932922127988,58.48111025443331 +73,2.5544137087735264,1.859866825017062,0.0,1.8371086400016603,56.12952968388589,40.82498072474942,57.4402467232074 +74,2.443770408630371,1.7645706155083396,0.0,1.8418604382755395,56.168080185042406,40.632228218966844,57.170393215111794 +75,2.504184137691151,1.8221033594825051,0.0,1.8495566074721337,55.70547417116423,40.5165767154973,56.97764070932922 +76,2.4907146367159756,1.805579965764826,0.0,1.8432391805656156,55.74402467232074,40.67077872012336,57.51734772552043 +77,2.463254841891202,1.792728770862926,0.0,1.8504272639613566,55.35851966075559,40.82498072474942,57.24749421742483 +78,2.5283753221685235,1.855991471897472,0.0,1.8559216546754977,55.66692367000771,41.017733230531995,56.322282189668464 +79,2.43806977705522,1.7679215994748203,0.0,1.8561896619745282,55.66692367000771,40.70932922127988,55.93677717810331 +80,2.4995392886075107,1.8273977583104914,0.0,1.8482537063710398,55.97532767925983,40.940632228218966,57.24749421742483 +81,2.447273861278187,1.7757724848660557,0.0,1.865626056468202,55.397070161912104,40.32382420971473,56.322282189668464 +82,2.5413402210582388,1.8561630790883845,0.0,1.8671063946684967,55.58982266769468,40.59367771781033,57.170393215111794 +83,2.4394211769104004,1.7662001631476663,0.0,1.8754245503277804,55.24286815728605,40.20817270624518,56.36083269082498 +84,2.440536694093184,1.7737461978738958,0.0,1.8709225954233726,55.20431765612953,40.28527370855821,56.86198920585968 +85,2.419894131747159,1.7468709837306629,0.0,1.86890560236911,55.05011565150347,40.59367771781033,57.170393215111794 +86,2.457799803126942,1.777259263125333,0.0,1.8767318196175369,55.16576715497302,40.32382420971473,57.01619121048574 +87,2.4696818481792104,1.7921430414373225,0.0,1.8706875987115417,55.51272166538165,40.555127216653815,56.437933693138014 +88,2.4394044442610308,1.757690668106079,0.0,1.878381196958061,55.24286815728605,40.32382420971473,56.90053970701619 +89,2.4448861208829014,1.7584844827651978,0.0,1.8813223504248084,55.28141865844256,40.05397070161912,56.47648419429453 +90,2.463672464544123,1.7734671939503064,0.0,1.8762813513335945,55.782575173477255,40.24672320740169,56.55358519660756 +91,2.431365034796975,1.762659495527094,0.0,1.884416566597285,55.24286815728605,40.092521202775636,56.59213569776407 +92,2.405337181958285,1.7371771769090132,0.0,1.8751984506546762,55.319969159599076,40.28527370855821,56.36083269082498 +93,2.5075244253331963,1.8076894608410923,0.0,1.8877609048150739,55.319969159599076,40.28527370855821,55.782575173477255 +94,2.398684783415361,1.7342462756417014,0.0,1.8853463648646818,55.20431765612953,40.05397070161912,57.093292212798765 +95,2.429596424102783,1.7440044446425005,0.0,1.8894190295623097,55.397070161912104,39.86121819583654,56.86198920585968 +96,2.4506863897497,1.7709588029167869,0.0,1.8789105163506572,55.47417116422513,40.32382420971473,56.168080185042406 +97,2.3225276036696,1.6597023660486394,0.0,1.8905925945584923,55.397070161912104,40.32382420971473,56.36083269082498 +98,2.3825330300764604,1.716467402198098,0.0,1.8879966691722296,55.47417116422513,40.43947571318427,56.36083269082498 +99,2.418989723378962,1.7442512620579114,0.0,1.8918366263072677,55.47417116422513,40.092521202775636,55.8982266769468 diff --git a/Audio Visual Classification/exp_results/readme.md b/Audio Visual Classification/exp_results/readme.md new file mode 100644 index 0000000000000000000000000000000000000000..e35bb493c2c080e414f695e24d09b4f0a33fdc63 --- /dev/null +++ b/Audio Visual Classification/exp_results/readme.md @@ -0,0 +1,45 @@ +Due to the upload speed limitation, we only upload the results of Normal (Concat method) on the Kinetics-Sound dataset here, and the rest of the results in the paper are uploaded to baidu netdisk. Its decompression structure is as follows： + +``` +├── AVresnet18-CREMAD-audio-visual-OGM_GE-inverse_False-psai_1.0-fusion_concat-seed_2025-LIFNode-4 +│   ├── args.yaml +│   ├── checkpoint-56.pth.tar +│   ├── events.out.tfevents.1745036026.af1fd63cd999.968888.0 +│   ├── last.pth.tar +│   ├── log.txt +│   ├── model_best.pth.tar +│   └── summary.csv +├── AVresnet18-CREMAD-audio-visual-OGM_GE-inverse_False-psai_1.0-fusion_concat-seed_2025-ReLUNode-1 +│   ├── args.yaml +│   ├── checkpoint-56.pth.tar +│   ├── events.out.tfevents.1744958014.af1fd63cd999.329244.0 +│   ├── last.pth.tar +│   ├── log.txt +│   ├── model_best.pth.tar +│   └── summary.csv +├── AVresnet18-CREMAD-audio-visual-OGM_GE-inverse_True-psai_1.0-fusion_concat-seed_2025-LIFNode-4 +│   ├── args.yaml +│   ├── checkpoint-56.pth.tar +│   ├── events.out.tfevents.1745036026.af1fd63cd999.968889.0 +│   ├── last.pth.tar +│   ├── log.txt +│   ├── model_best.pth.tar +│   └── summary.csv +├── AVresnet18-CREMAD-audio-visual-OGM_GE-inverse_True-psai_1.0-fusion_concat-seed_2025-ReLUNode-1 +│   ├── args.yaml +│   ├── checkpoint-55.pth.tar +│   ├── events.out.tfevents.1744958014.af1fd63cd999.329245.0 +│   ├── last.pth.tar +│   ├── log.txt +│   ├── model_best.pth.tar +│   └── summary.csv +... + + +``` + +There are a total of 62 directories in it. + + + +You can find all our experimental results [here](https://pan.baidu.com/s/1myFj4XVNIgdZIFXsN0pL1A) ( extraction code: q372 ) \ No newline at end of file diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..1c7c338e8ccf803c5b2b7f18f0ce1e1229d4867d Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..ab571cd26a8c01108e2a35f80eba1268c9d35e45 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..d10f4746672c4e3a642d0ada22abc80af99f4507 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..25376f91c4c901c05996c2079e9b613a6556e298 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..a76b5aef2d4607690c3f6c83cf436cb302eff8c1 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..e6eb4cc5c6bb90e3ad4c8b99542a62f60da8174d Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..ac5dfa15ee634863d19e0ed5baf238b74e6f1b87 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..fd2958dcedbd3145d2063bf50f5bcd2d1c43e43c Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8704922e30b1ef4da5a562c4fe1a5690130b0463 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9114a8babaf4afb1c2c1b67243be750a277e44570f8a6b9937420654d882123 +size 114115345 diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..03201babda9bdf8b71843dea3d017ea2f679aa94 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c29e36d7dc7d1b0283d7baf227744cdc78537fb27b199102c65476ea17275a5 +size 114179921 diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b95a74b399846425a491141c13c66d230ab9ea0c --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd31bbb96a44249bc14f4ed96e6b58f79949fa76393248030d720768edda071 +size 114244625 diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9ec0aa0c1fad65e58927e957b1a925fa7d3f8169 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a1a910e37c69bc613655b86b2d20d249d7a86e50677c17fc22f80b6431f04bb +size 114309137 diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/train.log b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..3665a920bf3467371d88cf4b67c28043d118bfc0 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_False-seed_0/train.log @@ -0,0 +1,885 @@ +2025-04-19 03:46:47,992 INFO Training start time: 2025-04-19 03:46:47.992610 +2025-04-19 04:06:48,306 INFO Incremental step: 0 +2025-04-19 04:07:08,530 INFO Epoch:0 train_loss:2.26734 +2025-04-19 04:07:13,724 INFO Epoch:0 val_res:0.257143 +2025-04-19 04:07:13,724 INFO Saving best model at Epoch 0 +2025-04-19 04:07:28,405 INFO Epoch:1 train_loss:1.55042 +2025-04-19 04:07:33,779 INFO Epoch:1 val_res:0.466667 +2025-04-19 04:07:33,779 INFO Saving best model at Epoch 1 +2025-04-19 04:07:47,208 INFO Epoch:2 train_loss:1.27226 +2025-04-19 04:07:52,431 INFO Epoch:2 val_res:0.628571 +2025-04-19 04:07:52,431 INFO Saving best model at Epoch 2 +2025-04-19 04:08:05,561 INFO Epoch:3 train_loss:1.00044 +2025-04-19 04:08:10,667 INFO Epoch:3 val_res:0.552381 +2025-04-19 04:08:20,574 INFO Epoch:4 train_loss:0.93713 +2025-04-19 04:08:26,069 INFO Epoch:4 val_res:0.742857 +2025-04-19 04:08:26,070 INFO Saving best model at Epoch 4 +2025-04-19 04:08:40,943 INFO Epoch:5 train_loss:0.77391 +2025-04-19 04:08:45,824 INFO Epoch:5 val_res:0.685714 +2025-04-19 04:08:55,774 INFO Epoch:6 train_loss:0.73917 +2025-04-19 04:09:00,828 INFO Epoch:6 val_res:0.723810 +2025-04-19 04:09:11,159 INFO Epoch:7 train_loss:0.65520 +2025-04-19 04:09:16,636 INFO Epoch:7 val_res:0.761905 +2025-04-19 04:09:16,636 INFO Saving best model at Epoch 7 +2025-04-19 04:09:29,546 INFO Epoch:8 train_loss:0.61123 +2025-04-19 04:09:35,331 INFO Epoch:8 val_res:0.742857 +2025-04-19 04:09:46,027 INFO Epoch:9 train_loss:0.59487 +2025-04-19 04:09:51,676 INFO Epoch:9 val_res:0.790476 +2025-04-19 04:09:51,676 INFO Saving best model at Epoch 9 +2025-04-19 04:10:05,613 INFO Epoch:10 train_loss:0.52868 +2025-04-19 04:10:11,031 INFO Epoch:10 val_res:0.771429 +2025-04-19 04:10:21,310 INFO Epoch:11 train_loss:0.48344 +2025-04-19 04:10:26,767 INFO Epoch:11 val_res:0.800000 +2025-04-19 04:10:26,767 INFO Saving best model at Epoch 11 +2025-04-19 04:10:40,613 INFO Epoch:12 train_loss:0.46746 +2025-04-19 04:10:45,904 INFO Epoch:12 val_res:0.800000 +2025-04-19 04:10:56,594 INFO Epoch:13 train_loss:0.43783 +2025-04-19 04:11:01,844 INFO Epoch:13 val_res:0.790476 +2025-04-19 04:11:12,707 INFO Epoch:14 train_loss:0.39908 +2025-04-19 04:11:17,978 INFO Epoch:14 val_res:0.800000 +2025-04-19 04:11:28,705 INFO Epoch:15 train_loss:0.37672 +2025-04-19 04:11:34,134 INFO Epoch:15 val_res:0.819048 +2025-04-19 04:11:34,134 INFO Saving best model at Epoch 15 +2025-04-19 04:11:47,257 INFO Epoch:16 train_loss:0.35163 +2025-04-19 04:11:52,283 INFO Epoch:16 val_res:0.828571 +2025-04-19 04:11:52,283 INFO Saving best model at Epoch 16 +2025-04-19 04:12:05,078 INFO Epoch:17 train_loss:0.33205 +2025-04-19 04:12:10,132 INFO Epoch:17 val_res:0.819048 +2025-04-19 04:12:20,482 INFO Epoch:18 train_loss:0.30715 +2025-04-19 04:12:25,760 INFO Epoch:18 val_res:0.828571 +2025-04-19 04:12:36,410 INFO Epoch:19 train_loss:0.29065 +2025-04-19 04:12:41,355 INFO Epoch:19 val_res:0.809524 +2025-04-19 04:12:51,712 INFO Epoch:20 train_loss:0.27594 +2025-04-19 04:12:57,011 INFO Epoch:20 val_res:0.800000 +2025-04-19 04:13:08,078 INFO Epoch:21 train_loss:0.26882 +2025-04-19 04:13:13,505 INFO Epoch:21 val_res:0.828571 +2025-04-19 04:13:23,719 INFO Epoch:22 train_loss:0.23536 +2025-04-19 04:13:28,826 INFO Epoch:22 val_res:0.800000 +2025-04-19 04:13:39,214 INFO Epoch:23 train_loss:0.22374 +2025-04-19 04:13:44,226 INFO Epoch:23 val_res:0.828571 +2025-04-19 04:13:54,686 INFO Epoch:24 train_loss:0.21201 +2025-04-19 04:14:00,938 INFO Epoch:24 val_res:0.809524 +2025-04-19 04:14:11,923 INFO Epoch:25 train_loss:0.20243 +2025-04-19 04:14:17,557 INFO Epoch:25 val_res:0.828571 +2025-04-19 04:14:28,816 INFO Epoch:26 train_loss:0.17748 +2025-04-19 04:14:34,260 INFO Epoch:26 val_res:0.819048 +2025-04-19 04:14:44,947 INFO Epoch:27 train_loss:0.17828 +2025-04-19 04:14:50,159 INFO Epoch:27 val_res:0.838095 +2025-04-19 04:14:50,159 INFO Saving best model at Epoch 27 +2025-04-19 04:15:03,264 INFO Epoch:28 train_loss:0.15906 +2025-04-19 04:15:08,513 INFO Epoch:28 val_res:0.838095 +2025-04-19 04:15:21,592 INFO Epoch:29 train_loss:0.15265 +2025-04-19 04:15:27,054 INFO Epoch:29 val_res:0.838095 +2025-04-19 04:15:38,317 INFO Epoch:30 train_loss:0.14531 +2025-04-19 04:15:43,782 INFO Epoch:30 val_res:0.819048 +2025-04-19 04:15:54,807 INFO Epoch:31 train_loss:0.12771 +2025-04-19 04:16:00,007 INFO Epoch:31 val_res:0.828571 +2025-04-19 04:16:11,550 INFO Epoch:32 train_loss:0.12039 +2025-04-19 04:16:17,028 INFO Epoch:32 val_res:0.828571 +2025-04-19 04:16:27,979 INFO Epoch:33 train_loss:0.10778 +2025-04-19 04:16:33,437 INFO Epoch:33 val_res:0.828571 +2025-04-19 04:16:44,655 INFO Epoch:34 train_loss:0.10372 +2025-04-19 04:16:50,128 INFO Epoch:34 val_res:0.838095 +2025-04-19 04:17:01,494 INFO Epoch:35 train_loss:0.09483 +2025-04-19 04:17:06,788 INFO Epoch:35 val_res:0.828571 +2025-04-19 04:17:18,230 INFO Epoch:36 train_loss:0.09487 +2025-04-19 04:17:23,691 INFO Epoch:36 val_res:0.828571 +2025-04-19 04:17:35,288 INFO Epoch:37 train_loss:0.09211 +2025-04-19 04:17:40,417 INFO Epoch:37 val_res:0.828571 +2025-04-19 04:17:51,908 INFO Epoch:38 train_loss:0.07836 +2025-04-19 04:17:57,044 INFO Epoch:38 val_res:0.838095 +2025-04-19 04:18:07,918 INFO Epoch:39 train_loss:0.06967 +2025-04-19 04:18:13,246 INFO Epoch:39 val_res:0.819048 +2025-04-19 04:18:24,780 INFO Epoch:40 train_loss:0.06636 +2025-04-19 04:18:30,638 INFO Epoch:40 val_res:0.819048 +2025-04-19 04:18:41,916 INFO Epoch:41 train_loss:0.06588 +2025-04-19 04:18:47,293 INFO Epoch:41 val_res:0.828571 +2025-04-19 04:18:58,318 INFO Epoch:42 train_loss:0.05647 +2025-04-19 04:19:03,745 INFO Epoch:42 val_res:0.819048 +2025-04-19 04:19:15,597 INFO Epoch:43 train_loss:0.05239 +2025-04-19 04:19:20,853 INFO Epoch:43 val_res:0.828571 +2025-04-19 04:19:32,594 INFO Epoch:44 train_loss:0.04980 +2025-04-19 04:19:37,909 INFO Epoch:44 val_res:0.828571 +2025-04-19 04:19:49,004 INFO Epoch:45 train_loss:0.04698 +2025-04-19 04:19:54,178 INFO Epoch:45 val_res:0.819048 +2025-04-19 04:20:05,007 INFO Epoch:46 train_loss:0.04317 +2025-04-19 04:20:10,096 INFO Epoch:46 val_res:0.828571 +2025-04-19 04:20:21,179 INFO Epoch:47 train_loss:0.04270 +2025-04-19 04:20:26,433 INFO Epoch:47 val_res:0.828571 +2025-04-19 04:20:36,879 INFO Epoch:48 train_loss:0.03995 +2025-04-19 04:20:41,984 INFO Epoch:48 val_res:0.828571 +2025-04-19 04:20:52,896 INFO Epoch:49 train_loss:0.03744 +2025-04-19 04:20:57,942 INFO Epoch:49 val_res:0.828571 +2025-04-19 04:21:08,409 INFO Epoch:50 train_loss:0.03656 +2025-04-19 04:21:13,340 INFO Epoch:50 val_res:0.828571 +2025-04-19 04:21:24,112 INFO Epoch:51 train_loss:0.03274 +2025-04-19 04:21:29,394 INFO Epoch:51 val_res:0.819048 +2025-04-19 04:21:40,494 INFO Epoch:52 train_loss:0.02987 +2025-04-19 04:21:46,047 INFO Epoch:52 val_res:0.809524 +2025-04-19 04:21:57,747 INFO Epoch:53 train_loss:0.03041 +2025-04-19 04:22:03,187 INFO Epoch:53 val_res:0.819048 +2025-04-19 04:22:13,893 INFO Epoch:54 train_loss:0.02775 +2025-04-19 04:22:19,245 INFO Epoch:54 val_res:0.819048 +2025-04-19 04:22:30,004 INFO Epoch:55 train_loss:0.02792 +2025-04-19 04:22:35,117 INFO Epoch:55 val_res:0.819048 +2025-04-19 04:22:46,301 INFO Epoch:56 train_loss:0.02554 +2025-04-19 04:22:51,684 INFO Epoch:56 val_res:0.828571 +2025-04-19 04:23:03,137 INFO Epoch:57 train_loss:0.02422 +2025-04-19 04:23:08,363 INFO Epoch:57 val_res:0.809524 +2025-04-19 04:23:20,597 INFO Epoch:58 train_loss:0.02448 +2025-04-19 04:23:25,970 INFO Epoch:58 val_res:0.809524 +2025-04-19 04:23:37,592 INFO Epoch:59 train_loss:0.02383 +2025-04-19 04:23:42,653 INFO Epoch:59 val_res:0.819048 +2025-04-19 04:23:53,823 INFO Epoch:60 train_loss:0.02276 +2025-04-19 04:23:58,941 INFO Epoch:60 val_res:0.828571 +2025-04-19 04:24:10,052 INFO Epoch:61 train_loss:0.02232 +2025-04-19 04:24:15,066 INFO Epoch:61 val_res:0.828571 +2025-04-19 04:24:25,649 INFO Epoch:62 train_loss:0.02243 +2025-04-19 04:24:30,632 INFO Epoch:62 val_res:0.819048 +2025-04-19 04:24:41,632 INFO Epoch:63 train_loss:0.02103 +2025-04-19 04:24:46,663 INFO Epoch:63 val_res:0.828571 +2025-04-19 04:24:57,444 INFO Epoch:64 train_loss:0.02037 +2025-04-19 04:25:02,501 INFO Epoch:64 val_res:0.819048 +2025-04-19 04:25:13,255 INFO Epoch:65 train_loss:0.02047 +2025-04-19 04:25:18,271 INFO Epoch:65 val_res:0.819048 +2025-04-19 04:25:31,635 INFO Epoch:66 train_loss:0.01881 +2025-04-19 04:25:36,977 INFO Epoch:66 val_res:0.819048 +2025-04-19 04:25:47,631 INFO Epoch:67 train_loss:0.01795 +2025-04-19 04:25:52,557 INFO Epoch:67 val_res:0.819048 +2025-04-19 04:26:03,465 INFO Epoch:68 train_loss:0.01733 +2025-04-19 04:26:08,413 INFO Epoch:68 val_res:0.809524 +2025-04-19 04:26:20,026 INFO Epoch:69 train_loss:0.01720 +2025-04-19 04:26:25,748 INFO Epoch:69 val_res:0.819048 +2025-04-19 04:26:37,248 INFO Epoch:70 train_loss:0.01672 +2025-04-19 04:26:42,801 INFO Epoch:70 val_res:0.819048 +2025-04-19 04:26:54,448 INFO Epoch:71 train_loss:0.01631 +2025-04-19 04:26:59,830 INFO Epoch:71 val_res:0.809524 +2025-04-19 04:27:10,908 INFO Epoch:72 train_loss:0.01544 +2025-04-19 04:27:15,940 INFO Epoch:72 val_res:0.809524 +2025-04-19 04:27:26,785 INFO Epoch:73 train_loss:0.01552 +2025-04-19 04:27:31,725 INFO Epoch:73 val_res:0.819048 +2025-04-19 04:27:42,621 INFO Epoch:74 train_loss:0.01578 +2025-04-19 04:27:47,627 INFO Epoch:74 val_res:0.819048 +2025-04-19 04:27:58,371 INFO Epoch:75 train_loss:0.01469 +2025-04-19 04:28:03,839 INFO Epoch:75 val_res:0.809524 +2025-04-19 04:28:15,439 INFO Epoch:76 train_loss:0.01454 +2025-04-19 04:28:20,682 INFO Epoch:76 val_res:0.809524 +2025-04-19 04:28:32,873 INFO Epoch:77 train_loss:0.01468 +2025-04-19 04:28:38,716 INFO Epoch:77 val_res:0.809524 +2025-04-19 04:28:50,666 INFO Epoch:78 train_loss:0.01445 +2025-04-19 04:28:55,784 INFO Epoch:78 val_res:0.819048 +2025-04-19 04:29:06,783 INFO Epoch:79 train_loss:0.01457 +2025-04-19 04:29:11,637 INFO Epoch:79 val_res:0.819048 +2025-04-19 04:29:23,069 INFO Epoch:80 train_loss:0.01342 +2025-04-19 04:29:28,186 INFO Epoch:80 val_res:0.819048 +2025-04-19 04:29:39,226 INFO Epoch:81 train_loss:0.01392 +2025-04-19 04:29:44,840 INFO Epoch:81 val_res:0.819048 +2025-04-19 04:29:56,590 INFO Epoch:82 train_loss:0.01361 +2025-04-19 04:30:01,663 INFO Epoch:82 val_res:0.819048 +2025-04-19 04:30:14,720 INFO Epoch:83 train_loss:0.01345 +2025-04-19 04:30:21,042 INFO Epoch:83 val_res:0.819048 +2025-04-19 04:30:32,340 INFO Epoch:84 train_loss:0.01321 +2025-04-19 04:30:37,387 INFO Epoch:84 val_res:0.809524 +2025-04-19 04:30:48,391 INFO Epoch:85 train_loss:0.01316 +2025-04-19 04:30:53,961 INFO Epoch:85 val_res:0.819048 +2025-04-19 04:31:06,125 INFO Epoch:86 train_loss:0.01257 +2025-04-19 04:31:12,059 INFO Epoch:86 val_res:0.819048 +2025-04-19 04:31:25,191 INFO Epoch:87 train_loss:0.01234 +2025-04-19 04:31:30,665 INFO Epoch:87 val_res:0.819048 +2025-04-19 04:31:41,904 INFO Epoch:88 train_loss:0.01236 +2025-04-19 04:31:49,031 INFO Epoch:88 val_res:0.809524 +2025-04-19 04:32:00,985 INFO Epoch:89 train_loss:0.01229 +2025-04-19 04:32:06,592 INFO Epoch:89 val_res:0.809524 +2025-04-19 04:32:20,335 INFO Epoch:90 train_loss:0.01214 +2025-04-19 04:32:25,597 INFO Epoch:90 val_res:0.809524 +2025-04-19 04:32:36,888 INFO Epoch:91 train_loss:0.01165 +2025-04-19 04:32:42,294 INFO Epoch:91 val_res:0.809524 +2025-04-19 04:32:57,072 INFO Epoch:92 train_loss:0.01149 +2025-04-19 04:33:02,740 INFO Epoch:92 val_res:0.809524 +2025-04-19 04:33:15,993 INFO Epoch:93 train_loss:0.01121 +2025-04-19 04:33:21,325 INFO Epoch:93 val_res:0.809524 +2025-04-19 04:33:34,305 INFO Epoch:94 train_loss:0.01164 +2025-04-19 04:33:40,145 INFO Epoch:94 val_res:0.819048 +2025-04-19 04:33:54,227 INFO Epoch:95 train_loss:0.01101 +2025-04-19 04:34:00,106 INFO Epoch:95 val_res:0.809524 +2025-04-19 04:34:11,688 INFO Epoch:96 train_loss:0.01099 +2025-04-19 04:34:17,683 INFO Epoch:96 val_res:0.809524 +2025-04-19 04:34:32,261 INFO Epoch:97 train_loss:0.01085 +2025-04-19 04:34:38,236 INFO Epoch:97 val_res:0.809524 +2025-04-19 04:34:51,108 INFO Epoch:98 train_loss:0.01092 +2025-04-19 04:34:56,412 INFO Epoch:98 val_res:0.809524 +2025-04-19 04:35:07,600 INFO Epoch:99 train_loss:0.01068 +2025-04-19 04:35:13,438 INFO Epoch:99 val_res:0.809524 +2025-04-19 04:35:13,967 INFO ===================================== +2025-04-19 04:35:13,968 INFO Start testing... +2025-04-19 04:35:13,968 INFO ===================================== +2025-04-19 04:35:23,848 INFO Incremental step 0 Testing res: 0.778846 +2025-04-19 04:35:23,850 INFO Incremental step: 1 +2025-04-19 04:35:53,902 INFO Epoch:0 train_loss:2.87659 +2025-04-19 04:36:00,605 INFO Epoch:0 val_res:0.399061 +2025-04-19 04:36:00,605 INFO Saving best model at Epoch 0 +2025-04-19 04:36:26,503 INFO Epoch:1 train_loss:2.49178 +2025-04-19 04:36:32,993 INFO Epoch:1 val_res:0.483568 +2025-04-19 04:36:32,994 INFO Saving best model at Epoch 1 +2025-04-19 04:36:58,149 INFO Epoch:2 train_loss:2.08639 +2025-04-19 04:37:04,528 INFO Epoch:2 val_res:0.488263 +2025-04-19 04:37:04,528 INFO Saving best model at Epoch 2 +2025-04-19 04:37:28,234 INFO Epoch:3 train_loss:1.91849 +2025-04-19 04:37:34,577 INFO Epoch:3 val_res:0.507042 +2025-04-19 04:37:34,577 INFO Saving best model at Epoch 3 +2025-04-19 04:38:00,495 INFO Epoch:4 train_loss:1.74276 +2025-04-19 04:38:06,583 INFO Epoch:4 val_res:0.568075 +2025-04-19 04:38:06,583 INFO Saving best model at Epoch 4 +2025-04-19 04:38:30,997 INFO Epoch:5 train_loss:1.69453 +2025-04-19 04:38:36,689 INFO Epoch:5 val_res:0.535211 +2025-04-19 04:39:00,311 INFO Epoch:6 train_loss:1.59656 +2025-04-19 04:39:06,101 INFO Epoch:6 val_res:0.553991 +2025-04-19 04:39:28,517 INFO Epoch:7 train_loss:1.52932 +2025-04-19 04:39:34,405 INFO Epoch:7 val_res:0.615023 +2025-04-19 04:39:34,406 INFO Saving best model at Epoch 7 +2025-04-19 04:40:00,329 INFO Epoch:8 train_loss:1.47690 +2025-04-19 04:40:06,573 INFO Epoch:8 val_res:0.596244 +2025-04-19 04:40:30,224 INFO Epoch:9 train_loss:1.45488 +2025-04-19 04:40:36,365 INFO Epoch:9 val_res:0.615023 +2025-04-19 04:40:58,455 INFO Epoch:10 train_loss:1.41195 +2025-04-19 04:41:04,734 INFO Epoch:10 val_res:0.586854 +2025-04-19 04:41:27,533 INFO Epoch:11 train_loss:1.37424 +2025-04-19 04:41:34,133 INFO Epoch:11 val_res:0.582160 +2025-04-19 04:41:58,395 INFO Epoch:12 train_loss:1.35671 +2025-04-19 04:42:04,503 INFO Epoch:12 val_res:0.582160 +2025-04-19 04:42:26,057 INFO Epoch:13 train_loss:1.33651 +2025-04-19 04:42:32,035 INFO Epoch:13 val_res:0.629108 +2025-04-19 04:42:32,036 INFO Saving best model at Epoch 13 +2025-04-19 04:42:57,012 INFO Epoch:14 train_loss:1.30658 +2025-04-19 04:43:02,977 INFO Epoch:14 val_res:0.624413 +2025-04-19 04:43:27,890 INFO Epoch:15 train_loss:1.29354 +2025-04-19 04:43:34,531 INFO Epoch:15 val_res:0.624413 +2025-04-19 04:43:56,974 INFO Epoch:16 train_loss:1.26306 +2025-04-19 04:44:03,610 INFO Epoch:16 val_res:0.661972 +2025-04-19 04:44:03,610 INFO Saving best model at Epoch 16 +2025-04-19 04:44:28,145 INFO Epoch:17 train_loss:1.25631 +2025-04-19 04:44:36,189 INFO Epoch:17 val_res:0.638498 +2025-04-19 04:44:59,391 INFO Epoch:18 train_loss:1.24186 +2025-04-19 04:45:05,336 INFO Epoch:18 val_res:0.647887 +2025-04-19 04:45:30,886 INFO Epoch:19 train_loss:1.22242 +2025-04-19 04:45:37,967 INFO Epoch:19 val_res:0.652582 +2025-04-19 04:46:00,525 INFO Epoch:20 train_loss:1.21569 +2025-04-19 04:46:07,647 INFO Epoch:20 val_res:0.633803 +2025-04-19 04:46:31,420 INFO Epoch:21 train_loss:1.20165 +2025-04-19 04:46:37,592 INFO Epoch:21 val_res:0.647887 +2025-04-19 04:47:01,663 INFO Epoch:22 train_loss:1.18124 +2025-04-19 04:47:08,775 INFO Epoch:22 val_res:0.647887 +2025-04-19 04:47:32,825 INFO Epoch:23 train_loss:1.16940 +2025-04-19 04:47:39,997 INFO Epoch:23 val_res:0.633803 +2025-04-19 04:48:03,925 INFO Epoch:24 train_loss:1.15707 +2025-04-19 04:48:10,242 INFO Epoch:24 val_res:0.647887 +2025-04-19 04:48:31,357 INFO Epoch:25 train_loss:1.13481 +2025-04-19 04:48:37,371 INFO Epoch:25 val_res:0.647887 +2025-04-19 04:49:01,705 INFO Epoch:26 train_loss:1.13422 +2025-04-19 04:49:08,468 INFO Epoch:26 val_res:0.643192 +2025-04-19 04:49:33,860 INFO Epoch:27 train_loss:1.12034 +2025-04-19 04:49:40,481 INFO Epoch:27 val_res:0.638498 +2025-04-19 04:50:02,700 INFO Epoch:28 train_loss:1.10088 +2025-04-19 04:50:09,162 INFO Epoch:28 val_res:0.647887 +2025-04-19 04:50:33,673 INFO Epoch:29 train_loss:1.09147 +2025-04-19 04:50:40,713 INFO Epoch:29 val_res:0.652582 +2025-04-19 04:51:05,590 INFO Epoch:30 train_loss:1.09043 +2025-04-19 04:51:12,641 INFO Epoch:30 val_res:0.643192 +2025-04-19 04:51:36,958 INFO Epoch:31 train_loss:1.07506 +2025-04-19 04:51:43,248 INFO Epoch:31 val_res:0.652582 +2025-04-19 04:52:07,363 INFO Epoch:32 train_loss:1.06859 +2025-04-19 04:52:14,710 INFO Epoch:32 val_res:0.652582 +2025-04-19 04:52:40,388 INFO Epoch:33 train_loss:1.05373 +2025-04-19 04:52:47,520 INFO Epoch:33 val_res:0.647887 +2025-04-19 04:53:13,113 INFO Epoch:34 train_loss:1.03862 +2025-04-19 04:53:20,825 INFO Epoch:34 val_res:0.647887 +2025-04-19 04:53:44,452 INFO Epoch:35 train_loss:1.02759 +2025-04-19 04:53:51,990 INFO Epoch:35 val_res:0.652582 +2025-04-19 04:54:16,157 INFO Epoch:36 train_loss:1.02545 +2025-04-19 04:54:23,837 INFO Epoch:36 val_res:0.661972 +2025-04-19 04:54:47,536 INFO Epoch:37 train_loss:1.02286 +2025-04-19 04:54:55,120 INFO Epoch:37 val_res:0.647887 +2025-04-19 04:55:20,024 INFO Epoch:38 train_loss:1.01146 +2025-04-19 04:55:28,647 INFO Epoch:38 val_res:0.676056 +2025-04-19 04:55:28,647 INFO Saving best model at Epoch 38 +2025-04-19 04:55:55,808 INFO Epoch:39 train_loss:0.99833 +2025-04-19 04:56:03,657 INFO Epoch:39 val_res:0.671362 +2025-04-19 04:56:30,150 INFO Epoch:40 train_loss:0.99172 +2025-04-19 04:56:38,249 INFO Epoch:40 val_res:0.666667 +2025-04-19 04:57:03,738 INFO Epoch:41 train_loss:0.97500 +2025-04-19 04:57:10,548 INFO Epoch:41 val_res:0.657277 +2025-04-19 04:57:35,931 INFO Epoch:42 train_loss:0.97483 +2025-04-19 04:57:43,440 INFO Epoch:42 val_res:0.643192 +2025-04-19 04:58:06,863 INFO Epoch:43 train_loss:0.96685 +2025-04-19 04:58:13,337 INFO Epoch:43 val_res:0.661972 +2025-04-19 04:58:37,132 INFO Epoch:44 train_loss:0.95945 +2025-04-19 04:58:44,179 INFO Epoch:44 val_res:0.647887 +2025-04-19 04:59:09,746 INFO Epoch:45 train_loss:0.95177 +2025-04-19 04:59:17,392 INFO Epoch:45 val_res:0.657277 +2025-04-19 04:59:42,917 INFO Epoch:46 train_loss:0.93911 +2025-04-19 04:59:49,547 INFO Epoch:46 val_res:0.657277 +2025-04-19 05:00:15,416 INFO Epoch:47 train_loss:0.93742 +2025-04-19 05:00:24,089 INFO Epoch:47 val_res:0.643192 +2025-04-19 05:00:51,476 INFO Epoch:48 train_loss:0.93398 +2025-04-19 05:00:59,974 INFO Epoch:48 val_res:0.666667 +2025-04-19 05:01:26,184 INFO Epoch:49 train_loss:0.92497 +2025-04-19 05:01:34,426 INFO Epoch:49 val_res:0.652582 +2025-04-19 05:02:00,782 INFO Epoch:50 train_loss:0.91717 +2025-04-19 05:02:09,023 INFO Epoch:50 val_res:0.666667 +2025-04-19 05:02:36,706 INFO Epoch:51 train_loss:0.91261 +2025-04-19 05:02:43,401 INFO Epoch:51 val_res:0.652582 +2025-04-19 05:03:10,428 INFO Epoch:52 train_loss:0.89786 +2025-04-19 05:03:17,675 INFO Epoch:52 val_res:0.657277 +2025-04-19 05:03:42,906 INFO Epoch:53 train_loss:0.90636 +2025-04-19 05:03:50,534 INFO Epoch:53 val_res:0.657277 +2025-04-19 05:04:18,081 INFO Epoch:54 train_loss:0.90125 +2025-04-19 05:04:27,362 INFO Epoch:54 val_res:0.657277 +2025-04-19 05:04:53,831 INFO Epoch:55 train_loss:0.88390 +2025-04-19 05:05:02,135 INFO Epoch:55 val_res:0.657277 +2025-04-19 05:05:31,278 INFO Epoch:56 train_loss:0.88072 +2025-04-19 05:05:38,796 INFO Epoch:56 val_res:0.666667 +2025-04-19 05:06:05,109 INFO Epoch:57 train_loss:0.86665 +2025-04-19 05:06:13,291 INFO Epoch:57 val_res:0.657277 +2025-04-19 05:06:40,100 INFO Epoch:58 train_loss:0.86555 +2025-04-19 05:06:48,050 INFO Epoch:58 val_res:0.652582 +2025-04-19 05:07:14,682 INFO Epoch:59 train_loss:0.86187 +2025-04-19 05:07:22,794 INFO Epoch:59 val_res:0.666667 +2025-04-19 05:07:49,474 INFO Epoch:60 train_loss:0.85403 +2025-04-19 05:07:57,732 INFO Epoch:60 val_res:0.652582 +2025-04-19 05:08:23,177 INFO Epoch:61 train_loss:0.85392 +2025-04-19 05:08:31,495 INFO Epoch:61 val_res:0.666667 +2025-04-19 05:08:58,439 INFO Epoch:62 train_loss:0.84927 +2025-04-19 05:09:06,017 INFO Epoch:62 val_res:0.657277 +2025-04-19 05:09:31,537 INFO Epoch:63 train_loss:0.84145 +2025-04-19 05:09:38,699 INFO Epoch:63 val_res:0.671362 +2025-04-19 05:10:05,458 INFO Epoch:64 train_loss:0.84488 +2025-04-19 05:10:13,604 INFO Epoch:64 val_res:0.657277 +2025-04-19 05:10:39,343 INFO Epoch:65 train_loss:0.84491 +2025-04-19 05:10:46,791 INFO Epoch:65 val_res:0.657277 +2025-04-19 05:11:11,645 INFO Epoch:66 train_loss:0.83197 +2025-04-19 05:11:19,564 INFO Epoch:66 val_res:0.661972 +2025-04-19 05:11:44,555 INFO Epoch:67 train_loss:0.83615 +2025-04-19 05:11:51,284 INFO Epoch:67 val_res:0.657277 +2025-04-19 05:12:17,123 INFO Epoch:68 train_loss:0.82324 +2025-04-19 05:12:25,738 INFO Epoch:68 val_res:0.657277 +2025-04-19 05:12:50,748 INFO Epoch:69 train_loss:0.81473 +2025-04-19 05:12:59,173 INFO Epoch:69 val_res:0.657277 +2025-04-19 05:13:27,317 INFO Epoch:70 train_loss:0.81410 +2025-04-19 05:13:34,969 INFO Epoch:70 val_res:0.666667 +2025-04-19 05:14:00,177 INFO Epoch:71 train_loss:0.79444 +2025-04-19 05:14:08,009 INFO Epoch:71 val_res:0.661972 +2025-04-19 05:14:33,916 INFO Epoch:72 train_loss:0.79974 +2025-04-19 05:14:41,399 INFO Epoch:72 val_res:0.661972 +2025-04-19 05:15:08,015 INFO Epoch:73 train_loss:0.79409 +2025-04-19 05:15:16,674 INFO Epoch:73 val_res:0.657277 +2025-04-19 05:15:41,448 INFO Epoch:74 train_loss:0.78789 +2025-04-19 05:15:49,130 INFO Epoch:74 val_res:0.671362 +2025-04-19 05:16:17,273 INFO Epoch:75 train_loss:0.77231 +2025-04-19 05:16:25,035 INFO Epoch:75 val_res:0.661972 +2025-04-19 05:16:49,375 INFO Epoch:76 train_loss:0.77250 +2025-04-19 05:16:57,720 INFO Epoch:76 val_res:0.666667 +2025-04-19 05:17:24,770 INFO Epoch:77 train_loss:0.77266 +2025-04-19 05:17:31,656 INFO Epoch:77 val_res:0.671362 +2025-04-19 05:17:57,962 INFO Epoch:78 train_loss:0.77180 +2025-04-19 05:18:06,414 INFO Epoch:78 val_res:0.676056 +2025-04-19 05:18:32,270 INFO Epoch:79 train_loss:0.76215 +2025-04-19 05:18:39,708 INFO Epoch:79 val_res:0.657277 +2025-04-19 05:19:05,348 INFO Epoch:80 train_loss:0.76284 +2025-04-19 05:19:12,466 INFO Epoch:80 val_res:0.661972 +2025-04-19 05:19:38,441 INFO Epoch:81 train_loss:0.76598 +2025-04-19 05:19:46,633 INFO Epoch:81 val_res:0.661972 +2025-04-19 05:20:14,697 INFO Epoch:82 train_loss:0.75792 +2025-04-19 05:20:21,201 INFO Epoch:82 val_res:0.671362 +2025-04-19 05:20:44,985 INFO Epoch:83 train_loss:0.76565 +2025-04-19 05:20:53,634 INFO Epoch:83 val_res:0.676056 +2025-04-19 05:21:19,665 INFO Epoch:84 train_loss:0.76576 +2025-04-19 05:21:27,691 INFO Epoch:84 val_res:0.661972 +2025-04-19 05:21:53,456 INFO Epoch:85 train_loss:0.75056 +2025-04-19 05:22:01,419 INFO Epoch:85 val_res:0.661972 +2025-04-19 05:22:26,536 INFO Epoch:86 train_loss:0.74927 +2025-04-19 05:22:32,928 INFO Epoch:86 val_res:0.661972 +2025-04-19 05:22:59,981 INFO Epoch:87 train_loss:0.73571 +2025-04-19 05:23:07,038 INFO Epoch:87 val_res:0.676056 +2025-04-19 05:23:33,157 INFO Epoch:88 train_loss:0.74306 +2025-04-19 05:23:42,022 INFO Epoch:88 val_res:0.666667 +2025-04-19 05:24:08,549 INFO Epoch:89 train_loss:0.78038 +2025-04-19 05:24:15,896 INFO Epoch:89 val_res:0.690141 +2025-04-19 05:24:15,896 INFO Saving best model at Epoch 89 +2025-04-19 05:24:44,019 INFO Epoch:90 train_loss:0.78606 +2025-04-19 05:24:51,696 INFO Epoch:90 val_res:0.690141 +2025-04-19 05:25:19,169 INFO Epoch:91 train_loss:0.79329 +2025-04-19 05:25:26,965 INFO Epoch:91 val_res:0.671362 +2025-04-19 05:25:53,651 INFO Epoch:92 train_loss:0.75971 +2025-04-19 05:26:01,756 INFO Epoch:92 val_res:0.676056 +2025-04-19 05:26:28,735 INFO Epoch:93 train_loss:0.76555 +2025-04-19 05:26:36,608 INFO Epoch:93 val_res:0.680751 +2025-04-19 05:27:04,958 INFO Epoch:94 train_loss:0.76633 +2025-04-19 05:27:11,992 INFO Epoch:94 val_res:0.680751 +2025-04-19 05:27:35,931 INFO Epoch:95 train_loss:0.77622 +2025-04-19 05:27:43,220 INFO Epoch:95 val_res:0.666667 +2025-04-19 05:28:08,339 INFO Epoch:96 train_loss:0.75844 +2025-04-19 05:28:16,109 INFO Epoch:96 val_res:0.671362 +2025-04-19 05:28:40,738 INFO Epoch:97 train_loss:0.74834 +2025-04-19 05:28:48,113 INFO Epoch:97 val_res:0.671362 +2025-04-19 05:29:13,674 INFO Epoch:98 train_loss:0.72671 +2025-04-19 05:29:21,756 INFO Epoch:98 val_res:0.676056 +2025-04-19 05:29:46,600 INFO Epoch:99 train_loss:0.72193 +2025-04-19 05:29:53,808 INFO Epoch:99 val_res:0.690141 +2025-04-19 05:29:54,247 INFO ===================================== +2025-04-19 05:29:54,248 INFO Start testing... +2025-04-19 05:29:54,248 INFO ===================================== +2025-04-19 05:30:02,060 INFO Incremental step 1 Testing res: 0.628571 +2025-04-19 05:30:02,061 INFO forgetting: 0.346154 +2025-04-19 05:30:02,065 INFO Incremental step: 2 +2025-04-19 05:30:28,743 INFO Epoch:0 train_loss:3.39496 +2025-04-19 05:30:37,190 INFO Epoch:0 val_res:0.471154 +2025-04-19 05:30:37,191 INFO Saving best model at Epoch 0 +2025-04-19 05:31:04,740 INFO Epoch:1 train_loss:2.90468 +2025-04-19 05:31:13,320 INFO Epoch:1 val_res:0.467949 +2025-04-19 05:31:42,034 INFO Epoch:2 train_loss:2.39375 +2025-04-19 05:31:50,636 INFO Epoch:2 val_res:0.503205 +2025-04-19 05:31:50,637 INFO Saving best model at Epoch 2 +2025-04-19 05:32:18,349 INFO Epoch:3 train_loss:1.95143 +2025-04-19 05:32:27,606 INFO Epoch:3 val_res:0.500000 +2025-04-19 05:32:53,897 INFO Epoch:4 train_loss:1.73963 +2025-04-19 05:33:01,305 INFO Epoch:4 val_res:0.512821 +2025-04-19 05:33:01,305 INFO Saving best model at Epoch 4 +2025-04-19 05:33:27,309 INFO Epoch:5 train_loss:1.65191 +2025-04-19 05:33:35,122 INFO Epoch:5 val_res:0.538462 +2025-04-19 05:33:35,122 INFO Saving best model at Epoch 5 +2025-04-19 05:34:02,037 INFO Epoch:6 train_loss:1.50180 +2025-04-19 05:34:10,006 INFO Epoch:6 val_res:0.522436 +2025-04-19 05:34:36,232 INFO Epoch:7 train_loss:1.42775 +2025-04-19 05:34:45,846 INFO Epoch:7 val_res:0.544872 +2025-04-19 05:34:45,847 INFO Saving best model at Epoch 7 +2025-04-19 05:35:14,477 INFO Epoch:8 train_loss:1.38460 +2025-04-19 05:35:22,631 INFO Epoch:8 val_res:0.554487 +2025-04-19 05:35:22,631 INFO Saving best model at Epoch 8 +2025-04-19 05:35:51,035 INFO Epoch:9 train_loss:1.33024 +2025-04-19 05:35:59,700 INFO Epoch:9 val_res:0.541667 +2025-04-19 05:36:24,271 INFO Epoch:10 train_loss:1.27901 +2025-04-19 05:36:32,807 INFO Epoch:10 val_res:0.541667 +2025-04-19 05:36:59,839 INFO Epoch:11 train_loss:1.25141 +2025-04-19 05:37:08,419 INFO Epoch:11 val_res:0.548077 +2025-04-19 05:37:33,622 INFO Epoch:12 train_loss:1.21144 +2025-04-19 05:37:41,387 INFO Epoch:12 val_res:0.554487 +2025-04-19 05:38:07,619 INFO Epoch:13 train_loss:1.19474 +2025-04-19 05:38:16,403 INFO Epoch:13 val_res:0.557692 +2025-04-19 05:38:16,404 INFO Saving best model at Epoch 13 +2025-04-19 05:38:46,565 INFO Epoch:14 train_loss:1.17113 +2025-04-19 05:38:55,721 INFO Epoch:14 val_res:0.560897 +2025-04-19 05:38:55,722 INFO Saving best model at Epoch 14 +2025-04-19 05:39:23,223 INFO Epoch:15 train_loss:1.14082 +2025-04-19 05:39:32,085 INFO Epoch:15 val_res:0.573718 +2025-04-19 05:39:32,086 INFO Saving best model at Epoch 15 +2025-04-19 05:40:00,792 INFO Epoch:16 train_loss:1.13575 +2025-04-19 05:40:07,720 INFO Epoch:16 val_res:0.564103 +2025-04-19 05:40:34,313 INFO Epoch:17 train_loss:1.11016 +2025-04-19 05:40:42,602 INFO Epoch:17 val_res:0.554487 +2025-04-19 05:41:08,583 INFO Epoch:18 train_loss:1.09610 +2025-04-19 05:41:16,354 INFO Epoch:18 val_res:0.564103 +2025-04-19 05:41:42,164 INFO Epoch:19 train_loss:1.07779 +2025-04-19 05:41:50,433 INFO Epoch:19 val_res:0.560897 +2025-04-19 05:42:18,140 INFO Epoch:20 train_loss:1.06378 +2025-04-19 05:42:26,010 INFO Epoch:20 val_res:0.557692 +2025-04-19 05:42:52,621 INFO Epoch:21 train_loss:1.05497 +2025-04-19 05:43:01,675 INFO Epoch:21 val_res:0.564103 +2025-04-19 05:43:26,977 INFO Epoch:22 train_loss:1.03563 +2025-04-19 05:43:35,189 INFO Epoch:22 val_res:0.560897 +2025-04-19 05:44:01,220 INFO Epoch:23 train_loss:1.01866 +2025-04-19 05:44:10,494 INFO Epoch:23 val_res:0.564103 +2025-04-19 05:44:36,691 INFO Epoch:24 train_loss:1.01375 +2025-04-19 05:44:44,015 INFO Epoch:24 val_res:0.573718 +2025-04-19 05:45:10,976 INFO Epoch:25 train_loss:1.00169 +2025-04-19 05:45:18,956 INFO Epoch:25 val_res:0.560897 +2025-04-19 05:45:42,273 INFO Epoch:26 train_loss:0.99573 +2025-04-19 05:45:49,210 INFO Epoch:26 val_res:0.554487 +2025-04-19 05:46:12,558 INFO Epoch:27 train_loss:0.98392 +2025-04-19 05:46:20,577 INFO Epoch:27 val_res:0.570513 +2025-04-19 05:46:45,309 INFO Epoch:28 train_loss:0.97057 +2025-04-19 05:46:52,261 INFO Epoch:28 val_res:0.576923 +2025-04-19 05:46:52,261 INFO Saving best model at Epoch 28 +2025-04-19 05:47:19,078 INFO Epoch:29 train_loss:0.95906 +2025-04-19 05:47:27,805 INFO Epoch:29 val_res:0.573718 +2025-04-19 05:47:54,263 INFO Epoch:30 train_loss:0.95423 +2025-04-19 05:48:03,066 INFO Epoch:30 val_res:0.570513 +2025-04-19 05:48:30,642 INFO Epoch:31 train_loss:0.94521 +2025-04-19 05:48:39,422 INFO Epoch:31 val_res:0.567308 +2025-04-19 05:49:02,550 INFO Epoch:32 train_loss:0.93007 +2025-04-19 05:49:10,950 INFO Epoch:32 val_res:0.580128 +2025-04-19 05:49:10,953 INFO Saving best model at Epoch 32 +2025-04-19 05:49:37,473 INFO Epoch:33 train_loss:0.92772 +2025-04-19 05:49:45,318 INFO Epoch:33 val_res:0.586538 +2025-04-19 05:49:45,319 INFO Saving best model at Epoch 33 +2025-04-19 05:50:11,179 INFO Epoch:34 train_loss:0.91153 +2025-04-19 05:50:19,719 INFO Epoch:34 val_res:0.570513 +2025-04-19 05:50:42,310 INFO Epoch:35 train_loss:0.91071 +2025-04-19 05:50:49,136 INFO Epoch:35 val_res:0.580128 +2025-04-19 05:51:13,298 INFO Epoch:36 train_loss:0.89606 +2025-04-19 05:51:20,889 INFO Epoch:36 val_res:0.583333 +2025-04-19 05:51:43,869 INFO Epoch:37 train_loss:0.89081 +2025-04-19 05:51:51,102 INFO Epoch:37 val_res:0.583333 +2025-04-19 05:52:15,170 INFO Epoch:38 train_loss:0.86181 +2025-04-19 05:52:24,584 INFO Epoch:38 val_res:0.586538 +2025-04-19 05:52:49,739 INFO Epoch:39 train_loss:0.85872 +2025-04-19 05:52:57,095 INFO Epoch:39 val_res:0.589744 +2025-04-19 05:52:57,095 INFO Saving best model at Epoch 39 +2025-04-19 05:53:25,309 INFO Epoch:40 train_loss:0.86122 +2025-04-19 05:53:33,600 INFO Epoch:40 val_res:0.592949 +2025-04-19 05:53:33,601 INFO Saving best model at Epoch 40 +2025-04-19 05:54:00,869 INFO Epoch:41 train_loss:0.85885 +2025-04-19 05:54:08,836 INFO Epoch:41 val_res:0.592949 +2025-04-19 05:54:34,430 INFO Epoch:42 train_loss:0.84400 +2025-04-19 05:54:41,703 INFO Epoch:42 val_res:0.586538 +2025-04-19 05:55:06,612 INFO Epoch:43 train_loss:0.83154 +2025-04-19 05:55:14,354 INFO Epoch:43 val_res:0.592949 +2025-04-19 05:55:39,333 INFO Epoch:44 train_loss:0.83377 +2025-04-19 05:55:46,566 INFO Epoch:44 val_res:0.589744 +2025-04-19 05:56:11,992 INFO Epoch:45 train_loss:0.82829 +2025-04-19 05:56:20,118 INFO Epoch:45 val_res:0.596154 +2025-04-19 05:56:20,118 INFO Saving best model at Epoch 45 +2025-04-19 05:56:50,517 INFO Epoch:46 train_loss:0.82146 +2025-04-19 05:56:57,879 INFO Epoch:46 val_res:0.589744 +2025-04-19 05:57:22,727 INFO Epoch:47 train_loss:0.81898 +2025-04-19 05:57:30,974 INFO Epoch:47 val_res:0.602564 +2025-04-19 05:57:30,974 INFO Saving best model at Epoch 47 +2025-04-19 05:58:02,530 INFO Epoch:48 train_loss:0.81417 +2025-04-19 05:58:09,622 INFO Epoch:48 val_res:0.599359 +2025-04-19 05:58:32,399 INFO Epoch:49 train_loss:0.79968 +2025-04-19 05:58:39,577 INFO Epoch:49 val_res:0.589744 +2025-04-19 05:59:02,867 INFO Epoch:50 train_loss:0.79189 +2025-04-19 05:59:10,692 INFO Epoch:50 val_res:0.602564 +2025-04-19 05:59:33,667 INFO Epoch:51 train_loss:0.78620 +2025-04-19 05:59:41,491 INFO Epoch:51 val_res:0.602564 +2025-04-19 06:00:04,629 INFO Epoch:52 train_loss:0.78777 +2025-04-19 06:00:11,286 INFO Epoch:52 val_res:0.599359 +2025-04-19 06:00:35,373 INFO Epoch:53 train_loss:0.78290 +2025-04-19 06:00:42,397 INFO Epoch:53 val_res:0.602564 +2025-04-19 06:01:06,525 INFO Epoch:54 train_loss:0.76779 +2025-04-19 06:01:14,138 INFO Epoch:54 val_res:0.605769 +2025-04-19 06:01:14,139 INFO Saving best model at Epoch 54 +2025-04-19 06:01:39,655 INFO Epoch:55 train_loss:0.77010 +2025-04-19 06:01:47,572 INFO Epoch:55 val_res:0.599359 +2025-04-19 06:02:11,586 INFO Epoch:56 train_loss:0.77016 +2025-04-19 06:02:19,100 INFO Epoch:56 val_res:0.605769 +2025-04-19 06:02:43,595 INFO Epoch:57 train_loss:0.76770 +2025-04-19 06:02:50,301 INFO Epoch:57 val_res:0.605769 +2025-04-19 06:03:16,981 INFO Epoch:58 train_loss:0.76170 +2025-04-19 06:03:25,588 INFO Epoch:58 val_res:0.608974 +2025-04-19 06:03:25,588 INFO Saving best model at Epoch 58 +2025-04-19 06:03:49,874 INFO Epoch:59 train_loss:0.76463 +2025-04-19 06:03:57,441 INFO Epoch:59 val_res:0.612179 +2025-04-19 06:03:57,441 INFO Saving best model at Epoch 59 +2025-04-19 06:04:24,914 INFO Epoch:60 train_loss:0.74682 +2025-04-19 06:04:33,201 INFO Epoch:60 val_res:0.605769 +2025-04-19 06:04:59,354 INFO Epoch:61 train_loss:0.74742 +2025-04-19 06:05:07,370 INFO Epoch:61 val_res:0.608974 +2025-04-19 06:05:31,816 INFO Epoch:62 train_loss:0.73755 +2025-04-19 06:05:40,596 INFO Epoch:62 val_res:0.608974 +2025-04-19 06:06:09,716 INFO Epoch:63 train_loss:0.73293 +2025-04-19 06:06:17,832 INFO Epoch:63 val_res:0.602564 +2025-04-19 06:06:44,264 INFO Epoch:64 train_loss:0.73606 +2025-04-19 06:06:51,681 INFO Epoch:64 val_res:0.615385 +2025-04-19 06:06:51,681 INFO Saving best model at Epoch 64 +2025-04-19 06:07:23,209 INFO Epoch:65 train_loss:0.73033 +2025-04-19 06:07:32,082 INFO Epoch:65 val_res:0.612179 +2025-04-19 06:07:58,878 INFO Epoch:66 train_loss:0.72776 +2025-04-19 06:08:07,106 INFO Epoch:66 val_res:0.608974 +2025-04-19 06:08:32,928 INFO Epoch:67 train_loss:0.72701 +2025-04-19 06:08:42,448 INFO Epoch:67 val_res:0.618590 +2025-04-19 06:08:42,449 INFO Saving best model at Epoch 67 +2025-04-19 06:09:11,423 INFO Epoch:68 train_loss:0.72055 +2025-04-19 06:09:19,364 INFO Epoch:68 val_res:0.615385 +2025-04-19 06:09:46,317 INFO Epoch:69 train_loss:0.71438 +2025-04-19 06:09:54,572 INFO Epoch:69 val_res:0.615385 +2025-04-19 06:10:19,773 INFO Epoch:70 train_loss:0.71515 +2025-04-19 06:10:29,110 INFO Epoch:70 val_res:0.612179 +2025-04-19 06:10:54,332 INFO Epoch:71 train_loss:0.70814 +2025-04-19 06:11:02,854 INFO Epoch:71 val_res:0.615385 +2025-04-19 06:11:28,692 INFO Epoch:72 train_loss:0.70507 +2025-04-19 06:11:37,002 INFO Epoch:72 val_res:0.618590 +2025-04-19 06:12:02,768 INFO Epoch:73 train_loss:0.70506 +2025-04-19 06:12:11,569 INFO Epoch:73 val_res:0.621795 +2025-04-19 06:12:11,569 INFO Saving best model at Epoch 73 +2025-04-19 06:12:40,296 INFO Epoch:74 train_loss:0.70299 +2025-04-19 06:12:47,814 INFO Epoch:74 val_res:0.612179 +2025-04-19 06:13:13,758 INFO Epoch:75 train_loss:0.70639 +2025-04-19 06:13:22,575 INFO Epoch:75 val_res:0.618590 +2025-04-19 06:13:49,032 INFO Epoch:76 train_loss:0.68869 +2025-04-19 06:13:59,111 INFO Epoch:76 val_res:0.618590 +2025-04-19 06:14:26,232 INFO Epoch:77 train_loss:0.69248 +2025-04-19 06:14:34,432 INFO Epoch:77 val_res:0.612179 +2025-04-19 06:15:00,964 INFO Epoch:78 train_loss:0.68906 +2025-04-19 06:15:09,648 INFO Epoch:78 val_res:0.618590 +2025-04-19 06:15:36,595 INFO Epoch:79 train_loss:0.68877 +2025-04-19 06:15:44,783 INFO Epoch:79 val_res:0.628205 +2025-04-19 06:15:44,783 INFO Saving best model at Epoch 79 +2025-04-19 06:16:13,941 INFO Epoch:80 train_loss:0.68197 +2025-04-19 06:16:23,178 INFO Epoch:80 val_res:0.625000 +2025-04-19 06:16:49,583 INFO Epoch:81 train_loss:0.68469 +2025-04-19 06:16:57,439 INFO Epoch:81 val_res:0.628205 +2025-04-19 06:17:24,294 INFO Epoch:82 train_loss:0.67239 +2025-04-19 06:17:31,668 INFO Epoch:82 val_res:0.631410 +2025-04-19 06:17:31,669 INFO Saving best model at Epoch 82 +2025-04-19 06:17:58,769 INFO Epoch:83 train_loss:0.67410 +2025-04-19 06:18:07,857 INFO Epoch:83 val_res:0.621795 +2025-04-19 06:18:35,031 INFO Epoch:84 train_loss:0.66848 +2025-04-19 06:18:42,843 INFO Epoch:84 val_res:0.618590 +2025-04-19 06:19:09,063 INFO Epoch:85 train_loss:0.67331 +2025-04-19 06:19:17,362 INFO Epoch:85 val_res:0.631410 +2025-04-19 06:19:45,521 INFO Epoch:86 train_loss:0.67536 +2025-04-19 06:19:53,065 INFO Epoch:86 val_res:0.634615 +2025-04-19 06:19:53,066 INFO Saving best model at Epoch 86 +2025-04-19 06:20:23,866 INFO Epoch:87 train_loss:0.67924 +2025-04-19 06:20:32,610 INFO Epoch:87 val_res:0.618590 +2025-04-19 06:20:58,185 INFO Epoch:88 train_loss:0.67201 +2025-04-19 06:21:07,402 INFO Epoch:88 val_res:0.618590 +2025-04-19 06:21:33,121 INFO Epoch:89 train_loss:0.66505 +2025-04-19 06:21:41,941 INFO Epoch:89 val_res:0.628205 +2025-04-19 06:22:08,479 INFO Epoch:90 train_loss:0.66443 +2025-04-19 06:22:16,464 INFO Epoch:90 val_res:0.625000 +2025-04-19 06:22:43,890 INFO Epoch:91 train_loss:0.66156 +2025-04-19 06:22:53,139 INFO Epoch:91 val_res:0.628205 +2025-04-19 06:23:20,445 INFO Epoch:92 train_loss:0.66185 +2025-04-19 06:23:28,513 INFO Epoch:92 val_res:0.621795 +2025-04-19 06:23:53,979 INFO Epoch:93 train_loss:0.65537 +2025-04-19 06:24:02,675 INFO Epoch:93 val_res:0.631410 +2025-04-19 06:24:29,425 INFO Epoch:94 train_loss:0.65422 +2025-04-19 06:24:38,231 INFO Epoch:94 val_res:0.625000 +2025-04-19 06:25:04,726 INFO Epoch:95 train_loss:0.65197 +2025-04-19 06:25:13,179 INFO Epoch:95 val_res:0.628205 +2025-04-19 06:25:38,099 INFO Epoch:96 train_loss:0.64868 +2025-04-19 06:25:47,621 INFO Epoch:96 val_res:0.621795 +2025-04-19 06:26:13,688 INFO Epoch:97 train_loss:0.64192 +2025-04-19 06:26:21,746 INFO Epoch:97 val_res:0.625000 +2025-04-19 06:26:47,987 INFO Epoch:98 train_loss:0.64612 +2025-04-19 06:26:56,572 INFO Epoch:98 val_res:0.625000 +2025-04-19 06:27:22,086 INFO Epoch:99 train_loss:0.64826 +2025-04-19 06:27:30,417 INFO Epoch:99 val_res:0.628205 +2025-04-19 06:27:30,702 INFO ===================================== +2025-04-19 06:27:30,707 INFO Start testing... +2025-04-19 06:27:30,707 INFO ===================================== +2025-04-19 06:27:40,938 INFO Incremental step 2 Testing res: 0.574603 +2025-04-19 06:27:40,940 INFO forgetting: 0.257892 +2025-04-19 06:27:40,944 INFO Incremental step: 3 +2025-04-19 06:28:07,675 INFO Epoch:0 train_loss:3.38011 +2025-04-19 06:28:17,315 INFO Epoch:0 val_res:0.452685 +2025-04-19 06:28:17,316 INFO Saving best model at Epoch 0 +2025-04-19 06:28:42,233 INFO Epoch:1 train_loss:4.13826 +2025-04-19 06:28:51,979 INFO Epoch:1 val_res:0.437340 +2025-04-19 06:29:17,173 INFO Epoch:2 train_loss:2.86830 +2025-04-19 06:29:26,940 INFO Epoch:2 val_res:0.521739 +2025-04-19 06:29:26,941 INFO Saving best model at Epoch 2 +2025-04-19 06:29:55,287 INFO Epoch:3 train_loss:2.50787 +2025-04-19 06:30:04,280 INFO Epoch:3 val_res:0.529412 +2025-04-19 06:30:04,280 INFO Saving best model at Epoch 3 +2025-04-19 06:30:30,991 INFO Epoch:4 train_loss:2.32324 +2025-04-19 06:30:40,408 INFO Epoch:4 val_res:0.498721 +2025-04-19 06:31:05,066 INFO Epoch:5 train_loss:1.87596 +2025-04-19 06:31:14,842 INFO Epoch:5 val_res:0.488491 +2025-04-19 06:31:37,799 INFO Epoch:6 train_loss:1.74407 +2025-04-19 06:31:46,920 INFO Epoch:6 val_res:0.519182 +2025-04-19 06:32:12,440 INFO Epoch:7 train_loss:1.73869 +2025-04-19 06:32:21,858 INFO Epoch:7 val_res:0.537084 +2025-04-19 06:32:21,858 INFO Saving best model at Epoch 7 +2025-04-19 06:32:48,457 INFO Epoch:8 train_loss:1.46716 +2025-04-19 06:32:59,142 INFO Epoch:8 val_res:0.554987 +2025-04-19 06:32:59,143 INFO Saving best model at Epoch 8 +2025-04-19 06:33:27,833 INFO Epoch:9 train_loss:1.53554 +2025-04-19 06:33:37,816 INFO Epoch:9 val_res:0.552430 +2025-04-19 06:34:01,436 INFO Epoch:10 train_loss:1.43512 +2025-04-19 06:34:10,850 INFO Epoch:10 val_res:0.554987 +2025-04-19 06:34:36,081 INFO Epoch:11 train_loss:1.28979 +2025-04-19 06:34:44,355 INFO Epoch:11 val_res:0.557545 +2025-04-19 06:34:44,356 INFO Saving best model at Epoch 11 +2025-04-19 06:35:14,645 INFO Epoch:12 train_loss:1.29425 +2025-04-19 06:35:23,722 INFO Epoch:12 val_res:0.531969 +2025-04-19 06:35:46,413 INFO Epoch:13 train_loss:1.25942 +2025-04-19 06:35:55,900 INFO Epoch:13 val_res:0.557545 +2025-04-19 06:36:20,556 INFO Epoch:14 train_loss:1.23337 +2025-04-19 06:36:30,537 INFO Epoch:14 val_res:0.567775 +2025-04-19 06:36:30,538 INFO Saving best model at Epoch 14 +2025-04-19 06:36:57,673 INFO Epoch:15 train_loss:1.19821 +2025-04-19 06:37:06,693 INFO Epoch:15 val_res:0.588235 +2025-04-19 06:37:06,693 INFO Saving best model at Epoch 15 +2025-04-19 06:37:33,649 INFO Epoch:16 train_loss:1.16489 +2025-04-19 06:37:42,692 INFO Epoch:16 val_res:0.575448 +2025-04-19 06:38:08,056 INFO Epoch:17 train_loss:1.12865 +2025-04-19 06:38:16,411 INFO Epoch:17 val_res:0.560102 +2025-04-19 06:38:42,899 INFO Epoch:18 train_loss:1.12054 +2025-04-19 06:38:51,899 INFO Epoch:18 val_res:0.552430 +2025-04-19 06:39:16,235 INFO Epoch:19 train_loss:1.11969 +2025-04-19 06:39:25,238 INFO Epoch:19 val_res:0.560102 +2025-04-19 06:39:51,189 INFO Epoch:20 train_loss:1.10122 +2025-04-19 06:40:00,118 INFO Epoch:20 val_res:0.570332 +2025-04-19 06:40:25,631 INFO Epoch:21 train_loss:1.05360 +2025-04-19 06:40:34,888 INFO Epoch:21 val_res:0.570332 +2025-04-19 06:41:00,346 INFO Epoch:22 train_loss:1.04817 +2025-04-19 06:41:09,231 INFO Epoch:22 val_res:0.572890 +2025-04-19 06:41:33,770 INFO Epoch:23 train_loss:1.05853 +2025-04-19 06:41:43,550 INFO Epoch:23 val_res:0.580563 +2025-04-19 06:42:09,383 INFO Epoch:24 train_loss:1.03578 +2025-04-19 06:42:18,298 INFO Epoch:24 val_res:0.567775 +2025-04-19 06:42:44,112 INFO Epoch:25 train_loss:1.01370 +2025-04-19 06:42:53,329 INFO Epoch:25 val_res:0.567775 +2025-04-19 06:43:18,264 INFO Epoch:26 train_loss:1.00191 +2025-04-19 06:43:27,498 INFO Epoch:26 val_res:0.578005 +2025-04-19 06:43:54,334 INFO Epoch:27 train_loss:1.01539 +2025-04-19 06:44:03,303 INFO Epoch:27 val_res:0.588235 +2025-04-19 06:44:27,639 INFO Epoch:28 train_loss:1.00665 +2025-04-19 06:44:37,140 INFO Epoch:28 val_res:0.590793 +2025-04-19 06:44:37,141 INFO Saving best model at Epoch 28 +2025-04-19 06:45:04,098 INFO Epoch:29 train_loss:0.98958 +2025-04-19 06:45:14,005 INFO Epoch:29 val_res:0.588235 +2025-04-19 06:45:36,066 INFO Epoch:30 train_loss:0.96916 +2025-04-19 06:45:45,563 INFO Epoch:30 val_res:0.590793 +2025-04-19 06:46:10,948 INFO Epoch:31 train_loss:0.97828 +2025-04-19 06:46:19,780 INFO Epoch:31 val_res:0.598466 +2025-04-19 06:46:19,780 INFO Saving best model at Epoch 31 +2025-04-19 06:46:46,996 INFO Epoch:32 train_loss:0.96839 +2025-04-19 06:46:56,369 INFO Epoch:32 val_res:0.606138 +2025-04-19 06:46:56,369 INFO Saving best model at Epoch 32 +2025-04-19 06:47:21,764 INFO Epoch:33 train_loss:0.96190 +2025-04-19 06:47:31,214 INFO Epoch:33 val_res:0.598466 +2025-04-19 06:47:56,782 INFO Epoch:34 train_loss:0.95478 +2025-04-19 06:48:06,828 INFO Epoch:34 val_res:0.595908 +2025-04-19 06:48:32,387 INFO Epoch:35 train_loss:0.93850 +2025-04-19 06:48:41,781 INFO Epoch:35 val_res:0.598466 +2025-04-19 06:49:06,597 INFO Epoch:36 train_loss:0.93392 +2025-04-19 06:49:16,116 INFO Epoch:36 val_res:0.603581 +2025-04-19 06:49:41,218 INFO Epoch:37 train_loss:0.93435 +2025-04-19 06:49:51,087 INFO Epoch:37 val_res:0.598466 +2025-04-19 06:50:15,628 INFO Epoch:38 train_loss:0.91670 +2025-04-19 06:50:25,424 INFO Epoch:38 val_res:0.606138 +2025-04-19 06:50:51,078 INFO Epoch:39 train_loss:0.91194 +2025-04-19 06:51:00,384 INFO Epoch:39 val_res:0.603581 +2025-04-19 06:51:26,043 INFO Epoch:40 train_loss:0.91345 +2025-04-19 06:51:35,844 INFO Epoch:40 val_res:0.601023 +2025-04-19 06:51:59,273 INFO Epoch:41 train_loss:0.89999 +2025-04-19 06:52:08,545 INFO Epoch:41 val_res:0.603581 +2025-04-19 06:52:32,470 INFO Epoch:42 train_loss:0.88086 +2025-04-19 06:52:41,797 INFO Epoch:42 val_res:0.595908 +2025-04-19 06:53:05,579 INFO Epoch:43 train_loss:0.88301 +2025-04-19 06:53:15,569 INFO Epoch:43 val_res:0.603581 +2025-04-19 06:53:40,550 INFO Epoch:44 train_loss:0.90119 +2025-04-19 06:53:50,051 INFO Epoch:44 val_res:0.585678 +2025-04-19 06:54:15,454 INFO Epoch:45 train_loss:0.87934 +2025-04-19 06:54:25,376 INFO Epoch:45 val_res:0.593350 +2025-04-19 06:54:51,101 INFO Epoch:46 train_loss:0.87032 +2025-04-19 06:54:59,053 INFO Epoch:46 val_res:0.595908 +2025-04-19 06:55:23,802 INFO Epoch:47 train_loss:0.86929 +2025-04-19 06:55:34,268 INFO Epoch:47 val_res:0.595908 +2025-04-19 06:55:58,418 INFO Epoch:48 train_loss:0.86531 +2025-04-19 06:56:08,280 INFO Epoch:48 val_res:0.598466 +2025-04-19 06:56:30,956 INFO Epoch:49 train_loss:0.84910 +2025-04-19 06:56:40,843 INFO Epoch:49 val_res:0.595908 +2025-04-19 06:57:06,215 INFO Epoch:50 train_loss:0.85603 +2025-04-19 06:57:15,678 INFO Epoch:50 val_res:0.588235 +2025-04-19 06:57:42,527 INFO Epoch:51 train_loss:0.87060 +2025-04-19 06:57:51,734 INFO Epoch:51 val_res:0.588235 +2025-04-19 06:58:15,573 INFO Epoch:52 train_loss:0.84394 +2025-04-19 06:58:25,642 INFO Epoch:52 val_res:0.588235 +2025-04-19 06:58:50,882 INFO Epoch:53 train_loss:0.84886 +2025-04-19 06:59:01,183 INFO Epoch:53 val_res:0.590793 +2025-04-19 06:59:26,477 INFO Epoch:54 train_loss:0.83513 +2025-04-19 06:59:36,892 INFO Epoch:54 val_res:0.588235 +2025-04-19 07:00:03,728 INFO Epoch:55 train_loss:0.82280 +2025-04-19 07:00:13,386 INFO Epoch:55 val_res:0.590793 +2025-04-19 07:00:38,866 INFO Epoch:56 train_loss:0.83593 +2025-04-19 07:00:48,895 INFO Epoch:56 val_res:0.598466 +2025-04-19 07:01:14,183 INFO Epoch:57 train_loss:0.82257 +2025-04-19 07:01:24,494 INFO Epoch:57 val_res:0.598466 +2025-04-19 07:01:49,940 INFO Epoch:58 train_loss:0.81759 +2025-04-19 07:01:58,130 INFO Epoch:58 val_res:0.601023 +2025-04-19 07:02:23,417 INFO Epoch:59 train_loss:0.81637 +2025-04-19 07:02:33,276 INFO Epoch:59 val_res:0.598466 +2025-04-19 07:02:59,402 INFO Epoch:60 train_loss:0.80930 +2025-04-19 07:03:09,009 INFO Epoch:60 val_res:0.595908 +2025-04-19 07:03:32,564 INFO Epoch:61 train_loss:0.79513 +2025-04-19 07:03:42,385 INFO Epoch:61 val_res:0.593350 +2025-04-19 07:04:07,873 INFO Epoch:62 train_loss:0.80163 +2025-04-19 07:04:18,108 INFO Epoch:62 val_res:0.611253 +2025-04-19 07:04:18,109 INFO Saving best model at Epoch 62 +2025-04-19 07:04:44,805 INFO Epoch:63 train_loss:0.79376 +2025-04-19 07:04:54,688 INFO Epoch:63 val_res:0.603581 +2025-04-19 07:05:18,118 INFO Epoch:64 train_loss:0.77790 +2025-04-19 07:05:27,655 INFO Epoch:64 val_res:0.611253 +2025-04-19 07:05:52,250 INFO Epoch:65 train_loss:0.78912 +2025-04-19 07:06:01,885 INFO Epoch:65 val_res:0.590793 +2025-04-19 07:06:24,610 INFO Epoch:66 train_loss:0.78291 +2025-04-19 07:06:34,209 INFO Epoch:66 val_res:0.611253 +2025-04-19 07:06:57,346 INFO Epoch:67 train_loss:0.76917 +2025-04-19 07:07:07,344 INFO Epoch:67 val_res:0.616368 +2025-04-19 07:07:07,344 INFO Saving best model at Epoch 67 +2025-04-19 07:07:34,416 INFO Epoch:68 train_loss:0.77430 +2025-04-19 07:07:44,622 INFO Epoch:68 val_res:0.608696 +2025-04-19 07:08:08,002 INFO Epoch:69 train_loss:0.77168 +2025-04-19 07:08:17,451 INFO Epoch:69 val_res:0.616368 +2025-04-19 07:08:44,178 INFO Epoch:70 train_loss:0.76969 +2025-04-19 07:08:54,078 INFO Epoch:70 val_res:0.616368 +2025-04-19 07:09:19,537 INFO Epoch:71 train_loss:0.76282 +2025-04-19 07:09:29,878 INFO Epoch:71 val_res:0.611253 +2025-04-19 07:09:55,249 INFO Epoch:72 train_loss:0.76299 +2025-04-19 07:10:04,911 INFO Epoch:72 val_res:0.618926 +2025-04-19 07:10:04,915 INFO Saving best model at Epoch 72 +2025-04-19 07:10:29,756 INFO Epoch:73 train_loss:0.73843 +2025-04-19 07:10:39,161 INFO Epoch:73 val_res:0.616368 +2025-04-19 07:11:03,929 INFO Epoch:74 train_loss:0.75582 +2025-04-19 07:11:13,364 INFO Epoch:74 val_res:0.613811 +2025-04-19 07:11:37,982 INFO Epoch:75 train_loss:0.74723 +2025-04-19 07:11:48,363 INFO Epoch:75 val_res:0.618926 +2025-04-19 07:12:14,206 INFO Epoch:76 train_loss:0.74862 +2025-04-19 07:12:23,822 INFO Epoch:76 val_res:0.608696 +2025-04-19 07:12:47,393 INFO Epoch:77 train_loss:0.74423 +2025-04-19 07:12:56,868 INFO Epoch:77 val_res:0.613811 +2025-04-19 07:13:21,519 INFO Epoch:78 train_loss:0.74976 +2025-04-19 07:13:30,379 INFO Epoch:78 val_res:0.608696 +2025-04-19 07:13:52,299 INFO Epoch:79 train_loss:0.75697 +2025-04-19 07:14:00,567 INFO Epoch:79 val_res:0.618926 +2025-04-19 07:14:25,873 INFO Epoch:80 train_loss:0.74760 +2025-04-19 07:14:34,191 INFO Epoch:80 val_res:0.616368 +2025-04-19 07:14:57,626 INFO Epoch:81 train_loss:0.72786 +2025-04-19 07:15:06,048 INFO Epoch:81 val_res:0.611253 +2025-04-19 07:15:30,182 INFO Epoch:82 train_loss:0.73431 +2025-04-19 07:15:39,272 INFO Epoch:82 val_res:0.613811 +2025-04-19 07:16:03,206 INFO Epoch:83 train_loss:0.73968 +2025-04-19 07:16:12,381 INFO Epoch:83 val_res:0.611253 +2025-04-19 07:16:38,276 INFO Epoch:84 train_loss:0.72041 +2025-04-19 07:16:47,185 INFO Epoch:84 val_res:0.608696 +2025-04-19 07:17:11,032 INFO Epoch:85 train_loss:0.71967 +2025-04-19 07:17:19,252 INFO Epoch:85 val_res:0.608696 +2025-04-19 07:17:43,802 INFO Epoch:86 train_loss:0.72109 +2025-04-19 07:17:52,775 INFO Epoch:86 val_res:0.611253 +2025-04-19 07:18:17,663 INFO Epoch:87 train_loss:0.72062 +2025-04-19 07:18:26,378 INFO Epoch:87 val_res:0.611253 +2025-04-19 07:18:50,553 INFO Epoch:88 train_loss:0.72032 +2025-04-19 07:19:00,805 INFO Epoch:88 val_res:0.603581 +2025-04-19 07:19:26,943 INFO Epoch:89 train_loss:0.71547 +2025-04-19 07:19:36,376 INFO Epoch:89 val_res:0.611253 +2025-04-19 07:20:01,393 INFO Epoch:90 train_loss:0.71745 +2025-04-19 07:20:10,609 INFO Epoch:90 val_res:0.611253 +2025-04-19 07:20:35,409 INFO Epoch:91 train_loss:0.71683 +2025-04-19 07:20:44,675 INFO Epoch:91 val_res:0.608696 +2025-04-19 07:21:08,581 INFO Epoch:92 train_loss:0.72381 +2025-04-19 07:21:17,672 INFO Epoch:92 val_res:0.613811 +2025-04-19 07:21:42,679 INFO Epoch:93 train_loss:0.71326 +2025-04-19 07:21:51,389 INFO Epoch:93 val_res:0.616368 +2025-04-19 07:22:16,601 INFO Epoch:94 train_loss:0.70276 +2025-04-19 07:22:25,754 INFO Epoch:94 val_res:0.618926 +2025-04-19 07:22:50,436 INFO Epoch:95 train_loss:0.71010 +2025-04-19 07:23:00,343 INFO Epoch:95 val_res:0.611253 +2025-04-19 07:23:26,028 INFO Epoch:96 train_loss:0.69572 +2025-04-19 07:23:35,572 INFO Epoch:96 val_res:0.613811 +2025-04-19 07:24:00,818 INFO Epoch:97 train_loss:0.69438 +2025-04-19 07:24:09,503 INFO Epoch:97 val_res:0.611253 +2025-04-19 07:24:34,501 INFO Epoch:98 train_loss:0.70946 +2025-04-19 07:24:44,504 INFO Epoch:98 val_res:0.611253 +2025-04-19 07:25:10,567 INFO Epoch:99 train_loss:0.70041 +2025-04-19 07:25:20,875 INFO Epoch:99 val_res:0.601023 +2025-04-19 07:25:21,161 INFO ===================================== +2025-04-19 07:25:21,162 INFO Start testing... +2025-04-19 07:25:21,162 INFO ===================================== +2025-04-19 07:25:32,775 INFO Incremental step 3 Testing res: 0.543147 +2025-04-19 07:25:32,776 INFO forgetting: 0.172017 +2025-04-19 07:25:32,777 INFO Average Accuracy: 0.628596 +2025-04-19 07:25:32,777 INFO Average Forgetting: 0.258687 diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..abd6f268f22aefae7e7798989e365c341620f454 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..a500662c270967ef54a86b7c51d5dee2a72f8a18 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..fa7f8a1cdc42bebc15bf24ac0033b95ea2681c5a Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..d6ccdc9e064ff27252d7df729871c77a315cd7e1 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..61702b495a3747280307278de969676eab319daf Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..34b0bf4b339608920b9726be4bfa315e1711cc71 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..137a63266922e78ce082e46ebd050aac1675afd8 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..8d5f582813cb4a77c0e15e20774c18ac1d83bb55 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f3d4b44837cac7c2ef89c868d65441d10fc5fde7 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7849d82134f11ba8fb20bd0ef99efcd2d5f7deb6a0f531ee2017afa3299d8e +size 114115345 diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ad9f19cbc1c70f362637e1f5e3e928fd4b6df7d4 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0737af443e1b24d6e89a24d415e19cb1bd1bc9de47057c5811266c43488913b6 +size 114179921 diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..4f4bb1f2c1af7f72ec0d12efaf983494ec8590ac --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:982637edb3b31decaa47fb8d051f6834c874b6f859c94e35fb05f1285d3cf304 +size 114244625 diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f145c48732424f17ffed3ba19d25e94bc11948e1 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:390c6999635a15ef85ffed77a629c1456d67f53d74dd70a079fabb146564048f +size 114309137 diff --git a/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/train.log b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..0c777b1a77f87b5b37752c3dae609ca551ffbeb1 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/AVE/audio-visual/use-inverse_True-seed_0/train.log @@ -0,0 +1,887 @@ +2025-04-19 03:46:47,996 INFO Training start time: 2025-04-19 03:46:47.996448 +2025-04-19 04:06:48,303 INFO Incremental step: 0 +2025-04-19 04:07:08,747 INFO Epoch:0 train_loss:2.26734 +2025-04-19 04:07:13,887 INFO Epoch:0 val_res:0.257143 +2025-04-19 04:07:13,887 INFO Saving best model at Epoch 0 +2025-04-19 04:07:28,538 INFO Epoch:1 train_loss:1.55042 +2025-04-19 04:07:34,118 INFO Epoch:1 val_res:0.466667 +2025-04-19 04:07:34,118 INFO Saving best model at Epoch 1 +2025-04-19 04:07:47,258 INFO Epoch:2 train_loss:1.27226 +2025-04-19 04:07:52,653 INFO Epoch:2 val_res:0.628571 +2025-04-19 04:07:52,654 INFO Saving best model at Epoch 2 +2025-04-19 04:08:05,389 INFO Epoch:3 train_loss:1.00044 +2025-04-19 04:08:10,437 INFO Epoch:3 val_res:0.552381 +2025-04-19 04:08:20,081 INFO Epoch:4 train_loss:0.93713 +2025-04-19 04:08:25,658 INFO Epoch:4 val_res:0.742857 +2025-04-19 04:08:25,658 INFO Saving best model at Epoch 4 +2025-04-19 04:08:40,355 INFO Epoch:5 train_loss:0.77391 +2025-04-19 04:08:45,283 INFO Epoch:5 val_res:0.685714 +2025-04-19 04:08:55,310 INFO Epoch:6 train_loss:0.73917 +2025-04-19 04:09:00,381 INFO Epoch:6 val_res:0.723810 +2025-04-19 04:09:10,324 INFO Epoch:7 train_loss:0.65520 +2025-04-19 04:09:15,878 INFO Epoch:7 val_res:0.761905 +2025-04-19 04:09:15,878 INFO Saving best model at Epoch 7 +2025-04-19 04:09:28,934 INFO Epoch:8 train_loss:0.61123 +2025-04-19 04:09:34,580 INFO Epoch:8 val_res:0.742857 +2025-04-19 04:09:45,145 INFO Epoch:9 train_loss:0.59487 +2025-04-19 04:09:50,757 INFO Epoch:9 val_res:0.790476 +2025-04-19 04:09:50,758 INFO Saving best model at Epoch 9 +2025-04-19 04:10:05,267 INFO Epoch:10 train_loss:0.52868 +2025-04-19 04:10:10,828 INFO Epoch:10 val_res:0.771429 +2025-04-19 04:10:20,910 INFO Epoch:11 train_loss:0.48344 +2025-04-19 04:10:26,695 INFO Epoch:11 val_res:0.800000 +2025-04-19 04:10:26,695 INFO Saving best model at Epoch 11 +2025-04-19 04:10:40,348 INFO Epoch:12 train_loss:0.46746 +2025-04-19 04:10:45,685 INFO Epoch:12 val_res:0.800000 +2025-04-19 04:10:56,214 INFO Epoch:13 train_loss:0.43783 +2025-04-19 04:11:01,553 INFO Epoch:13 val_res:0.790476 +2025-04-19 04:11:12,310 INFO Epoch:14 train_loss:0.39908 +2025-04-19 04:11:17,524 INFO Epoch:14 val_res:0.800000 +2025-04-19 04:11:28,069 INFO Epoch:15 train_loss:0.37672 +2025-04-19 04:11:33,461 INFO Epoch:15 val_res:0.819048 +2025-04-19 04:11:33,462 INFO Saving best model at Epoch 15 +2025-04-19 04:11:46,676 INFO Epoch:16 train_loss:0.35163 +2025-04-19 04:11:51,634 INFO Epoch:16 val_res:0.828571 +2025-04-19 04:11:51,635 INFO Saving best model at Epoch 16 +2025-04-19 04:12:04,733 INFO Epoch:17 train_loss:0.33205 +2025-04-19 04:12:09,817 INFO Epoch:17 val_res:0.819048 +2025-04-19 04:12:20,615 INFO Epoch:18 train_loss:0.30715 +2025-04-19 04:12:25,992 INFO Epoch:18 val_res:0.828571 +2025-04-19 04:12:36,614 INFO Epoch:19 train_loss:0.29065 +2025-04-19 04:12:41,629 INFO Epoch:19 val_res:0.809524 +2025-04-19 04:12:51,806 INFO Epoch:20 train_loss:3.79693 +2025-04-19 04:12:57,283 INFO Epoch:20 val_res:0.809524 +2025-04-19 04:13:08,378 INFO Epoch:21 train_loss:2.94520 +2025-04-19 04:13:13,927 INFO Epoch:21 val_res:0.828571 +2025-04-19 04:13:23,620 INFO Epoch:22 train_loss:2.46709 +2025-04-19 04:13:28,719 INFO Epoch:22 val_res:0.819048 +2025-04-19 04:13:38,534 INFO Epoch:23 train_loss:2.14747 +2025-04-19 04:13:43,603 INFO Epoch:23 val_res:0.838095 +2025-04-19 04:13:43,604 INFO Saving best model at Epoch 23 +2025-04-19 04:13:55,797 INFO Epoch:24 train_loss:1.91502 +2025-04-19 04:14:02,119 INFO Epoch:24 val_res:0.809524 +2025-04-19 04:14:13,123 INFO Epoch:25 train_loss:1.75515 +2025-04-19 04:14:18,766 INFO Epoch:25 val_res:0.828571 +2025-04-19 04:14:29,637 INFO Epoch:26 train_loss:1.62385 +2025-04-19 04:14:35,144 INFO Epoch:26 val_res:0.828571 +2025-04-19 04:14:45,348 INFO Epoch:27 train_loss:1.51604 +2025-04-19 04:14:50,529 INFO Epoch:27 val_res:0.838095 +2025-04-19 04:15:01,151 INFO Epoch:28 train_loss:1.39799 +2025-04-19 04:15:06,624 INFO Epoch:28 val_res:0.809524 +2025-04-19 04:15:18,271 INFO Epoch:29 train_loss:1.31817 +2025-04-19 04:15:23,878 INFO Epoch:29 val_res:0.819048 +2025-04-19 04:15:34,430 INFO Epoch:30 train_loss:1.24146 +2025-04-19 04:15:40,377 INFO Epoch:30 val_res:0.790476 +2025-04-19 04:15:50,999 INFO Epoch:31 train_loss:1.16538 +2025-04-19 04:15:56,204 INFO Epoch:31 val_res:0.828571 +2025-04-19 04:16:07,029 INFO Epoch:32 train_loss:1.09802 +2025-04-19 04:16:12,182 INFO Epoch:32 val_res:0.819048 +2025-04-19 04:16:22,909 INFO Epoch:33 train_loss:1.05402 +2025-04-19 04:16:28,539 INFO Epoch:33 val_res:0.838095 +2025-04-19 04:16:38,841 INFO Epoch:34 train_loss:1.01221 +2025-04-19 04:16:44,435 INFO Epoch:34 val_res:0.847619 +2025-04-19 04:16:44,435 INFO Saving best model at Epoch 34 +2025-04-19 04:16:56,652 INFO Epoch:35 train_loss:0.93402 +2025-04-19 04:17:01,888 INFO Epoch:35 val_res:0.819048 +2025-04-19 04:17:12,807 INFO Epoch:36 train_loss:0.93534 +2025-04-19 04:17:18,112 INFO Epoch:36 val_res:0.819048 +2025-04-19 04:17:28,842 INFO Epoch:37 train_loss:0.89730 +2025-04-19 04:17:34,450 INFO Epoch:37 val_res:0.828571 +2025-04-19 04:17:45,315 INFO Epoch:38 train_loss:0.82406 +2025-04-19 04:17:50,853 INFO Epoch:38 val_res:0.828571 +2025-04-19 04:18:00,725 INFO Epoch:39 train_loss:0.78561 +2025-04-19 04:18:06,140 INFO Epoch:39 val_res:0.838095 +2025-04-19 04:18:17,102 INFO Epoch:40 train_loss:0.76146 +2025-04-19 04:18:22,695 INFO Epoch:40 val_res:0.819048 +2025-04-19 04:18:33,653 INFO Epoch:41 train_loss:0.78214 +2025-04-19 04:18:39,165 INFO Epoch:41 val_res:0.828571 +2025-04-19 04:18:49,910 INFO Epoch:42 train_loss:0.74212 +2025-04-19 04:18:55,213 INFO Epoch:42 val_res:0.847619 +2025-04-19 04:19:06,179 INFO Epoch:43 train_loss:0.70217 +2025-04-19 04:19:11,661 INFO Epoch:43 val_res:0.838095 +2025-04-19 04:19:22,533 INFO Epoch:44 train_loss:0.68877 +2025-04-19 04:19:28,390 INFO Epoch:44 val_res:0.819048 +2025-04-19 04:19:39,389 INFO Epoch:45 train_loss:0.67994 +2025-04-19 04:19:44,409 INFO Epoch:45 val_res:0.847619 +2025-04-19 04:19:54,440 INFO Epoch:46 train_loss:0.67110 +2025-04-19 04:19:59,604 INFO Epoch:46 val_res:0.838095 +2025-04-19 04:20:09,616 INFO Epoch:47 train_loss:0.64953 +2025-04-19 04:20:15,052 INFO Epoch:47 val_res:0.838095 +2025-04-19 04:20:25,272 INFO Epoch:48 train_loss:0.60742 +2025-04-19 04:20:30,506 INFO Epoch:48 val_res:0.838095 +2025-04-19 04:20:41,324 INFO Epoch:49 train_loss:0.60751 +2025-04-19 04:20:46,399 INFO Epoch:49 val_res:0.838095 +2025-04-19 04:20:56,627 INFO Epoch:50 train_loss:0.61256 +2025-04-19 04:21:01,651 INFO Epoch:50 val_res:0.819048 +2025-04-19 04:21:13,096 INFO Epoch:51 train_loss:0.58607 +2025-04-19 04:21:18,011 INFO Epoch:51 val_res:0.847619 +2025-04-19 04:21:29,113 INFO Epoch:52 train_loss:0.57453 +2025-04-19 04:21:34,093 INFO Epoch:52 val_res:0.838095 +2025-04-19 04:21:45,126 INFO Epoch:53 train_loss:0.57961 +2025-04-19 04:21:50,328 INFO Epoch:53 val_res:0.819048 +2025-04-19 04:22:02,012 INFO Epoch:54 train_loss:0.56763 +2025-04-19 04:22:07,164 INFO Epoch:54 val_res:0.847619 +2025-04-19 04:22:18,207 INFO Epoch:55 train_loss:0.55811 +2025-04-19 04:22:23,208 INFO Epoch:55 val_res:0.828571 +2025-04-19 04:22:33,828 INFO Epoch:56 train_loss:0.53534 +2025-04-19 04:22:38,916 INFO Epoch:56 val_res:0.838095 +2025-04-19 04:22:49,695 INFO Epoch:57 train_loss:0.52837 +2025-04-19 04:22:54,972 INFO Epoch:57 val_res:0.828571 +2025-04-19 04:23:05,425 INFO Epoch:58 train_loss:0.52854 +2025-04-19 04:23:10,550 INFO Epoch:58 val_res:0.838095 +2025-04-19 04:23:21,537 INFO Epoch:59 train_loss:0.51832 +2025-04-19 04:23:26,723 INFO Epoch:59 val_res:0.838095 +2025-04-19 04:23:37,108 INFO Epoch:60 train_loss:0.51716 +2025-04-19 04:23:42,250 INFO Epoch:60 val_res:0.847619 +2025-04-19 04:23:53,019 INFO Epoch:61 train_loss:0.49917 +2025-04-19 04:23:58,072 INFO Epoch:61 val_res:0.828571 +2025-04-19 04:24:08,699 INFO Epoch:62 train_loss:0.49262 +2025-04-19 04:24:13,720 INFO Epoch:62 val_res:0.838095 +2025-04-19 04:24:23,823 INFO Epoch:63 train_loss:0.50105 +2025-04-19 04:24:28,935 INFO Epoch:63 val_res:0.828571 +2025-04-19 04:24:39,423 INFO Epoch:64 train_loss:0.50378 +2025-04-19 04:24:44,432 INFO Epoch:64 val_res:0.838095 +2025-04-19 04:24:54,716 INFO Epoch:65 train_loss:0.51097 +2025-04-19 04:24:59,814 INFO Epoch:65 val_res:0.828571 +2025-04-19 04:25:09,787 INFO Epoch:66 train_loss:0.49226 +2025-04-19 04:25:14,834 INFO Epoch:66 val_res:0.847619 +2025-04-19 04:25:26,258 INFO Epoch:67 train_loss:0.47109 +2025-04-19 04:25:32,072 INFO Epoch:67 val_res:0.819048 +2025-04-19 04:25:42,770 INFO Epoch:68 train_loss:0.46243 +2025-04-19 04:25:47,973 INFO Epoch:68 val_res:0.838095 +2025-04-19 04:25:58,485 INFO Epoch:69 train_loss:0.51031 +2025-04-19 04:26:03,634 INFO Epoch:69 val_res:0.819048 +2025-04-19 04:26:14,546 INFO Epoch:70 train_loss:0.49166 +2025-04-19 04:26:19,974 INFO Epoch:70 val_res:0.828571 +2025-04-19 04:26:31,682 INFO Epoch:71 train_loss:0.00972 +2025-04-19 04:26:36,939 INFO Epoch:71 val_res:0.828571 +2025-04-19 04:26:48,316 INFO Epoch:72 train_loss:0.00872 +2025-04-19 04:26:53,782 INFO Epoch:72 val_res:0.828571 +2025-04-19 04:27:04,611 INFO Epoch:73 train_loss:0.00836 +2025-04-19 04:27:10,296 INFO Epoch:73 val_res:0.828571 +2025-04-19 04:27:21,426 INFO Epoch:74 train_loss:0.00917 +2025-04-19 04:27:26,675 INFO Epoch:74 val_res:0.838095 +2025-04-19 04:27:37,707 INFO Epoch:75 train_loss:0.00781 +2025-04-19 04:27:42,881 INFO Epoch:75 val_res:0.828571 +2025-04-19 04:27:53,371 INFO Epoch:76 train_loss:0.00787 +2025-04-19 04:27:58,622 INFO Epoch:76 val_res:0.838095 +2025-04-19 04:28:10,254 INFO Epoch:77 train_loss:0.00785 +2025-04-19 04:28:15,242 INFO Epoch:77 val_res:0.838095 +2025-04-19 04:28:26,785 INFO Epoch:78 train_loss:0.00769 +2025-04-19 04:28:32,071 INFO Epoch:78 val_res:0.838095 +2025-04-19 04:28:43,123 INFO Epoch:79 train_loss:0.00782 +2025-04-19 04:28:49,613 INFO Epoch:79 val_res:0.838095 +2025-04-19 04:29:00,075 INFO Epoch:80 train_loss:0.00715 +2025-04-19 04:29:05,488 INFO Epoch:80 val_res:0.838095 +2025-04-19 04:29:16,026 INFO Epoch:81 train_loss:0.00756 +2025-04-19 04:29:21,437 INFO Epoch:81 val_res:0.838095 +2025-04-19 04:29:32,422 INFO Epoch:82 train_loss:0.00757 +2025-04-19 04:29:37,454 INFO Epoch:82 val_res:0.828571 +2025-04-19 04:29:49,752 INFO Epoch:83 train_loss:0.00754 +2025-04-19 04:29:54,925 INFO Epoch:83 val_res:0.838095 +2025-04-19 04:30:06,209 INFO Epoch:84 train_loss:0.00745 +2025-04-19 04:30:12,176 INFO Epoch:84 val_res:0.838095 +2025-04-19 04:30:23,724 INFO Epoch:85 train_loss:0.00770 +2025-04-19 04:30:29,060 INFO Epoch:85 val_res:0.838095 +2025-04-19 04:30:40,604 INFO Epoch:86 train_loss:0.00732 +2025-04-19 04:30:45,873 INFO Epoch:86 val_res:0.838095 +2025-04-19 04:30:57,785 INFO Epoch:87 train_loss:0.00725 +2025-04-19 04:31:03,474 INFO Epoch:87 val_res:0.838095 +2025-04-19 04:31:15,113 INFO Epoch:88 train_loss:0.00752 +2025-04-19 04:31:21,014 INFO Epoch:88 val_res:0.838095 +2025-04-19 04:31:32,310 INFO Epoch:89 train_loss:0.00765 +2025-04-19 04:31:37,648 INFO Epoch:89 val_res:0.838095 +2025-04-19 04:31:50,094 INFO Epoch:90 train_loss:0.00762 +2025-04-19 04:31:55,928 INFO Epoch:90 val_res:0.838095 +2025-04-19 04:32:07,621 INFO Epoch:91 train_loss:0.00743 +2025-04-19 04:32:13,743 INFO Epoch:91 val_res:0.838095 +2025-04-19 04:32:26,356 INFO Epoch:92 train_loss:0.00752 +2025-04-19 04:32:31,632 INFO Epoch:92 val_res:0.838095 +2025-04-19 04:32:42,745 INFO Epoch:93 train_loss:0.00732 +2025-04-19 04:32:50,442 INFO Epoch:93 val_res:0.838095 +2025-04-19 04:33:02,395 INFO Epoch:94 train_loss:0.00772 +2025-04-19 04:33:07,974 INFO Epoch:94 val_res:0.838095 +2025-04-19 04:33:19,472 INFO Epoch:95 train_loss:0.00742 +2025-04-19 04:33:25,249 INFO Epoch:95 val_res:0.838095 +2025-04-19 04:33:38,058 INFO Epoch:96 train_loss:0.00732 +2025-04-19 04:33:44,057 INFO Epoch:96 val_res:0.838095 +2025-04-19 04:33:56,647 INFO Epoch:97 train_loss:0.00742 +2025-04-19 04:34:02,249 INFO Epoch:97 val_res:0.838095 +2025-04-19 04:34:13,399 INFO Epoch:98 train_loss:0.00767 +2025-04-19 04:34:20,679 INFO Epoch:98 val_res:0.838095 +2025-04-19 04:34:33,479 INFO Epoch:99 train_loss:0.00734 +2025-04-19 04:34:39,276 INFO Epoch:99 val_res:0.838095 +2025-04-19 04:34:39,582 INFO ===================================== +2025-04-19 04:34:39,583 INFO Start testing... +2025-04-19 04:34:39,587 INFO ===================================== +2025-04-19 04:34:46,335 INFO Incremental step 0 Testing res: 0.750000 +2025-04-19 04:34:46,338 INFO Incremental step: 1 +2025-04-19 04:35:15,096 INFO Epoch:0 train_loss:2.87483 +2025-04-19 04:35:21,358 INFO Epoch:0 val_res:0.389671 +2025-04-19 04:35:21,359 INFO Saving best model at Epoch 0 +2025-04-19 04:35:47,912 INFO Epoch:1 train_loss:2.39633 +2025-04-19 04:35:54,650 INFO Epoch:1 val_res:0.436620 +2025-04-19 04:35:54,651 INFO Saving best model at Epoch 1 +2025-04-19 04:36:18,978 INFO Epoch:2 train_loss:1.95989 +2025-04-19 04:36:25,118 INFO Epoch:2 val_res:0.460094 +2025-04-19 04:36:25,118 INFO Saving best model at Epoch 2 +2025-04-19 04:36:50,479 INFO Epoch:3 train_loss:1.86984 +2025-04-19 04:36:56,627 INFO Epoch:3 val_res:0.488263 +2025-04-19 04:36:56,627 INFO Saving best model at Epoch 3 +2025-04-19 04:37:21,524 INFO Epoch:4 train_loss:1.68535 +2025-04-19 04:37:28,110 INFO Epoch:4 val_res:0.525822 +2025-04-19 04:37:28,110 INFO Saving best model at Epoch 4 +2025-04-19 04:37:53,494 INFO Epoch:5 train_loss:1.58863 +2025-04-19 04:37:59,781 INFO Epoch:5 val_res:0.530516 +2025-04-19 04:37:59,781 INFO Saving best model at Epoch 5 +2025-04-19 04:38:23,634 INFO Epoch:6 train_loss:1.54333 +2025-04-19 04:38:30,029 INFO Epoch:6 val_res:0.535211 +2025-04-19 04:38:30,029 INFO Saving best model at Epoch 6 +2025-04-19 04:38:55,240 INFO Epoch:7 train_loss:1.46010 +2025-04-19 04:39:01,866 INFO Epoch:7 val_res:0.582160 +2025-04-19 04:39:01,866 INFO Saving best model at Epoch 7 +2025-04-19 04:39:26,776 INFO Epoch:8 train_loss:1.41578 +2025-04-19 04:39:32,868 INFO Epoch:8 val_res:0.535211 +2025-04-19 04:39:56,515 INFO Epoch:9 train_loss:1.38986 +2025-04-19 04:40:02,778 INFO Epoch:9 val_res:0.600939 +2025-04-19 04:40:02,779 INFO Saving best model at Epoch 9 +2025-04-19 04:40:27,988 INFO Epoch:10 train_loss:1.34461 +2025-04-19 04:40:34,150 INFO Epoch:10 val_res:0.596244 +2025-04-19 04:40:56,821 INFO Epoch:11 train_loss:1.32072 +2025-04-19 04:41:03,125 INFO Epoch:11 val_res:0.558685 +2025-04-19 04:41:25,455 INFO Epoch:12 train_loss:1.29630 +2025-04-19 04:41:31,487 INFO Epoch:12 val_res:0.600939 +2025-04-19 04:41:54,257 INFO Epoch:13 train_loss:1.28104 +2025-04-19 04:42:00,698 INFO Epoch:13 val_res:0.596244 +2025-04-19 04:42:22,235 INFO Epoch:14 train_loss:1.25902 +2025-04-19 04:42:28,251 INFO Epoch:14 val_res:0.591549 +2025-04-19 04:42:51,437 INFO Epoch:15 train_loss:1.24175 +2025-04-19 04:42:57,647 INFO Epoch:15 val_res:0.596244 +2025-04-19 04:43:20,579 INFO Epoch:16 train_loss:1.21354 +2025-04-19 04:43:27,419 INFO Epoch:16 val_res:0.629108 +2025-04-19 04:43:27,419 INFO Saving best model at Epoch 16 +2025-04-19 04:43:50,893 INFO Epoch:17 train_loss:1.20840 +2025-04-19 04:43:56,933 INFO Epoch:17 val_res:0.624413 +2025-04-19 04:44:18,877 INFO Epoch:18 train_loss:1.19920 +2025-04-19 04:44:25,017 INFO Epoch:18 val_res:0.624413 +2025-04-19 04:44:49,677 INFO Epoch:19 train_loss:1.17863 +2025-04-19 04:44:55,807 INFO Epoch:19 val_res:0.629108 +2025-04-19 04:45:18,640 INFO Epoch:20 train_loss:4.14620 +2025-04-19 04:45:26,138 INFO Epoch:20 val_res:0.624413 +2025-04-19 04:45:50,174 INFO Epoch:21 train_loss:3.51663 +2025-04-19 04:45:56,914 INFO Epoch:21 val_res:0.633803 +2025-04-19 04:45:56,914 INFO Saving best model at Epoch 21 +2025-04-19 04:46:22,724 INFO Epoch:22 train_loss:3.14124 +2025-04-19 04:46:29,575 INFO Epoch:22 val_res:0.600939 +2025-04-19 04:46:52,563 INFO Epoch:23 train_loss:2.91637 +2025-04-19 04:46:59,041 INFO Epoch:23 val_res:0.661972 +2025-04-19 04:46:59,042 INFO Saving best model at Epoch 23 +2025-04-19 04:47:23,662 INFO Epoch:24 train_loss:2.76164 +2025-04-19 04:47:30,290 INFO Epoch:24 val_res:0.647887 +2025-04-19 04:47:54,757 INFO Epoch:25 train_loss:2.58395 +2025-04-19 04:48:01,773 INFO Epoch:25 val_res:0.633803 +2025-04-19 04:48:26,492 INFO Epoch:26 train_loss:2.52894 +2025-04-19 04:48:32,553 INFO Epoch:26 val_res:0.633803 +2025-04-19 04:48:56,127 INFO Epoch:27 train_loss:2.43893 +2025-04-19 04:49:02,863 INFO Epoch:27 val_res:0.647887 +2025-04-19 04:49:28,354 INFO Epoch:28 train_loss:2.33669 +2025-04-19 04:49:34,727 INFO Epoch:28 val_res:0.652582 +2025-04-19 04:49:57,162 INFO Epoch:29 train_loss:2.30900 +2025-04-19 04:50:04,278 INFO Epoch:29 val_res:0.661972 +2025-04-19 04:50:27,738 INFO Epoch:30 train_loss:2.24641 +2025-04-19 04:50:34,473 INFO Epoch:30 val_res:0.643192 +2025-04-19 04:50:59,506 INFO Epoch:31 train_loss:2.17377 +2025-04-19 04:51:07,334 INFO Epoch:31 val_res:0.643192 +2025-04-19 04:51:34,085 INFO Epoch:32 train_loss:2.12466 +2025-04-19 04:51:40,889 INFO Epoch:32 val_res:0.680751 +2025-04-19 04:51:40,889 INFO Saving best model at Epoch 32 +2025-04-19 04:52:07,020 INFO Epoch:33 train_loss:2.08035 +2025-04-19 04:52:14,462 INFO Epoch:33 val_res:0.661972 +2025-04-19 04:52:40,390 INFO Epoch:34 train_loss:2.03085 +2025-04-19 04:52:47,690 INFO Epoch:34 val_res:0.666667 +2025-04-19 04:53:15,651 INFO Epoch:35 train_loss:1.98569 +2025-04-19 04:53:24,168 INFO Epoch:35 val_res:0.666667 +2025-04-19 04:53:52,242 INFO Epoch:36 train_loss:1.95377 +2025-04-19 04:53:59,987 INFO Epoch:36 val_res:0.680751 +2025-04-19 04:54:26,760 INFO Epoch:37 train_loss:1.94824 +2025-04-19 04:54:34,818 INFO Epoch:37 val_res:0.671362 +2025-04-19 04:55:01,922 INFO Epoch:38 train_loss:1.89301 +2025-04-19 04:55:11,206 INFO Epoch:38 val_res:0.676056 +2025-04-19 04:55:37,279 INFO Epoch:39 train_loss:1.85774 +2025-04-19 04:55:46,014 INFO Epoch:39 val_res:0.676056 +2025-04-19 04:56:13,139 INFO Epoch:40 train_loss:1.84213 +2025-04-19 04:56:22,214 INFO Epoch:40 val_res:0.676056 +2025-04-19 04:56:49,523 INFO Epoch:41 train_loss:1.78614 +2025-04-19 04:56:57,697 INFO Epoch:41 val_res:0.676056 +2025-04-19 04:57:25,452 INFO Epoch:42 train_loss:1.77331 +2025-04-19 04:57:33,837 INFO Epoch:42 val_res:0.671362 +2025-04-19 04:57:59,451 INFO Epoch:43 train_loss:1.76765 +2025-04-19 04:58:07,933 INFO Epoch:43 val_res:0.671362 +2025-04-19 04:58:34,755 INFO Epoch:44 train_loss:1.72641 +2025-04-19 04:58:41,576 INFO Epoch:44 val_res:0.680751 +2025-04-19 04:59:08,068 INFO Epoch:45 train_loss:1.70095 +2025-04-19 04:59:16,436 INFO Epoch:45 val_res:0.676056 +2025-04-19 04:59:43,843 INFO Epoch:46 train_loss:1.68687 +2025-04-19 04:59:51,612 INFO Epoch:46 val_res:0.685446 +2025-04-19 04:59:51,613 INFO Saving best model at Epoch 46 +2025-04-19 05:00:19,132 INFO Epoch:47 train_loss:1.67373 +2025-04-19 05:00:26,781 INFO Epoch:47 val_res:0.671362 +2025-04-19 05:00:51,364 INFO Epoch:48 train_loss:1.66818 +2025-04-19 05:00:58,933 INFO Epoch:48 val_res:0.694836 +2025-04-19 05:00:58,933 INFO Saving best model at Epoch 48 +2025-04-19 05:01:25,235 INFO Epoch:49 train_loss:1.64828 +2025-04-19 05:01:32,837 INFO Epoch:49 val_res:0.676056 +2025-04-19 05:02:00,363 INFO Epoch:50 train_loss:1.63065 +2025-04-19 05:02:08,366 INFO Epoch:50 val_res:0.676056 +2025-04-19 05:02:35,454 INFO Epoch:51 train_loss:1.59248 +2025-04-19 05:02:43,317 INFO Epoch:51 val_res:0.680751 +2025-04-19 05:03:12,091 INFO Epoch:52 train_loss:1.55614 +2025-04-19 05:03:20,183 INFO Epoch:52 val_res:0.680751 +2025-04-19 05:03:48,822 INFO Epoch:53 train_loss:1.59285 +2025-04-19 05:03:57,975 INFO Epoch:53 val_res:0.676056 +2025-04-19 05:04:28,483 INFO Epoch:54 train_loss:1.57395 +2025-04-19 05:04:36,614 INFO Epoch:54 val_res:0.671362 +2025-04-19 05:05:07,382 INFO Epoch:55 train_loss:1.51194 +2025-04-19 05:05:15,884 INFO Epoch:55 val_res:0.694836 +2025-04-19 05:05:42,431 INFO Epoch:56 train_loss:1.53082 +2025-04-19 05:05:51,461 INFO Epoch:56 val_res:0.680751 +2025-04-19 05:06:17,296 INFO Epoch:57 train_loss:1.48056 +2025-04-19 05:06:26,622 INFO Epoch:57 val_res:0.690141 +2025-04-19 05:06:56,730 INFO Epoch:58 train_loss:1.50074 +2025-04-19 05:07:04,503 INFO Epoch:58 val_res:0.671362 +2025-04-19 05:07:37,232 INFO Epoch:59 train_loss:1.48600 +2025-04-19 05:07:44,520 INFO Epoch:59 val_res:0.699531 +2025-04-19 05:07:44,520 INFO Saving best model at Epoch 59 +2025-04-19 05:08:10,809 INFO Epoch:60 train_loss:1.45425 +2025-04-19 05:08:18,445 INFO Epoch:60 val_res:0.671362 +2025-04-19 05:08:44,196 INFO Epoch:61 train_loss:1.47900 +2025-04-19 05:08:52,072 INFO Epoch:61 val_res:0.676056 +2025-04-19 05:09:15,987 INFO Epoch:62 train_loss:1.44151 +2025-04-19 05:09:23,252 INFO Epoch:62 val_res:0.680751 +2025-04-19 05:09:48,575 INFO Epoch:63 train_loss:1.44269 +2025-04-19 05:09:56,585 INFO Epoch:63 val_res:0.685446 +2025-04-19 05:10:21,974 INFO Epoch:64 train_loss:1.41194 +2025-04-19 05:10:29,326 INFO Epoch:64 val_res:0.685446 +2025-04-19 05:10:55,048 INFO Epoch:65 train_loss:1.43894 +2025-04-19 05:11:02,521 INFO Epoch:65 val_res:0.685446 +2025-04-19 05:11:29,638 INFO Epoch:66 train_loss:1.40024 +2025-04-19 05:11:37,817 INFO Epoch:66 val_res:0.699531 +2025-04-19 05:12:05,804 INFO Epoch:67 train_loss:1.42546 +2025-04-19 05:12:13,230 INFO Epoch:67 val_res:0.676056 +2025-04-19 05:12:38,019 INFO Epoch:68 train_loss:1.39953 +2025-04-19 05:12:45,180 INFO Epoch:68 val_res:0.666667 +2025-04-19 05:13:12,345 INFO Epoch:69 train_loss:1.39189 +2025-04-19 05:13:20,574 INFO Epoch:69 val_res:0.685446 +2025-04-19 05:13:45,236 INFO Epoch:70 train_loss:1.39271 +2025-04-19 05:13:53,162 INFO Epoch:70 val_res:0.680751 +2025-04-19 05:14:19,624 INFO Epoch:71 train_loss:0.80557 +2025-04-19 05:14:27,049 INFO Epoch:71 val_res:0.704225 +2025-04-19 05:14:27,050 INFO Saving best model at Epoch 71 +2025-04-19 05:14:53,747 INFO Epoch:72 train_loss:0.81508 +2025-04-19 05:15:01,127 INFO Epoch:72 val_res:0.690141 +2025-04-19 05:15:26,987 INFO Epoch:73 train_loss:0.80597 +2025-04-19 05:15:34,690 INFO Epoch:73 val_res:0.671362 +2025-04-19 05:15:59,656 INFO Epoch:74 train_loss:0.80304 +2025-04-19 05:16:07,346 INFO Epoch:74 val_res:0.680751 +2025-04-19 05:16:32,422 INFO Epoch:75 train_loss:0.79044 +2025-04-19 05:16:39,675 INFO Epoch:75 val_res:0.690141 +2025-04-19 05:17:05,036 INFO Epoch:76 train_loss:0.78997 +2025-04-19 05:17:12,392 INFO Epoch:76 val_res:0.699531 +2025-04-19 05:17:37,022 INFO Epoch:77 train_loss:0.78653 +2025-04-19 05:17:44,531 INFO Epoch:77 val_res:0.685446 +2025-04-19 05:18:09,452 INFO Epoch:78 train_loss:0.78914 +2025-04-19 05:18:16,704 INFO Epoch:78 val_res:0.694836 +2025-04-19 05:18:43,190 INFO Epoch:79 train_loss:0.78391 +2025-04-19 05:18:50,674 INFO Epoch:79 val_res:0.699531 +2025-04-19 05:19:17,600 INFO Epoch:80 train_loss:0.78328 +2025-04-19 05:19:25,990 INFO Epoch:80 val_res:0.699531 +2025-04-19 05:19:51,836 INFO Epoch:81 train_loss:0.78094 +2025-04-19 05:19:58,558 INFO Epoch:81 val_res:0.713615 +2025-04-19 05:19:58,558 INFO Saving best model at Epoch 81 +2025-04-19 05:20:25,773 INFO Epoch:82 train_loss:0.77267 +2025-04-19 05:20:34,425 INFO Epoch:82 val_res:0.713615 +2025-04-19 05:20:59,064 INFO Epoch:83 train_loss:0.77942 +2025-04-19 05:21:06,754 INFO Epoch:83 val_res:0.708920 +2025-04-19 05:21:31,695 INFO Epoch:84 train_loss:0.77411 +2025-04-19 05:21:39,528 INFO Epoch:84 val_res:0.713615 +2025-04-19 05:22:05,007 INFO Epoch:85 train_loss:0.77311 +2025-04-19 05:22:12,297 INFO Epoch:85 val_res:0.713615 +2025-04-19 05:22:36,335 INFO Epoch:86 train_loss:0.77014 +2025-04-19 05:22:44,945 INFO Epoch:86 val_res:0.713615 +2025-04-19 05:23:13,038 INFO Epoch:87 train_loss:0.76178 +2025-04-19 05:23:21,162 INFO Epoch:87 val_res:0.708920 +2025-04-19 05:23:47,067 INFO Epoch:88 train_loss:0.76646 +2025-04-19 05:23:54,904 INFO Epoch:88 val_res:0.708920 +2025-04-19 05:24:20,038 INFO Epoch:89 train_loss:0.77530 +2025-04-19 05:24:27,810 INFO Epoch:89 val_res:0.713615 +2025-04-19 05:24:53,812 INFO Epoch:90 train_loss:0.75854 +2025-04-19 05:25:01,204 INFO Epoch:90 val_res:0.718310 +2025-04-19 05:25:01,208 INFO Saving best model at Epoch 90 +2025-04-19 05:25:28,871 INFO Epoch:91 train_loss:0.76200 +2025-04-19 05:25:36,588 INFO Epoch:91 val_res:0.708920 +2025-04-19 05:26:02,493 INFO Epoch:92 train_loss:0.75428 +2025-04-19 05:26:09,845 INFO Epoch:92 val_res:0.704225 +2025-04-19 05:26:36,580 INFO Epoch:93 train_loss:0.74602 +2025-04-19 05:26:44,342 INFO Epoch:93 val_res:0.718310 +2025-04-19 05:27:10,957 INFO Epoch:94 train_loss:0.74831 +2025-04-19 05:27:18,717 INFO Epoch:94 val_res:0.718310 +2025-04-19 05:27:43,834 INFO Epoch:95 train_loss:0.75087 +2025-04-19 05:27:50,454 INFO Epoch:95 val_res:0.708920 +2025-04-19 05:28:15,745 INFO Epoch:96 train_loss:0.74574 +2025-04-19 05:28:23,964 INFO Epoch:96 val_res:0.713615 +2025-04-19 05:28:49,043 INFO Epoch:97 train_loss:0.74794 +2025-04-19 05:28:56,084 INFO Epoch:97 val_res:0.718310 +2025-04-19 05:29:22,076 INFO Epoch:98 train_loss:0.74210 +2025-04-19 05:29:29,449 INFO Epoch:98 val_res:0.723005 +2025-04-19 05:29:29,450 INFO Saving best model at Epoch 98 +2025-04-19 05:29:54,977 INFO Epoch:99 train_loss:0.74070 +2025-04-19 05:30:02,580 INFO Epoch:99 val_res:0.718310 +2025-04-19 05:30:03,114 INFO ===================================== +2025-04-19 05:30:03,115 INFO Start testing... +2025-04-19 05:30:03,116 INFO ===================================== +2025-04-19 05:30:11,451 INFO Incremental step 1 Testing res: 0.661905 +2025-04-19 05:30:11,452 INFO forgetting: 0.211538 +2025-04-19 05:30:11,455 INFO Incremental step: 2 +2025-04-19 05:30:38,124 INFO Epoch:0 train_loss:3.18428 +2025-04-19 05:30:46,373 INFO Epoch:0 val_res:0.471154 +2025-04-19 05:30:46,374 INFO Saving best model at Epoch 0 +2025-04-19 05:31:14,293 INFO Epoch:1 train_loss:2.66234 +2025-04-19 05:31:22,609 INFO Epoch:1 val_res:0.496795 +2025-04-19 05:31:22,617 INFO Saving best model at Epoch 1 +2025-04-19 05:31:52,074 INFO Epoch:2 train_loss:2.23314 +2025-04-19 05:31:59,658 INFO Epoch:2 val_res:0.490385 +2025-04-19 05:32:24,939 INFO Epoch:3 train_loss:1.82310 +2025-04-19 05:32:34,437 INFO Epoch:3 val_res:0.512821 +2025-04-19 05:32:34,438 INFO Saving best model at Epoch 3 +2025-04-19 05:33:01,339 INFO Epoch:4 train_loss:1.76715 +2025-04-19 05:33:09,106 INFO Epoch:4 val_res:0.506410 +2025-04-19 05:33:34,718 INFO Epoch:5 train_loss:1.53247 +2025-04-19 05:33:43,051 INFO Epoch:5 val_res:0.528846 +2025-04-19 05:33:43,052 INFO Saving best model at Epoch 5 +2025-04-19 05:34:10,026 INFO Epoch:6 train_loss:1.45199 +2025-04-19 05:34:17,776 INFO Epoch:6 val_res:0.535256 +2025-04-19 05:34:17,776 INFO Saving best model at Epoch 6 +2025-04-19 05:34:44,750 INFO Epoch:7 train_loss:1.43102 +2025-04-19 05:34:52,623 INFO Epoch:7 val_res:0.535256 +2025-04-19 05:35:17,692 INFO Epoch:8 train_loss:1.31540 +2025-04-19 05:35:25,753 INFO Epoch:8 val_res:0.554487 +2025-04-19 05:35:25,753 INFO Saving best model at Epoch 8 +2025-04-19 05:35:55,811 INFO Epoch:9 train_loss:1.31947 +2025-04-19 05:36:02,917 INFO Epoch:9 val_res:0.548077 +2025-04-19 05:36:30,623 INFO Epoch:10 train_loss:1.25739 +2025-04-19 05:36:39,899 INFO Epoch:10 val_res:0.538462 +2025-04-19 05:37:08,217 INFO Epoch:11 train_loss:1.22217 +2025-04-19 05:37:16,452 INFO Epoch:11 val_res:0.551282 +2025-04-19 05:37:41,291 INFO Epoch:12 train_loss:1.20111 +2025-04-19 05:37:49,543 INFO Epoch:12 val_res:0.554487 +2025-04-19 05:38:16,085 INFO Epoch:13 train_loss:1.18148 +2025-04-19 05:38:23,915 INFO Epoch:13 val_res:0.554487 +2025-04-19 05:38:50,187 INFO Epoch:14 train_loss:1.15829 +2025-04-19 05:38:58,356 INFO Epoch:14 val_res:0.554487 +2025-04-19 05:39:24,463 INFO Epoch:15 train_loss:1.13062 +2025-04-19 05:39:32,659 INFO Epoch:15 val_res:0.548077 +2025-04-19 05:39:57,352 INFO Epoch:16 train_loss:1.12361 +2025-04-19 05:40:05,062 INFO Epoch:16 val_res:0.557692 +2025-04-19 05:40:05,063 INFO Saving best model at Epoch 16 +2025-04-19 05:40:32,838 INFO Epoch:17 train_loss:1.09980 +2025-04-19 05:40:41,432 INFO Epoch:17 val_res:0.557692 +2025-04-19 05:41:07,064 INFO Epoch:18 train_loss:1.09097 +2025-04-19 05:41:14,729 INFO Epoch:18 val_res:0.541667 +2025-04-19 05:41:40,424 INFO Epoch:19 train_loss:1.07130 +2025-04-19 05:41:48,206 INFO Epoch:19 val_res:0.557692 +2025-04-19 05:42:15,596 INFO Epoch:20 train_loss:4.10708 +2025-04-19 05:42:23,374 INFO Epoch:20 val_res:0.557692 +2025-04-19 05:42:50,423 INFO Epoch:21 train_loss:3.50735 +2025-04-19 05:42:59,090 INFO Epoch:21 val_res:0.551282 +2025-04-19 05:43:23,780 INFO Epoch:22 train_loss:3.19522 +2025-04-19 05:43:31,658 INFO Epoch:22 val_res:0.557692 +2025-04-19 05:43:57,011 INFO Epoch:23 train_loss:2.89543 +2025-04-19 05:44:05,393 INFO Epoch:23 val_res:0.548077 +2025-04-19 05:44:31,538 INFO Epoch:24 train_loss:2.73976 +2025-04-19 05:44:39,938 INFO Epoch:24 val_res:0.554487 +2025-04-19 05:45:06,754 INFO Epoch:25 train_loss:2.59030 +2025-04-19 05:45:15,421 INFO Epoch:25 val_res:0.544872 +2025-04-19 05:45:40,454 INFO Epoch:26 train_loss:2.49889 +2025-04-19 05:45:47,915 INFO Epoch:26 val_res:0.551282 +2025-04-19 05:46:14,485 INFO Epoch:27 train_loss:2.40166 +2025-04-19 05:46:22,910 INFO Epoch:27 val_res:0.557692 +2025-04-19 05:46:48,342 INFO Epoch:28 train_loss:2.33306 +2025-04-19 05:46:56,227 INFO Epoch:28 val_res:0.560897 +2025-04-19 05:46:56,227 INFO Saving best model at Epoch 28 +2025-04-19 05:47:25,285 INFO Epoch:29 train_loss:2.23951 +2025-04-19 05:47:34,001 INFO Epoch:29 val_res:0.551282 +2025-04-19 05:47:58,879 INFO Epoch:30 train_loss:2.18196 +2025-04-19 05:48:06,754 INFO Epoch:30 val_res:0.548077 +2025-04-19 05:48:32,518 INFO Epoch:31 train_loss:2.13191 +2025-04-19 05:48:40,478 INFO Epoch:31 val_res:0.554487 +2025-04-19 05:49:04,807 INFO Epoch:32 train_loss:2.07571 +2025-04-19 05:49:12,485 INFO Epoch:32 val_res:0.557692 +2025-04-19 05:49:39,207 INFO Epoch:33 train_loss:2.01269 +2025-04-19 05:49:46,915 INFO Epoch:33 val_res:0.544872 +2025-04-19 05:50:11,742 INFO Epoch:34 train_loss:1.96479 +2025-04-19 05:50:20,422 INFO Epoch:34 val_res:0.560897 +2025-04-19 05:50:46,227 INFO Epoch:35 train_loss:1.93285 +2025-04-19 05:50:53,930 INFO Epoch:35 val_res:0.557692 +2025-04-19 05:51:19,565 INFO Epoch:36 train_loss:1.89463 +2025-04-19 05:51:27,684 INFO Epoch:36 val_res:0.573718 +2025-04-19 05:51:27,684 INFO Saving best model at Epoch 36 +2025-04-19 05:51:56,193 INFO Epoch:37 train_loss:1.86335 +2025-04-19 05:52:04,130 INFO Epoch:37 val_res:0.560897 +2025-04-19 05:52:30,977 INFO Epoch:38 train_loss:1.80159 +2025-04-19 05:52:39,153 INFO Epoch:38 val_res:0.551282 +2025-04-19 05:53:02,959 INFO Epoch:39 train_loss:1.77337 +2025-04-19 05:53:10,834 INFO Epoch:39 val_res:0.554487 +2025-04-19 05:53:37,041 INFO Epoch:40 train_loss:1.77672 +2025-04-19 05:53:45,623 INFO Epoch:40 val_res:0.560897 +2025-04-19 05:54:09,849 INFO Epoch:41 train_loss:1.76971 +2025-04-19 05:54:17,319 INFO Epoch:41 val_res:0.560897 +2025-04-19 05:54:42,965 INFO Epoch:42 train_loss:1.71485 +2025-04-19 05:54:50,935 INFO Epoch:42 val_res:0.560897 +2025-04-19 05:55:16,124 INFO Epoch:43 train_loss:1.68009 +2025-04-19 05:55:24,723 INFO Epoch:43 val_res:0.557692 +2025-04-19 05:55:50,657 INFO Epoch:44 train_loss:1.63907 +2025-04-19 05:55:58,952 INFO Epoch:44 val_res:0.567308 +2025-04-19 05:56:22,453 INFO Epoch:45 train_loss:1.62208 +2025-04-19 05:56:30,392 INFO Epoch:45 val_res:0.560897 +2025-04-19 05:56:52,391 INFO Epoch:46 train_loss:1.59085 +2025-04-19 05:56:59,084 INFO Epoch:46 val_res:0.564103 +2025-04-19 05:57:23,102 INFO Epoch:47 train_loss:1.58358 +2025-04-19 05:57:31,118 INFO Epoch:47 val_res:0.573718 +2025-04-19 05:57:55,459 INFO Epoch:48 train_loss:1.57484 +2025-04-19 05:58:02,069 INFO Epoch:48 val_res:0.583333 +2025-04-19 05:58:02,070 INFO Saving best model at Epoch 48 +2025-04-19 05:58:27,892 INFO Epoch:49 train_loss:1.53623 +2025-04-19 05:58:35,491 INFO Epoch:49 val_res:0.570513 +2025-04-19 05:59:02,194 INFO Epoch:50 train_loss:1.52201 +2025-04-19 05:59:11,490 INFO Epoch:50 val_res:0.567308 +2025-04-19 05:59:38,464 INFO Epoch:51 train_loss:1.48015 +2025-04-19 05:59:46,817 INFO Epoch:51 val_res:0.567308 +2025-04-19 06:00:11,438 INFO Epoch:52 train_loss:1.46926 +2025-04-19 06:00:19,920 INFO Epoch:52 val_res:0.573718 +2025-04-19 06:00:47,167 INFO Epoch:53 train_loss:1.47844 +2025-04-19 06:00:56,152 INFO Epoch:53 val_res:0.567308 +2025-04-19 06:01:24,191 INFO Epoch:54 train_loss:1.44538 +2025-04-19 06:01:32,418 INFO Epoch:54 val_res:0.567308 +2025-04-19 06:01:55,408 INFO Epoch:55 train_loss:1.42850 +2025-04-19 06:02:02,789 INFO Epoch:55 val_res:0.570513 +2025-04-19 06:02:26,450 INFO Epoch:56 train_loss:1.42388 +2025-04-19 06:02:34,975 INFO Epoch:56 val_res:0.564103 +2025-04-19 06:02:59,039 INFO Epoch:57 train_loss:1.42061 +2025-04-19 06:03:07,856 INFO Epoch:57 val_res:0.567308 +2025-04-19 06:03:32,693 INFO Epoch:58 train_loss:1.40369 +2025-04-19 06:03:40,811 INFO Epoch:58 val_res:0.570513 +2025-04-19 06:04:06,516 INFO Epoch:59 train_loss:1.39125 +2025-04-19 06:04:14,259 INFO Epoch:59 val_res:0.576923 +2025-04-19 06:04:39,864 INFO Epoch:60 train_loss:1.35750 +2025-04-19 06:04:47,965 INFO Epoch:60 val_res:0.580128 +2025-04-19 06:05:13,982 INFO Epoch:61 train_loss:1.34945 +2025-04-19 06:05:22,485 INFO Epoch:61 val_res:0.583333 +2025-04-19 06:05:47,948 INFO Epoch:62 train_loss:1.33947 +2025-04-19 06:05:55,996 INFO Epoch:62 val_res:0.580128 +2025-04-19 06:06:23,216 INFO Epoch:63 train_loss:1.34998 +2025-04-19 06:06:31,823 INFO Epoch:63 val_res:0.576923 +2025-04-19 06:06:56,481 INFO Epoch:64 train_loss:1.32775 +2025-04-19 06:07:05,391 INFO Epoch:64 val_res:0.580128 +2025-04-19 06:07:33,569 INFO Epoch:65 train_loss:1.33408 +2025-04-19 06:07:41,551 INFO Epoch:65 val_res:0.592949 +2025-04-19 06:07:41,551 INFO Saving best model at Epoch 65 +2025-04-19 06:08:14,958 INFO Epoch:66 train_loss:1.31005 +2025-04-19 06:08:23,747 INFO Epoch:66 val_res:0.586538 +2025-04-19 06:08:50,463 INFO Epoch:67 train_loss:1.32489 +2025-04-19 06:08:58,970 INFO Epoch:67 val_res:0.580128 +2025-04-19 06:09:24,087 INFO Epoch:68 train_loss:1.30329 +2025-04-19 06:09:33,148 INFO Epoch:68 val_res:0.589744 +2025-04-19 06:09:59,665 INFO Epoch:69 train_loss:1.29134 +2025-04-19 06:10:07,851 INFO Epoch:69 val_res:0.583333 +2025-04-19 06:10:34,566 INFO Epoch:70 train_loss:1.29075 +2025-04-19 06:10:42,886 INFO Epoch:70 val_res:0.592949 +2025-04-19 06:11:09,172 INFO Epoch:71 train_loss:0.71879 +2025-04-19 06:11:17,670 INFO Epoch:71 val_res:0.586538 +2025-04-19 06:11:42,173 INFO Epoch:72 train_loss:0.71462 +2025-04-19 06:11:50,274 INFO Epoch:72 val_res:0.580128 +2025-04-19 06:12:15,416 INFO Epoch:73 train_loss:0.71337 +2025-04-19 06:12:23,375 INFO Epoch:73 val_res:0.599359 +2025-04-19 06:12:23,375 INFO Saving best model at Epoch 73 +2025-04-19 06:12:51,244 INFO Epoch:74 train_loss:0.71107 +2025-04-19 06:12:59,455 INFO Epoch:74 val_res:0.589744 +2025-04-19 06:13:24,609 INFO Epoch:75 train_loss:0.71532 +2025-04-19 06:13:33,068 INFO Epoch:75 val_res:0.592949 +2025-04-19 06:14:00,164 INFO Epoch:76 train_loss:0.69741 +2025-04-19 06:14:08,438 INFO Epoch:76 val_res:0.592949 +2025-04-19 06:14:33,874 INFO Epoch:77 train_loss:0.70030 +2025-04-19 06:14:42,352 INFO Epoch:77 val_res:0.589744 +2025-04-19 06:15:08,388 INFO Epoch:78 train_loss:0.69723 +2025-04-19 06:15:15,564 INFO Epoch:78 val_res:0.592949 +2025-04-19 06:15:37,935 INFO Epoch:79 train_loss:0.69920 +2025-04-19 06:15:46,120 INFO Epoch:79 val_res:0.592949 +2025-04-19 06:16:11,409 INFO Epoch:80 train_loss:0.69331 +2025-04-19 06:16:19,879 INFO Epoch:80 val_res:0.596154 +2025-04-19 06:16:46,070 INFO Epoch:81 train_loss:0.69562 +2025-04-19 06:16:54,010 INFO Epoch:81 val_res:0.586538 +2025-04-19 06:17:17,943 INFO Epoch:82 train_loss:0.68671 +2025-04-19 06:17:26,949 INFO Epoch:82 val_res:0.596154 +2025-04-19 06:17:51,316 INFO Epoch:83 train_loss:0.68802 +2025-04-19 06:18:00,920 INFO Epoch:83 val_res:0.596154 +2025-04-19 06:18:29,307 INFO Epoch:84 train_loss:0.68398 +2025-04-19 06:18:37,977 INFO Epoch:84 val_res:0.596154 +2025-04-19 06:19:04,092 INFO Epoch:85 train_loss:0.68601 +2025-04-19 06:19:11,871 INFO Epoch:85 val_res:0.589744 +2025-04-19 06:19:38,055 INFO Epoch:86 train_loss:0.68886 +2025-04-19 06:19:46,737 INFO Epoch:86 val_res:0.596154 +2025-04-19 06:20:08,365 INFO Epoch:87 train_loss:0.69068 +2025-04-19 06:20:16,682 INFO Epoch:87 val_res:0.596154 +2025-04-19 06:20:40,718 INFO Epoch:88 train_loss:0.68673 +2025-04-19 06:20:49,023 INFO Epoch:88 val_res:0.599359 +2025-04-19 06:21:15,668 INFO Epoch:89 train_loss:0.68339 +2025-04-19 06:21:24,126 INFO Epoch:89 val_res:0.602564 +2025-04-19 06:21:24,127 INFO Saving best model at Epoch 89 +2025-04-19 06:21:52,149 INFO Epoch:90 train_loss:0.67973 +2025-04-19 06:22:01,107 INFO Epoch:90 val_res:0.602564 +2025-04-19 06:22:26,664 INFO Epoch:91 train_loss:0.67919 +2025-04-19 06:22:34,807 INFO Epoch:91 val_res:0.596154 +2025-04-19 06:22:58,892 INFO Epoch:92 train_loss:0.67899 +2025-04-19 06:23:07,188 INFO Epoch:92 val_res:0.599359 +2025-04-19 06:23:32,889 INFO Epoch:93 train_loss:0.67446 +2025-04-19 06:23:40,642 INFO Epoch:93 val_res:0.605769 +2025-04-19 06:23:40,642 INFO Saving best model at Epoch 93 +2025-04-19 06:24:08,583 INFO Epoch:94 train_loss:0.67357 +2025-04-19 06:24:18,266 INFO Epoch:94 val_res:0.605769 +2025-04-19 06:24:44,396 INFO Epoch:95 train_loss:0.67102 +2025-04-19 06:24:52,776 INFO Epoch:95 val_res:0.605769 +2025-04-19 06:25:17,070 INFO Epoch:96 train_loss:0.66737 +2025-04-19 06:25:25,357 INFO Epoch:96 val_res:0.612179 +2025-04-19 06:25:25,357 INFO Saving best model at Epoch 96 +2025-04-19 06:25:55,126 INFO Epoch:97 train_loss:0.66229 +2025-04-19 06:26:03,299 INFO Epoch:97 val_res:0.605769 +2025-04-19 06:26:28,253 INFO Epoch:98 train_loss:0.66322 +2025-04-19 06:26:36,957 INFO Epoch:98 val_res:0.602564 +2025-04-19 06:26:59,391 INFO Epoch:99 train_loss:0.66430 +2025-04-19 06:27:06,493 INFO Epoch:99 val_res:0.605769 +2025-04-19 06:27:06,741 INFO ===================================== +2025-04-19 06:27:06,741 INFO Start testing... +2025-04-19 06:27:06,742 INFO ===================================== +2025-04-19 06:27:16,686 INFO Incremental step 2 Testing res: 0.549206 +2025-04-19 06:27:16,687 INFO forgetting: 0.238752 +2025-04-19 06:27:16,689 INFO Incremental step: 3 +2025-04-19 06:27:43,430 INFO Epoch:0 train_loss:2.99799 +2025-04-19 06:27:52,581 INFO Epoch:0 val_res:0.483376 +2025-04-19 06:27:52,582 INFO Saving best model at Epoch 0 +2025-04-19 06:28:18,154 INFO Epoch:1 train_loss:3.94262 +2025-04-19 06:28:26,887 INFO Epoch:1 val_res:0.450128 +2025-04-19 06:28:52,979 INFO Epoch:2 train_loss:2.55740 +2025-04-19 06:29:03,163 INFO Epoch:2 val_res:0.537084 +2025-04-19 06:29:03,164 INFO Saving best model at Epoch 2 +2025-04-19 06:29:28,019 INFO Epoch:3 train_loss:2.47854 +2025-04-19 06:29:36,922 INFO Epoch:3 val_res:0.547315 +2025-04-19 06:29:36,922 INFO Saving best model at Epoch 3 +2025-04-19 06:30:03,538 INFO Epoch:4 train_loss:2.00019 +2025-04-19 06:30:12,254 INFO Epoch:4 val_res:0.501279 +2025-04-19 06:30:36,468 INFO Epoch:5 train_loss:1.82643 +2025-04-19 06:30:45,188 INFO Epoch:5 val_res:0.498721 +2025-04-19 06:31:10,079 INFO Epoch:6 train_loss:1.72234 +2025-04-19 06:31:19,496 INFO Epoch:6 val_res:0.542199 +2025-04-19 06:31:43,392 INFO Epoch:7 train_loss:1.53419 +2025-04-19 06:31:53,062 INFO Epoch:7 val_res:0.570332 +2025-04-19 06:31:53,062 INFO Saving best model at Epoch 7 +2025-04-19 06:32:20,484 INFO Epoch:8 train_loss:1.45648 +2025-04-19 06:32:29,441 INFO Epoch:8 val_res:0.580563 +2025-04-19 06:32:29,442 INFO Saving best model at Epoch 8 +2025-04-19 06:32:55,151 INFO Epoch:9 train_loss:1.44281 +2025-04-19 06:33:03,280 INFO Epoch:9 val_res:0.570332 +2025-04-19 06:33:25,455 INFO Epoch:10 train_loss:1.33204 +2025-04-19 06:33:33,878 INFO Epoch:10 val_res:0.554987 +2025-04-19 06:33:55,379 INFO Epoch:11 train_loss:1.29033 +2025-04-19 06:34:04,457 INFO Epoch:11 val_res:0.567775 +2025-04-19 06:34:28,470 INFO Epoch:12 train_loss:1.26365 +2025-04-19 06:34:37,139 INFO Epoch:12 val_res:0.567775 +2025-04-19 06:34:59,451 INFO Epoch:13 train_loss:1.20907 +2025-04-19 06:35:09,148 INFO Epoch:13 val_res:0.593350 +2025-04-19 06:35:09,148 INFO Saving best model at Epoch 13 +2025-04-19 06:35:34,535 INFO Epoch:14 train_loss:1.19071 +2025-04-19 06:35:42,829 INFO Epoch:14 val_res:0.588235 +2025-04-19 06:36:05,350 INFO Epoch:15 train_loss:1.19347 +2025-04-19 06:36:14,134 INFO Epoch:15 val_res:0.588235 +2025-04-19 06:36:38,081 INFO Epoch:16 train_loss:1.11473 +2025-04-19 06:36:47,678 INFO Epoch:16 val_res:0.585678 +2025-04-19 06:37:10,450 INFO Epoch:17 train_loss:1.10984 +2025-04-19 06:37:20,652 INFO Epoch:17 val_res:0.578005 +2025-04-19 06:37:45,144 INFO Epoch:18 train_loss:1.10965 +2025-04-19 06:37:54,430 INFO Epoch:18 val_res:0.575448 +2025-04-19 06:38:17,447 INFO Epoch:19 train_loss:1.08975 +2025-04-19 06:38:26,318 INFO Epoch:19 val_res:0.580563 +2025-04-19 06:38:50,440 INFO Epoch:20 train_loss:4.34760 +2025-04-19 06:38:58,494 INFO Epoch:20 val_res:0.593350 +2025-04-19 06:39:20,821 INFO Epoch:21 train_loss:3.76062 +2025-04-19 06:39:29,344 INFO Epoch:21 val_res:0.583120 +2025-04-19 06:39:53,613 INFO Epoch:22 train_loss:3.39437 +2025-04-19 06:40:01,511 INFO Epoch:22 val_res:0.580563 +2025-04-19 06:40:25,267 INFO Epoch:23 train_loss:3.13314 +2025-04-19 06:40:34,458 INFO Epoch:23 val_res:0.580563 +2025-04-19 06:40:57,694 INFO Epoch:24 train_loss:2.88175 +2025-04-19 06:41:06,640 INFO Epoch:24 val_res:0.585678 +2025-04-19 06:41:30,182 INFO Epoch:25 train_loss:2.69463 +2025-04-19 06:41:39,129 INFO Epoch:25 val_res:0.590793 +2025-04-19 06:42:04,225 INFO Epoch:26 train_loss:2.57724 +2025-04-19 06:42:13,097 INFO Epoch:26 val_res:0.588235 +2025-04-19 06:42:36,596 INFO Epoch:27 train_loss:2.53825 +2025-04-19 06:42:45,564 INFO Epoch:27 val_res:0.588235 +2025-04-19 06:43:09,287 INFO Epoch:28 train_loss:2.43802 +2025-04-19 06:43:17,944 INFO Epoch:28 val_res:0.595908 +2025-04-19 06:43:17,945 INFO Saving best model at Epoch 28 +2025-04-19 06:43:44,065 INFO Epoch:29 train_loss:2.35036 +2025-04-19 06:43:53,603 INFO Epoch:29 val_res:0.588235 +2025-04-19 06:44:17,989 INFO Epoch:30 train_loss:2.27424 +2025-04-19 06:44:26,437 INFO Epoch:30 val_res:0.590793 +2025-04-19 06:44:48,172 INFO Epoch:31 train_loss:2.24925 +2025-04-19 06:44:56,600 INFO Epoch:31 val_res:0.603581 +2025-04-19 06:44:56,601 INFO Saving best model at Epoch 31 +2025-04-19 06:45:21,873 INFO Epoch:32 train_loss:2.20187 +2025-04-19 06:45:30,560 INFO Epoch:32 val_res:0.601023 +2025-04-19 06:45:53,174 INFO Epoch:33 train_loss:2.15129 +2025-04-19 06:46:02,377 INFO Epoch:33 val_res:0.598466 +2025-04-19 06:46:23,543 INFO Epoch:34 train_loss:2.11817 +2025-04-19 06:46:31,281 INFO Epoch:34 val_res:0.598466 +2025-04-19 06:46:53,032 INFO Epoch:35 train_loss:2.05767 +2025-04-19 06:47:01,839 INFO Epoch:35 val_res:0.606138 +2025-04-19 06:47:01,839 INFO Saving best model at Epoch 35 +2025-04-19 06:47:29,007 INFO Epoch:36 train_loss:2.03341 +2025-04-19 06:47:37,661 INFO Epoch:36 val_res:0.606138 +2025-04-19 06:48:00,781 INFO Epoch:37 train_loss:1.99464 +2025-04-19 06:48:08,907 INFO Epoch:37 val_res:0.611253 +2025-04-19 06:48:08,907 INFO Saving best model at Epoch 37 +2025-04-19 06:48:34,354 INFO Epoch:38 train_loss:1.95678 +2025-04-19 06:48:43,476 INFO Epoch:38 val_res:0.608696 +2025-04-19 06:49:06,133 INFO Epoch:39 train_loss:1.91304 +2025-04-19 06:49:15,386 INFO Epoch:39 val_res:0.613811 +2025-04-19 06:49:15,387 INFO Saving best model at Epoch 39 +2025-04-19 06:49:41,472 INFO Epoch:40 train_loss:1.92143 +2025-04-19 06:49:50,009 INFO Epoch:40 val_res:0.611253 +2025-04-19 06:50:11,979 INFO Epoch:41 train_loss:1.87783 +2025-04-19 06:50:19,599 INFO Epoch:41 val_res:0.621483 +2025-04-19 06:50:19,600 INFO Saving best model at Epoch 41 +2025-04-19 06:50:43,307 INFO Epoch:42 train_loss:1.84022 +2025-04-19 06:50:51,637 INFO Epoch:42 val_res:0.611253 +2025-04-19 06:51:11,746 INFO Epoch:43 train_loss:1.81665 +2025-04-19 06:51:20,047 INFO Epoch:43 val_res:0.613811 +2025-04-19 06:51:41,407 INFO Epoch:44 train_loss:1.84673 +2025-04-19 06:51:49,271 INFO Epoch:44 val_res:0.608696 +2025-04-19 06:52:11,019 INFO Epoch:45 train_loss:1.77727 +2025-04-19 06:52:19,569 INFO Epoch:45 val_res:0.621483 +2025-04-19 06:52:40,616 INFO Epoch:46 train_loss:1.78276 +2025-04-19 06:52:49,314 INFO Epoch:46 val_res:0.618926 +2025-04-19 06:53:10,502 INFO Epoch:47 train_loss:1.77253 +2025-04-19 06:53:19,480 INFO Epoch:47 val_res:0.611253 +2025-04-19 06:53:40,410 INFO Epoch:48 train_loss:1.72767 +2025-04-19 06:53:48,893 INFO Epoch:48 val_res:0.624041 +2025-04-19 06:53:48,894 INFO Saving best model at Epoch 48 +2025-04-19 06:54:12,884 INFO Epoch:49 train_loss:1.70488 +2025-04-19 06:54:20,697 INFO Epoch:49 val_res:0.626598 +2025-04-19 06:54:20,697 INFO Saving best model at Epoch 49 +2025-04-19 06:54:44,768 INFO Epoch:50 train_loss:1.69148 +2025-04-19 06:54:52,848 INFO Epoch:50 val_res:0.603581 +2025-04-19 06:55:13,680 INFO Epoch:51 train_loss:1.73214 +2025-04-19 06:55:22,051 INFO Epoch:51 val_res:0.611253 +2025-04-19 06:55:43,661 INFO Epoch:52 train_loss:1.69050 +2025-04-19 06:55:52,073 INFO Epoch:52 val_res:0.613811 +2025-04-19 06:56:14,495 INFO Epoch:53 train_loss:1.67723 +2025-04-19 06:56:23,088 INFO Epoch:53 val_res:0.621483 +2025-04-19 06:56:44,476 INFO Epoch:54 train_loss:1.65268 +2025-04-19 06:56:53,052 INFO Epoch:54 val_res:0.624041 +2025-04-19 06:57:14,562 INFO Epoch:55 train_loss:1.62344 +2025-04-19 06:57:22,286 INFO Epoch:55 val_res:0.616368 +2025-04-19 06:57:47,110 INFO Epoch:56 train_loss:1.60456 +2025-04-19 06:57:55,731 INFO Epoch:56 val_res:0.624041 +2025-04-19 06:58:19,980 INFO Epoch:57 train_loss:1.60475 +2025-04-19 06:58:28,802 INFO Epoch:57 val_res:0.624041 +2025-04-19 06:58:50,654 INFO Epoch:58 train_loss:1.57748 +2025-04-19 06:58:59,671 INFO Epoch:58 val_res:0.624041 +2025-04-19 06:59:21,255 INFO Epoch:59 train_loss:1.59871 +2025-04-19 06:59:29,894 INFO Epoch:59 val_res:0.621483 +2025-04-19 06:59:51,927 INFO Epoch:60 train_loss:1.54970 +2025-04-19 07:00:00,126 INFO Epoch:60 val_res:0.624041 +2025-04-19 07:00:22,158 INFO Epoch:61 train_loss:1.51777 +2025-04-19 07:00:30,953 INFO Epoch:61 val_res:0.626598 +2025-04-19 07:00:55,148 INFO Epoch:62 train_loss:1.52246 +2025-04-19 07:01:04,772 INFO Epoch:62 val_res:0.624041 +2025-04-19 07:01:25,376 INFO Epoch:63 train_loss:1.52930 +2025-04-19 07:01:33,677 INFO Epoch:63 val_res:0.624041 +2025-04-19 07:01:54,511 INFO Epoch:64 train_loss:1.48145 +2025-04-19 07:02:03,105 INFO Epoch:64 val_res:0.626598 +2025-04-19 07:02:24,306 INFO Epoch:65 train_loss:1.48729 +2025-04-19 07:02:32,792 INFO Epoch:65 val_res:0.626598 +2025-04-19 07:02:55,248 INFO Epoch:66 train_loss:1.48022 +2025-04-19 07:03:03,050 INFO Epoch:66 val_res:0.624041 +2025-04-19 07:03:24,884 INFO Epoch:67 train_loss:1.43332 +2025-04-19 07:03:33,647 INFO Epoch:67 val_res:0.624041 +2025-04-19 07:03:55,150 INFO Epoch:68 train_loss:1.45863 +2025-04-19 07:04:03,503 INFO Epoch:68 val_res:0.631714 +2025-04-19 07:04:03,503 INFO Saving best model at Epoch 68 +2025-04-19 07:04:26,719 INFO Epoch:69 train_loss:1.45605 +2025-04-19 07:04:35,901 INFO Epoch:69 val_res:0.621483 +2025-04-19 07:04:57,325 INFO Epoch:70 train_loss:1.44366 +2025-04-19 07:05:05,564 INFO Epoch:70 val_res:0.621483 +2025-04-19 07:05:27,016 INFO Epoch:71 train_loss:0.76177 +2025-04-19 07:05:34,945 INFO Epoch:71 val_res:0.629156 +2025-04-19 07:05:56,188 INFO Epoch:72 train_loss:0.76050 +2025-04-19 07:06:04,234 INFO Epoch:72 val_res:0.624041 +2025-04-19 07:06:25,786 INFO Epoch:73 train_loss:0.74187 +2025-04-19 07:06:34,603 INFO Epoch:73 val_res:0.631714 +2025-04-19 07:06:56,560 INFO Epoch:74 train_loss:0.75412 +2025-04-19 07:07:04,693 INFO Epoch:74 val_res:0.626598 +2025-04-19 07:07:26,676 INFO Epoch:75 train_loss:0.74398 +2025-04-19 07:07:34,648 INFO Epoch:75 val_res:0.631714 +2025-04-19 07:07:57,353 INFO Epoch:76 train_loss:0.74646 +2025-04-19 07:08:06,558 INFO Epoch:76 val_res:0.618926 +2025-04-19 07:08:28,119 INFO Epoch:77 train_loss:0.73788 +2025-04-19 07:08:37,585 INFO Epoch:77 val_res:0.624041 +2025-04-19 07:08:58,683 INFO Epoch:78 train_loss:0.74338 +2025-04-19 07:09:07,643 INFO Epoch:78 val_res:0.621483 +2025-04-19 07:09:29,425 INFO Epoch:79 train_loss:0.75065 +2025-04-19 07:09:37,325 INFO Epoch:79 val_res:0.616368 +2025-04-19 07:10:00,424 INFO Epoch:80 train_loss:0.74466 +2025-04-19 07:10:09,486 INFO Epoch:80 val_res:0.613811 +2025-04-19 07:10:31,439 INFO Epoch:81 train_loss:0.72539 +2025-04-19 07:10:39,525 INFO Epoch:81 val_res:0.616368 +2025-04-19 07:11:01,434 INFO Epoch:82 train_loss:0.73186 +2025-04-19 07:11:09,649 INFO Epoch:82 val_res:0.621483 +2025-04-19 07:11:33,252 INFO Epoch:83 train_loss:0.73644 +2025-04-19 07:11:42,398 INFO Epoch:83 val_res:0.613811 +2025-04-19 07:12:04,362 INFO Epoch:84 train_loss:0.71643 +2025-04-19 07:12:12,844 INFO Epoch:84 val_res:0.608696 +2025-04-19 07:12:32,696 INFO Epoch:85 train_loss:0.71697 +2025-04-19 07:12:40,939 INFO Epoch:85 val_res:0.618926 +2025-04-19 07:13:02,098 INFO Epoch:86 train_loss:0.71822 +2025-04-19 07:13:10,303 INFO Epoch:86 val_res:0.611253 +2025-04-19 07:13:30,921 INFO Epoch:87 train_loss:0.71971 +2025-04-19 07:13:39,403 INFO Epoch:87 val_res:0.624041 +2025-04-19 07:13:59,902 INFO Epoch:88 train_loss:0.71537 +2025-04-19 07:14:09,002 INFO Epoch:88 val_res:0.616368 +2025-04-19 07:14:30,560 INFO Epoch:89 train_loss:0.71379 +2025-04-19 07:14:38,909 INFO Epoch:89 val_res:0.621483 +2025-04-19 07:15:02,622 INFO Epoch:90 train_loss:0.71731 +2025-04-19 07:15:11,841 INFO Epoch:90 val_res:0.618926 +2025-04-19 07:15:35,784 INFO Epoch:91 train_loss:0.71399 +2025-04-19 07:15:45,603 INFO Epoch:91 val_res:0.618926 +2025-04-19 07:16:09,935 INFO Epoch:92 train_loss:0.72284 +2025-04-19 07:16:18,905 INFO Epoch:92 val_res:0.616368 +2025-04-19 07:16:42,948 INFO Epoch:93 train_loss:0.71512 +2025-04-19 07:16:51,347 INFO Epoch:93 val_res:0.621483 +2025-04-19 07:17:12,391 INFO Epoch:94 train_loss:0.70658 +2025-04-19 07:17:20,606 INFO Epoch:94 val_res:0.611253 +2025-04-19 07:17:40,955 INFO Epoch:95 train_loss:0.71321 +2025-04-19 07:17:49,125 INFO Epoch:95 val_res:0.616368 +2025-04-19 07:18:09,218 INFO Epoch:96 train_loss:0.70038 +2025-04-19 07:18:16,694 INFO Epoch:96 val_res:0.616368 +2025-04-19 07:18:37,835 INFO Epoch:97 train_loss:0.69668 +2025-04-19 07:18:46,185 INFO Epoch:97 val_res:0.621483 +2025-04-19 07:19:09,244 INFO Epoch:98 train_loss:0.71223 +2025-04-19 07:19:17,589 INFO Epoch:98 val_res:0.613811 +2025-04-19 07:19:39,145 INFO Epoch:99 train_loss:0.70420 +2025-04-19 07:19:47,015 INFO Epoch:99 val_res:0.608696 +2025-04-19 07:19:47,411 INFO ===================================== +2025-04-19 07:19:47,411 INFO Start testing... +2025-04-19 07:19:47,412 INFO ===================================== +2025-04-19 07:19:59,020 INFO Incremental step 3 Testing res: 0.545685 +2025-04-19 07:19:59,021 INFO forgetting: 0.121220 +2025-04-19 07:19:59,023 INFO Average Accuracy: 0.623575 +2025-04-19 07:19:59,023 INFO Average Forgetting: 0.190503 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..0bff6172de12e9eabbde9c77ac720ee23018fcc0 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..c902858344abec31066ed419f2769e68ea056635 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..83a020a24a7786081f480453bbc30fcfca257a65 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..be6b652c2fcadf142bfe497f3e890a7cdfcc9c7a Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..5cc160be687530392935fa4f54e8e7fe40f2bbfe Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_5.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..cf0aa32793408a26a7d4ff36b74809c878b61e50 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_5.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_6.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..86088e90fc4740bf8ba08378bf8db0e68a2a5ea7 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_6.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_7.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..f4f9f38f975d0205c01245b156d833c8bcad908c Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_7.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_8.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..48afae483dea9ca720024d3bf6d96ba6ac43d36f Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_8.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_9.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..931632f8b1eafecc322be2715e4e5157dcf3bf10 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_9.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..9ae9f105b30f8dc688411f2a28d8fd32a82a5dba Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..fb028213d7eb050516b76832592ef20ab1657138 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..84ea50cc74f0ca7c073e466af6ee5918de93cb37 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..6e7efd518ba25e2a08325bdd1c3512592ba807cc Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..41077b2268721d29a2ae66043096086c4cd630c2 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_5.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..92a5e29b70dc5b025d601a3902b4f3af27144cf8 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_5.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_6.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..4a46cea9b6bf4ba441978cda15b2f5e9ceff6863 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_6.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_7.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..8637b78a1ce186065a52b6dee68eb37478b8af22 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_7.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_8.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..95baafde6507046f3b3dbc996db9c464cc998baf Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_8.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_9.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..e638a148f7984edbb61f51ffba7f65a3d7a54592 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_9.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b6ac8fda0589fc6c11635805f9dc3e84444c1d97 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dae7ee639c126f1d8ba187e792b26007a9960933880d437a50e94994fea800c +size 114142993 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..89db521e8d13249e4fb2b33fbdba66af0adb73a1 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa1cb5a622fca69e0fc6f839039fa5a14bcff62037046b88e2a18c4cebd2378 +size 114235409 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9b6810ae521ff0c791a2e1f20e6d5aceacd5f8b2 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f6b8c25b5e99966a3b2f1a250a1b7cf4f1595c36b0647383ac730dcd57d926 +size 114327569 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..558359a96f946ee80694a99f49733a91c5527756 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610657bf96bd52ea656a06b576c8bfa49ada896e889d972eb76fd15b7b881f4d +size 114419921 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..373ee46bceb81397b41c9541380e5353f4b25af2 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90a9ef79b2e1e810fd01c17c881d8828faa614888973e37f1dcd6a141cc6f96e +size 114512273 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_5_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_5_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..02374909dc8dd7ee137292048267fd51f3fe509a --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_5_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c7da565d55911905eb5318afaa34fc821d3b7bba2d5823a70bae568f3643fbc +size 114604433 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_6_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_6_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..1f7fc5079b83bd35ea837638b12de16a11756503 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_6_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5127479d991cd41075315e306a8a978400d69933e23d1b8f2116e6213758cb +size 114696785 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_7_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_7_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..2490d8c2ddc296e3221dc08f157317b9e82b5559 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_7_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b77320ddb967a6c01c5f6ff6c09fa56f93d7e3689dcb9388ee5b9fc0f9d00bbc +size 114789137 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_8_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_8_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ab8718b3846adb7404c19e13de725d1f0e44934c --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_8_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a586f656de234056558a08f8a496b6787d125099da93f9978079ffda63c760f +size 114881297 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_9_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_9_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..70ae9873d4a3ac6760fd99a551545dca4e5247f0 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_9_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773007ef5c35bec4fa6ae2e6137665e41ee3334cae0def25537070ee2a85b472 +size 114973649 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/train.log b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..e56a6915d22699e00fad7343d9fbec00c4c8a582 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/train.log @@ -0,0 +1,2339 @@ +2025-04-19 15:16:07,691 INFO Training start time: 2025-04-19 15:16:07.691642 +2025-04-19 15:16:09,148 INFO Incremental step: 0 +2025-04-19 15:16:36,349 INFO Epoch:0 train_loss:1.57833 +2025-04-19 15:16:39,644 INFO Epoch:0 val_res:0.566000 +2025-04-19 15:16:39,644 INFO Saving best model at Epoch 0 +2025-04-19 15:16:56,819 INFO Epoch:1 train_loss:0.67806 +2025-04-19 15:16:59,572 INFO Epoch:1 val_res:0.738000 +2025-04-19 15:16:59,572 INFO Saving best model at Epoch 1 +2025-04-19 15:17:15,701 INFO Epoch:2 train_loss:0.42002 +2025-04-19 15:17:18,447 INFO Epoch:2 val_res:0.782000 +2025-04-19 15:17:18,447 INFO Saving best model at Epoch 2 +2025-04-19 15:17:36,415 INFO Epoch:3 train_loss:0.31691 +2025-04-19 15:17:39,399 INFO Epoch:3 val_res:0.770000 +2025-04-19 15:17:54,277 INFO Epoch:4 train_loss:0.26087 +2025-04-19 15:17:57,064 INFO Epoch:4 val_res:0.804000 +2025-04-19 15:17:57,064 INFO Saving best model at Epoch 4 +2025-04-19 15:18:15,514 INFO Epoch:5 train_loss:0.21645 +2025-04-19 15:18:18,195 INFO Epoch:5 val_res:0.812000 +2025-04-19 15:18:18,196 INFO Saving best model at Epoch 5 +2025-04-19 15:18:36,368 INFO Epoch:6 train_loss:0.18516 +2025-04-19 15:18:39,186 INFO Epoch:6 val_res:0.812000 +2025-04-19 15:18:54,133 INFO Epoch:7 train_loss:0.16608 +2025-04-19 15:18:56,963 INFO Epoch:7 val_res:0.816000 +2025-04-19 15:18:56,964 INFO Saving best model at Epoch 7 +2025-04-19 15:19:16,614 INFO Epoch:8 train_loss:0.14958 +2025-04-19 15:19:19,620 INFO Epoch:8 val_res:0.848000 +2025-04-19 15:19:19,620 INFO Saving best model at Epoch 8 +2025-04-19 15:19:38,375 INFO Epoch:9 train_loss:0.13568 +2025-04-19 15:19:41,271 INFO Epoch:9 val_res:0.858000 +2025-04-19 15:19:41,271 INFO Saving best model at Epoch 9 +2025-04-19 15:19:58,434 INFO Epoch:10 train_loss:0.11070 +2025-04-19 15:20:01,162 INFO Epoch:10 val_res:0.852000 +2025-04-19 15:20:16,725 INFO Epoch:11 train_loss:0.09472 +2025-04-19 15:20:19,439 INFO Epoch:11 val_res:0.860000 +2025-04-19 15:20:19,440 INFO Saving best model at Epoch 11 +2025-04-19 15:20:35,833 INFO Epoch:12 train_loss:0.08878 +2025-04-19 15:20:38,650 INFO Epoch:12 val_res:0.872000 +2025-04-19 15:20:38,650 INFO Saving best model at Epoch 12 +2025-04-19 15:20:54,894 INFO Epoch:13 train_loss:0.07628 +2025-04-19 15:20:57,668 INFO Epoch:13 val_res:0.854000 +2025-04-19 15:21:13,247 INFO Epoch:14 train_loss:0.07572 +2025-04-19 15:21:16,125 INFO Epoch:14 val_res:0.874000 +2025-04-19 15:21:16,125 INFO Saving best model at Epoch 14 +2025-04-19 15:21:33,459 INFO Epoch:15 train_loss:0.06578 +2025-04-19 15:21:36,280 INFO Epoch:15 val_res:0.860000 +2025-04-19 15:21:52,172 INFO Epoch:16 train_loss:0.05786 +2025-04-19 15:21:55,131 INFO Epoch:16 val_res:0.886000 +2025-04-19 15:21:55,132 INFO Saving best model at Epoch 16 +2025-04-19 15:22:13,181 INFO Epoch:17 train_loss:0.05267 +2025-04-19 15:22:16,060 INFO Epoch:17 val_res:0.886000 +2025-04-19 15:22:32,268 INFO Epoch:18 train_loss:0.04460 +2025-04-19 15:22:35,184 INFO Epoch:18 val_res:0.866000 +2025-04-19 15:22:50,328 INFO Epoch:19 train_loss:0.04436 +2025-04-19 15:22:53,049 INFO Epoch:19 val_res:0.882000 +2025-04-19 15:23:08,429 INFO Epoch:20 train_loss:0.04433 +2025-04-19 15:23:11,094 INFO Epoch:20 val_res:0.874000 +2025-04-19 15:23:26,211 INFO Epoch:21 train_loss:0.03674 +2025-04-19 15:23:29,134 INFO Epoch:21 val_res:0.878000 +2025-04-19 15:23:44,556 INFO Epoch:22 train_loss:0.03254 +2025-04-19 15:23:47,412 INFO Epoch:22 val_res:0.888000 +2025-04-19 15:23:47,412 INFO Saving best model at Epoch 22 +2025-04-19 15:24:05,608 INFO Epoch:23 train_loss:0.03313 +2025-04-19 15:24:08,333 INFO Epoch:23 val_res:0.854000 +2025-04-19 15:24:25,256 INFO Epoch:24 train_loss:0.03610 +2025-04-19 15:24:27,998 INFO Epoch:24 val_res:0.884000 +2025-04-19 15:24:40,897 INFO Epoch:25 train_loss:0.03032 +2025-04-19 15:24:43,603 INFO Epoch:25 val_res:0.878000 +2025-04-19 15:24:56,831 INFO Epoch:26 train_loss:0.02924 +2025-04-19 15:24:59,588 INFO Epoch:26 val_res:0.884000 +2025-04-19 15:25:12,381 INFO Epoch:27 train_loss:0.02615 +2025-04-19 15:25:15,044 INFO Epoch:27 val_res:0.890000 +2025-04-19 15:25:15,044 INFO Saving best model at Epoch 27 +2025-04-19 15:25:29,661 INFO Epoch:28 train_loss:0.02284 +2025-04-19 15:25:32,250 INFO Epoch:28 val_res:0.884000 +2025-04-19 15:25:45,639 INFO Epoch:29 train_loss:0.01936 +2025-04-19 15:25:48,353 INFO Epoch:29 val_res:0.892000 +2025-04-19 15:25:48,353 INFO Saving best model at Epoch 29 +2025-04-19 15:26:03,224 INFO Epoch:30 train_loss:0.01997 +2025-04-19 15:26:05,918 INFO Epoch:30 val_res:0.886000 +2025-04-19 15:26:18,978 INFO Epoch:31 train_loss:0.01812 +2025-04-19 15:26:21,591 INFO Epoch:31 val_res:0.896000 +2025-04-19 15:26:21,592 INFO Saving best model at Epoch 31 +2025-04-19 15:26:36,433 INFO Epoch:32 train_loss:0.01850 +2025-04-19 15:26:39,149 INFO Epoch:32 val_res:0.886000 +2025-04-19 15:26:52,769 INFO Epoch:33 train_loss:0.01906 +2025-04-19 15:26:55,447 INFO Epoch:33 val_res:0.880000 +2025-04-19 15:27:09,684 INFO Epoch:34 train_loss:0.02031 +2025-04-19 15:27:12,435 INFO Epoch:34 val_res:0.892000 +2025-04-19 15:27:25,650 INFO Epoch:35 train_loss:0.01784 +2025-04-19 15:27:28,399 INFO Epoch:35 val_res:0.888000 +2025-04-19 15:27:41,934 INFO Epoch:36 train_loss:0.01414 +2025-04-19 15:27:44,559 INFO Epoch:36 val_res:0.882000 +2025-04-19 15:27:58,288 INFO Epoch:37 train_loss:0.01494 +2025-04-19 15:28:01,007 INFO Epoch:37 val_res:0.882000 +2025-04-19 15:28:14,893 INFO Epoch:38 train_loss:0.01747 +2025-04-19 15:28:17,538 INFO Epoch:38 val_res:0.884000 +2025-04-19 15:28:30,947 INFO Epoch:39 train_loss:0.01818 +2025-04-19 15:28:33,804 INFO Epoch:39 val_res:0.888000 +2025-04-19 15:28:47,463 INFO Epoch:40 train_loss:0.02001 +2025-04-19 15:28:50,125 INFO Epoch:40 val_res:0.882000 +2025-04-19 15:29:03,208 INFO Epoch:41 train_loss:0.02127 +2025-04-19 15:29:05,948 INFO Epoch:41 val_res:0.892000 +2025-04-19 15:29:19,369 INFO Epoch:42 train_loss:0.01365 +2025-04-19 15:29:22,018 INFO Epoch:42 val_res:0.894000 +2025-04-19 15:29:35,048 INFO Epoch:43 train_loss:0.01287 +2025-04-19 15:29:37,787 INFO Epoch:43 val_res:0.888000 +2025-04-19 15:29:51,046 INFO Epoch:44 train_loss:0.01109 +2025-04-19 15:29:53,744 INFO Epoch:44 val_res:0.884000 +2025-04-19 15:30:06,669 INFO Epoch:45 train_loss:0.01061 +2025-04-19 15:30:09,353 INFO Epoch:45 val_res:0.892000 +2025-04-19 15:30:22,606 INFO Epoch:46 train_loss:0.00987 +2025-04-19 15:30:25,324 INFO Epoch:46 val_res:0.874000 +2025-04-19 15:30:39,132 INFO Epoch:47 train_loss:0.01042 +2025-04-19 15:30:41,772 INFO Epoch:47 val_res:0.900000 +2025-04-19 15:30:41,773 INFO Saving best model at Epoch 47 +2025-04-19 15:30:56,906 INFO Epoch:48 train_loss:0.01220 +2025-04-19 15:30:59,497 INFO Epoch:48 val_res:0.872000 +2025-04-19 15:31:12,334 INFO Epoch:49 train_loss:0.01183 +2025-04-19 15:31:15,023 INFO Epoch:49 val_res:0.876000 +2025-04-19 15:31:28,996 INFO Epoch:50 train_loss:0.01042 +2025-04-19 15:31:31,617 INFO Epoch:50 val_res:0.894000 +2025-04-19 15:31:44,774 INFO Epoch:51 train_loss:0.12755 +2025-04-19 15:31:47,551 INFO Epoch:51 val_res:0.774000 +2025-04-19 15:32:01,701 INFO Epoch:52 train_loss:0.76904 +2025-04-19 15:32:04,387 INFO Epoch:52 val_res:0.844000 +2025-04-19 15:32:17,807 INFO Epoch:53 train_loss:0.16118 +2025-04-19 15:32:20,474 INFO Epoch:53 val_res:0.842000 +2025-04-19 15:32:33,909 INFO Epoch:54 train_loss:0.05346 +2025-04-19 15:32:36,561 INFO Epoch:54 val_res:0.878000 +2025-04-19 15:32:49,623 INFO Epoch:55 train_loss:0.01596 +2025-04-19 15:32:52,285 INFO Epoch:55 val_res:0.866000 +2025-04-19 15:33:05,546 INFO Epoch:56 train_loss:0.00925 +2025-04-19 15:33:08,316 INFO Epoch:56 val_res:0.882000 +2025-04-19 15:33:21,150 INFO Epoch:57 train_loss:0.00676 +2025-04-19 15:33:23,827 INFO Epoch:57 val_res:0.876000 +2025-04-19 15:33:37,288 INFO Epoch:58 train_loss:0.00588 +2025-04-19 15:33:39,920 INFO Epoch:58 val_res:0.876000 +2025-04-19 15:33:53,036 INFO Epoch:59 train_loss:0.00553 +2025-04-19 15:33:55,771 INFO Epoch:59 val_res:0.886000 +2025-04-19 15:34:09,256 INFO Epoch:60 train_loss:0.00562 +2025-04-19 15:34:12,013 INFO Epoch:60 val_res:0.876000 +2025-04-19 15:34:25,134 INFO Epoch:61 train_loss:0.00682 +2025-04-19 15:34:27,841 INFO Epoch:61 val_res:0.882000 +2025-04-19 15:34:41,297 INFO Epoch:62 train_loss:0.00603 +2025-04-19 15:34:43,993 INFO Epoch:62 val_res:0.882000 +2025-04-19 15:34:56,976 INFO Epoch:63 train_loss:0.00577 +2025-04-19 15:34:59,649 INFO Epoch:63 val_res:0.878000 +2025-04-19 15:35:13,560 INFO Epoch:64 train_loss:0.00674 +2025-04-19 15:35:16,263 INFO Epoch:64 val_res:0.872000 +2025-04-19 15:35:29,290 INFO Epoch:65 train_loss:0.00664 +2025-04-19 15:35:32,066 INFO Epoch:65 val_res:0.884000 +2025-04-19 15:35:45,274 INFO Epoch:66 train_loss:0.00596 +2025-04-19 15:35:47,845 INFO Epoch:66 val_res:0.882000 +2025-04-19 15:36:00,907 INFO Epoch:67 train_loss:0.00598 +2025-04-19 15:36:03,572 INFO Epoch:67 val_res:0.878000 +2025-04-19 15:36:17,187 INFO Epoch:68 train_loss:0.00629 +2025-04-19 15:36:19,930 INFO Epoch:68 val_res:0.890000 +2025-04-19 15:36:32,849 INFO Epoch:69 train_loss:0.00602 +2025-04-19 15:36:35,582 INFO Epoch:69 val_res:0.878000 +2025-04-19 15:36:48,809 INFO Epoch:70 train_loss:0.00644 +2025-04-19 15:36:51,466 INFO Epoch:70 val_res:0.878000 +2025-04-19 15:37:04,779 INFO Epoch:71 train_loss:0.00739 +2025-04-19 15:37:07,505 INFO Epoch:71 val_res:0.880000 +2025-04-19 15:37:21,076 INFO Epoch:72 train_loss:0.00740 +2025-04-19 15:37:23,841 INFO Epoch:72 val_res:0.900000 +2025-04-19 15:37:37,048 INFO Epoch:73 train_loss:0.00718 +2025-04-19 15:37:39,789 INFO Epoch:73 val_res:0.890000 +2025-04-19 15:37:53,787 INFO Epoch:74 train_loss:0.00717 +2025-04-19 15:37:56,418 INFO Epoch:74 val_res:0.876000 +2025-04-19 15:38:10,267 INFO Epoch:75 train_loss:0.00611 +2025-04-19 15:38:12,938 INFO Epoch:75 val_res:0.880000 +2025-04-19 15:38:26,307 INFO Epoch:76 train_loss:0.00702 +2025-04-19 15:38:28,913 INFO Epoch:76 val_res:0.880000 +2025-04-19 15:38:41,653 INFO Epoch:77 train_loss:0.00861 +2025-04-19 15:38:44,476 INFO Epoch:77 val_res:0.888000 +2025-04-19 15:38:57,734 INFO Epoch:78 train_loss:0.00705 +2025-04-19 15:39:00,459 INFO Epoch:78 val_res:0.886000 +2025-04-19 15:39:13,507 INFO Epoch:79 train_loss:0.00705 +2025-04-19 15:39:16,209 INFO Epoch:79 val_res:0.884000 +2025-04-19 15:39:29,313 INFO Epoch:80 train_loss:0.00623 +2025-04-19 15:39:31,951 INFO Epoch:80 val_res:0.884000 +2025-04-19 15:39:44,954 INFO Epoch:81 train_loss:0.00682 +2025-04-19 15:39:47,722 INFO Epoch:81 val_res:0.884000 +2025-04-19 15:40:01,544 INFO Epoch:82 train_loss:0.00665 +2025-04-19 15:40:04,216 INFO Epoch:82 val_res:0.888000 +2025-04-19 15:40:17,849 INFO Epoch:83 train_loss:0.00641 +2025-04-19 15:40:20,593 INFO Epoch:83 val_res:0.884000 +2025-04-19 15:40:34,180 INFO Epoch:84 train_loss:0.00634 +2025-04-19 15:40:36,792 INFO Epoch:84 val_res:0.886000 +2025-04-19 15:40:49,969 INFO Epoch:85 train_loss:0.00696 +2025-04-19 15:40:52,672 INFO Epoch:85 val_res:0.878000 +2025-04-19 15:41:06,121 INFO Epoch:86 train_loss:0.00742 +2025-04-19 15:41:08,753 INFO Epoch:86 val_res:0.876000 +2025-04-19 15:41:21,755 INFO Epoch:87 train_loss:0.00667 +2025-04-19 15:41:24,454 INFO Epoch:87 val_res:0.882000 +2025-04-19 15:41:37,735 INFO Epoch:88 train_loss:0.00628 +2025-04-19 15:41:40,403 INFO Epoch:88 val_res:0.890000 +2025-04-19 15:41:53,034 INFO Epoch:89 train_loss:0.00642 +2025-04-19 15:41:55,715 INFO Epoch:89 val_res:0.876000 +2025-04-19 15:42:09,021 INFO Epoch:90 train_loss:0.00745 +2025-04-19 15:42:11,608 INFO Epoch:90 val_res:0.888000 +2025-04-19 15:42:24,982 INFO Epoch:91 train_loss:0.00759 +2025-04-19 15:42:27,632 INFO Epoch:91 val_res:0.884000 +2025-04-19 15:42:40,944 INFO Epoch:92 train_loss:0.00737 +2025-04-19 15:42:43,642 INFO Epoch:92 val_res:0.870000 +2025-04-19 15:42:56,551 INFO Epoch:93 train_loss:0.02350 +2025-04-19 15:42:59,321 INFO Epoch:93 val_res:0.812000 +2025-04-19 15:43:12,594 INFO Epoch:94 train_loss:0.03090 +2025-04-19 15:43:15,254 INFO Epoch:94 val_res:0.840000 +2025-04-19 15:43:28,208 INFO Epoch:95 train_loss:0.02423 +2025-04-19 15:43:30,917 INFO Epoch:95 val_res:0.874000 +2025-04-19 15:43:44,274 INFO Epoch:96 train_loss:0.01761 +2025-04-19 15:43:46,933 INFO Epoch:96 val_res:0.882000 +2025-04-19 15:43:59,977 INFO Epoch:97 train_loss:0.00889 +2025-04-19 15:44:02,711 INFO Epoch:97 val_res:0.862000 +2025-04-19 15:44:16,299 INFO Epoch:98 train_loss:0.00552 +2025-04-19 15:44:18,911 INFO Epoch:98 val_res:0.888000 +2025-04-19 15:44:32,835 INFO Epoch:99 train_loss:0.00464 +2025-04-19 15:44:35,631 INFO Epoch:99 val_res:0.890000 +2025-04-19 15:44:35,851 INFO ===================================== +2025-04-19 15:44:35,852 INFO Start testing... +2025-04-19 15:44:35,852 INFO ===================================== +2025-04-19 15:44:38,738 INFO Incremental step 0 Testing res: 0.900000 +2025-04-19 15:44:38,740 INFO Incremental step: 1 +2025-04-19 15:45:43,946 INFO Epoch:0 train_loss:2.58083 +2025-04-19 15:45:47,573 INFO Epoch:0 val_res:0.465000 +2025-04-19 15:45:47,573 INFO Saving best model at Epoch 0 +2025-04-19 15:46:18,407 INFO Epoch:1 train_loss:1.55107 +2025-04-19 15:46:22,228 INFO Epoch:1 val_res:0.523000 +2025-04-19 15:46:22,229 INFO Saving best model at Epoch 1 +2025-04-19 15:46:52,876 INFO Epoch:2 train_loss:1.31431 +2025-04-19 15:46:56,788 INFO Epoch:2 val_res:0.545000 +2025-04-19 15:46:56,789 INFO Saving best model at Epoch 2 +2025-04-19 15:47:26,979 INFO Epoch:3 train_loss:1.22363 +2025-04-19 15:47:30,793 INFO Epoch:3 val_res:0.575000 +2025-04-19 15:47:30,793 INFO Saving best model at Epoch 3 +2025-04-19 15:47:59,396 INFO Epoch:4 train_loss:1.16331 +2025-04-19 15:48:03,218 INFO Epoch:4 val_res:0.604000 +2025-04-19 15:48:03,218 INFO Saving best model at Epoch 4 +2025-04-19 15:48:31,976 INFO Epoch:5 train_loss:1.10887 +2025-04-19 15:48:35,764 INFO Epoch:5 val_res:0.621000 +2025-04-19 15:48:35,764 INFO Saving best model at Epoch 5 +2025-04-19 15:49:04,609 INFO Epoch:6 train_loss:1.07370 +2025-04-19 15:49:08,326 INFO Epoch:6 val_res:0.643000 +2025-04-19 15:49:08,327 INFO Saving best model at Epoch 6 +2025-04-19 15:49:37,734 INFO Epoch:7 train_loss:1.03499 +2025-04-19 15:49:41,430 INFO Epoch:7 val_res:0.651000 +2025-04-19 15:49:41,430 INFO Saving best model at Epoch 7 +2025-04-19 15:50:09,862 INFO Epoch:8 train_loss:1.00111 +2025-04-19 15:50:13,686 INFO Epoch:8 val_res:0.676000 +2025-04-19 15:50:13,687 INFO Saving best model at Epoch 8 +2025-04-19 15:50:41,600 INFO Epoch:9 train_loss:0.97582 +2025-04-19 15:50:45,748 INFO Epoch:9 val_res:0.684000 +2025-04-19 15:50:45,748 INFO Saving best model at Epoch 9 +2025-04-19 15:51:15,702 INFO Epoch:10 train_loss:0.95011 +2025-04-19 15:51:20,288 INFO Epoch:10 val_res:0.697000 +2025-04-19 15:51:20,289 INFO Saving best model at Epoch 10 +2025-04-19 15:51:47,692 INFO Epoch:11 train_loss:0.91413 +2025-04-19 15:51:51,371 INFO Epoch:11 val_res:0.712000 +2025-04-19 15:51:51,372 INFO Saving best model at Epoch 11 +2025-04-19 15:52:20,971 INFO Epoch:12 train_loss:0.88811 +2025-04-19 15:52:25,573 INFO Epoch:12 val_res:0.724000 +2025-04-19 15:52:25,573 INFO Saving best model at Epoch 12 +2025-04-19 15:52:55,123 INFO Epoch:13 train_loss:0.87283 +2025-04-19 15:52:59,829 INFO Epoch:13 val_res:0.730000 +2025-04-19 15:52:59,830 INFO Saving best model at Epoch 13 +2025-04-19 15:53:27,915 INFO Epoch:14 train_loss:0.84846 +2025-04-19 15:53:32,385 INFO Epoch:14 val_res:0.742000 +2025-04-19 15:53:32,385 INFO Saving best model at Epoch 14 +2025-04-19 15:54:00,484 INFO Epoch:15 train_loss:0.83586 +2025-04-19 15:54:05,245 INFO Epoch:15 val_res:0.743000 +2025-04-19 15:54:05,246 INFO Saving best model at Epoch 15 +2025-04-19 15:54:32,851 INFO Epoch:16 train_loss:0.81822 +2025-04-19 15:54:37,188 INFO Epoch:16 val_res:0.751000 +2025-04-19 15:54:37,189 INFO Saving best model at Epoch 16 +2025-04-19 15:55:07,205 INFO Epoch:17 train_loss:0.79845 +2025-04-19 15:55:11,781 INFO Epoch:17 val_res:0.766000 +2025-04-19 15:55:11,781 INFO Saving best model at Epoch 17 +2025-04-19 15:55:41,709 INFO Epoch:18 train_loss:0.77865 +2025-04-19 15:55:46,491 INFO Epoch:18 val_res:0.757000 +2025-04-19 15:56:13,053 INFO Epoch:19 train_loss:0.77242 +2025-04-19 15:56:17,668 INFO Epoch:19 val_res:0.771000 +2025-04-19 15:56:17,669 INFO Saving best model at Epoch 19 +2025-04-19 15:56:45,461 INFO Epoch:20 train_loss:0.77231 +2025-04-19 15:56:49,239 INFO Epoch:20 val_res:0.773000 +2025-04-19 15:56:49,239 INFO Saving best model at Epoch 20 +2025-04-19 15:57:19,298 INFO Epoch:21 train_loss:0.87416 +2025-04-19 15:57:23,910 INFO Epoch:21 val_res:0.770000 +2025-04-19 15:57:52,101 INFO Epoch:22 train_loss:0.77276 +2025-04-19 15:57:56,637 INFO Epoch:22 val_res:0.784000 +2025-04-19 15:57:56,638 INFO Saving best model at Epoch 22 +2025-04-19 15:58:24,377 INFO Epoch:23 train_loss:0.73513 +2025-04-19 15:58:28,879 INFO Epoch:23 val_res:0.784000 +2025-04-19 15:58:55,986 INFO Epoch:24 train_loss:0.71724 +2025-04-19 15:59:00,432 INFO Epoch:24 val_res:0.798000 +2025-04-19 15:59:00,433 INFO Saving best model at Epoch 24 +2025-04-19 15:59:27,898 INFO Epoch:25 train_loss:0.70916 +2025-04-19 15:59:31,724 INFO Epoch:25 val_res:0.795000 +2025-04-19 15:59:59,454 INFO Epoch:26 train_loss:0.70564 +2025-04-19 16:00:03,340 INFO Epoch:26 val_res:0.794000 +2025-04-19 16:00:30,561 INFO Epoch:27 train_loss:0.69571 +2025-04-19 16:00:34,946 INFO Epoch:27 val_res:0.792000 +2025-04-19 16:01:03,050 INFO Epoch:28 train_loss:0.70033 +2025-04-19 16:01:07,698 INFO Epoch:28 val_res:0.797000 +2025-04-19 16:01:35,028 INFO Epoch:29 train_loss:0.68623 +2025-04-19 16:01:39,528 INFO Epoch:29 val_res:0.802000 +2025-04-19 16:01:39,528 INFO Saving best model at Epoch 29 +2025-04-19 16:02:08,371 INFO Epoch:30 train_loss:0.67941 +2025-04-19 16:02:13,035 INFO Epoch:30 val_res:0.811000 +2025-04-19 16:02:13,036 INFO Saving best model at Epoch 30 +2025-04-19 16:02:41,279 INFO Epoch:31 train_loss:0.66725 +2025-04-19 16:02:45,714 INFO Epoch:31 val_res:0.804000 +2025-04-19 16:03:12,366 INFO Epoch:32 train_loss:0.66527 +2025-04-19 16:03:16,848 INFO Epoch:32 val_res:0.810000 +2025-04-19 16:03:45,002 INFO Epoch:33 train_loss:0.65458 +2025-04-19 16:03:48,810 INFO Epoch:33 val_res:0.803000 +2025-04-19 16:04:16,993 INFO Epoch:34 train_loss:0.65295 +2025-04-19 16:04:21,589 INFO Epoch:34 val_res:0.806000 +2025-04-19 16:04:49,112 INFO Epoch:35 train_loss:0.65354 +2025-04-19 16:04:53,729 INFO Epoch:35 val_res:0.806000 +2025-04-19 16:05:21,777 INFO Epoch:36 train_loss:0.65210 +2025-04-19 16:05:25,940 INFO Epoch:36 val_res:0.811000 +2025-04-19 16:05:53,582 INFO Epoch:37 train_loss:0.66068 +2025-04-19 16:05:57,567 INFO Epoch:37 val_res:0.808000 +2025-04-19 16:06:25,888 INFO Epoch:38 train_loss:0.68678 +2025-04-19 16:06:30,475 INFO Epoch:38 val_res:0.802000 +2025-04-19 16:06:58,904 INFO Epoch:39 train_loss:1.05455 +2025-04-19 16:07:03,515 INFO Epoch:39 val_res:0.766000 +2025-04-19 16:07:29,992 INFO Epoch:40 train_loss:0.96656 +2025-04-19 16:07:34,404 INFO Epoch:40 val_res:0.806000 +2025-04-19 16:08:01,864 INFO Epoch:41 train_loss:0.71531 +2025-04-19 16:08:06,427 INFO Epoch:41 val_res:0.825000 +2025-04-19 16:08:06,427 INFO Saving best model at Epoch 41 +2025-04-19 16:08:36,079 INFO Epoch:42 train_loss:0.65138 +2025-04-19 16:08:40,548 INFO Epoch:42 val_res:0.813000 +2025-04-19 16:09:08,772 INFO Epoch:43 train_loss:0.62738 +2025-04-19 16:09:13,250 INFO Epoch:43 val_res:0.807000 +2025-04-19 16:09:41,645 INFO Epoch:44 train_loss:0.61773 +2025-04-19 16:09:46,280 INFO Epoch:44 val_res:0.813000 +2025-04-19 16:10:13,006 INFO Epoch:45 train_loss:0.60961 +2025-04-19 16:10:17,561 INFO Epoch:45 val_res:0.815000 +2025-04-19 16:10:44,491 INFO Epoch:46 train_loss:0.60668 +2025-04-19 16:10:49,044 INFO Epoch:46 val_res:0.811000 +2025-04-19 16:11:17,054 INFO Epoch:47 train_loss:0.60170 +2025-04-19 16:11:21,752 INFO Epoch:47 val_res:0.819000 +2025-04-19 16:11:48,797 INFO Epoch:48 train_loss:0.60061 +2025-04-19 16:11:53,535 INFO Epoch:48 val_res:0.820000 +2025-04-19 16:12:21,178 INFO Epoch:49 train_loss:0.59836 +2025-04-19 16:12:25,959 INFO Epoch:49 val_res:0.813000 +2025-04-19 16:12:52,728 INFO Epoch:50 train_loss:0.59349 +2025-04-19 16:12:57,338 INFO Epoch:50 val_res:0.816000 +2025-04-19 16:13:25,158 INFO Epoch:51 train_loss:0.58762 +2025-04-19 16:13:29,650 INFO Epoch:51 val_res:0.812000 +2025-04-19 16:13:56,745 INFO Epoch:52 train_loss:0.58654 +2025-04-19 16:14:01,375 INFO Epoch:52 val_res:0.814000 +2025-04-19 16:14:29,168 INFO Epoch:53 train_loss:0.58602 +2025-04-19 16:14:33,901 INFO Epoch:53 val_res:0.810000 +2025-04-19 16:15:00,591 INFO Epoch:54 train_loss:0.58614 +2025-04-19 16:15:05,250 INFO Epoch:54 val_res:0.806000 +2025-04-19 16:15:32,169 INFO Epoch:55 train_loss:0.57961 +2025-04-19 16:15:36,603 INFO Epoch:55 val_res:0.816000 +2025-04-19 16:16:04,059 INFO Epoch:56 train_loss:0.58358 +2025-04-19 16:16:08,769 INFO Epoch:56 val_res:0.806000 +2025-04-19 16:16:35,950 INFO Epoch:57 train_loss:0.58523 +2025-04-19 16:16:40,642 INFO Epoch:57 val_res:0.823000 +2025-04-19 16:17:08,581 INFO Epoch:58 train_loss:0.57814 +2025-04-19 16:17:13,235 INFO Epoch:58 val_res:0.811000 +2025-04-19 16:17:40,797 INFO Epoch:59 train_loss:0.57370 +2025-04-19 16:17:45,485 INFO Epoch:59 val_res:0.812000 +2025-04-19 16:18:14,582 INFO Epoch:60 train_loss:0.57517 +2025-04-19 16:18:19,388 INFO Epoch:60 val_res:0.814000 +2025-04-19 16:18:47,559 INFO Epoch:61 train_loss:0.57239 +2025-04-19 16:18:52,257 INFO Epoch:61 val_res:0.815000 +2025-04-19 16:19:19,106 INFO Epoch:62 train_loss:0.56792 +2025-04-19 16:19:23,613 INFO Epoch:62 val_res:0.816000 +2025-04-19 16:19:50,212 INFO Epoch:63 train_loss:0.57729 +2025-04-19 16:19:55,187 INFO Epoch:63 val_res:0.803000 +2025-04-19 16:20:22,599 INFO Epoch:64 train_loss:0.57035 +2025-04-19 16:20:27,177 INFO Epoch:64 val_res:0.811000 +2025-04-19 16:20:54,651 INFO Epoch:65 train_loss:0.56385 +2025-04-19 16:20:59,425 INFO Epoch:65 val_res:0.814000 +2025-04-19 16:21:27,750 INFO Epoch:66 train_loss:0.56012 +2025-04-19 16:21:32,429 INFO Epoch:66 val_res:0.816000 +2025-04-19 16:22:00,440 INFO Epoch:67 train_loss:0.55857 +2025-04-19 16:22:05,206 INFO Epoch:67 val_res:0.813000 +2025-04-19 16:22:30,920 INFO Epoch:68 train_loss:0.58486 +2025-04-19 16:22:34,624 INFO Epoch:68 val_res:0.814000 +2025-04-19 16:23:00,648 INFO Epoch:69 train_loss:0.59332 +2025-04-19 16:23:04,416 INFO Epoch:69 val_res:0.815000 +2025-04-19 16:23:31,363 INFO Epoch:70 train_loss:0.58382 +2025-04-19 16:23:35,814 INFO Epoch:70 val_res:0.806000 +2025-04-19 16:24:02,556 INFO Epoch:71 train_loss:0.57172 +2025-04-19 16:24:07,238 INFO Epoch:71 val_res:0.813000 +2025-04-19 16:24:33,777 INFO Epoch:72 train_loss:0.55777 +2025-04-19 16:24:38,249 INFO Epoch:72 val_res:0.808000 +2025-04-19 16:25:04,951 INFO Epoch:73 train_loss:0.55021 +2025-04-19 16:25:09,475 INFO Epoch:73 val_res:0.816000 +2025-04-19 16:25:37,417 INFO Epoch:74 train_loss:0.54344 +2025-04-19 16:25:42,000 INFO Epoch:74 val_res:0.820000 +2025-04-19 16:26:10,610 INFO Epoch:75 train_loss:0.54403 +2025-04-19 16:26:15,570 INFO Epoch:75 val_res:0.815000 +2025-04-19 16:26:43,561 INFO Epoch:76 train_loss:0.54975 +2025-04-19 16:26:48,139 INFO Epoch:76 val_res:0.822000 +2025-04-19 16:27:15,826 INFO Epoch:77 train_loss:0.58481 +2025-04-19 16:27:20,617 INFO Epoch:77 val_res:0.823000 +2025-04-19 16:27:50,310 INFO Epoch:78 train_loss:0.62742 +2025-04-19 16:27:55,094 INFO Epoch:78 val_res:0.802000 +2025-04-19 16:28:22,629 INFO Epoch:79 train_loss:0.79281 +2025-04-19 16:28:27,440 INFO Epoch:79 val_res:0.806000 +2025-04-19 16:28:55,904 INFO Epoch:80 train_loss:0.64556 +2025-04-19 16:29:00,599 INFO Epoch:80 val_res:0.811000 +2025-04-19 16:29:27,354 INFO Epoch:81 train_loss:0.57730 +2025-04-19 16:29:32,130 INFO Epoch:81 val_res:0.814000 +2025-04-19 16:29:59,792 INFO Epoch:82 train_loss:0.54821 +2025-04-19 16:30:04,280 INFO Epoch:82 val_res:0.819000 +2025-04-19 16:30:31,075 INFO Epoch:83 train_loss:0.53113 +2025-04-19 16:30:35,878 INFO Epoch:83 val_res:0.815000 +2025-04-19 16:31:03,731 INFO Epoch:84 train_loss:0.53513 +2025-04-19 16:31:08,428 INFO Epoch:84 val_res:0.810000 +2025-04-19 16:31:35,702 INFO Epoch:85 train_loss:0.52891 +2025-04-19 16:31:40,394 INFO Epoch:85 val_res:0.817000 +2025-04-19 16:32:08,261 INFO Epoch:86 train_loss:0.52674 +2025-04-19 16:32:12,829 INFO Epoch:86 val_res:0.812000 +2025-04-19 16:32:41,695 INFO Epoch:87 train_loss:0.52679 +2025-04-19 16:32:46,975 INFO Epoch:87 val_res:0.818000 +2025-04-19 16:33:16,029 INFO Epoch:88 train_loss:0.52475 +2025-04-19 16:33:20,847 INFO Epoch:88 val_res:0.826000 +2025-04-19 16:33:20,848 INFO Saving best model at Epoch 88 +2025-04-19 16:33:50,124 INFO Epoch:89 train_loss:0.53020 +2025-04-19 16:33:54,675 INFO Epoch:89 val_res:0.817000 +2025-04-19 16:34:21,918 INFO Epoch:90 train_loss:0.52401 +2025-04-19 16:34:26,493 INFO Epoch:90 val_res:0.819000 +2025-04-19 16:34:55,440 INFO Epoch:91 train_loss:0.52391 +2025-04-19 16:35:00,126 INFO Epoch:91 val_res:0.822000 +2025-04-19 16:35:27,922 INFO Epoch:92 train_loss:0.52256 +2025-04-19 16:35:32,577 INFO Epoch:92 val_res:0.824000 +2025-04-19 16:36:01,114 INFO Epoch:93 train_loss:0.53070 +2025-04-19 16:36:05,542 INFO Epoch:93 val_res:0.810000 +2025-04-19 16:36:33,083 INFO Epoch:94 train_loss:0.52883 +2025-04-19 16:36:37,664 INFO Epoch:94 val_res:0.822000 +2025-04-19 16:37:06,046 INFO Epoch:95 train_loss:0.52945 +2025-04-19 16:37:10,509 INFO Epoch:95 val_res:0.827000 +2025-04-19 16:37:10,509 INFO Saving best model at Epoch 95 +2025-04-19 16:37:39,907 INFO Epoch:96 train_loss:0.54487 +2025-04-19 16:37:44,474 INFO Epoch:96 val_res:0.825000 +2025-04-19 16:38:11,605 INFO Epoch:97 train_loss:0.54248 +2025-04-19 16:38:16,161 INFO Epoch:97 val_res:0.819000 +2025-04-19 16:38:44,193 INFO Epoch:98 train_loss:0.53973 +2025-04-19 16:38:48,657 INFO Epoch:98 val_res:0.809000 +2025-04-19 16:39:15,915 INFO Epoch:99 train_loss:0.53361 +2025-04-19 16:39:20,335 INFO Epoch:99 val_res:0.812000 +2025-04-19 16:39:20,661 INFO ===================================== +2025-04-19 16:39:20,661 INFO Start testing... +2025-04-19 16:39:20,662 INFO ===================================== +2025-04-19 16:39:25,413 INFO Incremental step 1 Testing res: 0.808000 +2025-04-19 16:39:25,415 INFO forgetting: 0.122000 +2025-04-19 16:39:25,427 INFO Incremental step: 2 +2025-04-19 16:42:13,018 INFO Epoch:0 train_loss:3.66610 +2025-04-19 16:42:17,691 INFO Epoch:0 val_res:0.530000 +2025-04-19 16:42:17,692 INFO Saving best model at Epoch 0 +2025-04-19 16:42:50,510 INFO Epoch:1 train_loss:1.34315 +2025-04-19 16:42:55,306 INFO Epoch:1 val_res:0.558000 +2025-04-19 16:42:55,307 INFO Saving best model at Epoch 1 +2025-04-19 16:43:27,906 INFO Epoch:2 train_loss:0.97600 +2025-04-19 16:43:32,811 INFO Epoch:2 val_res:0.572667 +2025-04-19 16:43:32,811 INFO Saving best model at Epoch 2 +2025-04-19 16:44:03,877 INFO Epoch:3 train_loss:0.87677 +2025-04-19 16:44:08,722 INFO Epoch:3 val_res:0.584667 +2025-04-19 16:44:08,722 INFO Saving best model at Epoch 3 +2025-04-19 16:44:39,780 INFO Epoch:4 train_loss:0.83039 +2025-04-19 16:44:44,366 INFO Epoch:4 val_res:0.592000 +2025-04-19 16:44:44,366 INFO Saving best model at Epoch 4 +2025-04-19 16:45:15,043 INFO Epoch:5 train_loss:0.79812 +2025-04-19 16:45:19,704 INFO Epoch:5 val_res:0.600667 +2025-04-19 16:45:19,704 INFO Saving best model at Epoch 5 +2025-04-19 16:45:49,975 INFO Epoch:6 train_loss:0.77329 +2025-04-19 16:45:54,794 INFO Epoch:6 val_res:0.616000 +2025-04-19 16:45:54,794 INFO Saving best model at Epoch 6 +2025-04-19 16:46:26,011 INFO Epoch:7 train_loss:0.74970 +2025-04-19 16:46:30,905 INFO Epoch:7 val_res:0.623333 +2025-04-19 16:46:30,905 INFO Saving best model at Epoch 7 +2025-04-19 16:47:01,949 INFO Epoch:8 train_loss:0.73306 +2025-04-19 16:47:07,019 INFO Epoch:8 val_res:0.626667 +2025-04-19 16:47:07,020 INFO Saving best model at Epoch 8 +2025-04-19 16:47:37,372 INFO Epoch:9 train_loss:0.71867 +2025-04-19 16:47:42,083 INFO Epoch:9 val_res:0.638667 +2025-04-19 16:47:42,084 INFO Saving best model at Epoch 9 +2025-04-19 16:48:12,836 INFO Epoch:10 train_loss:0.69911 +2025-04-19 16:48:17,843 INFO Epoch:10 val_res:0.648000 +2025-04-19 16:48:17,843 INFO Saving best model at Epoch 10 +2025-04-19 16:48:48,863 INFO Epoch:11 train_loss:0.68516 +2025-04-19 16:48:53,585 INFO Epoch:11 val_res:0.656667 +2025-04-19 16:48:53,586 INFO Saving best model at Epoch 11 +2025-04-19 16:49:25,076 INFO Epoch:12 train_loss:0.67339 +2025-04-19 16:49:29,838 INFO Epoch:12 val_res:0.664667 +2025-04-19 16:49:29,839 INFO Saving best model at Epoch 12 +2025-04-19 16:50:00,074 INFO Epoch:13 train_loss:0.66492 +2025-04-19 16:50:04,756 INFO Epoch:13 val_res:0.672000 +2025-04-19 16:50:04,756 INFO Saving best model at Epoch 13 +2025-04-19 16:50:35,111 INFO Epoch:14 train_loss:0.65099 +2025-04-19 16:50:39,731 INFO Epoch:14 val_res:0.678000 +2025-04-19 16:50:39,731 INFO Saving best model at Epoch 14 +2025-04-19 16:51:11,251 INFO Epoch:15 train_loss:0.64229 +2025-04-19 16:51:15,888 INFO Epoch:15 val_res:0.686000 +2025-04-19 16:51:15,888 INFO Saving best model at Epoch 15 +2025-04-19 16:51:46,836 INFO Epoch:16 train_loss:0.63594 +2025-04-19 16:51:51,374 INFO Epoch:16 val_res:0.694667 +2025-04-19 16:51:51,375 INFO Saving best model at Epoch 16 +2025-04-19 16:52:23,397 INFO Epoch:17 train_loss:0.63068 +2025-04-19 16:52:28,128 INFO Epoch:17 val_res:0.698000 +2025-04-19 16:52:28,128 INFO Saving best model at Epoch 17 +2025-04-19 16:52:58,632 INFO Epoch:18 train_loss:0.62024 +2025-04-19 16:53:03,153 INFO Epoch:18 val_res:0.708000 +2025-04-19 16:53:03,153 INFO Saving best model at Epoch 18 +2025-04-19 16:53:35,218 INFO Epoch:19 train_loss:0.61529 +2025-04-19 16:53:39,791 INFO Epoch:19 val_res:0.703333 +2025-04-19 16:54:10,556 INFO Epoch:20 train_loss:0.62260 +2025-04-19 16:54:15,372 INFO Epoch:20 val_res:0.714667 +2025-04-19 16:54:15,373 INFO Saving best model at Epoch 20 +2025-04-19 16:54:46,328 INFO Epoch:21 train_loss:0.60808 +2025-04-19 16:54:51,152 INFO Epoch:21 val_res:0.714667 +2025-04-19 16:55:21,432 INFO Epoch:22 train_loss:0.61039 +2025-04-19 16:55:26,318 INFO Epoch:22 val_res:0.729333 +2025-04-19 16:55:26,319 INFO Saving best model at Epoch 22 +2025-04-19 16:55:57,392 INFO Epoch:23 train_loss:0.59349 +2025-04-19 16:56:02,216 INFO Epoch:23 val_res:0.734000 +2025-04-19 16:56:02,217 INFO Saving best model at Epoch 23 +2025-04-19 16:56:32,888 INFO Epoch:24 train_loss:0.59908 +2025-04-19 16:56:37,590 INFO Epoch:24 val_res:0.732000 +2025-04-19 16:57:06,197 INFO Epoch:25 train_loss:0.58831 +2025-04-19 16:57:10,908 INFO Epoch:25 val_res:0.735333 +2025-04-19 16:57:10,908 INFO Saving best model at Epoch 25 +2025-04-19 16:57:40,777 INFO Epoch:26 train_loss:0.59842 +2025-04-19 16:57:45,853 INFO Epoch:26 val_res:0.740667 +2025-04-19 16:57:45,853 INFO Saving best model at Epoch 26 +2025-04-19 16:58:16,511 INFO Epoch:27 train_loss:0.59445 +2025-04-19 16:58:21,118 INFO Epoch:27 val_res:0.752000 +2025-04-19 16:58:21,118 INFO Saving best model at Epoch 27 +2025-04-19 16:58:51,375 INFO Epoch:28 train_loss:1.47565 +2025-04-19 16:58:55,939 INFO Epoch:28 val_res:0.656667 +2025-04-19 16:59:24,687 INFO Epoch:29 train_loss:2.39343 +2025-04-19 16:59:30,077 INFO Epoch:29 val_res:0.728667 +2025-04-19 16:59:58,662 INFO Epoch:30 train_loss:0.87712 +2025-04-19 17:00:03,223 INFO Epoch:30 val_res:0.764000 +2025-04-19 17:00:03,224 INFO Saving best model at Epoch 30 +2025-04-19 17:00:35,057 INFO Epoch:31 train_loss:0.63022 +2025-04-19 17:00:40,245 INFO Epoch:31 val_res:0.768000 +2025-04-19 17:00:40,246 INFO Saving best model at Epoch 31 +2025-04-19 17:01:12,044 INFO Epoch:32 train_loss:0.58459 +2025-04-19 17:01:16,907 INFO Epoch:32 val_res:0.765333 +2025-04-19 17:01:47,329 INFO Epoch:33 train_loss:0.56937 +2025-04-19 17:01:52,167 INFO Epoch:33 val_res:0.767333 +2025-04-19 17:02:21,814 INFO Epoch:34 train_loss:0.56139 +2025-04-19 17:02:26,718 INFO Epoch:34 val_res:0.766000 +2025-04-19 17:02:56,277 INFO Epoch:35 train_loss:0.55398 +2025-04-19 17:03:00,992 INFO Epoch:35 val_res:0.764667 +2025-04-19 17:03:29,912 INFO Epoch:36 train_loss:0.55080 +2025-04-19 17:03:34,667 INFO Epoch:36 val_res:0.769333 +2025-04-19 17:03:34,670 INFO Saving best model at Epoch 36 +2025-04-19 17:04:05,032 INFO Epoch:37 train_loss:0.54596 +2025-04-19 17:04:09,773 INFO Epoch:37 val_res:0.770000 +2025-04-19 17:04:09,774 INFO Saving best model at Epoch 37 +2025-04-19 17:04:40,589 INFO Epoch:38 train_loss:0.54006 +2025-04-19 17:04:45,306 INFO Epoch:38 val_res:0.770667 +2025-04-19 17:04:45,307 INFO Saving best model at Epoch 38 +2025-04-19 17:05:15,856 INFO Epoch:39 train_loss:0.53652 +2025-04-19 17:05:20,589 INFO Epoch:39 val_res:0.776000 +2025-04-19 17:05:20,589 INFO Saving best model at Epoch 39 +2025-04-19 17:05:51,955 INFO Epoch:40 train_loss:0.53787 +2025-04-19 17:05:56,583 INFO Epoch:40 val_res:0.776000 +2025-04-19 17:06:25,634 INFO Epoch:41 train_loss:0.53105 +2025-04-19 17:06:30,289 INFO Epoch:41 val_res:0.770000 +2025-04-19 17:06:59,466 INFO Epoch:42 train_loss:0.53332 +2025-04-19 17:07:04,010 INFO Epoch:42 val_res:0.776000 +2025-04-19 17:07:33,290 INFO Epoch:43 train_loss:0.52998 +2025-04-19 17:07:37,816 INFO Epoch:43 val_res:0.776000 +2025-04-19 17:08:07,847 INFO Epoch:44 train_loss:0.52894 +2025-04-19 17:08:12,324 INFO Epoch:44 val_res:0.770000 +2025-04-19 17:08:42,771 INFO Epoch:45 train_loss:0.52612 +2025-04-19 17:08:47,556 INFO Epoch:45 val_res:0.774000 +2025-04-19 17:09:17,764 INFO Epoch:46 train_loss:0.52246 +2025-04-19 17:09:22,638 INFO Epoch:46 val_res:0.774000 +2025-04-19 17:09:52,909 INFO Epoch:47 train_loss:0.52256 +2025-04-19 17:09:57,988 INFO Epoch:47 val_res:0.775333 +2025-04-19 17:10:28,904 INFO Epoch:48 train_loss:0.52206 +2025-04-19 17:10:33,691 INFO Epoch:48 val_res:0.768000 +2025-04-19 17:11:04,001 INFO Epoch:49 train_loss:0.52520 +2025-04-19 17:11:08,793 INFO Epoch:49 val_res:0.777333 +2025-04-19 17:11:08,793 INFO Saving best model at Epoch 49 +2025-04-19 17:11:38,863 INFO Epoch:50 train_loss:0.53694 +2025-04-19 17:11:43,728 INFO Epoch:50 val_res:0.774667 +2025-04-19 17:12:13,974 INFO Epoch:51 train_loss:0.52879 +2025-04-19 17:12:18,528 INFO Epoch:51 val_res:0.775333 +2025-04-19 17:12:47,774 INFO Epoch:52 train_loss:0.52612 +2025-04-19 17:12:52,739 INFO Epoch:52 val_res:0.775333 +2025-04-19 17:13:22,327 INFO Epoch:53 train_loss:0.52975 +2025-04-19 17:13:27,133 INFO Epoch:53 val_res:0.774667 +2025-04-19 17:13:56,305 INFO Epoch:54 train_loss:0.53234 +2025-04-19 17:14:01,409 INFO Epoch:54 val_res:0.776000 +2025-04-19 17:14:29,885 INFO Epoch:55 train_loss:0.53631 +2025-04-19 17:14:34,499 INFO Epoch:55 val_res:0.772000 +2025-04-19 17:15:03,486 INFO Epoch:56 train_loss:0.52308 +2025-04-19 17:15:08,113 INFO Epoch:56 val_res:0.770000 +2025-04-19 17:15:37,623 INFO Epoch:57 train_loss:0.52055 +2025-04-19 17:15:42,323 INFO Epoch:57 val_res:0.774667 +2025-04-19 17:16:13,303 INFO Epoch:58 train_loss:0.51601 +2025-04-19 17:16:18,446 INFO Epoch:58 val_res:0.773333 +2025-04-19 17:16:48,153 INFO Epoch:59 train_loss:0.56152 +2025-04-19 17:16:53,076 INFO Epoch:59 val_res:0.765333 +2025-04-19 17:17:22,295 INFO Epoch:60 train_loss:0.57269 +2025-04-19 17:17:27,271 INFO Epoch:60 val_res:0.774000 +2025-04-19 17:17:56,027 INFO Epoch:61 train_loss:0.55279 +2025-04-19 17:18:01,016 INFO Epoch:61 val_res:0.772000 +2025-04-19 17:18:30,660 INFO Epoch:62 train_loss:0.52426 +2025-04-19 17:18:35,614 INFO Epoch:62 val_res:0.782000 +2025-04-19 17:18:35,614 INFO Saving best model at Epoch 62 +2025-04-19 17:19:06,540 INFO Epoch:63 train_loss:0.52458 +2025-04-19 17:19:11,378 INFO Epoch:63 val_res:0.773333 +2025-04-19 17:19:40,651 INFO Epoch:64 train_loss:0.51565 +2025-04-19 17:19:45,449 INFO Epoch:64 val_res:0.779333 +2025-04-19 17:20:15,267 INFO Epoch:65 train_loss:0.51879 +2025-04-19 17:20:20,220 INFO Epoch:65 val_res:0.777333 +2025-04-19 17:20:50,107 INFO Epoch:66 train_loss:0.54668 +2025-04-19 17:20:55,084 INFO Epoch:66 val_res:0.773333 +2025-04-19 17:21:24,219 INFO Epoch:67 train_loss:0.54288 +2025-04-19 17:21:29,141 INFO Epoch:67 val_res:0.780000 +2025-04-19 17:21:58,496 INFO Epoch:68 train_loss:0.53255 +2025-04-19 17:22:03,126 INFO Epoch:68 val_res:0.768000 +2025-04-19 17:22:32,693 INFO Epoch:69 train_loss:0.58114 +2025-04-19 17:22:37,426 INFO Epoch:69 val_res:0.776667 +2025-04-19 17:23:07,115 INFO Epoch:70 train_loss:0.53146 +2025-04-19 17:23:11,857 INFO Epoch:70 val_res:0.772667 +2025-04-19 17:23:42,208 INFO Epoch:71 train_loss:0.53893 +2025-04-19 17:23:47,246 INFO Epoch:71 val_res:0.777333 +2025-04-19 17:24:17,458 INFO Epoch:72 train_loss:0.51079 +2025-04-19 17:24:22,325 INFO Epoch:72 val_res:0.778000 +2025-04-19 17:24:51,240 INFO Epoch:73 train_loss:0.51028 +2025-04-19 17:24:55,992 INFO Epoch:73 val_res:0.777333 +2025-04-19 17:25:26,425 INFO Epoch:74 train_loss:0.50753 +2025-04-19 17:25:31,404 INFO Epoch:74 val_res:0.772667 +2025-04-19 17:26:00,819 INFO Epoch:75 train_loss:0.51874 +2025-04-19 17:26:05,633 INFO Epoch:75 val_res:0.772667 +2025-04-19 17:26:35,897 INFO Epoch:76 train_loss:0.52469 +2025-04-19 17:26:41,171 INFO Epoch:76 val_res:0.766000 +2025-04-19 17:27:10,323 INFO Epoch:77 train_loss:0.52397 +2025-04-19 17:27:15,228 INFO Epoch:77 val_res:0.780667 +2025-04-19 17:27:44,846 INFO Epoch:78 train_loss:0.50815 +2025-04-19 17:27:49,679 INFO Epoch:78 val_res:0.774000 +2025-04-19 17:28:20,123 INFO Epoch:79 train_loss:0.50130 +2025-04-19 17:28:25,202 INFO Epoch:79 val_res:0.772667 +2025-04-19 17:28:55,151 INFO Epoch:80 train_loss:0.50444 +2025-04-19 17:29:00,104 INFO Epoch:80 val_res:0.776000 +2025-04-19 17:29:29,516 INFO Epoch:81 train_loss:0.51748 +2025-04-19 17:29:34,382 INFO Epoch:81 val_res:0.778000 +2025-04-19 17:30:04,188 INFO Epoch:82 train_loss:0.54140 +2025-04-19 17:30:08,813 INFO Epoch:82 val_res:0.769333 +2025-04-19 17:30:37,917 INFO Epoch:83 train_loss:0.64774 +2025-04-19 17:30:42,866 INFO Epoch:83 val_res:0.771333 +2025-04-19 17:31:12,982 INFO Epoch:84 train_loss:0.66874 +2025-04-19 17:31:17,659 INFO Epoch:84 val_res:0.776000 +2025-04-19 17:31:47,340 INFO Epoch:85 train_loss:0.59385 +2025-04-19 17:31:51,972 INFO Epoch:85 val_res:0.775333 +2025-04-19 17:32:23,029 INFO Epoch:86 train_loss:0.54476 +2025-04-19 17:32:27,952 INFO Epoch:86 val_res:0.777333 +2025-04-19 17:32:57,865 INFO Epoch:87 train_loss:0.52890 +2025-04-19 17:33:02,782 INFO Epoch:87 val_res:0.770667 +2025-04-19 17:33:32,852 INFO Epoch:88 train_loss:0.50504 +2025-04-19 17:33:37,811 INFO Epoch:88 val_res:0.777333 +2025-04-19 17:34:07,815 INFO Epoch:89 train_loss:0.50199 +2025-04-19 17:34:12,771 INFO Epoch:89 val_res:0.772000 +2025-04-19 17:34:42,748 INFO Epoch:90 train_loss:0.49669 +2025-04-19 17:34:47,875 INFO Epoch:90 val_res:0.774000 +2025-04-19 17:35:17,491 INFO Epoch:91 train_loss:0.49700 +2025-04-19 17:35:22,265 INFO Epoch:91 val_res:0.773333 +2025-04-19 17:35:52,149 INFO Epoch:92 train_loss:0.49241 +2025-04-19 17:35:57,106 INFO Epoch:92 val_res:0.772667 +2025-04-19 17:36:26,881 INFO Epoch:93 train_loss:0.49142 +2025-04-19 17:36:31,824 INFO Epoch:93 val_res:0.775333 +2025-04-19 17:37:02,271 INFO Epoch:94 train_loss:0.50295 +2025-04-19 17:37:07,087 INFO Epoch:94 val_res:0.776667 +2025-04-19 17:37:36,907 INFO Epoch:95 train_loss:0.51294 +2025-04-19 17:37:41,654 INFO Epoch:95 val_res:0.772667 +2025-04-19 17:38:10,960 INFO Epoch:96 train_loss:0.51688 +2025-04-19 17:38:15,774 INFO Epoch:96 val_res:0.771333 +2025-04-19 17:38:45,560 INFO Epoch:97 train_loss:0.54432 +2025-04-19 17:38:50,769 INFO Epoch:97 val_res:0.772667 +2025-04-19 17:39:20,594 INFO Epoch:98 train_loss:0.56169 +2025-04-19 17:39:25,676 INFO Epoch:98 val_res:0.781333 +2025-04-19 17:39:54,794 INFO Epoch:99 train_loss:0.66591 +2025-04-19 17:39:59,706 INFO Epoch:99 val_res:0.778667 +2025-04-19 17:39:59,891 INFO ===================================== +2025-04-19 17:39:59,891 INFO Start testing... +2025-04-19 17:39:59,892 INFO ===================================== +2025-04-19 17:40:04,788 INFO Incremental step 2 Testing res: 0.778667 +2025-04-19 17:40:04,790 INFO forgetting: 0.085000 +2025-04-19 17:40:04,794 INFO Incremental step: 3 +2025-04-19 17:42:21,349 INFO Epoch:0 train_loss:4.36187 +2025-04-19 17:42:27,596 INFO Epoch:0 val_res:0.572500 +2025-04-19 17:42:27,597 INFO Saving best model at Epoch 0 +2025-04-19 17:42:57,663 INFO Epoch:1 train_loss:1.49142 +2025-04-19 17:43:03,750 INFO Epoch:1 val_res:0.595500 +2025-04-19 17:43:03,750 INFO Saving best model at Epoch 1 +2025-04-19 17:43:34,750 INFO Epoch:2 train_loss:1.08753 +2025-04-19 17:43:40,882 INFO Epoch:2 val_res:0.602000 +2025-04-19 17:43:40,882 INFO Saving best model at Epoch 2 +2025-04-19 17:44:11,861 INFO Epoch:3 train_loss:0.97995 +2025-04-19 17:44:17,933 INFO Epoch:3 val_res:0.603500 +2025-04-19 17:44:17,933 INFO Saving best model at Epoch 3 +2025-04-19 17:44:47,914 INFO Epoch:4 train_loss:0.93537 +2025-04-19 17:44:53,829 INFO Epoch:4 val_res:0.607500 +2025-04-19 17:44:53,829 INFO Saving best model at Epoch 4 +2025-04-19 17:45:24,580 INFO Epoch:5 train_loss:0.90179 +2025-04-19 17:45:30,563 INFO Epoch:5 val_res:0.609000 +2025-04-19 17:45:30,563 INFO Saving best model at Epoch 5 +2025-04-19 17:46:01,219 INFO Epoch:6 train_loss:0.87276 +2025-04-19 17:46:07,598 INFO Epoch:6 val_res:0.611500 +2025-04-19 17:46:07,598 INFO Saving best model at Epoch 6 +2025-04-19 17:46:39,166 INFO Epoch:7 train_loss:0.85475 +2025-04-19 17:46:45,746 INFO Epoch:7 val_res:0.616500 +2025-04-19 17:46:45,747 INFO Saving best model at Epoch 7 +2025-04-19 17:47:17,795 INFO Epoch:8 train_loss:0.84000 +2025-04-19 17:47:24,023 INFO Epoch:8 val_res:0.619000 +2025-04-19 17:47:24,023 INFO Saving best model at Epoch 8 +2025-04-19 17:47:55,525 INFO Epoch:9 train_loss:0.82417 +2025-04-19 17:48:01,945 INFO Epoch:9 val_res:0.626500 +2025-04-19 17:48:01,945 INFO Saving best model at Epoch 9 +2025-04-19 17:48:33,565 INFO Epoch:10 train_loss:0.80767 +2025-04-19 17:48:39,753 INFO Epoch:10 val_res:0.627000 +2025-04-19 17:48:39,754 INFO Saving best model at Epoch 10 +2025-04-19 17:49:11,516 INFO Epoch:11 train_loss:0.78958 +2025-04-19 17:49:17,673 INFO Epoch:11 val_res:0.636000 +2025-04-19 17:49:17,674 INFO Saving best model at Epoch 11 +2025-04-19 17:49:50,027 INFO Epoch:12 train_loss:0.78022 +2025-04-19 17:49:55,822 INFO Epoch:12 val_res:0.638500 +2025-04-19 17:49:55,822 INFO Saving best model at Epoch 12 +2025-04-19 17:50:29,112 INFO Epoch:13 train_loss:0.76626 +2025-04-19 17:50:35,222 INFO Epoch:13 val_res:0.643500 +2025-04-19 17:50:35,223 INFO Saving best model at Epoch 13 +2025-04-19 17:51:09,496 INFO Epoch:14 train_loss:0.75361 +2025-04-19 17:51:15,778 INFO Epoch:14 val_res:0.650000 +2025-04-19 17:51:15,778 INFO Saving best model at Epoch 14 +2025-04-19 17:51:47,452 INFO Epoch:15 train_loss:0.74559 +2025-04-19 17:51:53,752 INFO Epoch:15 val_res:0.655000 +2025-04-19 17:51:53,758 INFO Saving best model at Epoch 15 +2025-04-19 17:52:25,985 INFO Epoch:16 train_loss:0.72896 +2025-04-19 17:52:32,207 INFO Epoch:16 val_res:0.660500 +2025-04-19 17:52:32,208 INFO Saving best model at Epoch 16 +2025-04-19 17:53:03,911 INFO Epoch:17 train_loss:0.72485 +2025-04-19 17:53:10,238 INFO Epoch:17 val_res:0.666000 +2025-04-19 17:53:10,239 INFO Saving best model at Epoch 17 +2025-04-19 17:53:41,373 INFO Epoch:18 train_loss:0.71900 +2025-04-19 17:53:47,435 INFO Epoch:18 val_res:0.670500 +2025-04-19 17:53:47,436 INFO Saving best model at Epoch 18 +2025-04-19 17:54:18,586 INFO Epoch:19 train_loss:0.70661 +2025-04-19 17:54:24,600 INFO Epoch:19 val_res:0.678000 +2025-04-19 17:54:24,600 INFO Saving best model at Epoch 19 +2025-04-19 17:54:55,995 INFO Epoch:20 train_loss:0.70988 +2025-04-19 17:55:02,133 INFO Epoch:20 val_res:0.676500 +2025-04-19 17:55:32,913 INFO Epoch:21 train_loss:0.70633 +2025-04-19 17:55:38,993 INFO Epoch:21 val_res:0.686000 +2025-04-19 17:55:38,993 INFO Saving best model at Epoch 21 +2025-04-19 17:56:09,245 INFO Epoch:22 train_loss:0.69476 +2025-04-19 17:56:15,445 INFO Epoch:22 val_res:0.681500 +2025-04-19 17:56:44,967 INFO Epoch:23 train_loss:0.68794 +2025-04-19 17:56:51,159 INFO Epoch:23 val_res:0.685500 +2025-04-19 17:57:20,500 INFO Epoch:24 train_loss:0.68725 +2025-04-19 17:57:27,072 INFO Epoch:24 val_res:0.688500 +2025-04-19 17:57:27,073 INFO Saving best model at Epoch 24 +2025-04-19 17:57:58,437 INFO Epoch:25 train_loss:0.69665 +2025-04-19 17:58:04,329 INFO Epoch:25 val_res:0.693500 +2025-04-19 17:58:04,329 INFO Saving best model at Epoch 25 +2025-04-19 17:58:35,375 INFO Epoch:26 train_loss:0.67681 +2025-04-19 17:58:41,283 INFO Epoch:26 val_res:0.698500 +2025-04-19 17:58:41,283 INFO Saving best model at Epoch 26 +2025-04-19 17:59:13,512 INFO Epoch:27 train_loss:0.66908 +2025-04-19 17:59:20,021 INFO Epoch:27 val_res:0.700000 +2025-04-19 17:59:20,022 INFO Saving best model at Epoch 27 +2025-04-19 17:59:51,336 INFO Epoch:28 train_loss:0.69590 +2025-04-19 17:59:57,215 INFO Epoch:28 val_res:0.697500 +2025-04-19 18:00:26,807 INFO Epoch:29 train_loss:0.66042 +2025-04-19 18:00:32,750 INFO Epoch:29 val_res:0.705500 +2025-04-19 18:00:32,751 INFO Saving best model at Epoch 29 +2025-04-19 18:01:05,142 INFO Epoch:30 train_loss:0.64697 +2025-04-19 18:01:11,178 INFO Epoch:30 val_res:0.717000 +2025-04-19 18:01:11,179 INFO Saving best model at Epoch 30 +2025-04-19 18:01:43,342 INFO Epoch:31 train_loss:0.65034 +2025-04-19 18:01:49,587 INFO Epoch:31 val_res:0.711000 +2025-04-19 18:02:20,122 INFO Epoch:32 train_loss:0.64276 +2025-04-19 18:02:26,463 INFO Epoch:32 val_res:0.711000 +2025-04-19 18:02:57,407 INFO Epoch:33 train_loss:0.63258 +2025-04-19 18:03:03,261 INFO Epoch:33 val_res:0.711500 +2025-04-19 18:03:34,283 INFO Epoch:34 train_loss:0.62726 +2025-04-19 18:03:40,432 INFO Epoch:34 val_res:0.703500 +2025-04-19 18:04:10,934 INFO Epoch:35 train_loss:0.64602 +2025-04-19 18:04:17,012 INFO Epoch:35 val_res:0.712000 +2025-04-19 18:04:47,176 INFO Epoch:36 train_loss:0.61262 +2025-04-19 18:04:53,410 INFO Epoch:36 val_res:0.706000 +2025-04-19 18:05:23,452 INFO Epoch:37 train_loss:0.60567 +2025-04-19 18:05:29,337 INFO Epoch:37 val_res:0.717500 +2025-04-19 18:05:29,337 INFO Saving best model at Epoch 37 +2025-04-19 18:06:00,612 INFO Epoch:38 train_loss:0.62600 +2025-04-19 18:06:06,580 INFO Epoch:38 val_res:0.715500 +2025-04-19 18:06:36,529 INFO Epoch:39 train_loss:0.65619 +2025-04-19 18:06:42,861 INFO Epoch:39 val_res:0.718500 +2025-04-19 18:06:42,862 INFO Saving best model at Epoch 39 +2025-04-19 18:07:13,831 INFO Epoch:40 train_loss:0.64391 +2025-04-19 18:07:19,683 INFO Epoch:40 val_res:0.720500 +2025-04-19 18:07:19,683 INFO Saving best model at Epoch 40 +2025-04-19 18:07:50,883 INFO Epoch:41 train_loss:0.66043 +2025-04-19 18:07:56,793 INFO Epoch:41 val_res:0.728500 +2025-04-19 18:07:56,793 INFO Saving best model at Epoch 41 +2025-04-19 18:08:28,259 INFO Epoch:42 train_loss:0.62264 +2025-04-19 18:08:34,115 INFO Epoch:42 val_res:0.728500 +2025-04-19 18:09:05,831 INFO Epoch:43 train_loss:0.59477 +2025-04-19 18:09:12,025 INFO Epoch:43 val_res:0.732000 +2025-04-19 18:09:12,025 INFO Saving best model at Epoch 43 +2025-04-19 18:09:46,027 INFO Epoch:44 train_loss:0.63379 +2025-04-19 18:09:52,259 INFO Epoch:44 val_res:0.724000 +2025-04-19 18:10:22,175 INFO Epoch:45 train_loss:0.69329 +2025-04-19 18:10:28,410 INFO Epoch:45 val_res:0.730000 +2025-04-19 18:10:59,075 INFO Epoch:46 train_loss:0.63098 +2025-04-19 18:11:05,518 INFO Epoch:46 val_res:0.732500 +2025-04-19 18:11:05,519 INFO Saving best model at Epoch 46 +2025-04-19 18:11:37,624 INFO Epoch:47 train_loss:0.59547 +2025-04-19 18:11:43,875 INFO Epoch:47 val_res:0.729000 +2025-04-19 18:12:13,566 INFO Epoch:48 train_loss:0.61648 +2025-04-19 18:12:19,708 INFO Epoch:48 val_res:0.733000 +2025-04-19 18:12:19,708 INFO Saving best model at Epoch 48 +2025-04-19 18:12:51,055 INFO Epoch:49 train_loss:0.62539 +2025-04-19 18:12:57,387 INFO Epoch:49 val_res:0.733500 +2025-04-19 18:12:57,388 INFO Saving best model at Epoch 49 +2025-04-19 18:13:30,385 INFO Epoch:50 train_loss:0.61824 +2025-04-19 18:13:37,326 INFO Epoch:50 val_res:0.734500 +2025-04-19 18:13:37,327 INFO Saving best model at Epoch 50 +2025-04-19 18:14:09,206 INFO Epoch:51 train_loss:0.60101 +2025-04-19 18:14:15,370 INFO Epoch:51 val_res:0.738500 +2025-04-19 18:14:15,371 INFO Saving best model at Epoch 51 +2025-04-19 18:14:46,941 INFO Epoch:52 train_loss:0.58545 +2025-04-19 18:14:53,135 INFO Epoch:52 val_res:0.736000 +2025-04-19 18:15:22,948 INFO Epoch:53 train_loss:0.56562 +2025-04-19 18:15:29,061 INFO Epoch:53 val_res:0.728000 +2025-04-19 18:15:58,333 INFO Epoch:54 train_loss:0.55435 +2025-04-19 18:16:04,409 INFO Epoch:54 val_res:0.738500 +2025-04-19 18:16:33,994 INFO Epoch:55 train_loss:0.56100 +2025-04-19 18:16:40,176 INFO Epoch:55 val_res:0.734000 +2025-04-19 18:17:09,322 INFO Epoch:56 train_loss:0.59221 +2025-04-19 18:17:15,549 INFO Epoch:56 val_res:0.734500 +2025-04-19 18:17:45,580 INFO Epoch:57 train_loss:0.57612 +2025-04-19 18:17:51,468 INFO Epoch:57 val_res:0.729000 +2025-04-19 18:18:21,201 INFO Epoch:58 train_loss:0.56985 +2025-04-19 18:18:27,134 INFO Epoch:58 val_res:0.723000 +2025-04-19 18:18:57,820 INFO Epoch:59 train_loss:0.56744 +2025-04-19 18:19:03,674 INFO Epoch:59 val_res:0.728500 +2025-04-19 18:19:34,608 INFO Epoch:60 train_loss:0.59490 +2025-04-19 18:19:40,722 INFO Epoch:60 val_res:0.734000 +2025-04-19 18:20:12,384 INFO Epoch:61 train_loss:0.66529 +2025-04-19 18:20:18,652 INFO Epoch:61 val_res:0.736000 +2025-04-19 18:20:48,784 INFO Epoch:62 train_loss:0.69624 +2025-04-19 18:20:55,549 INFO Epoch:62 val_res:0.729500 +2025-04-19 18:21:25,223 INFO Epoch:63 train_loss:0.65224 +2025-04-19 18:21:31,406 INFO Epoch:63 val_res:0.730500 +2025-04-19 18:22:00,855 INFO Epoch:64 train_loss:0.62868 +2025-04-19 18:22:06,849 INFO Epoch:64 val_res:0.727500 +2025-04-19 18:22:37,184 INFO Epoch:65 train_loss:0.57768 +2025-04-19 18:22:43,235 INFO Epoch:65 val_res:0.731000 +2025-04-19 18:23:13,727 INFO Epoch:66 train_loss:0.55480 +2025-04-19 18:23:19,712 INFO Epoch:66 val_res:0.734000 +2025-04-19 18:23:50,660 INFO Epoch:67 train_loss:0.54573 +2025-04-19 18:23:56,966 INFO Epoch:67 val_res:0.730000 +2025-04-19 18:24:28,040 INFO Epoch:68 train_loss:0.53977 +2025-04-19 18:24:34,458 INFO Epoch:68 val_res:0.734500 +2025-04-19 18:25:04,341 INFO Epoch:69 train_loss:0.54141 +2025-04-19 18:25:10,786 INFO Epoch:69 val_res:0.730000 +2025-04-19 18:25:40,370 INFO Epoch:70 train_loss:0.56497 +2025-04-19 18:25:46,517 INFO Epoch:70 val_res:0.729000 +2025-04-19 18:26:18,115 INFO Epoch:71 train_loss:0.59379 +2025-04-19 18:26:24,958 INFO Epoch:71 val_res:0.729000 +2025-04-19 18:26:55,816 INFO Epoch:72 train_loss:0.58992 +2025-04-19 18:27:03,348 INFO Epoch:72 val_res:0.728000 +2025-04-19 18:27:34,747 INFO Epoch:73 train_loss:0.57635 +2025-04-19 18:27:41,177 INFO Epoch:73 val_res:0.735500 +2025-04-19 18:28:11,761 INFO Epoch:74 train_loss:0.57575 +2025-04-19 18:28:18,190 INFO Epoch:74 val_res:0.730500 +2025-04-19 18:28:48,724 INFO Epoch:75 train_loss:0.55377 +2025-04-19 18:28:54,883 INFO Epoch:75 val_res:0.733000 +2025-04-19 18:29:24,750 INFO Epoch:76 train_loss:0.58351 +2025-04-19 18:29:30,847 INFO Epoch:76 val_res:0.726500 +2025-04-19 18:30:00,833 INFO Epoch:77 train_loss:0.62105 +2025-04-19 18:30:07,133 INFO Epoch:77 val_res:0.729000 +2025-04-19 18:30:37,265 INFO Epoch:78 train_loss:0.55824 +2025-04-19 18:30:43,429 INFO Epoch:78 val_res:0.729000 +2025-04-19 18:31:14,025 INFO Epoch:79 train_loss:0.54314 +2025-04-19 18:31:20,563 INFO Epoch:79 val_res:0.730000 +2025-04-19 18:31:50,861 INFO Epoch:80 train_loss:0.54268 +2025-04-19 18:31:57,049 INFO Epoch:80 val_res:0.729000 +2025-04-19 18:32:27,024 INFO Epoch:81 train_loss:0.56337 +2025-04-19 18:32:33,128 INFO Epoch:81 val_res:0.724500 +2025-04-19 18:33:03,394 INFO Epoch:82 train_loss:0.57663 +2025-04-19 18:33:09,287 INFO Epoch:82 val_res:0.729500 +2025-04-19 18:33:41,132 INFO Epoch:83 train_loss:0.66488 +2025-04-19 18:33:47,285 INFO Epoch:83 val_res:0.723000 +2025-04-19 18:34:17,226 INFO Epoch:84 train_loss:0.74570 +2025-04-19 18:34:23,337 INFO Epoch:84 val_res:0.721500 +2025-04-19 18:34:54,711 INFO Epoch:85 train_loss:0.72127 +2025-04-19 18:35:01,031 INFO Epoch:85 val_res:0.713500 +2025-04-19 18:35:32,101 INFO Epoch:86 train_loss:0.63983 +2025-04-19 18:35:38,524 INFO Epoch:86 val_res:0.715500 +2025-04-19 18:36:09,788 INFO Epoch:87 train_loss:0.57478 +2025-04-19 18:36:16,364 INFO Epoch:87 val_res:0.724500 +2025-04-19 18:36:46,105 INFO Epoch:88 train_loss:0.54331 +2025-04-19 18:36:52,317 INFO Epoch:88 val_res:0.722500 +2025-04-19 18:37:22,850 INFO Epoch:89 train_loss:0.54021 +2025-04-19 18:37:29,103 INFO Epoch:89 val_res:0.722000 +2025-04-19 18:37:58,747 INFO Epoch:90 train_loss:0.52872 +2025-04-19 18:38:04,991 INFO Epoch:90 val_res:0.723000 +2025-04-19 18:38:35,512 INFO Epoch:91 train_loss:0.53009 +2025-04-19 18:38:41,600 INFO Epoch:91 val_res:0.725500 +2025-04-19 18:39:12,365 INFO Epoch:92 train_loss:0.52795 +2025-04-19 18:39:19,018 INFO Epoch:92 val_res:0.722000 +2025-04-19 18:39:48,594 INFO Epoch:93 train_loss:0.52856 +2025-04-19 18:39:55,145 INFO Epoch:93 val_res:0.725500 +2025-04-19 18:40:25,517 INFO Epoch:94 train_loss:0.54600 +2025-04-19 18:40:31,911 INFO Epoch:94 val_res:0.725500 +2025-04-19 18:41:01,713 INFO Epoch:95 train_loss:0.58783 +2025-04-19 18:41:07,833 INFO Epoch:95 val_res:0.728500 +2025-04-19 18:41:37,518 INFO Epoch:96 train_loss:0.55714 +2025-04-19 18:41:43,671 INFO Epoch:96 val_res:0.728500 +2025-04-19 18:42:14,102 INFO Epoch:97 train_loss:0.54642 +2025-04-19 18:42:20,340 INFO Epoch:97 val_res:0.729500 +2025-04-19 18:42:50,491 INFO Epoch:98 train_loss:0.53601 +2025-04-19 18:42:56,662 INFO Epoch:98 val_res:0.724500 +2025-04-19 18:43:26,321 INFO Epoch:99 train_loss:0.55490 +2025-04-19 18:43:32,624 INFO Epoch:99 val_res:0.728000 +2025-04-19 18:43:32,837 INFO ===================================== +2025-04-19 18:43:32,837 INFO Start testing... +2025-04-19 18:43:32,837 INFO ===================================== +2025-04-19 18:43:39,084 INFO Incremental step 3 Testing res: 0.730500 +2025-04-19 18:43:39,086 INFO forgetting: 0.071333 +2025-04-19 18:43:39,090 INFO Incremental step: 4 +2025-04-19 18:44:56,762 INFO Epoch:0 train_loss:4.54509 +2025-04-19 18:45:04,658 INFO Epoch:0 val_res:0.578800 +2025-04-19 18:45:04,664 INFO Saving best model at Epoch 0 +2025-04-19 18:45:35,881 INFO Epoch:1 train_loss:1.57783 +2025-04-19 18:45:43,689 INFO Epoch:1 val_res:0.590400 +2025-04-19 18:45:43,689 INFO Saving best model at Epoch 1 +2025-04-19 18:46:13,850 INFO Epoch:2 train_loss:1.10323 +2025-04-19 18:46:21,133 INFO Epoch:2 val_res:0.598400 +2025-04-19 18:46:21,134 INFO Saving best model at Epoch 2 +2025-04-19 18:46:51,744 INFO Epoch:3 train_loss:0.95657 +2025-04-19 18:46:59,397 INFO Epoch:3 val_res:0.597200 +2025-04-19 18:47:28,563 INFO Epoch:4 train_loss:0.89261 +2025-04-19 18:47:35,701 INFO Epoch:4 val_res:0.599200 +2025-04-19 18:47:35,701 INFO Saving best model at Epoch 4 +2025-04-19 18:48:06,591 INFO Epoch:5 train_loss:0.85495 +2025-04-19 18:48:14,334 INFO Epoch:5 val_res:0.600000 +2025-04-19 18:48:14,334 INFO Saving best model at Epoch 5 +2025-04-19 18:48:45,831 INFO Epoch:6 train_loss:0.82424 +2025-04-19 18:48:53,820 INFO Epoch:6 val_res:0.605600 +2025-04-19 18:48:53,821 INFO Saving best model at Epoch 6 +2025-04-19 18:49:23,980 INFO Epoch:7 train_loss:0.80629 +2025-04-19 18:49:32,260 INFO Epoch:7 val_res:0.602800 +2025-04-19 18:50:01,635 INFO Epoch:8 train_loss:0.78471 +2025-04-19 18:50:09,995 INFO Epoch:8 val_res:0.608400 +2025-04-19 18:50:09,995 INFO Saving best model at Epoch 8 +2025-04-19 18:50:41,917 INFO Epoch:9 train_loss:0.77076 +2025-04-19 18:50:49,501 INFO Epoch:9 val_res:0.609200 +2025-04-19 18:50:49,501 INFO Saving best model at Epoch 9 +2025-04-19 18:51:19,631 INFO Epoch:10 train_loss:0.77357 +2025-04-19 18:51:27,309 INFO Epoch:10 val_res:0.609600 +2025-04-19 18:51:27,310 INFO Saving best model at Epoch 10 +2025-04-19 18:51:57,357 INFO Epoch:11 train_loss:0.74292 +2025-04-19 18:52:04,551 INFO Epoch:11 val_res:0.610800 +2025-04-19 18:52:04,551 INFO Saving best model at Epoch 11 +2025-04-19 18:52:34,896 INFO Epoch:12 train_loss:0.72856 +2025-04-19 18:52:41,685 INFO Epoch:12 val_res:0.617200 +2025-04-19 18:52:41,685 INFO Saving best model at Epoch 12 +2025-04-19 18:53:12,750 INFO Epoch:13 train_loss:0.73183 +2025-04-19 18:53:19,631 INFO Epoch:13 val_res:0.614800 +2025-04-19 18:53:50,157 INFO Epoch:14 train_loss:0.75834 +2025-04-19 18:53:59,499 INFO Epoch:14 val_res:0.622000 +2025-04-19 18:53:59,499 INFO Saving best model at Epoch 14 +2025-04-19 18:54:32,083 INFO Epoch:15 train_loss:0.72649 +2025-04-19 18:54:41,529 INFO Epoch:15 val_res:0.627200 +2025-04-19 18:54:41,529 INFO Saving best model at Epoch 15 +2025-04-19 18:55:13,125 INFO Epoch:16 train_loss:0.72621 +2025-04-19 18:55:22,752 INFO Epoch:16 val_res:0.632000 +2025-04-19 18:55:22,752 INFO Saving best model at Epoch 16 +2025-04-19 18:55:54,233 INFO Epoch:17 train_loss:0.70596 +2025-04-19 18:56:04,267 INFO Epoch:17 val_res:0.628400 +2025-04-19 18:56:34,596 INFO Epoch:18 train_loss:0.72764 +2025-04-19 18:56:43,934 INFO Epoch:18 val_res:0.631600 +2025-04-19 18:57:12,890 INFO Epoch:19 train_loss:0.72382 +2025-04-19 18:57:21,797 INFO Epoch:19 val_res:0.639600 +2025-04-19 18:57:21,798 INFO Saving best model at Epoch 19 +2025-04-19 18:57:56,730 INFO Epoch:20 train_loss:0.67354 +2025-04-19 18:58:05,814 INFO Epoch:20 val_res:0.637600 +2025-04-19 18:58:35,148 INFO Epoch:21 train_loss:0.66887 +2025-04-19 18:58:45,158 INFO Epoch:21 val_res:0.640000 +2025-04-19 18:58:45,158 INFO Saving best model at Epoch 21 +2025-04-19 18:59:16,208 INFO Epoch:22 train_loss:0.66915 +2025-04-19 18:59:25,535 INFO Epoch:22 val_res:0.646400 +2025-04-19 18:59:25,536 INFO Saving best model at Epoch 22 +2025-04-19 18:59:57,051 INFO Epoch:23 train_loss:0.69906 +2025-04-19 19:00:06,306 INFO Epoch:23 val_res:0.645200 +2025-04-19 19:00:36,946 INFO Epoch:24 train_loss:0.67385 +2025-04-19 19:00:46,994 INFO Epoch:24 val_res:0.646800 +2025-04-19 19:00:46,995 INFO Saving best model at Epoch 24 +2025-04-19 19:01:18,713 INFO Epoch:25 train_loss:0.66996 +2025-04-19 19:01:28,158 INFO Epoch:25 val_res:0.644400 +2025-04-19 19:01:58,181 INFO Epoch:26 train_loss:0.65069 +2025-04-19 19:02:05,924 INFO Epoch:26 val_res:0.658000 +2025-04-19 19:02:05,924 INFO Saving best model at Epoch 26 +2025-04-19 19:02:39,735 INFO Epoch:27 train_loss:0.61487 +2025-04-19 19:02:49,603 INFO Epoch:27 val_res:0.660800 +2025-04-19 19:02:49,603 INFO Saving best model at Epoch 27 +2025-04-19 19:03:21,186 INFO Epoch:28 train_loss:0.62151 +2025-04-19 19:03:30,779 INFO Epoch:28 val_res:0.664800 +2025-04-19 19:03:30,780 INFO Saving best model at Epoch 28 +2025-04-19 19:04:03,430 INFO Epoch:29 train_loss:0.61771 +2025-04-19 19:04:13,506 INFO Epoch:29 val_res:0.662400 +2025-04-19 19:04:46,168 INFO Epoch:30 train_loss:0.65877 +2025-04-19 19:04:56,999 INFO Epoch:30 val_res:0.666400 +2025-04-19 19:04:56,999 INFO Saving best model at Epoch 30 +2025-04-19 19:05:31,164 INFO Epoch:31 train_loss:0.62730 +2025-04-19 19:05:40,708 INFO Epoch:31 val_res:0.663200 +2025-04-19 19:06:13,285 INFO Epoch:32 train_loss:0.62147 +2025-04-19 19:06:22,922 INFO Epoch:32 val_res:0.659200 +2025-04-19 19:06:54,544 INFO Epoch:33 train_loss:0.73325 +2025-04-19 19:07:04,123 INFO Epoch:33 val_res:0.668000 +2025-04-19 19:07:04,124 INFO Saving best model at Epoch 33 +2025-04-19 19:07:38,621 INFO Epoch:34 train_loss:0.83188 +2025-04-19 19:07:47,751 INFO Epoch:34 val_res:0.658000 +2025-04-19 19:08:18,083 INFO Epoch:35 train_loss:0.84842 +2025-04-19 19:08:27,892 INFO Epoch:35 val_res:0.672800 +2025-04-19 19:08:27,892 INFO Saving best model at Epoch 35 +2025-04-19 19:09:02,484 INFO Epoch:36 train_loss:0.62424 +2025-04-19 19:09:11,746 INFO Epoch:36 val_res:0.672800 +2025-04-19 19:09:44,417 INFO Epoch:37 train_loss:0.59022 +2025-04-19 19:09:53,488 INFO Epoch:37 val_res:0.673200 +2025-04-19 19:09:53,489 INFO Saving best model at Epoch 37 +2025-04-19 19:10:28,478 INFO Epoch:38 train_loss:0.58035 +2025-04-19 19:10:38,087 INFO Epoch:38 val_res:0.672400 +2025-04-19 19:11:09,975 INFO Epoch:39 train_loss:0.57225 +2025-04-19 19:11:19,241 INFO Epoch:39 val_res:0.672000 +2025-04-19 19:11:51,329 INFO Epoch:40 train_loss:0.56852 +2025-04-19 19:12:00,566 INFO Epoch:40 val_res:0.676800 +2025-04-19 19:12:00,566 INFO Saving best model at Epoch 40 +2025-04-19 19:12:33,889 INFO Epoch:41 train_loss:0.56900 +2025-04-19 19:12:43,154 INFO Epoch:41 val_res:0.675600 +2025-04-19 19:13:16,756 INFO Epoch:42 train_loss:0.57732 +2025-04-19 19:13:26,495 INFO Epoch:42 val_res:0.677600 +2025-04-19 19:13:26,495 INFO Saving best model at Epoch 42 +2025-04-19 19:14:02,496 INFO Epoch:43 train_loss:0.57768 +2025-04-19 19:14:11,723 INFO Epoch:43 val_res:0.676000 +2025-04-19 19:14:40,724 INFO Epoch:44 train_loss:0.57621 +2025-04-19 19:14:48,309 INFO Epoch:44 val_res:0.674400 +2025-04-19 19:15:17,417 INFO Epoch:45 train_loss:0.57292 +2025-04-19 19:15:24,764 INFO Epoch:45 val_res:0.671200 +2025-04-19 19:15:55,404 INFO Epoch:46 train_loss:0.57794 +2025-04-19 19:16:05,478 INFO Epoch:46 val_res:0.679200 +2025-04-19 19:16:05,478 INFO Saving best model at Epoch 46 +2025-04-19 19:16:36,384 INFO Epoch:47 train_loss:0.58087 +2025-04-19 19:16:44,093 INFO Epoch:47 val_res:0.675600 +2025-04-19 19:17:12,233 INFO Epoch:48 train_loss:0.60531 +2025-04-19 19:17:19,844 INFO Epoch:48 val_res:0.678000 +2025-04-19 19:17:50,440 INFO Epoch:49 train_loss:0.60498 +2025-04-19 19:17:59,541 INFO Epoch:49 val_res:0.677600 +2025-04-19 19:18:28,592 INFO Epoch:50 train_loss:0.66026 +2025-04-19 19:18:35,996 INFO Epoch:50 val_res:0.676800 +2025-04-19 19:19:06,981 INFO Epoch:51 train_loss:0.64026 +2025-04-19 19:19:16,142 INFO Epoch:51 val_res:0.677200 +2025-04-19 19:19:46,661 INFO Epoch:52 train_loss:0.60692 +2025-04-19 19:19:55,921 INFO Epoch:52 val_res:0.672000 +2025-04-19 19:20:26,627 INFO Epoch:53 train_loss:0.61849 +2025-04-19 19:20:37,880 INFO Epoch:53 val_res:0.676000 +2025-04-19 19:21:07,169 INFO Epoch:54 train_loss:0.60270 +2025-04-19 19:21:15,108 INFO Epoch:54 val_res:0.676400 +2025-04-19 19:21:43,624 INFO Epoch:55 train_loss:0.60763 +2025-04-19 19:21:51,436 INFO Epoch:55 val_res:0.672400 +2025-04-19 19:22:19,859 INFO Epoch:56 train_loss:0.59906 +2025-04-19 19:22:27,435 INFO Epoch:56 val_res:0.681200 +2025-04-19 19:22:27,436 INFO Saving best model at Epoch 56 +2025-04-19 19:22:57,820 INFO Epoch:57 train_loss:0.58986 +2025-04-19 19:23:05,506 INFO Epoch:57 val_res:0.678400 +2025-04-19 19:23:33,694 INFO Epoch:58 train_loss:0.56078 +2025-04-19 19:23:41,360 INFO Epoch:58 val_res:0.675600 +2025-04-19 19:24:10,680 INFO Epoch:59 train_loss:0.56585 +2025-04-19 19:24:20,270 INFO Epoch:59 val_res:0.678000 +2025-04-19 19:24:48,641 INFO Epoch:60 train_loss:0.55858 +2025-04-19 19:24:56,284 INFO Epoch:60 val_res:0.674000 +2025-04-19 19:25:26,465 INFO Epoch:61 train_loss:0.56478 +2025-04-19 19:25:35,612 INFO Epoch:61 val_res:0.681600 +2025-04-19 19:25:35,612 INFO Saving best model at Epoch 61 +2025-04-19 19:26:07,276 INFO Epoch:62 train_loss:0.57653 +2025-04-19 19:26:16,201 INFO Epoch:62 val_res:0.675200 +2025-04-19 19:26:45,087 INFO Epoch:63 train_loss:0.58453 +2025-04-19 19:26:52,450 INFO Epoch:63 val_res:0.677200 +2025-04-19 19:27:20,852 INFO Epoch:64 train_loss:0.65169 +2025-04-19 19:27:28,475 INFO Epoch:64 val_res:0.678800 +2025-04-19 19:27:58,696 INFO Epoch:65 train_loss:0.63487 +2025-04-19 19:28:07,890 INFO Epoch:65 val_res:0.672800 +2025-04-19 19:28:39,534 INFO Epoch:66 train_loss:0.59137 +2025-04-19 19:28:48,689 INFO Epoch:66 val_res:0.678400 +2025-04-19 19:29:17,565 INFO Epoch:67 train_loss:0.55208 +2025-04-19 19:29:25,100 INFO Epoch:67 val_res:0.677600 +2025-04-19 19:29:55,582 INFO Epoch:68 train_loss:0.54202 +2025-04-19 19:30:04,985 INFO Epoch:68 val_res:0.675600 +2025-04-19 19:30:33,961 INFO Epoch:69 train_loss:0.54143 +2025-04-19 19:30:41,678 INFO Epoch:69 val_res:0.675200 +2025-04-19 19:31:13,173 INFO Epoch:70 train_loss:0.55460 +2025-04-19 19:31:22,194 INFO Epoch:70 val_res:0.671600 +2025-04-19 19:31:52,190 INFO Epoch:71 train_loss:0.55908 +2025-04-19 19:32:01,411 INFO Epoch:71 val_res:0.676400 +2025-04-19 19:32:30,710 INFO Epoch:72 train_loss:0.54929 +2025-04-19 19:32:38,401 INFO Epoch:72 val_res:0.671200 +2025-04-19 19:33:06,876 INFO Epoch:73 train_loss:0.57542 +2025-04-19 19:33:14,493 INFO Epoch:73 val_res:0.671200 +2025-04-19 19:33:45,721 INFO Epoch:74 train_loss:0.62588 +2025-04-19 19:33:55,134 INFO Epoch:74 val_res:0.677200 +2025-04-19 19:34:24,060 INFO Epoch:75 train_loss:0.67647 +2025-04-19 19:34:31,805 INFO Epoch:75 val_res:0.670400 +2025-04-19 19:35:00,215 INFO Epoch:76 train_loss:0.60232 +2025-04-19 19:35:07,467 INFO Epoch:76 val_res:0.670800 +2025-04-19 19:35:36,503 INFO Epoch:77 train_loss:0.56892 +2025-04-19 19:35:44,036 INFO Epoch:77 val_res:0.670000 +2025-04-19 19:36:14,990 INFO Epoch:78 train_loss:0.55295 +2025-04-19 19:36:24,207 INFO Epoch:78 val_res:0.670400 +2025-04-19 19:36:52,574 INFO Epoch:79 train_loss:0.54420 +2025-04-19 19:37:00,191 INFO Epoch:79 val_res:0.672800 +2025-04-19 19:37:30,362 INFO Epoch:80 train_loss:0.53935 +2025-04-19 19:37:39,661 INFO Epoch:80 val_res:0.667600 +2025-04-19 19:38:07,742 INFO Epoch:81 train_loss:0.52672 +2025-04-19 19:38:15,482 INFO Epoch:81 val_res:0.669600 +2025-04-19 19:38:45,510 INFO Epoch:82 train_loss:0.52254 +2025-04-19 19:38:54,155 INFO Epoch:82 val_res:0.670000 +2025-04-19 19:39:23,751 INFO Epoch:83 train_loss:0.62298 +2025-04-19 19:39:31,317 INFO Epoch:83 val_res:0.668000 +2025-04-19 19:40:00,046 INFO Epoch:84 train_loss:0.62507 +2025-04-19 19:40:07,468 INFO Epoch:84 val_res:0.670400 +2025-04-19 19:40:36,214 INFO Epoch:85 train_loss:0.58428 +2025-04-19 19:40:44,070 INFO Epoch:85 val_res:0.664800 +2025-04-19 19:41:13,690 INFO Epoch:86 train_loss:0.58527 +2025-04-19 19:41:23,351 INFO Epoch:86 val_res:0.666400 +2025-04-19 19:41:52,577 INFO Epoch:87 train_loss:0.57708 +2025-04-19 19:42:02,123 INFO Epoch:87 val_res:0.660400 +2025-04-19 19:42:30,660 INFO Epoch:88 train_loss:0.58339 +2025-04-19 19:42:38,148 INFO Epoch:88 val_res:0.668400 +2025-04-19 19:43:08,986 INFO Epoch:89 train_loss:0.55551 +2025-04-19 19:43:18,040 INFO Epoch:89 val_res:0.666400 +2025-04-19 19:43:48,752 INFO Epoch:90 train_loss:0.53728 +2025-04-19 19:43:57,593 INFO Epoch:90 val_res:0.668000 +2025-04-19 19:44:28,465 INFO Epoch:91 train_loss:0.52661 +2025-04-19 19:44:37,635 INFO Epoch:91 val_res:0.664400 +2025-04-19 19:45:06,235 INFO Epoch:92 train_loss:0.51867 +2025-04-19 19:45:13,985 INFO Epoch:92 val_res:0.669200 +2025-04-19 19:45:41,727 INFO Epoch:93 train_loss:0.52120 +2025-04-19 19:45:49,705 INFO Epoch:93 val_res:0.667200 +2025-04-19 19:46:21,072 INFO Epoch:94 train_loss:0.53005 +2025-04-19 19:46:30,355 INFO Epoch:94 val_res:0.669200 +2025-04-19 19:46:58,557 INFO Epoch:95 train_loss:0.60519 +2025-04-19 19:47:06,499 INFO Epoch:95 val_res:0.669200 +2025-04-19 19:47:34,696 INFO Epoch:96 train_loss:0.59926 +2025-04-19 19:47:42,399 INFO Epoch:96 val_res:0.662000 +2025-04-19 19:48:12,726 INFO Epoch:97 train_loss:0.56429 +2025-04-19 19:48:21,634 INFO Epoch:97 val_res:0.664800 +2025-04-19 19:48:54,829 INFO Epoch:98 train_loss:0.60668 +2025-04-19 19:49:04,464 INFO Epoch:98 val_res:0.666400 +2025-04-19 19:49:34,734 INFO Epoch:99 train_loss:0.59302 +2025-04-19 19:49:43,858 INFO Epoch:99 val_res:0.663200 +2025-04-19 19:49:44,160 INFO ===================================== +2025-04-19 19:49:44,160 INFO Start testing... +2025-04-19 19:49:44,160 INFO ===================================== +2025-04-19 19:50:29,938 INFO Incremental step 4 Testing res: 0.677600 +2025-04-19 19:50:29,940 INFO forgetting: 0.100000 +2025-04-19 19:50:29,950 INFO Incremental step: 5 +2025-04-19 19:51:31,666 INFO Epoch:0 train_loss:5.70863 +2025-04-19 19:51:49,191 INFO Epoch:0 val_res:0.547333 +2025-04-19 19:51:49,191 INFO Saving best model at Epoch 0 +2025-04-19 19:52:17,530 INFO Epoch:1 train_loss:1.80979 +2025-04-19 19:52:25,628 INFO Epoch:1 val_res:0.576333 +2025-04-19 19:52:25,628 INFO Saving best model at Epoch 1 +2025-04-19 19:52:55,253 INFO Epoch:2 train_loss:1.16023 +2025-04-19 19:53:03,875 INFO Epoch:2 val_res:0.587000 +2025-04-19 19:53:03,875 INFO Saving best model at Epoch 2 +2025-04-19 19:53:32,865 INFO Epoch:3 train_loss:0.99007 +2025-04-19 19:53:41,708 INFO Epoch:3 val_res:0.593000 +2025-04-19 19:53:41,708 INFO Saving best model at Epoch 3 +2025-04-19 19:54:09,970 INFO Epoch:4 train_loss:0.93471 +2025-04-19 19:54:18,484 INFO Epoch:4 val_res:0.590667 +2025-04-19 19:54:44,980 INFO Epoch:5 train_loss:0.88800 +2025-04-19 19:54:53,182 INFO Epoch:5 val_res:0.593333 +2025-04-19 19:54:53,183 INFO Saving best model at Epoch 5 +2025-04-19 19:55:21,663 INFO Epoch:6 train_loss:0.86735 +2025-04-19 19:55:29,984 INFO Epoch:6 val_res:0.594333 +2025-04-19 19:55:29,985 INFO Saving best model at Epoch 6 +2025-04-19 19:55:58,936 INFO Epoch:7 train_loss:0.85222 +2025-04-19 19:56:07,174 INFO Epoch:7 val_res:0.595333 +2025-04-19 19:56:07,174 INFO Saving best model at Epoch 7 +2025-04-19 19:56:36,767 INFO Epoch:8 train_loss:0.83450 +2025-04-19 19:56:44,930 INFO Epoch:8 val_res:0.596667 +2025-04-19 19:56:44,931 INFO Saving best model at Epoch 8 +2025-04-19 19:57:14,965 INFO Epoch:9 train_loss:0.82199 +2025-04-19 19:57:23,451 INFO Epoch:9 val_res:0.597333 +2025-04-19 19:57:23,451 INFO Saving best model at Epoch 9 +2025-04-19 19:57:52,772 INFO Epoch:10 train_loss:0.80416 +2025-04-19 19:58:01,536 INFO Epoch:10 val_res:0.600000 +2025-04-19 19:58:01,537 INFO Saving best model at Epoch 10 +2025-04-19 19:58:29,870 INFO Epoch:11 train_loss:0.79305 +2025-04-19 19:58:38,666 INFO Epoch:11 val_res:0.604333 +2025-04-19 19:58:38,666 INFO Saving best model at Epoch 11 +2025-04-19 19:59:07,719 INFO Epoch:12 train_loss:0.78448 +2025-04-19 19:59:16,512 INFO Epoch:12 val_res:0.602333 +2025-04-19 19:59:43,232 INFO Epoch:13 train_loss:0.77441 +2025-04-19 19:59:51,466 INFO Epoch:13 val_res:0.604333 +2025-04-19 20:00:18,795 INFO Epoch:14 train_loss:0.76319 +2025-04-19 20:00:27,148 INFO Epoch:14 val_res:0.607333 +2025-04-19 20:00:27,148 INFO Saving best model at Epoch 14 +2025-04-19 20:00:56,238 INFO Epoch:15 train_loss:0.75477 +2025-04-19 20:01:04,458 INFO Epoch:15 val_res:0.609000 +2025-04-19 20:01:04,459 INFO Saving best model at Epoch 15 +2025-04-19 20:01:33,391 INFO Epoch:16 train_loss:0.74807 +2025-04-19 20:01:41,693 INFO Epoch:16 val_res:0.609667 +2025-04-19 20:01:41,694 INFO Saving best model at Epoch 16 +2025-04-19 20:02:10,446 INFO Epoch:17 train_loss:0.76752 +2025-04-19 20:02:18,922 INFO Epoch:17 val_res:0.608333 +2025-04-19 20:02:45,825 INFO Epoch:18 train_loss:0.74113 +2025-04-19 20:02:54,516 INFO Epoch:18 val_res:0.613333 +2025-04-19 20:02:54,517 INFO Saving best model at Epoch 18 +2025-04-19 20:03:22,237 INFO Epoch:19 train_loss:0.76288 +2025-04-19 20:03:30,764 INFO Epoch:19 val_res:0.614333 +2025-04-19 20:03:30,764 INFO Saving best model at Epoch 19 +2025-04-19 20:03:58,835 INFO Epoch:20 train_loss:0.79993 +2025-04-19 20:04:07,194 INFO Epoch:20 val_res:0.615333 +2025-04-19 20:04:07,194 INFO Saving best model at Epoch 20 +2025-04-19 20:04:35,434 INFO Epoch:21 train_loss:0.73712 +2025-04-19 20:04:43,866 INFO Epoch:21 val_res:0.615667 +2025-04-19 20:04:43,867 INFO Saving best model at Epoch 21 +2025-04-19 20:05:13,307 INFO Epoch:22 train_loss:0.72591 +2025-04-19 20:05:21,944 INFO Epoch:22 val_res:0.621333 +2025-04-19 20:05:21,944 INFO Saving best model at Epoch 22 +2025-04-19 20:05:50,900 INFO Epoch:23 train_loss:0.74177 +2025-04-19 20:05:59,020 INFO Epoch:23 val_res:0.621667 +2025-04-19 20:05:59,020 INFO Saving best model at Epoch 23 +2025-04-19 20:06:27,737 INFO Epoch:24 train_loss:0.71745 +2025-04-19 20:06:36,367 INFO Epoch:24 val_res:0.618667 +2025-04-19 20:07:02,464 INFO Epoch:25 train_loss:0.69122 +2025-04-19 20:07:10,650 INFO Epoch:25 val_res:0.625000 +2025-04-19 20:07:10,650 INFO Saving best model at Epoch 25 +2025-04-19 20:07:37,838 INFO Epoch:26 train_loss:0.72565 +2025-04-19 20:07:46,358 INFO Epoch:26 val_res:0.625667 +2025-04-19 20:07:46,358 INFO Saving best model at Epoch 26 +2025-04-19 20:08:15,518 INFO Epoch:27 train_loss:0.76081 +2025-04-19 20:08:23,766 INFO Epoch:27 val_res:0.628667 +2025-04-19 20:08:23,767 INFO Saving best model at Epoch 27 +2025-04-19 20:08:53,720 INFO Epoch:28 train_loss:0.74865 +2025-04-19 20:09:01,916 INFO Epoch:28 val_res:0.626000 +2025-04-19 20:09:28,968 INFO Epoch:29 train_loss:0.71639 +2025-04-19 20:09:37,350 INFO Epoch:29 val_res:0.632667 +2025-04-19 20:09:37,350 INFO Saving best model at Epoch 29 +2025-04-19 20:10:05,358 INFO Epoch:30 train_loss:0.68001 +2025-04-19 20:10:13,888 INFO Epoch:30 val_res:0.638667 +2025-04-19 20:10:13,889 INFO Saving best model at Epoch 30 +2025-04-19 20:10:42,540 INFO Epoch:31 train_loss:0.67004 +2025-04-19 20:10:50,796 INFO Epoch:31 val_res:0.634000 +2025-04-19 20:11:17,810 INFO Epoch:32 train_loss:0.67167 +2025-04-19 20:11:25,884 INFO Epoch:32 val_res:0.638000 +2025-04-19 20:11:52,874 INFO Epoch:33 train_loss:0.75410 +2025-04-19 20:12:01,253 INFO Epoch:33 val_res:0.640667 +2025-04-19 20:12:01,254 INFO Saving best model at Epoch 33 +2025-04-19 20:12:29,334 INFO Epoch:34 train_loss:0.68987 +2025-04-19 20:12:37,539 INFO Epoch:34 val_res:0.648667 +2025-04-19 20:12:37,540 INFO Saving best model at Epoch 34 +2025-04-19 20:13:05,866 INFO Epoch:35 train_loss:0.67229 +2025-04-19 20:13:14,818 INFO Epoch:35 val_res:0.637333 +2025-04-19 20:13:41,116 INFO Epoch:36 train_loss:0.66198 +2025-04-19 20:13:49,722 INFO Epoch:36 val_res:0.641333 +2025-04-19 20:14:16,928 INFO Epoch:37 train_loss:0.66193 +2025-04-19 20:14:25,407 INFO Epoch:37 val_res:0.648333 +2025-04-19 20:14:52,809 INFO Epoch:38 train_loss:0.66122 +2025-04-19 20:15:01,139 INFO Epoch:38 val_res:0.645333 +2025-04-19 20:15:27,876 INFO Epoch:39 train_loss:0.75221 +2025-04-19 20:15:36,098 INFO Epoch:39 val_res:0.644333 +2025-04-19 20:16:03,484 INFO Epoch:40 train_loss:0.71450 +2025-04-19 20:16:12,265 INFO Epoch:40 val_res:0.648000 +2025-04-19 20:16:38,941 INFO Epoch:41 train_loss:0.69962 +2025-04-19 20:16:47,883 INFO Epoch:41 val_res:0.641000 +2025-04-19 20:17:14,262 INFO Epoch:42 train_loss:0.67560 +2025-04-19 20:17:22,778 INFO Epoch:42 val_res:0.644000 +2025-04-19 20:17:49,181 INFO Epoch:43 train_loss:0.63788 +2025-04-19 20:17:57,253 INFO Epoch:43 val_res:0.645333 +2025-04-19 20:18:23,789 INFO Epoch:44 train_loss:0.64387 +2025-04-19 20:18:32,049 INFO Epoch:44 val_res:0.642333 +2025-04-19 20:18:59,004 INFO Epoch:45 train_loss:0.67036 +2025-04-19 20:19:07,117 INFO Epoch:45 val_res:0.643000 +2025-04-19 20:19:34,101 INFO Epoch:46 train_loss:0.68309 +2025-04-19 20:19:42,453 INFO Epoch:46 val_res:0.644333 +2025-04-19 20:20:09,096 INFO Epoch:47 train_loss:0.65527 +2025-04-19 20:20:17,791 INFO Epoch:47 val_res:0.641000 +2025-04-19 20:20:43,609 INFO Epoch:48 train_loss:0.63617 +2025-04-19 20:20:52,041 INFO Epoch:48 val_res:0.642333 +2025-04-19 20:21:18,614 INFO Epoch:49 train_loss:0.63041 +2025-04-19 20:21:26,836 INFO Epoch:49 val_res:0.641000 +2025-04-19 20:21:53,598 INFO Epoch:50 train_loss:0.62639 +2025-04-19 20:22:01,918 INFO Epoch:50 val_res:0.648667 +2025-04-19 20:22:29,519 INFO Epoch:51 train_loss:0.63924 +2025-04-19 20:22:37,959 INFO Epoch:51 val_res:0.640333 +2025-04-19 20:23:04,670 INFO Epoch:52 train_loss:0.62712 +2025-04-19 20:23:13,544 INFO Epoch:52 val_res:0.643333 +2025-04-19 20:23:39,556 INFO Epoch:53 train_loss:0.63529 +2025-04-19 20:23:48,091 INFO Epoch:53 val_res:0.642667 +2025-04-19 20:24:14,999 INFO Epoch:54 train_loss:0.73440 +2025-04-19 20:24:23,137 INFO Epoch:54 val_res:0.645333 +2025-04-19 20:24:49,760 INFO Epoch:55 train_loss:0.69931 +2025-04-19 20:24:58,016 INFO Epoch:55 val_res:0.642667 +2025-04-19 20:25:24,892 INFO Epoch:56 train_loss:0.63436 +2025-04-19 20:25:33,199 INFO Epoch:56 val_res:0.641667 +2025-04-19 20:25:59,965 INFO Epoch:57 train_loss:0.63058 +2025-04-19 20:26:08,602 INFO Epoch:57 val_res:0.643000 +2025-04-19 20:26:35,509 INFO Epoch:58 train_loss:0.62068 +2025-04-19 20:26:44,190 INFO Epoch:58 val_res:0.640000 +2025-04-19 20:27:10,521 INFO Epoch:59 train_loss:0.61266 +2025-04-19 20:27:18,736 INFO Epoch:59 val_res:0.642333 +2025-04-19 20:27:45,534 INFO Epoch:60 train_loss:0.63190 +2025-04-19 20:27:53,876 INFO Epoch:60 val_res:0.643333 +2025-04-19 20:28:21,020 INFO Epoch:61 train_loss:0.61730 +2025-04-19 20:28:29,415 INFO Epoch:61 val_res:0.645333 +2025-04-19 20:28:56,512 INFO Epoch:62 train_loss:0.68530 +2025-04-19 20:29:04,888 INFO Epoch:62 val_res:0.640667 +2025-04-19 20:29:31,874 INFO Epoch:63 train_loss:0.72659 +2025-04-19 20:29:40,223 INFO Epoch:63 val_res:0.640667 +2025-04-19 20:30:07,227 INFO Epoch:64 train_loss:0.67332 +2025-04-19 20:30:15,444 INFO Epoch:64 val_res:0.641000 +2025-04-19 20:30:41,893 INFO Epoch:65 train_loss:0.62058 +2025-04-19 20:30:50,047 INFO Epoch:65 val_res:0.639333 +2025-04-19 20:31:17,435 INFO Epoch:66 train_loss:0.61274 +2025-04-19 20:31:25,548 INFO Epoch:66 val_res:0.640667 +2025-04-19 20:31:52,701 INFO Epoch:67 train_loss:0.69438 +2025-04-19 20:32:01,320 INFO Epoch:67 val_res:0.638000 +2025-04-19 20:32:27,269 INFO Epoch:68 train_loss:0.67197 +2025-04-19 20:32:35,838 INFO Epoch:68 val_res:0.640000 +2025-04-19 20:33:01,999 INFO Epoch:69 train_loss:0.62653 +2025-04-19 20:33:10,254 INFO Epoch:69 val_res:0.644000 +2025-04-19 20:33:37,066 INFO Epoch:70 train_loss:0.63660 +2025-04-19 20:33:45,531 INFO Epoch:70 val_res:0.639333 +2025-04-19 20:34:12,758 INFO Epoch:71 train_loss:0.62355 +2025-04-19 20:34:21,114 INFO Epoch:71 val_res:0.640000 +2025-04-19 20:34:48,624 INFO Epoch:72 train_loss:0.59764 +2025-04-19 20:34:57,229 INFO Epoch:72 val_res:0.640667 +2025-04-19 20:35:23,946 INFO Epoch:73 train_loss:0.60204 +2025-04-19 20:35:32,538 INFO Epoch:73 val_res:0.639667 +2025-04-19 20:35:58,855 INFO Epoch:74 train_loss:0.60833 +2025-04-19 20:36:07,417 INFO Epoch:74 val_res:0.645000 +2025-04-19 20:36:33,381 INFO Epoch:75 train_loss:0.60625 +2025-04-19 20:36:41,769 INFO Epoch:75 val_res:0.640667 +2025-04-19 20:37:07,968 INFO Epoch:76 train_loss:0.60751 +2025-04-19 20:37:16,328 INFO Epoch:76 val_res:0.642000 +2025-04-19 20:37:42,800 INFO Epoch:77 train_loss:0.61788 +2025-04-19 20:37:51,252 INFO Epoch:77 val_res:0.636667 +2025-04-19 20:38:18,189 INFO Epoch:78 train_loss:0.64464 +2025-04-19 20:38:28,478 INFO Epoch:78 val_res:0.630333 +2025-04-19 20:38:54,685 INFO Epoch:79 train_loss:0.64299 +2025-04-19 20:39:03,424 INFO Epoch:79 val_res:0.633333 +2025-04-19 20:39:29,240 INFO Epoch:80 train_loss:0.62927 +2025-04-19 20:39:38,360 INFO Epoch:80 val_res:0.636000 +2025-04-19 20:40:04,782 INFO Epoch:81 train_loss:0.63968 +2025-04-19 20:40:13,045 INFO Epoch:81 val_res:0.640333 +2025-04-19 20:40:39,946 INFO Epoch:82 train_loss:0.69248 +2025-04-19 20:40:48,226 INFO Epoch:82 val_res:0.637000 +2025-04-19 20:41:15,287 INFO Epoch:83 train_loss:0.67513 +2025-04-19 20:41:24,134 INFO Epoch:83 val_res:0.630333 +2025-04-19 20:41:50,924 INFO Epoch:84 train_loss:0.66111 +2025-04-19 20:41:59,401 INFO Epoch:84 val_res:0.626333 +2025-04-19 20:42:25,481 INFO Epoch:85 train_loss:0.68273 +2025-04-19 20:42:33,610 INFO Epoch:85 val_res:0.642000 +2025-04-19 20:43:00,036 INFO Epoch:86 train_loss:0.64636 +2025-04-19 20:43:08,252 INFO Epoch:86 val_res:0.635667 +2025-04-19 20:43:34,374 INFO Epoch:87 train_loss:0.59685 +2025-04-19 20:43:42,681 INFO Epoch:87 val_res:0.634667 +2025-04-19 20:44:09,809 INFO Epoch:88 train_loss:0.58400 +2025-04-19 20:44:18,413 INFO Epoch:88 val_res:0.636000 +2025-04-19 20:44:44,506 INFO Epoch:89 train_loss:0.58146 +2025-04-19 20:44:53,233 INFO Epoch:89 val_res:0.632667 +2025-04-19 20:45:20,143 INFO Epoch:90 train_loss:0.57802 +2025-04-19 20:45:28,622 INFO Epoch:90 val_res:0.634667 +2025-04-19 20:45:56,677 INFO Epoch:91 train_loss:0.60015 +2025-04-19 20:46:06,644 INFO Epoch:91 val_res:0.634667 +2025-04-19 20:46:33,194 INFO Epoch:92 train_loss:0.65943 +2025-04-19 20:46:41,416 INFO Epoch:92 val_res:0.636000 +2025-04-19 20:47:08,125 INFO Epoch:93 train_loss:0.65629 +2025-04-19 20:47:16,464 INFO Epoch:93 val_res:0.635333 +2025-04-19 20:47:43,174 INFO Epoch:94 train_loss:0.62975 +2025-04-19 20:47:52,034 INFO Epoch:94 val_res:0.636333 +2025-04-19 20:48:17,989 INFO Epoch:95 train_loss:0.60983 +2025-04-19 20:48:26,370 INFO Epoch:95 val_res:0.631000 +2025-04-19 20:48:52,565 INFO Epoch:96 train_loss:0.58499 +2025-04-19 20:49:00,896 INFO Epoch:96 val_res:0.635667 +2025-04-19 20:49:27,687 INFO Epoch:97 train_loss:0.59070 +2025-04-19 20:49:35,862 INFO Epoch:97 val_res:0.630667 +2025-04-19 20:50:02,493 INFO Epoch:98 train_loss:0.59764 +2025-04-19 20:50:10,665 INFO Epoch:98 val_res:0.635667 +2025-04-19 20:50:38,024 INFO Epoch:99 train_loss:0.61668 +2025-04-19 20:50:46,466 INFO Epoch:99 val_res:0.630000 +2025-04-19 20:50:46,695 INFO ===================================== +2025-04-19 20:50:46,696 INFO Start testing... +2025-04-19 20:50:46,696 INFO ===================================== +2025-04-19 20:51:09,821 INFO Incremental step 5 Testing res: 0.642667 +2025-04-19 20:51:09,826 INFO forgetting: 0.054400 +2025-04-19 20:51:09,832 INFO Incremental step: 6 +2025-04-19 20:51:52,351 INFO Epoch:0 train_loss:4.89800 +2025-04-19 20:52:09,368 INFO Epoch:0 val_res:0.524857 +2025-04-19 20:52:09,369 INFO Saving best model at Epoch 0 +2025-04-19 20:52:41,126 INFO Epoch:1 train_loss:1.54251 +2025-04-19 20:52:50,932 INFO Epoch:1 val_res:0.559429 +2025-04-19 20:52:50,933 INFO Saving best model at Epoch 1 +2025-04-19 20:53:20,077 INFO Epoch:2 train_loss:1.02242 +2025-04-19 20:53:29,539 INFO Epoch:2 val_res:0.560000 +2025-04-19 20:53:29,542 INFO Saving best model at Epoch 2 +2025-04-19 20:53:59,582 INFO Epoch:3 train_loss:0.89236 +2025-04-19 20:54:09,332 INFO Epoch:3 val_res:0.563714 +2025-04-19 20:54:09,333 INFO Saving best model at Epoch 3 +2025-04-19 20:54:38,861 INFO Epoch:4 train_loss:0.84429 +2025-04-19 20:54:48,249 INFO Epoch:4 val_res:0.570571 +2025-04-19 20:54:48,249 INFO Saving best model at Epoch 4 +2025-04-19 20:55:17,235 INFO Epoch:5 train_loss:0.80940 +2025-04-19 20:55:26,445 INFO Epoch:5 val_res:0.576571 +2025-04-19 20:55:26,446 INFO Saving best model at Epoch 5 +2025-04-19 20:55:56,183 INFO Epoch:6 train_loss:0.79022 +2025-04-19 20:56:05,147 INFO Epoch:6 val_res:0.577429 +2025-04-19 20:56:05,148 INFO Saving best model at Epoch 6 +2025-04-19 20:56:35,253 INFO Epoch:7 train_loss:0.76870 +2025-04-19 20:56:44,329 INFO Epoch:7 val_res:0.583429 +2025-04-19 20:56:44,329 INFO Saving best model at Epoch 7 +2025-04-19 20:57:14,788 INFO Epoch:8 train_loss:0.76146 +2025-04-19 20:57:23,780 INFO Epoch:8 val_res:0.586286 +2025-04-19 20:57:23,780 INFO Saving best model at Epoch 8 +2025-04-19 20:57:53,313 INFO Epoch:9 train_loss:0.74182 +2025-04-19 20:58:02,244 INFO Epoch:9 val_res:0.586571 +2025-04-19 20:58:02,244 INFO Saving best model at Epoch 9 +2025-04-19 20:58:32,097 INFO Epoch:10 train_loss:0.73321 +2025-04-19 20:58:41,251 INFO Epoch:10 val_res:0.588000 +2025-04-19 20:58:41,251 INFO Saving best model at Epoch 10 +2025-04-19 20:59:12,836 INFO Epoch:11 train_loss:0.72121 +2025-04-19 20:59:24,817 INFO Epoch:11 val_res:0.594286 +2025-04-19 20:59:24,817 INFO Saving best model at Epoch 11 +2025-04-19 20:59:56,525 INFO Epoch:12 train_loss:0.71684 +2025-04-19 21:00:08,178 INFO Epoch:12 val_res:0.592857 +2025-04-19 21:00:38,395 INFO Epoch:13 train_loss:0.71689 +2025-04-19 21:00:51,408 INFO Epoch:13 val_res:0.595714 +2025-04-19 21:00:51,408 INFO Saving best model at Epoch 13 +2025-04-19 21:01:21,563 INFO Epoch:14 train_loss:0.72950 +2025-04-19 21:01:33,591 INFO Epoch:14 val_res:0.600571 +2025-04-19 21:01:33,591 INFO Saving best model at Epoch 14 +2025-04-19 21:02:03,894 INFO Epoch:15 train_loss:0.74249 +2025-04-19 21:02:15,896 INFO Epoch:15 val_res:0.600857 +2025-04-19 21:02:15,896 INFO Saving best model at Epoch 15 +2025-04-19 21:02:46,936 INFO Epoch:16 train_loss:0.71690 +2025-04-19 21:02:58,884 INFO Epoch:16 val_res:0.606286 +2025-04-19 21:02:58,885 INFO Saving best model at Epoch 16 +2025-04-19 21:03:29,697 INFO Epoch:17 train_loss:0.71187 +2025-04-19 21:03:41,794 INFO Epoch:17 val_res:0.606000 +2025-04-19 21:04:11,129 INFO Epoch:18 train_loss:0.69139 +2025-04-19 21:04:23,264 INFO Epoch:18 val_res:0.608857 +2025-04-19 21:04:23,265 INFO Saving best model at Epoch 18 +2025-04-19 21:04:54,340 INFO Epoch:19 train_loss:0.67211 +2025-04-19 21:05:06,052 INFO Epoch:19 val_res:0.610571 +2025-04-19 21:05:06,053 INFO Saving best model at Epoch 19 +2025-04-19 21:05:36,430 INFO Epoch:20 train_loss:0.66759 +2025-04-19 21:05:48,111 INFO Epoch:20 val_res:0.611714 +2025-04-19 21:05:48,111 INFO Saving best model at Epoch 20 +2025-04-19 21:06:18,495 INFO Epoch:21 train_loss:0.68768 +2025-04-19 21:06:30,266 INFO Epoch:21 val_res:0.616000 +2025-04-19 21:06:30,266 INFO Saving best model at Epoch 21 +2025-04-19 21:06:59,870 INFO Epoch:22 train_loss:0.67218 +2025-04-19 21:07:11,543 INFO Epoch:22 val_res:0.616857 +2025-04-19 21:07:11,543 INFO Saving best model at Epoch 22 +2025-04-19 21:07:42,090 INFO Epoch:23 train_loss:0.74689 +2025-04-19 21:07:54,029 INFO Epoch:23 val_res:0.621143 +2025-04-19 21:07:54,029 INFO Saving best model at Epoch 23 +2025-04-19 21:08:23,771 INFO Epoch:24 train_loss:0.75971 +2025-04-19 21:08:36,418 INFO Epoch:24 val_res:0.623714 +2025-04-19 21:08:36,418 INFO Saving best model at Epoch 24 +2025-04-19 21:09:08,701 INFO Epoch:25 train_loss:0.71870 +2025-04-19 21:09:20,768 INFO Epoch:25 val_res:0.625714 +2025-04-19 21:09:20,768 INFO Saving best model at Epoch 25 +2025-04-19 21:09:50,681 INFO Epoch:26 train_loss:0.71349 +2025-04-19 21:10:02,616 INFO Epoch:26 val_res:0.627429 +2025-04-19 21:10:02,616 INFO Saving best model at Epoch 26 +2025-04-19 21:10:32,880 INFO Epoch:27 train_loss:0.67550 +2025-04-19 21:10:44,534 INFO Epoch:27 val_res:0.631429 +2025-04-19 21:10:44,534 INFO Saving best model at Epoch 27 +2025-04-19 21:11:15,267 INFO Epoch:28 train_loss:0.67687 +2025-04-19 21:11:27,144 INFO Epoch:28 val_res:0.637143 +2025-04-19 21:11:27,144 INFO Saving best model at Epoch 28 +2025-04-19 21:11:57,777 INFO Epoch:29 train_loss:0.66081 +2025-04-19 21:12:09,620 INFO Epoch:29 val_res:0.637143 +2025-04-19 21:12:38,028 INFO Epoch:30 train_loss:0.64523 +2025-04-19 21:12:49,940 INFO Epoch:30 val_res:0.636571 +2025-04-19 21:13:19,225 INFO Epoch:31 train_loss:0.63806 +2025-04-19 21:13:31,063 INFO Epoch:31 val_res:0.637714 +2025-04-19 21:13:31,063 INFO Saving best model at Epoch 31 +2025-04-19 21:14:01,892 INFO Epoch:32 train_loss:0.62645 +2025-04-19 21:14:13,724 INFO Epoch:32 val_res:0.639429 +2025-04-19 21:14:13,725 INFO Saving best model at Epoch 32 +2025-04-19 21:14:44,538 INFO Epoch:33 train_loss:0.63131 +2025-04-19 21:14:56,530 INFO Epoch:33 val_res:0.638571 +2025-04-19 21:15:25,734 INFO Epoch:34 train_loss:0.64435 +2025-04-19 21:15:37,575 INFO Epoch:34 val_res:0.638571 +2025-04-19 21:16:07,418 INFO Epoch:35 train_loss:0.70666 +2025-04-19 21:16:19,374 INFO Epoch:35 val_res:0.645143 +2025-04-19 21:16:19,374 INFO Saving best model at Epoch 35 +2025-04-19 21:16:50,169 INFO Epoch:36 train_loss:0.67621 +2025-04-19 21:17:01,818 INFO Epoch:36 val_res:0.643143 +2025-04-19 21:17:31,095 INFO Epoch:37 train_loss:0.62957 +2025-04-19 21:17:44,087 INFO Epoch:37 val_res:0.648286 +2025-04-19 21:17:44,088 INFO Saving best model at Epoch 37 +2025-04-19 21:18:14,174 INFO Epoch:38 train_loss:0.67510 +2025-04-19 21:18:26,447 INFO Epoch:38 val_res:0.645429 +2025-04-19 21:18:53,519 INFO Epoch:39 train_loss:0.66905 +2025-04-19 21:19:03,137 INFO Epoch:39 val_res:0.644000 +2025-04-19 21:19:31,966 INFO Epoch:40 train_loss:0.63654 +2025-04-19 21:19:44,154 INFO Epoch:40 val_res:0.646286 +2025-04-19 21:20:13,282 INFO Epoch:41 train_loss:0.65664 +2025-04-19 21:20:25,832 INFO Epoch:41 val_res:0.650857 +2025-04-19 21:20:25,832 INFO Saving best model at Epoch 41 +2025-04-19 21:20:56,583 INFO Epoch:42 train_loss:0.62983 +2025-04-19 21:21:08,761 INFO Epoch:42 val_res:0.649429 +2025-04-19 21:21:37,887 INFO Epoch:43 train_loss:0.63287 +2025-04-19 21:21:49,954 INFO Epoch:43 val_res:0.649429 +2025-04-19 21:22:18,932 INFO Epoch:44 train_loss:0.74843 +2025-04-19 21:22:30,961 INFO Epoch:44 val_res:0.645143 +2025-04-19 21:22:59,598 INFO Epoch:45 train_loss:0.78252 +2025-04-19 21:23:11,602 INFO Epoch:45 val_res:0.653429 +2025-04-19 21:23:11,602 INFO Saving best model at Epoch 45 +2025-04-19 21:23:42,247 INFO Epoch:46 train_loss:0.67935 +2025-04-19 21:23:54,063 INFO Epoch:46 val_res:0.650286 +2025-04-19 21:24:21,516 INFO Epoch:47 train_loss:0.62243 +2025-04-19 21:24:33,293 INFO Epoch:47 val_res:0.650286 +2025-04-19 21:25:06,112 INFO Epoch:48 train_loss:0.60155 +2025-04-19 21:25:19,420 INFO Epoch:48 val_res:0.650571 +2025-04-19 21:25:47,689 INFO Epoch:49 train_loss:0.58737 +2025-04-19 21:25:58,196 INFO Epoch:49 val_res:0.651714 +2025-04-19 21:26:26,942 INFO Epoch:50 train_loss:0.60586 +2025-04-19 21:26:36,643 INFO Epoch:50 val_res:0.650286 +2025-04-19 21:27:05,596 INFO Epoch:51 train_loss:0.62316 +2025-04-19 21:27:15,314 INFO Epoch:51 val_res:0.647429 +2025-04-19 21:27:43,252 INFO Epoch:52 train_loss:0.62226 +2025-04-19 21:27:53,200 INFO Epoch:52 val_res:0.649429 +2025-04-19 21:28:21,049 INFO Epoch:53 train_loss:0.69559 +2025-04-19 21:28:30,701 INFO Epoch:53 val_res:0.646000 +2025-04-19 21:28:59,039 INFO Epoch:54 train_loss:0.61194 +2025-04-19 21:29:08,853 INFO Epoch:54 val_res:0.648571 +2025-04-19 21:29:36,670 INFO Epoch:55 train_loss:0.60422 +2025-04-19 21:29:46,260 INFO Epoch:55 val_res:0.647429 +2025-04-19 21:30:14,277 INFO Epoch:56 train_loss:0.58719 +2025-04-19 21:30:24,164 INFO Epoch:56 val_res:0.648286 +2025-04-19 21:30:52,006 INFO Epoch:57 train_loss:0.58813 +2025-04-19 21:31:01,840 INFO Epoch:57 val_res:0.649143 +2025-04-19 21:31:29,257 INFO Epoch:58 train_loss:0.58348 +2025-04-19 21:31:39,037 INFO Epoch:58 val_res:0.652286 +2025-04-19 21:32:06,035 INFO Epoch:59 train_loss:0.63120 +2025-04-19 21:32:15,753 INFO Epoch:59 val_res:0.645143 +2025-04-19 21:32:43,222 INFO Epoch:60 train_loss:0.66201 +2025-04-19 21:32:53,052 INFO Epoch:60 val_res:0.639714 +2025-04-19 21:33:22,688 INFO Epoch:61 train_loss:0.64491 +2025-04-19 21:33:32,355 INFO Epoch:61 val_res:0.642571 +2025-04-19 21:34:00,352 INFO Epoch:62 train_loss:0.60681 +2025-04-19 21:34:10,053 INFO Epoch:62 val_res:0.646857 +2025-04-19 21:34:37,552 INFO Epoch:63 train_loss:0.62590 +2025-04-19 21:34:47,285 INFO Epoch:63 val_res:0.644857 +2025-04-19 21:35:14,517 INFO Epoch:64 train_loss:0.60269 +2025-04-19 21:35:23,988 INFO Epoch:64 val_res:0.646857 +2025-04-19 21:35:51,621 INFO Epoch:65 train_loss:0.58564 +2025-04-19 21:36:01,093 INFO Epoch:65 val_res:0.644286 +2025-04-19 21:36:29,258 INFO Epoch:66 train_loss:0.56843 +2025-04-19 21:36:39,248 INFO Epoch:66 val_res:0.642000 +2025-04-19 21:37:07,233 INFO Epoch:67 train_loss:0.57523 +2025-04-19 21:37:17,161 INFO Epoch:67 val_res:0.640286 +2025-04-19 21:37:44,030 INFO Epoch:68 train_loss:0.60202 +2025-04-19 21:37:53,846 INFO Epoch:68 val_res:0.644286 +2025-04-19 21:38:21,736 INFO Epoch:69 train_loss:0.68893 +2025-04-19 21:38:31,299 INFO Epoch:69 val_res:0.637143 +2025-04-19 21:38:58,671 INFO Epoch:70 train_loss:0.72803 +2025-04-19 21:39:08,343 INFO Epoch:70 val_res:0.638286 +2025-04-19 21:39:36,369 INFO Epoch:71 train_loss:0.62719 +2025-04-19 21:39:46,374 INFO Epoch:71 val_res:0.638571 +2025-04-19 21:40:14,340 INFO Epoch:72 train_loss:0.58491 +2025-04-19 21:40:24,261 INFO Epoch:72 val_res:0.634857 +2025-04-19 21:40:51,320 INFO Epoch:73 train_loss:0.57071 +2025-04-19 21:41:00,921 INFO Epoch:73 val_res:0.638571 +2025-04-19 21:41:28,530 INFO Epoch:74 train_loss:0.59469 +2025-04-19 21:41:38,256 INFO Epoch:74 val_res:0.638286 +2025-04-19 21:42:07,410 INFO Epoch:75 train_loss:0.58239 +2025-04-19 21:42:17,409 INFO Epoch:75 val_res:0.630857 +2025-04-19 21:42:44,901 INFO Epoch:76 train_loss:0.60110 +2025-04-19 21:42:54,529 INFO Epoch:76 val_res:0.636286 +2025-04-19 21:43:21,236 INFO Epoch:77 train_loss:0.61664 +2025-04-19 21:43:30,685 INFO Epoch:77 val_res:0.632286 +2025-04-19 21:43:57,900 INFO Epoch:78 train_loss:0.59624 +2025-04-19 21:44:07,908 INFO Epoch:78 val_res:0.638857 +2025-04-19 21:44:35,547 INFO Epoch:79 train_loss:0.63275 +2025-04-19 21:44:45,367 INFO Epoch:79 val_res:0.633143 +2025-04-19 21:45:12,901 INFO Epoch:80 train_loss:0.59312 +2025-04-19 21:45:22,567 INFO Epoch:80 val_res:0.634571 +2025-04-19 21:45:50,566 INFO Epoch:81 train_loss:0.57828 +2025-04-19 21:46:00,424 INFO Epoch:81 val_res:0.629714 +2025-04-19 21:46:28,378 INFO Epoch:82 train_loss:0.59146 +2025-04-19 21:46:38,068 INFO Epoch:82 val_res:0.631714 +2025-04-19 21:47:05,755 INFO Epoch:83 train_loss:0.64199 +2025-04-19 21:47:15,359 INFO Epoch:83 val_res:0.630857 +2025-04-19 21:47:44,677 INFO Epoch:84 train_loss:0.59915 +2025-04-19 21:47:54,364 INFO Epoch:84 val_res:0.625714 +2025-04-19 21:48:22,291 INFO Epoch:85 train_loss:0.64183 +2025-04-19 21:48:32,484 INFO Epoch:85 val_res:0.631429 +2025-04-19 21:49:00,783 INFO Epoch:86 train_loss:0.62077 +2025-04-19 21:49:10,358 INFO Epoch:86 val_res:0.629714 +2025-04-19 21:49:37,926 INFO Epoch:87 train_loss:0.59190 +2025-04-19 21:49:47,810 INFO Epoch:87 val_res:0.630571 +2025-04-19 21:50:15,835 INFO Epoch:88 train_loss:0.59539 +2025-04-19 21:50:25,587 INFO Epoch:88 val_res:0.622000 +2025-04-19 21:50:53,697 INFO Epoch:89 train_loss:0.63247 +2025-04-19 21:51:03,266 INFO Epoch:89 val_res:0.630571 +2025-04-19 21:51:31,412 INFO Epoch:90 train_loss:0.61746 +2025-04-19 21:51:41,332 INFO Epoch:90 val_res:0.627429 +2025-04-19 21:52:08,462 INFO Epoch:91 train_loss:0.59528 +2025-04-19 21:52:18,161 INFO Epoch:91 val_res:0.618857 +2025-04-19 21:52:45,829 INFO Epoch:92 train_loss:0.59436 +2025-04-19 21:52:55,434 INFO Epoch:92 val_res:0.620286 +2025-04-19 21:53:23,504 INFO Epoch:93 train_loss:0.58292 +2025-04-19 21:53:33,170 INFO Epoch:93 val_res:0.623143 +2025-04-19 21:54:01,166 INFO Epoch:94 train_loss:0.57535 +2025-04-19 21:54:11,110 INFO Epoch:94 val_res:0.620571 +2025-04-19 21:54:38,338 INFO Epoch:95 train_loss:0.59860 +2025-04-19 21:54:48,036 INFO Epoch:95 val_res:0.622286 +2025-04-19 21:55:14,865 INFO Epoch:96 train_loss:0.59330 +2025-04-19 21:55:24,349 INFO Epoch:96 val_res:0.620857 +2025-04-19 21:55:52,377 INFO Epoch:97 train_loss:0.58562 +2025-04-19 21:56:01,910 INFO Epoch:97 val_res:0.615143 +2025-04-19 21:56:30,129 INFO Epoch:98 train_loss:0.61747 +2025-04-19 21:56:39,962 INFO Epoch:98 val_res:0.618000 +2025-04-19 21:57:08,335 INFO Epoch:99 train_loss:0.58019 +2025-04-19 21:57:18,087 INFO Epoch:99 val_res:0.618000 +2025-04-19 21:57:18,485 INFO ===================================== +2025-04-19 21:57:18,486 INFO Start testing... +2025-04-19 21:57:18,486 INFO ===================================== +2025-04-19 21:57:31,867 INFO Incremental step 6 Testing res: 0.646857 +2025-04-19 21:57:31,870 INFO forgetting: 0.034667 +2025-04-19 21:57:31,874 INFO Incremental step: 7 +2025-04-19 21:58:22,756 INFO Epoch:0 train_loss:4.55621 +2025-04-19 21:58:38,635 INFO Epoch:0 val_res:0.561000 +2025-04-19 21:58:38,635 INFO Saving best model at Epoch 0 +2025-04-19 21:59:13,711 INFO Epoch:1 train_loss:1.33230 +2025-04-19 21:59:24,261 INFO Epoch:1 val_res:0.573750 +2025-04-19 21:59:24,261 INFO Saving best model at Epoch 1 +2025-04-19 21:59:59,255 INFO Epoch:2 train_loss:1.00747 +2025-04-19 22:00:09,859 INFO Epoch:2 val_res:0.576750 +2025-04-19 22:00:09,859 INFO Saving best model at Epoch 2 +2025-04-19 22:00:45,441 INFO Epoch:3 train_loss:0.92151 +2025-04-19 22:00:56,157 INFO Epoch:3 val_res:0.578500 +2025-04-19 22:00:56,157 INFO Saving best model at Epoch 3 +2025-04-19 22:01:31,223 INFO Epoch:4 train_loss:0.88111 +2025-04-19 22:01:41,889 INFO Epoch:4 val_res:0.577500 +2025-04-19 22:02:15,163 INFO Epoch:5 train_loss:0.85104 +2025-04-19 22:02:25,527 INFO Epoch:5 val_res:0.579500 +2025-04-19 22:02:25,528 INFO Saving best model at Epoch 5 +2025-04-19 22:03:00,862 INFO Epoch:6 train_loss:0.82626 +2025-04-19 22:03:12,240 INFO Epoch:6 val_res:0.580750 +2025-04-19 22:03:12,241 INFO Saving best model at Epoch 6 +2025-04-19 22:03:46,983 INFO Epoch:7 train_loss:0.81646 +2025-04-19 22:03:57,648 INFO Epoch:7 val_res:0.583250 +2025-04-19 22:03:57,648 INFO Saving best model at Epoch 7 +2025-04-19 22:04:33,197 INFO Epoch:8 train_loss:0.80150 +2025-04-19 22:04:43,558 INFO Epoch:8 val_res:0.582750 +2025-04-19 22:05:17,692 INFO Epoch:9 train_loss:0.78725 +2025-04-19 22:05:27,981 INFO Epoch:9 val_res:0.586000 +2025-04-19 22:05:27,982 INFO Saving best model at Epoch 9 +2025-04-19 22:06:03,201 INFO Epoch:10 train_loss:0.79458 +2025-04-19 22:06:13,744 INFO Epoch:10 val_res:0.587250 +2025-04-19 22:06:13,744 INFO Saving best model at Epoch 10 +2025-04-19 22:06:50,001 INFO Epoch:11 train_loss:0.80059 +2025-04-19 22:07:00,314 INFO Epoch:11 val_res:0.591750 +2025-04-19 22:07:00,314 INFO Saving best model at Epoch 11 +2025-04-19 22:07:35,358 INFO Epoch:12 train_loss:0.78384 +2025-04-19 22:07:46,451 INFO Epoch:12 val_res:0.587000 +2025-04-19 22:08:19,493 INFO Epoch:13 train_loss:0.75888 +2025-04-19 22:08:30,224 INFO Epoch:13 val_res:0.592250 +2025-04-19 22:08:30,224 INFO Saving best model at Epoch 13 +2025-04-19 22:09:05,825 INFO Epoch:14 train_loss:0.76817 +2025-04-19 22:09:16,940 INFO Epoch:14 val_res:0.595250 +2025-04-19 22:09:16,941 INFO Saving best model at Epoch 14 +2025-04-19 22:09:52,864 INFO Epoch:15 train_loss:0.80128 +2025-04-19 22:10:03,230 INFO Epoch:15 val_res:0.594500 +2025-04-19 22:10:37,281 INFO Epoch:16 train_loss:0.73487 +2025-04-19 22:10:48,237 INFO Epoch:16 val_res:0.595000 +2025-04-19 22:11:22,448 INFO Epoch:17 train_loss:0.69878 +2025-04-19 22:11:32,704 INFO Epoch:17 val_res:0.599500 +2025-04-19 22:11:32,704 INFO Saving best model at Epoch 17 +2025-04-19 22:12:08,411 INFO Epoch:18 train_loss:0.73111 +2025-04-19 22:12:18,990 INFO Epoch:18 val_res:0.593000 +2025-04-19 22:12:52,738 INFO Epoch:19 train_loss:0.81040 +2025-04-19 22:13:03,157 INFO Epoch:19 val_res:0.600750 +2025-04-19 22:13:03,157 INFO Saving best model at Epoch 19 +2025-04-19 22:13:38,975 INFO Epoch:20 train_loss:0.71961 +2025-04-19 22:13:49,253 INFO Epoch:20 val_res:0.601750 +2025-04-19 22:13:49,254 INFO Saving best model at Epoch 20 +2025-04-19 22:14:24,028 INFO Epoch:21 train_loss:0.69135 +2025-04-19 22:14:34,558 INFO Epoch:21 val_res:0.603500 +2025-04-19 22:14:34,558 INFO Saving best model at Epoch 21 +2025-04-19 22:15:10,382 INFO Epoch:22 train_loss:0.67523 +2025-04-19 22:15:21,230 INFO Epoch:22 val_res:0.603750 +2025-04-19 22:15:21,236 INFO Saving best model at Epoch 22 +2025-04-19 22:15:56,370 INFO Epoch:23 train_loss:0.68514 +2025-04-19 22:16:06,878 INFO Epoch:23 val_res:0.606250 +2025-04-19 22:16:06,879 INFO Saving best model at Epoch 23 +2025-04-19 22:16:41,996 INFO Epoch:24 train_loss:0.69542 +2025-04-19 22:16:52,861 INFO Epoch:24 val_res:0.608000 +2025-04-19 22:16:52,862 INFO Saving best model at Epoch 24 +2025-04-19 22:17:28,248 INFO Epoch:25 train_loss:0.68249 +2025-04-19 22:17:39,752 INFO Epoch:25 val_res:0.613000 +2025-04-19 22:17:39,753 INFO Saving best model at Epoch 25 +2025-04-19 22:18:14,879 INFO Epoch:26 train_loss:0.67880 +2025-04-19 22:18:25,708 INFO Epoch:26 val_res:0.607000 +2025-04-19 22:19:00,381 INFO Epoch:27 train_loss:0.70769 +2025-04-19 22:19:11,933 INFO Epoch:27 val_res:0.607500 +2025-04-19 22:19:46,883 INFO Epoch:28 train_loss:0.65874 +2025-04-19 22:19:57,223 INFO Epoch:28 val_res:0.612250 +2025-04-19 22:20:32,353 INFO Epoch:29 train_loss:0.62382 +2025-04-19 22:20:42,933 INFO Epoch:29 val_res:0.617500 +2025-04-19 22:20:42,933 INFO Saving best model at Epoch 29 +2025-04-19 22:21:18,572 INFO Epoch:30 train_loss:0.64535 +2025-04-19 22:21:28,935 INFO Epoch:30 val_res:0.620250 +2025-04-19 22:21:28,936 INFO Saving best model at Epoch 30 +2025-04-19 22:22:04,803 INFO Epoch:31 train_loss:0.71398 +2025-04-19 22:22:15,048 INFO Epoch:31 val_res:0.615000 +2025-04-19 22:22:49,177 INFO Epoch:32 train_loss:0.71951 +2025-04-19 22:22:59,778 INFO Epoch:32 val_res:0.620250 +2025-04-19 22:23:33,129 INFO Epoch:33 train_loss:0.62208 +2025-04-19 22:23:44,434 INFO Epoch:33 val_res:0.620500 +2025-04-19 22:23:44,434 INFO Saving best model at Epoch 33 +2025-04-19 22:24:20,165 INFO Epoch:34 train_loss:0.61045 +2025-04-19 22:24:30,303 INFO Epoch:34 val_res:0.623750 +2025-04-19 22:24:30,304 INFO Saving best model at Epoch 34 +2025-04-19 22:25:05,082 INFO Epoch:35 train_loss:0.64855 +2025-04-19 22:25:15,379 INFO Epoch:35 val_res:0.616750 +2025-04-19 22:25:50,780 INFO Epoch:36 train_loss:0.62758 +2025-04-19 22:26:01,605 INFO Epoch:36 val_res:0.622250 +2025-04-19 22:26:35,540 INFO Epoch:37 train_loss:0.63261 +2025-04-19 22:26:46,256 INFO Epoch:37 val_res:0.624000 +2025-04-19 22:26:46,256 INFO Saving best model at Epoch 37 +2025-04-19 22:27:22,493 INFO Epoch:38 train_loss:0.60677 +2025-04-19 22:27:33,563 INFO Epoch:38 val_res:0.621000 +2025-04-19 22:28:07,006 INFO Epoch:39 train_loss:0.68678 +2025-04-19 22:28:17,592 INFO Epoch:39 val_res:0.619000 +2025-04-19 22:28:51,823 INFO Epoch:40 train_loss:0.69121 +2025-04-19 22:29:02,254 INFO Epoch:40 val_res:0.622250 +2025-04-19 22:29:37,842 INFO Epoch:41 train_loss:0.64935 +2025-04-19 22:29:48,491 INFO Epoch:41 val_res:0.622250 +2025-04-19 22:30:22,640 INFO Epoch:42 train_loss:0.61668 +2025-04-19 22:30:33,139 INFO Epoch:42 val_res:0.621500 +2025-04-19 22:31:07,008 INFO Epoch:43 train_loss:0.62750 +2025-04-19 22:31:17,661 INFO Epoch:43 val_res:0.620000 +2025-04-19 22:31:54,185 INFO Epoch:44 train_loss:0.58289 +2025-04-19 22:32:04,643 INFO Epoch:44 val_res:0.622250 +2025-04-19 22:32:39,798 INFO Epoch:45 train_loss:0.59747 +2025-04-19 22:32:50,323 INFO Epoch:45 val_res:0.628250 +2025-04-19 22:32:50,324 INFO Saving best model at Epoch 45 +2025-04-19 22:33:26,515 INFO Epoch:46 train_loss:0.63024 +2025-04-19 22:33:36,933 INFO Epoch:46 val_res:0.627750 +2025-04-19 22:34:11,101 INFO Epoch:47 train_loss:0.61658 +2025-04-19 22:34:21,836 INFO Epoch:47 val_res:0.624500 +2025-04-19 22:34:55,616 INFO Epoch:48 train_loss:0.65075 +2025-04-19 22:35:07,104 INFO Epoch:48 val_res:0.627500 +2025-04-19 22:35:42,267 INFO Epoch:49 train_loss:0.62868 +2025-04-19 22:35:53,282 INFO Epoch:49 val_res:0.627250 +2025-04-19 22:36:27,266 INFO Epoch:50 train_loss:0.59199 +2025-04-19 22:36:37,764 INFO Epoch:50 val_res:0.625250 +2025-04-19 22:37:11,479 INFO Epoch:51 train_loss:0.58903 +2025-04-19 22:37:22,684 INFO Epoch:51 val_res:0.619250 +2025-04-19 22:37:56,064 INFO Epoch:52 train_loss:0.58681 +2025-04-19 22:38:06,458 INFO Epoch:52 val_res:0.624000 +2025-04-19 22:38:40,655 INFO Epoch:53 train_loss:0.57829 +2025-04-19 22:38:51,371 INFO Epoch:53 val_res:0.621250 +2025-04-19 22:39:25,772 INFO Epoch:54 train_loss:0.58198 +2025-04-19 22:39:36,802 INFO Epoch:54 val_res:0.617250 +2025-04-19 22:40:10,474 INFO Epoch:55 train_loss:0.64734 +2025-04-19 22:40:21,473 INFO Epoch:55 val_res:0.609000 +2025-04-19 22:40:55,275 INFO Epoch:56 train_loss:0.61277 +2025-04-19 22:41:06,117 INFO Epoch:56 val_res:0.620000 +2025-04-19 22:41:39,359 INFO Epoch:57 train_loss:0.57080 +2025-04-19 22:41:50,010 INFO Epoch:57 val_res:0.619250 +2025-04-19 22:42:23,748 INFO Epoch:58 train_loss:0.54583 +2025-04-19 22:42:35,199 INFO Epoch:58 val_res:0.619750 +2025-04-19 22:43:10,961 INFO Epoch:59 train_loss:0.54770 +2025-04-19 22:43:21,714 INFO Epoch:59 val_res:0.615000 +2025-04-19 22:43:55,549 INFO Epoch:60 train_loss:0.59480 +2025-04-19 22:44:06,585 INFO Epoch:60 val_res:0.614000 +2025-04-19 22:44:40,036 INFO Epoch:61 train_loss:0.59691 +2025-04-19 22:44:50,884 INFO Epoch:61 val_res:0.608500 +2025-04-19 22:45:25,094 INFO Epoch:62 train_loss:0.57764 +2025-04-19 22:45:35,861 INFO Epoch:62 val_res:0.610000 +2025-04-19 22:46:10,037 INFO Epoch:63 train_loss:0.61241 +2025-04-19 22:46:20,415 INFO Epoch:63 val_res:0.610750 +2025-04-19 22:46:53,947 INFO Epoch:64 train_loss:0.72319 +2025-04-19 22:47:04,446 INFO Epoch:64 val_res:0.615750 +2025-04-19 22:47:38,838 INFO Epoch:65 train_loss:0.60115 +2025-04-19 22:47:49,361 INFO Epoch:65 val_res:0.609500 +2025-04-19 22:48:23,913 INFO Epoch:66 train_loss:0.56686 +2025-04-19 22:48:35,011 INFO Epoch:66 val_res:0.613750 +2025-04-19 22:49:09,225 INFO Epoch:67 train_loss:0.53853 +2025-04-19 22:49:20,359 INFO Epoch:67 val_res:0.613500 +2025-04-19 22:49:54,137 INFO Epoch:68 train_loss:0.55268 +2025-04-19 22:50:05,610 INFO Epoch:68 val_res:0.612500 +2025-04-19 22:50:39,174 INFO Epoch:69 train_loss:0.56537 +2025-04-19 22:50:49,753 INFO Epoch:69 val_res:0.604000 +2025-04-19 22:51:24,040 INFO Epoch:70 train_loss:0.61620 +2025-04-19 22:51:34,283 INFO Epoch:70 val_res:0.604000 +2025-04-19 22:52:08,556 INFO Epoch:71 train_loss:0.63198 +2025-04-19 22:52:19,157 INFO Epoch:71 val_res:0.597250 +2025-04-19 22:52:52,957 INFO Epoch:72 train_loss:0.61364 +2025-04-19 22:53:03,433 INFO Epoch:72 val_res:0.604500 +2025-04-19 22:53:38,431 INFO Epoch:73 train_loss:0.54748 +2025-04-19 22:53:49,107 INFO Epoch:73 val_res:0.604500 +2025-04-19 22:54:22,675 INFO Epoch:74 train_loss:0.53601 +2025-04-19 22:54:33,334 INFO Epoch:74 val_res:0.604250 +2025-04-19 22:55:06,830 INFO Epoch:75 train_loss:0.53651 +2025-04-19 22:55:17,041 INFO Epoch:75 val_res:0.600250 +2025-04-19 22:55:51,731 INFO Epoch:76 train_loss:0.59820 +2025-04-19 22:56:02,299 INFO Epoch:76 val_res:0.601750 +2025-04-19 22:56:37,037 INFO Epoch:77 train_loss:0.61932 +2025-04-19 22:56:47,732 INFO Epoch:77 val_res:0.599250 +2025-04-19 22:57:21,189 INFO Epoch:78 train_loss:0.54775 +2025-04-19 22:57:32,351 INFO Epoch:78 val_res:0.595000 +2025-04-19 22:58:06,072 INFO Epoch:79 train_loss:0.53028 +2025-04-19 22:58:16,776 INFO Epoch:79 val_res:0.595500 +2025-04-19 22:58:50,040 INFO Epoch:80 train_loss:0.55783 +2025-04-19 22:59:00,651 INFO Epoch:80 val_res:0.592500 +2025-04-19 22:59:34,443 INFO Epoch:81 train_loss:0.59578 +2025-04-19 22:59:44,959 INFO Epoch:81 val_res:0.596750 +2025-04-19 23:00:18,861 INFO Epoch:82 train_loss:0.57449 +2025-04-19 23:00:29,562 INFO Epoch:82 val_res:0.591750 +2025-04-19 23:01:03,460 INFO Epoch:83 train_loss:0.60367 +2025-04-19 23:01:14,175 INFO Epoch:83 val_res:0.594000 +2025-04-19 23:01:47,565 INFO Epoch:84 train_loss:0.54739 +2025-04-19 23:01:58,122 INFO Epoch:84 val_res:0.592750 +2025-04-19 23:02:31,232 INFO Epoch:85 train_loss:0.57490 +2025-04-19 23:02:42,373 INFO Epoch:85 val_res:0.597000 +2025-04-19 23:03:16,591 INFO Epoch:86 train_loss:0.57255 +2025-04-19 23:03:27,545 INFO Epoch:86 val_res:0.589000 +2025-04-19 23:04:01,870 INFO Epoch:87 train_loss:0.64583 +2025-04-19 23:04:12,607 INFO Epoch:87 val_res:0.587500 +2025-04-19 23:04:46,331 INFO Epoch:88 train_loss:0.59856 +2025-04-19 23:04:57,471 INFO Epoch:88 val_res:0.591250 +2025-04-19 23:05:30,376 INFO Epoch:89 train_loss:0.54087 +2025-04-19 23:05:41,215 INFO Epoch:89 val_res:0.588750 +2025-04-19 23:06:15,365 INFO Epoch:90 train_loss:0.53048 +2025-04-19 23:06:25,942 INFO Epoch:90 val_res:0.582500 +2025-04-19 23:06:59,278 INFO Epoch:91 train_loss:0.55621 +2025-04-19 23:07:10,055 INFO Epoch:91 val_res:0.592250 +2025-04-19 23:07:44,026 INFO Epoch:92 train_loss:0.55008 +2025-04-19 23:07:55,029 INFO Epoch:92 val_res:0.589500 +2025-04-19 23:08:28,559 INFO Epoch:93 train_loss:0.55178 +2025-04-19 23:08:39,587 INFO Epoch:93 val_res:0.586750 +2025-04-19 23:09:13,626 INFO Epoch:94 train_loss:0.55672 +2025-04-19 23:09:25,381 INFO Epoch:94 val_res:0.583250 +2025-04-19 23:09:59,140 INFO Epoch:95 train_loss:0.59502 +2025-04-19 23:10:09,807 INFO Epoch:95 val_res:0.578750 +2025-04-19 23:10:44,613 INFO Epoch:96 train_loss:0.61525 +2025-04-19 23:10:55,439 INFO Epoch:96 val_res:0.578500 +2025-04-19 23:11:28,929 INFO Epoch:97 train_loss:0.66425 +2025-04-19 23:11:39,900 INFO Epoch:97 val_res:0.581750 +2025-04-19 23:12:12,685 INFO Epoch:98 train_loss:0.65044 +2025-04-19 23:12:23,531 INFO Epoch:98 val_res:0.580750 +2025-04-19 23:12:56,936 INFO Epoch:99 train_loss:0.55041 +2025-04-19 23:13:07,722 INFO Epoch:99 val_res:0.579500 +2025-04-19 23:13:07,929 INFO ===================================== +2025-04-19 23:13:07,929 INFO Start testing... +2025-04-19 23:13:07,929 INFO ===================================== +2025-04-19 23:13:21,126 INFO Incremental step 7 Testing res: 0.624750 +2025-04-19 23:13:21,129 INFO forgetting: 0.080286 +2025-04-19 23:13:21,132 INFO Incremental step: 8 +2025-04-19 23:13:53,586 INFO Epoch:0 train_loss:5.12804 +2025-04-19 23:14:05,811 INFO Epoch:0 val_res:0.537333 +2025-04-19 23:14:05,812 INFO Saving best model at Epoch 0 +2025-04-19 23:14:36,200 INFO Epoch:1 train_loss:1.48168 +2025-04-19 23:14:48,068 INFO Epoch:1 val_res:0.556889 +2025-04-19 23:14:48,068 INFO Saving best model at Epoch 1 +2025-04-19 23:15:18,226 INFO Epoch:2 train_loss:0.97331 +2025-04-19 23:15:30,198 INFO Epoch:2 val_res:0.562667 +2025-04-19 23:15:30,198 INFO Saving best model at Epoch 2 +2025-04-19 23:16:00,278 INFO Epoch:3 train_loss:0.85720 +2025-04-19 23:16:12,401 INFO Epoch:3 val_res:0.562667 +2025-04-19 23:16:41,472 INFO Epoch:4 train_loss:0.81418 +2025-04-19 23:16:53,428 INFO Epoch:4 val_res:0.563111 +2025-04-19 23:16:53,428 INFO Saving best model at Epoch 4 +2025-04-19 23:17:23,541 INFO Epoch:5 train_loss:0.78712 +2025-04-19 23:17:35,232 INFO Epoch:5 val_res:0.565778 +2025-04-19 23:17:35,232 INFO Saving best model at Epoch 5 +2025-04-19 23:18:06,613 INFO Epoch:6 train_loss:0.77352 +2025-04-19 23:18:18,731 INFO Epoch:6 val_res:0.568000 +2025-04-19 23:18:18,732 INFO Saving best model at Epoch 6 +2025-04-19 23:18:49,332 INFO Epoch:7 train_loss:0.75791 +2025-04-19 23:19:01,092 INFO Epoch:7 val_res:0.570000 +2025-04-19 23:19:01,092 INFO Saving best model at Epoch 7 +2025-04-19 23:19:32,077 INFO Epoch:8 train_loss:0.74181 +2025-04-19 23:19:44,039 INFO Epoch:8 val_res:0.568889 +2025-04-19 23:20:13,974 INFO Epoch:9 train_loss:0.73368 +2025-04-19 23:20:25,868 INFO Epoch:9 val_res:0.569556 +2025-04-19 23:20:55,192 INFO Epoch:10 train_loss:0.72563 +2025-04-19 23:21:07,371 INFO Epoch:10 val_res:0.570000 +2025-04-19 23:21:35,528 INFO Epoch:11 train_loss:0.71274 +2025-04-19 23:21:47,543 INFO Epoch:11 val_res:0.573333 +2025-04-19 23:21:47,544 INFO Saving best model at Epoch 11 +2025-04-19 23:22:18,448 INFO Epoch:12 train_loss:0.69951 +2025-04-19 23:22:29,928 INFO Epoch:12 val_res:0.573333 +2025-04-19 23:22:58,685 INFO Epoch:13 train_loss:0.70117 +2025-04-19 23:23:10,390 INFO Epoch:13 val_res:0.573333 +2025-04-19 23:23:38,995 INFO Epoch:14 train_loss:0.69536 +2025-04-19 23:23:51,082 INFO Epoch:14 val_res:0.577111 +2025-04-19 23:23:51,082 INFO Saving best model at Epoch 14 +2025-04-19 23:24:22,386 INFO Epoch:15 train_loss:0.73347 +2025-04-19 23:24:34,183 INFO Epoch:15 val_res:0.577111 +2025-04-19 23:25:02,726 INFO Epoch:16 train_loss:0.73566 +2025-04-19 23:25:14,163 INFO Epoch:16 val_res:0.581111 +2025-04-19 23:25:14,163 INFO Saving best model at Epoch 16 +2025-04-19 23:25:45,083 INFO Epoch:17 train_loss:0.69391 +2025-04-19 23:25:56,866 INFO Epoch:17 val_res:0.580444 +2025-04-19 23:26:25,705 INFO Epoch:18 train_loss:0.68186 +2025-04-19 23:26:37,739 INFO Epoch:18 val_res:0.580667 +2025-04-19 23:27:06,862 INFO Epoch:19 train_loss:0.78394 +2025-04-19 23:27:18,902 INFO Epoch:19 val_res:0.580889 +2025-04-19 23:27:48,294 INFO Epoch:20 train_loss:0.69725 +2025-04-19 23:28:00,057 INFO Epoch:20 val_res:0.582222 +2025-04-19 23:28:00,058 INFO Saving best model at Epoch 20 +2025-04-19 23:28:30,478 INFO Epoch:21 train_loss:0.66740 +2025-04-19 23:28:42,481 INFO Epoch:21 val_res:0.586222 +2025-04-19 23:28:42,482 INFO Saving best model at Epoch 21 +2025-04-19 23:29:15,375 INFO Epoch:22 train_loss:0.65800 +2025-04-19 23:29:27,650 INFO Epoch:22 val_res:0.587111 +2025-04-19 23:29:27,651 INFO Saving best model at Epoch 22 +2025-04-19 23:29:58,614 INFO Epoch:23 train_loss:0.66251 +2025-04-19 23:30:10,271 INFO Epoch:23 val_res:0.590667 +2025-04-19 23:30:10,271 INFO Saving best model at Epoch 23 +2025-04-19 23:30:40,590 INFO Epoch:24 train_loss:0.67184 +2025-04-19 23:30:52,048 INFO Epoch:24 val_res:0.586444 +2025-04-19 23:31:20,648 INFO Epoch:25 train_loss:0.69224 +2025-04-19 23:31:32,364 INFO Epoch:25 val_res:0.590667 +2025-04-19 23:32:01,603 INFO Epoch:26 train_loss:0.69461 +2025-04-19 23:32:13,564 INFO Epoch:26 val_res:0.586889 +2025-04-19 23:32:42,450 INFO Epoch:27 train_loss:0.64713 +2025-04-19 23:32:54,211 INFO Epoch:27 val_res:0.593556 +2025-04-19 23:32:54,211 INFO Saving best model at Epoch 27 +2025-04-19 23:33:24,356 INFO Epoch:28 train_loss:0.65690 +2025-04-19 23:33:35,993 INFO Epoch:28 val_res:0.590667 +2025-04-19 23:34:04,909 INFO Epoch:29 train_loss:0.76930 +2025-04-19 23:34:16,571 INFO Epoch:29 val_res:0.590667 +2025-04-19 23:34:46,369 INFO Epoch:30 train_loss:0.72955 +2025-04-19 23:34:59,855 INFO Epoch:30 val_res:0.596667 +2025-04-19 23:34:59,856 INFO Saving best model at Epoch 30 +2025-04-19 23:35:30,181 INFO Epoch:31 train_loss:0.63960 +2025-04-19 23:35:42,881 INFO Epoch:31 val_res:0.598000 +2025-04-19 23:35:42,881 INFO Saving best model at Epoch 31 +2025-04-19 23:36:13,958 INFO Epoch:32 train_loss:0.63114 +2025-04-19 23:36:25,697 INFO Epoch:32 val_res:0.595111 +2025-04-19 23:36:54,548 INFO Epoch:33 train_loss:0.63277 +2025-04-19 23:37:06,414 INFO Epoch:33 val_res:0.598222 +2025-04-19 23:37:06,414 INFO Saving best model at Epoch 33 +2025-04-19 23:37:37,850 INFO Epoch:34 train_loss:0.68828 +2025-04-19 23:37:50,001 INFO Epoch:34 val_res:0.597333 +2025-04-19 23:38:18,175 INFO Epoch:35 train_loss:0.64707 +2025-04-19 23:38:29,806 INFO Epoch:35 val_res:0.599111 +2025-04-19 23:38:29,807 INFO Saving best model at Epoch 35 +2025-04-19 23:39:00,337 INFO Epoch:36 train_loss:0.62418 +2025-04-19 23:39:12,025 INFO Epoch:36 val_res:0.597556 +2025-04-19 23:39:40,641 INFO Epoch:37 train_loss:0.62443 +2025-04-19 23:39:52,442 INFO Epoch:37 val_res:0.594889 +2025-04-19 23:40:22,441 INFO Epoch:38 train_loss:0.63035 +2025-04-19 23:40:34,175 INFO Epoch:38 val_res:0.601111 +2025-04-19 23:40:34,175 INFO Saving best model at Epoch 38 +2025-04-19 23:41:04,656 INFO Epoch:39 train_loss:0.65112 +2025-04-19 23:41:16,880 INFO Epoch:39 val_res:0.598222 +2025-04-19 23:41:46,143 INFO Epoch:40 train_loss:0.66385 +2025-04-19 23:41:58,096 INFO Epoch:40 val_res:0.600000 +2025-04-19 23:42:27,742 INFO Epoch:41 train_loss:0.71131 +2025-04-19 23:42:39,790 INFO Epoch:41 val_res:0.596000 +2025-04-19 23:43:09,645 INFO Epoch:42 train_loss:0.67335 +2025-04-19 23:43:21,932 INFO Epoch:42 val_res:0.600667 +2025-04-19 23:43:50,333 INFO Epoch:43 train_loss:0.65138 +2025-04-19 23:44:02,153 INFO Epoch:43 val_res:0.596667 +2025-04-19 23:44:31,529 INFO Epoch:44 train_loss:0.63050 +2025-04-19 23:44:43,956 INFO Epoch:44 val_res:0.600222 +2025-04-19 23:45:13,972 INFO Epoch:45 train_loss:0.62288 +2025-04-19 23:45:25,842 INFO Epoch:45 val_res:0.602444 +2025-04-19 23:45:25,842 INFO Saving best model at Epoch 45 +2025-04-19 23:45:56,759 INFO Epoch:46 train_loss:0.63256 +2025-04-19 23:46:08,701 INFO Epoch:46 val_res:0.598667 +2025-04-19 23:46:38,283 INFO Epoch:47 train_loss:0.61632 +2025-04-19 23:46:50,101 INFO Epoch:47 val_res:0.598889 +2025-04-19 23:47:18,750 INFO Epoch:48 train_loss:0.61670 +2025-04-19 23:47:31,343 INFO Epoch:48 val_res:0.601556 +2025-04-19 23:48:00,070 INFO Epoch:49 train_loss:0.61521 +2025-04-19 23:48:11,860 INFO Epoch:49 val_res:0.601333 +2025-04-19 23:48:41,418 INFO Epoch:50 train_loss:0.61245 +2025-04-19 23:48:53,328 INFO Epoch:50 val_res:0.595778 +2025-04-19 23:49:22,155 INFO Epoch:51 train_loss:0.62457 +2025-04-19 23:49:34,300 INFO Epoch:51 val_res:0.598444 +2025-04-19 23:50:02,546 INFO Epoch:52 train_loss:0.66079 +2025-04-19 23:50:14,437 INFO Epoch:52 val_res:0.599111 +2025-04-19 23:50:42,967 INFO Epoch:53 train_loss:0.68025 +2025-04-19 23:50:54,477 INFO Epoch:53 val_res:0.596222 +2025-04-19 23:51:22,603 INFO Epoch:54 train_loss:0.67688 +2025-04-19 23:51:34,258 INFO Epoch:54 val_res:0.599333 +2025-04-19 23:52:03,214 INFO Epoch:55 train_loss:0.61432 +2025-04-19 23:52:15,848 INFO Epoch:55 val_res:0.596667 +2025-04-19 23:52:44,281 INFO Epoch:56 train_loss:0.59005 +2025-04-19 23:52:56,067 INFO Epoch:56 val_res:0.599778 +2025-04-19 23:53:25,054 INFO Epoch:57 train_loss:0.59519 +2025-04-19 23:53:37,312 INFO Epoch:57 val_res:0.598444 +2025-04-19 23:54:07,110 INFO Epoch:58 train_loss:0.63527 +2025-04-19 23:54:19,003 INFO Epoch:58 val_res:0.592667 +2025-04-19 23:54:49,440 INFO Epoch:59 train_loss:0.70364 +2025-04-19 23:55:01,596 INFO Epoch:59 val_res:0.593778 +2025-04-19 23:55:29,608 INFO Epoch:60 train_loss:0.61325 +2025-04-19 23:55:41,440 INFO Epoch:60 val_res:0.594444 +2025-04-19 23:56:10,634 INFO Epoch:61 train_loss:0.60317 +2025-04-19 23:56:22,693 INFO Epoch:61 val_res:0.591111 +2025-04-19 23:56:52,199 INFO Epoch:62 train_loss:0.59973 +2025-04-19 23:57:04,107 INFO Epoch:62 val_res:0.594889 +2025-04-19 23:57:33,449 INFO Epoch:63 train_loss:0.62894 +2025-04-19 23:57:45,574 INFO Epoch:63 val_res:0.590222 +2025-04-19 23:58:14,623 INFO Epoch:64 train_loss:0.66435 +2025-04-19 23:58:26,630 INFO Epoch:64 val_res:0.591778 +2025-04-19 23:58:54,979 INFO Epoch:65 train_loss:0.67985 +2025-04-19 23:59:06,719 INFO Epoch:65 val_res:0.591556 +2025-04-19 23:59:37,241 INFO Epoch:66 train_loss:0.62162 +2025-04-19 23:59:49,166 INFO Epoch:66 val_res:0.586667 +2025-04-20 00:00:17,359 INFO Epoch:67 train_loss:0.61435 +2025-04-20 00:00:29,237 INFO Epoch:67 val_res:0.584889 +2025-04-20 00:00:58,230 INFO Epoch:68 train_loss:0.58408 +2025-04-20 00:01:10,333 INFO Epoch:68 val_res:0.585778 +2025-04-20 00:01:38,766 INFO Epoch:69 train_loss:0.55534 +2025-04-20 00:01:50,854 INFO Epoch:69 val_res:0.587111 +2025-04-20 00:02:20,085 INFO Epoch:70 train_loss:0.56010 +2025-04-20 00:02:34,258 INFO Epoch:70 val_res:0.586000 +2025-04-20 00:03:02,676 INFO Epoch:71 train_loss:0.63349 +2025-04-20 00:03:14,552 INFO Epoch:71 val_res:0.583556 +2025-04-20 00:03:45,256 INFO Epoch:72 train_loss:0.64256 +2025-04-20 00:03:57,634 INFO Epoch:72 val_res:0.581333 +2025-04-20 00:04:26,535 INFO Epoch:73 train_loss:0.61432 +2025-04-20 00:04:38,430 INFO Epoch:73 val_res:0.579333 +2025-04-20 00:05:08,154 INFO Epoch:74 train_loss:0.61116 +2025-04-20 00:05:19,895 INFO Epoch:74 val_res:0.580222 +2025-04-20 00:05:49,709 INFO Epoch:75 train_loss:0.58557 +2025-04-20 00:06:01,729 INFO Epoch:75 val_res:0.582222 +2025-04-20 00:06:31,683 INFO Epoch:76 train_loss:0.57930 +2025-04-20 00:06:43,854 INFO Epoch:76 val_res:0.576667 +2025-04-20 00:07:11,947 INFO Epoch:77 train_loss:0.58292 +2025-04-20 00:07:23,763 INFO Epoch:77 val_res:0.571111 +2025-04-20 00:07:52,494 INFO Epoch:78 train_loss:0.67689 +2025-04-20 00:08:04,407 INFO Epoch:78 val_res:0.579111 +2025-04-20 00:08:33,213 INFO Epoch:79 train_loss:0.67220 +2025-04-20 00:08:45,206 INFO Epoch:79 val_res:0.574889 +2025-04-20 00:09:14,833 INFO Epoch:80 train_loss:0.61536 +2025-04-20 00:09:26,723 INFO Epoch:80 val_res:0.574222 +2025-04-20 00:09:57,305 INFO Epoch:81 train_loss:0.59300 +2025-04-20 00:10:10,223 INFO Epoch:81 val_res:0.572444 +2025-04-20 00:10:38,993 INFO Epoch:82 train_loss:0.59556 +2025-04-20 00:10:51,091 INFO Epoch:82 val_res:0.572000 +2025-04-20 00:11:20,418 INFO Epoch:83 train_loss:0.62956 +2025-04-20 00:11:32,270 INFO Epoch:83 val_res:0.571333 +2025-04-20 00:12:00,700 INFO Epoch:84 train_loss:0.66004 +2025-04-20 00:12:12,797 INFO Epoch:84 val_res:0.575556 +2025-04-20 00:12:40,966 INFO Epoch:85 train_loss:0.61757 +2025-04-20 00:12:53,053 INFO Epoch:85 val_res:0.568444 +2025-04-20 00:13:22,285 INFO Epoch:86 train_loss:0.60836 +2025-04-20 00:13:34,223 INFO Epoch:86 val_res:0.564667 +2025-04-20 00:14:03,850 INFO Epoch:87 train_loss:0.59769 +2025-04-20 00:14:15,727 INFO Epoch:87 val_res:0.569556 +2025-04-20 00:14:44,178 INFO Epoch:88 train_loss:0.65314 +2025-04-20 00:14:56,058 INFO Epoch:88 val_res:0.565556 +2025-04-20 00:15:25,469 INFO Epoch:89 train_loss:0.58866 +2025-04-20 00:15:37,468 INFO Epoch:89 val_res:0.562889 +2025-04-20 00:16:06,663 INFO Epoch:90 train_loss:0.58071 +2025-04-20 00:16:18,588 INFO Epoch:90 val_res:0.558889 +2025-04-20 00:16:48,380 INFO Epoch:91 train_loss:0.57678 +2025-04-20 00:17:00,319 INFO Epoch:91 val_res:0.560667 +2025-04-20 00:17:28,938 INFO Epoch:92 train_loss:0.58439 +2025-04-20 00:17:41,028 INFO Epoch:92 val_res:0.560889 +2025-04-20 00:18:09,379 INFO Epoch:93 train_loss:0.59844 +2025-04-20 00:18:21,365 INFO Epoch:93 val_res:0.559111 +2025-04-20 00:18:50,323 INFO Epoch:94 train_loss:0.65024 +2025-04-20 00:19:02,294 INFO Epoch:94 val_res:0.554444 +2025-04-20 00:19:31,848 INFO Epoch:95 train_loss:0.61216 +2025-04-20 00:19:43,564 INFO Epoch:95 val_res:0.561333 +2025-04-20 00:20:13,679 INFO Epoch:96 train_loss:0.56706 +2025-04-20 00:20:26,385 INFO Epoch:96 val_res:0.560000 +2025-04-20 00:20:55,591 INFO Epoch:97 train_loss:0.65758 +2025-04-20 00:21:08,093 INFO Epoch:97 val_res:0.550889 +2025-04-20 00:21:37,204 INFO Epoch:98 train_loss:0.64193 +2025-04-20 00:21:49,171 INFO Epoch:98 val_res:0.552000 +2025-04-20 00:22:16,754 INFO Epoch:99 train_loss:0.58958 +2025-04-20 00:22:28,730 INFO Epoch:99 val_res:0.553556 +2025-04-20 00:22:28,940 INFO ===================================== +2025-04-20 00:22:28,940 INFO Start testing... +2025-04-20 00:22:28,940 INFO ===================================== +2025-04-20 00:22:42,949 INFO Incremental step 8 Testing res: 0.596000 +2025-04-20 00:22:42,954 INFO forgetting: 0.093250 +2025-04-20 00:22:42,959 INFO Incremental step: 9 +2025-04-20 00:23:16,618 INFO Epoch:0 train_loss:4.26498 +2025-04-20 00:23:30,193 INFO Epoch:0 val_res:0.529000 +2025-04-20 00:23:30,193 INFO Saving best model at Epoch 0 +2025-04-20 00:24:05,284 INFO Epoch:1 train_loss:1.08905 +2025-04-20 00:24:18,305 INFO Epoch:1 val_res:0.546400 +2025-04-20 00:24:18,306 INFO Saving best model at Epoch 1 +2025-04-20 00:24:53,354 INFO Epoch:2 train_loss:0.77906 +2025-04-20 00:25:06,401 INFO Epoch:2 val_res:0.549400 +2025-04-20 00:25:06,401 INFO Saving best model at Epoch 2 +2025-04-20 00:25:42,034 INFO Epoch:3 train_loss:0.70835 +2025-04-20 00:25:55,163 INFO Epoch:3 val_res:0.552200 +2025-04-20 00:25:55,163 INFO Saving best model at Epoch 3 +2025-04-20 00:26:28,931 INFO Epoch:4 train_loss:0.67987 +2025-04-20 00:26:41,757 INFO Epoch:4 val_res:0.552800 +2025-04-20 00:26:41,758 INFO Saving best model at Epoch 4 +2025-04-20 00:27:16,777 INFO Epoch:5 train_loss:0.66026 +2025-04-20 00:27:29,826 INFO Epoch:5 val_res:0.555000 +2025-04-20 00:27:29,827 INFO Saving best model at Epoch 5 +2025-04-20 00:28:06,528 INFO Epoch:6 train_loss:0.64540 +2025-04-20 00:28:20,678 INFO Epoch:6 val_res:0.556200 +2025-04-20 00:28:20,678 INFO Saving best model at Epoch 6 +2025-04-20 00:28:56,113 INFO Epoch:7 train_loss:0.63266 +2025-04-20 00:29:09,088 INFO Epoch:7 val_res:0.557200 +2025-04-20 00:29:09,091 INFO Saving best model at Epoch 7 +2025-04-20 00:29:43,393 INFO Epoch:8 train_loss:0.62550 +2025-04-20 00:29:56,684 INFO Epoch:8 val_res:0.557800 +2025-04-20 00:29:56,684 INFO Saving best model at Epoch 8 +2025-04-20 00:30:32,158 INFO Epoch:9 train_loss:0.61967 +2025-04-20 00:30:45,350 INFO Epoch:9 val_res:0.557600 +2025-04-20 00:31:19,014 INFO Epoch:10 train_loss:0.63685 +2025-04-20 00:31:35,654 INFO Epoch:10 val_res:0.557000 +2025-04-20 00:32:09,008 INFO Epoch:11 train_loss:0.63393 +2025-04-20 00:32:22,492 INFO Epoch:11 val_res:0.560800 +2025-04-20 00:32:22,493 INFO Saving best model at Epoch 11 +2025-04-20 00:32:56,215 INFO Epoch:12 train_loss:0.60801 +2025-04-20 00:33:09,574 INFO Epoch:12 val_res:0.561800 +2025-04-20 00:33:09,574 INFO Saving best model at Epoch 12 +2025-04-20 00:33:44,473 INFO Epoch:13 train_loss:0.61711 +2025-04-20 00:33:57,765 INFO Epoch:13 val_res:0.562000 +2025-04-20 00:33:57,766 INFO Saving best model at Epoch 13 +2025-04-20 00:34:32,266 INFO Epoch:14 train_loss:0.62593 +2025-04-20 00:34:47,706 INFO Epoch:14 val_res:0.564600 +2025-04-20 00:34:47,706 INFO Saving best model at Epoch 14 +2025-04-20 00:35:23,265 INFO Epoch:15 train_loss:0.69808 +2025-04-20 00:35:36,142 INFO Epoch:15 val_res:0.563000 +2025-04-20 00:36:09,429 INFO Epoch:16 train_loss:0.63455 +2025-04-20 00:36:22,416 INFO Epoch:16 val_res:0.571000 +2025-04-20 00:36:22,416 INFO Saving best model at Epoch 16 +2025-04-20 00:36:57,291 INFO Epoch:17 train_loss:0.58938 +2025-04-20 00:37:10,182 INFO Epoch:17 val_res:0.568200 +2025-04-20 00:37:44,085 INFO Epoch:18 train_loss:0.57867 +2025-04-20 00:37:58,889 INFO Epoch:18 val_res:0.573800 +2025-04-20 00:37:58,889 INFO Saving best model at Epoch 18 +2025-04-20 00:38:34,435 INFO Epoch:19 train_loss:0.57648 +2025-04-20 00:38:47,595 INFO Epoch:19 val_res:0.574000 +2025-04-20 00:38:47,596 INFO Saving best model at Epoch 19 +2025-04-20 00:39:22,785 INFO Epoch:20 train_loss:0.60637 +2025-04-20 00:39:35,766 INFO Epoch:20 val_res:0.575800 +2025-04-20 00:39:35,767 INFO Saving best model at Epoch 20 +2025-04-20 00:40:10,772 INFO Epoch:21 train_loss:0.66898 +2025-04-20 00:40:24,397 INFO Epoch:21 val_res:0.576200 +2025-04-20 00:40:24,398 INFO Saving best model at Epoch 21 +2025-04-20 00:41:00,296 INFO Epoch:22 train_loss:0.59118 +2025-04-20 00:41:13,925 INFO Epoch:22 val_res:0.580400 +2025-04-20 00:41:13,926 INFO Saving best model at Epoch 22 +2025-04-20 00:41:48,853 INFO Epoch:23 train_loss:0.56695 +2025-04-20 00:42:02,687 INFO Epoch:23 val_res:0.579600 +2025-04-20 00:42:34,886 INFO Epoch:24 train_loss:0.62290 +2025-04-20 00:42:48,107 INFO Epoch:24 val_res:0.576600 +2025-04-20 00:43:19,614 INFO Epoch:25 train_loss:0.63870 +2025-04-20 00:43:32,698 INFO Epoch:25 val_res:0.581400 +2025-04-20 00:43:32,699 INFO Saving best model at Epoch 25 +2025-04-20 00:44:06,665 INFO Epoch:26 train_loss:0.61638 +2025-04-20 00:44:21,901 INFO Epoch:26 val_res:0.579600 +2025-04-20 00:44:53,937 INFO Epoch:27 train_loss:0.61884 +2025-04-20 00:45:07,455 INFO Epoch:27 val_res:0.583400 +2025-04-20 00:45:07,455 INFO Saving best model at Epoch 27 +2025-04-20 00:45:43,266 INFO Epoch:28 train_loss:0.59355 +2025-04-20 00:45:57,593 INFO Epoch:28 val_res:0.582800 +2025-04-20 00:46:31,017 INFO Epoch:29 train_loss:0.56592 +2025-04-20 00:46:44,242 INFO Epoch:29 val_res:0.583000 +2025-04-20 00:47:17,379 INFO Epoch:30 train_loss:0.55808 +2025-04-20 00:47:30,221 INFO Epoch:30 val_res:0.585000 +2025-04-20 00:47:30,221 INFO Saving best model at Epoch 30 +2025-04-20 00:48:04,763 INFO Epoch:31 train_loss:0.56567 +2025-04-20 00:48:17,621 INFO Epoch:31 val_res:0.585400 +2025-04-20 00:48:17,622 INFO Saving best model at Epoch 31 +2025-04-20 00:48:51,375 INFO Epoch:32 train_loss:0.56027 +2025-04-20 00:49:04,040 INFO Epoch:32 val_res:0.583600 +2025-04-20 00:49:37,373 INFO Epoch:33 train_loss:0.59348 +2025-04-20 00:49:50,393 INFO Epoch:33 val_res:0.581800 +2025-04-20 00:50:24,232 INFO Epoch:34 train_loss:0.61903 +2025-04-20 00:50:40,597 INFO Epoch:34 val_res:0.582600 +2025-04-20 00:51:14,705 INFO Epoch:35 train_loss:0.64711 +2025-04-20 00:51:27,706 INFO Epoch:35 val_res:0.586600 +2025-04-20 00:51:27,706 INFO Saving best model at Epoch 35 +2025-04-20 00:52:03,458 INFO Epoch:36 train_loss:0.57539 +2025-04-20 00:52:16,219 INFO Epoch:36 val_res:0.586400 +2025-04-20 00:52:50,345 INFO Epoch:37 train_loss:0.57608 +2025-04-20 00:53:05,002 INFO Epoch:37 val_res:0.586200 +2025-04-20 00:53:39,414 INFO Epoch:38 train_loss:0.56111 +2025-04-20 00:53:52,437 INFO Epoch:38 val_res:0.586000 +2025-04-20 00:54:26,236 INFO Epoch:39 train_loss:0.58858 +2025-04-20 00:54:39,340 INFO Epoch:39 val_res:0.585800 +2025-04-20 00:55:13,624 INFO Epoch:40 train_loss:0.58936 +2025-04-20 00:55:26,915 INFO Epoch:40 val_res:0.586600 +2025-04-20 00:56:01,000 INFO Epoch:41 train_loss:0.54884 +2025-04-20 00:56:14,445 INFO Epoch:41 val_res:0.586000 +2025-04-20 00:56:47,373 INFO Epoch:42 train_loss:0.56094 +2025-04-20 00:57:00,797 INFO Epoch:42 val_res:0.587200 +2025-04-20 00:57:00,798 INFO Saving best model at Epoch 42 +2025-04-20 00:57:34,847 INFO Epoch:43 train_loss:0.59162 +2025-04-20 00:57:48,292 INFO Epoch:43 val_res:0.588800 +2025-04-20 00:57:48,293 INFO Saving best model at Epoch 43 +2025-04-20 00:58:21,946 INFO Epoch:44 train_loss:0.56488 +2025-04-20 00:58:34,907 INFO Epoch:44 val_res:0.588200 +2025-04-20 00:59:07,130 INFO Epoch:45 train_loss:0.59572 +2025-04-20 00:59:20,324 INFO Epoch:45 val_res:0.588400 +2025-04-20 00:59:51,773 INFO Epoch:46 train_loss:0.59158 +2025-04-20 01:00:04,774 INFO Epoch:46 val_res:0.587000 +2025-04-20 01:00:36,927 INFO Epoch:47 train_loss:0.54596 +2025-04-20 01:00:50,129 INFO Epoch:47 val_res:0.584400 +2025-04-20 01:01:23,781 INFO Epoch:48 train_loss:0.55959 +2025-04-20 01:01:38,051 INFO Epoch:48 val_res:0.587000 +2025-04-20 01:02:10,107 INFO Epoch:49 train_loss:0.58223 +2025-04-20 01:02:22,968 INFO Epoch:49 val_res:0.584000 +2025-04-20 01:02:56,487 INFO Epoch:50 train_loss:0.58054 +2025-04-20 01:03:09,349 INFO Epoch:50 val_res:0.583200 +2025-04-20 01:03:44,298 INFO Epoch:51 train_loss:0.58144 +2025-04-20 01:03:57,002 INFO Epoch:51 val_res:0.582400 +2025-04-20 01:04:31,130 INFO Epoch:52 train_loss:0.58794 +2025-04-20 01:04:44,191 INFO Epoch:52 val_res:0.582200 +2025-04-20 01:05:18,375 INFO Epoch:53 train_loss:0.56940 +2025-04-20 01:05:31,784 INFO Epoch:53 val_res:0.578400 +2025-04-20 01:06:05,687 INFO Epoch:54 train_loss:0.54924 +2025-04-20 01:06:18,631 INFO Epoch:54 val_res:0.578400 +2025-04-20 01:06:52,304 INFO Epoch:55 train_loss:0.53018 +2025-04-20 01:07:05,564 INFO Epoch:55 val_res:0.580200 +2025-04-20 01:07:38,451 INFO Epoch:56 train_loss:0.54640 +2025-04-20 01:07:51,393 INFO Epoch:56 val_res:0.579600 +2025-04-20 01:08:23,875 INFO Epoch:57 train_loss:0.57854 +2025-04-20 01:08:37,274 INFO Epoch:57 val_res:0.579000 +2025-04-20 01:09:10,810 INFO Epoch:58 train_loss:0.58426 +2025-04-20 01:09:24,888 INFO Epoch:58 val_res:0.575400 +2025-04-20 01:09:58,778 INFO Epoch:59 train_loss:0.57646 +2025-04-20 01:10:12,095 INFO Epoch:59 val_res:0.574200 +2025-04-20 01:10:44,375 INFO Epoch:60 train_loss:0.55435 +2025-04-20 01:10:57,737 INFO Epoch:60 val_res:0.571800 +2025-04-20 01:11:30,118 INFO Epoch:61 train_loss:0.54383 +2025-04-20 01:11:43,338 INFO Epoch:61 val_res:0.573000 +2025-04-20 01:12:15,640 INFO Epoch:62 train_loss:0.54090 +2025-04-20 01:12:28,875 INFO Epoch:62 val_res:0.568800 +2025-04-20 01:13:00,913 INFO Epoch:63 train_loss:0.56436 +2025-04-20 01:13:14,185 INFO Epoch:63 val_res:0.563000 +2025-04-20 01:13:47,712 INFO Epoch:64 train_loss:0.61528 +2025-04-20 01:14:00,703 INFO Epoch:64 val_res:0.570600 +2025-04-20 01:14:33,499 INFO Epoch:65 train_loss:0.54624 +2025-04-20 01:14:47,676 INFO Epoch:65 val_res:0.567800 +2025-04-20 01:15:19,591 INFO Epoch:66 train_loss:0.55598 +2025-04-20 01:15:32,470 INFO Epoch:66 val_res:0.567400 +2025-04-20 01:16:05,538 INFO Epoch:67 train_loss:0.53090 +2025-04-20 01:16:18,320 INFO Epoch:67 val_res:0.562000 +2025-04-20 01:16:52,304 INFO Epoch:68 train_loss:0.56748 +2025-04-20 01:17:05,809 INFO Epoch:68 val_res:0.553200 +2025-04-20 01:17:39,969 INFO Epoch:69 train_loss:0.62481 +2025-04-20 01:17:52,970 INFO Epoch:69 val_res:0.554800 +2025-04-20 01:18:25,859 INFO Epoch:70 train_loss:0.61929 +2025-04-20 01:18:38,915 INFO Epoch:70 val_res:0.557600 +2025-04-20 01:19:11,637 INFO Epoch:71 train_loss:0.52828 +2025-04-20 01:19:24,488 INFO Epoch:71 val_res:0.554000 +2025-04-20 01:19:58,112 INFO Epoch:72 train_loss:0.51717 +2025-04-20 01:20:10,804 INFO Epoch:72 val_res:0.558400 +2025-04-20 01:20:45,297 INFO Epoch:73 train_loss:0.50811 +2025-04-20 01:20:58,262 INFO Epoch:73 val_res:0.553600 +2025-04-20 01:21:31,680 INFO Epoch:74 train_loss:0.52571 +2025-04-20 01:21:44,487 INFO Epoch:74 val_res:0.553400 +2025-04-20 01:22:18,698 INFO Epoch:75 train_loss:0.56062 +2025-04-20 01:22:32,109 INFO Epoch:75 val_res:0.555600 +2025-04-20 01:23:04,785 INFO Epoch:76 train_loss:0.56079 +2025-04-20 01:23:17,680 INFO Epoch:76 val_res:0.557000 +2025-04-20 01:23:51,182 INFO Epoch:77 train_loss:0.55381 +2025-04-20 01:24:03,916 INFO Epoch:77 val_res:0.553000 +2025-04-20 01:24:37,687 INFO Epoch:78 train_loss:0.64661 +2025-04-20 01:24:50,596 INFO Epoch:78 val_res:0.554800 +2025-04-20 01:25:25,111 INFO Epoch:79 train_loss:0.54248 +2025-04-20 01:25:37,987 INFO Epoch:79 val_res:0.547000 +2025-04-20 01:26:13,143 INFO Epoch:80 train_loss:0.51787 +2025-04-20 01:26:26,007 INFO Epoch:80 val_res:0.546400 +2025-04-20 01:27:00,286 INFO Epoch:81 train_loss:0.51489 +2025-04-20 01:27:13,190 INFO Epoch:81 val_res:0.547200 +2025-04-20 01:27:46,946 INFO Epoch:82 train_loss:0.54751 +2025-04-20 01:27:59,916 INFO Epoch:82 val_res:0.543000 +2025-04-20 01:28:33,649 INFO Epoch:83 train_loss:0.54971 +2025-04-20 01:28:46,443 INFO Epoch:83 val_res:0.546400 +2025-04-20 01:29:19,997 INFO Epoch:84 train_loss:0.53410 +2025-04-20 01:29:33,603 INFO Epoch:84 val_res:0.542400 +2025-04-20 01:30:05,888 INFO Epoch:85 train_loss:0.50606 +2025-04-20 01:30:18,961 INFO Epoch:85 val_res:0.542200 +2025-04-20 01:30:52,680 INFO Epoch:86 train_loss:0.51974 +2025-04-20 01:31:05,704 INFO Epoch:86 val_res:0.545800 +2025-04-20 01:31:39,595 INFO Epoch:87 train_loss:0.63068 +2025-04-20 01:31:52,726 INFO Epoch:87 val_res:0.546200 +2025-04-20 01:32:26,566 INFO Epoch:88 train_loss:0.64431 +2025-04-20 01:32:39,748 INFO Epoch:88 val_res:0.548800 +2025-04-20 01:33:13,950 INFO Epoch:89 train_loss:0.64434 +2025-04-20 01:33:27,287 INFO Epoch:89 val_res:0.537800 +2025-04-20 01:33:59,299 INFO Epoch:90 train_loss:0.57008 +2025-04-20 01:34:12,230 INFO Epoch:90 val_res:0.532400 +2025-04-20 01:34:46,083 INFO Epoch:91 train_loss:0.51657 +2025-04-20 01:34:59,301 INFO Epoch:91 val_res:0.537800 +2025-04-20 01:35:32,477 INFO Epoch:92 train_loss:0.49666 +2025-04-20 01:35:45,793 INFO Epoch:92 val_res:0.534400 +2025-04-20 01:36:20,313 INFO Epoch:93 train_loss:0.50693 +2025-04-20 01:36:33,365 INFO Epoch:93 val_res:0.537000 +2025-04-20 01:37:05,888 INFO Epoch:94 train_loss:0.49893 +2025-04-20 01:37:19,164 INFO Epoch:94 val_res:0.538400 +2025-04-20 01:37:51,642 INFO Epoch:95 train_loss:0.51115 +2025-04-20 01:38:04,780 INFO Epoch:95 val_res:0.536600 +2025-04-20 01:38:37,983 INFO Epoch:96 train_loss:0.54370 +2025-04-20 01:38:51,818 INFO Epoch:96 val_res:0.529800 +2025-04-20 01:39:24,329 INFO Epoch:97 train_loss:0.60778 +2025-04-20 01:39:37,434 INFO Epoch:97 val_res:0.533000 +2025-04-20 01:40:10,424 INFO Epoch:98 train_loss:0.57976 +2025-04-20 01:40:23,355 INFO Epoch:98 val_res:0.533600 +2025-04-20 01:40:57,035 INFO Epoch:99 train_loss:0.61945 +2025-04-20 01:41:10,150 INFO Epoch:99 val_res:0.531400 +2025-04-20 01:41:10,350 INFO ===================================== +2025-04-20 01:41:10,350 INFO Start testing... +2025-04-20 01:41:10,351 INFO ===================================== +2025-04-20 01:41:24,698 INFO Incremental step 9 Testing res: 0.589400 +2025-04-20 01:41:24,704 INFO forgetting: 0.099333 +2025-04-20 01:41:24,706 INFO Average Accuracy: 0.699444 +2025-04-20 01:41:24,706 INFO Average Forgetting: 0.082252 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..453a9ca92700c8987923908236b5016b9e19cab3 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..dc0d713fc3caea60e896d66348517b6549bb5f4a Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..49aa54dc0c648a4683d2fcd355bda3cf93c3b9fa Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..8b7fe0b186d09cc756c0f2b1acde7bbe19190944 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..ec5a251c42898bbd7948159b3db2a4ab7eb968b8 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_5.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..dd8044d0ecdc596d775cf4d8683130bf8ef82442 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_5.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_6.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..410ef336e252a5f99b038a6794589456b91278c5 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_6.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_7.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..daa4e2a09ba90709424eae9dbeddddd595eb00fb Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_7.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_8.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..cc243720d0afe24fb947864a0593eb948d094c03 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_8.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_9.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..cadf6d3c39a0cea441d34a1feba47b0c341a676c Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_9.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..f9c583840893f40359e14aba2ebf13df1d36bff7 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..cec544730e607f8f08ee27e440e81c0cce4a46ff Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..40be2b7e170f5368f1f3d20cdef553a662184da3 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..06b1c86a2ca9c2100907f45c7340dd5d7acdd430 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..d8c05dc4c79b1377a650ed79d7e451a7013bafaf Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_5.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..eb598492ed660902cb464419e4465ce1717c139e Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_5.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_6.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..083608c606af90c38827b608f345fcba6fa570c6 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_6.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_7.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..27da01bd370c421cd5d49b24cbe895154bab63d5 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_7.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_8.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..6b2d6e6e3272b2bd46d9cb0a40bd74d48f8b7add Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_8.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_9.png b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..98430755501a648d40c3e8bdcc9de0f546913667 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_9.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..6dab46ccf3c7de92f60fc2bfa62b6b9a4963a460 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:668a1eb5a25503db5db6467b67c7bae43f3812d1d2398d6c022f1b754f015824 +size 114142993 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ca270bebe6eac2cb1c09b421127106dd97d506cc --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea201b00119857694494266a3311cf3edf21c2fcd0819eeda1eaca06bd52d5c5 +size 114235409 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9e3505664f6e2cc2bfbfe18d91f3598e56345f21 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f89db6ab26cefadc04b3a855bc6db044e5c2571fd1804891ae3204de30c9a11 +size 114327569 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..27f0a086491e545a909ad52c704e89f516b81265 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7441fbbc11630a7eac90160b2c2e72e03fecced28a0f4d97361134ac4c606406 +size 114419921 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..bac2c397bf8041a0dd2b8d0bf883fe80c7c14898 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:593d728fd19c9f4a989ab587d2aacdd909e7ff1cda23b851cffc8b2762b63277 +size 114512273 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_5_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_5_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8b7105ee8986d7438c170913895229e4f9d79cd4 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_5_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea57656ae6721cf4c1e6c91f764aeade7c26077c95466f8a4bcac79f8ac1cc50 +size 114604433 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_6_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_6_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..dc5e9d4e59949dfd3717ebe33473e8058bfa47fa --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_6_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac67d9dbab93f3f07dc4bdd63c4056fdb4317f200ae0ed2bb5871e3ca3d039b +size 114696785 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_7_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_7_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..1125e6766629d3a715305af27bb73b6cdf2fc767 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_7_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8d72fd5de8b74d40e23b13e86a3bf4555a442a7523542ec239ad2c191a4163 +size 114789137 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_8_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_8_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9a25332dc97949f0d5ea5d5b1369fddf939a08c1 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_8_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f38882b23c329e4a68e1ca1d4a6bf843fad60fb8032280c913ae330c2a64a113 +size 114881297 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_9_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_9_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c5ad2bc0bf843d540dfd4b73c39a41c0876ef8ab --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_9_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:558fadff8c2579d1f80aaedaac02b8de4fce2d1c8a63a01c4909b0c20cb69d42 +size 114973649 diff --git a/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/train.log b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..28109ef04c43870883954018b8e00521f184b70f --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/train.log @@ -0,0 +1,2348 @@ +2025-04-19 15:16:07,637 INFO Training start time: 2025-04-19 15:16:07.637070 +2025-04-19 15:16:09,141 INFO Incremental step: 0 +2025-04-19 15:16:36,360 INFO Epoch:0 train_loss:1.57833 +2025-04-19 15:16:40,135 INFO Epoch:0 val_res:0.566000 +2025-04-19 15:16:40,135 INFO Saving best model at Epoch 0 +2025-04-19 15:16:58,497 INFO Epoch:1 train_loss:0.67806 +2025-04-19 15:17:01,284 INFO Epoch:1 val_res:0.738000 +2025-04-19 15:17:01,284 INFO Saving best model at Epoch 1 +2025-04-19 15:17:17,299 INFO Epoch:2 train_loss:0.42002 +2025-04-19 15:17:20,150 INFO Epoch:2 val_res:0.782000 +2025-04-19 15:17:20,150 INFO Saving best model at Epoch 2 +2025-04-19 15:17:37,201 INFO Epoch:3 train_loss:0.31691 +2025-04-19 15:17:40,086 INFO Epoch:3 val_res:0.770000 +2025-04-19 15:17:55,154 INFO Epoch:4 train_loss:0.26087 +2025-04-19 15:17:57,943 INFO Epoch:4 val_res:0.804000 +2025-04-19 15:17:57,943 INFO Saving best model at Epoch 4 +2025-04-19 15:18:15,326 INFO Epoch:5 train_loss:0.21645 +2025-04-19 15:18:18,265 INFO Epoch:5 val_res:0.812000 +2025-04-19 15:18:18,266 INFO Saving best model at Epoch 5 +2025-04-19 15:18:36,518 INFO Epoch:6 train_loss:0.18516 +2025-04-19 15:18:39,345 INFO Epoch:6 val_res:0.812000 +2025-04-19 15:18:54,870 INFO Epoch:7 train_loss:0.16608 +2025-04-19 15:18:57,719 INFO Epoch:7 val_res:0.816000 +2025-04-19 15:18:57,720 INFO Saving best model at Epoch 7 +2025-04-19 15:19:17,202 INFO Epoch:8 train_loss:0.14958 +2025-04-19 15:19:20,100 INFO Epoch:8 val_res:0.848000 +2025-04-19 15:19:20,100 INFO Saving best model at Epoch 8 +2025-04-19 15:19:37,757 INFO Epoch:9 train_loss:0.13568 +2025-04-19 15:19:40,729 INFO Epoch:9 val_res:0.858000 +2025-04-19 15:19:40,730 INFO Saving best model at Epoch 9 +2025-04-19 15:19:57,987 INFO Epoch:10 train_loss:0.11070 +2025-04-19 15:20:01,017 INFO Epoch:10 val_res:0.852000 +2025-04-19 15:20:14,974 INFO Epoch:11 train_loss:0.09472 +2025-04-19 15:20:18,143 INFO Epoch:11 val_res:0.860000 +2025-04-19 15:20:18,144 INFO Saving best model at Epoch 11 +2025-04-19 15:20:33,551 INFO Epoch:12 train_loss:0.08878 +2025-04-19 15:20:36,283 INFO Epoch:12 val_res:0.872000 +2025-04-19 15:20:36,284 INFO Saving best model at Epoch 12 +2025-04-19 15:20:52,585 INFO Epoch:13 train_loss:0.07628 +2025-04-19 15:20:55,536 INFO Epoch:13 val_res:0.854000 +2025-04-19 15:21:10,890 INFO Epoch:14 train_loss:0.07572 +2025-04-19 15:21:13,848 INFO Epoch:14 val_res:0.874000 +2025-04-19 15:21:13,849 INFO Saving best model at Epoch 14 +2025-04-19 15:21:31,306 INFO Epoch:15 train_loss:0.06578 +2025-04-19 15:21:34,239 INFO Epoch:15 val_res:0.860000 +2025-04-19 15:21:50,216 INFO Epoch:16 train_loss:0.05786 +2025-04-19 15:21:53,257 INFO Epoch:16 val_res:0.886000 +2025-04-19 15:21:53,257 INFO Saving best model at Epoch 16 +2025-04-19 15:22:11,171 INFO Epoch:17 train_loss:0.05267 +2025-04-19 15:22:14,003 INFO Epoch:17 val_res:0.886000 +2025-04-19 15:22:30,294 INFO Epoch:18 train_loss:0.04460 +2025-04-19 15:22:33,329 INFO Epoch:18 val_res:0.866000 +2025-04-19 15:22:48,773 INFO Epoch:19 train_loss:0.04436 +2025-04-19 15:22:51,765 INFO Epoch:19 val_res:0.882000 +2025-04-19 15:23:07,094 INFO Epoch:20 train_loss:2.45432 +2025-04-19 15:23:10,184 INFO Epoch:20 val_res:0.856000 +2025-04-19 15:23:25,944 INFO Epoch:21 train_loss:1.20575 +2025-04-19 15:23:28,762 INFO Epoch:21 val_res:0.890000 +2025-04-19 15:23:28,763 INFO Saving best model at Epoch 21 +2025-04-19 15:23:46,295 INFO Epoch:22 train_loss:0.97727 +2025-04-19 15:23:49,331 INFO Epoch:22 val_res:0.882000 +2025-04-19 15:24:04,401 INFO Epoch:23 train_loss:0.82508 +2025-04-19 15:24:07,370 INFO Epoch:23 val_res:0.836000 +2025-04-19 15:24:23,966 INFO Epoch:24 train_loss:0.73920 +2025-04-19 15:24:27,041 INFO Epoch:24 val_res:0.874000 +2025-04-19 15:24:41,075 INFO Epoch:25 train_loss:0.67033 +2025-04-19 15:24:43,903 INFO Epoch:25 val_res:0.872000 +2025-04-19 15:24:58,121 INFO Epoch:26 train_loss:0.65892 +2025-04-19 15:25:00,885 INFO Epoch:26 val_res:0.906000 +2025-04-19 15:25:00,886 INFO Saving best model at Epoch 26 +2025-04-19 15:25:16,900 INFO Epoch:27 train_loss:0.58303 +2025-04-19 15:25:19,676 INFO Epoch:27 val_res:0.904000 +2025-04-19 15:25:34,289 INFO Epoch:28 train_loss:0.56562 +2025-04-19 15:25:37,148 INFO Epoch:28 val_res:0.900000 +2025-04-19 15:25:51,131 INFO Epoch:29 train_loss:0.52882 +2025-04-19 15:25:53,966 INFO Epoch:29 val_res:0.896000 +2025-04-19 15:26:08,315 INFO Epoch:30 train_loss:0.49758 +2025-04-19 15:26:11,107 INFO Epoch:30 val_res:0.880000 +2025-04-19 15:26:25,525 INFO Epoch:31 train_loss:0.54125 +2025-04-19 15:26:28,327 INFO Epoch:31 val_res:0.898000 +2025-04-19 15:26:42,211 INFO Epoch:32 train_loss:0.51572 +2025-04-19 15:26:44,964 INFO Epoch:32 val_res:0.856000 +2025-04-19 15:26:59,344 INFO Epoch:33 train_loss:0.46748 +2025-04-19 15:27:02,158 INFO Epoch:33 val_res:0.902000 +2025-04-19 15:27:16,774 INFO Epoch:34 train_loss:0.47214 +2025-04-19 15:27:19,618 INFO Epoch:34 val_res:0.900000 +2025-04-19 15:27:33,937 INFO Epoch:35 train_loss:0.45325 +2025-04-19 15:27:36,661 INFO Epoch:35 val_res:0.894000 +2025-04-19 15:27:51,216 INFO Epoch:36 train_loss:0.43364 +2025-04-19 15:27:54,046 INFO Epoch:36 val_res:0.904000 +2025-04-19 15:28:08,171 INFO Epoch:37 train_loss:0.47193 +2025-04-19 15:28:10,958 INFO Epoch:37 val_res:0.902000 +2025-04-19 15:28:25,201 INFO Epoch:38 train_loss:0.46028 +2025-04-19 15:28:27,988 INFO Epoch:38 val_res:0.902000 +2025-04-19 15:28:42,124 INFO Epoch:39 train_loss:0.42580 +2025-04-19 15:28:44,804 INFO Epoch:39 val_res:0.894000 +2025-04-19 15:28:59,073 INFO Epoch:40 train_loss:0.41441 +2025-04-19 15:29:01,900 INFO Epoch:40 val_res:0.906000 +2025-04-19 15:29:15,931 INFO Epoch:41 train_loss:0.42670 +2025-04-19 15:29:18,603 INFO Epoch:41 val_res:0.890000 +2025-04-19 15:29:32,843 INFO Epoch:42 train_loss:0.39144 +2025-04-19 15:29:35,684 INFO Epoch:42 val_res:0.898000 +2025-04-19 15:29:49,520 INFO Epoch:43 train_loss:0.39952 +2025-04-19 15:29:52,327 INFO Epoch:43 val_res:0.892000 +2025-04-19 15:30:07,106 INFO Epoch:44 train_loss:0.41290 +2025-04-19 15:30:09,896 INFO Epoch:44 val_res:0.890000 +2025-04-19 15:30:25,488 INFO Epoch:45 train_loss:0.38668 +2025-04-19 15:30:28,310 INFO Epoch:45 val_res:0.906000 +2025-04-19 15:30:42,668 INFO Epoch:46 train_loss:0.39117 +2025-04-19 15:30:45,442 INFO Epoch:46 val_res:0.892000 +2025-04-19 15:30:59,296 INFO Epoch:47 train_loss:0.39171 +2025-04-19 15:31:02,134 INFO Epoch:47 val_res:0.894000 +2025-04-19 15:31:15,746 INFO Epoch:48 train_loss:0.36582 +2025-04-19 15:31:18,354 INFO Epoch:48 val_res:0.896000 +2025-04-19 15:31:32,611 INFO Epoch:49 train_loss:0.37624 +2025-04-19 15:31:35,444 INFO Epoch:49 val_res:0.890000 +2025-04-19 15:31:49,384 INFO Epoch:50 train_loss:0.36311 +2025-04-19 15:31:52,151 INFO Epoch:50 val_res:0.902000 +2025-04-19 15:32:05,963 INFO Epoch:51 train_loss:0.36041 +2025-04-19 15:32:08,913 INFO Epoch:51 val_res:0.888000 +2025-04-19 15:32:23,692 INFO Epoch:52 train_loss:0.37580 +2025-04-19 15:32:26,478 INFO Epoch:52 val_res:0.898000 +2025-04-19 15:32:40,684 INFO Epoch:53 train_loss:0.40580 +2025-04-19 15:32:43,389 INFO Epoch:53 val_res:0.902000 +2025-04-19 15:32:58,047 INFO Epoch:54 train_loss:0.35300 +2025-04-19 15:33:00,934 INFO Epoch:54 val_res:0.902000 +2025-04-19 15:33:14,962 INFO Epoch:55 train_loss:0.33480 +2025-04-19 15:33:17,788 INFO Epoch:55 val_res:0.892000 +2025-04-19 15:33:31,854 INFO Epoch:56 train_loss:0.34044 +2025-04-19 15:33:34,616 INFO Epoch:56 val_res:0.898000 +2025-04-19 15:33:48,791 INFO Epoch:57 train_loss:0.34061 +2025-04-19 15:33:51,590 INFO Epoch:57 val_res:0.894000 +2025-04-19 15:34:05,321 INFO Epoch:58 train_loss:0.35731 +2025-04-19 15:34:08,058 INFO Epoch:58 val_res:0.894000 +2025-04-19 15:34:22,385 INFO Epoch:59 train_loss:0.35962 +2025-04-19 15:34:25,189 INFO Epoch:59 val_res:0.874000 +2025-04-19 15:34:39,066 INFO Epoch:60 train_loss:0.33184 +2025-04-19 15:34:41,864 INFO Epoch:60 val_res:0.884000 +2025-04-19 15:34:56,218 INFO Epoch:61 train_loss:0.31575 +2025-04-19 15:34:59,015 INFO Epoch:61 val_res:0.894000 +2025-04-19 15:35:13,574 INFO Epoch:62 train_loss:0.35796 +2025-04-19 15:35:16,417 INFO Epoch:62 val_res:0.900000 +2025-04-19 15:35:30,844 INFO Epoch:63 train_loss:0.34927 +2025-04-19 15:35:33,744 INFO Epoch:63 val_res:0.892000 +2025-04-19 15:35:47,931 INFO Epoch:64 train_loss:0.32556 +2025-04-19 15:35:50,785 INFO Epoch:64 val_res:0.876000 +2025-04-19 15:36:05,177 INFO Epoch:65 train_loss:0.32563 +2025-04-19 15:36:08,039 INFO Epoch:65 val_res:0.880000 +2025-04-19 15:36:22,123 INFO Epoch:66 train_loss:0.30695 +2025-04-19 15:36:24,944 INFO Epoch:66 val_res:0.898000 +2025-04-19 15:36:39,420 INFO Epoch:67 train_loss:0.30018 +2025-04-19 15:36:42,192 INFO Epoch:67 val_res:0.892000 +2025-04-19 15:36:56,174 INFO Epoch:68 train_loss:0.29880 +2025-04-19 15:36:58,873 INFO Epoch:68 val_res:0.890000 +2025-04-19 15:37:13,488 INFO Epoch:69 train_loss:0.29987 +2025-04-19 15:37:16,279 INFO Epoch:69 val_res:0.896000 +2025-04-19 15:37:30,174 INFO Epoch:70 train_loss:0.31052 +2025-04-19 15:37:33,017 INFO Epoch:70 val_res:0.898000 +2025-04-19 15:37:47,026 INFO Epoch:71 train_loss:0.00636 +2025-04-19 15:37:49,843 INFO Epoch:71 val_res:0.890000 +2025-04-19 15:38:03,903 INFO Epoch:72 train_loss:0.00336 +2025-04-19 15:38:06,709 INFO Epoch:72 val_res:0.900000 +2025-04-19 15:38:21,113 INFO Epoch:73 train_loss:0.00310 +2025-04-19 15:38:23,909 INFO Epoch:73 val_res:0.896000 +2025-04-19 15:38:38,646 INFO Epoch:74 train_loss:0.00348 +2025-04-19 15:38:41,467 INFO Epoch:74 val_res:0.898000 +2025-04-19 15:38:55,669 INFO Epoch:75 train_loss:0.00342 +2025-04-19 15:38:58,545 INFO Epoch:75 val_res:0.896000 +2025-04-19 15:39:12,914 INFO Epoch:76 train_loss:0.00410 +2025-04-19 15:39:15,744 INFO Epoch:76 val_res:0.898000 +2025-04-19 15:39:30,045 INFO Epoch:77 train_loss:0.00402 +2025-04-19 15:39:32,858 INFO Epoch:77 val_res:0.894000 +2025-04-19 15:39:47,278 INFO Epoch:78 train_loss:0.00410 +2025-04-19 15:39:50,141 INFO Epoch:78 val_res:0.892000 +2025-04-19 15:40:04,148 INFO Epoch:79 train_loss:0.00417 +2025-04-19 15:40:06,970 INFO Epoch:79 val_res:0.894000 +2025-04-19 15:40:21,072 INFO Epoch:80 train_loss:0.00424 +2025-04-19 15:40:23,842 INFO Epoch:80 val_res:0.892000 +2025-04-19 15:40:37,989 INFO Epoch:81 train_loss:0.00479 +2025-04-19 15:40:40,794 INFO Epoch:81 val_res:0.890000 +2025-04-19 15:40:54,660 INFO Epoch:82 train_loss:0.00468 +2025-04-19 15:40:57,609 INFO Epoch:82 val_res:0.898000 +2025-04-19 15:41:11,895 INFO Epoch:83 train_loss:0.00474 +2025-04-19 15:41:14,739 INFO Epoch:83 val_res:0.890000 +2025-04-19 15:41:28,817 INFO Epoch:84 train_loss:0.00516 +2025-04-19 15:41:31,663 INFO Epoch:84 val_res:0.896000 +2025-04-19 15:41:46,023 INFO Epoch:85 train_loss:0.00536 +2025-04-19 15:41:48,775 INFO Epoch:85 val_res:0.890000 +2025-04-19 15:42:02,885 INFO Epoch:86 train_loss:0.00551 +2025-04-19 15:42:05,653 INFO Epoch:86 val_res:0.888000 +2025-04-19 15:42:19,695 INFO Epoch:87 train_loss:0.00527 +2025-04-19 15:42:22,512 INFO Epoch:87 val_res:0.888000 +2025-04-19 15:42:36,423 INFO Epoch:88 train_loss:0.00518 +2025-04-19 15:42:39,184 INFO Epoch:88 val_res:0.892000 +2025-04-19 15:42:53,638 INFO Epoch:89 train_loss:0.00518 +2025-04-19 15:42:56,424 INFO Epoch:89 val_res:0.894000 +2025-04-19 15:43:10,682 INFO Epoch:90 train_loss:0.00607 +2025-04-19 15:43:13,626 INFO Epoch:90 val_res:0.888000 +2025-04-19 15:43:27,821 INFO Epoch:91 train_loss:0.00563 +2025-04-19 15:43:30,588 INFO Epoch:91 val_res:0.890000 +2025-04-19 15:43:44,383 INFO Epoch:92 train_loss:0.00515 +2025-04-19 15:43:47,167 INFO Epoch:92 val_res:0.888000 +2025-04-19 15:44:01,448 INFO Epoch:93 train_loss:0.00475 +2025-04-19 15:44:04,336 INFO Epoch:93 val_res:0.886000 +2025-04-19 15:44:18,259 INFO Epoch:94 train_loss:0.00578 +2025-04-19 15:44:21,050 INFO Epoch:94 val_res:0.886000 +2025-04-19 15:44:35,344 INFO Epoch:95 train_loss:0.00550 +2025-04-19 15:44:38,103 INFO Epoch:95 val_res:0.890000 +2025-04-19 15:44:52,196 INFO Epoch:96 train_loss:0.00508 +2025-04-19 15:44:55,095 INFO Epoch:96 val_res:0.884000 +2025-04-19 15:45:09,799 INFO Epoch:97 train_loss:0.00475 +2025-04-19 15:45:12,824 INFO Epoch:97 val_res:0.884000 +2025-04-19 15:45:26,874 INFO Epoch:98 train_loss:0.00462 +2025-04-19 15:45:29,955 INFO Epoch:98 val_res:0.906000 +2025-04-19 15:45:45,922 INFO Epoch:99 train_loss:0.00584 +2025-04-19 15:45:48,933 INFO Epoch:99 val_res:0.884000 +2025-04-19 15:45:49,282 INFO ===================================== +2025-04-19 15:45:49,283 INFO Start testing... +2025-04-19 15:45:49,283 INFO ===================================== +2025-04-19 15:45:52,460 INFO Incremental step 0 Testing res: 0.908000 +2025-04-19 15:45:52,463 INFO Incremental step: 1 +2025-04-19 15:46:41,726 INFO Epoch:0 train_loss:1.95588 +2025-04-19 15:46:45,974 INFO Epoch:0 val_res:0.502000 +2025-04-19 15:46:45,975 INFO Saving best model at Epoch 0 +2025-04-19 15:47:17,146 INFO Epoch:1 train_loss:1.29074 +2025-04-19 15:47:21,598 INFO Epoch:1 val_res:0.566000 +2025-04-19 15:47:21,598 INFO Saving best model at Epoch 1 +2025-04-19 15:47:50,132 INFO Epoch:2 train_loss:1.14271 +2025-04-19 15:47:54,407 INFO Epoch:2 val_res:0.597000 +2025-04-19 15:47:54,408 INFO Saving best model at Epoch 2 +2025-04-19 15:48:22,677 INFO Epoch:3 train_loss:1.08143 +2025-04-19 15:48:26,847 INFO Epoch:3 val_res:0.617000 +2025-04-19 15:48:26,848 INFO Saving best model at Epoch 3 +2025-04-19 15:48:55,161 INFO Epoch:4 train_loss:1.03028 +2025-04-19 15:48:59,421 INFO Epoch:4 val_res:0.630000 +2025-04-19 15:48:59,421 INFO Saving best model at Epoch 4 +2025-04-19 15:49:28,466 INFO Epoch:5 train_loss:0.98547 +2025-04-19 15:49:32,729 INFO Epoch:5 val_res:0.652000 +2025-04-19 15:49:32,729 INFO Saving best model at Epoch 5 +2025-04-19 15:50:01,423 INFO Epoch:6 train_loss:0.96221 +2025-04-19 15:50:05,652 INFO Epoch:6 val_res:0.668000 +2025-04-19 15:50:05,652 INFO Saving best model at Epoch 6 +2025-04-19 15:50:34,158 INFO Epoch:7 train_loss:0.93112 +2025-04-19 15:50:38,479 INFO Epoch:7 val_res:0.673000 +2025-04-19 15:50:38,479 INFO Saving best model at Epoch 7 +2025-04-19 15:51:07,765 INFO Epoch:8 train_loss:0.90345 +2025-04-19 15:51:11,971 INFO Epoch:8 val_res:0.685000 +2025-04-19 15:51:11,971 INFO Saving best model at Epoch 8 +2025-04-19 15:51:39,944 INFO Epoch:9 train_loss:0.88575 +2025-04-19 15:51:44,052 INFO Epoch:9 val_res:0.699000 +2025-04-19 15:51:44,053 INFO Saving best model at Epoch 9 +2025-04-19 15:52:12,818 INFO Epoch:10 train_loss:0.87131 +2025-04-19 15:52:17,082 INFO Epoch:10 val_res:0.710000 +2025-04-19 15:52:17,082 INFO Saving best model at Epoch 10 +2025-04-19 15:52:46,206 INFO Epoch:11 train_loss:0.83470 +2025-04-19 15:52:50,552 INFO Epoch:11 val_res:0.721000 +2025-04-19 15:52:50,553 INFO Saving best model at Epoch 11 +2025-04-19 15:53:18,828 INFO Epoch:12 train_loss:0.81761 +2025-04-19 15:53:23,035 INFO Epoch:12 val_res:0.742000 +2025-04-19 15:53:23,035 INFO Saving best model at Epoch 12 +2025-04-19 15:53:51,158 INFO Epoch:13 train_loss:0.80798 +2025-04-19 15:53:55,308 INFO Epoch:13 val_res:0.733000 +2025-04-19 15:54:22,187 INFO Epoch:14 train_loss:0.80118 +2025-04-19 15:54:26,356 INFO Epoch:14 val_res:0.742000 +2025-04-19 15:54:52,911 INFO Epoch:15 train_loss:0.78460 +2025-04-19 15:54:57,160 INFO Epoch:15 val_res:0.753000 +2025-04-19 15:54:57,160 INFO Saving best model at Epoch 15 +2025-04-19 15:55:26,296 INFO Epoch:16 train_loss:0.76338 +2025-04-19 15:55:30,580 INFO Epoch:16 val_res:0.760000 +2025-04-19 15:55:30,580 INFO Saving best model at Epoch 16 +2025-04-19 15:55:59,093 INFO Epoch:17 train_loss:0.74596 +2025-04-19 15:56:03,393 INFO Epoch:17 val_res:0.767000 +2025-04-19 15:56:03,394 INFO Saving best model at Epoch 17 +2025-04-19 15:56:32,419 INFO Epoch:18 train_loss:0.73535 +2025-04-19 15:56:36,519 INFO Epoch:18 val_res:0.765000 +2025-04-19 15:57:02,970 INFO Epoch:19 train_loss:0.73341 +2025-04-19 15:57:07,143 INFO Epoch:19 val_res:0.781000 +2025-04-19 15:57:07,143 INFO Saving best model at Epoch 19 +2025-04-19 15:57:36,437 INFO Epoch:20 train_loss:3.10496 +2025-04-19 15:57:40,686 INFO Epoch:20 val_res:0.785000 +2025-04-19 15:57:40,686 INFO Saving best model at Epoch 20 +2025-04-19 15:58:09,631 INFO Epoch:21 train_loss:1.97500 +2025-04-19 15:58:13,807 INFO Epoch:21 val_res:0.817000 +2025-04-19 15:58:13,807 INFO Saving best model at Epoch 21 +2025-04-19 15:58:42,791 INFO Epoch:22 train_loss:1.67068 +2025-04-19 15:58:46,983 INFO Epoch:22 val_res:0.812000 +2025-04-19 15:59:15,319 INFO Epoch:23 train_loss:1.55402 +2025-04-19 15:59:19,661 INFO Epoch:23 val_res:0.820000 +2025-04-19 15:59:19,661 INFO Saving best model at Epoch 23 +2025-04-19 15:59:49,047 INFO Epoch:24 train_loss:1.46470 +2025-04-19 15:59:53,312 INFO Epoch:24 val_res:0.822000 +2025-04-19 15:59:53,313 INFO Saving best model at Epoch 24 +2025-04-19 16:00:23,552 INFO Epoch:25 train_loss:1.42332 +2025-04-19 16:00:27,783 INFO Epoch:25 val_res:0.819000 +2025-04-19 16:00:55,545 INFO Epoch:26 train_loss:1.37874 +2025-04-19 16:00:59,882 INFO Epoch:26 val_res:0.815000 +2025-04-19 16:01:27,421 INFO Epoch:27 train_loss:1.34966 +2025-04-19 16:01:31,636 INFO Epoch:27 val_res:0.822000 +2025-04-19 16:01:59,216 INFO Epoch:28 train_loss:1.32216 +2025-04-19 16:02:03,317 INFO Epoch:28 val_res:0.832000 +2025-04-19 16:02:03,317 INFO Saving best model at Epoch 28 +2025-04-19 16:02:32,468 INFO Epoch:29 train_loss:1.28889 +2025-04-19 16:02:36,787 INFO Epoch:29 val_res:0.828000 +2025-04-19 16:03:05,015 INFO Epoch:30 train_loss:1.27288 +2025-04-19 16:03:09,291 INFO Epoch:30 val_res:0.828000 +2025-04-19 16:03:36,712 INFO Epoch:31 train_loss:1.25618 +2025-04-19 16:03:40,873 INFO Epoch:31 val_res:0.828000 +2025-04-19 16:04:08,688 INFO Epoch:32 train_loss:1.23737 +2025-04-19 16:04:12,900 INFO Epoch:32 val_res:0.816000 +2025-04-19 16:04:39,891 INFO Epoch:33 train_loss:1.22296 +2025-04-19 16:04:44,269 INFO Epoch:33 val_res:0.838000 +2025-04-19 16:04:44,270 INFO Saving best model at Epoch 33 +2025-04-19 16:05:13,875 INFO Epoch:34 train_loss:1.20642 +2025-04-19 16:05:18,092 INFO Epoch:34 val_res:0.839000 +2025-04-19 16:05:18,092 INFO Saving best model at Epoch 34 +2025-04-19 16:05:47,749 INFO Epoch:35 train_loss:1.19392 +2025-04-19 16:05:51,923 INFO Epoch:35 val_res:0.822000 +2025-04-19 16:06:20,062 INFO Epoch:36 train_loss:1.21449 +2025-04-19 16:06:24,487 INFO Epoch:36 val_res:0.825000 +2025-04-19 16:06:52,278 INFO Epoch:37 train_loss:1.18095 +2025-04-19 16:06:56,542 INFO Epoch:37 val_res:0.841000 +2025-04-19 16:06:56,542 INFO Saving best model at Epoch 37 +2025-04-19 16:07:26,778 INFO Epoch:38 train_loss:1.18916 +2025-04-19 16:07:30,981 INFO Epoch:38 val_res:0.838000 +2025-04-19 16:07:59,743 INFO Epoch:39 train_loss:1.18483 +2025-04-19 16:08:04,013 INFO Epoch:39 val_res:0.828000 +2025-04-19 16:08:32,576 INFO Epoch:40 train_loss:1.13449 +2025-04-19 16:08:36,936 INFO Epoch:40 val_res:0.837000 +2025-04-19 16:09:05,224 INFO Epoch:41 train_loss:1.14334 +2025-04-19 16:09:09,533 INFO Epoch:41 val_res:0.837000 +2025-04-19 16:09:37,701 INFO Epoch:42 train_loss:1.12304 +2025-04-19 16:09:41,885 INFO Epoch:42 val_res:0.831000 +2025-04-19 16:10:10,097 INFO Epoch:43 train_loss:1.12047 +2025-04-19 16:10:14,439 INFO Epoch:43 val_res:0.830000 +2025-04-19 16:10:42,781 INFO Epoch:44 train_loss:1.10792 +2025-04-19 16:10:47,196 INFO Epoch:44 val_res:0.829000 +2025-04-19 16:11:15,166 INFO Epoch:45 train_loss:1.09898 +2025-04-19 16:11:19,374 INFO Epoch:45 val_res:0.842000 +2025-04-19 16:11:19,374 INFO Saving best model at Epoch 45 +2025-04-19 16:11:49,338 INFO Epoch:46 train_loss:1.11325 +2025-04-19 16:11:53,457 INFO Epoch:46 val_res:0.835000 +2025-04-19 16:12:21,509 INFO Epoch:47 train_loss:1.07724 +2025-04-19 16:12:25,620 INFO Epoch:47 val_res:0.841000 +2025-04-19 16:12:53,942 INFO Epoch:48 train_loss:1.08272 +2025-04-19 16:12:58,073 INFO Epoch:48 val_res:0.835000 +2025-04-19 16:13:26,104 INFO Epoch:49 train_loss:1.09280 +2025-04-19 16:13:30,268 INFO Epoch:49 val_res:0.838000 +2025-04-19 16:13:58,439 INFO Epoch:50 train_loss:1.10642 +2025-04-19 16:14:02,550 INFO Epoch:50 val_res:0.843000 +2025-04-19 16:14:02,550 INFO Saving best model at Epoch 50 +2025-04-19 16:14:32,462 INFO Epoch:51 train_loss:1.06191 +2025-04-19 16:14:36,629 INFO Epoch:51 val_res:0.834000 +2025-04-19 16:15:04,352 INFO Epoch:52 train_loss:1.06469 +2025-04-19 16:15:08,605 INFO Epoch:52 val_res:0.832000 +2025-04-19 16:15:37,030 INFO Epoch:53 train_loss:1.05972 +2025-04-19 16:15:41,138 INFO Epoch:53 val_res:0.831000 +2025-04-19 16:16:09,252 INFO Epoch:54 train_loss:1.05144 +2025-04-19 16:16:13,334 INFO Epoch:54 val_res:0.828000 +2025-04-19 16:16:41,452 INFO Epoch:55 train_loss:1.04790 +2025-04-19 16:16:45,525 INFO Epoch:55 val_res:0.851000 +2025-04-19 16:16:45,526 INFO Saving best model at Epoch 55 +2025-04-19 16:17:15,402 INFO Epoch:56 train_loss:1.03513 +2025-04-19 16:17:19,516 INFO Epoch:56 val_res:0.843000 +2025-04-19 16:17:48,366 INFO Epoch:57 train_loss:1.04179 +2025-04-19 16:17:52,689 INFO Epoch:57 val_res:0.831000 +2025-04-19 16:18:20,840 INFO Epoch:58 train_loss:1.03609 +2025-04-19 16:18:25,038 INFO Epoch:58 val_res:0.840000 +2025-04-19 16:18:53,061 INFO Epoch:59 train_loss:1.05575 +2025-04-19 16:18:57,085 INFO Epoch:59 val_res:0.831000 +2025-04-19 16:19:25,202 INFO Epoch:60 train_loss:1.04774 +2025-04-19 16:19:29,339 INFO Epoch:60 val_res:0.834000 +2025-04-19 16:19:57,257 INFO Epoch:61 train_loss:1.01236 +2025-04-19 16:20:01,562 INFO Epoch:61 val_res:0.835000 +2025-04-19 16:20:30,075 INFO Epoch:62 train_loss:1.02558 +2025-04-19 16:20:34,257 INFO Epoch:62 val_res:0.828000 +2025-04-19 16:21:02,778 INFO Epoch:63 train_loss:1.01750 +2025-04-19 16:21:07,084 INFO Epoch:63 val_res:0.824000 +2025-04-19 16:21:35,715 INFO Epoch:64 train_loss:1.00130 +2025-04-19 16:21:39,893 INFO Epoch:64 val_res:0.822000 +2025-04-19 16:22:08,265 INFO Epoch:65 train_loss:1.00513 +2025-04-19 16:22:12,389 INFO Epoch:65 val_res:0.828000 +2025-04-19 16:22:40,404 INFO Epoch:66 train_loss:1.00301 +2025-04-19 16:22:44,621 INFO Epoch:66 val_res:0.832000 +2025-04-19 16:23:12,019 INFO Epoch:67 train_loss:1.00622 +2025-04-19 16:23:16,391 INFO Epoch:67 val_res:0.835000 +2025-04-19 16:23:44,334 INFO Epoch:68 train_loss:1.01197 +2025-04-19 16:23:48,672 INFO Epoch:68 val_res:0.831000 +2025-04-19 16:24:16,610 INFO Epoch:69 train_loss:1.00892 +2025-04-19 16:24:20,973 INFO Epoch:69 val_res:0.824000 +2025-04-19 16:24:48,729 INFO Epoch:70 train_loss:1.00518 +2025-04-19 16:24:52,980 INFO Epoch:70 val_res:0.843000 +2025-04-19 16:25:20,005 INFO Epoch:71 train_loss:0.57158 +2025-04-19 16:25:24,447 INFO Epoch:71 val_res:0.843000 +2025-04-19 16:25:51,688 INFO Epoch:72 train_loss:0.55622 +2025-04-19 16:25:56,162 INFO Epoch:72 val_res:0.843000 +2025-04-19 16:26:24,001 INFO Epoch:73 train_loss:0.55475 +2025-04-19 16:26:28,256 INFO Epoch:73 val_res:0.839000 +2025-04-19 16:26:55,474 INFO Epoch:74 train_loss:0.54870 +2025-04-19 16:26:59,770 INFO Epoch:74 val_res:0.834000 +2025-04-19 16:27:27,417 INFO Epoch:75 train_loss:0.54740 +2025-04-19 16:27:31,903 INFO Epoch:75 val_res:0.838000 +2025-04-19 16:27:59,556 INFO Epoch:76 train_loss:0.54717 +2025-04-19 16:28:03,891 INFO Epoch:76 val_res:0.836000 +2025-04-19 16:28:31,195 INFO Epoch:77 train_loss:0.54964 +2025-04-19 16:28:35,444 INFO Epoch:77 val_res:0.847000 +2025-04-19 16:29:02,569 INFO Epoch:78 train_loss:0.54025 +2025-04-19 16:29:06,901 INFO Epoch:78 val_res:0.848000 +2025-04-19 16:29:34,851 INFO Epoch:79 train_loss:0.54246 +2025-04-19 16:29:39,083 INFO Epoch:79 val_res:0.844000 +2025-04-19 16:30:06,910 INFO Epoch:80 train_loss:0.54117 +2025-04-19 16:30:11,419 INFO Epoch:80 val_res:0.844000 +2025-04-19 16:30:39,787 INFO Epoch:81 train_loss:0.54051 +2025-04-19 16:30:44,259 INFO Epoch:81 val_res:0.833000 +2025-04-19 16:31:11,654 INFO Epoch:82 train_loss:0.54007 +2025-04-19 16:31:16,094 INFO Epoch:82 val_res:0.839000 +2025-04-19 16:31:43,482 INFO Epoch:83 train_loss:0.53485 +2025-04-19 16:31:47,884 INFO Epoch:83 val_res:0.843000 +2025-04-19 16:32:15,122 INFO Epoch:84 train_loss:0.54264 +2025-04-19 16:32:19,385 INFO Epoch:84 val_res:0.837000 +2025-04-19 16:32:47,253 INFO Epoch:85 train_loss:0.53979 +2025-04-19 16:32:51,363 INFO Epoch:85 val_res:0.835000 +2025-04-19 16:33:19,319 INFO Epoch:86 train_loss:0.54822 +2025-04-19 16:33:23,637 INFO Epoch:86 val_res:0.844000 +2025-04-19 16:33:51,533 INFO Epoch:87 train_loss:0.55194 +2025-04-19 16:33:55,667 INFO Epoch:87 val_res:0.833000 +2025-04-19 16:34:23,606 INFO Epoch:88 train_loss:0.54274 +2025-04-19 16:34:27,731 INFO Epoch:88 val_res:0.841000 +2025-04-19 16:34:55,606 INFO Epoch:89 train_loss:0.54613 +2025-04-19 16:34:59,694 INFO Epoch:89 val_res:0.833000 +2025-04-19 16:35:27,203 INFO Epoch:90 train_loss:0.53486 +2025-04-19 16:35:31,443 INFO Epoch:90 val_res:0.850000 +2025-04-19 16:35:59,771 INFO Epoch:91 train_loss:0.53581 +2025-04-19 16:36:04,067 INFO Epoch:91 val_res:0.848000 +2025-04-19 16:36:32,176 INFO Epoch:92 train_loss:0.54455 +2025-04-19 16:36:36,414 INFO Epoch:92 val_res:0.848000 +2025-04-19 16:37:04,186 INFO Epoch:93 train_loss:0.58740 +2025-04-19 16:37:08,412 INFO Epoch:93 val_res:0.832000 +2025-04-19 16:37:36,106 INFO Epoch:94 train_loss:0.99196 +2025-04-19 16:37:40,348 INFO Epoch:94 val_res:0.819000 +2025-04-19 16:38:08,396 INFO Epoch:95 train_loss:1.04174 +2025-04-19 16:38:12,662 INFO Epoch:95 val_res:0.812000 +2025-04-19 16:38:41,096 INFO Epoch:96 train_loss:0.69294 +2025-04-19 16:38:45,432 INFO Epoch:96 val_res:0.834000 +2025-04-19 16:39:12,528 INFO Epoch:97 train_loss:0.58973 +2025-04-19 16:39:16,824 INFO Epoch:97 val_res:0.836000 +2025-04-19 16:39:44,871 INFO Epoch:98 train_loss:0.55089 +2025-04-19 16:39:49,194 INFO Epoch:98 val_res:0.835000 +2025-04-19 16:40:15,588 INFO Epoch:99 train_loss:0.53469 +2025-04-19 16:40:19,953 INFO Epoch:99 val_res:0.837000 +2025-04-19 16:40:20,454 INFO ===================================== +2025-04-19 16:40:20,455 INFO Start testing... +2025-04-19 16:40:20,455 INFO ===================================== +2025-04-19 16:40:25,629 INFO Incremental step 1 Testing res: 0.834000 +2025-04-19 16:40:25,631 INFO forgetting: 0.102000 +2025-04-19 16:40:25,634 INFO Incremental step: 2 +2025-04-19 16:42:13,809 INFO Epoch:0 train_loss:2.21987 +2025-04-19 16:42:19,166 INFO Epoch:0 val_res:0.564667 +2025-04-19 16:42:19,166 INFO Saving best model at Epoch 0 +2025-04-19 16:42:51,986 INFO Epoch:1 train_loss:1.11894 +2025-04-19 16:42:57,503 INFO Epoch:1 val_res:0.590667 +2025-04-19 16:42:57,503 INFO Saving best model at Epoch 1 +2025-04-19 16:43:33,126 INFO Epoch:2 train_loss:0.94265 +2025-04-19 16:43:40,067 INFO Epoch:2 val_res:0.606000 +2025-04-19 16:43:40,067 INFO Saving best model at Epoch 2 +2025-04-19 16:44:11,146 INFO Epoch:3 train_loss:0.87875 +2025-04-19 16:44:17,395 INFO Epoch:3 val_res:0.624000 +2025-04-19 16:44:17,395 INFO Saving best model at Epoch 3 +2025-04-19 16:44:49,275 INFO Epoch:4 train_loss:0.84379 +2025-04-19 16:44:55,333 INFO Epoch:4 val_res:0.631333 +2025-04-19 16:44:55,334 INFO Saving best model at Epoch 4 +2025-04-19 16:45:26,815 INFO Epoch:5 train_loss:0.81759 +2025-04-19 16:45:32,374 INFO Epoch:5 val_res:0.636000 +2025-04-19 16:45:32,375 INFO Saving best model at Epoch 5 +2025-04-19 16:46:03,360 INFO Epoch:6 train_loss:0.79449 +2025-04-19 16:46:09,375 INFO Epoch:6 val_res:0.648000 +2025-04-19 16:46:09,375 INFO Saving best model at Epoch 6 +2025-04-19 16:46:40,477 INFO Epoch:7 train_loss:0.77397 +2025-04-19 16:46:46,100 INFO Epoch:7 val_res:0.654000 +2025-04-19 16:46:46,100 INFO Saving best model at Epoch 7 +2025-04-19 16:47:18,409 INFO Epoch:8 train_loss:0.75875 +2025-04-19 16:47:24,219 INFO Epoch:8 val_res:0.663333 +2025-04-19 16:47:24,219 INFO Saving best model at Epoch 8 +2025-04-19 16:47:55,790 INFO Epoch:9 train_loss:0.74595 +2025-04-19 16:48:01,176 INFO Epoch:9 val_res:0.678000 +2025-04-19 16:48:01,176 INFO Saving best model at Epoch 9 +2025-04-19 16:48:33,915 INFO Epoch:10 train_loss:0.72805 +2025-04-19 16:48:39,237 INFO Epoch:10 val_res:0.675333 +2025-04-19 16:49:08,897 INFO Epoch:11 train_loss:0.71693 +2025-04-19 16:49:15,079 INFO Epoch:11 val_res:0.696000 +2025-04-19 16:49:15,080 INFO Saving best model at Epoch 11 +2025-04-19 16:49:46,353 INFO Epoch:12 train_loss:0.71184 +2025-04-19 16:49:52,066 INFO Epoch:12 val_res:0.694667 +2025-04-19 16:50:22,801 INFO Epoch:13 train_loss:0.71010 +2025-04-19 16:50:28,720 INFO Epoch:13 val_res:0.702667 +2025-04-19 16:50:28,721 INFO Saving best model at Epoch 13 +2025-04-19 16:51:00,677 INFO Epoch:14 train_loss:0.68707 +2025-04-19 16:51:06,471 INFO Epoch:14 val_res:0.709333 +2025-04-19 16:51:06,472 INFO Saving best model at Epoch 14 +2025-04-19 16:51:39,201 INFO Epoch:15 train_loss:0.68044 +2025-04-19 16:51:44,567 INFO Epoch:15 val_res:0.710000 +2025-04-19 16:51:44,568 INFO Saving best model at Epoch 15 +2025-04-19 16:52:17,138 INFO Epoch:16 train_loss:0.68257 +2025-04-19 16:52:22,698 INFO Epoch:16 val_res:0.720667 +2025-04-19 16:52:22,699 INFO Saving best model at Epoch 16 +2025-04-19 16:52:55,212 INFO Epoch:17 train_loss:0.70178 +2025-04-19 16:53:00,843 INFO Epoch:17 val_res:0.720667 +2025-04-19 16:53:31,414 INFO Epoch:18 train_loss:0.69688 +2025-04-19 16:53:36,768 INFO Epoch:18 val_res:0.733333 +2025-04-19 16:53:36,768 INFO Saving best model at Epoch 18 +2025-04-19 16:54:12,860 INFO Epoch:19 train_loss:0.67498 +2025-04-19 16:54:19,615 INFO Epoch:19 val_res:0.728000 +2025-04-19 16:54:51,229 INFO Epoch:20 train_loss:6.10158 +2025-04-19 16:54:57,724 INFO Epoch:20 val_res:0.702000 +2025-04-19 16:55:29,149 INFO Epoch:21 train_loss:2.74482 +2025-04-19 16:55:35,016 INFO Epoch:21 val_res:0.754667 +2025-04-19 16:55:35,017 INFO Saving best model at Epoch 21 +2025-04-19 16:56:06,782 INFO Epoch:22 train_loss:1.80920 +2025-04-19 16:56:12,677 INFO Epoch:22 val_res:0.765333 +2025-04-19 16:56:12,678 INFO Saving best model at Epoch 22 +2025-04-19 16:56:44,365 INFO Epoch:23 train_loss:1.56794 +2025-04-19 16:56:49,929 INFO Epoch:23 val_res:0.766000 +2025-04-19 16:56:49,929 INFO Saving best model at Epoch 23 +2025-04-19 16:57:21,353 INFO Epoch:24 train_loss:1.45936 +2025-04-19 16:57:27,132 INFO Epoch:24 val_res:0.767333 +2025-04-19 16:57:27,138 INFO Saving best model at Epoch 24 +2025-04-19 16:58:00,035 INFO Epoch:25 train_loss:1.40463 +2025-04-19 16:58:06,081 INFO Epoch:25 val_res:0.771333 +2025-04-19 16:58:06,082 INFO Saving best model at Epoch 25 +2025-04-19 16:58:38,873 INFO Epoch:26 train_loss:1.35192 +2025-04-19 16:58:44,143 INFO Epoch:26 val_res:0.770000 +2025-04-19 16:59:15,025 INFO Epoch:27 train_loss:1.30458 +2025-04-19 16:59:20,606 INFO Epoch:27 val_res:0.772667 +2025-04-19 16:59:20,607 INFO Saving best model at Epoch 27 +2025-04-19 16:59:53,607 INFO Epoch:28 train_loss:1.26546 +2025-04-19 16:59:59,094 INFO Epoch:28 val_res:0.775333 +2025-04-19 16:59:59,094 INFO Saving best model at Epoch 28 +2025-04-19 17:00:32,267 INFO Epoch:29 train_loss:1.24145 +2025-04-19 17:00:37,899 INFO Epoch:29 val_res:0.776667 +2025-04-19 17:00:37,900 INFO Saving best model at Epoch 29 +2025-04-19 17:01:15,039 INFO Epoch:30 train_loss:1.21594 +2025-04-19 17:01:21,911 INFO Epoch:30 val_res:0.775333 +2025-04-19 17:01:53,548 INFO Epoch:31 train_loss:1.19617 +2025-04-19 17:01:59,773 INFO Epoch:31 val_res:0.774000 +2025-04-19 17:02:30,274 INFO Epoch:32 train_loss:1.17579 +2025-04-19 17:02:36,172 INFO Epoch:32 val_res:0.770000 +2025-04-19 17:03:06,993 INFO Epoch:33 train_loss:1.15696 +2025-04-19 17:03:12,872 INFO Epoch:33 val_res:0.780000 +2025-04-19 17:03:12,872 INFO Saving best model at Epoch 33 +2025-04-19 17:03:45,450 INFO Epoch:34 train_loss:1.13487 +2025-04-19 17:03:51,040 INFO Epoch:34 val_res:0.772667 +2025-04-19 17:04:21,200 INFO Epoch:35 train_loss:1.12783 +2025-04-19 17:04:26,929 INFO Epoch:35 val_res:0.782000 +2025-04-19 17:04:26,930 INFO Saving best model at Epoch 35 +2025-04-19 17:04:59,778 INFO Epoch:36 train_loss:1.11306 +2025-04-19 17:05:05,520 INFO Epoch:36 val_res:0.785333 +2025-04-19 17:05:05,521 INFO Saving best model at Epoch 36 +2025-04-19 17:05:38,389 INFO Epoch:37 train_loss:1.09490 +2025-04-19 17:05:43,905 INFO Epoch:37 val_res:0.778667 +2025-04-19 17:06:14,717 INFO Epoch:38 train_loss:1.09619 +2025-04-19 17:06:20,154 INFO Epoch:38 val_res:0.780667 +2025-04-19 17:06:51,094 INFO Epoch:39 train_loss:1.07965 +2025-04-19 17:06:56,358 INFO Epoch:39 val_res:0.779333 +2025-04-19 17:07:27,686 INFO Epoch:40 train_loss:1.07481 +2025-04-19 17:07:33,040 INFO Epoch:40 val_res:0.772667 +2025-04-19 17:08:05,162 INFO Epoch:41 train_loss:1.06003 +2025-04-19 17:08:10,687 INFO Epoch:41 val_res:0.774667 +2025-04-19 17:08:46,611 INFO Epoch:42 train_loss:1.04573 +2025-04-19 17:08:53,782 INFO Epoch:42 val_res:0.773333 +2025-04-19 17:09:24,124 INFO Epoch:43 train_loss:1.04028 +2025-04-19 17:09:30,529 INFO Epoch:43 val_res:0.774000 +2025-04-19 17:10:01,267 INFO Epoch:44 train_loss:1.02785 +2025-04-19 17:10:07,452 INFO Epoch:44 val_res:0.780667 +2025-04-19 17:10:38,348 INFO Epoch:45 train_loss:1.02999 +2025-04-19 17:10:44,666 INFO Epoch:45 val_res:0.784667 +2025-04-19 17:11:15,848 INFO Epoch:46 train_loss:1.02691 +2025-04-19 17:11:21,736 INFO Epoch:46 val_res:0.775333 +2025-04-19 17:11:51,775 INFO Epoch:47 train_loss:1.00723 +2025-04-19 17:11:57,466 INFO Epoch:47 val_res:0.773333 +2025-04-19 17:12:29,149 INFO Epoch:48 train_loss:1.01386 +2025-04-19 17:12:34,974 INFO Epoch:48 val_res:0.775333 +2025-04-19 17:13:06,716 INFO Epoch:49 train_loss:1.00839 +2025-04-19 17:13:12,185 INFO Epoch:49 val_res:0.776000 +2025-04-19 17:13:42,637 INFO Epoch:50 train_loss:1.00420 +2025-04-19 17:13:48,930 INFO Epoch:50 val_res:0.772000 +2025-04-19 17:14:19,612 INFO Epoch:51 train_loss:0.99686 +2025-04-19 17:14:25,383 INFO Epoch:51 val_res:0.786667 +2025-04-19 17:14:25,383 INFO Saving best model at Epoch 51 +2025-04-19 17:14:58,951 INFO Epoch:52 train_loss:0.97771 +2025-04-19 17:15:04,260 INFO Epoch:52 val_res:0.777333 +2025-04-19 17:15:36,724 INFO Epoch:53 train_loss:0.99309 +2025-04-19 17:15:42,148 INFO Epoch:53 val_res:0.774000 +2025-04-19 17:16:19,626 INFO Epoch:54 train_loss:0.97837 +2025-04-19 17:16:26,823 INFO Epoch:54 val_res:0.783333 +2025-04-19 17:16:57,907 INFO Epoch:55 train_loss:0.97390 +2025-04-19 17:17:03,681 INFO Epoch:55 val_res:0.782667 +2025-04-19 17:17:34,175 INFO Epoch:56 train_loss:0.97543 +2025-04-19 17:17:39,849 INFO Epoch:56 val_res:0.777333 +2025-04-19 17:18:10,683 INFO Epoch:57 train_loss:0.96747 +2025-04-19 17:18:16,546 INFO Epoch:57 val_res:0.781333 +2025-04-19 17:18:47,587 INFO Epoch:58 train_loss:0.95576 +2025-04-19 17:18:53,020 INFO Epoch:58 val_res:0.779333 +2025-04-19 17:19:23,816 INFO Epoch:59 train_loss:0.96901 +2025-04-19 17:19:29,617 INFO Epoch:59 val_res:0.776000 +2025-04-19 17:20:00,101 INFO Epoch:60 train_loss:1.01150 +2025-04-19 17:20:05,530 INFO Epoch:60 val_res:0.775333 +2025-04-19 17:20:36,981 INFO Epoch:61 train_loss:1.00397 +2025-04-19 17:20:42,557 INFO Epoch:61 val_res:0.781333 +2025-04-19 17:21:14,237 INFO Epoch:62 train_loss:0.96327 +2025-04-19 17:21:20,336 INFO Epoch:62 val_res:0.779333 +2025-04-19 17:21:52,017 INFO Epoch:63 train_loss:0.95765 +2025-04-19 17:21:57,761 INFO Epoch:63 val_res:0.779333 +2025-04-19 17:22:28,939 INFO Epoch:64 train_loss:0.94383 +2025-04-19 17:22:34,358 INFO Epoch:64 val_res:0.773333 +2025-04-19 17:23:06,350 INFO Epoch:65 train_loss:0.94548 +2025-04-19 17:23:11,935 INFO Epoch:65 val_res:0.778000 +2025-04-19 17:23:47,019 INFO Epoch:66 train_loss:0.93372 +2025-04-19 17:23:54,744 INFO Epoch:66 val_res:0.779333 +2025-04-19 17:24:26,437 INFO Epoch:67 train_loss:0.93415 +2025-04-19 17:24:32,104 INFO Epoch:67 val_res:0.781333 +2025-04-19 17:25:02,434 INFO Epoch:68 train_loss:0.94203 +2025-04-19 17:25:08,027 INFO Epoch:68 val_res:0.772667 +2025-04-19 17:25:39,822 INFO Epoch:69 train_loss:0.94025 +2025-04-19 17:25:45,347 INFO Epoch:69 val_res:0.778000 +2025-04-19 17:26:16,136 INFO Epoch:70 train_loss:0.92319 +2025-04-19 17:26:21,989 INFO Epoch:70 val_res:0.780667 +2025-04-19 17:26:52,699 INFO Epoch:71 train_loss:0.54609 +2025-04-19 17:26:58,863 INFO Epoch:71 val_res:0.780000 +2025-04-19 17:27:29,591 INFO Epoch:72 train_loss:0.53114 +2025-04-19 17:27:35,020 INFO Epoch:72 val_res:0.784000 +2025-04-19 17:28:05,880 INFO Epoch:73 train_loss:0.52839 +2025-04-19 17:28:11,770 INFO Epoch:73 val_res:0.786000 +2025-04-19 17:28:42,428 INFO Epoch:74 train_loss:0.52564 +2025-04-19 17:28:48,394 INFO Epoch:74 val_res:0.780667 +2025-04-19 17:29:18,886 INFO Epoch:75 train_loss:0.52367 +2025-04-19 17:29:24,446 INFO Epoch:75 val_res:0.783333 +2025-04-19 17:29:54,555 INFO Epoch:76 train_loss:0.52180 +2025-04-19 17:30:00,824 INFO Epoch:76 val_res:0.783333 +2025-04-19 17:30:31,252 INFO Epoch:77 train_loss:0.52156 +2025-04-19 17:30:36,673 INFO Epoch:77 val_res:0.782000 +2025-04-19 17:31:07,559 INFO Epoch:78 train_loss:0.51915 +2025-04-19 17:31:13,001 INFO Epoch:78 val_res:0.782667 +2025-04-19 17:31:45,073 INFO Epoch:79 train_loss:0.52113 +2025-04-19 17:31:50,715 INFO Epoch:79 val_res:0.783333 +2025-04-19 17:32:24,904 INFO Epoch:80 train_loss:0.51684 +2025-04-19 17:32:32,154 INFO Epoch:80 val_res:0.788000 +2025-04-19 17:32:32,155 INFO Saving best model at Epoch 80 +2025-04-19 17:33:04,114 INFO Epoch:81 train_loss:0.51632 +2025-04-19 17:33:10,058 INFO Epoch:81 val_res:0.787333 +2025-04-19 17:33:40,627 INFO Epoch:82 train_loss:0.51883 +2025-04-19 17:33:46,478 INFO Epoch:82 val_res:0.786000 +2025-04-19 17:34:16,384 INFO Epoch:83 train_loss:0.51628 +2025-04-19 17:34:22,097 INFO Epoch:83 val_res:0.786000 +2025-04-19 17:34:51,527 INFO Epoch:84 train_loss:0.52124 +2025-04-19 17:34:57,267 INFO Epoch:84 val_res:0.785333 +2025-04-19 17:35:26,566 INFO Epoch:85 train_loss:0.52063 +2025-04-19 17:35:32,588 INFO Epoch:85 val_res:0.780000 +2025-04-19 17:36:03,756 INFO Epoch:86 train_loss:0.51595 +2025-04-19 17:36:09,715 INFO Epoch:86 val_res:0.788667 +2025-04-19 17:36:09,715 INFO Saving best model at Epoch 86 +2025-04-19 17:36:42,049 INFO Epoch:87 train_loss:0.52194 +2025-04-19 17:36:47,676 INFO Epoch:87 val_res:0.784667 +2025-04-19 17:37:18,415 INFO Epoch:88 train_loss:0.52051 +2025-04-19 17:37:24,034 INFO Epoch:88 val_res:0.789333 +2025-04-19 17:37:24,034 INFO Saving best model at Epoch 88 +2025-04-19 17:37:55,510 INFO Epoch:89 train_loss:0.51609 +2025-04-19 17:38:01,202 INFO Epoch:89 val_res:0.788000 +2025-04-19 17:38:31,691 INFO Epoch:90 train_loss:0.51876 +2025-04-19 17:38:37,090 INFO Epoch:90 val_res:0.780000 +2025-04-19 17:39:07,181 INFO Epoch:91 train_loss:0.52804 +2025-04-19 17:39:12,745 INFO Epoch:91 val_res:0.782000 +2025-04-19 17:39:43,157 INFO Epoch:92 train_loss:0.56644 +2025-04-19 17:39:48,536 INFO Epoch:92 val_res:0.782667 +2025-04-19 17:40:17,721 INFO Epoch:93 train_loss:0.67200 +2025-04-19 17:40:23,065 INFO Epoch:93 val_res:0.765333 +2025-04-19 17:40:51,354 INFO Epoch:94 train_loss:0.83391 +2025-04-19 17:40:56,796 INFO Epoch:94 val_res:0.778667 +2025-04-19 17:41:26,605 INFO Epoch:95 train_loss:0.57777 +2025-04-19 17:41:32,130 INFO Epoch:95 val_res:0.778000 +2025-04-19 17:42:00,778 INFO Epoch:96 train_loss:0.52953 +2025-04-19 17:42:06,533 INFO Epoch:96 val_res:0.784000 +2025-04-19 17:42:37,048 INFO Epoch:97 train_loss:0.51803 +2025-04-19 17:42:42,731 INFO Epoch:97 val_res:0.785333 +2025-04-19 17:43:13,285 INFO Epoch:98 train_loss:0.52023 +2025-04-19 17:43:18,934 INFO Epoch:98 val_res:0.786667 +2025-04-19 17:43:50,578 INFO Epoch:99 train_loss:0.51013 +2025-04-19 17:43:56,344 INFO Epoch:99 val_res:0.783333 +2025-04-19 17:43:56,522 INFO ===================================== +2025-04-19 17:43:56,522 INFO Start testing... +2025-04-19 17:43:56,522 INFO ===================================== +2025-04-19 17:44:02,233 INFO Incremental step 2 Testing res: 0.787333 +2025-04-19 17:44:02,234 INFO forgetting: 0.127000 +2025-04-19 17:44:02,238 INFO Incremental step: 3 +2025-04-19 17:44:32,333 INFO Epoch:0 train_loss:2.90125 +2025-04-19 17:44:38,778 INFO Epoch:0 val_res:0.605000 +2025-04-19 17:44:38,778 INFO Saving best model at Epoch 0 +2025-04-19 17:45:10,649 INFO Epoch:1 train_loss:1.25201 +2025-04-19 17:45:17,859 INFO Epoch:1 val_res:0.605500 +2025-04-19 17:45:17,859 INFO Saving best model at Epoch 1 +2025-04-19 17:45:49,720 INFO Epoch:2 train_loss:1.00978 +2025-04-19 17:45:56,372 INFO Epoch:2 val_res:0.618000 +2025-04-19 17:45:56,372 INFO Saving best model at Epoch 2 +2025-04-19 17:46:29,023 INFO Epoch:3 train_loss:0.93199 +2025-04-19 17:46:36,304 INFO Epoch:3 val_res:0.616500 +2025-04-19 17:47:07,164 INFO Epoch:4 train_loss:0.90033 +2025-04-19 17:47:14,112 INFO Epoch:4 val_res:0.617000 +2025-04-19 17:47:44,405 INFO Epoch:5 train_loss:0.87169 +2025-04-19 17:47:50,911 INFO Epoch:5 val_res:0.623000 +2025-04-19 17:47:50,911 INFO Saving best model at Epoch 5 +2025-04-19 17:48:23,632 INFO Epoch:6 train_loss:0.84943 +2025-04-19 17:48:31,234 INFO Epoch:6 val_res:0.625500 +2025-04-19 17:48:31,234 INFO Saving best model at Epoch 6 +2025-04-19 17:49:03,893 INFO Epoch:7 train_loss:0.83430 +2025-04-19 17:49:10,715 INFO Epoch:7 val_res:0.626500 +2025-04-19 17:49:10,716 INFO Saving best model at Epoch 7 +2025-04-19 17:49:44,681 INFO Epoch:8 train_loss:0.82060 +2025-04-19 17:49:52,805 INFO Epoch:8 val_res:0.632000 +2025-04-19 17:49:52,805 INFO Saving best model at Epoch 8 +2025-04-19 17:50:28,314 INFO Epoch:9 train_loss:0.80830 +2025-04-19 17:50:36,741 INFO Epoch:9 val_res:0.638000 +2025-04-19 17:50:36,741 INFO Saving best model at Epoch 9 +2025-04-19 17:51:14,464 INFO Epoch:10 train_loss:0.80037 +2025-04-19 17:51:23,448 INFO Epoch:10 val_res:0.645500 +2025-04-19 17:51:23,449 INFO Saving best model at Epoch 10 +2025-04-19 17:51:55,560 INFO Epoch:11 train_loss:0.78479 +2025-04-19 17:52:03,046 INFO Epoch:11 val_res:0.645500 +2025-04-19 17:52:32,861 INFO Epoch:12 train_loss:0.78029 +2025-04-19 17:52:40,471 INFO Epoch:12 val_res:0.649500 +2025-04-19 17:52:40,472 INFO Saving best model at Epoch 12 +2025-04-19 17:53:13,159 INFO Epoch:13 train_loss:0.75754 +2025-04-19 17:53:20,942 INFO Epoch:13 val_res:0.653500 +2025-04-19 17:53:20,943 INFO Saving best model at Epoch 13 +2025-04-19 17:53:52,877 INFO Epoch:14 train_loss:0.74481 +2025-04-19 17:53:59,950 INFO Epoch:14 val_res:0.656500 +2025-04-19 17:53:59,951 INFO Saving best model at Epoch 14 +2025-04-19 17:54:31,292 INFO Epoch:15 train_loss:0.76283 +2025-04-19 17:54:38,569 INFO Epoch:15 val_res:0.658500 +2025-04-19 17:54:38,569 INFO Saving best model at Epoch 15 +2025-04-19 17:55:10,721 INFO Epoch:16 train_loss:0.74220 +2025-04-19 17:55:18,249 INFO Epoch:16 val_res:0.666500 +2025-04-19 17:55:18,249 INFO Saving best model at Epoch 16 +2025-04-19 17:55:50,225 INFO Epoch:17 train_loss:0.71773 +2025-04-19 17:55:57,085 INFO Epoch:17 val_res:0.667000 +2025-04-19 17:55:57,085 INFO Saving best model at Epoch 17 +2025-04-19 17:56:28,191 INFO Epoch:18 train_loss:0.70793 +2025-04-19 17:56:34,905 INFO Epoch:18 val_res:0.671500 +2025-04-19 17:56:34,905 INFO Saving best model at Epoch 18 +2025-04-19 17:57:06,720 INFO Epoch:19 train_loss:0.70100 +2025-04-19 17:57:13,420 INFO Epoch:19 val_res:0.674500 +2025-04-19 17:57:13,421 INFO Saving best model at Epoch 19 +2025-04-19 17:57:46,498 INFO Epoch:20 train_loss:13.37850 +2025-04-19 17:57:53,750 INFO Epoch:20 val_res:0.614000 +2025-04-19 17:58:24,431 INFO Epoch:21 train_loss:4.10665 +2025-04-19 17:58:31,094 INFO Epoch:21 val_res:0.673500 +2025-04-19 17:59:02,668 INFO Epoch:22 train_loss:2.36476 +2025-04-19 17:59:09,572 INFO Epoch:22 val_res:0.688000 +2025-04-19 17:59:09,573 INFO Saving best model at Epoch 22 +2025-04-19 17:59:42,710 INFO Epoch:23 train_loss:1.94348 +2025-04-19 17:59:49,509 INFO Epoch:23 val_res:0.696000 +2025-04-19 17:59:49,509 INFO Saving best model at Epoch 23 +2025-04-19 18:00:22,600 INFO Epoch:24 train_loss:1.79227 +2025-04-19 18:00:29,277 INFO Epoch:24 val_res:0.701000 +2025-04-19 18:00:29,277 INFO Saving best model at Epoch 24 +2025-04-19 18:01:06,177 INFO Epoch:25 train_loss:1.70036 +2025-04-19 18:01:14,848 INFO Epoch:25 val_res:0.703500 +2025-04-19 18:01:14,848 INFO Saving best model at Epoch 25 +2025-04-19 18:01:48,637 INFO Epoch:26 train_loss:1.64151 +2025-04-19 18:01:56,673 INFO Epoch:26 val_res:0.705500 +2025-04-19 18:01:56,673 INFO Saving best model at Epoch 26 +2025-04-19 18:02:29,558 INFO Epoch:27 train_loss:1.59785 +2025-04-19 18:02:36,983 INFO Epoch:27 val_res:0.715500 +2025-04-19 18:02:36,984 INFO Saving best model at Epoch 27 +2025-04-19 18:03:10,100 INFO Epoch:28 train_loss:1.54800 +2025-04-19 18:03:17,617 INFO Epoch:28 val_res:0.709500 +2025-04-19 18:03:48,913 INFO Epoch:29 train_loss:1.51143 +2025-04-19 18:03:55,952 INFO Epoch:29 val_res:0.723000 +2025-04-19 18:03:55,952 INFO Saving best model at Epoch 29 +2025-04-19 18:04:29,306 INFO Epoch:30 train_loss:1.47764 +2025-04-19 18:04:36,489 INFO Epoch:30 val_res:0.721500 +2025-04-19 18:05:07,967 INFO Epoch:31 train_loss:1.45084 +2025-04-19 18:05:15,003 INFO Epoch:31 val_res:0.724000 +2025-04-19 18:05:15,004 INFO Saving best model at Epoch 31 +2025-04-19 18:05:48,132 INFO Epoch:32 train_loss:1.42589 +2025-04-19 18:05:54,920 INFO Epoch:32 val_res:0.723500 +2025-04-19 18:06:25,796 INFO Epoch:33 train_loss:1.39841 +2025-04-19 18:06:32,921 INFO Epoch:33 val_res:0.723000 +2025-04-19 18:07:04,443 INFO Epoch:34 train_loss:1.38978 +2025-04-19 18:07:11,046 INFO Epoch:34 val_res:0.724500 +2025-04-19 18:07:11,046 INFO Saving best model at Epoch 34 +2025-04-19 18:07:44,244 INFO Epoch:35 train_loss:1.36458 +2025-04-19 18:07:50,849 INFO Epoch:35 val_res:0.733000 +2025-04-19 18:07:50,849 INFO Saving best model at Epoch 35 +2025-04-19 18:08:24,632 INFO Epoch:36 train_loss:1.33250 +2025-04-19 18:08:31,555 INFO Epoch:36 val_res:0.724000 +2025-04-19 18:09:07,554 INFO Epoch:37 train_loss:1.32602 +2025-04-19 18:09:15,684 INFO Epoch:37 val_res:0.726500 +2025-04-19 18:09:48,508 INFO Epoch:38 train_loss:1.30828 +2025-04-19 18:09:56,589 INFO Epoch:38 val_res:0.731500 +2025-04-19 18:10:28,335 INFO Epoch:39 train_loss:1.29476 +2025-04-19 18:10:36,813 INFO Epoch:39 val_res:0.733000 +2025-04-19 18:11:07,989 INFO Epoch:40 train_loss:1.27565 +2025-04-19 18:11:16,345 INFO Epoch:40 val_res:0.742000 +2025-04-19 18:11:16,345 INFO Saving best model at Epoch 40 +2025-04-19 18:11:49,551 INFO Epoch:41 train_loss:1.26095 +2025-04-19 18:11:57,001 INFO Epoch:41 val_res:0.735000 +2025-04-19 18:12:28,359 INFO Epoch:42 train_loss:1.25176 +2025-04-19 18:12:35,159 INFO Epoch:42 val_res:0.737500 +2025-04-19 18:13:06,773 INFO Epoch:43 train_loss:1.24555 +2025-04-19 18:13:14,011 INFO Epoch:43 val_res:0.736500 +2025-04-19 18:13:45,024 INFO Epoch:44 train_loss:1.23159 +2025-04-19 18:13:51,944 INFO Epoch:44 val_res:0.732500 +2025-04-19 18:14:23,801 INFO Epoch:45 train_loss:1.22442 +2025-04-19 18:14:30,797 INFO Epoch:45 val_res:0.735500 +2025-04-19 18:15:02,337 INFO Epoch:46 train_loss:1.20859 +2025-04-19 18:15:09,100 INFO Epoch:46 val_res:0.733000 +2025-04-19 18:15:40,117 INFO Epoch:47 train_loss:1.20925 +2025-04-19 18:15:46,920 INFO Epoch:47 val_res:0.734000 +2025-04-19 18:16:17,955 INFO Epoch:48 train_loss:1.21550 +2025-04-19 18:16:24,714 INFO Epoch:48 val_res:0.735000 +2025-04-19 18:16:56,055 INFO Epoch:49 train_loss:1.20968 +2025-04-19 18:17:02,971 INFO Epoch:49 val_res:0.734000 +2025-04-19 18:17:34,956 INFO Epoch:50 train_loss:1.21141 +2025-04-19 18:17:42,083 INFO Epoch:50 val_res:0.736500 +2025-04-19 18:18:13,350 INFO Epoch:51 train_loss:1.17542 +2025-04-19 18:18:20,070 INFO Epoch:51 val_res:0.749000 +2025-04-19 18:18:20,070 INFO Saving best model at Epoch 51 +2025-04-19 18:18:53,067 INFO Epoch:52 train_loss:1.16846 +2025-04-19 18:18:59,808 INFO Epoch:52 val_res:0.735500 +2025-04-19 18:19:32,965 INFO Epoch:53 train_loss:1.16534 +2025-04-19 18:19:39,989 INFO Epoch:53 val_res:0.728500 +2025-04-19 18:20:16,997 INFO Epoch:54 train_loss:1.16174 +2025-04-19 18:20:25,832 INFO Epoch:54 val_res:0.745000 +2025-04-19 18:20:59,539 INFO Epoch:55 train_loss:1.16181 +2025-04-19 18:21:08,294 INFO Epoch:55 val_res:0.742000 +2025-04-19 18:21:45,286 INFO Epoch:56 train_loss:1.15853 +2025-04-19 18:21:54,083 INFO Epoch:56 val_res:0.739000 +2025-04-19 18:22:26,888 INFO Epoch:57 train_loss:1.14964 +2025-04-19 18:22:34,815 INFO Epoch:57 val_res:0.737500 +2025-04-19 18:23:12,406 INFO Epoch:58 train_loss:1.14724 +2025-04-19 18:23:20,566 INFO Epoch:58 val_res:0.740500 +2025-04-19 18:23:54,543 INFO Epoch:59 train_loss:1.14911 +2025-04-19 18:24:03,691 INFO Epoch:59 val_res:0.742000 +2025-04-19 18:24:38,179 INFO Epoch:60 train_loss:1.14413 +2025-04-19 18:24:46,819 INFO Epoch:60 val_res:0.745500 +2025-04-19 18:25:21,511 INFO Epoch:61 train_loss:1.13183 +2025-04-19 18:25:30,567 INFO Epoch:61 val_res:0.744000 +2025-04-19 18:26:08,113 INFO Epoch:62 train_loss:1.13134 +2025-04-19 18:26:16,617 INFO Epoch:62 val_res:0.745000 +2025-04-19 18:26:54,051 INFO Epoch:63 train_loss:1.12753 +2025-04-19 18:27:03,123 INFO Epoch:63 val_res:0.742000 +2025-04-19 18:27:36,899 INFO Epoch:64 train_loss:1.12635 +2025-04-19 18:27:45,160 INFO Epoch:64 val_res:0.744500 +2025-04-19 18:28:18,177 INFO Epoch:65 train_loss:1.13781 +2025-04-19 18:28:26,970 INFO Epoch:65 val_res:0.743500 +2025-04-19 18:29:03,842 INFO Epoch:66 train_loss:1.10366 +2025-04-19 18:29:12,469 INFO Epoch:66 val_res:0.742500 +2025-04-19 18:29:49,095 INFO Epoch:67 train_loss:1.11219 +2025-04-19 18:29:57,422 INFO Epoch:67 val_res:0.745500 +2025-04-19 18:30:35,427 INFO Epoch:68 train_loss:1.10827 +2025-04-19 18:30:44,444 INFO Epoch:68 val_res:0.743500 +2025-04-19 18:31:19,308 INFO Epoch:69 train_loss:1.11930 +2025-04-19 18:31:28,218 INFO Epoch:69 val_res:0.737500 +2025-04-19 18:32:04,778 INFO Epoch:70 train_loss:1.11173 +2025-04-19 18:32:13,406 INFO Epoch:70 val_res:0.741000 +2025-04-19 18:32:49,455 INFO Epoch:71 train_loss:0.55624 +2025-04-19 18:32:57,668 INFO Epoch:71 val_res:0.752000 +2025-04-19 18:32:57,668 INFO Saving best model at Epoch 71 +2025-04-19 18:33:33,853 INFO Epoch:72 train_loss:0.54553 +2025-04-19 18:33:40,890 INFO Epoch:72 val_res:0.743500 +2025-04-19 18:34:15,016 INFO Epoch:73 train_loss:0.54215 +2025-04-19 18:34:23,713 INFO Epoch:73 val_res:0.747500 +2025-04-19 18:34:55,515 INFO Epoch:74 train_loss:0.53940 +2025-04-19 18:35:03,516 INFO Epoch:74 val_res:0.747000 +2025-04-19 18:35:36,238 INFO Epoch:75 train_loss:0.53948 +2025-04-19 18:35:44,936 INFO Epoch:75 val_res:0.746500 +2025-04-19 18:36:16,785 INFO Epoch:76 train_loss:0.54061 +2025-04-19 18:36:25,551 INFO Epoch:76 val_res:0.746000 +2025-04-19 18:37:00,348 INFO Epoch:77 train_loss:0.53828 +2025-04-19 18:37:09,400 INFO Epoch:77 val_res:0.746000 +2025-04-19 18:37:45,963 INFO Epoch:78 train_loss:0.53923 +2025-04-19 18:37:56,612 INFO Epoch:78 val_res:0.742500 +2025-04-19 18:38:34,454 INFO Epoch:79 train_loss:0.54072 +2025-04-19 18:38:42,827 INFO Epoch:79 val_res:0.742500 +2025-04-19 18:39:15,337 INFO Epoch:80 train_loss:0.54087 +2025-04-19 18:39:23,894 INFO Epoch:80 val_res:0.743500 +2025-04-19 18:39:55,577 INFO Epoch:81 train_loss:0.53761 +2025-04-19 18:40:04,788 INFO Epoch:81 val_res:0.744000 +2025-04-19 18:40:37,890 INFO Epoch:82 train_loss:0.53892 +2025-04-19 18:40:46,160 INFO Epoch:82 val_res:0.744000 +2025-04-19 18:41:21,195 INFO Epoch:83 train_loss:0.53576 +2025-04-19 18:41:29,264 INFO Epoch:83 val_res:0.747000 +2025-04-19 18:42:04,699 INFO Epoch:84 train_loss:0.53429 +2025-04-19 18:42:13,383 INFO Epoch:84 val_res:0.747500 +2025-04-19 18:42:45,783 INFO Epoch:85 train_loss:0.53496 +2025-04-19 18:42:53,992 INFO Epoch:85 val_res:0.749000 +2025-04-19 18:43:25,655 INFO Epoch:86 train_loss:0.53782 +2025-04-19 18:43:33,839 INFO Epoch:86 val_res:0.744000 +2025-04-19 18:44:07,163 INFO Epoch:87 train_loss:0.54589 +2025-04-19 18:44:17,049 INFO Epoch:87 val_res:0.744500 +2025-04-19 18:44:47,694 INFO Epoch:88 train_loss:0.54001 +2025-04-19 18:44:54,356 INFO Epoch:88 val_res:0.745500 +2025-04-19 18:45:25,953 INFO Epoch:89 train_loss:0.54256 +2025-04-19 18:45:33,492 INFO Epoch:89 val_res:0.745500 +2025-04-19 18:46:04,019 INFO Epoch:90 train_loss:0.54182 +2025-04-19 18:46:10,803 INFO Epoch:90 val_res:0.739000 +2025-04-19 18:46:41,803 INFO Epoch:91 train_loss:0.54407 +2025-04-19 18:46:48,457 INFO Epoch:91 val_res:0.745500 +2025-04-19 18:47:19,990 INFO Epoch:92 train_loss:0.54268 +2025-04-19 18:47:26,929 INFO Epoch:92 val_res:0.747000 +2025-04-19 18:47:58,242 INFO Epoch:93 train_loss:0.54135 +2025-04-19 18:48:04,884 INFO Epoch:93 val_res:0.745500 +2025-04-19 18:48:36,255 INFO Epoch:94 train_loss:0.54861 +2025-04-19 18:48:43,308 INFO Epoch:94 val_res:0.741500 +2025-04-19 18:49:14,039 INFO Epoch:95 train_loss:0.57506 +2025-04-19 18:49:21,085 INFO Epoch:95 val_res:0.741000 +2025-04-19 18:49:51,981 INFO Epoch:96 train_loss:0.55084 +2025-04-19 18:49:59,096 INFO Epoch:96 val_res:0.741500 +2025-04-19 18:50:30,303 INFO Epoch:97 train_loss:0.54116 +2025-04-19 18:50:37,490 INFO Epoch:97 val_res:0.742500 +2025-04-19 18:51:07,704 INFO Epoch:98 train_loss:0.53501 +2025-04-19 18:51:14,985 INFO Epoch:98 val_res:0.741500 +2025-04-19 18:51:45,114 INFO Epoch:99 train_loss:0.53772 +2025-04-19 18:51:52,179 INFO Epoch:99 val_res:0.746500 +2025-04-19 18:51:52,394 INFO ===================================== +2025-04-19 18:51:52,395 INFO Start testing... +2025-04-19 18:51:52,395 INFO ===================================== +2025-04-19 18:51:59,093 INFO Incremental step 3 Testing res: 0.729500 +2025-04-19 18:51:59,095 INFO forgetting: 0.134667 +2025-04-19 18:51:59,099 INFO Incremental step: 4 +2025-04-19 18:52:29,474 INFO Epoch:0 train_loss:4.22307 +2025-04-19 18:52:37,350 INFO Epoch:0 val_res:0.588000 +2025-04-19 18:52:37,350 INFO Saving best model at Epoch 0 +2025-04-19 18:53:09,257 INFO Epoch:1 train_loss:1.49317 +2025-04-19 18:53:17,265 INFO Epoch:1 val_res:0.602000 +2025-04-19 18:53:17,265 INFO Saving best model at Epoch 1 +2025-04-19 18:53:52,839 INFO Epoch:2 train_loss:1.06333 +2025-04-19 18:54:02,890 INFO Epoch:2 val_res:0.604400 +2025-04-19 18:54:02,890 INFO Saving best model at Epoch 2 +2025-04-19 18:54:35,655 INFO Epoch:3 train_loss:0.93873 +2025-04-19 18:54:45,606 INFO Epoch:3 val_res:0.608400 +2025-04-19 18:54:45,606 INFO Saving best model at Epoch 3 +2025-04-19 18:55:18,733 INFO Epoch:4 train_loss:0.88196 +2025-04-19 18:55:28,860 INFO Epoch:4 val_res:0.604800 +2025-04-19 18:56:00,435 INFO Epoch:5 train_loss:0.84769 +2025-04-19 18:56:11,022 INFO Epoch:5 val_res:0.606000 +2025-04-19 18:56:46,329 INFO Epoch:6 train_loss:0.82038 +2025-04-19 18:56:56,689 INFO Epoch:6 val_res:0.610000 +2025-04-19 18:56:56,690 INFO Saving best model at Epoch 6 +2025-04-19 18:57:32,979 INFO Epoch:7 train_loss:0.80032 +2025-04-19 18:57:43,721 INFO Epoch:7 val_res:0.611200 +2025-04-19 18:57:43,722 INFO Saving best model at Epoch 7 +2025-04-19 18:58:17,064 INFO Epoch:8 train_loss:0.78022 +2025-04-19 18:58:27,077 INFO Epoch:8 val_res:0.616800 +2025-04-19 18:58:27,077 INFO Saving best model at Epoch 8 +2025-04-19 18:59:03,716 INFO Epoch:9 train_loss:0.76825 +2025-04-19 18:59:15,498 INFO Epoch:9 val_res:0.616400 +2025-04-19 18:59:50,623 INFO Epoch:10 train_loss:0.74936 +2025-04-19 19:00:00,784 INFO Epoch:10 val_res:0.615200 +2025-04-19 19:00:35,293 INFO Epoch:11 train_loss:0.73906 +2025-04-19 19:00:45,705 INFO Epoch:11 val_res:0.616400 +2025-04-19 19:01:17,829 INFO Epoch:12 train_loss:0.72682 +2025-04-19 19:01:27,934 INFO Epoch:12 val_res:0.618400 +2025-04-19 19:01:27,935 INFO Saving best model at Epoch 12 +2025-04-19 19:02:00,030 INFO Epoch:13 train_loss:0.71738 +2025-04-19 19:02:09,726 INFO Epoch:13 val_res:0.621600 +2025-04-19 19:02:09,726 INFO Saving best model at Epoch 13 +2025-04-19 19:02:43,719 INFO Epoch:14 train_loss:0.70760 +2025-04-19 19:02:53,705 INFO Epoch:14 val_res:0.625600 +2025-04-19 19:02:53,705 INFO Saving best model at Epoch 14 +2025-04-19 19:03:26,590 INFO Epoch:15 train_loss:0.70366 +2025-04-19 19:03:36,307 INFO Epoch:15 val_res:0.623200 +2025-04-19 19:04:07,398 INFO Epoch:16 train_loss:0.68650 +2025-04-19 19:04:17,329 INFO Epoch:16 val_res:0.628000 +2025-04-19 19:04:17,330 INFO Saving best model at Epoch 16 +2025-04-19 19:04:54,559 INFO Epoch:17 train_loss:0.68115 +2025-04-19 19:05:05,032 INFO Epoch:17 val_res:0.628800 +2025-04-19 19:05:05,032 INFO Saving best model at Epoch 17 +2025-04-19 19:05:41,873 INFO Epoch:18 train_loss:0.68514 +2025-04-19 19:05:52,113 INFO Epoch:18 val_res:0.633200 +2025-04-19 19:05:52,114 INFO Saving best model at Epoch 18 +2025-04-19 19:06:25,844 INFO Epoch:19 train_loss:0.67832 +2025-04-19 19:06:35,922 INFO Epoch:19 val_res:0.633600 +2025-04-19 19:06:35,922 INFO Saving best model at Epoch 19 +2025-04-19 19:07:13,879 INFO Epoch:20 train_loss:7.24739 +2025-04-19 19:07:24,129 INFO Epoch:20 val_res:0.617600 +2025-04-19 19:08:00,399 INFO Epoch:21 train_loss:3.36747 +2025-04-19 19:08:10,400 INFO Epoch:21 val_res:0.640400 +2025-04-19 19:08:10,401 INFO Saving best model at Epoch 21 +2025-04-19 19:08:52,858 INFO Epoch:22 train_loss:2.28768 +2025-04-19 19:09:03,143 INFO Epoch:22 val_res:0.653600 +2025-04-19 19:09:03,143 INFO Saving best model at Epoch 22 +2025-04-19 19:09:40,995 INFO Epoch:23 train_loss:1.99417 +2025-04-19 19:09:50,395 INFO Epoch:23 val_res:0.650800 +2025-04-19 19:10:26,945 INFO Epoch:24 train_loss:1.86220 +2025-04-19 19:10:37,675 INFO Epoch:24 val_res:0.655200 +2025-04-19 19:10:37,676 INFO Saving best model at Epoch 24 +2025-04-19 19:11:15,401 INFO Epoch:25 train_loss:1.79127 +2025-04-19 19:11:25,647 INFO Epoch:25 val_res:0.655600 +2025-04-19 19:11:25,648 INFO Saving best model at Epoch 25 +2025-04-19 19:12:04,410 INFO Epoch:26 train_loss:1.73751 +2025-04-19 19:12:14,752 INFO Epoch:26 val_res:0.659600 +2025-04-19 19:12:14,752 INFO Saving best model at Epoch 26 +2025-04-19 19:12:50,391 INFO Epoch:27 train_loss:1.68442 +2025-04-19 19:13:00,652 INFO Epoch:27 val_res:0.661600 +2025-04-19 19:13:00,652 INFO Saving best model at Epoch 27 +2025-04-19 19:13:39,480 INFO Epoch:28 train_loss:1.65648 +2025-04-19 19:13:49,999 INFO Epoch:28 val_res:0.669200 +2025-04-19 19:13:49,999 INFO Saving best model at Epoch 28 +2025-04-19 19:14:28,078 INFO Epoch:29 train_loss:1.61888 +2025-04-19 19:14:37,887 INFO Epoch:29 val_res:0.668400 +2025-04-19 19:15:13,340 INFO Epoch:30 train_loss:1.59621 +2025-04-19 19:15:23,299 INFO Epoch:30 val_res:0.670400 +2025-04-19 19:15:23,299 INFO Saving best model at Epoch 30 +2025-04-19 19:15:59,568 INFO Epoch:31 train_loss:1.54040 +2025-04-19 19:16:09,076 INFO Epoch:31 val_res:0.670400 +2025-04-19 19:16:41,623 INFO Epoch:32 train_loss:1.53495 +2025-04-19 19:16:51,753 INFO Epoch:32 val_res:0.670400 +2025-04-19 19:17:26,416 INFO Epoch:33 train_loss:1.49464 +2025-04-19 19:17:36,414 INFO Epoch:33 val_res:0.676800 +2025-04-19 19:17:36,414 INFO Saving best model at Epoch 33 +2025-04-19 19:18:12,849 INFO Epoch:34 train_loss:1.48114 +2025-04-19 19:18:22,697 INFO Epoch:34 val_res:0.672800 +2025-04-19 19:18:56,274 INFO Epoch:35 train_loss:1.46603 +2025-04-19 19:19:06,497 INFO Epoch:35 val_res:0.678400 +2025-04-19 19:19:06,498 INFO Saving best model at Epoch 35 +2025-04-19 19:19:44,052 INFO Epoch:36 train_loss:1.45631 +2025-04-19 19:19:54,142 INFO Epoch:36 val_res:0.683200 +2025-04-19 19:19:54,142 INFO Saving best model at Epoch 36 +2025-04-19 19:20:31,218 INFO Epoch:37 train_loss:1.43474 +2025-04-19 19:20:41,256 INFO Epoch:37 val_res:0.684400 +2025-04-19 19:20:41,256 INFO Saving best model at Epoch 37 +2025-04-19 19:21:16,191 INFO Epoch:38 train_loss:1.43764 +2025-04-19 19:21:25,979 INFO Epoch:38 val_res:0.680000 +2025-04-19 19:22:01,461 INFO Epoch:39 train_loss:1.44178 +2025-04-19 19:22:11,295 INFO Epoch:39 val_res:0.684800 +2025-04-19 19:22:11,296 INFO Saving best model at Epoch 39 +2025-04-19 19:22:45,539 INFO Epoch:40 train_loss:1.42220 +2025-04-19 19:22:56,087 INFO Epoch:40 val_res:0.686800 +2025-04-19 19:22:56,088 INFO Saving best model at Epoch 40 +2025-04-19 19:23:33,442 INFO Epoch:41 train_loss:1.41271 +2025-04-19 19:23:43,085 INFO Epoch:41 val_res:0.690000 +2025-04-19 19:23:43,085 INFO Saving best model at Epoch 41 +2025-04-19 19:24:19,764 INFO Epoch:42 train_loss:1.37598 +2025-04-19 19:24:29,579 INFO Epoch:42 val_res:0.686000 +2025-04-19 19:25:03,926 INFO Epoch:43 train_loss:1.34413 +2025-04-19 19:25:14,421 INFO Epoch:43 val_res:0.684800 +2025-04-19 19:25:49,405 INFO Epoch:44 train_loss:1.36042 +2025-04-19 19:25:59,367 INFO Epoch:44 val_res:0.691600 +2025-04-19 19:25:59,367 INFO Saving best model at Epoch 44 +2025-04-19 19:26:34,329 INFO Epoch:45 train_loss:1.34590 +2025-04-19 19:26:44,108 INFO Epoch:45 val_res:0.684800 +2025-04-19 19:27:19,817 INFO Epoch:46 train_loss:1.34286 +2025-04-19 19:27:29,784 INFO Epoch:46 val_res:0.690400 +2025-04-19 19:28:02,379 INFO Epoch:47 train_loss:1.35141 +2025-04-19 19:28:12,480 INFO Epoch:47 val_res:0.695600 +2025-04-19 19:28:12,480 INFO Saving best model at Epoch 47 +2025-04-19 19:28:50,314 INFO Epoch:48 train_loss:1.31603 +2025-04-19 19:28:59,855 INFO Epoch:48 val_res:0.690400 +2025-04-19 19:29:35,206 INFO Epoch:49 train_loss:1.28772 +2025-04-19 19:29:45,510 INFO Epoch:49 val_res:0.690800 +2025-04-19 19:30:22,270 INFO Epoch:50 train_loss:1.33668 +2025-04-19 19:30:32,340 INFO Epoch:50 val_res:0.692400 +2025-04-19 19:31:07,824 INFO Epoch:51 train_loss:1.30736 +2025-04-19 19:31:17,886 INFO Epoch:51 val_res:0.686000 +2025-04-19 19:31:52,161 INFO Epoch:52 train_loss:1.31599 +2025-04-19 19:32:02,150 INFO Epoch:52 val_res:0.693200 +2025-04-19 19:32:35,424 INFO Epoch:53 train_loss:1.32861 +2025-04-19 19:32:45,211 INFO Epoch:53 val_res:0.692800 +2025-04-19 19:33:19,999 INFO Epoch:54 train_loss:1.27133 +2025-04-19 19:33:30,058 INFO Epoch:54 val_res:0.690800 +2025-04-19 19:34:03,661 INFO Epoch:55 train_loss:1.26611 +2025-04-19 19:34:14,674 INFO Epoch:55 val_res:0.684800 +2025-04-19 19:34:50,591 INFO Epoch:56 train_loss:1.25855 +2025-04-19 19:35:00,458 INFO Epoch:56 val_res:0.687200 +2025-04-19 19:35:32,486 INFO Epoch:57 train_loss:1.24443 +2025-04-19 19:35:42,538 INFO Epoch:57 val_res:0.692800 +2025-04-19 19:36:18,563 INFO Epoch:58 train_loss:1.22129 +2025-04-19 19:36:28,616 INFO Epoch:58 val_res:0.688400 +2025-04-19 19:37:04,541 INFO Epoch:59 train_loss:1.24187 +2025-04-19 19:37:14,602 INFO Epoch:59 val_res:0.695200 +2025-04-19 19:37:48,231 INFO Epoch:60 train_loss:1.22466 +2025-04-19 19:37:58,093 INFO Epoch:60 val_res:0.690800 +2025-04-19 19:38:32,184 INFO Epoch:61 train_loss:1.21756 +2025-04-19 19:38:42,391 INFO Epoch:61 val_res:0.689200 +2025-04-19 19:39:15,288 INFO Epoch:62 train_loss:1.22254 +2025-04-19 19:39:25,115 INFO Epoch:62 val_res:0.687200 +2025-04-19 19:40:01,154 INFO Epoch:63 train_loss:1.20791 +2025-04-19 19:40:10,828 INFO Epoch:63 val_res:0.689600 +2025-04-19 19:40:43,806 INFO Epoch:64 train_loss:1.21026 +2025-04-19 19:40:53,776 INFO Epoch:64 val_res:0.688400 +2025-04-19 19:41:27,921 INFO Epoch:65 train_loss:1.18945 +2025-04-19 19:41:37,786 INFO Epoch:65 val_res:0.694400 +2025-04-19 19:42:11,804 INFO Epoch:66 train_loss:1.24109 +2025-04-19 19:42:21,796 INFO Epoch:66 val_res:0.692800 +2025-04-19 19:42:57,056 INFO Epoch:67 train_loss:1.20649 +2025-04-19 19:43:06,954 INFO Epoch:67 val_res:0.690800 +2025-04-19 19:43:43,427 INFO Epoch:68 train_loss:1.18683 +2025-04-19 19:43:53,465 INFO Epoch:68 val_res:0.691200 +2025-04-19 19:44:29,933 INFO Epoch:69 train_loss:1.17856 +2025-04-19 19:44:39,711 INFO Epoch:69 val_res:0.692400 +2025-04-19 19:45:12,619 INFO Epoch:70 train_loss:1.19100 +2025-04-19 19:45:22,437 INFO Epoch:70 val_res:0.683600 +2025-04-19 19:45:52,568 INFO Epoch:71 train_loss:0.56510 +2025-04-19 19:46:02,324 INFO Epoch:71 val_res:0.692000 +2025-04-19 19:46:34,971 INFO Epoch:72 train_loss:0.53183 +2025-04-19 19:46:44,712 INFO Epoch:72 val_res:0.692000 +2025-04-19 19:47:15,684 INFO Epoch:73 train_loss:0.52497 +2025-04-19 19:47:25,452 INFO Epoch:73 val_res:0.690400 +2025-04-19 19:47:59,804 INFO Epoch:74 train_loss:0.52250 +2025-04-19 19:48:09,618 INFO Epoch:74 val_res:0.693600 +2025-04-19 19:48:39,992 INFO Epoch:75 train_loss:0.51921 +2025-04-19 19:48:50,875 INFO Epoch:75 val_res:0.693600 +2025-04-19 19:49:23,353 INFO Epoch:76 train_loss:0.51904 +2025-04-19 19:49:33,382 INFO Epoch:76 val_res:0.694400 +2025-04-19 19:50:07,782 INFO Epoch:77 train_loss:0.51655 +2025-04-19 19:50:17,806 INFO Epoch:77 val_res:0.693600 +2025-04-19 19:50:54,162 INFO Epoch:78 train_loss:0.52009 +2025-04-19 19:51:04,198 INFO Epoch:78 val_res:0.692400 +2025-04-19 19:51:35,794 INFO Epoch:79 train_loss:0.51653 +2025-04-19 19:51:45,433 INFO Epoch:79 val_res:0.694800 +2025-04-19 19:52:18,838 INFO Epoch:80 train_loss:0.51696 +2025-04-19 19:52:28,609 INFO Epoch:80 val_res:0.692800 +2025-04-19 19:53:00,629 INFO Epoch:81 train_loss:0.51256 +2025-04-19 19:53:12,145 INFO Epoch:81 val_res:0.691600 +2025-04-19 19:53:43,371 INFO Epoch:82 train_loss:0.51497 +2025-04-19 19:53:53,827 INFO Epoch:82 val_res:0.694000 +2025-04-19 19:54:27,941 INFO Epoch:83 train_loss:0.51544 +2025-04-19 19:54:38,497 INFO Epoch:83 val_res:0.692800 +2025-04-19 19:55:09,009 INFO Epoch:84 train_loss:0.51200 +2025-04-19 19:55:21,117 INFO Epoch:84 val_res:0.691200 +2025-04-19 19:55:55,800 INFO Epoch:85 train_loss:0.51342 +2025-04-19 19:56:05,682 INFO Epoch:85 val_res:0.690800 +2025-04-19 19:56:37,244 INFO Epoch:86 train_loss:0.51141 +2025-04-19 19:56:47,040 INFO Epoch:86 val_res:0.692000 +2025-04-19 19:57:19,681 INFO Epoch:87 train_loss:0.51293 +2025-04-19 19:57:29,675 INFO Epoch:87 val_res:0.690800 +2025-04-19 19:58:01,531 INFO Epoch:88 train_loss:0.51174 +2025-04-19 19:58:13,515 INFO Epoch:88 val_res:0.691200 +2025-04-19 19:58:44,201 INFO Epoch:89 train_loss:0.51527 +2025-04-19 19:58:54,381 INFO Epoch:89 val_res:0.693600 +2025-04-19 19:59:26,433 INFO Epoch:90 train_loss:0.51379 +2025-04-19 19:59:36,403 INFO Epoch:90 val_res:0.693600 +2025-04-19 20:00:09,712 INFO Epoch:91 train_loss:0.51443 +2025-04-19 20:00:19,913 INFO Epoch:91 val_res:0.692400 +2025-04-19 20:00:50,658 INFO Epoch:92 train_loss:0.51797 +2025-04-19 20:01:00,482 INFO Epoch:92 val_res:0.695200 +2025-04-19 20:01:32,566 INFO Epoch:93 train_loss:0.52810 +2025-04-19 20:01:43,551 INFO Epoch:93 val_res:0.692800 +2025-04-19 20:02:15,106 INFO Epoch:94 train_loss:0.52729 +2025-04-19 20:02:25,345 INFO Epoch:94 val_res:0.694400 +2025-04-19 20:02:57,328 INFO Epoch:95 train_loss:0.52668 +2025-04-19 20:03:07,543 INFO Epoch:95 val_res:0.693200 +2025-04-19 20:03:39,931 INFO Epoch:96 train_loss:0.51994 +2025-04-19 20:03:49,952 INFO Epoch:96 val_res:0.694000 +2025-04-19 20:04:22,755 INFO Epoch:97 train_loss:0.51290 +2025-04-19 20:04:32,436 INFO Epoch:97 val_res:0.694400 +2025-04-19 20:05:03,090 INFO Epoch:98 train_loss:0.54431 +2025-04-19 20:05:12,707 INFO Epoch:98 val_res:0.690000 +2025-04-19 20:05:47,181 INFO Epoch:99 train_loss:0.55858 +2025-04-19 20:05:57,124 INFO Epoch:99 val_res:0.690800 +2025-04-19 20:05:57,439 INFO ===================================== +2025-04-19 20:05:57,439 INFO Start testing... +2025-04-19 20:05:57,440 INFO ===================================== +2025-04-19 20:06:08,467 INFO Incremental step 4 Testing res: 0.695600 +2025-04-19 20:06:08,476 INFO forgetting: 0.104500 +2025-04-19 20:06:08,481 INFO Incremental step: 5 +2025-04-19 20:06:39,832 INFO Epoch:0 train_loss:4.15914 +2025-04-19 20:06:51,652 INFO Epoch:0 val_res:0.577333 +2025-04-19 20:06:51,653 INFO Saving best model at Epoch 0 +2025-04-19 20:07:24,207 INFO Epoch:1 train_loss:1.49314 +2025-04-19 20:07:36,613 INFO Epoch:1 val_res:0.592000 +2025-04-19 20:07:36,614 INFO Saving best model at Epoch 1 +2025-04-19 20:08:10,479 INFO Epoch:2 train_loss:1.06052 +2025-04-19 20:08:21,628 INFO Epoch:2 val_res:0.601333 +2025-04-19 20:08:21,628 INFO Saving best model at Epoch 2 +2025-04-19 20:08:54,970 INFO Epoch:3 train_loss:0.93978 +2025-04-19 20:09:06,300 INFO Epoch:3 val_res:0.602333 +2025-04-19 20:09:06,301 INFO Saving best model at Epoch 3 +2025-04-19 20:09:40,506 INFO Epoch:4 train_loss:0.90001 +2025-04-19 20:09:52,217 INFO Epoch:4 val_res:0.603667 +2025-04-19 20:09:52,218 INFO Saving best model at Epoch 4 +2025-04-19 20:10:22,878 INFO Epoch:5 train_loss:0.86109 +2025-04-19 20:10:34,596 INFO Epoch:5 val_res:0.603667 +2025-04-19 20:11:04,949 INFO Epoch:6 train_loss:0.84367 +2025-04-19 20:11:16,365 INFO Epoch:6 val_res:0.604333 +2025-04-19 20:11:16,365 INFO Saving best model at Epoch 6 +2025-04-19 20:11:46,226 INFO Epoch:7 train_loss:0.82946 +2025-04-19 20:11:57,935 INFO Epoch:7 val_res:0.605333 +2025-04-19 20:11:57,936 INFO Saving best model at Epoch 7 +2025-04-19 20:12:31,174 INFO Epoch:8 train_loss:0.81344 +2025-04-19 20:12:42,674 INFO Epoch:8 val_res:0.606667 +2025-04-19 20:12:42,674 INFO Saving best model at Epoch 8 +2025-04-19 20:13:13,016 INFO Epoch:9 train_loss:0.80356 +2025-04-19 20:13:25,074 INFO Epoch:9 val_res:0.608333 +2025-04-19 20:13:25,074 INFO Saving best model at Epoch 9 +2025-04-19 20:13:55,805 INFO Epoch:10 train_loss:0.78792 +2025-04-19 20:14:07,144 INFO Epoch:10 val_res:0.610000 +2025-04-19 20:14:07,145 INFO Saving best model at Epoch 10 +2025-04-19 20:14:41,328 INFO Epoch:11 train_loss:0.77816 +2025-04-19 20:14:52,729 INFO Epoch:11 val_res:0.613333 +2025-04-19 20:14:52,730 INFO Saving best model at Epoch 11 +2025-04-19 20:15:26,864 INFO Epoch:12 train_loss:0.76819 +2025-04-19 20:15:38,230 INFO Epoch:12 val_res:0.613667 +2025-04-19 20:15:38,231 INFO Saving best model at Epoch 12 +2025-04-19 20:16:08,744 INFO Epoch:13 train_loss:0.75778 +2025-04-19 20:16:20,495 INFO Epoch:13 val_res:0.612667 +2025-04-19 20:16:50,236 INFO Epoch:14 train_loss:0.75031 +2025-04-19 20:17:01,719 INFO Epoch:14 val_res:0.616667 +2025-04-19 20:17:01,720 INFO Saving best model at Epoch 14 +2025-04-19 20:17:31,183 INFO Epoch:15 train_loss:0.74639 +2025-04-19 20:17:42,766 INFO Epoch:15 val_res:0.618333 +2025-04-19 20:17:42,767 INFO Saving best model at Epoch 15 +2025-04-19 20:18:13,229 INFO Epoch:16 train_loss:0.74149 +2025-04-19 20:18:25,188 INFO Epoch:16 val_res:0.620000 +2025-04-19 20:18:25,188 INFO Saving best model at Epoch 16 +2025-04-19 20:18:56,488 INFO Epoch:17 train_loss:0.73510 +2025-04-19 20:19:07,584 INFO Epoch:17 val_res:0.618333 +2025-04-19 20:19:35,792 INFO Epoch:18 train_loss:0.72354 +2025-04-19 20:19:47,110 INFO Epoch:18 val_res:0.622333 +2025-04-19 20:19:47,111 INFO Saving best model at Epoch 18 +2025-04-19 20:20:18,714 INFO Epoch:19 train_loss:0.73187 +2025-04-19 20:20:30,526 INFO Epoch:19 val_res:0.622667 +2025-04-19 20:20:30,527 INFO Saving best model at Epoch 19 +2025-04-19 20:21:05,502 INFO Epoch:20 train_loss:12.18821 +2025-04-19 20:21:18,349 INFO Epoch:20 val_res:0.578000 +2025-04-19 20:21:51,305 INFO Epoch:21 train_loss:4.38480 +2025-04-19 20:22:03,019 INFO Epoch:21 val_res:0.621000 +2025-04-19 20:22:33,105 INFO Epoch:22 train_loss:2.54978 +2025-04-19 20:22:44,518 INFO Epoch:22 val_res:0.625667 +2025-04-19 20:22:44,518 INFO Saving best model at Epoch 22 +2025-04-19 20:23:16,625 INFO Epoch:23 train_loss:2.06332 +2025-04-19 20:23:27,947 INFO Epoch:23 val_res:0.631667 +2025-04-19 20:23:27,948 INFO Saving best model at Epoch 23 +2025-04-19 20:24:00,284 INFO Epoch:24 train_loss:1.88333 +2025-04-19 20:24:12,308 INFO Epoch:24 val_res:0.638667 +2025-04-19 20:24:12,308 INFO Saving best model at Epoch 24 +2025-04-19 20:24:43,744 INFO Epoch:25 train_loss:1.79870 +2025-04-19 20:24:54,805 INFO Epoch:25 val_res:0.638000 +2025-04-19 20:25:26,417 INFO Epoch:26 train_loss:1.71424 +2025-04-19 20:25:37,828 INFO Epoch:26 val_res:0.639000 +2025-04-19 20:25:37,828 INFO Saving best model at Epoch 26 +2025-04-19 20:26:10,564 INFO Epoch:27 train_loss:1.66494 +2025-04-19 20:26:22,102 INFO Epoch:27 val_res:0.643333 +2025-04-19 20:26:22,102 INFO Saving best model at Epoch 27 +2025-04-19 20:26:53,807 INFO Epoch:28 train_loss:1.63089 +2025-04-19 20:27:05,128 INFO Epoch:28 val_res:0.645000 +2025-04-19 20:27:05,129 INFO Saving best model at Epoch 28 +2025-04-19 20:27:39,817 INFO Epoch:29 train_loss:1.59114 +2025-04-19 20:27:51,062 INFO Epoch:29 val_res:0.646333 +2025-04-19 20:27:51,063 INFO Saving best model at Epoch 29 +2025-04-19 20:28:24,348 INFO Epoch:30 train_loss:1.58575 +2025-04-19 20:28:35,944 INFO Epoch:30 val_res:0.645333 +2025-04-19 20:29:09,111 INFO Epoch:31 train_loss:1.55701 +2025-04-19 20:29:20,459 INFO Epoch:31 val_res:0.650333 +2025-04-19 20:29:20,459 INFO Saving best model at Epoch 31 +2025-04-19 20:29:52,296 INFO Epoch:32 train_loss:1.52988 +2025-04-19 20:30:03,504 INFO Epoch:32 val_res:0.651667 +2025-04-19 20:30:03,504 INFO Saving best model at Epoch 32 +2025-04-19 20:30:34,822 INFO Epoch:33 train_loss:1.51084 +2025-04-19 20:30:45,977 INFO Epoch:33 val_res:0.648667 +2025-04-19 20:31:15,903 INFO Epoch:34 train_loss:1.48948 +2025-04-19 20:31:27,558 INFO Epoch:34 val_res:0.648333 +2025-04-19 20:31:58,919 INFO Epoch:35 train_loss:1.45468 +2025-04-19 20:32:10,528 INFO Epoch:35 val_res:0.649333 +2025-04-19 20:32:40,474 INFO Epoch:36 train_loss:1.46122 +2025-04-19 20:32:52,143 INFO Epoch:36 val_res:0.652000 +2025-04-19 20:32:52,143 INFO Saving best model at Epoch 36 +2025-04-19 20:33:23,290 INFO Epoch:37 train_loss:1.44488 +2025-04-19 20:33:34,666 INFO Epoch:37 val_res:0.655667 +2025-04-19 20:33:34,666 INFO Saving best model at Epoch 37 +2025-04-19 20:34:08,892 INFO Epoch:38 train_loss:1.43537 +2025-04-19 20:34:20,489 INFO Epoch:38 val_res:0.656333 +2025-04-19 20:34:20,490 INFO Saving best model at Epoch 38 +2025-04-19 20:34:53,873 INFO Epoch:39 train_loss:1.41234 +2025-04-19 20:35:05,500 INFO Epoch:39 val_res:0.656333 +2025-04-19 20:35:35,451 INFO Epoch:40 train_loss:1.39228 +2025-04-19 20:35:47,123 INFO Epoch:40 val_res:0.657667 +2025-04-19 20:35:47,123 INFO Saving best model at Epoch 40 +2025-04-19 20:36:20,055 INFO Epoch:41 train_loss:1.38705 +2025-04-19 20:36:31,281 INFO Epoch:41 val_res:0.656333 +2025-04-19 20:37:03,402 INFO Epoch:42 train_loss:1.38125 +2025-04-19 20:37:14,846 INFO Epoch:42 val_res:0.655667 +2025-04-19 20:37:46,000 INFO Epoch:43 train_loss:1.36931 +2025-04-19 20:37:57,290 INFO Epoch:43 val_res:0.658667 +2025-04-19 20:37:57,290 INFO Saving best model at Epoch 43 +2025-04-19 20:38:31,980 INFO Epoch:44 train_loss:1.33979 +2025-04-19 20:38:44,047 INFO Epoch:44 val_res:0.656333 +2025-04-19 20:39:14,424 INFO Epoch:45 train_loss:1.34987 +2025-04-19 20:39:26,086 INFO Epoch:45 val_res:0.657667 +2025-04-19 20:39:58,112 INFO Epoch:46 train_loss:1.33414 +2025-04-19 20:40:09,695 INFO Epoch:46 val_res:0.655333 +2025-04-19 20:40:40,302 INFO Epoch:47 train_loss:1.33120 +2025-04-19 20:40:51,753 INFO Epoch:47 val_res:0.661667 +2025-04-19 20:40:51,753 INFO Saving best model at Epoch 47 +2025-04-19 20:41:23,729 INFO Epoch:48 train_loss:1.31489 +2025-04-19 20:41:35,650 INFO Epoch:48 val_res:0.661333 +2025-04-19 20:42:08,130 INFO Epoch:49 train_loss:1.30261 +2025-04-19 20:42:19,587 INFO Epoch:49 val_res:0.659000 +2025-04-19 20:42:51,898 INFO Epoch:50 train_loss:1.29344 +2025-04-19 20:43:04,650 INFO Epoch:50 val_res:0.656333 +2025-04-19 20:43:35,078 INFO Epoch:51 train_loss:1.29509 +2025-04-19 20:43:46,420 INFO Epoch:51 val_res:0.659000 +2025-04-19 20:44:16,745 INFO Epoch:52 train_loss:1.27872 +2025-04-19 20:44:28,487 INFO Epoch:52 val_res:0.660333 +2025-04-19 20:44:58,200 INFO Epoch:53 train_loss:1.31201 +2025-04-19 20:45:10,614 INFO Epoch:53 val_res:0.655333 +2025-04-19 20:45:43,569 INFO Epoch:54 train_loss:1.30762 +2025-04-19 20:45:55,442 INFO Epoch:54 val_res:0.658667 +2025-04-19 20:46:26,988 INFO Epoch:55 train_loss:1.28517 +2025-04-19 20:46:38,312 INFO Epoch:55 val_res:0.657000 +2025-04-19 20:47:08,596 INFO Epoch:56 train_loss:1.28112 +2025-04-19 20:47:19,868 INFO Epoch:56 val_res:0.655333 +2025-04-19 20:47:50,220 INFO Epoch:57 train_loss:1.29090 +2025-04-19 20:48:02,191 INFO Epoch:57 val_res:0.657333 +2025-04-19 20:48:33,547 INFO Epoch:58 train_loss:1.29009 +2025-04-19 20:48:45,045 INFO Epoch:58 val_res:0.657333 +2025-04-19 20:49:15,027 INFO Epoch:59 train_loss:1.28263 +2025-04-19 20:49:26,763 INFO Epoch:59 val_res:0.657000 +2025-04-19 20:49:56,296 INFO Epoch:60 train_loss:1.24800 +2025-04-19 20:50:08,518 INFO Epoch:60 val_res:0.659000 +2025-04-19 20:50:39,528 INFO Epoch:61 train_loss:1.22621 +2025-04-19 20:50:51,139 INFO Epoch:61 val_res:0.659667 +2025-04-19 20:51:23,184 INFO Epoch:62 train_loss:1.22576 +2025-04-19 20:51:36,293 INFO Epoch:62 val_res:0.655000 +2025-04-19 20:52:07,007 INFO Epoch:63 train_loss:1.23451 +2025-04-19 20:52:19,114 INFO Epoch:63 val_res:0.656000 +2025-04-19 20:52:49,790 INFO Epoch:64 train_loss:1.22979 +2025-04-19 20:53:02,578 INFO Epoch:64 val_res:0.657667 +2025-04-19 20:53:33,977 INFO Epoch:65 train_loss:1.24139 +2025-04-19 20:53:47,884 INFO Epoch:65 val_res:0.653667 +2025-04-19 20:54:20,372 INFO Epoch:66 train_loss:1.21585 +2025-04-19 20:54:32,186 INFO Epoch:66 val_res:0.657333 +2025-04-19 20:55:02,234 INFO Epoch:67 train_loss:1.22267 +2025-04-19 20:55:13,649 INFO Epoch:67 val_res:0.653667 +2025-04-19 20:55:44,423 INFO Epoch:68 train_loss:1.21480 +2025-04-19 20:55:55,599 INFO Epoch:68 val_res:0.657333 +2025-04-19 20:56:26,906 INFO Epoch:69 train_loss:1.24475 +2025-04-19 20:56:38,259 INFO Epoch:69 val_res:0.652333 +2025-04-19 20:57:08,350 INFO Epoch:70 train_loss:1.25704 +2025-04-19 20:57:19,559 INFO Epoch:70 val_res:0.658333 +2025-04-19 20:57:48,218 INFO Epoch:71 train_loss:0.60625 +2025-04-19 20:57:59,555 INFO Epoch:71 val_res:0.654333 +2025-04-19 20:58:29,308 INFO Epoch:72 train_loss:0.58462 +2025-04-19 20:58:41,944 INFO Epoch:72 val_res:0.654333 +2025-04-19 20:59:13,728 INFO Epoch:73 train_loss:0.58430 +2025-04-19 20:59:25,436 INFO Epoch:73 val_res:0.654333 +2025-04-19 20:59:54,607 INFO Epoch:74 train_loss:0.58401 +2025-04-19 21:00:06,384 INFO Epoch:74 val_res:0.654000 +2025-04-19 21:00:37,046 INFO Epoch:75 train_loss:0.58205 +2025-04-19 21:00:49,356 INFO Epoch:75 val_res:0.653333 +2025-04-19 21:01:20,158 INFO Epoch:76 train_loss:0.58220 +2025-04-19 21:01:31,822 INFO Epoch:76 val_res:0.654000 +2025-04-19 21:02:01,861 INFO Epoch:77 train_loss:0.57937 +2025-04-19 21:02:14,111 INFO Epoch:77 val_res:0.653333 +2025-04-19 21:02:45,790 INFO Epoch:78 train_loss:0.58236 +2025-04-19 21:02:57,291 INFO Epoch:78 val_res:0.654333 +2025-04-19 21:03:29,007 INFO Epoch:79 train_loss:0.57591 +2025-04-19 21:03:40,924 INFO Epoch:79 val_res:0.653667 +2025-04-19 21:04:10,616 INFO Epoch:80 train_loss:0.57963 +2025-04-19 21:04:22,393 INFO Epoch:80 val_res:0.652333 +2025-04-19 21:04:52,552 INFO Epoch:81 train_loss:0.57906 +2025-04-19 21:05:04,198 INFO Epoch:81 val_res:0.652667 +2025-04-19 21:05:33,780 INFO Epoch:82 train_loss:0.57662 +2025-04-19 21:05:45,274 INFO Epoch:82 val_res:0.651000 +2025-04-19 21:06:16,273 INFO Epoch:83 train_loss:0.57348 +2025-04-19 21:06:27,995 INFO Epoch:83 val_res:0.651000 +2025-04-19 21:07:00,475 INFO Epoch:84 train_loss:0.57821 +2025-04-19 21:07:12,043 INFO Epoch:84 val_res:0.652333 +2025-04-19 21:07:40,882 INFO Epoch:85 train_loss:0.57535 +2025-04-19 21:07:52,587 INFO Epoch:85 val_res:0.650333 +2025-04-19 21:08:22,606 INFO Epoch:86 train_loss:0.58283 +2025-04-19 21:08:35,063 INFO Epoch:86 val_res:0.651333 +2025-04-19 21:09:07,276 INFO Epoch:87 train_loss:0.57514 +2025-04-19 21:09:19,461 INFO Epoch:87 val_res:0.649667 +2025-04-19 21:09:49,251 INFO Epoch:88 train_loss:0.57623 +2025-04-19 21:10:00,818 INFO Epoch:88 val_res:0.650000 +2025-04-19 21:10:29,991 INFO Epoch:89 train_loss:0.57757 +2025-04-19 21:10:41,733 INFO Epoch:89 val_res:0.651000 +2025-04-19 21:11:13,569 INFO Epoch:90 train_loss:0.57525 +2025-04-19 21:11:25,903 INFO Epoch:90 val_res:0.648667 +2025-04-19 21:11:55,623 INFO Epoch:91 train_loss:0.57361 +2025-04-19 21:12:07,802 INFO Epoch:91 val_res:0.650333 +2025-04-19 21:12:38,554 INFO Epoch:92 train_loss:0.57335 +2025-04-19 21:12:50,101 INFO Epoch:92 val_res:0.653000 +2025-04-19 21:13:20,126 INFO Epoch:93 train_loss:0.57614 +2025-04-19 21:13:31,766 INFO Epoch:93 val_res:0.650667 +2025-04-19 21:14:03,036 INFO Epoch:94 train_loss:0.57293 +2025-04-19 21:14:14,604 INFO Epoch:94 val_res:0.652333 +2025-04-19 21:14:45,129 INFO Epoch:95 train_loss:0.57475 +2025-04-19 21:14:56,857 INFO Epoch:95 val_res:0.648333 +2025-04-19 21:15:26,740 INFO Epoch:96 train_loss:0.57146 +2025-04-19 21:15:38,379 INFO Epoch:96 val_res:0.649667 +2025-04-19 21:16:09,134 INFO Epoch:97 train_loss:0.57057 +2025-04-19 21:16:20,623 INFO Epoch:97 val_res:0.649667 +2025-04-19 21:16:51,853 INFO Epoch:98 train_loss:0.56949 +2025-04-19 21:17:03,166 INFO Epoch:98 val_res:0.650333 +2025-04-19 21:17:32,827 INFO Epoch:99 train_loss:0.57643 +2025-04-19 21:17:44,827 INFO Epoch:99 val_res:0.649000 +2025-04-19 21:17:45,235 INFO ===================================== +2025-04-19 21:17:45,235 INFO Start testing... +2025-04-19 21:17:45,235 INFO ===================================== +2025-04-19 21:17:58,200 INFO Incremental step 5 Testing res: 0.653333 +2025-04-19 21:17:58,203 INFO forgetting: 0.089200 +2025-04-19 21:17:58,206 INFO Incremental step: 6 +2025-04-19 21:18:30,276 INFO Epoch:0 train_loss:4.32725 +2025-04-19 21:18:43,754 INFO Epoch:0 val_res:0.556286 +2025-04-19 21:18:43,754 INFO Saving best model at Epoch 0 +2025-04-19 21:19:17,990 INFO Epoch:1 train_loss:1.39223 +2025-04-19 21:19:30,852 INFO Epoch:1 val_res:0.574286 +2025-04-19 21:19:30,859 INFO Saving best model at Epoch 1 +2025-04-19 21:20:05,756 INFO Epoch:2 train_loss:0.95617 +2025-04-19 21:20:19,849 INFO Epoch:2 val_res:0.580000 +2025-04-19 21:20:19,850 INFO Saving best model at Epoch 2 +2025-04-19 21:20:54,752 INFO Epoch:3 train_loss:0.84715 +2025-04-19 21:21:08,347 INFO Epoch:3 val_res:0.584000 +2025-04-19 21:21:08,348 INFO Saving best model at Epoch 3 +2025-04-19 21:21:40,343 INFO Epoch:4 train_loss:0.80744 +2025-04-19 21:21:53,581 INFO Epoch:4 val_res:0.583714 +2025-04-19 21:22:25,719 INFO Epoch:5 train_loss:0.77405 +2025-04-19 21:22:39,500 INFO Epoch:5 val_res:0.588286 +2025-04-19 21:22:39,501 INFO Saving best model at Epoch 5 +2025-04-19 21:23:15,391 INFO Epoch:6 train_loss:0.75860 +2025-04-19 21:23:28,756 INFO Epoch:6 val_res:0.588571 +2025-04-19 21:23:28,756 INFO Saving best model at Epoch 6 +2025-04-19 21:24:03,677 INFO Epoch:7 train_loss:0.74132 +2025-04-19 21:24:16,783 INFO Epoch:7 val_res:0.589429 +2025-04-19 21:24:16,784 INFO Saving best model at Epoch 7 +2025-04-19 21:24:51,472 INFO Epoch:8 train_loss:0.73483 +2025-04-19 21:25:04,432 INFO Epoch:8 val_res:0.590286 +2025-04-19 21:25:04,432 INFO Saving best model at Epoch 8 +2025-04-19 21:25:40,413 INFO Epoch:9 train_loss:0.71839 +2025-04-19 21:25:53,564 INFO Epoch:9 val_res:0.592286 +2025-04-19 21:25:53,565 INFO Saving best model at Epoch 9 +2025-04-19 21:26:26,010 INFO Epoch:10 train_loss:0.71344 +2025-04-19 21:26:38,689 INFO Epoch:10 val_res:0.591429 +2025-04-19 21:27:08,200 INFO Epoch:11 train_loss:0.70097 +2025-04-19 21:27:21,396 INFO Epoch:11 val_res:0.596857 +2025-04-19 21:27:21,397 INFO Saving best model at Epoch 11 +2025-04-19 21:27:55,784 INFO Epoch:12 train_loss:0.69772 +2025-04-19 21:28:09,033 INFO Epoch:12 val_res:0.597429 +2025-04-19 21:28:09,033 INFO Saving best model at Epoch 12 +2025-04-19 21:28:43,627 INFO Epoch:13 train_loss:0.69111 +2025-04-19 21:28:58,855 INFO Epoch:13 val_res:0.599714 +2025-04-19 21:28:58,855 INFO Saving best model at Epoch 13 +2025-04-19 21:29:32,506 INFO Epoch:14 train_loss:0.68246 +2025-04-19 21:29:45,154 INFO Epoch:14 val_res:0.598571 +2025-04-19 21:30:16,725 INFO Epoch:15 train_loss:0.68389 +2025-04-19 21:30:29,717 INFO Epoch:15 val_res:0.601714 +2025-04-19 21:30:29,717 INFO Saving best model at Epoch 15 +2025-04-19 21:31:03,142 INFO Epoch:16 train_loss:0.67515 +2025-04-19 21:31:16,621 INFO Epoch:16 val_res:0.602286 +2025-04-19 21:31:16,627 INFO Saving best model at Epoch 16 +2025-04-19 21:31:50,965 INFO Epoch:17 train_loss:0.68695 +2025-04-19 21:32:03,743 INFO Epoch:17 val_res:0.605143 +2025-04-19 21:32:03,743 INFO Saving best model at Epoch 17 +2025-04-19 21:32:39,297 INFO Epoch:18 train_loss:0.67617 +2025-04-19 21:32:52,277 INFO Epoch:18 val_res:0.607143 +2025-04-19 21:32:52,277 INFO Saving best model at Epoch 18 +2025-04-19 21:33:24,039 INFO Epoch:19 train_loss:0.65582 +2025-04-19 21:33:36,821 INFO Epoch:19 val_res:0.610286 +2025-04-19 21:33:36,822 INFO Saving best model at Epoch 19 +2025-04-19 21:34:12,335 INFO Epoch:20 train_loss:9.32540 +2025-04-19 21:34:25,753 INFO Epoch:20 val_res:0.588571 +2025-04-19 21:34:59,880 INFO Epoch:21 train_loss:3.38001 +2025-04-19 21:35:12,596 INFO Epoch:21 val_res:0.615429 +2025-04-19 21:35:12,596 INFO Saving best model at Epoch 21 +2025-04-19 21:35:48,635 INFO Epoch:22 train_loss:2.11860 +2025-04-19 21:36:01,410 INFO Epoch:22 val_res:0.622286 +2025-04-19 21:36:01,411 INFO Saving best model at Epoch 22 +2025-04-19 21:36:35,188 INFO Epoch:23 train_loss:1.80232 +2025-04-19 21:36:48,635 INFO Epoch:23 val_res:0.626571 +2025-04-19 21:36:48,635 INFO Saving best model at Epoch 23 +2025-04-19 21:37:23,535 INFO Epoch:24 train_loss:1.67405 +2025-04-19 21:37:37,114 INFO Epoch:24 val_res:0.626000 +2025-04-19 21:38:11,525 INFO Epoch:25 train_loss:1.60827 +2025-04-19 21:38:24,441 INFO Epoch:25 val_res:0.630286 +2025-04-19 21:38:24,442 INFO Saving best model at Epoch 25 +2025-04-19 21:39:01,214 INFO Epoch:26 train_loss:1.55787 +2025-04-19 21:39:14,315 INFO Epoch:26 val_res:0.628571 +2025-04-19 21:39:46,277 INFO Epoch:27 train_loss:1.51039 +2025-04-19 21:39:59,731 INFO Epoch:27 val_res:0.633714 +2025-04-19 21:39:59,731 INFO Saving best model at Epoch 27 +2025-04-19 21:40:35,823 INFO Epoch:28 train_loss:1.50312 +2025-04-19 21:40:48,671 INFO Epoch:28 val_res:0.634000 +2025-04-19 21:40:48,671 INFO Saving best model at Epoch 28 +2025-04-19 21:41:24,950 INFO Epoch:29 train_loss:1.46877 +2025-04-19 21:41:38,481 INFO Epoch:29 val_res:0.635714 +2025-04-19 21:41:38,481 INFO Saving best model at Epoch 29 +2025-04-19 21:42:12,804 INFO Epoch:30 train_loss:1.44470 +2025-04-19 21:42:26,278 INFO Epoch:30 val_res:0.637714 +2025-04-19 21:42:26,278 INFO Saving best model at Epoch 30 +2025-04-19 21:43:02,473 INFO Epoch:31 train_loss:1.43599 +2025-04-19 21:43:15,928 INFO Epoch:31 val_res:0.638571 +2025-04-19 21:43:15,929 INFO Saving best model at Epoch 31 +2025-04-19 21:43:52,317 INFO Epoch:32 train_loss:1.41851 +2025-04-19 21:44:05,492 INFO Epoch:32 val_res:0.642571 +2025-04-19 21:44:05,493 INFO Saving best model at Epoch 32 +2025-04-19 21:44:39,563 INFO Epoch:33 train_loss:1.39429 +2025-04-19 21:44:52,968 INFO Epoch:33 val_res:0.644286 +2025-04-19 21:44:52,968 INFO Saving best model at Epoch 33 +2025-04-19 21:45:28,196 INFO Epoch:34 train_loss:1.38004 +2025-04-19 21:45:41,123 INFO Epoch:34 val_res:0.642857 +2025-04-19 21:46:15,185 INFO Epoch:35 train_loss:1.36475 +2025-04-19 21:46:28,803 INFO Epoch:35 val_res:0.644571 +2025-04-19 21:46:28,803 INFO Saving best model at Epoch 35 +2025-04-19 21:47:03,982 INFO Epoch:36 train_loss:1.37928 +2025-04-19 21:47:16,859 INFO Epoch:36 val_res:0.643429 +2025-04-19 21:47:48,600 INFO Epoch:37 train_loss:1.37556 +2025-04-19 21:48:01,775 INFO Epoch:37 val_res:0.644286 +2025-04-19 21:48:35,799 INFO Epoch:38 train_loss:1.34309 +2025-04-19 21:48:49,175 INFO Epoch:38 val_res:0.647429 +2025-04-19 21:48:49,176 INFO Saving best model at Epoch 38 +2025-04-19 21:49:24,361 INFO Epoch:39 train_loss:1.32209 +2025-04-19 21:49:36,902 INFO Epoch:39 val_res:0.649429 +2025-04-19 21:49:36,902 INFO Saving best model at Epoch 39 +2025-04-19 21:50:12,466 INFO Epoch:40 train_loss:1.32409 +2025-04-19 21:50:25,877 INFO Epoch:40 val_res:0.648571 +2025-04-19 21:50:57,380 INFO Epoch:41 train_loss:1.30605 +2025-04-19 21:51:13,451 INFO Epoch:41 val_res:0.648857 +2025-04-19 21:51:46,765 INFO Epoch:42 train_loss:1.30398 +2025-04-19 21:51:59,553 INFO Epoch:42 val_res:0.649429 +2025-04-19 21:52:33,902 INFO Epoch:43 train_loss:1.32238 +2025-04-19 21:52:46,821 INFO Epoch:43 val_res:0.650286 +2025-04-19 21:52:46,821 INFO Saving best model at Epoch 43 +2025-04-19 21:53:22,703 INFO Epoch:44 train_loss:1.31380 +2025-04-19 21:53:35,637 INFO Epoch:44 val_res:0.651429 +2025-04-19 21:53:35,638 INFO Saving best model at Epoch 44 +2025-04-19 21:54:08,758 INFO Epoch:45 train_loss:1.29602 +2025-04-19 21:54:22,191 INFO Epoch:45 val_res:0.650571 +2025-04-19 21:54:55,015 INFO Epoch:46 train_loss:1.26749 +2025-04-19 21:55:08,424 INFO Epoch:46 val_res:0.650000 +2025-04-19 21:55:42,749 INFO Epoch:47 train_loss:1.26893 +2025-04-19 21:55:55,604 INFO Epoch:47 val_res:0.649429 +2025-04-19 21:56:29,244 INFO Epoch:48 train_loss:1.25773 +2025-04-19 21:56:41,948 INFO Epoch:48 val_res:0.649714 +2025-04-19 21:57:13,338 INFO Epoch:49 train_loss:1.28999 +2025-04-19 21:57:26,016 INFO Epoch:49 val_res:0.650857 +2025-04-19 21:57:58,879 INFO Epoch:50 train_loss:1.30237 +2025-04-19 21:58:11,490 INFO Epoch:50 val_res:0.652571 +2025-04-19 21:58:11,490 INFO Saving best model at Epoch 50 +2025-04-19 21:58:46,996 INFO Epoch:51 train_loss:1.26739 +2025-04-19 21:59:00,090 INFO Epoch:51 val_res:0.652286 +2025-04-19 21:59:32,512 INFO Epoch:52 train_loss:1.25840 +2025-04-19 21:59:45,669 INFO Epoch:52 val_res:0.652857 +2025-04-19 21:59:45,669 INFO Saving best model at Epoch 52 +2025-04-19 22:00:20,311 INFO Epoch:53 train_loss:1.23833 +2025-04-19 22:00:33,004 INFO Epoch:53 val_res:0.653143 +2025-04-19 22:00:33,004 INFO Saving best model at Epoch 53 +2025-04-19 22:01:08,125 INFO Epoch:54 train_loss:1.24070 +2025-04-19 22:01:20,882 INFO Epoch:54 val_res:0.653714 +2025-04-19 22:01:20,883 INFO Saving best model at Epoch 54 +2025-04-19 22:01:55,580 INFO Epoch:55 train_loss:1.22897 +2025-04-19 22:02:09,707 INFO Epoch:55 val_res:0.648571 +2025-04-19 22:02:43,344 INFO Epoch:56 train_loss:1.22996 +2025-04-19 22:02:58,066 INFO Epoch:56 val_res:0.653714 +2025-04-19 22:03:32,111 INFO Epoch:57 train_loss:1.23276 +2025-04-19 22:03:45,317 INFO Epoch:57 val_res:0.649143 +2025-04-19 22:04:21,245 INFO Epoch:58 train_loss:1.22766 +2025-04-19 22:04:35,358 INFO Epoch:58 val_res:0.649429 +2025-04-19 22:05:06,269 INFO Epoch:59 train_loss:1.21271 +2025-04-19 22:05:20,523 INFO Epoch:59 val_res:0.650000 +2025-04-19 22:05:52,051 INFO Epoch:60 train_loss:1.29851 +2025-04-19 22:06:04,347 INFO Epoch:60 val_res:0.652286 +2025-04-19 22:06:33,872 INFO Epoch:61 train_loss:1.26724 +2025-04-19 22:06:46,222 INFO Epoch:61 val_res:0.650000 +2025-04-19 22:07:18,855 INFO Epoch:62 train_loss:1.24948 +2025-04-19 22:07:31,191 INFO Epoch:62 val_res:0.652571 +2025-04-19 22:08:05,355 INFO Epoch:63 train_loss:1.19526 +2025-04-19 22:08:17,983 INFO Epoch:63 val_res:0.652571 +2025-04-19 22:08:51,293 INFO Epoch:64 train_loss:1.21808 +2025-04-19 22:09:03,759 INFO Epoch:64 val_res:0.648286 +2025-04-19 22:09:38,211 INFO Epoch:65 train_loss:1.20291 +2025-04-19 22:09:51,804 INFO Epoch:65 val_res:0.645714 +2025-04-19 22:10:22,804 INFO Epoch:66 train_loss:1.19377 +2025-04-19 22:10:35,172 INFO Epoch:66 val_res:0.645429 +2025-04-19 22:11:07,365 INFO Epoch:67 train_loss:1.20556 +2025-04-19 22:11:22,130 INFO Epoch:67 val_res:0.646857 +2025-04-19 22:11:52,056 INFO Epoch:68 train_loss:1.23668 +2025-04-19 22:12:05,005 INFO Epoch:68 val_res:0.646857 +2025-04-19 22:12:34,539 INFO Epoch:69 train_loss:1.20069 +2025-04-19 22:12:46,749 INFO Epoch:69 val_res:0.645143 +2025-04-19 22:13:20,771 INFO Epoch:70 train_loss:1.18373 +2025-04-19 22:13:33,383 INFO Epoch:70 val_res:0.647429 +2025-04-19 22:14:02,744 INFO Epoch:71 train_loss:0.57469 +2025-04-19 22:14:13,028 INFO Epoch:71 val_res:0.651429 +2025-04-19 22:14:40,721 INFO Epoch:72 train_loss:0.55176 +2025-04-19 22:14:53,790 INFO Epoch:72 val_res:0.646000 +2025-04-19 22:15:23,024 INFO Epoch:73 train_loss:0.54969 +2025-04-19 22:15:36,766 INFO Epoch:73 val_res:0.646857 +2025-04-19 22:16:09,613 INFO Epoch:74 train_loss:0.55078 +2025-04-19 22:16:23,870 INFO Epoch:74 val_res:0.647714 +2025-04-19 22:16:52,561 INFO Epoch:75 train_loss:0.54450 +2025-04-19 22:17:06,533 INFO Epoch:75 val_res:0.643429 +2025-04-19 22:17:35,142 INFO Epoch:76 train_loss:0.54480 +2025-04-19 22:17:50,458 INFO Epoch:76 val_res:0.648286 +2025-04-19 22:18:19,181 INFO Epoch:77 train_loss:0.54416 +2025-04-19 22:18:33,238 INFO Epoch:77 val_res:0.647143 +2025-04-19 22:19:02,789 INFO Epoch:78 train_loss:0.54369 +2025-04-19 22:19:16,847 INFO Epoch:78 val_res:0.646857 +2025-04-19 22:19:45,008 INFO Epoch:79 train_loss:0.54389 +2025-04-19 22:19:58,176 INFO Epoch:79 val_res:0.645714 +2025-04-19 22:20:27,572 INFO Epoch:80 train_loss:0.54417 +2025-04-19 22:20:40,624 INFO Epoch:80 val_res:0.644857 +2025-04-19 22:21:11,088 INFO Epoch:81 train_loss:0.54346 +2025-04-19 22:21:23,633 INFO Epoch:81 val_res:0.645143 +2025-04-19 22:21:53,509 INFO Epoch:82 train_loss:0.54353 +2025-04-19 22:22:05,191 INFO Epoch:82 val_res:0.649143 +2025-04-19 22:22:33,909 INFO Epoch:83 train_loss:0.54046 +2025-04-19 22:22:46,425 INFO Epoch:83 val_res:0.645143 +2025-04-19 22:23:18,263 INFO Epoch:84 train_loss:0.54095 +2025-04-19 22:23:30,658 INFO Epoch:84 val_res:0.643143 +2025-04-19 22:24:02,008 INFO Epoch:85 train_loss:0.53888 +2025-04-19 22:24:14,161 INFO Epoch:85 val_res:0.645143 +2025-04-19 22:24:42,700 INFO Epoch:86 train_loss:0.54000 +2025-04-19 22:24:53,339 INFO Epoch:86 val_res:0.645429 +2025-04-19 22:25:21,196 INFO Epoch:87 train_loss:0.54022 +2025-04-19 22:25:34,224 INFO Epoch:87 val_res:0.641429 +2025-04-19 22:26:02,439 INFO Epoch:88 train_loss:0.54109 +2025-04-19 22:26:16,839 INFO Epoch:88 val_res:0.639714 +2025-04-19 22:26:45,620 INFO Epoch:89 train_loss:0.53925 +2025-04-19 22:26:58,274 INFO Epoch:89 val_res:0.643429 +2025-04-19 22:27:26,761 INFO Epoch:90 train_loss:0.53700 +2025-04-19 22:27:39,756 INFO Epoch:90 val_res:0.645714 +2025-04-19 22:28:08,293 INFO Epoch:91 train_loss:0.53864 +2025-04-19 22:28:20,863 INFO Epoch:91 val_res:0.642000 +2025-04-19 22:28:49,539 INFO Epoch:92 train_loss:0.54070 +2025-04-19 22:29:02,468 INFO Epoch:92 val_res:0.641714 +2025-04-19 22:29:34,957 INFO Epoch:93 train_loss:0.53643 +2025-04-19 22:29:49,920 INFO Epoch:93 val_res:0.643429 +2025-04-19 22:30:21,947 INFO Epoch:94 train_loss:0.54024 +2025-04-19 22:30:34,928 INFO Epoch:94 val_res:0.643143 +2025-04-19 22:31:04,300 INFO Epoch:95 train_loss:0.53726 +2025-04-19 22:31:17,127 INFO Epoch:95 val_res:0.646286 +2025-04-19 22:31:49,322 INFO Epoch:96 train_loss:0.54574 +2025-04-19 22:32:02,742 INFO Epoch:96 val_res:0.643429 +2025-04-19 22:32:33,855 INFO Epoch:97 train_loss:0.55419 +2025-04-19 22:32:46,782 INFO Epoch:97 val_res:0.639143 +2025-04-19 22:33:17,826 INFO Epoch:98 train_loss:0.56135 +2025-04-19 22:33:30,423 INFO Epoch:98 val_res:0.643143 +2025-04-19 22:34:01,191 INFO Epoch:99 train_loss:0.54436 +2025-04-19 22:34:13,730 INFO Epoch:99 val_res:0.642000 +2025-04-19 22:34:13,975 INFO ===================================== +2025-04-19 22:34:13,975 INFO Start testing... +2025-04-19 22:34:13,975 INFO ===================================== +2025-04-19 22:34:30,920 INFO Incremental step 6 Testing res: 0.649714 +2025-04-19 22:34:30,923 INFO forgetting: 0.082000 +2025-04-19 22:34:30,928 INFO Incremental step: 7 +2025-04-19 22:35:10,207 INFO Epoch:0 train_loss:3.49158 +2025-04-19 22:35:24,477 INFO Epoch:0 val_res:0.568000 +2025-04-19 22:35:24,477 INFO Saving best model at Epoch 0 +2025-04-19 22:36:02,614 INFO Epoch:1 train_loss:1.17282 +2025-04-19 22:36:19,479 INFO Epoch:1 val_res:0.576000 +2025-04-19 22:36:19,479 INFO Saving best model at Epoch 1 +2025-04-19 22:36:59,776 INFO Epoch:2 train_loss:0.94051 +2025-04-19 22:37:14,370 INFO Epoch:2 val_res:0.576750 +2025-04-19 22:37:14,370 INFO Saving best model at Epoch 2 +2025-04-19 22:37:53,068 INFO Epoch:3 train_loss:0.87592 +2025-04-19 22:38:08,296 INFO Epoch:3 val_res:0.574750 +2025-04-19 22:38:44,822 INFO Epoch:4 train_loss:0.84309 +2025-04-19 22:38:59,506 INFO Epoch:4 val_res:0.577250 +2025-04-19 22:38:59,507 INFO Saving best model at Epoch 4 +2025-04-19 22:39:35,687 INFO Epoch:5 train_loss:0.81714 +2025-04-19 22:39:52,738 INFO Epoch:5 val_res:0.576250 +2025-04-19 22:40:29,379 INFO Epoch:6 train_loss:0.79372 +2025-04-19 22:40:44,671 INFO Epoch:6 val_res:0.577000 +2025-04-19 22:41:23,958 INFO Epoch:7 train_loss:0.78492 +2025-04-19 22:41:37,998 INFO Epoch:7 val_res:0.577500 +2025-04-19 22:41:37,998 INFO Saving best model at Epoch 7 +2025-04-19 22:42:18,544 INFO Epoch:8 train_loss:0.79737 +2025-04-19 22:42:34,713 INFO Epoch:8 val_res:0.578000 +2025-04-19 22:42:34,713 INFO Saving best model at Epoch 8 +2025-04-19 22:43:12,496 INFO Epoch:9 train_loss:0.78476 +2025-04-19 22:43:27,436 INFO Epoch:9 val_res:0.583000 +2025-04-19 22:43:27,437 INFO Saving best model at Epoch 9 +2025-04-19 22:44:04,430 INFO Epoch:10 train_loss:0.77442 +2025-04-19 22:44:19,777 INFO Epoch:10 val_res:0.584750 +2025-04-19 22:44:19,778 INFO Saving best model at Epoch 10 +2025-04-19 22:44:57,034 INFO Epoch:11 train_loss:0.75412 +2025-04-19 22:45:12,286 INFO Epoch:11 val_res:0.584000 +2025-04-19 22:45:53,673 INFO Epoch:12 train_loss:0.74367 +2025-04-19 22:46:08,982 INFO Epoch:12 val_res:0.584750 +2025-04-19 22:46:44,599 INFO Epoch:13 train_loss:0.71921 +2025-04-19 22:46:59,158 INFO Epoch:13 val_res:0.587500 +2025-04-19 22:46:59,158 INFO Saving best model at Epoch 13 +2025-04-19 22:47:36,147 INFO Epoch:14 train_loss:0.75255 +2025-04-19 22:47:50,418 INFO Epoch:14 val_res:0.590750 +2025-04-19 22:47:50,418 INFO Saving best model at Epoch 14 +2025-04-19 22:48:27,825 INFO Epoch:15 train_loss:0.74203 +2025-04-19 22:48:42,561 INFO Epoch:15 val_res:0.589250 +2025-04-19 22:49:18,505 INFO Epoch:16 train_loss:0.74408 +2025-04-19 22:49:34,297 INFO Epoch:16 val_res:0.590000 +2025-04-19 22:50:08,896 INFO Epoch:17 train_loss:0.69959 +2025-04-19 22:50:24,235 INFO Epoch:17 val_res:0.592750 +2025-04-19 22:50:24,235 INFO Saving best model at Epoch 17 +2025-04-19 22:51:02,886 INFO Epoch:18 train_loss:0.68550 +2025-04-19 22:51:17,288 INFO Epoch:18 val_res:0.590250 +2025-04-19 22:51:51,852 INFO Epoch:19 train_loss:0.70799 +2025-04-19 22:52:05,658 INFO Epoch:19 val_res:0.597750 +2025-04-19 22:52:05,658 INFO Saving best model at Epoch 19 +2025-04-19 22:52:49,987 INFO Epoch:20 train_loss:15.25341 +2025-04-19 22:53:05,773 INFO Epoch:20 val_res:0.572250 +2025-04-19 22:53:44,477 INFO Epoch:21 train_loss:3.71301 +2025-04-19 22:53:59,966 INFO Epoch:21 val_res:0.598000 +2025-04-19 22:53:59,966 INFO Saving best model at Epoch 21 +2025-04-19 22:54:43,620 INFO Epoch:22 train_loss:2.36782 +2025-04-19 22:54:59,649 INFO Epoch:22 val_res:0.599000 +2025-04-19 22:54:59,650 INFO Saving best model at Epoch 22 +2025-04-19 22:55:40,066 INFO Epoch:23 train_loss:2.05172 +2025-04-19 22:55:55,546 INFO Epoch:23 val_res:0.605750 +2025-04-19 22:55:55,546 INFO Saving best model at Epoch 23 +2025-04-19 22:56:35,134 INFO Epoch:24 train_loss:1.92941 +2025-04-19 22:56:50,746 INFO Epoch:24 val_res:0.606500 +2025-04-19 22:56:50,747 INFO Saving best model at Epoch 24 +2025-04-19 22:57:28,268 INFO Epoch:25 train_loss:1.84720 +2025-04-19 22:57:43,205 INFO Epoch:25 val_res:0.606500 +2025-04-19 22:58:23,644 INFO Epoch:26 train_loss:1.78516 +2025-04-19 22:58:38,252 INFO Epoch:26 val_res:0.611250 +2025-04-19 22:58:38,253 INFO Saving best model at Epoch 26 +2025-04-19 22:59:22,102 INFO Epoch:27 train_loss:1.74406 +2025-04-19 22:59:36,555 INFO Epoch:27 val_res:0.609500 +2025-04-19 23:00:19,104 INFO Epoch:28 train_loss:1.70760 +2025-04-19 23:00:33,635 INFO Epoch:28 val_res:0.613000 +2025-04-19 23:00:33,636 INFO Saving best model at Epoch 28 +2025-04-19 23:01:13,801 INFO Epoch:29 train_loss:1.67575 +2025-04-19 23:01:29,150 INFO Epoch:29 val_res:0.612000 +2025-04-19 23:02:09,979 INFO Epoch:30 train_loss:1.64716 +2025-04-19 23:02:27,571 INFO Epoch:30 val_res:0.614750 +2025-04-19 23:02:27,572 INFO Saving best model at Epoch 30 +2025-04-19 23:03:11,295 INFO Epoch:31 train_loss:1.62303 +2025-04-19 23:03:26,086 INFO Epoch:31 val_res:0.617000 +2025-04-19 23:03:26,087 INFO Saving best model at Epoch 31 +2025-04-19 23:04:09,657 INFO Epoch:32 train_loss:1.60528 +2025-04-19 23:04:24,217 INFO Epoch:32 val_res:0.615250 +2025-04-19 23:05:02,368 INFO Epoch:33 train_loss:1.57367 +2025-04-19 23:05:20,791 INFO Epoch:33 val_res:0.617750 +2025-04-19 23:05:20,792 INFO Saving best model at Epoch 33 +2025-04-19 23:06:04,294 INFO Epoch:34 train_loss:1.56205 +2025-04-19 23:06:18,754 INFO Epoch:34 val_res:0.620500 +2025-04-19 23:06:18,754 INFO Saving best model at Epoch 34 +2025-04-19 23:06:58,869 INFO Epoch:35 train_loss:1.54467 +2025-04-19 23:07:13,379 INFO Epoch:35 val_res:0.622250 +2025-04-19 23:07:13,379 INFO Saving best model at Epoch 35 +2025-04-19 23:07:55,044 INFO Epoch:36 train_loss:1.52461 +2025-04-19 23:08:10,299 INFO Epoch:36 val_res:0.622250 +2025-04-19 23:08:51,272 INFO Epoch:37 train_loss:1.51383 +2025-04-19 23:09:06,253 INFO Epoch:37 val_res:0.622250 +2025-04-19 23:09:47,803 INFO Epoch:38 train_loss:1.51762 +2025-04-19 23:10:02,557 INFO Epoch:38 val_res:0.620500 +2025-04-19 23:10:39,092 INFO Epoch:39 train_loss:1.50838 +2025-04-19 23:10:53,727 INFO Epoch:39 val_res:0.623750 +2025-04-19 23:10:53,728 INFO Saving best model at Epoch 39 +2025-04-19 23:11:36,155 INFO Epoch:40 train_loss:1.49597 +2025-04-19 23:11:51,342 INFO Epoch:40 val_res:0.626500 +2025-04-19 23:11:51,342 INFO Saving best model at Epoch 40 +2025-04-19 23:12:32,781 INFO Epoch:41 train_loss:1.46898 +2025-04-19 23:12:50,383 INFO Epoch:41 val_res:0.626250 +2025-04-19 23:13:30,805 INFO Epoch:42 train_loss:1.45516 +2025-04-19 23:13:45,843 INFO Epoch:42 val_res:0.626250 +2025-04-19 23:14:22,513 INFO Epoch:43 train_loss:1.44332 +2025-04-19 23:14:37,048 INFO Epoch:43 val_res:0.627500 +2025-04-19 23:14:37,049 INFO Saving best model at Epoch 43 +2025-04-19 23:15:19,941 INFO Epoch:44 train_loss:1.43466 +2025-04-19 23:15:36,269 INFO Epoch:44 val_res:0.626250 +2025-04-19 23:16:16,516 INFO Epoch:45 train_loss:1.43400 +2025-04-19 23:16:31,845 INFO Epoch:45 val_res:0.627500 +2025-04-19 23:17:13,515 INFO Epoch:46 train_loss:1.45214 +2025-04-19 23:17:31,689 INFO Epoch:46 val_res:0.627750 +2025-04-19 23:17:31,690 INFO Saving best model at Epoch 46 +2025-04-19 23:18:12,094 INFO Epoch:47 train_loss:1.46307 +2025-04-19 23:18:27,455 INFO Epoch:47 val_res:0.628750 +2025-04-19 23:18:27,456 INFO Saving best model at Epoch 47 +2025-04-19 23:19:09,625 INFO Epoch:48 train_loss:1.48873 +2025-04-19 23:19:28,287 INFO Epoch:48 val_res:0.626000 +2025-04-19 23:20:10,478 INFO Epoch:49 train_loss:1.41534 +2025-04-19 23:20:28,951 INFO Epoch:49 val_res:0.628750 +2025-04-19 23:21:06,798 INFO Epoch:50 train_loss:1.39340 +2025-04-19 23:21:22,164 INFO Epoch:50 val_res:0.628000 +2025-04-19 23:22:03,106 INFO Epoch:51 train_loss:1.37713 +2025-04-19 23:22:20,975 INFO Epoch:51 val_res:0.627750 +2025-04-19 23:23:02,270 INFO Epoch:52 train_loss:1.37160 +2025-04-19 23:23:16,978 INFO Epoch:52 val_res:0.627000 +2025-04-19 23:23:53,878 INFO Epoch:53 train_loss:1.38851 +2025-04-19 23:24:12,014 INFO Epoch:53 val_res:0.628250 +2025-04-19 23:24:53,029 INFO Epoch:54 train_loss:1.39378 +2025-04-19 23:25:07,549 INFO Epoch:54 val_res:0.625500 +2025-04-19 23:25:46,345 INFO Epoch:55 train_loss:1.38198 +2025-04-19 23:26:00,757 INFO Epoch:55 val_res:0.625250 +2025-04-19 23:26:38,738 INFO Epoch:56 train_loss:1.35827 +2025-04-19 23:26:56,667 INFO Epoch:56 val_res:0.628250 +2025-04-19 23:27:38,354 INFO Epoch:57 train_loss:1.35490 +2025-04-19 23:27:53,884 INFO Epoch:57 val_res:0.628500 +2025-04-19 23:28:31,345 INFO Epoch:58 train_loss:1.32583 +2025-04-19 23:28:45,358 INFO Epoch:58 val_res:0.627000 +2025-04-19 23:29:23,097 INFO Epoch:59 train_loss:1.40910 +2025-04-19 23:29:38,091 INFO Epoch:59 val_res:0.623000 +2025-04-19 23:30:18,754 INFO Epoch:60 train_loss:1.40890 +2025-04-19 23:30:36,988 INFO Epoch:60 val_res:0.624750 +2025-04-19 23:31:20,420 INFO Epoch:61 train_loss:1.36567 +2025-04-19 23:31:35,053 INFO Epoch:61 val_res:0.626000 +2025-04-19 23:32:12,947 INFO Epoch:62 train_loss:1.35847 +2025-04-19 23:32:28,600 INFO Epoch:62 val_res:0.624500 +2025-04-19 23:33:09,595 INFO Epoch:63 train_loss:1.33461 +2025-04-19 23:33:25,044 INFO Epoch:63 val_res:0.624000 +2025-04-19 23:34:05,927 INFO Epoch:64 train_loss:1.34460 +2025-04-19 23:34:20,969 INFO Epoch:64 val_res:0.622500 +2025-04-19 23:34:59,376 INFO Epoch:65 train_loss:1.34232 +2025-04-19 23:35:16,250 INFO Epoch:65 val_res:0.622500 +2025-04-19 23:35:55,537 INFO Epoch:66 train_loss:1.34232 +2025-04-19 23:36:13,330 INFO Epoch:66 val_res:0.619000 +2025-04-19 23:36:54,947 INFO Epoch:67 train_loss:1.35592 +2025-04-19 23:37:09,307 INFO Epoch:67 val_res:0.623000 +2025-04-19 23:37:47,720 INFO Epoch:68 train_loss:1.30773 +2025-04-19 23:38:03,502 INFO Epoch:68 val_res:0.627000 +2025-04-19 23:38:44,053 INFO Epoch:69 train_loss:1.31745 +2025-04-19 23:38:59,529 INFO Epoch:69 val_res:0.622250 +2025-04-19 23:39:40,827 INFO Epoch:70 train_loss:1.28613 +2025-04-19 23:39:55,371 INFO Epoch:70 val_res:0.618750 +2025-04-19 23:40:35,043 INFO Epoch:71 train_loss:0.53669 +2025-04-19 23:40:51,054 INFO Epoch:71 val_res:0.623000 +2025-04-19 23:41:34,531 INFO Epoch:72 train_loss:0.51679 +2025-04-19 23:41:51,210 INFO Epoch:72 val_res:0.622750 +2025-04-19 23:42:28,630 INFO Epoch:73 train_loss:0.51151 +2025-04-19 23:42:43,003 INFO Epoch:73 val_res:0.619750 +2025-04-19 23:43:19,238 INFO Epoch:74 train_loss:0.50761 +2025-04-19 23:43:34,652 INFO Epoch:74 val_res:0.621000 +2025-04-19 23:44:13,328 INFO Epoch:75 train_loss:0.50588 +2025-04-19 23:44:29,136 INFO Epoch:75 val_res:0.620500 +2025-04-19 23:45:10,059 INFO Epoch:76 train_loss:0.50667 +2025-04-19 23:45:24,711 INFO Epoch:76 val_res:0.620750 +2025-04-19 23:46:04,254 INFO Epoch:77 train_loss:0.50742 +2025-04-19 23:46:20,486 INFO Epoch:77 val_res:0.620500 +2025-04-19 23:47:00,097 INFO Epoch:78 train_loss:0.50781 +2025-04-19 23:47:16,716 INFO Epoch:78 val_res:0.618500 +2025-04-19 23:47:55,180 INFO Epoch:79 train_loss:0.50431 +2025-04-19 23:48:09,954 INFO Epoch:79 val_res:0.618000 +2025-04-19 23:48:48,416 INFO Epoch:80 train_loss:0.50502 +2025-04-19 23:49:03,691 INFO Epoch:80 val_res:0.620000 +2025-04-19 23:49:38,848 INFO Epoch:81 train_loss:0.50447 +2025-04-19 23:49:53,936 INFO Epoch:81 val_res:0.620250 +2025-04-19 23:50:31,734 INFO Epoch:82 train_loss:0.50566 +2025-04-19 23:50:46,516 INFO Epoch:82 val_res:0.619250 +2025-04-19 23:51:24,364 INFO Epoch:83 train_loss:0.50611 +2025-04-19 23:51:39,126 INFO Epoch:83 val_res:0.621000 +2025-04-19 23:52:13,704 INFO Epoch:84 train_loss:0.50317 +2025-04-19 23:52:29,538 INFO Epoch:84 val_res:0.619750 +2025-04-19 23:53:08,579 INFO Epoch:85 train_loss:0.50500 +2025-04-19 23:53:23,420 INFO Epoch:85 val_res:0.618000 +2025-04-19 23:54:02,895 INFO Epoch:86 train_loss:0.50441 +2025-04-19 23:54:18,427 INFO Epoch:86 val_res:0.616750 +2025-04-19 23:54:59,428 INFO Epoch:87 train_loss:0.50476 +2025-04-19 23:55:14,941 INFO Epoch:87 val_res:0.618250 +2025-04-19 23:55:53,640 INFO Epoch:88 train_loss:0.50621 +2025-04-19 23:56:09,015 INFO Epoch:88 val_res:0.619250 +2025-04-19 23:56:48,300 INFO Epoch:89 train_loss:0.51918 +2025-04-19 23:57:03,818 INFO Epoch:89 val_res:0.616750 +2025-04-19 23:57:41,310 INFO Epoch:90 train_loss:0.54175 +2025-04-19 23:57:57,016 INFO Epoch:90 val_res:0.618500 +2025-04-19 23:58:34,995 INFO Epoch:91 train_loss:0.53570 +2025-04-19 23:58:49,548 INFO Epoch:91 val_res:0.616000 +2025-04-19 23:59:27,476 INFO Epoch:92 train_loss:0.50713 +2025-04-19 23:59:42,434 INFO Epoch:92 val_res:0.613250 +2025-04-20 00:00:19,900 INFO Epoch:93 train_loss:0.50610 +2025-04-20 00:00:35,154 INFO Epoch:93 val_res:0.615250 +2025-04-20 00:01:12,999 INFO Epoch:94 train_loss:0.51729 +2025-04-20 00:01:27,934 INFO Epoch:94 val_res:0.614250 +2025-04-20 00:02:07,035 INFO Epoch:95 train_loss:0.51537 +2025-04-20 00:02:23,939 INFO Epoch:95 val_res:0.615250 +2025-04-20 00:03:02,126 INFO Epoch:96 train_loss:0.51339 +2025-04-20 00:03:16,274 INFO Epoch:96 val_res:0.611500 +2025-04-20 00:03:52,361 INFO Epoch:97 train_loss:0.52363 +2025-04-20 00:04:08,268 INFO Epoch:97 val_res:0.611750 +2025-04-20 00:04:46,816 INFO Epoch:98 train_loss:0.52764 +2025-04-20 00:05:02,569 INFO Epoch:98 val_res:0.614250 +2025-04-20 00:05:40,175 INFO Epoch:99 train_loss:0.57508 +2025-04-20 00:05:54,349 INFO Epoch:99 val_res:0.612500 +2025-04-20 00:05:54,633 INFO ===================================== +2025-04-20 00:05:54,633 INFO Start testing... +2025-04-20 00:05:54,634 INFO ===================================== +2025-04-20 00:06:10,880 INFO Incremental step 7 Testing res: 0.630250 +2025-04-20 00:06:10,883 INFO forgetting: 0.098857 +2025-04-20 00:06:10,889 INFO Incremental step: 8 +2025-04-20 00:06:42,879 INFO Epoch:0 train_loss:3.66087 +2025-04-20 00:07:01,098 INFO Epoch:0 val_res:0.557556 +2025-04-20 00:07:01,099 INFO Saving best model at Epoch 0 +2025-04-20 00:07:35,475 INFO Epoch:1 train_loss:1.22192 +2025-04-20 00:07:51,479 INFO Epoch:1 val_res:0.561333 +2025-04-20 00:07:51,480 INFO Saving best model at Epoch 1 +2025-04-20 00:08:22,891 INFO Epoch:2 train_loss:0.89802 +2025-04-20 00:08:38,619 INFO Epoch:2 val_res:0.562222 +2025-04-20 00:08:38,619 INFO Saving best model at Epoch 2 +2025-04-20 00:09:13,467 INFO Epoch:3 train_loss:0.81754 +2025-04-20 00:09:31,191 INFO Epoch:3 val_res:0.561111 +2025-04-20 00:10:02,946 INFO Epoch:4 train_loss:0.78391 +2025-04-20 00:10:20,894 INFO Epoch:4 val_res:0.565111 +2025-04-20 00:10:20,894 INFO Saving best model at Epoch 4 +2025-04-20 00:10:54,987 INFO Epoch:5 train_loss:0.76035 +2025-04-20 00:11:12,266 INFO Epoch:5 val_res:0.566667 +2025-04-20 00:11:12,266 INFO Saving best model at Epoch 5 +2025-04-20 00:11:46,587 INFO Epoch:6 train_loss:0.75072 +2025-04-20 00:12:03,137 INFO Epoch:6 val_res:0.568000 +2025-04-20 00:12:03,138 INFO Saving best model at Epoch 6 +2025-04-20 00:12:36,964 INFO Epoch:7 train_loss:0.73869 +2025-04-20 00:12:54,627 INFO Epoch:7 val_res:0.569333 +2025-04-20 00:12:54,628 INFO Saving best model at Epoch 7 +2025-04-20 00:13:27,018 INFO Epoch:8 train_loss:0.72367 +2025-04-20 00:13:44,316 INFO Epoch:8 val_res:0.569333 +2025-04-20 00:14:17,765 INFO Epoch:9 train_loss:0.71466 +2025-04-20 00:14:34,483 INFO Epoch:9 val_res:0.569778 +2025-04-20 00:14:34,483 INFO Saving best model at Epoch 9 +2025-04-20 00:15:09,194 INFO Epoch:10 train_loss:0.70989 +2025-04-20 00:15:25,760 INFO Epoch:10 val_res:0.570222 +2025-04-20 00:15:25,761 INFO Saving best model at Epoch 10 +2025-04-20 00:16:01,200 INFO Epoch:11 train_loss:0.73882 +2025-04-20 00:16:16,842 INFO Epoch:11 val_res:0.573778 +2025-04-20 00:16:16,842 INFO Saving best model at Epoch 11 +2025-04-20 00:16:50,895 INFO Epoch:12 train_loss:0.73980 +2025-04-20 00:17:07,336 INFO Epoch:12 val_res:0.575556 +2025-04-20 00:17:07,336 INFO Saving best model at Epoch 12 +2025-04-20 00:17:41,900 INFO Epoch:13 train_loss:0.70304 +2025-04-20 00:18:01,504 INFO Epoch:13 val_res:0.576222 +2025-04-20 00:18:01,504 INFO Saving best model at Epoch 13 +2025-04-20 00:18:37,883 INFO Epoch:14 train_loss:0.68623 +2025-04-20 00:18:55,140 INFO Epoch:14 val_res:0.578444 +2025-04-20 00:18:55,141 INFO Saving best model at Epoch 14 +2025-04-20 00:19:28,441 INFO Epoch:15 train_loss:0.68278 +2025-04-20 00:19:44,556 INFO Epoch:15 val_res:0.576667 +2025-04-20 00:20:17,180 INFO Epoch:16 train_loss:0.70546 +2025-04-20 00:20:35,286 INFO Epoch:16 val_res:0.577556 +2025-04-20 00:21:06,018 INFO Epoch:17 train_loss:0.70314 +2025-04-20 00:21:25,175 INFO Epoch:17 val_res:0.579111 +2025-04-20 00:21:25,176 INFO Saving best model at Epoch 17 +2025-04-20 00:22:01,340 INFO Epoch:18 train_loss:0.68361 +2025-04-20 00:22:17,539 INFO Epoch:18 val_res:0.575111 +2025-04-20 00:22:51,308 INFO Epoch:19 train_loss:0.69322 +2025-04-20 00:23:09,756 INFO Epoch:19 val_res:0.577778 +2025-04-20 00:23:44,983 INFO Epoch:20 train_loss:14.45363 +2025-04-20 00:24:02,531 INFO Epoch:20 val_res:0.545556 +2025-04-20 00:24:37,563 INFO Epoch:21 train_loss:4.04492 +2025-04-20 00:24:54,162 INFO Epoch:21 val_res:0.576000 +2025-04-20 00:25:26,826 INFO Epoch:22 train_loss:2.32434 +2025-04-20 00:25:44,478 INFO Epoch:22 val_res:0.585333 +2025-04-20 00:25:44,479 INFO Saving best model at Epoch 22 +2025-04-20 00:26:21,051 INFO Epoch:23 train_loss:1.91710 +2025-04-20 00:26:37,930 INFO Epoch:23 val_res:0.587111 +2025-04-20 00:26:37,931 INFO Saving best model at Epoch 23 +2025-04-20 00:27:12,178 INFO Epoch:24 train_loss:1.76711 +2025-04-20 00:27:28,251 INFO Epoch:24 val_res:0.588667 +2025-04-20 00:27:28,251 INFO Saving best model at Epoch 24 +2025-04-20 00:28:07,598 INFO Epoch:25 train_loss:1.67616 +2025-04-20 00:28:25,834 INFO Epoch:25 val_res:0.592000 +2025-04-20 00:28:25,834 INFO Saving best model at Epoch 25 +2025-04-20 00:28:59,998 INFO Epoch:26 train_loss:1.63315 +2025-04-20 00:29:16,642 INFO Epoch:26 val_res:0.592000 +2025-04-20 00:29:47,892 INFO Epoch:27 train_loss:1.59392 +2025-04-20 00:30:05,436 INFO Epoch:27 val_res:0.594222 +2025-04-20 00:30:05,437 INFO Saving best model at Epoch 27 +2025-04-20 00:30:46,191 INFO Epoch:28 train_loss:1.56498 +2025-04-20 00:31:06,765 INFO Epoch:28 val_res:0.594667 +2025-04-20 00:31:06,765 INFO Saving best model at Epoch 28 +2025-04-20 00:31:43,819 INFO Epoch:29 train_loss:1.54390 +2025-04-20 00:32:00,292 INFO Epoch:29 val_res:0.596444 +2025-04-20 00:32:00,293 INFO Saving best model at Epoch 29 +2025-04-20 00:32:37,193 INFO Epoch:30 train_loss:1.50783 +2025-04-20 00:32:52,663 INFO Epoch:30 val_res:0.596667 +2025-04-20 00:32:52,664 INFO Saving best model at Epoch 30 +2025-04-20 00:33:29,053 INFO Epoch:31 train_loss:1.48188 +2025-04-20 00:33:44,465 INFO Epoch:31 val_res:0.598222 +2025-04-20 00:33:44,465 INFO Saving best model at Epoch 31 +2025-04-20 00:34:21,955 INFO Epoch:32 train_loss:1.46756 +2025-04-20 00:34:38,695 INFO Epoch:32 val_res:0.597111 +2025-04-20 00:35:12,410 INFO Epoch:33 train_loss:1.45729 +2025-04-20 00:35:29,201 INFO Epoch:33 val_res:0.598667 +2025-04-20 00:35:29,201 INFO Saving best model at Epoch 33 +2025-04-20 00:36:03,721 INFO Epoch:34 train_loss:1.44450 +2025-04-20 00:36:19,488 INFO Epoch:34 val_res:0.598889 +2025-04-20 00:36:19,488 INFO Saving best model at Epoch 34 +2025-04-20 00:36:55,195 INFO Epoch:35 train_loss:1.42439 +2025-04-20 00:37:11,067 INFO Epoch:35 val_res:0.600444 +2025-04-20 00:37:11,067 INFO Saving best model at Epoch 35 +2025-04-20 00:37:44,615 INFO Epoch:36 train_loss:1.40992 +2025-04-20 00:38:02,611 INFO Epoch:36 val_res:0.600667 +2025-04-20 00:38:02,612 INFO Saving best model at Epoch 36 +2025-04-20 00:38:36,470 INFO Epoch:37 train_loss:1.39077 +2025-04-20 00:38:52,730 INFO Epoch:37 val_res:0.600222 +2025-04-20 00:39:24,096 INFO Epoch:38 train_loss:1.38562 +2025-04-20 00:39:40,107 INFO Epoch:38 val_res:0.599778 +2025-04-20 00:40:14,113 INFO Epoch:39 train_loss:1.37848 +2025-04-20 00:40:32,337 INFO Epoch:39 val_res:0.603778 +2025-04-20 00:40:32,337 INFO Saving best model at Epoch 39 +2025-04-20 00:41:11,552 INFO Epoch:40 train_loss:1.36789 +2025-04-20 00:41:29,026 INFO Epoch:40 val_res:0.603111 +2025-04-20 00:42:02,565 INFO Epoch:41 train_loss:1.35727 +2025-04-20 00:42:19,588 INFO Epoch:41 val_res:0.603333 +2025-04-20 00:42:53,743 INFO Epoch:42 train_loss:1.35764 +2025-04-20 00:43:10,068 INFO Epoch:42 val_res:0.603778 +2025-04-20 00:43:45,362 INFO Epoch:43 train_loss:1.34391 +2025-04-20 00:44:01,135 INFO Epoch:43 val_res:0.599111 +2025-04-20 00:44:33,481 INFO Epoch:44 train_loss:1.33791 +2025-04-20 00:44:52,012 INFO Epoch:44 val_res:0.601556 +2025-04-20 00:45:26,822 INFO Epoch:45 train_loss:1.32839 +2025-04-20 00:45:45,354 INFO Epoch:45 val_res:0.599556 +2025-04-20 00:46:21,032 INFO Epoch:46 train_loss:1.31592 +2025-04-20 00:46:37,041 INFO Epoch:46 val_res:0.600444 +2025-04-20 00:47:08,864 INFO Epoch:47 train_loss:1.31314 +2025-04-20 00:47:25,245 INFO Epoch:47 val_res:0.601556 +2025-04-20 00:47:57,184 INFO Epoch:48 train_loss:1.32673 +2025-04-20 00:48:12,654 INFO Epoch:48 val_res:0.600444 +2025-04-20 00:48:45,090 INFO Epoch:49 train_loss:1.34888 +2025-04-20 00:49:00,901 INFO Epoch:49 val_res:0.602889 +2025-04-20 00:49:36,297 INFO Epoch:50 train_loss:1.33451 +2025-04-20 00:49:52,838 INFO Epoch:50 val_res:0.598667 +2025-04-20 00:50:25,084 INFO Epoch:51 train_loss:1.29176 +2025-04-20 00:50:43,364 INFO Epoch:51 val_res:0.600000 +2025-04-20 00:51:14,904 INFO Epoch:52 train_loss:1.28188 +2025-04-20 00:51:30,822 INFO Epoch:52 val_res:0.598667 +2025-04-20 00:52:03,790 INFO Epoch:53 train_loss:1.27040 +2025-04-20 00:52:19,661 INFO Epoch:53 val_res:0.599556 +2025-04-20 00:52:50,302 INFO Epoch:54 train_loss:1.28418 +2025-04-20 00:53:05,815 INFO Epoch:54 val_res:0.598667 +2025-04-20 00:53:38,372 INFO Epoch:55 train_loss:1.29257 +2025-04-20 00:53:54,360 INFO Epoch:55 val_res:0.598444 +2025-04-20 00:54:26,034 INFO Epoch:56 train_loss:1.27332 +2025-04-20 00:54:42,094 INFO Epoch:56 val_res:0.598889 +2025-04-20 00:55:17,863 INFO Epoch:57 train_loss:1.28690 +2025-04-20 00:55:35,054 INFO Epoch:57 val_res:0.597778 +2025-04-20 00:56:07,224 INFO Epoch:58 train_loss:1.29184 +2025-04-20 00:56:23,874 INFO Epoch:58 val_res:0.594222 +2025-04-20 00:56:58,325 INFO Epoch:59 train_loss:1.25541 +2025-04-20 00:57:15,871 INFO Epoch:59 val_res:0.596444 +2025-04-20 00:57:47,367 INFO Epoch:60 train_loss:1.23690 +2025-04-20 00:58:05,192 INFO Epoch:60 val_res:0.596667 +2025-04-20 00:58:38,718 INFO Epoch:61 train_loss:1.24672 +2025-04-20 00:58:54,882 INFO Epoch:61 val_res:0.594000 +2025-04-20 00:59:29,389 INFO Epoch:62 train_loss:1.25361 +2025-04-20 00:59:45,192 INFO Epoch:62 val_res:0.597111 +2025-04-20 01:00:19,717 INFO Epoch:63 train_loss:1.26706 +2025-04-20 01:00:39,079 INFO Epoch:63 val_res:0.592444 +2025-04-20 01:01:14,003 INFO Epoch:64 train_loss:1.27914 +2025-04-20 01:01:29,281 INFO Epoch:64 val_res:0.591778 +2025-04-20 01:02:03,441 INFO Epoch:65 train_loss:1.27875 +2025-04-20 01:02:19,078 INFO Epoch:65 val_res:0.590667 +2025-04-20 01:02:53,018 INFO Epoch:66 train_loss:1.25997 +2025-04-20 01:03:09,319 INFO Epoch:66 val_res:0.592444 +2025-04-20 01:03:44,517 INFO Epoch:67 train_loss:1.23588 +2025-04-20 01:04:00,798 INFO Epoch:67 val_res:0.592889 +2025-04-20 01:04:32,551 INFO Epoch:68 train_loss:1.23995 +2025-04-20 01:04:48,849 INFO Epoch:68 val_res:0.591333 +2025-04-20 01:05:20,083 INFO Epoch:69 train_loss:1.26836 +2025-04-20 01:05:35,996 INFO Epoch:69 val_res:0.595333 +2025-04-20 01:06:07,453 INFO Epoch:70 train_loss:1.22830 +2025-04-20 01:06:23,701 INFO Epoch:70 val_res:0.590444 +2025-04-20 01:06:53,822 INFO Epoch:71 train_loss:0.56618 +2025-04-20 01:07:09,506 INFO Epoch:71 val_res:0.589556 +2025-04-20 01:07:39,484 INFO Epoch:72 train_loss:0.54940 +2025-04-20 01:07:55,752 INFO Epoch:72 val_res:0.591556 +2025-04-20 01:08:25,895 INFO Epoch:73 train_loss:0.54897 +2025-04-20 01:08:42,020 INFO Epoch:73 val_res:0.589333 +2025-04-20 01:09:14,309 INFO Epoch:74 train_loss:0.54488 +2025-04-20 01:09:33,698 INFO Epoch:74 val_res:0.588667 +2025-04-20 01:10:04,610 INFO Epoch:75 train_loss:0.54699 +2025-04-20 01:10:21,018 INFO Epoch:75 val_res:0.588889 +2025-04-20 01:10:54,477 INFO Epoch:76 train_loss:0.54115 +2025-04-20 01:11:11,162 INFO Epoch:76 val_res:0.590000 +2025-04-20 01:11:43,243 INFO Epoch:77 train_loss:0.54204 +2025-04-20 01:12:00,016 INFO Epoch:77 val_res:0.588000 +2025-04-20 01:12:33,288 INFO Epoch:78 train_loss:0.54190 +2025-04-20 01:12:50,536 INFO Epoch:78 val_res:0.587333 +2025-04-20 01:13:21,903 INFO Epoch:79 train_loss:0.54385 +2025-04-20 01:13:38,398 INFO Epoch:79 val_res:0.588667 +2025-04-20 01:14:10,692 INFO Epoch:80 train_loss:0.54202 +2025-04-20 01:14:26,962 INFO Epoch:80 val_res:0.585778 +2025-04-20 01:15:00,255 INFO Epoch:81 train_loss:0.54221 +2025-04-20 01:15:16,064 INFO Epoch:81 val_res:0.586889 +2025-04-20 01:15:50,010 INFO Epoch:82 train_loss:0.54227 +2025-04-20 01:16:06,665 INFO Epoch:82 val_res:0.586222 +2025-04-20 01:16:38,717 INFO Epoch:83 train_loss:0.54020 +2025-04-20 01:16:55,435 INFO Epoch:83 val_res:0.586667 +2025-04-20 01:17:27,915 INFO Epoch:84 train_loss:0.54061 +2025-04-20 01:17:47,137 INFO Epoch:84 val_res:0.586667 +2025-04-20 01:18:18,742 INFO Epoch:85 train_loss:0.53869 +2025-04-20 01:18:34,933 INFO Epoch:85 val_res:0.585778 +2025-04-20 01:19:06,732 INFO Epoch:86 train_loss:0.54046 +2025-04-20 01:19:22,574 INFO Epoch:86 val_res:0.584000 +2025-04-20 01:19:54,439 INFO Epoch:87 train_loss:0.53786 +2025-04-20 01:20:10,360 INFO Epoch:87 val_res:0.586444 +2025-04-20 01:20:44,366 INFO Epoch:88 train_loss:0.53919 +2025-04-20 01:21:00,366 INFO Epoch:88 val_res:0.585333 +2025-04-20 01:21:30,980 INFO Epoch:89 train_loss:0.53985 +2025-04-20 01:21:46,979 INFO Epoch:89 val_res:0.583778 +2025-04-20 01:22:19,374 INFO Epoch:90 train_loss:0.53756 +2025-04-20 01:22:35,998 INFO Epoch:90 val_res:0.584000 +2025-04-20 01:23:05,724 INFO Epoch:91 train_loss:0.53835 +2025-04-20 01:23:22,408 INFO Epoch:91 val_res:0.583556 +2025-04-20 01:23:51,274 INFO Epoch:92 train_loss:0.53951 +2025-04-20 01:24:07,207 INFO Epoch:92 val_res:0.584444 +2025-04-20 01:24:39,366 INFO Epoch:93 train_loss:0.53692 +2025-04-20 01:24:55,453 INFO Epoch:93 val_res:0.584444 +2025-04-20 01:25:26,642 INFO Epoch:94 train_loss:0.53927 +2025-04-20 01:25:42,708 INFO Epoch:94 val_res:0.585333 +2025-04-20 01:26:14,116 INFO Epoch:95 train_loss:0.53408 +2025-04-20 01:26:30,674 INFO Epoch:95 val_res:0.584444 +2025-04-20 01:27:01,610 INFO Epoch:96 train_loss:0.53627 +2025-04-20 01:27:17,815 INFO Epoch:96 val_res:0.584000 +2025-04-20 01:27:47,982 INFO Epoch:97 train_loss:0.54902 +2025-04-20 01:28:04,080 INFO Epoch:97 val_res:0.582222 +2025-04-20 01:28:34,501 INFO Epoch:98 train_loss:0.56004 +2025-04-20 01:28:50,594 INFO Epoch:98 val_res:0.580000 +2025-04-20 01:29:21,677 INFO Epoch:99 train_loss:0.57720 +2025-04-20 01:29:36,885 INFO Epoch:99 val_res:0.580889 +2025-04-20 01:29:37,137 INFO ===================================== +2025-04-20 01:29:37,137 INFO Start testing... +2025-04-20 01:29:37,137 INFO ===================================== +2025-04-20 01:29:54,487 INFO Incremental step 8 Testing res: 0.602000 +2025-04-20 01:29:54,492 INFO forgetting: 0.099500 +2025-04-20 01:29:54,497 INFO Incremental step: 9 +2025-04-20 01:30:32,476 INFO Epoch:0 train_loss:3.22611 +2025-04-20 01:30:51,619 INFO Epoch:0 val_res:0.538200 +2025-04-20 01:30:51,619 INFO Saving best model at Epoch 0 +2025-04-20 01:31:32,432 INFO Epoch:1 train_loss:0.96880 +2025-04-20 01:31:50,080 INFO Epoch:1 val_res:0.549400 +2025-04-20 01:31:50,081 INFO Saving best model at Epoch 1 +2025-04-20 01:32:29,718 INFO Epoch:2 train_loss:0.74515 +2025-04-20 01:32:47,867 INFO Epoch:2 val_res:0.551400 +2025-04-20 01:32:47,868 INFO Saving best model at Epoch 2 +2025-04-20 01:33:29,607 INFO Epoch:3 train_loss:0.68716 +2025-04-20 01:33:47,644 INFO Epoch:3 val_res:0.556200 +2025-04-20 01:33:47,645 INFO Saving best model at Epoch 3 +2025-04-20 01:34:27,154 INFO Epoch:4 train_loss:0.66269 +2025-04-20 01:34:47,324 INFO Epoch:4 val_res:0.557600 +2025-04-20 01:34:47,324 INFO Saving best model at Epoch 4 +2025-04-20 01:35:26,714 INFO Epoch:5 train_loss:0.64659 +2025-04-20 01:35:44,379 INFO Epoch:5 val_res:0.560200 +2025-04-20 01:35:44,379 INFO Saving best model at Epoch 5 +2025-04-20 01:36:22,389 INFO Epoch:6 train_loss:0.63308 +2025-04-20 01:36:40,677 INFO Epoch:6 val_res:0.560800 +2025-04-20 01:36:40,677 INFO Saving best model at Epoch 6 +2025-04-20 01:37:19,571 INFO Epoch:7 train_loss:0.62299 +2025-04-20 01:37:37,960 INFO Epoch:7 val_res:0.559400 +2025-04-20 01:38:15,143 INFO Epoch:8 train_loss:0.61653 +2025-04-20 01:38:36,066 INFO Epoch:8 val_res:0.561800 +2025-04-20 01:38:36,066 INFO Saving best model at Epoch 8 +2025-04-20 01:39:13,674 INFO Epoch:9 train_loss:0.60679 +2025-04-20 01:39:30,794 INFO Epoch:9 val_res:0.564400 +2025-04-20 01:39:30,795 INFO Saving best model at Epoch 9 +2025-04-20 01:40:09,005 INFO Epoch:10 train_loss:0.64556 +2025-04-20 01:40:28,449 INFO Epoch:10 val_res:0.561000 +2025-04-20 01:41:03,320 INFO Epoch:11 train_loss:0.65099 +2025-04-20 01:41:20,678 INFO Epoch:11 val_res:0.563600 +2025-04-20 01:41:59,104 INFO Epoch:12 train_loss:0.60676 +2025-04-20 01:42:20,904 INFO Epoch:12 val_res:0.565600 +2025-04-20 01:42:20,905 INFO Saving best model at Epoch 12 +2025-04-20 01:42:59,598 INFO Epoch:13 train_loss:0.59753 +2025-04-20 01:43:22,298 INFO Epoch:13 val_res:0.564600 +2025-04-20 01:44:01,948 INFO Epoch:14 train_loss:0.62071 +2025-04-20 01:44:23,504 INFO Epoch:14 val_res:0.562600 +2025-04-20 01:45:04,467 INFO Epoch:15 train_loss:0.63142 +2025-04-20 01:45:22,890 INFO Epoch:15 val_res:0.567000 +2025-04-20 01:45:22,890 INFO Saving best model at Epoch 15 +2025-04-20 01:46:02,289 INFO Epoch:16 train_loss:0.62085 +2025-04-20 01:46:19,694 INFO Epoch:16 val_res:0.567600 +2025-04-20 01:46:19,694 INFO Saving best model at Epoch 16 +2025-04-20 01:46:58,250 INFO Epoch:17 train_loss:0.62357 +2025-04-20 01:47:15,830 INFO Epoch:17 val_res:0.570600 +2025-04-20 01:47:15,830 INFO Saving best model at Epoch 17 +2025-04-20 01:47:57,339 INFO Epoch:18 train_loss:0.62620 +2025-04-20 01:48:15,201 INFO Epoch:18 val_res:0.572200 +2025-04-20 01:48:15,201 INFO Saving best model at Epoch 18 +2025-04-20 01:48:53,898 INFO Epoch:19 train_loss:0.62263 +2025-04-20 01:49:18,185 INFO Epoch:19 val_res:0.573000 +2025-04-20 01:49:18,186 INFO Saving best model at Epoch 19 +2025-04-20 01:49:58,552 INFO Epoch:20 train_loss:13.71683 +2025-04-20 01:50:23,393 INFO Epoch:20 val_res:0.545800 +2025-04-20 01:51:06,116 INFO Epoch:21 train_loss:3.36663 +2025-04-20 01:51:24,129 INFO Epoch:21 val_res:0.566400 +2025-04-20 01:52:06,338 INFO Epoch:22 train_loss:2.00234 +2025-04-20 01:52:24,706 INFO Epoch:22 val_res:0.575000 +2025-04-20 01:52:24,706 INFO Saving best model at Epoch 22 +2025-04-20 01:53:08,073 INFO Epoch:23 train_loss:1.69086 +2025-04-20 01:53:27,679 INFO Epoch:23 val_res:0.578200 +2025-04-20 01:53:27,679 INFO Saving best model at Epoch 23 +2025-04-20 01:54:08,653 INFO Epoch:24 train_loss:1.57543 +2025-04-20 01:54:26,553 INFO Epoch:24 val_res:0.581800 +2025-04-20 01:54:26,554 INFO Saving best model at Epoch 24 +2025-04-20 01:55:08,996 INFO Epoch:25 train_loss:1.50136 +2025-04-20 01:55:29,135 INFO Epoch:25 val_res:0.581200 +2025-04-20 01:56:09,521 INFO Epoch:26 train_loss:1.45614 +2025-04-20 01:56:32,403 INFO Epoch:26 val_res:0.584000 +2025-04-20 01:56:32,404 INFO Saving best model at Epoch 26 +2025-04-20 01:57:14,753 INFO Epoch:27 train_loss:1.42686 +2025-04-20 01:57:32,790 INFO Epoch:27 val_res:0.583200 +2025-04-20 01:58:12,989 INFO Epoch:28 train_loss:1.39560 +2025-04-20 01:58:36,462 INFO Epoch:28 val_res:0.584800 +2025-04-20 01:58:36,462 INFO Saving best model at Epoch 28 +2025-04-20 01:59:14,846 INFO Epoch:29 train_loss:1.36970 +2025-04-20 01:59:31,469 INFO Epoch:29 val_res:0.583800 +2025-04-20 02:00:05,120 INFO Epoch:30 train_loss:1.34779 +2025-04-20 02:00:20,954 INFO Epoch:30 val_res:0.584200 +2025-04-20 02:00:53,009 INFO Epoch:31 train_loss:1.33381 +2025-04-20 02:01:07,285 INFO Epoch:31 val_res:0.586600 +2025-04-20 02:01:07,286 INFO Saving best model at Epoch 31 +2025-04-20 02:01:43,368 INFO Epoch:32 train_loss:1.32435 +2025-04-20 02:01:58,648 INFO Epoch:32 val_res:0.584800 +2025-04-20 02:02:30,704 INFO Epoch:33 train_loss:1.31165 +2025-04-20 02:02:44,805 INFO Epoch:33 val_res:0.585400 +2025-04-20 02:03:17,481 INFO Epoch:34 train_loss:1.28788 +2025-04-20 02:03:33,905 INFO Epoch:34 val_res:0.587800 +2025-04-20 02:03:33,905 INFO Saving best model at Epoch 34 +2025-04-20 02:04:09,556 INFO Epoch:35 train_loss:1.29491 +2025-04-20 02:04:22,792 INFO Epoch:35 val_res:0.587200 +2025-04-20 02:04:55,063 INFO Epoch:36 train_loss:1.26832 +2025-04-20 02:05:09,449 INFO Epoch:36 val_res:0.587400 +2025-04-20 02:05:41,993 INFO Epoch:37 train_loss:1.25793 +2025-04-20 02:05:57,916 INFO Epoch:37 val_res:0.589400 +2025-04-20 02:05:57,917 INFO Saving best model at Epoch 37 +2025-04-20 02:06:32,506 INFO Epoch:38 train_loss:1.25873 +2025-04-20 02:06:48,948 INFO Epoch:38 val_res:0.590800 +2025-04-20 02:06:48,948 INFO Saving best model at Epoch 38 +2025-04-20 02:07:23,997 INFO Epoch:39 train_loss:1.25540 +2025-04-20 02:07:36,988 INFO Epoch:39 val_res:0.590400 +2025-04-20 02:08:09,058 INFO Epoch:40 train_loss:1.25233 +2025-04-20 02:08:21,936 INFO Epoch:40 val_res:0.589800 +2025-04-20 02:08:55,897 INFO Epoch:41 train_loss:1.22685 +2025-04-20 02:09:09,068 INFO Epoch:41 val_res:0.591200 +2025-04-20 02:09:09,069 INFO Saving best model at Epoch 41 +2025-04-20 02:09:43,504 INFO Epoch:42 train_loss:1.22717 +2025-04-20 02:09:58,741 INFO Epoch:42 val_res:0.591800 +2025-04-20 02:09:58,742 INFO Saving best model at Epoch 42 +2025-04-20 02:10:33,375 INFO Epoch:43 train_loss:1.22038 +2025-04-20 02:10:46,813 INFO Epoch:43 val_res:0.591000 +2025-04-20 02:11:19,469 INFO Epoch:44 train_loss:1.22409 +2025-04-20 02:11:32,468 INFO Epoch:44 val_res:0.589600 +2025-04-20 02:12:05,029 INFO Epoch:45 train_loss:1.22141 +2025-04-20 02:12:18,154 INFO Epoch:45 val_res:0.592400 +2025-04-20 02:12:18,154 INFO Saving best model at Epoch 45 +2025-04-20 02:12:52,026 INFO Epoch:46 train_loss:1.22499 +2025-04-20 02:13:05,274 INFO Epoch:46 val_res:0.591200 +2025-04-20 02:13:37,835 INFO Epoch:47 train_loss:1.21037 +2025-04-20 02:13:50,688 INFO Epoch:47 val_res:0.592200 +2025-04-20 02:14:23,249 INFO Epoch:48 train_loss:1.22230 +2025-04-20 02:14:35,979 INFO Epoch:48 val_res:0.591400 +2025-04-20 02:15:07,319 INFO Epoch:49 train_loss:1.22145 +2025-04-20 02:15:22,560 INFO Epoch:49 val_res:0.591400 +2025-04-20 02:15:55,403 INFO Epoch:50 train_loss:1.19477 +2025-04-20 02:16:08,364 INFO Epoch:50 val_res:0.587600 +2025-04-20 02:16:42,212 INFO Epoch:51 train_loss:1.18381 +2025-04-20 02:16:56,842 INFO Epoch:51 val_res:0.590800 +2025-04-20 02:17:29,313 INFO Epoch:52 train_loss:1.19426 +2025-04-20 02:17:43,783 INFO Epoch:52 val_res:0.592200 +2025-04-20 02:18:15,628 INFO Epoch:53 train_loss:1.15719 +2025-04-20 02:18:28,775 INFO Epoch:53 val_res:0.588000 +2025-04-20 02:19:01,775 INFO Epoch:54 train_loss:1.19409 +2025-04-20 02:19:14,798 INFO Epoch:54 val_res:0.589000 +2025-04-20 02:19:49,413 INFO Epoch:55 train_loss:1.17804 +2025-04-20 02:20:02,744 INFO Epoch:55 val_res:0.588600 +2025-04-20 02:20:36,220 INFO Epoch:56 train_loss:1.17556 +2025-04-20 02:20:51,778 INFO Epoch:56 val_res:0.586000 +2025-04-20 02:21:24,573 INFO Epoch:57 train_loss:1.18569 +2025-04-20 02:21:37,625 INFO Epoch:57 val_res:0.586000 +2025-04-20 02:22:10,337 INFO Epoch:58 train_loss:1.17195 +2025-04-20 02:22:23,499 INFO Epoch:58 val_res:0.586400 +2025-04-20 02:22:57,807 INFO Epoch:59 train_loss:1.22386 +2025-04-20 02:23:11,742 INFO Epoch:59 val_res:0.584200 +2025-04-20 02:23:44,808 INFO Epoch:60 train_loss:1.20701 +2025-04-20 02:24:00,870 INFO Epoch:60 val_res:0.586400 +2025-04-20 02:24:35,117 INFO Epoch:61 train_loss:1.16841 +2025-04-20 02:24:51,397 INFO Epoch:61 val_res:0.582000 +2025-04-20 02:25:24,364 INFO Epoch:62 train_loss:1.23530 +2025-04-20 02:25:40,956 INFO Epoch:62 val_res:0.584600 +2025-04-20 02:26:15,054 INFO Epoch:63 train_loss:1.20082 +2025-04-20 02:26:28,128 INFO Epoch:63 val_res:0.584400 +2025-04-20 02:27:01,689 INFO Epoch:64 train_loss:1.13326 +2025-04-20 02:27:14,686 INFO Epoch:64 val_res:0.581200 +2025-04-20 02:27:48,038 INFO Epoch:65 train_loss:1.14401 +2025-04-20 02:28:02,417 INFO Epoch:65 val_res:0.580400 +2025-04-20 02:28:38,378 INFO Epoch:66 train_loss:1.16885 +2025-04-20 02:28:51,871 INFO Epoch:66 val_res:0.581200 +2025-04-20 02:29:24,891 INFO Epoch:67 train_loss:1.18088 +2025-04-20 02:29:40,202 INFO Epoch:67 val_res:0.577400 +2025-04-20 02:30:13,574 INFO Epoch:68 train_loss:1.12171 +2025-04-20 02:30:28,986 INFO Epoch:68 val_res:0.581800 +2025-04-20 02:31:02,151 INFO Epoch:69 train_loss:1.13330 +2025-04-20 02:31:15,797 INFO Epoch:69 val_res:0.578000 +2025-04-20 02:31:49,944 INFO Epoch:70 train_loss:1.18618 +2025-04-20 02:32:03,088 INFO Epoch:70 val_res:0.579000 +2025-04-20 02:32:35,615 INFO Epoch:71 train_loss:0.51166 +2025-04-20 02:32:49,072 INFO Epoch:71 val_res:0.577800 +2025-04-20 02:33:20,895 INFO Epoch:72 train_loss:0.49015 +2025-04-20 02:33:33,880 INFO Epoch:72 val_res:0.578400 +2025-04-20 02:34:04,837 INFO Epoch:73 train_loss:0.48624 +2025-04-20 02:34:17,972 INFO Epoch:73 val_res:0.577000 +2025-04-20 02:34:50,591 INFO Epoch:74 train_loss:0.48401 +2025-04-20 02:35:03,842 INFO Epoch:74 val_res:0.578200 +2025-04-20 02:35:35,040 INFO Epoch:75 train_loss:0.48467 +2025-04-20 02:35:47,996 INFO Epoch:75 val_res:0.577400 +2025-04-20 02:36:19,520 INFO Epoch:76 train_loss:0.48203 +2025-04-20 02:36:32,372 INFO Epoch:76 val_res:0.577000 +2025-04-20 02:37:04,381 INFO Epoch:77 train_loss:0.48060 +2025-04-20 02:37:17,840 INFO Epoch:77 val_res:0.576200 +2025-04-20 02:37:49,355 INFO Epoch:78 train_loss:0.48369 +2025-04-20 02:38:03,481 INFO Epoch:78 val_res:0.577800 +2025-04-20 02:38:34,683 INFO Epoch:79 train_loss:0.48283 +2025-04-20 02:38:47,733 INFO Epoch:79 val_res:0.575000 +2025-04-20 02:39:19,222 INFO Epoch:80 train_loss:0.48105 +2025-04-20 02:39:32,363 INFO Epoch:80 val_res:0.576000 +2025-04-20 02:40:05,134 INFO Epoch:81 train_loss:0.48314 +2025-04-20 02:40:18,783 INFO Epoch:81 val_res:0.574800 +2025-04-20 02:40:51,087 INFO Epoch:82 train_loss:0.48342 +2025-04-20 02:41:04,733 INFO Epoch:82 val_res:0.574600 +2025-04-20 02:41:37,168 INFO Epoch:83 train_loss:0.48219 +2025-04-20 02:41:52,540 INFO Epoch:83 val_res:0.574600 +2025-04-20 02:42:24,818 INFO Epoch:84 train_loss:0.48613 +2025-04-20 02:42:37,878 INFO Epoch:84 val_res:0.575600 +2025-04-20 02:43:09,640 INFO Epoch:85 train_loss:0.48099 +2025-04-20 02:43:22,628 INFO Epoch:85 val_res:0.576000 +2025-04-20 02:43:55,970 INFO Epoch:86 train_loss:0.48199 +2025-04-20 02:44:09,061 INFO Epoch:86 val_res:0.574400 +2025-04-20 02:44:42,427 INFO Epoch:87 train_loss:0.48484 +2025-04-20 02:44:55,451 INFO Epoch:87 val_res:0.574800 +2025-04-20 02:45:27,533 INFO Epoch:88 train_loss:0.48574 +2025-04-20 02:45:40,728 INFO Epoch:88 val_res:0.574200 +2025-04-20 02:46:13,012 INFO Epoch:89 train_loss:0.48601 +2025-04-20 02:46:25,968 INFO Epoch:89 val_res:0.575000 +2025-04-20 02:46:57,715 INFO Epoch:90 train_loss:0.51160 +2025-04-20 02:47:10,630 INFO Epoch:90 val_res:0.574200 +2025-04-20 02:47:43,653 INFO Epoch:91 train_loss:0.51331 +2025-04-20 02:47:56,537 INFO Epoch:91 val_res:0.577000 +2025-04-20 02:48:29,638 INFO Epoch:92 train_loss:0.50735 +2025-04-20 02:48:42,936 INFO Epoch:92 val_res:0.572600 +2025-04-20 02:49:15,655 INFO Epoch:93 train_loss:0.49177 +2025-04-20 02:49:29,680 INFO Epoch:93 val_res:0.574600 +2025-04-20 02:50:02,242 INFO Epoch:94 train_loss:0.49170 +2025-04-20 02:50:15,824 INFO Epoch:94 val_res:0.570200 +2025-04-20 02:50:47,166 INFO Epoch:95 train_loss:0.54089 +2025-04-20 02:51:00,953 INFO Epoch:95 val_res:0.569600 +2025-04-20 02:51:34,020 INFO Epoch:96 train_loss:0.58343 +2025-04-20 02:51:50,416 INFO Epoch:96 val_res:0.573000 +2025-04-20 02:52:21,712 INFO Epoch:97 train_loss:0.55042 +2025-04-20 02:52:34,709 INFO Epoch:97 val_res:0.568800 +2025-04-20 02:53:08,011 INFO Epoch:98 train_loss:0.53179 +2025-04-20 02:53:24,515 INFO Epoch:98 val_res:0.571000 +2025-04-20 02:53:57,720 INFO Epoch:99 train_loss:0.51898 +2025-04-20 02:54:10,931 INFO Epoch:99 val_res:0.567600 +2025-04-20 02:54:11,100 INFO ===================================== +2025-04-20 02:54:11,101 INFO Start testing... +2025-04-20 02:54:11,101 INFO ===================================== +2025-04-20 02:54:24,435 INFO Incremental step 9 Testing res: 0.589400 +2025-04-20 02:54:24,440 INFO forgetting: 0.113778 +2025-04-20 02:54:24,441 INFO Average Accuracy: 0.707913 +2025-04-20 02:54:24,442 INFO Average Forgetting: 0.105722 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..b15691016623f8f33ff884fde7f955af80d17d29 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..9d324415709d7b7c415e6bc139c0fd6e0fb7baaa Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..527ae78e02ee271989b23799896bb572b17aeef8 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..21ca598473c7c58740a83a56b3af9bf32b61028b Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..77d4f825b4c76a592e95c91c2fea6eed34a1c325 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..4004f48433e217e3736dcb75015544b89d8815c7 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..463c132eea48ac7c852b683167e77d0b5573ee0e Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..f5ca12befe594396f6bc539406824255c32afefc Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..1e8e31dd439abfad53253ce6fc4c169f680c0ba1 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..ea93b513d1497304bf267136b7087562e95c346e Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a3c46ba10f3d9c05d091ec79bd2dc6382495bb20 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0876bf241bdda0851ef2b8b16c7d8d4c16297f45284e5595e8d10a270893757 +size 114106129 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..2864cdec9e91e22f76bc5e0664ddfe4e0bb3553d --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d6dee44810db2bca8ff9b5bdf7073092b3c8995b62a9b916d129d7feff9f7c6 +size 114161489 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ff5378b849a435f2050ba27faaf56769fab3b037 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c13de45181388e5151763873e80a2a51d8da86f10b3c985644b88c44bdcddb8 +size 114216977 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..6696d8423f3c38cf75d986e44d5fe2261bd0a8d2 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12b703d267cd6f6c61ad8f741df02f0ef945e2f29f4a4b29198aad4e6840385 +size 114272273 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..5d2ec02da91b422e7b0624723b4361531cdf5d72 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6becacce41430d927894d27150c0f157c8f7762accbff0ccc456c7decbf2be +size 114327569 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/train.log b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..eeb6b2b280ed7a35e02c8f8de4a4c47e9e31211e --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_False-seed_0/train.log @@ -0,0 +1,1148 @@ +2025-04-19 03:46:47,985 INFO Training start time: 2025-04-19 03:46:47.985003 +2025-04-19 03:46:49,778 INFO Incremental step: 0 +2025-04-19 03:49:50,382 INFO Epoch:0 train_loss:1.62565 +2025-04-19 03:49:54,737 INFO Epoch:0 val_res:0.602122 +2025-04-19 03:49:54,737 INFO Saving best model at Epoch 0 +2025-04-19 03:50:16,790 INFO Epoch:1 train_loss:0.76612 +2025-04-19 03:50:19,343 INFO Epoch:1 val_res:0.803714 +2025-04-19 03:50:19,344 INFO Saving best model at Epoch 1 +2025-04-19 03:50:34,823 INFO Epoch:2 train_loss:0.47780 +2025-04-19 03:50:37,461 INFO Epoch:2 val_res:0.867374 +2025-04-19 03:50:37,461 INFO Saving best model at Epoch 2 +2025-04-19 03:50:53,369 INFO Epoch:3 train_loss:0.34041 +2025-04-19 03:50:55,936 INFO Epoch:3 val_res:0.907162 +2025-04-19 03:50:55,936 INFO Saving best model at Epoch 3 +2025-04-19 03:51:11,894 INFO Epoch:4 train_loss:0.26224 +2025-04-19 03:51:14,562 INFO Epoch:4 val_res:0.917772 +2025-04-19 03:51:14,563 INFO Saving best model at Epoch 4 +2025-04-19 03:51:30,042 INFO Epoch:5 train_loss:0.21298 +2025-04-19 03:51:32,878 INFO Epoch:5 val_res:0.917772 +2025-04-19 03:51:45,492 INFO Epoch:6 train_loss:0.18117 +2025-04-19 03:51:48,132 INFO Epoch:6 val_res:0.925729 +2025-04-19 03:51:48,132 INFO Saving best model at Epoch 6 +2025-04-19 03:52:04,179 INFO Epoch:7 train_loss:0.15896 +2025-04-19 03:52:06,750 INFO Epoch:7 val_res:0.917772 +2025-04-19 03:52:19,549 INFO Epoch:8 train_loss:0.13977 +2025-04-19 03:52:22,109 INFO Epoch:8 val_res:0.920424 +2025-04-19 03:52:34,475 INFO Epoch:9 train_loss:0.12456 +2025-04-19 03:52:37,164 INFO Epoch:9 val_res:0.933687 +2025-04-19 03:52:37,164 INFO Saving best model at Epoch 9 +2025-04-19 03:52:53,051 INFO Epoch:10 train_loss:0.10835 +2025-04-19 03:52:55,995 INFO Epoch:10 val_res:0.933687 +2025-04-19 03:53:10,352 INFO Epoch:11 train_loss:0.10429 +2025-04-19 03:53:13,325 INFO Epoch:11 val_res:0.907162 +2025-04-19 03:53:27,477 INFO Epoch:12 train_loss:0.09043 +2025-04-19 03:53:30,930 INFO Epoch:12 val_res:0.925729 +2025-04-19 03:53:48,800 INFO Epoch:13 train_loss:0.08789 +2025-04-19 03:53:52,663 INFO Epoch:13 val_res:0.928382 +2025-04-19 03:54:07,222 INFO Epoch:14 train_loss:0.07048 +2025-04-19 03:54:10,192 INFO Epoch:14 val_res:0.936339 +2025-04-19 03:54:10,192 INFO Saving best model at Epoch 14 +2025-04-19 03:54:25,865 INFO Epoch:15 train_loss:0.06559 +2025-04-19 03:54:28,827 INFO Epoch:15 val_res:0.936339 +2025-04-19 03:54:43,518 INFO Epoch:16 train_loss:0.06032 +2025-04-19 03:54:46,441 INFO Epoch:16 val_res:0.936339 +2025-04-19 03:55:00,657 INFO Epoch:17 train_loss:0.04985 +2025-04-19 03:55:03,692 INFO Epoch:17 val_res:0.936339 +2025-04-19 03:55:18,170 INFO Epoch:18 train_loss:0.05060 +2025-04-19 03:55:21,233 INFO Epoch:18 val_res:0.933687 +2025-04-19 03:55:35,084 INFO Epoch:19 train_loss:0.04268 +2025-04-19 03:55:38,141 INFO Epoch:19 val_res:0.944297 +2025-04-19 03:55:38,141 INFO Saving best model at Epoch 19 +2025-04-19 03:55:55,130 INFO Epoch:20 train_loss:0.03442 +2025-04-19 03:55:58,286 INFO Epoch:20 val_res:0.941645 +2025-04-19 03:56:12,824 INFO Epoch:21 train_loss:0.03148 +2025-04-19 03:56:15,468 INFO Epoch:21 val_res:0.938992 +2025-04-19 03:56:29,203 INFO Epoch:22 train_loss:0.02918 +2025-04-19 03:56:32,214 INFO Epoch:22 val_res:0.933687 +2025-04-19 03:56:45,985 INFO Epoch:23 train_loss:0.02610 +2025-04-19 03:56:49,140 INFO Epoch:23 val_res:0.941645 +2025-04-19 03:57:03,536 INFO Epoch:24 train_loss:0.02255 +2025-04-19 03:57:06,357 INFO Epoch:24 val_res:0.936339 +2025-04-19 03:57:21,398 INFO Epoch:25 train_loss:0.02134 +2025-04-19 03:57:24,589 INFO Epoch:25 val_res:0.944297 +2025-04-19 03:57:38,883 INFO Epoch:26 train_loss:0.02162 +2025-04-19 03:57:41,755 INFO Epoch:26 val_res:0.938992 +2025-04-19 03:57:55,907 INFO Epoch:27 train_loss:0.02083 +2025-04-19 03:57:58,526 INFO Epoch:27 val_res:0.933687 +2025-04-19 03:58:11,006 INFO Epoch:28 train_loss:0.01769 +2025-04-19 03:58:13,630 INFO Epoch:28 val_res:0.938992 +2025-04-19 03:58:25,833 INFO Epoch:29 train_loss:0.01768 +2025-04-19 03:58:29,035 INFO Epoch:29 val_res:0.936339 +2025-04-19 03:58:42,302 INFO Epoch:30 train_loss:0.01859 +2025-04-19 03:58:45,207 INFO Epoch:30 val_res:0.917772 +2025-04-19 03:58:59,363 INFO Epoch:31 train_loss:0.01997 +2025-04-19 03:59:01,930 INFO Epoch:31 val_res:0.936339 +2025-04-19 03:59:15,032 INFO Epoch:32 train_loss:0.01712 +2025-04-19 03:59:17,626 INFO Epoch:32 val_res:0.938992 +2025-04-19 03:59:31,391 INFO Epoch:33 train_loss:0.01612 +2025-04-19 03:59:34,017 INFO Epoch:33 val_res:0.936339 +2025-04-19 03:59:47,680 INFO Epoch:34 train_loss:0.01419 +2025-04-19 03:59:50,430 INFO Epoch:34 val_res:0.938992 +2025-04-19 04:00:10,830 INFO Epoch:35 train_loss:0.01424 +2025-04-19 04:00:13,628 INFO Epoch:35 val_res:0.941645 +2025-04-19 04:00:27,416 INFO Epoch:36 train_loss:0.01429 +2025-04-19 04:00:30,583 INFO Epoch:36 val_res:0.941645 +2025-04-19 04:01:07,996 INFO Epoch:37 train_loss:0.01385 +2025-04-19 04:01:10,983 INFO Epoch:37 val_res:0.941645 +2025-04-19 04:01:49,189 INFO Epoch:38 train_loss:0.01252 +2025-04-19 04:01:54,724 INFO Epoch:38 val_res:0.931035 +2025-04-19 04:02:16,787 INFO Epoch:39 train_loss:0.01345 +2025-04-19 04:02:19,328 INFO Epoch:39 val_res:0.931035 +2025-04-19 04:02:31,890 INFO Epoch:40 train_loss:0.01202 +2025-04-19 04:02:34,899 INFO Epoch:40 val_res:0.938992 +2025-04-19 04:03:40,053 INFO Epoch:41 train_loss:0.01121 +2025-04-19 04:03:50,754 INFO Epoch:41 val_res:0.925729 +2025-04-19 04:04:10,085 INFO Epoch:42 train_loss:0.01136 +2025-04-19 04:04:13,064 INFO Epoch:42 val_res:0.933687 +2025-04-19 04:04:26,970 INFO Epoch:43 train_loss:0.01073 +2025-04-19 04:04:29,804 INFO Epoch:43 val_res:0.938992 +2025-04-19 04:04:44,177 INFO Epoch:44 train_loss:0.01272 +2025-04-19 04:04:47,321 INFO Epoch:44 val_res:0.936339 +2025-04-19 04:05:00,499 INFO Epoch:45 train_loss:0.01159 +2025-04-19 04:05:03,231 INFO Epoch:45 val_res:0.933687 +2025-04-19 04:05:15,900 INFO Epoch:46 train_loss:0.01186 +2025-04-19 04:05:18,777 INFO Epoch:46 val_res:0.925729 +2025-04-19 04:05:31,752 INFO Epoch:47 train_loss:0.01252 +2025-04-19 04:05:34,526 INFO Epoch:47 val_res:0.938992 +2025-04-19 04:05:47,018 INFO Epoch:48 train_loss:0.01030 +2025-04-19 04:05:49,855 INFO Epoch:48 val_res:0.933687 +2025-04-19 04:06:01,849 INFO Epoch:49 train_loss:0.00994 +2025-04-19 04:06:04,402 INFO Epoch:49 val_res:0.933687 +2025-04-19 04:06:17,529 INFO Epoch:50 train_loss:0.01002 +2025-04-19 04:06:20,255 INFO Epoch:50 val_res:0.933687 +2025-04-19 04:06:33,607 INFO Epoch:51 train_loss:0.01033 +2025-04-19 04:06:36,244 INFO Epoch:51 val_res:0.931035 +2025-04-19 04:06:50,184 INFO Epoch:52 train_loss:0.01023 +2025-04-19 04:06:53,267 INFO Epoch:52 val_res:0.931035 +2025-04-19 04:07:08,491 INFO Epoch:53 train_loss:0.00887 +2025-04-19 04:07:11,594 INFO Epoch:53 val_res:0.925729 +2025-04-19 04:07:28,217 INFO Epoch:54 train_loss:0.00947 +2025-04-19 04:07:31,239 INFO Epoch:54 val_res:0.933687 +2025-04-19 04:07:47,345 INFO Epoch:55 train_loss:0.00902 +2025-04-19 04:07:50,636 INFO Epoch:55 val_res:0.933687 +2025-04-19 04:08:05,658 INFO Epoch:56 train_loss:0.00960 +2025-04-19 04:08:08,958 INFO Epoch:56 val_res:0.917772 +2025-04-19 04:08:24,082 INFO Epoch:57 train_loss:0.01616 +2025-04-19 04:08:27,287 INFO Epoch:57 val_res:0.920424 +2025-04-19 04:08:43,147 INFO Epoch:58 train_loss:0.02067 +2025-04-19 04:08:46,342 INFO Epoch:58 val_res:0.933687 +2025-04-19 04:08:59,872 INFO Epoch:59 train_loss:0.01201 +2025-04-19 04:09:02,608 INFO Epoch:59 val_res:0.931035 +2025-04-19 04:09:15,699 INFO Epoch:60 train_loss:0.00809 +2025-04-19 04:09:18,463 INFO Epoch:60 val_res:0.936339 +2025-04-19 04:09:32,279 INFO Epoch:61 train_loss:0.00675 +2025-04-19 04:09:35,052 INFO Epoch:61 val_res:0.933687 +2025-04-19 04:09:48,680 INFO Epoch:62 train_loss:0.00629 +2025-04-19 04:09:51,505 INFO Epoch:62 val_res:0.931035 +2025-04-19 04:10:05,311 INFO Epoch:63 train_loss:0.00800 +2025-04-19 04:10:08,188 INFO Epoch:63 val_res:0.931035 +2025-04-19 04:10:21,002 INFO Epoch:64 train_loss:0.00805 +2025-04-19 04:10:23,860 INFO Epoch:64 val_res:0.928382 +2025-04-19 04:10:36,172 INFO Epoch:65 train_loss:0.00756 +2025-04-19 04:10:38,857 INFO Epoch:65 val_res:0.931035 +2025-04-19 04:10:51,705 INFO Epoch:66 train_loss:0.00896 +2025-04-19 04:10:54,471 INFO Epoch:66 val_res:0.933687 +2025-04-19 04:11:07,678 INFO Epoch:67 train_loss:0.00597 +2025-04-19 04:11:10,477 INFO Epoch:67 val_res:0.933687 +2025-04-19 04:11:23,274 INFO Epoch:68 train_loss:0.00675 +2025-04-19 04:11:26,233 INFO Epoch:68 val_res:0.938992 +2025-04-19 04:11:39,608 INFO Epoch:69 train_loss:0.00875 +2025-04-19 04:11:42,530 INFO Epoch:69 val_res:0.931035 +2025-04-19 04:11:54,971 INFO Epoch:70 train_loss:0.00791 +2025-04-19 04:11:57,648 INFO Epoch:70 val_res:0.933687 +2025-04-19 04:12:10,309 INFO Epoch:71 train_loss:0.00710 +2025-04-19 04:12:12,958 INFO Epoch:71 val_res:0.936339 +2025-04-19 04:12:25,619 INFO Epoch:72 train_loss:0.00732 +2025-04-19 04:12:28,364 INFO Epoch:72 val_res:0.936339 +2025-04-19 04:12:41,243 INFO Epoch:73 train_loss:0.00643 +2025-04-19 04:12:43,929 INFO Epoch:73 val_res:0.923077 +2025-04-19 04:12:58,379 INFO Epoch:74 train_loss:0.00693 +2025-04-19 04:13:01,483 INFO Epoch:74 val_res:0.933687 +2025-04-19 04:13:14,589 INFO Epoch:75 train_loss:0.00651 +2025-04-19 04:13:17,296 INFO Epoch:75 val_res:0.931035 +2025-04-19 04:13:30,649 INFO Epoch:76 train_loss:0.00733 +2025-04-19 04:13:33,552 INFO Epoch:76 val_res:0.923077 +2025-04-19 04:13:46,126 INFO Epoch:77 train_loss:0.01395 +2025-04-19 04:13:48,878 INFO Epoch:77 val_res:0.923077 +2025-04-19 04:14:03,416 INFO Epoch:78 train_loss:0.10932 +2025-04-19 04:14:06,241 INFO Epoch:78 val_res:0.888594 +2025-04-19 04:14:20,220 INFO Epoch:79 train_loss:1.57178 +2025-04-19 04:14:23,276 INFO Epoch:79 val_res:0.763926 +2025-04-19 04:14:36,733 INFO Epoch:80 train_loss:0.29897 +2025-04-19 04:14:39,553 INFO Epoch:80 val_res:0.864721 +2025-04-19 04:14:53,599 INFO Epoch:81 train_loss:0.09953 +2025-04-19 04:14:56,441 INFO Epoch:81 val_res:0.925729 +2025-04-19 04:15:10,629 INFO Epoch:82 train_loss:0.04148 +2025-04-19 04:15:14,125 INFO Epoch:82 val_res:0.925729 +2025-04-19 04:15:28,470 INFO Epoch:83 train_loss:0.01670 +2025-04-19 04:15:31,577 INFO Epoch:83 val_res:0.928382 +2025-04-19 04:15:46,422 INFO Epoch:84 train_loss:0.00599 +2025-04-19 04:15:49,384 INFO Epoch:84 val_res:0.936339 +2025-04-19 04:16:03,529 INFO Epoch:85 train_loss:0.00618 +2025-04-19 04:16:06,464 INFO Epoch:85 val_res:0.936339 +2025-04-19 04:16:20,542 INFO Epoch:86 train_loss:0.00451 +2025-04-19 04:16:23,530 INFO Epoch:86 val_res:0.933687 +2025-04-19 04:16:37,326 INFO Epoch:87 train_loss:0.00373 +2025-04-19 04:16:40,266 INFO Epoch:87 val_res:0.931035 +2025-04-19 04:16:57,191 INFO Epoch:88 train_loss:0.00338 +2025-04-19 04:17:00,533 INFO Epoch:88 val_res:0.936339 +2025-04-19 04:17:17,186 INFO Epoch:89 train_loss:0.00319 +2025-04-19 04:17:21,078 INFO Epoch:89 val_res:0.931035 +2025-04-19 04:17:39,317 INFO Epoch:90 train_loss:0.00302 +2025-04-19 04:17:42,838 INFO Epoch:90 val_res:0.928382 +2025-04-19 04:18:00,321 INFO Epoch:91 train_loss:0.00309 +2025-04-19 04:18:04,165 INFO Epoch:91 val_res:0.933687 +2025-04-19 04:18:20,467 INFO Epoch:92 train_loss:0.00286 +2025-04-19 04:18:23,505 INFO Epoch:92 val_res:0.936339 +2025-04-19 04:18:38,908 INFO Epoch:93 train_loss:0.00297 +2025-04-19 04:18:41,818 INFO Epoch:93 val_res:0.933687 +2025-04-19 04:18:56,461 INFO Epoch:94 train_loss:0.00283 +2025-04-19 04:19:00,084 INFO Epoch:94 val_res:0.933687 +2025-04-19 04:19:18,362 INFO Epoch:95 train_loss:0.00279 +2025-04-19 04:19:21,941 INFO Epoch:95 val_res:0.928382 +2025-04-19 04:19:37,111 INFO Epoch:96 train_loss:0.00283 +2025-04-19 04:19:40,072 INFO Epoch:96 val_res:0.923077 +2025-04-19 04:19:54,428 INFO Epoch:97 train_loss:0.00291 +2025-04-19 04:19:58,286 INFO Epoch:97 val_res:0.925729 +2025-04-19 04:20:15,421 INFO Epoch:98 train_loss:0.00306 +2025-04-19 04:20:18,552 INFO Epoch:98 val_res:0.925729 +2025-04-19 04:20:33,294 INFO Epoch:99 train_loss:0.00306 +2025-04-19 04:20:36,176 INFO Epoch:99 val_res:0.923077 +2025-04-19 04:20:36,747 INFO ===================================== +2025-04-19 04:20:36,747 INFO Start testing... +2025-04-19 04:20:36,748 INFO ===================================== +2025-04-19 04:20:42,549 INFO Incremental step 0 Testing res: 0.922043 +2025-04-19 04:20:42,553 INFO Incremental step: 1 +2025-04-19 04:23:37,632 INFO Epoch:0 train_loss:3.40926 +2025-04-19 04:24:10,018 INFO Epoch:0 val_res:0.425974 +2025-04-19 04:24:10,019 INFO Saving best model at Epoch 0 +2025-04-19 04:26:57,620 INFO Epoch:1 train_loss:2.02937 +2025-04-19 04:27:18,633 INFO Epoch:1 val_res:0.454545 +2025-04-19 04:27:18,633 INFO Saving best model at Epoch 1 +2025-04-19 04:28:53,559 INFO Epoch:2 train_loss:1.71165 +2025-04-19 04:29:06,912 INFO Epoch:2 val_res:0.474026 +2025-04-19 04:29:06,912 INFO Saving best model at Epoch 2 +2025-04-19 04:30:24,717 INFO Epoch:3 train_loss:1.60250 +2025-04-19 04:30:39,342 INFO Epoch:3 val_res:0.493506 +2025-04-19 04:30:39,343 INFO Saving best model at Epoch 3 +2025-04-19 04:31:28,095 INFO Epoch:4 train_loss:1.52555 +2025-04-19 04:31:35,453 INFO Epoch:4 val_res:0.533766 +2025-04-19 04:31:35,453 INFO Saving best model at Epoch 4 +2025-04-19 04:32:21,453 INFO Epoch:5 train_loss:1.48356 +2025-04-19 04:32:34,501 INFO Epoch:5 val_res:0.557143 +2025-04-19 04:32:34,501 INFO Saving best model at Epoch 5 +2025-04-19 04:33:15,926 INFO Epoch:6 train_loss:1.44942 +2025-04-19 04:33:21,795 INFO Epoch:6 val_res:0.559740 +2025-04-19 04:33:21,795 INFO Saving best model at Epoch 6 +2025-04-19 04:33:58,214 INFO Epoch:7 train_loss:1.41665 +2025-04-19 04:34:04,856 INFO Epoch:7 val_res:0.577922 +2025-04-19 04:34:04,857 INFO Saving best model at Epoch 7 +2025-04-19 04:34:47,459 INFO Epoch:8 train_loss:1.38962 +2025-04-19 04:34:53,558 INFO Epoch:8 val_res:0.576623 +2025-04-19 04:36:54,724 INFO Epoch:9 train_loss:1.35138 +2025-04-19 04:37:27,311 INFO Epoch:9 val_res:0.602597 +2025-04-19 04:37:27,311 INFO Saving best model at Epoch 9 +2025-04-19 04:40:30,029 INFO Epoch:10 train_loss:1.33060 +2025-04-19 04:40:57,471 INFO Epoch:10 val_res:0.620779 +2025-04-19 04:40:57,472 INFO Saving best model at Epoch 10 +2025-04-19 04:43:23,127 INFO Epoch:11 train_loss:1.31438 +2025-04-19 04:43:43,574 INFO Epoch:11 val_res:0.640260 +2025-04-19 04:43:43,575 INFO Saving best model at Epoch 11 +2025-04-19 04:45:52,959 INFO Epoch:12 train_loss:1.28534 +2025-04-19 04:46:18,048 INFO Epoch:12 val_res:0.641558 +2025-04-19 04:46:18,048 INFO Saving best model at Epoch 12 +2025-04-19 04:47:53,934 INFO Epoch:13 train_loss:1.25606 +2025-04-19 04:48:11,229 INFO Epoch:13 val_res:0.641558 +2025-04-19 04:49:23,823 INFO Epoch:14 train_loss:1.23697 +2025-04-19 04:49:44,240 INFO Epoch:14 val_res:0.657143 +2025-04-19 04:49:44,241 INFO Saving best model at Epoch 14 +2025-04-19 04:50:42,051 INFO Epoch:15 train_loss:1.21663 +2025-04-19 04:50:55,491 INFO Epoch:15 val_res:0.671429 +2025-04-19 04:50:55,492 INFO Saving best model at Epoch 15 +2025-04-19 04:51:34,522 INFO Epoch:16 train_loss:1.20212 +2025-04-19 04:51:48,920 INFO Epoch:16 val_res:0.681818 +2025-04-19 04:51:48,921 INFO Saving best model at Epoch 16 +2025-04-19 04:52:35,977 INFO Epoch:17 train_loss:1.18623 +2025-04-19 04:52:46,690 INFO Epoch:17 val_res:0.685714 +2025-04-19 04:52:46,690 INFO Saving best model at Epoch 17 +2025-04-19 04:53:30,716 INFO Epoch:18 train_loss:1.16536 +2025-04-19 04:53:40,962 INFO Epoch:18 val_res:0.711688 +2025-04-19 04:53:40,962 INFO Saving best model at Epoch 18 +2025-04-19 04:54:23,622 INFO Epoch:19 train_loss:1.15757 +2025-04-19 04:54:30,877 INFO Epoch:19 val_res:0.707792 +2025-04-19 04:55:08,318 INFO Epoch:20 train_loss:1.13739 +2025-04-19 04:55:15,616 INFO Epoch:20 val_res:0.720779 +2025-04-19 04:55:15,616 INFO Saving best model at Epoch 20 +2025-04-19 04:55:55,646 INFO Epoch:21 train_loss:1.11756 +2025-04-19 04:56:02,963 INFO Epoch:21 val_res:0.723377 +2025-04-19 04:56:02,963 INFO Saving best model at Epoch 21 +2025-04-19 04:56:47,058 INFO Epoch:22 train_loss:1.10925 +2025-04-19 04:56:54,197 INFO Epoch:22 val_res:0.712987 +2025-04-19 04:57:28,197 INFO Epoch:23 train_loss:1.09648 +2025-04-19 04:57:34,663 INFO Epoch:23 val_res:0.705195 +2025-04-19 04:58:15,523 INFO Epoch:24 train_loss:1.07908 +2025-04-19 04:58:21,338 INFO Epoch:24 val_res:0.710390 +2025-04-19 04:58:56,268 INFO Epoch:25 train_loss:1.05820 +2025-04-19 04:59:02,672 INFO Epoch:25 val_res:0.725974 +2025-04-19 04:59:02,672 INFO Saving best model at Epoch 25 +2025-04-19 04:59:44,960 INFO Epoch:26 train_loss:1.04699 +2025-04-19 04:59:51,787 INFO Epoch:26 val_res:0.722078 +2025-04-19 05:00:29,871 INFO Epoch:27 train_loss:1.03056 +2025-04-19 05:00:35,293 INFO Epoch:27 val_res:0.732468 +2025-04-19 05:00:35,293 INFO Saving best model at Epoch 27 +2025-04-19 05:01:14,108 INFO Epoch:28 train_loss:1.02696 +2025-04-19 05:01:20,785 INFO Epoch:28 val_res:0.735065 +2025-04-19 05:01:20,786 INFO Saving best model at Epoch 28 +2025-04-19 05:01:59,924 INFO Epoch:29 train_loss:1.02313 +2025-04-19 05:02:05,220 INFO Epoch:29 val_res:0.725974 +2025-04-19 05:02:37,495 INFO Epoch:30 train_loss:1.00420 +2025-04-19 05:02:43,750 INFO Epoch:30 val_res:0.716883 +2025-04-19 05:03:25,191 INFO Epoch:31 train_loss:0.98667 +2025-04-19 05:03:31,688 INFO Epoch:31 val_res:0.722078 +2025-04-19 05:04:05,776 INFO Epoch:32 train_loss:0.97126 +2025-04-19 05:04:11,452 INFO Epoch:32 val_res:0.742857 +2025-04-19 05:04:11,455 INFO Saving best model at Epoch 32 +2025-04-19 05:04:52,973 INFO Epoch:33 train_loss:0.96217 +2025-04-19 05:05:00,376 INFO Epoch:33 val_res:0.742857 +2025-04-19 05:05:38,170 INFO Epoch:34 train_loss:0.96651 +2025-04-19 05:05:44,307 INFO Epoch:34 val_res:0.720779 +2025-04-19 05:06:23,452 INFO Epoch:35 train_loss:0.96515 +2025-04-19 05:06:30,879 INFO Epoch:35 val_res:0.722078 +2025-04-19 05:07:07,960 INFO Epoch:36 train_loss:0.95187 +2025-04-19 05:07:13,664 INFO Epoch:36 val_res:0.724675 +2025-04-19 05:07:54,549 INFO Epoch:37 train_loss:0.94039 +2025-04-19 05:08:01,881 INFO Epoch:37 val_res:0.742857 +2025-04-19 05:08:37,507 INFO Epoch:38 train_loss:0.93198 +2025-04-19 05:08:43,658 INFO Epoch:38 val_res:0.714286 +2025-04-19 05:09:18,660 INFO Epoch:39 train_loss:0.91956 +2025-04-19 05:09:24,737 INFO Epoch:39 val_res:0.716883 +2025-04-19 05:10:00,948 INFO Epoch:40 train_loss:0.92577 +2025-04-19 05:10:07,278 INFO Epoch:40 val_res:0.722078 +2025-04-19 05:10:41,874 INFO Epoch:41 train_loss:0.93470 +2025-04-19 05:10:47,841 INFO Epoch:41 val_res:0.715584 +2025-04-19 05:11:26,772 INFO Epoch:42 train_loss:0.99328 +2025-04-19 05:11:42,788 INFO Epoch:42 val_res:0.700000 +2025-04-19 05:12:36,154 INFO Epoch:43 train_loss:0.97871 +2025-04-19 05:12:49,396 INFO Epoch:43 val_res:0.702597 +2025-04-19 05:13:24,204 INFO Epoch:44 train_loss:0.93015 +2025-04-19 05:13:30,050 INFO Epoch:44 val_res:0.710390 +2025-04-19 05:14:04,399 INFO Epoch:45 train_loss:0.91240 +2025-04-19 05:14:16,209 INFO Epoch:45 val_res:0.718182 +2025-04-19 05:14:50,259 INFO Epoch:46 train_loss:0.89944 +2025-04-19 05:14:58,783 INFO Epoch:46 val_res:0.715584 +2025-04-19 05:15:35,345 INFO Epoch:47 train_loss:0.88887 +2025-04-19 05:15:43,598 INFO Epoch:47 val_res:0.711688 +2025-04-19 05:16:18,667 INFO Epoch:48 train_loss:0.87911 +2025-04-19 05:16:31,513 INFO Epoch:48 val_res:0.719481 +2025-04-19 05:17:10,623 INFO Epoch:49 train_loss:0.87453 +2025-04-19 05:17:26,613 INFO Epoch:49 val_res:0.711688 +2025-04-19 05:18:05,391 INFO Epoch:50 train_loss:0.87329 +2025-04-19 05:18:18,990 INFO Epoch:50 val_res:0.718182 +2025-04-19 05:18:58,923 INFO Epoch:51 train_loss:0.88618 +2025-04-19 05:19:08,882 INFO Epoch:51 val_res:0.716883 +2025-04-19 05:19:51,483 INFO Epoch:52 train_loss:0.89022 +2025-04-19 05:19:57,172 INFO Epoch:52 val_res:0.709091 +2025-04-19 05:20:31,979 INFO Epoch:53 train_loss:0.87021 +2025-04-19 05:20:39,304 INFO Epoch:53 val_res:0.711688 +2025-04-19 05:21:17,654 INFO Epoch:54 train_loss:0.86242 +2025-04-19 05:21:25,176 INFO Epoch:54 val_res:0.719481 +2025-04-19 05:22:01,622 INFO Epoch:55 train_loss:0.84183 +2025-04-19 05:22:08,053 INFO Epoch:55 val_res:0.705195 +2025-04-19 05:22:42,636 INFO Epoch:56 train_loss:0.85741 +2025-04-19 05:22:49,200 INFO Epoch:56 val_res:0.720779 +2025-04-19 05:23:25,125 INFO Epoch:57 train_loss:0.85672 +2025-04-19 05:23:30,880 INFO Epoch:57 val_res:0.728571 +2025-04-19 05:24:06,240 INFO Epoch:58 train_loss:0.95925 +2025-04-19 05:24:12,857 INFO Epoch:58 val_res:0.688312 +2025-04-19 05:24:53,034 INFO Epoch:59 train_loss:0.91647 +2025-04-19 05:24:59,286 INFO Epoch:59 val_res:0.696104 +2025-04-19 05:25:35,015 INFO Epoch:60 train_loss:0.87850 +2025-04-19 05:25:42,252 INFO Epoch:60 val_res:0.684416 +2025-04-19 05:26:22,419 INFO Epoch:61 train_loss:0.89007 +2025-04-19 05:26:28,723 INFO Epoch:61 val_res:0.688312 +2025-04-19 05:27:01,743 INFO Epoch:62 train_loss:0.84503 +2025-04-19 05:27:07,894 INFO Epoch:62 val_res:0.700000 +2025-04-19 05:27:46,831 INFO Epoch:63 train_loss:0.82525 +2025-04-19 05:27:53,867 INFO Epoch:63 val_res:0.700000 +2025-04-19 05:28:33,879 INFO Epoch:64 train_loss:0.81594 +2025-04-19 05:28:40,322 INFO Epoch:64 val_res:0.703896 +2025-04-19 05:29:18,697 INFO Epoch:65 train_loss:0.80978 +2025-04-19 05:29:25,850 INFO Epoch:65 val_res:0.701299 +2025-04-19 05:30:07,877 INFO Epoch:66 train_loss:0.80601 +2025-04-19 05:30:14,940 INFO Epoch:66 val_res:0.720779 +2025-04-19 05:30:45,686 INFO Epoch:67 train_loss:0.81051 +2025-04-19 05:30:50,388 INFO Epoch:67 val_res:0.722078 +2025-04-19 05:31:26,497 INFO Epoch:68 train_loss:0.80772 +2025-04-19 05:31:34,083 INFO Epoch:68 val_res:0.727273 +2025-04-19 05:32:12,093 INFO Epoch:69 train_loss:0.83135 +2025-04-19 05:32:18,738 INFO Epoch:69 val_res:0.696104 +2025-04-19 05:32:56,498 INFO Epoch:70 train_loss:0.82357 +2025-04-19 05:33:03,904 INFO Epoch:70 val_res:0.716883 +2025-04-19 05:33:44,780 INFO Epoch:71 train_loss:0.89456 +2025-04-19 05:33:51,673 INFO Epoch:71 val_res:0.701299 +2025-04-19 05:34:28,976 INFO Epoch:72 train_loss:0.86626 +2025-04-19 05:34:36,675 INFO Epoch:72 val_res:0.702597 +2025-04-19 05:35:14,669 INFO Epoch:73 train_loss:0.84102 +2025-04-19 05:35:20,976 INFO Epoch:73 val_res:0.688312 +2025-04-19 05:35:57,065 INFO Epoch:74 train_loss:0.82426 +2025-04-19 05:36:03,283 INFO Epoch:74 val_res:0.692208 +2025-04-19 05:36:37,485 INFO Epoch:75 train_loss:0.80960 +2025-04-19 05:36:52,846 INFO Epoch:75 val_res:0.698701 +2025-04-19 05:37:31,160 INFO Epoch:76 train_loss:0.79076 +2025-04-19 05:37:42,658 INFO Epoch:76 val_res:0.710390 +2025-04-19 05:38:18,343 INFO Epoch:77 train_loss:0.78687 +2025-04-19 05:38:26,347 INFO Epoch:77 val_res:0.706493 +2025-04-19 05:39:02,189 INFO Epoch:78 train_loss:0.77189 +2025-04-19 05:39:13,731 INFO Epoch:78 val_res:0.702597 +2025-04-19 05:39:46,114 INFO Epoch:79 train_loss:0.76972 +2025-04-19 05:40:05,690 INFO Epoch:79 val_res:0.716883 +2025-04-19 05:40:43,064 INFO Epoch:80 train_loss:0.80443 +2025-04-19 05:40:54,104 INFO Epoch:80 val_res:0.703896 +2025-04-19 05:41:31,413 INFO Epoch:81 train_loss:0.79923 +2025-04-19 05:41:42,588 INFO Epoch:81 val_res:0.697403 +2025-04-19 05:42:19,092 INFO Epoch:82 train_loss:0.79771 +2025-04-19 05:42:29,715 INFO Epoch:82 val_res:0.703896 +2025-04-19 05:43:05,763 INFO Epoch:83 train_loss:0.79634 +2025-04-19 05:43:18,195 INFO Epoch:83 val_res:0.711688 +2025-04-19 05:43:53,145 INFO Epoch:84 train_loss:0.84117 +2025-04-19 05:44:02,266 INFO Epoch:84 val_res:0.689610 +2025-04-19 05:44:37,817 INFO Epoch:85 train_loss:0.83214 +2025-04-19 05:44:45,549 INFO Epoch:85 val_res:0.700000 +2025-04-19 05:45:20,710 INFO Epoch:86 train_loss:0.79619 +2025-04-19 05:45:28,236 INFO Epoch:86 val_res:0.693506 +2025-04-19 05:45:58,751 INFO Epoch:87 train_loss:0.77082 +2025-04-19 05:46:05,377 INFO Epoch:87 val_res:0.707792 +2025-04-19 05:46:40,894 INFO Epoch:88 train_loss:0.77415 +2025-04-19 05:46:47,502 INFO Epoch:88 val_res:0.709091 +2025-04-19 05:47:21,230 INFO Epoch:89 train_loss:0.76148 +2025-04-19 05:47:27,470 INFO Epoch:89 val_res:0.697403 +2025-04-19 05:48:02,359 INFO Epoch:90 train_loss:0.75037 +2025-04-19 05:48:08,100 INFO Epoch:90 val_res:0.712987 +2025-04-19 05:48:46,323 INFO Epoch:91 train_loss:0.77971 +2025-04-19 05:48:53,161 INFO Epoch:91 val_res:0.710390 +2025-04-19 05:49:32,706 INFO Epoch:92 train_loss:0.80017 +2025-04-19 05:49:37,646 INFO Epoch:92 val_res:0.697403 +2025-04-19 05:50:05,866 INFO Epoch:93 train_loss:0.77413 +2025-04-19 05:50:11,637 INFO Epoch:93 val_res:0.698701 +2025-04-19 05:50:45,593 INFO Epoch:94 train_loss:0.78228 +2025-04-19 05:50:51,380 INFO Epoch:94 val_res:0.710390 +2025-04-19 05:51:28,950 INFO Epoch:95 train_loss:0.80708 +2025-04-19 05:51:34,522 INFO Epoch:95 val_res:0.710390 +2025-04-19 05:52:07,421 INFO Epoch:96 train_loss:0.77408 +2025-04-19 05:52:14,069 INFO Epoch:96 val_res:0.696104 +2025-04-19 05:52:53,548 INFO Epoch:97 train_loss:0.76508 +2025-04-19 05:52:59,735 INFO Epoch:97 val_res:0.710390 +2025-04-19 05:53:33,112 INFO Epoch:98 train_loss:0.75498 +2025-04-19 05:53:38,151 INFO Epoch:98 val_res:0.710390 +2025-04-19 05:54:12,058 INFO Epoch:99 train_loss:0.75062 +2025-04-19 05:54:18,063 INFO Epoch:99 val_res:0.710390 +2025-04-19 05:54:18,447 INFO ===================================== +2025-04-19 05:54:18,448 INFO Start testing... +2025-04-19 05:54:18,448 INFO ===================================== +2025-04-19 05:54:58,273 INFO Incremental step 1 Testing res: 0.715584 +2025-04-19 05:54:58,275 INFO forgetting: 0.166667 +2025-04-19 05:54:58,280 INFO Incremental step: 2 +2025-04-19 05:59:27,755 INFO Epoch:0 train_loss:4.87681 +2025-04-19 05:59:53,898 INFO Epoch:0 val_res:0.479167 +2025-04-19 05:59:53,899 INFO Saving best model at Epoch 0 +2025-04-19 06:01:24,478 INFO Epoch:1 train_loss:2.29834 +2025-04-19 06:01:36,225 INFO Epoch:1 val_res:0.500868 +2025-04-19 06:01:36,225 INFO Saving best model at Epoch 1 +2025-04-19 06:02:42,771 INFO Epoch:2 train_loss:1.73895 +2025-04-19 06:02:49,990 INFO Epoch:2 val_res:0.519965 +2025-04-19 06:02:49,990 INFO Saving best model at Epoch 2 +2025-04-19 06:03:25,733 INFO Epoch:3 train_loss:1.56418 +2025-04-19 06:03:33,184 INFO Epoch:3 val_res:0.536458 +2025-04-19 06:03:33,184 INFO Saving best model at Epoch 3 +2025-04-19 06:04:06,736 INFO Epoch:4 train_loss:1.48183 +2025-04-19 06:04:15,256 INFO Epoch:4 val_res:0.559028 +2025-04-19 06:04:15,257 INFO Saving best model at Epoch 4 +2025-04-19 06:04:49,973 INFO Epoch:5 train_loss:1.43394 +2025-04-19 06:04:58,493 INFO Epoch:5 val_res:0.573785 +2025-04-19 06:04:58,494 INFO Saving best model at Epoch 5 +2025-04-19 06:05:38,488 INFO Epoch:6 train_loss:1.38884 +2025-04-19 06:05:52,321 INFO Epoch:6 val_res:0.579861 +2025-04-19 06:05:52,321 INFO Saving best model at Epoch 6 +2025-04-19 06:06:31,542 INFO Epoch:7 train_loss:1.36690 +2025-04-19 06:06:45,787 INFO Epoch:7 val_res:0.584201 +2025-04-19 06:06:45,788 INFO Saving best model at Epoch 7 +2025-04-19 06:07:35,745 INFO Epoch:8 train_loss:1.33510 +2025-04-19 06:07:42,686 INFO Epoch:8 val_res:0.586806 +2025-04-19 06:07:42,687 INFO Saving best model at Epoch 8 +2025-04-19 06:08:20,788 INFO Epoch:9 train_loss:1.31555 +2025-04-19 06:08:29,208 INFO Epoch:9 val_res:0.596354 +2025-04-19 06:08:29,209 INFO Saving best model at Epoch 9 +2025-04-19 06:09:05,592 INFO Epoch:10 train_loss:1.29283 +2025-04-19 06:09:13,789 INFO Epoch:10 val_res:0.594618 +2025-04-19 06:09:46,403 INFO Epoch:11 train_loss:1.27127 +2025-04-19 06:09:53,189 INFO Epoch:11 val_res:0.598090 +2025-04-19 06:09:53,189 INFO Saving best model at Epoch 11 +2025-04-19 06:10:28,100 INFO Epoch:12 train_loss:1.25132 +2025-04-19 06:10:35,894 INFO Epoch:12 val_res:0.602431 +2025-04-19 06:10:35,894 INFO Saving best model at Epoch 12 +2025-04-19 06:11:11,603 INFO Epoch:13 train_loss:1.23743 +2025-04-19 06:11:18,309 INFO Epoch:13 val_res:0.613715 +2025-04-19 06:11:18,309 INFO Saving best model at Epoch 13 +2025-04-19 06:11:53,364 INFO Epoch:14 train_loss:1.21659 +2025-04-19 06:12:00,910 INFO Epoch:14 val_res:0.609375 +2025-04-19 06:12:37,274 INFO Epoch:15 train_loss:1.19727 +2025-04-19 06:12:45,441 INFO Epoch:15 val_res:0.617188 +2025-04-19 06:12:45,441 INFO Saving best model at Epoch 15 +2025-04-19 06:13:21,220 INFO Epoch:16 train_loss:1.18189 +2025-04-19 06:13:28,026 INFO Epoch:16 val_res:0.622396 +2025-04-19 06:13:28,026 INFO Saving best model at Epoch 16 +2025-04-19 06:14:00,740 INFO Epoch:17 train_loss:1.17316 +2025-04-19 06:14:08,194 INFO Epoch:17 val_res:0.623264 +2025-04-19 06:14:08,195 INFO Saving best model at Epoch 17 +2025-04-19 06:14:44,652 INFO Epoch:18 train_loss:1.15310 +2025-04-19 06:14:51,688 INFO Epoch:18 val_res:0.626736 +2025-04-19 06:14:51,688 INFO Saving best model at Epoch 18 +2025-04-19 06:15:22,929 INFO Epoch:19 train_loss:1.13608 +2025-04-19 06:15:29,957 INFO Epoch:19 val_res:0.618924 +2025-04-19 06:16:06,453 INFO Epoch:20 train_loss:1.11418 +2025-04-19 06:16:13,837 INFO Epoch:20 val_res:0.624132 +2025-04-19 06:16:47,752 INFO Epoch:21 train_loss:1.10407 +2025-04-19 06:16:54,664 INFO Epoch:21 val_res:0.626736 +2025-04-19 06:17:27,643 INFO Epoch:22 train_loss:1.09182 +2025-04-19 06:17:35,596 INFO Epoch:22 val_res:0.627604 +2025-04-19 06:17:35,597 INFO Saving best model at Epoch 22 +2025-04-19 06:18:17,406 INFO Epoch:23 train_loss:1.07376 +2025-04-19 06:18:26,045 INFO Epoch:23 val_res:0.630208 +2025-04-19 06:18:26,046 INFO Saving best model at Epoch 23 +2025-04-19 06:18:59,925 INFO Epoch:24 train_loss:1.06931 +2025-04-19 06:19:06,250 INFO Epoch:24 val_res:0.632812 +2025-04-19 06:19:06,250 INFO Saving best model at Epoch 24 +2025-04-19 06:19:44,199 INFO Epoch:25 train_loss:1.05673 +2025-04-19 06:19:52,120 INFO Epoch:25 val_res:0.634549 +2025-04-19 06:19:52,120 INFO Saving best model at Epoch 25 +2025-04-19 06:20:29,358 INFO Epoch:26 train_loss:1.05198 +2025-04-19 06:20:36,362 INFO Epoch:26 val_res:0.635417 +2025-04-19 06:20:36,362 INFO Saving best model at Epoch 26 +2025-04-19 06:21:10,402 INFO Epoch:27 train_loss:1.03681 +2025-04-19 06:21:18,528 INFO Epoch:27 val_res:0.639757 +2025-04-19 06:21:18,529 INFO Saving best model at Epoch 27 +2025-04-19 06:21:56,293 INFO Epoch:28 train_loss:1.04370 +2025-04-19 06:22:03,551 INFO Epoch:28 val_res:0.648438 +2025-04-19 06:22:03,551 INFO Saving best model at Epoch 28 +2025-04-19 06:22:35,843 INFO Epoch:29 train_loss:1.00874 +2025-04-19 06:22:43,274 INFO Epoch:29 val_res:0.649306 +2025-04-19 06:22:43,274 INFO Saving best model at Epoch 29 +2025-04-19 06:23:19,283 INFO Epoch:30 train_loss:1.00953 +2025-04-19 06:23:26,841 INFO Epoch:30 val_res:0.644097 +2025-04-19 06:23:58,105 INFO Epoch:31 train_loss:0.99577 +2025-04-19 06:24:04,764 INFO Epoch:31 val_res:0.651042 +2025-04-19 06:24:04,765 INFO Saving best model at Epoch 31 +2025-04-19 06:24:43,106 INFO Epoch:32 train_loss:0.99073 +2025-04-19 06:24:50,036 INFO Epoch:32 val_res:0.657118 +2025-04-19 06:24:50,036 INFO Saving best model at Epoch 32 +2025-04-19 06:25:28,252 INFO Epoch:33 train_loss:0.98055 +2025-04-19 06:25:36,135 INFO Epoch:33 val_res:0.665799 +2025-04-19 06:25:36,135 INFO Saving best model at Epoch 33 +2025-04-19 06:26:13,716 INFO Epoch:34 train_loss:0.97531 +2025-04-19 06:26:21,398 INFO Epoch:34 val_res:0.664931 +2025-04-19 06:26:55,297 INFO Epoch:35 train_loss:0.96868 +2025-04-19 06:27:02,604 INFO Epoch:35 val_res:0.664062 +2025-04-19 06:27:36,923 INFO Epoch:36 train_loss:0.95821 +2025-04-19 06:27:43,169 INFO Epoch:36 val_res:0.663194 +2025-04-19 06:28:17,739 INFO Epoch:37 train_loss:0.94475 +2025-04-19 06:28:26,104 INFO Epoch:37 val_res:0.671875 +2025-04-19 06:28:26,104 INFO Saving best model at Epoch 37 +2025-04-19 06:29:02,645 INFO Epoch:38 train_loss:0.92842 +2025-04-19 06:29:11,698 INFO Epoch:38 val_res:0.668403 +2025-04-19 06:29:52,786 INFO Epoch:39 train_loss:0.92660 +2025-04-19 06:30:01,060 INFO Epoch:39 val_res:0.672743 +2025-04-19 06:30:01,060 INFO Saving best model at Epoch 39 +2025-04-19 06:30:37,121 INFO Epoch:40 train_loss:0.94408 +2025-04-19 06:30:44,168 INFO Epoch:40 val_res:0.673611 +2025-04-19 06:30:44,168 INFO Saving best model at Epoch 40 +2025-04-19 06:31:16,368 INFO Epoch:41 train_loss:0.91253 +2025-04-19 06:31:22,505 INFO Epoch:41 val_res:0.669271 +2025-04-19 06:31:56,230 INFO Epoch:42 train_loss:0.90337 +2025-04-19 06:32:03,587 INFO Epoch:42 val_res:0.657118 +2025-04-19 06:32:35,284 INFO Epoch:43 train_loss:0.90887 +2025-04-19 06:32:42,081 INFO Epoch:43 val_res:0.671007 +2025-04-19 06:33:15,458 INFO Epoch:44 train_loss:0.99020 +2025-04-19 06:33:23,104 INFO Epoch:44 val_res:0.669271 +2025-04-19 06:33:59,536 INFO Epoch:45 train_loss:0.95252 +2025-04-19 06:34:06,300 INFO Epoch:45 val_res:0.667535 +2025-04-19 06:34:38,864 INFO Epoch:46 train_loss:0.90053 +2025-04-19 06:34:45,507 INFO Epoch:46 val_res:0.672743 +2025-04-19 06:35:19,238 INFO Epoch:47 train_loss:0.88902 +2025-04-19 06:35:26,788 INFO Epoch:47 val_res:0.678819 +2025-04-19 06:35:26,788 INFO Saving best model at Epoch 47 +2025-04-19 06:36:05,215 INFO Epoch:48 train_loss:0.89029 +2025-04-19 06:36:12,441 INFO Epoch:48 val_res:0.678819 +2025-04-19 06:36:44,329 INFO Epoch:49 train_loss:0.87896 +2025-04-19 06:36:51,419 INFO Epoch:49 val_res:0.674479 +2025-04-19 06:37:23,887 INFO Epoch:50 train_loss:0.87623 +2025-04-19 06:37:30,588 INFO Epoch:50 val_res:0.680556 +2025-04-19 06:37:30,589 INFO Saving best model at Epoch 50 +2025-04-19 06:38:05,359 INFO Epoch:51 train_loss:0.85635 +2025-04-19 06:38:12,202 INFO Epoch:51 val_res:0.677083 +2025-04-19 06:38:44,146 INFO Epoch:52 train_loss:0.85554 +2025-04-19 06:38:50,908 INFO Epoch:52 val_res:0.675347 +2025-04-19 06:39:19,354 INFO Epoch:53 train_loss:0.85034 +2025-04-19 06:39:25,383 INFO Epoch:53 val_res:0.669271 +2025-04-19 06:40:00,562 INFO Epoch:54 train_loss:0.90799 +2025-04-19 06:40:07,144 INFO Epoch:54 val_res:0.669271 +2025-04-19 06:40:40,918 INFO Epoch:55 train_loss:0.86383 +2025-04-19 06:40:47,307 INFO Epoch:55 val_res:0.660590 +2025-04-19 06:41:21,816 INFO Epoch:56 train_loss:0.85684 +2025-04-19 06:41:29,850 INFO Epoch:56 val_res:0.680556 +2025-04-19 06:42:03,405 INFO Epoch:57 train_loss:0.86336 +2025-04-19 06:42:10,522 INFO Epoch:57 val_res:0.670139 +2025-04-19 06:42:41,218 INFO Epoch:58 train_loss:0.83456 +2025-04-19 06:42:47,172 INFO Epoch:58 val_res:0.667535 +2025-04-19 06:43:21,453 INFO Epoch:59 train_loss:0.84994 +2025-04-19 06:43:28,450 INFO Epoch:59 val_res:0.678819 +2025-04-19 06:44:01,763 INFO Epoch:60 train_loss:0.84083 +2025-04-19 06:44:08,941 INFO Epoch:60 val_res:0.677083 +2025-04-19 06:44:42,667 INFO Epoch:61 train_loss:0.83240 +2025-04-19 06:44:49,379 INFO Epoch:61 val_res:0.664062 +2025-04-19 06:45:25,458 INFO Epoch:62 train_loss:0.83008 +2025-04-19 06:45:32,021 INFO Epoch:62 val_res:0.666667 +2025-04-19 06:46:05,817 INFO Epoch:63 train_loss:0.85873 +2025-04-19 06:46:13,530 INFO Epoch:63 val_res:0.670139 +2025-04-19 06:46:47,857 INFO Epoch:64 train_loss:0.84366 +2025-04-19 06:46:54,813 INFO Epoch:64 val_res:0.662326 +2025-04-19 06:47:25,051 INFO Epoch:65 train_loss:0.84501 +2025-04-19 06:47:30,866 INFO Epoch:65 val_res:0.668403 +2025-04-19 06:48:07,072 INFO Epoch:66 train_loss:0.85474 +2025-04-19 06:48:14,401 INFO Epoch:66 val_res:0.662326 +2025-04-19 06:48:48,207 INFO Epoch:67 train_loss:0.82530 +2025-04-19 06:48:56,969 INFO Epoch:67 val_res:0.677951 +2025-04-19 06:49:34,980 INFO Epoch:68 train_loss:0.84030 +2025-04-19 06:49:42,743 INFO Epoch:68 val_res:0.662326 +2025-04-19 06:50:12,854 INFO Epoch:69 train_loss:0.80558 +2025-04-19 06:50:18,226 INFO Epoch:69 val_res:0.663194 +2025-04-19 06:50:53,601 INFO Epoch:70 train_loss:0.84893 +2025-04-19 06:51:00,865 INFO Epoch:70 val_res:0.659722 +2025-04-19 06:51:36,608 INFO Epoch:71 train_loss:0.83335 +2025-04-19 06:51:43,250 INFO Epoch:71 val_res:0.679688 +2025-04-19 06:52:14,996 INFO Epoch:72 train_loss:0.80863 +2025-04-19 06:52:22,444 INFO Epoch:72 val_res:0.661458 +2025-04-19 06:52:57,255 INFO Epoch:73 train_loss:0.78974 +2025-04-19 06:53:03,739 INFO Epoch:73 val_res:0.669271 +2025-04-19 06:53:33,320 INFO Epoch:74 train_loss:0.78724 +2025-04-19 06:53:39,590 INFO Epoch:74 val_res:0.656250 +2025-04-19 06:54:13,399 INFO Epoch:75 train_loss:0.79745 +2025-04-19 06:54:20,372 INFO Epoch:75 val_res:0.671007 +2025-04-19 06:54:55,441 INFO Epoch:76 train_loss:0.81145 +2025-04-19 06:55:01,787 INFO Epoch:76 val_res:0.675347 +2025-04-19 06:55:37,955 INFO Epoch:77 train_loss:1.06028 +2025-04-19 06:55:46,780 INFO Epoch:77 val_res:0.653646 +2025-04-19 06:56:21,838 INFO Epoch:78 train_loss:1.51688 +2025-04-19 06:56:27,558 INFO Epoch:78 val_res:0.653646 +2025-04-19 06:57:00,631 INFO Epoch:79 train_loss:1.14797 +2025-04-19 06:57:08,938 INFO Epoch:79 val_res:0.636285 +2025-04-19 06:57:43,976 INFO Epoch:80 train_loss:0.92409 +2025-04-19 06:57:52,457 INFO Epoch:80 val_res:0.638021 +2025-04-19 06:58:24,661 INFO Epoch:81 train_loss:0.82360 +2025-04-19 06:58:32,350 INFO Epoch:81 val_res:0.650174 +2025-04-19 06:59:06,694 INFO Epoch:82 train_loss:0.78975 +2025-04-19 06:59:14,280 INFO Epoch:82 val_res:0.660590 +2025-04-19 06:59:47,648 INFO Epoch:83 train_loss:0.77555 +2025-04-19 06:59:56,051 INFO Epoch:83 val_res:0.657986 +2025-04-19 07:00:26,306 INFO Epoch:84 train_loss:0.76848 +2025-04-19 07:00:33,482 INFO Epoch:84 val_res:0.654514 +2025-04-19 07:01:08,677 INFO Epoch:85 train_loss:0.76943 +2025-04-19 07:01:15,971 INFO Epoch:85 val_res:0.655382 +2025-04-19 07:01:52,634 INFO Epoch:86 train_loss:0.76630 +2025-04-19 07:02:00,651 INFO Epoch:86 val_res:0.655382 +2025-04-19 07:02:33,352 INFO Epoch:87 train_loss:0.75466 +2025-04-19 07:02:39,969 INFO Epoch:87 val_res:0.660590 +2025-04-19 07:03:16,984 INFO Epoch:88 train_loss:0.75210 +2025-04-19 07:03:24,530 INFO Epoch:88 val_res:0.662326 +2025-04-19 07:03:58,917 INFO Epoch:89 train_loss:0.75506 +2025-04-19 07:04:04,938 INFO Epoch:89 val_res:0.658854 +2025-04-19 07:04:36,622 INFO Epoch:90 train_loss:0.75538 +2025-04-19 07:04:44,922 INFO Epoch:90 val_res:0.662326 +2025-04-19 07:05:19,586 INFO Epoch:91 train_loss:0.76074 +2025-04-19 07:05:27,216 INFO Epoch:91 val_res:0.660590 +2025-04-19 07:06:03,272 INFO Epoch:92 train_loss:0.75672 +2025-04-19 07:06:10,855 INFO Epoch:92 val_res:0.659722 +2025-04-19 07:06:44,081 INFO Epoch:93 train_loss:0.75573 +2025-04-19 07:06:53,538 INFO Epoch:93 val_res:0.660590 +2025-04-19 07:07:29,323 INFO Epoch:94 train_loss:0.74856 +2025-04-19 07:07:37,481 INFO Epoch:94 val_res:0.657986 +2025-04-19 07:08:09,762 INFO Epoch:95 train_loss:0.75183 +2025-04-19 07:08:15,443 INFO Epoch:95 val_res:0.657986 +2025-04-19 07:08:49,420 INFO Epoch:96 train_loss:0.75036 +2025-04-19 07:08:57,864 INFO Epoch:96 val_res:0.667535 +2025-04-19 07:09:32,692 INFO Epoch:97 train_loss:0.76152 +2025-04-19 07:09:39,092 INFO Epoch:97 val_res:0.655382 +2025-04-19 07:10:15,688 INFO Epoch:98 train_loss:0.75813 +2025-04-19 07:10:24,397 INFO Epoch:98 val_res:0.660590 +2025-04-19 07:10:56,274 INFO Epoch:99 train_loss:0.76099 +2025-04-19 07:11:03,226 INFO Epoch:99 val_res:0.656250 +2025-04-19 07:11:03,523 INFO ===================================== +2025-04-19 07:11:03,523 INFO Start testing... +2025-04-19 07:11:03,524 INFO ===================================== +2025-04-19 07:11:58,813 INFO Incremental step 2 Testing res: 0.661179 +2025-04-19 07:11:58,816 INFO forgetting: 0.135516 +2025-04-19 07:11:58,824 INFO Incremental step: 3 +2025-04-19 07:14:47,536 INFO Epoch:0 train_loss:4.24306 +2025-04-19 07:15:15,921 INFO Epoch:0 val_res:0.480545 +2025-04-19 07:15:15,922 INFO Saving best model at Epoch 0 +2025-04-19 07:16:01,224 INFO Epoch:1 train_loss:1.92735 +2025-04-19 07:16:16,791 INFO Epoch:1 val_res:0.498054 +2025-04-19 07:16:16,797 INFO Saving best model at Epoch 1 +2025-04-19 07:18:21,244 INFO Epoch:2 train_loss:1.48038 +2025-04-19 07:18:49,097 INFO Epoch:2 val_res:0.514916 +2025-04-19 07:18:49,098 INFO Saving best model at Epoch 2 +2025-04-19 07:19:50,307 INFO Epoch:3 train_loss:1.34420 +2025-04-19 07:20:02,821 INFO Epoch:3 val_res:0.525940 +2025-04-19 07:20:02,823 INFO Saving best model at Epoch 3 +2025-04-19 07:20:47,179 INFO Epoch:4 train_loss:1.27364 +2025-04-19 07:20:57,181 INFO Epoch:4 val_res:0.536316 +2025-04-19 07:20:57,185 INFO Saving best model at Epoch 4 +2025-04-19 07:21:36,395 INFO Epoch:5 train_loss:1.22754 +2025-04-19 07:21:45,873 INFO Epoch:5 val_res:0.547990 +2025-04-19 07:21:45,874 INFO Saving best model at Epoch 5 +2025-04-19 07:22:23,070 INFO Epoch:6 train_loss:1.20520 +2025-04-19 07:22:33,313 INFO Epoch:6 val_res:0.555772 +2025-04-19 07:22:33,314 INFO Saving best model at Epoch 6 +2025-04-19 07:23:18,341 INFO Epoch:7 train_loss:1.18266 +2025-04-19 07:23:28,062 INFO Epoch:7 val_res:0.553178 +2025-04-19 07:24:05,824 INFO Epoch:8 train_loss:1.15654 +2025-04-19 07:24:14,045 INFO Epoch:8 val_res:0.562257 +2025-04-19 07:24:14,052 INFO Saving best model at Epoch 8 +2025-04-19 07:24:56,655 INFO Epoch:9 train_loss:1.14270 +2025-04-19 07:25:04,423 INFO Epoch:9 val_res:0.582361 +2025-04-19 07:25:04,423 INFO Saving best model at Epoch 9 +2025-04-19 07:25:43,391 INFO Epoch:10 train_loss:1.12159 +2025-04-19 07:25:52,043 INFO Epoch:10 val_res:0.587549 +2025-04-19 07:25:52,044 INFO Saving best model at Epoch 10 +2025-04-19 07:26:33,219 INFO Epoch:11 train_loss:1.09855 +2025-04-19 07:26:43,919 INFO Epoch:11 val_res:0.584306 +2025-04-19 07:27:21,361 INFO Epoch:12 train_loss:1.10312 +2025-04-19 07:27:29,575 INFO Epoch:12 val_res:0.588197 +2025-04-19 07:27:29,579 INFO Saving best model at Epoch 12 +2025-04-19 07:28:09,127 INFO Epoch:13 train_loss:1.08337 +2025-04-19 07:28:18,618 INFO Epoch:13 val_res:0.590143 +2025-04-19 07:28:18,625 INFO Saving best model at Epoch 13 +2025-04-19 07:29:00,792 INFO Epoch:14 train_loss:1.06671 +2025-04-19 07:29:09,387 INFO Epoch:14 val_res:0.598573 +2025-04-19 07:29:09,395 INFO Saving best model at Epoch 14 +2025-04-19 07:29:48,924 INFO Epoch:15 train_loss:1.05556 +2025-04-19 07:29:57,889 INFO Epoch:15 val_res:0.592088 +2025-04-19 07:30:33,956 INFO Epoch:16 train_loss:1.07518 +2025-04-19 07:30:42,660 INFO Epoch:16 val_res:0.607004 +2025-04-19 07:30:42,661 INFO Saving best model at Epoch 16 +2025-04-19 07:31:22,104 INFO Epoch:17 train_loss:1.03924 +2025-04-19 07:31:30,014 INFO Epoch:17 val_res:0.619974 +2025-04-19 07:31:30,015 INFO Saving best model at Epoch 17 +2025-04-19 07:32:06,891 INFO Epoch:18 train_loss:1.03372 +2025-04-19 07:32:15,280 INFO Epoch:18 val_res:0.621920 +2025-04-19 07:32:15,283 INFO Saving best model at Epoch 18 +2025-04-19 07:32:53,060 INFO Epoch:19 train_loss:0.99902 +2025-04-19 07:33:01,711 INFO Epoch:19 val_res:0.622568 +2025-04-19 07:33:01,716 INFO Saving best model at Epoch 19 +2025-04-19 07:33:42,573 INFO Epoch:20 train_loss:0.99964 +2025-04-19 07:33:50,484 INFO Epoch:20 val_res:0.624514 +2025-04-19 07:33:50,488 INFO Saving best model at Epoch 20 +2025-04-19 07:34:27,655 INFO Epoch:21 train_loss:0.99769 +2025-04-19 07:34:35,586 INFO Epoch:21 val_res:0.612192 +2025-04-19 07:35:10,873 INFO Epoch:22 train_loss:1.01795 +2025-04-19 07:35:18,434 INFO Epoch:22 val_res:0.628405 +2025-04-19 07:35:18,439 INFO Saving best model at Epoch 22 +2025-04-19 07:35:55,437 INFO Epoch:23 train_loss:1.01244 +2025-04-19 07:36:02,829 INFO Epoch:23 val_res:0.627108 +2025-04-19 07:36:39,624 INFO Epoch:24 train_loss:0.98842 +2025-04-19 07:36:47,944 INFO Epoch:24 val_res:0.631647 +2025-04-19 07:36:47,950 INFO Saving best model at Epoch 24 +2025-04-19 07:37:26,814 INFO Epoch:25 train_loss:0.96548 +2025-04-19 07:37:35,219 INFO Epoch:25 val_res:0.642023 +2025-04-19 07:37:35,222 INFO Saving best model at Epoch 25 +2025-04-19 07:38:11,609 INFO Epoch:26 train_loss:0.98754 +2025-04-19 07:38:19,210 INFO Epoch:26 val_res:0.650454 +2025-04-19 07:38:19,210 INFO Saving best model at Epoch 26 +2025-04-19 07:38:56,243 INFO Epoch:27 train_loss:0.96667 +2025-04-19 07:39:05,076 INFO Epoch:27 val_res:0.642023 +2025-04-19 07:39:44,546 INFO Epoch:28 train_loss:0.93691 +2025-04-19 07:39:51,749 INFO Epoch:28 val_res:0.649157 +2025-04-19 07:40:28,921 INFO Epoch:29 train_loss:0.92420 +2025-04-19 07:40:38,288 INFO Epoch:29 val_res:0.649157 +2025-04-19 07:41:16,469 INFO Epoch:30 train_loss:0.92570 +2025-04-19 07:41:24,328 INFO Epoch:30 val_res:0.651102 +2025-04-19 07:41:24,335 INFO Saving best model at Epoch 30 +2025-04-19 07:42:03,854 INFO Epoch:31 train_loss:0.92728 +2025-04-19 07:42:13,638 INFO Epoch:31 val_res:0.654994 +2025-04-19 07:42:13,641 INFO Saving best model at Epoch 31 +2025-04-19 07:42:51,724 INFO Epoch:32 train_loss:0.92911 +2025-04-19 07:42:59,328 INFO Epoch:32 val_res:0.649805 +2025-04-19 07:43:35,406 INFO Epoch:33 train_loss:0.94092 +2025-04-19 07:43:44,297 INFO Epoch:33 val_res:0.652399 +2025-04-19 07:44:20,511 INFO Epoch:34 train_loss:0.89663 +2025-04-19 07:44:28,352 INFO Epoch:34 val_res:0.650454 +2025-04-19 07:45:02,979 INFO Epoch:35 train_loss:0.90912 +2025-04-19 07:45:10,482 INFO Epoch:35 val_res:0.651751 +2025-04-19 07:45:45,022 INFO Epoch:36 train_loss:0.92579 +2025-04-19 07:45:52,702 INFO Epoch:36 val_res:0.645914 +2025-04-19 07:46:27,048 INFO Epoch:37 train_loss:0.87287 +2025-04-19 07:46:34,751 INFO Epoch:37 val_res:0.651102 +2025-04-19 07:47:10,629 INFO Epoch:38 train_loss:0.88024 +2025-04-19 07:47:18,393 INFO Epoch:38 val_res:0.651751 +2025-04-19 07:47:53,055 INFO Epoch:39 train_loss:0.89811 +2025-04-19 07:48:00,775 INFO Epoch:39 val_res:0.645266 +2025-04-19 07:48:36,564 INFO Epoch:40 train_loss:0.87638 +2025-04-19 07:48:44,429 INFO Epoch:40 val_res:0.653696 +2025-04-19 07:49:17,360 INFO Epoch:41 train_loss:0.88050 +2025-04-19 07:49:25,077 INFO Epoch:41 val_res:0.651751 +2025-04-19 07:50:00,003 INFO Epoch:42 train_loss:0.89718 +2025-04-19 07:50:07,394 INFO Epoch:42 val_res:0.638781 +2025-04-19 07:50:43,689 INFO Epoch:43 train_loss:0.94386 +2025-04-19 07:50:51,657 INFO Epoch:43 val_res:0.633593 +2025-04-19 07:51:25,412 INFO Epoch:44 train_loss:0.87684 +2025-04-19 07:51:33,488 INFO Epoch:44 val_res:0.634890 +2025-04-19 07:52:10,133 INFO Epoch:45 train_loss:0.85128 +2025-04-19 07:52:18,968 INFO Epoch:45 val_res:0.632944 +2025-04-19 07:52:56,397 INFO Epoch:46 train_loss:0.84352 +2025-04-19 07:53:05,418 INFO Epoch:46 val_res:0.633593 +2025-04-19 07:53:40,169 INFO Epoch:47 train_loss:0.84123 +2025-04-19 07:53:48,018 INFO Epoch:47 val_res:0.629702 +2025-04-19 07:54:22,626 INFO Epoch:48 train_loss:0.83184 +2025-04-19 07:54:30,436 INFO Epoch:48 val_res:0.639429 +2025-04-19 07:55:03,642 INFO Epoch:49 train_loss:0.88230 +2025-04-19 07:55:12,575 INFO Epoch:49 val_res:0.628405 +2025-04-19 07:55:51,070 INFO Epoch:50 train_loss:0.87180 +2025-04-19 07:55:57,920 INFO Epoch:50 val_res:0.620623 +2025-04-19 07:56:28,850 INFO Epoch:51 train_loss:0.83229 +2025-04-19 07:56:37,842 INFO Epoch:51 val_res:0.631647 +2025-04-19 07:57:12,651 INFO Epoch:52 train_loss:0.84418 +2025-04-19 07:57:21,218 INFO Epoch:52 val_res:0.616083 +2025-04-19 07:58:00,150 INFO Epoch:53 train_loss:0.85610 +2025-04-19 07:58:08,982 INFO Epoch:53 val_res:0.620623 +2025-04-19 07:58:45,734 INFO Epoch:54 train_loss:0.85179 +2025-04-19 07:58:54,167 INFO Epoch:54 val_res:0.629053 +2025-04-19 07:59:29,817 INFO Epoch:55 train_loss:0.86473 +2025-04-19 07:59:39,273 INFO Epoch:55 val_res:0.614786 +2025-04-19 08:00:19,692 INFO Epoch:56 train_loss:0.81065 +2025-04-19 08:00:28,906 INFO Epoch:56 val_res:0.620623 +2025-04-19 08:01:06,420 INFO Epoch:57 train_loss:0.81396 +2025-04-19 08:01:14,911 INFO Epoch:57 val_res:0.619974 +2025-04-19 08:01:51,884 INFO Epoch:58 train_loss:0.82333 +2025-04-19 08:02:00,753 INFO Epoch:58 val_res:0.626459 +2025-04-19 08:02:37,903 INFO Epoch:59 train_loss:0.82419 +2025-04-19 08:02:46,805 INFO Epoch:59 val_res:0.614786 +2025-04-19 08:03:24,032 INFO Epoch:60 train_loss:0.80717 +2025-04-19 08:03:31,852 INFO Epoch:60 val_res:0.616732 +2025-04-19 08:04:06,404 INFO Epoch:61 train_loss:0.79236 +2025-04-19 08:04:15,132 INFO Epoch:61 val_res:0.614137 +2025-04-19 08:04:49,143 INFO Epoch:62 train_loss:0.81036 +2025-04-19 08:04:58,227 INFO Epoch:62 val_res:0.612840 +2025-04-19 08:05:33,620 INFO Epoch:63 train_loss:0.83394 +2025-04-19 08:05:42,828 INFO Epoch:63 val_res:0.621920 +2025-04-19 08:06:18,492 INFO Epoch:64 train_loss:0.81774 +2025-04-19 08:06:27,184 INFO Epoch:64 val_res:0.614137 +2025-04-19 08:07:04,196 INFO Epoch:65 train_loss:0.81329 +2025-04-19 08:07:12,708 INFO Epoch:65 val_res:0.616732 +2025-04-19 08:07:48,828 INFO Epoch:66 train_loss:0.80690 +2025-04-19 08:07:57,529 INFO Epoch:66 val_res:0.617380 +2025-04-19 08:08:35,206 INFO Epoch:67 train_loss:0.80257 +2025-04-19 08:08:43,401 INFO Epoch:67 val_res:0.610246 +2025-04-19 08:09:16,981 INFO Epoch:68 train_loss:0.80838 +2025-04-19 08:09:26,447 INFO Epoch:68 val_res:0.604410 +2025-04-19 08:10:02,374 INFO Epoch:69 train_loss:0.81792 +2025-04-19 08:10:11,833 INFO Epoch:69 val_res:0.608949 +2025-04-19 08:10:48,822 INFO Epoch:70 train_loss:0.81501 +2025-04-19 08:10:56,367 INFO Epoch:70 val_res:0.596628 +2025-04-19 08:11:29,497 INFO Epoch:71 train_loss:0.88083 +2025-04-19 08:11:37,943 INFO Epoch:71 val_res:0.607652 +2025-04-19 08:12:13,475 INFO Epoch:72 train_loss:0.80560 +2025-04-19 08:12:21,808 INFO Epoch:72 val_res:0.607652 +2025-04-19 08:12:56,820 INFO Epoch:73 train_loss:0.78501 +2025-04-19 08:13:05,514 INFO Epoch:73 val_res:0.616732 +2025-04-19 08:13:40,050 INFO Epoch:74 train_loss:0.79339 +2025-04-19 08:13:49,897 INFO Epoch:74 val_res:0.603761 +2025-04-19 08:15:38,323 INFO Epoch:75 train_loss:0.76952 +2025-04-19 08:15:47,246 INFO Epoch:75 val_res:0.607004 +2025-04-19 08:16:23,088 INFO Epoch:76 train_loss:0.82393 +2025-04-19 08:16:31,577 INFO Epoch:76 val_res:0.605058 +2025-04-19 08:17:08,714 INFO Epoch:77 train_loss:0.76847 +2025-04-19 08:17:17,593 INFO Epoch:77 val_res:0.603761 +2025-04-19 08:17:48,620 INFO Epoch:78 train_loss:0.77845 +2025-04-19 08:17:55,830 INFO Epoch:78 val_res:0.605058 +2025-04-19 08:18:27,040 INFO Epoch:79 train_loss:0.80821 +2025-04-19 08:18:34,018 INFO Epoch:79 val_res:0.599870 +2025-04-19 08:19:05,345 INFO Epoch:80 train_loss:0.81458 +2025-04-19 08:19:13,285 INFO Epoch:80 val_res:0.601167 +2025-04-19 08:19:44,400 INFO Epoch:81 train_loss:0.79375 +2025-04-19 08:19:51,227 INFO Epoch:81 val_res:0.598573 +2025-04-19 08:20:20,433 INFO Epoch:82 train_loss:0.78660 +2025-04-19 08:20:27,605 INFO Epoch:82 val_res:0.601816 +2025-04-19 08:21:04,523 INFO Epoch:83 train_loss:0.78460 +2025-04-19 08:21:12,011 INFO Epoch:83 val_res:0.597276 +2025-04-19 08:21:49,558 INFO Epoch:84 train_loss:0.79264 +2025-04-19 08:21:57,264 INFO Epoch:84 val_res:0.593385 +2025-04-19 08:22:37,900 INFO Epoch:85 train_loss:0.79474 +2025-04-19 08:22:45,081 INFO Epoch:85 val_res:0.604410 +2025-04-19 08:23:27,089 INFO Epoch:86 train_loss:0.86850 +2025-04-19 08:23:36,939 INFO Epoch:86 val_res:0.591440 +2025-04-19 08:24:16,674 INFO Epoch:87 train_loss:0.79938 +2025-04-19 08:24:27,593 INFO Epoch:87 val_res:0.598573 +2025-04-19 08:25:12,774 INFO Epoch:88 train_loss:0.76617 +2025-04-19 08:25:21,655 INFO Epoch:88 val_res:0.590791 +2025-04-19 08:26:15,053 INFO Epoch:89 train_loss:0.79250 +2025-04-19 08:26:25,877 INFO Epoch:89 val_res:0.592088 +2025-04-19 08:27:17,367 INFO Epoch:90 train_loss:0.75056 +2025-04-19 08:27:27,012 INFO Epoch:90 val_res:0.590791 +2025-04-19 08:28:18,639 INFO Epoch:91 train_loss:0.76478 +2025-04-19 08:28:30,453 INFO Epoch:91 val_res:0.590143 +2025-04-19 08:29:23,750 INFO Epoch:92 train_loss:0.76981 +2025-04-19 08:29:33,605 INFO Epoch:92 val_res:0.594682 +2025-04-19 08:30:19,030 INFO Epoch:93 train_loss:0.74080 +2025-04-19 08:30:27,374 INFO Epoch:93 val_res:0.596628 +2025-04-19 08:31:11,926 INFO Epoch:94 train_loss:0.75135 +2025-04-19 08:31:20,313 INFO Epoch:94 val_res:0.600519 +2025-04-19 08:32:00,834 INFO Epoch:95 train_loss:0.75834 +2025-04-19 08:32:10,220 INFO Epoch:95 val_res:0.595331 +2025-04-19 08:32:54,213 INFO Epoch:96 train_loss:0.84780 +2025-04-19 08:33:03,644 INFO Epoch:96 val_res:0.588846 +2025-04-19 08:33:50,898 INFO Epoch:97 train_loss:0.80199 +2025-04-19 08:33:59,326 INFO Epoch:97 val_res:0.584955 +2025-04-19 08:34:47,537 INFO Epoch:98 train_loss:0.76273 +2025-04-19 08:34:55,080 INFO Epoch:98 val_res:0.590143 +2025-04-19 08:35:42,897 INFO Epoch:99 train_loss:0.75536 +2025-04-19 08:35:51,111 INFO Epoch:99 val_res:0.586252 +2025-04-19 08:35:51,474 INFO ===================================== +2025-04-19 08:35:51,474 INFO Start testing... +2025-04-19 08:35:51,475 INFO ===================================== +2025-04-19 08:37:12,149 INFO Incremental step 3 Testing res: 0.629773 +2025-04-19 08:37:12,158 INFO forgetting: 0.113581 +2025-04-19 08:37:12,161 INFO Incremental step: 4 +2025-04-19 08:40:48,054 INFO Epoch:0 train_loss:5.65301 +2025-04-19 08:41:19,963 INFO Epoch:0 val_res:0.468413 +2025-04-19 08:41:19,969 INFO Saving best model at Epoch 0 +2025-04-19 08:42:05,771 INFO Epoch:1 train_loss:2.47211 +2025-04-19 08:42:16,699 INFO Epoch:1 val_res:0.511043 +2025-04-19 08:42:16,702 INFO Saving best model at Epoch 1 +2025-04-19 08:42:57,134 INFO Epoch:2 train_loss:1.77036 +2025-04-19 08:43:08,261 INFO Epoch:2 val_res:0.519260 +2025-04-19 08:43:08,265 INFO Saving best model at Epoch 2 +2025-04-19 08:43:50,216 INFO Epoch:3 train_loss:1.56026 +2025-04-19 08:44:00,957 INFO Epoch:3 val_res:0.522342 +2025-04-19 08:44:00,960 INFO Saving best model at Epoch 3 +2025-04-19 08:44:51,353 INFO Epoch:4 train_loss:1.47246 +2025-04-19 08:45:03,788 INFO Epoch:4 val_res:0.523883 +2025-04-19 08:45:03,796 INFO Saving best model at Epoch 4 +2025-04-19 08:45:50,323 INFO Epoch:5 train_loss:1.43155 +2025-04-19 08:46:00,820 INFO Epoch:5 val_res:0.528505 +2025-04-19 08:46:00,828 INFO Saving best model at Epoch 5 +2025-04-19 08:46:52,120 INFO Epoch:6 train_loss:1.39491 +2025-04-19 08:47:05,503 INFO Epoch:6 val_res:0.527478 +2025-04-19 08:47:55,198 INFO Epoch:7 train_loss:1.34722 +2025-04-19 08:48:08,792 INFO Epoch:7 val_res:0.528505 +2025-04-19 08:48:54,465 INFO Epoch:8 train_loss:1.33505 +2025-04-19 08:49:05,964 INFO Epoch:8 val_res:0.527478 +2025-04-19 08:49:49,604 INFO Epoch:9 train_loss:1.30975 +2025-04-19 08:50:00,975 INFO Epoch:9 val_res:0.529533 +2025-04-19 08:50:00,985 INFO Saving best model at Epoch 9 +2025-04-19 08:50:44,279 INFO Epoch:10 train_loss:1.29176 +2025-04-19 08:50:55,286 INFO Epoch:10 val_res:0.537237 +2025-04-19 08:50:55,300 INFO Saving best model at Epoch 10 +2025-04-19 08:51:42,509 INFO Epoch:11 train_loss:1.26629 +2025-04-19 08:51:53,068 INFO Epoch:11 val_res:0.533642 +2025-04-19 08:52:39,669 INFO Epoch:12 train_loss:1.24289 +2025-04-19 08:52:51,436 INFO Epoch:12 val_res:0.528505 +2025-04-19 08:53:38,206 INFO Epoch:13 train_loss:1.23456 +2025-04-19 08:53:49,227 INFO Epoch:13 val_res:0.533128 +2025-04-19 08:54:37,043 INFO Epoch:14 train_loss:1.21569 +2025-04-19 08:54:49,593 INFO Epoch:14 val_res:0.534669 +2025-04-19 08:55:27,838 INFO Epoch:15 train_loss:1.20978 +2025-04-19 08:55:39,790 INFO Epoch:15 val_res:0.532614 +2025-04-19 08:56:25,053 INFO Epoch:16 train_loss:1.18627 +2025-04-19 08:56:37,112 INFO Epoch:16 val_res:0.539291 +2025-04-19 08:56:37,120 INFO Saving best model at Epoch 16 +2025-04-19 08:57:24,768 INFO Epoch:17 train_loss:1.16735 +2025-04-19 08:57:38,503 INFO Epoch:17 val_res:0.542373 +2025-04-19 08:57:38,508 INFO Saving best model at Epoch 17 +2025-04-19 08:58:30,071 INFO Epoch:18 train_loss:1.16151 +2025-04-19 08:58:40,300 INFO Epoch:18 val_res:0.542373 +2025-04-19 08:59:26,779 INFO Epoch:19 train_loss:1.15228 +2025-04-19 08:59:38,923 INFO Epoch:19 val_res:0.542886 +2025-04-19 08:59:38,940 INFO Saving best model at Epoch 19 +2025-04-19 09:00:24,128 INFO Epoch:20 train_loss:1.13853 +2025-04-19 09:00:35,354 INFO Epoch:20 val_res:0.545455 +2025-04-19 09:00:35,362 INFO Saving best model at Epoch 20 +2025-04-19 09:01:24,434 INFO Epoch:21 train_loss:1.12600 +2025-04-19 09:01:35,257 INFO Epoch:21 val_res:0.543400 +2025-04-19 09:02:17,364 INFO Epoch:22 train_loss:1.11940 +2025-04-19 09:02:30,523 INFO Epoch:22 val_res:0.542886 +2025-04-19 09:03:14,920 INFO Epoch:23 train_loss:1.12085 +2025-04-19 09:03:26,506 INFO Epoch:23 val_res:0.551104 +2025-04-19 09:03:26,515 INFO Saving best model at Epoch 23 +2025-04-19 09:04:11,382 INFO Epoch:24 train_loss:1.12986 +2025-04-19 09:04:24,138 INFO Epoch:24 val_res:0.557781 +2025-04-19 09:04:24,144 INFO Saving best model at Epoch 24 +2025-04-19 09:05:12,223 INFO Epoch:25 train_loss:1.11293 +2025-04-19 09:05:24,666 INFO Epoch:25 val_res:0.552131 +2025-04-19 09:06:11,566 INFO Epoch:26 train_loss:1.08627 +2025-04-19 09:06:25,399 INFO Epoch:26 val_res:0.563431 +2025-04-19 09:06:25,403 INFO Saving best model at Epoch 26 +2025-04-19 09:07:12,940 INFO Epoch:27 train_loss:1.07510 +2025-04-19 09:07:25,802 INFO Epoch:27 val_res:0.567026 +2025-04-19 09:07:25,812 INFO Saving best model at Epoch 27 +2025-04-19 09:08:14,989 INFO Epoch:28 train_loss:1.06991 +2025-04-19 09:08:27,554 INFO Epoch:28 val_res:0.567540 +2025-04-19 09:08:27,563 INFO Saving best model at Epoch 28 +2025-04-19 09:09:13,898 INFO Epoch:29 train_loss:1.06241 +2025-04-19 09:09:25,953 INFO Epoch:29 val_res:0.572162 +2025-04-19 09:09:25,960 INFO Saving best model at Epoch 29 +2025-04-19 09:10:15,464 INFO Epoch:30 train_loss:1.03446 +2025-04-19 09:10:28,168 INFO Epoch:30 val_res:0.570108 +2025-04-19 09:11:15,475 INFO Epoch:31 train_loss:1.02381 +2025-04-19 09:11:27,762 INFO Epoch:31 val_res:0.580380 +2025-04-19 09:11:27,764 INFO Saving best model at Epoch 31 +2025-04-19 09:12:11,785 INFO Epoch:32 train_loss:1.03629 +2025-04-19 09:12:23,716 INFO Epoch:32 val_res:0.577298 +2025-04-19 09:13:10,812 INFO Epoch:33 train_loss:1.02710 +2025-04-19 09:13:22,907 INFO Epoch:33 val_res:0.582948 +2025-04-19 09:13:22,908 INFO Saving best model at Epoch 33 +2025-04-19 09:14:11,897 INFO Epoch:34 train_loss:1.00765 +2025-04-19 09:14:23,583 INFO Epoch:34 val_res:0.578326 +2025-04-19 09:15:10,526 INFO Epoch:35 train_loss:1.02572 +2025-04-19 09:15:22,321 INFO Epoch:35 val_res:0.574730 +2025-04-19 09:16:12,009 INFO Epoch:36 train_loss:1.02201 +2025-04-19 09:16:22,856 INFO Epoch:36 val_res:0.594761 +2025-04-19 09:16:22,861 INFO Saving best model at Epoch 36 +2025-04-19 09:17:08,656 INFO Epoch:37 train_loss:0.99791 +2025-04-19 09:17:20,191 INFO Epoch:37 val_res:0.592193 +2025-04-19 09:18:07,206 INFO Epoch:38 train_loss:0.97726 +2025-04-19 09:18:20,364 INFO Epoch:38 val_res:0.595788 +2025-04-19 09:18:20,386 INFO Saving best model at Epoch 38 +2025-04-19 09:19:11,347 INFO Epoch:39 train_loss:0.97276 +2025-04-19 09:19:23,160 INFO Epoch:39 val_res:0.591680 +2025-04-19 09:20:06,154 INFO Epoch:40 train_loss:0.96804 +2025-04-19 09:20:17,945 INFO Epoch:40 val_res:0.594761 +2025-04-19 09:21:05,207 INFO Epoch:41 train_loss:0.95299 +2025-04-19 09:21:17,479 INFO Epoch:41 val_res:0.594248 +2025-04-19 09:22:05,782 INFO Epoch:42 train_loss:0.93439 +2025-04-19 09:22:18,379 INFO Epoch:42 val_res:0.598870 +2025-04-19 09:22:18,380 INFO Saving best model at Epoch 42 +2025-04-19 09:23:08,540 INFO Epoch:43 train_loss:0.99554 +2025-04-19 09:23:19,706 INFO Epoch:43 val_res:0.607601 +2025-04-19 09:23:19,713 INFO Saving best model at Epoch 43 +2025-04-19 09:24:07,339 INFO Epoch:44 train_loss:0.95989 +2025-04-19 09:24:21,167 INFO Epoch:44 val_res:0.605547 +2025-04-19 09:25:10,178 INFO Epoch:45 train_loss:0.92594 +2025-04-19 09:25:22,271 INFO Epoch:45 val_res:0.601952 +2025-04-19 09:26:11,158 INFO Epoch:46 train_loss:0.91507 +2025-04-19 09:26:23,635 INFO Epoch:46 val_res:0.602465 +2025-04-19 09:27:09,674 INFO Epoch:47 train_loss:0.92787 +2025-04-19 09:27:23,161 INFO Epoch:47 val_res:0.598870 +2025-04-19 09:28:09,995 INFO Epoch:48 train_loss:0.98430 +2025-04-19 09:28:23,627 INFO Epoch:48 val_res:0.598870 +2025-04-19 09:29:03,808 INFO Epoch:49 train_loss:1.00597 +2025-04-19 09:29:17,483 INFO Epoch:49 val_res:0.601438 +2025-04-19 09:30:04,717 INFO Epoch:50 train_loss:0.92387 +2025-04-19 09:30:17,351 INFO Epoch:50 val_res:0.608115 +2025-04-19 09:30:17,362 INFO Saving best model at Epoch 50 +2025-04-19 09:31:07,570 INFO Epoch:51 train_loss:0.90009 +2025-04-19 09:31:19,860 INFO Epoch:51 val_res:0.609142 +2025-04-19 09:31:19,878 INFO Saving best model at Epoch 51 +2025-04-19 09:32:08,006 INFO Epoch:52 train_loss:0.87664 +2025-04-19 09:32:19,210 INFO Epoch:52 val_res:0.606574 +2025-04-19 09:33:03,465 INFO Epoch:53 train_loss:0.88594 +2025-04-19 09:33:14,192 INFO Epoch:53 val_res:0.605033 +2025-04-19 09:33:57,493 INFO Epoch:54 train_loss:0.87541 +2025-04-19 09:34:11,108 INFO Epoch:54 val_res:0.615306 +2025-04-19 09:34:11,116 INFO Saving best model at Epoch 54 +2025-04-19 09:35:00,840 INFO Epoch:55 train_loss:0.86823 +2025-04-19 09:35:13,303 INFO Epoch:55 val_res:0.611197 +2025-04-19 09:35:55,500 INFO Epoch:56 train_loss:0.87379 +2025-04-19 09:36:05,738 INFO Epoch:56 val_res:0.603493 +2025-04-19 09:36:49,410 INFO Epoch:57 train_loss:0.91566 +2025-04-19 09:36:59,742 INFO Epoch:57 val_res:0.604006 +2025-04-19 09:37:43,148 INFO Epoch:58 train_loss:0.87246 +2025-04-19 09:37:53,915 INFO Epoch:58 val_res:0.598356 +2025-04-19 09:38:36,299 INFO Epoch:59 train_loss:0.88240 +2025-04-19 09:38:47,379 INFO Epoch:59 val_res:0.606061 +2025-04-19 09:39:30,228 INFO Epoch:60 train_loss:0.90592 +2025-04-19 09:39:40,707 INFO Epoch:60 val_res:0.606061 +2025-04-19 09:40:22,508 INFO Epoch:61 train_loss:0.87078 +2025-04-19 09:40:32,744 INFO Epoch:61 val_res:0.606574 +2025-04-19 09:41:12,640 INFO Epoch:62 train_loss:0.85325 +2025-04-19 09:41:24,986 INFO Epoch:62 val_res:0.603493 +2025-04-19 09:42:11,767 INFO Epoch:63 train_loss:0.87687 +2025-04-19 09:42:23,962 INFO Epoch:63 val_res:0.604006 +2025-04-19 09:43:07,858 INFO Epoch:64 train_loss:0.86586 +2025-04-19 09:43:18,371 INFO Epoch:64 val_res:0.607088 +2025-04-19 09:43:58,965 INFO Epoch:65 train_loss:0.86917 +2025-04-19 09:44:10,133 INFO Epoch:65 val_res:0.604006 +2025-04-19 09:44:53,783 INFO Epoch:66 train_loss:0.83435 +2025-04-19 09:45:05,575 INFO Epoch:66 val_res:0.612738 +2025-04-19 09:45:52,150 INFO Epoch:67 train_loss:0.94845 +2025-04-19 09:46:04,566 INFO Epoch:67 val_res:0.606574 +2025-04-19 09:46:52,034 INFO Epoch:68 train_loss:0.86232 +2025-04-19 09:47:04,171 INFO Epoch:68 val_res:0.601952 +2025-04-19 09:47:47,787 INFO Epoch:69 train_loss:0.82943 +2025-04-19 09:47:58,218 INFO Epoch:69 val_res:0.604006 +2025-04-19 09:48:44,430 INFO Epoch:70 train_loss:0.81847 +2025-04-19 09:48:55,839 INFO Epoch:70 val_res:0.596302 +2025-04-19 09:49:43,180 INFO Epoch:71 train_loss:0.82304 +2025-04-19 09:49:56,119 INFO Epoch:71 val_res:0.606061 +2025-04-19 09:50:44,078 INFO Epoch:72 train_loss:0.80722 +2025-04-19 09:50:55,272 INFO Epoch:72 val_res:0.598870 +2025-04-19 09:51:39,598 INFO Epoch:73 train_loss:0.87989 +2025-04-19 09:51:49,988 INFO Epoch:73 val_res:0.607601 +2025-04-19 09:52:33,463 INFO Epoch:74 train_loss:0.85726 +2025-04-19 09:52:45,248 INFO Epoch:74 val_res:0.601438 +2025-04-19 09:53:31,928 INFO Epoch:75 train_loss:0.81191 +2025-04-19 09:53:43,692 INFO Epoch:75 val_res:0.594248 +2025-04-19 09:54:27,818 INFO Epoch:76 train_loss:0.82209 +2025-04-19 09:54:38,606 INFO Epoch:76 val_res:0.605547 +2025-04-19 09:55:19,844 INFO Epoch:77 train_loss:0.84256 +2025-04-19 09:55:31,920 INFO Epoch:77 val_res:0.607601 +2025-04-19 09:56:17,058 INFO Epoch:78 train_loss:0.81606 +2025-04-19 09:56:28,043 INFO Epoch:78 val_res:0.601952 +2025-04-19 09:57:13,753 INFO Epoch:79 train_loss:0.80339 +2025-04-19 09:57:25,855 INFO Epoch:79 val_res:0.594761 +2025-04-19 09:58:10,963 INFO Epoch:80 train_loss:0.87505 +2025-04-19 09:58:20,662 INFO Epoch:80 val_res:0.598356 +2025-04-19 09:59:04,138 INFO Epoch:81 train_loss:0.84556 +2025-04-19 09:59:14,716 INFO Epoch:81 val_res:0.604520 +2025-04-19 09:59:58,783 INFO Epoch:82 train_loss:0.82098 +2025-04-19 10:00:09,832 INFO Epoch:82 val_res:0.590652 +2025-04-19 10:00:52,025 INFO Epoch:83 train_loss:0.82545 +2025-04-19 10:01:02,733 INFO Epoch:83 val_res:0.610169 +2025-04-19 10:01:46,844 INFO Epoch:84 train_loss:0.78581 +2025-04-19 10:01:57,363 INFO Epoch:84 val_res:0.606574 +2025-04-19 10:02:37,933 INFO Epoch:85 train_loss:0.80661 +2025-04-19 10:02:48,369 INFO Epoch:85 val_res:0.601952 +2025-04-19 10:03:32,563 INFO Epoch:86 train_loss:0.81098 +2025-04-19 10:03:42,700 INFO Epoch:86 val_res:0.597329 +2025-04-19 10:04:25,133 INFO Epoch:87 train_loss:0.83063 +2025-04-19 10:04:34,424 INFO Epoch:87 val_res:0.607088 +2025-04-19 10:05:16,221 INFO Epoch:88 train_loss:0.79205 +2025-04-19 10:05:26,388 INFO Epoch:88 val_res:0.603493 +2025-04-19 10:06:08,250 INFO Epoch:89 train_loss:0.78983 +2025-04-19 10:06:20,179 INFO Epoch:89 val_res:0.599384 +2025-04-19 10:07:03,630 INFO Epoch:90 train_loss:0.91863 +2025-04-19 10:07:13,931 INFO Epoch:90 val_res:0.598870 +2025-04-19 10:07:56,686 INFO Epoch:91 train_loss:0.82808 +2025-04-19 10:08:07,048 INFO Epoch:91 val_res:0.586543 +2025-04-19 10:08:52,953 INFO Epoch:92 train_loss:0.79607 +2025-04-19 10:09:03,013 INFO Epoch:92 val_res:0.595275 +2025-04-19 10:09:45,696 INFO Epoch:93 train_loss:0.80543 +2025-04-19 10:09:56,076 INFO Epoch:93 val_res:0.591680 +2025-04-19 10:10:38,187 INFO Epoch:94 train_loss:0.80955 +2025-04-19 10:10:47,976 INFO Epoch:94 val_res:0.596302 +2025-04-19 10:11:32,506 INFO Epoch:95 train_loss:0.82754 +2025-04-19 10:11:42,141 INFO Epoch:95 val_res:0.600411 +2025-04-19 10:12:24,977 INFO Epoch:96 train_loss:0.80937 +2025-04-19 10:12:35,679 INFO Epoch:96 val_res:0.591680 +2025-04-19 10:13:19,219 INFO Epoch:97 train_loss:0.83494 +2025-04-19 10:13:29,352 INFO Epoch:97 val_res:0.594248 +2025-04-19 10:14:10,297 INFO Epoch:98 train_loss:0.79665 +2025-04-19 10:14:20,356 INFO Epoch:98 val_res:0.588084 +2025-04-19 10:15:05,397 INFO Epoch:99 train_loss:0.78402 +2025-04-19 10:15:14,815 INFO Epoch:99 val_res:0.590139 +2025-04-19 10:15:15,139 INFO ===================================== +2025-04-19 10:15:15,140 INFO Start testing... +2025-04-19 10:15:15,140 INFO ===================================== +2025-04-19 10:16:30,111 INFO Incremental step 4 Testing res: 0.574566 +2025-04-19 10:16:30,113 INFO forgetting: 0.130488 +2025-04-19 10:16:30,115 INFO Average Accuracy: 0.701536 +2025-04-19 10:16:30,115 INFO Average Forgetting: 0.136563 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..59385b0ed1e52ba3cd3d6e8ff11635d49451b3aa Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..25c86f3a96a271810a677028bcab9cdce4186f1e Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..c929af089c3e524336084f0c94c078b8c11aadeb Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..acf8a80c367504e3697ce3cfb3d4961a3287f1be Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..02b4eefa811a30b094c73f2431752f709d198637 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..8fac145defd17f96bb99777b06aa463bea01103b Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..a3549e0d0e3df6e330a3fb55776bb1fef34cec5c Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..f484b9f6e9655c048cd7db887f00caab86e66c4e Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..de11e1f26bd52148d7aa6c1972fd8a311dd30fe4 Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..9fc152ac499bdc566e749bd2601f53d4641a966c Binary files /dev/null and b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..eba9e0f7045caf122c4794e923d472522104bef0 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0506bdc1f2badecbe56d9498c277f7d6b2931d3d352bc25422fced94ee859cc +size 114106129 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..12433d4a03e7ffcb455e480daf5284d33ba443d6 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81d1694da8552dcee061e98730624d10231d62ba1bbc0d19bb200e14799b74d2 +size 114161489 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..4b265f73323b3b8de1aca819e1f66b2331c92674 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7c67f4a516b752f0746c0c1839d99cf9fe5ea7897581bfcd055f802a495419f +size 114216977 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..3330d93f67613e617d9f87e3a6c6b5bf13fa79c8 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14c7cc0a3c7f1ad284bf05cdb266a0772d69df9a2f4aca208f0c5cb5c55e7ed9 +size 114272273 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b82b4cb652d45f6cf832e87a240be6f9ea052958 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b8185546849179408bb364332aa02ef6e2c3a24b290bcdff39957bbc925ed4 +size 114327569 diff --git a/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/train.log b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..c153a9e01cee7b51ebfb5183e5dc6a9dfa17e3e3 --- /dev/null +++ b/Audio Visual Continual Learning/AV-CIL/save/ksounds/audio-visual/use-inverse_True-seed_0/train.log @@ -0,0 +1,1179 @@ +2025-04-19 03:46:47,999 INFO Training start time: 2025-04-19 03:46:47.999142 +2025-04-19 03:46:49,831 INFO Incremental step: 0 +2025-04-19 03:49:50,665 INFO Epoch:0 train_loss:1.62565 +2025-04-19 03:49:54,717 INFO Epoch:0 val_res:0.602122 +2025-04-19 03:49:54,717 INFO Saving best model at Epoch 0 +2025-04-19 03:50:16,911 INFO Epoch:1 train_loss:0.76612 +2025-04-19 03:50:19,674 INFO Epoch:1 val_res:0.803714 +2025-04-19 03:50:19,675 INFO Saving best model at Epoch 1 +2025-04-19 03:50:35,067 INFO Epoch:2 train_loss:0.47780 +2025-04-19 03:50:37,661 INFO Epoch:2 val_res:0.867374 +2025-04-19 03:50:37,662 INFO Saving best model at Epoch 2 +2025-04-19 03:50:53,225 INFO Epoch:3 train_loss:0.34041 +2025-04-19 03:50:55,774 INFO Epoch:3 val_res:0.907162 +2025-04-19 03:50:55,774 INFO Saving best model at Epoch 3 +2025-04-19 03:51:11,360 INFO Epoch:4 train_loss:0.26224 +2025-04-19 03:51:14,135 INFO Epoch:4 val_res:0.917772 +2025-04-19 03:51:14,135 INFO Saving best model at Epoch 4 +2025-04-19 03:51:29,676 INFO Epoch:5 train_loss:0.21298 +2025-04-19 03:51:32,470 INFO Epoch:5 val_res:0.917772 +2025-04-19 03:51:44,953 INFO Epoch:6 train_loss:0.18117 +2025-04-19 03:51:47,515 INFO Epoch:6 val_res:0.925729 +2025-04-19 03:51:47,516 INFO Saving best model at Epoch 6 +2025-04-19 03:52:03,414 INFO Epoch:7 train_loss:0.15896 +2025-04-19 03:52:06,133 INFO Epoch:7 val_res:0.917772 +2025-04-19 03:52:18,399 INFO Epoch:8 train_loss:0.13977 +2025-04-19 03:52:20,942 INFO Epoch:8 val_res:0.920424 +2025-04-19 03:52:33,443 INFO Epoch:9 train_loss:0.12456 +2025-04-19 03:52:36,138 INFO Epoch:9 val_res:0.933687 +2025-04-19 03:52:36,139 INFO Saving best model at Epoch 9 +2025-04-19 03:52:51,292 INFO Epoch:10 train_loss:0.10835 +2025-04-19 03:52:54,113 INFO Epoch:10 val_res:0.933687 +2025-04-19 03:53:07,189 INFO Epoch:11 train_loss:0.10429 +2025-04-19 03:53:09,924 INFO Epoch:11 val_res:0.907162 +2025-04-19 03:53:23,533 INFO Epoch:12 train_loss:0.09043 +2025-04-19 03:53:26,269 INFO Epoch:12 val_res:0.925729 +2025-04-19 03:53:41,854 INFO Epoch:13 train_loss:0.08789 +2025-04-19 03:53:45,010 INFO Epoch:13 val_res:0.928382 +2025-04-19 03:53:58,673 INFO Epoch:14 train_loss:0.07048 +2025-04-19 03:54:01,280 INFO Epoch:14 val_res:0.936339 +2025-04-19 03:54:01,280 INFO Saving best model at Epoch 14 +2025-04-19 03:54:16,487 INFO Epoch:15 train_loss:0.06559 +2025-04-19 03:54:19,454 INFO Epoch:15 val_res:0.936339 +2025-04-19 03:54:33,090 INFO Epoch:16 train_loss:0.06032 +2025-04-19 03:54:35,837 INFO Epoch:16 val_res:0.936339 +2025-04-19 03:54:49,449 INFO Epoch:17 train_loss:0.04985 +2025-04-19 03:54:52,060 INFO Epoch:17 val_res:0.936339 +2025-04-19 03:55:06,070 INFO Epoch:18 train_loss:0.05060 +2025-04-19 03:55:08,778 INFO Epoch:18 val_res:0.933687 +2025-04-19 03:55:22,341 INFO Epoch:19 train_loss:0.04268 +2025-04-19 03:55:24,967 INFO Epoch:19 val_res:0.944297 +2025-04-19 03:55:24,968 INFO Saving best model at Epoch 19 +2025-04-19 03:55:42,259 INFO Epoch:20 train_loss:2.41570 +2025-04-19 03:55:44,927 INFO Epoch:20 val_res:0.933687 +2025-04-19 03:55:58,734 INFO Epoch:21 train_loss:1.46763 +2025-04-19 03:56:02,026 INFO Epoch:21 val_res:0.938992 +2025-04-19 03:56:14,688 INFO Epoch:22 train_loss:1.28750 +2025-04-19 03:56:17,386 INFO Epoch:22 val_res:0.931035 +2025-04-19 03:56:30,378 INFO Epoch:23 train_loss:1.14946 +2025-04-19 03:56:33,181 INFO Epoch:23 val_res:0.936339 +2025-04-19 03:56:46,569 INFO Epoch:24 train_loss:1.08280 +2025-04-19 03:56:49,488 INFO Epoch:24 val_res:0.938992 +2025-04-19 03:57:02,568 INFO Epoch:25 train_loss:1.01966 +2025-04-19 03:57:05,066 INFO Epoch:25 val_res:0.944297 +2025-04-19 03:57:18,106 INFO Epoch:26 train_loss:0.98754 +2025-04-19 03:57:20,960 INFO Epoch:26 val_res:0.938992 +2025-04-19 03:57:33,980 INFO Epoch:27 train_loss:0.97556 +2025-04-19 03:57:36,670 INFO Epoch:27 val_res:0.944297 +2025-04-19 03:57:51,852 INFO Epoch:28 train_loss:0.93844 +2025-04-19 03:57:54,751 INFO Epoch:28 val_res:0.941645 +2025-04-19 03:58:07,226 INFO Epoch:29 train_loss:0.94690 +2025-04-19 03:58:09,761 INFO Epoch:29 val_res:0.944297 +2025-04-19 03:58:22,361 INFO Epoch:30 train_loss:0.93908 +2025-04-19 03:58:24,928 INFO Epoch:30 val_res:0.931035 +2025-04-19 03:58:38,158 INFO Epoch:31 train_loss:0.92343 +2025-04-19 03:58:40,839 INFO Epoch:31 val_res:0.944297 +2025-04-19 03:58:54,371 INFO Epoch:32 train_loss:0.91913 +2025-04-19 03:58:56,946 INFO Epoch:32 val_res:0.946950 +2025-04-19 03:58:56,947 INFO Saving best model at Epoch 32 +2025-04-19 03:59:11,767 INFO Epoch:33 train_loss:0.88360 +2025-04-19 03:59:14,593 INFO Epoch:33 val_res:0.944297 +2025-04-19 03:59:27,759 INFO Epoch:34 train_loss:0.85139 +2025-04-19 03:59:30,461 INFO Epoch:34 val_res:0.944297 +2025-04-19 03:59:42,954 INFO Epoch:35 train_loss:0.86727 +2025-04-19 03:59:45,571 INFO Epoch:35 val_res:0.941645 +2025-04-19 04:00:03,725 INFO Epoch:36 train_loss:0.85417 +2025-04-19 04:00:06,717 INFO Epoch:36 val_res:0.944297 +2025-04-19 04:00:19,589 INFO Epoch:37 train_loss:0.83965 +2025-04-19 04:00:22,248 INFO Epoch:37 val_res:0.938992 +2025-04-19 04:00:39,561 INFO Epoch:38 train_loss:0.87457 +2025-04-19 04:00:50,884 INFO Epoch:38 val_res:0.938992 +2025-04-19 04:01:21,337 INFO Epoch:39 train_loss:0.88279 +2025-04-19 04:01:26,855 INFO Epoch:39 val_res:0.944297 +2025-04-19 04:02:00,740 INFO Epoch:40 train_loss:0.84654 +2025-04-19 04:02:05,212 INFO Epoch:40 val_res:0.946950 +2025-04-19 04:02:21,024 INFO Epoch:41 train_loss:0.82254 +2025-04-19 04:02:23,613 INFO Epoch:41 val_res:0.946950 +2025-04-19 04:02:36,601 INFO Epoch:42 train_loss:0.80141 +2025-04-19 04:02:49,985 INFO Epoch:42 val_res:0.941645 +2025-04-19 04:03:58,678 INFO Epoch:43 train_loss:0.81291 +2025-04-19 04:04:07,008 INFO Epoch:43 val_res:0.946950 +2025-04-19 04:04:21,033 INFO Epoch:44 train_loss:0.82259 +2025-04-19 04:04:23,725 INFO Epoch:44 val_res:0.944297 +2025-04-19 04:04:37,200 INFO Epoch:45 train_loss:0.80832 +2025-04-19 04:04:39,753 INFO Epoch:45 val_res:0.944297 +2025-04-19 04:04:52,603 INFO Epoch:46 train_loss:0.80915 +2025-04-19 04:04:55,215 INFO Epoch:46 val_res:0.938992 +2025-04-19 04:05:07,916 INFO Epoch:47 train_loss:0.81447 +2025-04-19 04:05:10,605 INFO Epoch:47 val_res:0.938992 +2025-04-19 04:05:23,488 INFO Epoch:48 train_loss:0.81723 +2025-04-19 04:05:26,008 INFO Epoch:48 val_res:0.936339 +2025-04-19 04:05:38,370 INFO Epoch:49 train_loss:0.84272 +2025-04-19 04:05:41,087 INFO Epoch:49 val_res:0.944297 +2025-04-19 04:05:53,515 INFO Epoch:50 train_loss:0.81037 +2025-04-19 04:05:56,097 INFO Epoch:50 val_res:0.949602 +2025-04-19 04:05:56,097 INFO Saving best model at Epoch 50 +2025-04-19 04:06:10,542 INFO Epoch:51 train_loss:0.83478 +2025-04-19 04:06:13,154 INFO Epoch:51 val_res:0.938992 +2025-04-19 04:06:25,591 INFO Epoch:52 train_loss:0.82336 +2025-04-19 04:06:28,245 INFO Epoch:52 val_res:0.938992 +2025-04-19 04:06:41,058 INFO Epoch:53 train_loss:0.78323 +2025-04-19 04:06:43,598 INFO Epoch:53 val_res:0.944297 +2025-04-19 04:06:59,391 INFO Epoch:54 train_loss:0.80521 +2025-04-19 04:07:02,266 INFO Epoch:54 val_res:0.933687 +2025-04-19 04:07:16,445 INFO Epoch:55 train_loss:0.77975 +2025-04-19 04:07:19,340 INFO Epoch:55 val_res:0.941645 +2025-04-19 04:07:32,822 INFO Epoch:56 train_loss:0.77764 +2025-04-19 04:07:35,873 INFO Epoch:56 val_res:0.928382 +2025-04-19 04:07:49,956 INFO Epoch:57 train_loss:0.79101 +2025-04-19 04:07:52,739 INFO Epoch:57 val_res:0.941645 +2025-04-19 04:08:06,393 INFO Epoch:58 train_loss:0.75037 +2025-04-19 04:08:09,104 INFO Epoch:58 val_res:0.941645 +2025-04-19 04:08:22,274 INFO Epoch:59 train_loss:0.76215 +2025-04-19 04:08:25,024 INFO Epoch:59 val_res:0.944297 +2025-04-19 04:08:38,523 INFO Epoch:60 train_loss:0.74754 +2025-04-19 04:08:41,165 INFO Epoch:60 val_res:0.944297 +2025-04-19 04:08:54,775 INFO Epoch:61 train_loss:0.75460 +2025-04-19 04:08:57,326 INFO Epoch:61 val_res:0.938992 +2025-04-19 04:09:09,769 INFO Epoch:62 train_loss:0.77627 +2025-04-19 04:09:12,375 INFO Epoch:62 val_res:0.941645 +2025-04-19 04:09:26,215 INFO Epoch:63 train_loss:0.77721 +2025-04-19 04:09:29,211 INFO Epoch:63 val_res:0.936339 +2025-04-19 04:09:41,831 INFO Epoch:64 train_loss:0.75044 +2025-04-19 04:09:44,347 INFO Epoch:64 val_res:0.946950 +2025-04-19 04:09:56,780 INFO Epoch:65 train_loss:0.76148 +2025-04-19 04:09:59,311 INFO Epoch:65 val_res:0.931035 +2025-04-19 04:10:11,435 INFO Epoch:66 train_loss:0.77383 +2025-04-19 04:10:14,011 INFO Epoch:66 val_res:0.946950 +2025-04-19 04:10:27,111 INFO Epoch:67 train_loss:0.73738 +2025-04-19 04:10:29,825 INFO Epoch:67 val_res:0.941645 +2025-04-19 04:10:43,198 INFO Epoch:68 train_loss:0.72053 +2025-04-19 04:10:45,762 INFO Epoch:68 val_res:0.946950 +2025-04-19 04:10:58,250 INFO Epoch:69 train_loss:0.73691 +2025-04-19 04:11:00,824 INFO Epoch:69 val_res:0.936339 +2025-04-19 04:11:13,524 INFO Epoch:70 train_loss:0.74163 +2025-04-19 04:11:16,051 INFO Epoch:70 val_res:0.938992 +2025-04-19 04:11:29,455 INFO Epoch:71 train_loss:0.00533 +2025-04-19 04:11:32,057 INFO Epoch:71 val_res:0.936339 +2025-04-19 04:11:44,606 INFO Epoch:72 train_loss:0.00352 +2025-04-19 04:11:47,158 INFO Epoch:72 val_res:0.936339 +2025-04-19 04:11:59,725 INFO Epoch:73 train_loss:0.00341 +2025-04-19 04:12:02,345 INFO Epoch:73 val_res:0.941645 +2025-04-19 04:12:14,878 INFO Epoch:74 train_loss:0.00346 +2025-04-19 04:12:17,402 INFO Epoch:74 val_res:0.936339 +2025-04-19 04:12:30,245 INFO Epoch:75 train_loss:0.00349 +2025-04-19 04:12:33,073 INFO Epoch:75 val_res:0.936339 +2025-04-19 04:12:45,798 INFO Epoch:76 train_loss:0.00385 +2025-04-19 04:12:48,434 INFO Epoch:76 val_res:0.936339 +2025-04-19 04:13:01,719 INFO Epoch:77 train_loss:0.00372 +2025-04-19 04:13:04,465 INFO Epoch:77 val_res:0.936339 +2025-04-19 04:13:16,718 INFO Epoch:78 train_loss:0.00395 +2025-04-19 04:13:19,218 INFO Epoch:78 val_res:0.941645 +2025-04-19 04:13:33,264 INFO Epoch:79 train_loss:0.00427 +2025-04-19 04:13:35,912 INFO Epoch:79 val_res:0.933687 +2025-04-19 04:13:48,700 INFO Epoch:80 train_loss:0.00426 +2025-04-19 04:13:51,266 INFO Epoch:80 val_res:0.933687 +2025-04-19 04:14:07,365 INFO Epoch:81 train_loss:0.00466 +2025-04-19 04:14:10,324 INFO Epoch:81 val_res:0.936339 +2025-04-19 04:14:26,689 INFO Epoch:82 train_loss:0.00449 +2025-04-19 04:14:30,157 INFO Epoch:82 val_res:0.933687 +2025-04-19 04:14:44,961 INFO Epoch:83 train_loss:0.00443 +2025-04-19 04:14:47,710 INFO Epoch:83 val_res:0.936339 +2025-04-19 04:15:02,730 INFO Epoch:84 train_loss:0.00456 +2025-04-19 04:15:05,677 INFO Epoch:84 val_res:0.938992 +2025-04-19 04:15:22,904 INFO Epoch:85 train_loss:0.00465 +2025-04-19 04:15:26,213 INFO Epoch:85 val_res:0.933687 +2025-04-19 04:15:42,693 INFO Epoch:86 train_loss:0.00486 +2025-04-19 04:15:45,646 INFO Epoch:86 val_res:0.931035 +2025-04-19 04:16:00,178 INFO Epoch:87 train_loss:0.00471 +2025-04-19 04:16:03,359 INFO Epoch:87 val_res:0.936339 +2025-04-19 04:16:18,712 INFO Epoch:88 train_loss:0.00474 +2025-04-19 04:16:21,654 INFO Epoch:88 val_res:0.944297 +2025-04-19 04:16:37,111 INFO Epoch:89 train_loss:0.00465 +2025-04-19 04:16:40,081 INFO Epoch:89 val_res:0.938992 +2025-04-19 04:16:56,097 INFO Epoch:90 train_loss:0.00487 +2025-04-19 04:16:59,202 INFO Epoch:90 val_res:0.933687 +2025-04-19 04:17:16,139 INFO Epoch:91 train_loss:0.00501 +2025-04-19 04:17:19,614 INFO Epoch:91 val_res:0.936339 +2025-04-19 04:17:37,357 INFO Epoch:92 train_loss:0.00486 +2025-04-19 04:17:40,846 INFO Epoch:92 val_res:0.938992 +2025-04-19 04:17:56,604 INFO Epoch:93 train_loss:0.00487 +2025-04-19 04:18:00,132 INFO Epoch:93 val_res:0.938992 +2025-04-19 04:18:17,425 INFO Epoch:94 train_loss:0.00471 +2025-04-19 04:18:20,788 INFO Epoch:94 val_res:0.941645 +2025-04-19 04:18:36,969 INFO Epoch:95 train_loss:0.00422 +2025-04-19 04:18:39,795 INFO Epoch:95 val_res:0.936339 +2025-04-19 04:18:55,429 INFO Epoch:96 train_loss:0.00423 +2025-04-19 04:18:59,165 INFO Epoch:96 val_res:0.936339 +2025-04-19 04:19:16,703 INFO Epoch:97 train_loss:0.00433 +2025-04-19 04:19:20,136 INFO Epoch:97 val_res:0.936339 +2025-04-19 04:19:37,162 INFO Epoch:98 train_loss:0.00431 +2025-04-19 04:19:40,213 INFO Epoch:98 val_res:0.936339 +2025-04-19 04:19:55,809 INFO Epoch:99 train_loss:0.00461 +2025-04-19 04:19:58,907 INFO Epoch:99 val_res:0.944297 +2025-04-19 04:19:59,139 INFO ===================================== +2025-04-19 04:19:59,139 INFO Start testing... +2025-04-19 04:19:59,140 INFO ===================================== +2025-04-19 04:20:21,323 INFO Incremental step 0 Testing res: 0.940860 +2025-04-19 04:20:21,326 INFO Incremental step: 1 +2025-04-19 04:23:37,730 INFO Epoch:0 train_loss:2.86524 +2025-04-19 04:24:10,399 INFO Epoch:0 val_res:0.451948 +2025-04-19 04:24:10,399 INFO Saving best model at Epoch 0 +2025-04-19 04:26:57,626 INFO Epoch:1 train_loss:1.86172 +2025-04-19 04:27:18,872 INFO Epoch:1 val_res:0.459740 +2025-04-19 04:27:18,873 INFO Saving best model at Epoch 1 +2025-04-19 04:28:53,917 INFO Epoch:2 train_loss:1.60560 +2025-04-19 04:29:07,570 INFO Epoch:2 val_res:0.471429 +2025-04-19 04:29:07,570 INFO Saving best model at Epoch 2 +2025-04-19 04:30:26,128 INFO Epoch:3 train_loss:1.49869 +2025-04-19 04:30:40,038 INFO Epoch:3 val_res:0.471429 +2025-04-19 04:31:27,906 INFO Epoch:4 train_loss:1.42917 +2025-04-19 04:31:36,125 INFO Epoch:4 val_res:0.484416 +2025-04-19 04:31:36,126 INFO Saving best model at Epoch 4 +2025-04-19 04:32:19,968 INFO Epoch:5 train_loss:1.39636 +2025-04-19 04:32:35,104 INFO Epoch:5 val_res:0.497403 +2025-04-19 04:32:35,105 INFO Saving best model at Epoch 5 +2025-04-19 04:33:19,150 INFO Epoch:6 train_loss:1.36978 +2025-04-19 04:33:26,204 INFO Epoch:6 val_res:0.500000 +2025-04-19 04:33:26,205 INFO Saving best model at Epoch 6 +2025-04-19 04:34:02,913 INFO Epoch:7 train_loss:1.33562 +2025-04-19 04:34:09,356 INFO Epoch:7 val_res:0.511688 +2025-04-19 04:34:09,356 INFO Saving best model at Epoch 7 +2025-04-19 04:34:49,661 INFO Epoch:8 train_loss:1.31282 +2025-04-19 04:34:55,900 INFO Epoch:8 val_res:0.522078 +2025-04-19 04:34:55,900 INFO Saving best model at Epoch 8 +2025-04-19 04:36:54,286 INFO Epoch:9 train_loss:1.28599 +2025-04-19 04:37:27,620 INFO Epoch:9 val_res:0.536364 +2025-04-19 04:37:27,620 INFO Saving best model at Epoch 9 +2025-04-19 04:40:30,588 INFO Epoch:10 train_loss:1.26897 +2025-04-19 04:40:57,852 INFO Epoch:10 val_res:0.538961 +2025-04-19 04:40:57,852 INFO Saving best model at Epoch 10 +2025-04-19 04:43:24,154 INFO Epoch:11 train_loss:1.25295 +2025-04-19 04:43:43,226 INFO Epoch:11 val_res:0.549351 +2025-04-19 04:43:43,227 INFO Saving best model at Epoch 11 +2025-04-19 04:45:53,290 INFO Epoch:12 train_loss:1.22782 +2025-04-19 04:46:17,925 INFO Epoch:12 val_res:0.564935 +2025-04-19 04:46:17,925 INFO Saving best model at Epoch 12 +2025-04-19 04:47:54,337 INFO Epoch:13 train_loss:1.20518 +2025-04-19 04:48:10,880 INFO Epoch:13 val_res:0.581818 +2025-04-19 04:48:10,881 INFO Saving best model at Epoch 13 +2025-04-19 04:49:25,762 INFO Epoch:14 train_loss:1.18096 +2025-04-19 04:49:44,594 INFO Epoch:14 val_res:0.584416 +2025-04-19 04:49:44,595 INFO Saving best model at Epoch 14 +2025-04-19 04:50:43,418 INFO Epoch:15 train_loss:1.16444 +2025-04-19 04:50:54,923 INFO Epoch:15 val_res:0.598701 +2025-04-19 04:50:54,924 INFO Saving best model at Epoch 15 +2025-04-19 04:51:35,341 INFO Epoch:16 train_loss:1.14941 +2025-04-19 04:51:49,011 INFO Epoch:16 val_res:0.611688 +2025-04-19 04:51:49,012 INFO Saving best model at Epoch 16 +2025-04-19 04:52:41,438 INFO Epoch:17 train_loss:1.14619 +2025-04-19 04:52:48,942 INFO Epoch:17 val_res:0.628571 +2025-04-19 04:52:48,943 INFO Saving best model at Epoch 17 +2025-04-19 04:53:32,774 INFO Epoch:18 train_loss:1.12863 +2025-04-19 04:53:41,354 INFO Epoch:18 val_res:0.615584 +2025-04-19 04:54:25,042 INFO Epoch:19 train_loss:1.12015 +2025-04-19 04:54:32,921 INFO Epoch:19 val_res:0.615584 +2025-04-19 04:55:16,381 INFO Epoch:20 train_loss:3.27834 +2025-04-19 04:55:25,612 INFO Epoch:20 val_res:0.659740 +2025-04-19 04:55:25,612 INFO Saving best model at Epoch 20 +2025-04-19 04:56:07,091 INFO Epoch:21 train_loss:2.50300 +2025-04-19 04:56:14,068 INFO Epoch:21 val_res:0.688312 +2025-04-19 04:56:14,069 INFO Saving best model at Epoch 21 +2025-04-19 04:56:55,230 INFO Epoch:22 train_loss:2.31707 +2025-04-19 04:57:02,182 INFO Epoch:22 val_res:0.679221 +2025-04-19 04:57:39,871 INFO Epoch:23 train_loss:2.19772 +2025-04-19 04:57:46,570 INFO Epoch:23 val_res:0.642857 +2025-04-19 04:58:37,245 INFO Epoch:24 train_loss:2.10469 +2025-04-19 04:58:44,102 INFO Epoch:24 val_res:0.694805 +2025-04-19 04:58:44,102 INFO Saving best model at Epoch 24 +2025-04-19 04:59:24,944 INFO Epoch:25 train_loss:2.03041 +2025-04-19 04:59:31,366 INFO Epoch:25 val_res:0.724675 +2025-04-19 04:59:31,370 INFO Saving best model at Epoch 25 +2025-04-19 05:00:15,148 INFO Epoch:26 train_loss:1.95323 +2025-04-19 05:00:20,868 INFO Epoch:26 val_res:0.724675 +2025-04-19 05:00:58,508 INFO Epoch:27 train_loss:1.91838 +2025-04-19 05:01:05,457 INFO Epoch:27 val_res:0.740260 +2025-04-19 05:01:05,457 INFO Saving best model at Epoch 27 +2025-04-19 05:01:42,326 INFO Epoch:28 train_loss:1.95947 +2025-04-19 05:01:48,347 INFO Epoch:28 val_res:0.749351 +2025-04-19 05:01:48,347 INFO Saving best model at Epoch 28 +2025-04-19 05:02:29,926 INFO Epoch:29 train_loss:1.88164 +2025-04-19 05:02:36,376 INFO Epoch:29 val_res:0.724675 +2025-04-19 05:03:17,755 INFO Epoch:30 train_loss:1.80760 +2025-04-19 05:03:24,928 INFO Epoch:30 val_res:0.725974 +2025-04-19 05:04:03,890 INFO Epoch:31 train_loss:1.75958 +2025-04-19 05:04:10,035 INFO Epoch:31 val_res:0.740260 +2025-04-19 05:04:54,951 INFO Epoch:32 train_loss:1.74929 +2025-04-19 05:05:01,704 INFO Epoch:32 val_res:0.750649 +2025-04-19 05:05:01,705 INFO Saving best model at Epoch 32 +2025-04-19 05:05:44,248 INFO Epoch:33 train_loss:1.72304 +2025-04-19 05:05:50,237 INFO Epoch:33 val_res:0.744156 +2025-04-19 05:06:30,969 INFO Epoch:34 train_loss:1.70187 +2025-04-19 05:06:38,996 INFO Epoch:34 val_res:0.750649 +2025-04-19 05:07:19,265 INFO Epoch:35 train_loss:1.67211 +2025-04-19 05:07:27,200 INFO Epoch:35 val_res:0.745455 +2025-04-19 05:08:11,403 INFO Epoch:36 train_loss:1.63796 +2025-04-19 05:08:17,347 INFO Epoch:36 val_res:0.744156 +2025-04-19 05:08:55,882 INFO Epoch:37 train_loss:1.65980 +2025-04-19 05:09:03,025 INFO Epoch:37 val_res:0.757143 +2025-04-19 05:09:03,026 INFO Saving best model at Epoch 37 +2025-04-19 05:09:45,544 INFO Epoch:38 train_loss:1.65653 +2025-04-19 05:09:53,608 INFO Epoch:38 val_res:0.750649 +2025-04-19 05:10:36,252 INFO Epoch:39 train_loss:1.62727 +2025-04-19 05:10:42,483 INFO Epoch:39 val_res:0.753247 +2025-04-19 05:11:23,865 INFO Epoch:40 train_loss:1.60443 +2025-04-19 05:11:42,531 INFO Epoch:40 val_res:0.750649 +2025-04-19 05:12:40,936 INFO Epoch:41 train_loss:1.61114 +2025-04-19 05:12:49,533 INFO Epoch:41 val_res:0.722078 +2025-04-19 05:13:28,712 INFO Epoch:42 train_loss:1.66363 +2025-04-19 05:13:35,507 INFO Epoch:42 val_res:0.735065 +2025-04-19 05:14:15,793 INFO Epoch:43 train_loss:1.65932 +2025-04-19 05:14:22,228 INFO Epoch:43 val_res:0.754545 +2025-04-19 05:14:57,293 INFO Epoch:44 train_loss:1.58186 +2025-04-19 05:15:04,790 INFO Epoch:44 val_res:0.750649 +2025-04-19 05:15:41,806 INFO Epoch:45 train_loss:1.56407 +2025-04-19 05:15:49,520 INFO Epoch:45 val_res:0.753247 +2025-04-19 05:16:25,705 INFO Epoch:46 train_loss:1.56778 +2025-04-19 05:16:31,829 INFO Epoch:46 val_res:0.751948 +2025-04-19 05:17:12,143 INFO Epoch:47 train_loss:1.55354 +2025-04-19 05:17:26,504 INFO Epoch:47 val_res:0.745455 +2025-04-19 05:18:09,032 INFO Epoch:48 train_loss:1.52545 +2025-04-19 05:18:19,379 INFO Epoch:48 val_res:0.750649 +2025-04-19 05:18:58,915 INFO Epoch:49 train_loss:1.53381 +2025-04-19 05:19:08,901 INFO Epoch:49 val_res:0.745455 +2025-04-19 05:19:51,693 INFO Epoch:50 train_loss:1.52839 +2025-04-19 05:19:57,761 INFO Epoch:50 val_res:0.738961 +2025-04-19 05:20:34,982 INFO Epoch:51 train_loss:1.54447 +2025-04-19 05:20:41,925 INFO Epoch:51 val_res:0.758442 +2025-04-19 05:20:41,926 INFO Saving best model at Epoch 51 +2025-04-19 05:21:22,774 INFO Epoch:52 train_loss:1.55058 +2025-04-19 05:21:29,604 INFO Epoch:52 val_res:0.729870 +2025-04-19 05:22:09,307 INFO Epoch:53 train_loss:1.53851 +2025-04-19 05:22:15,676 INFO Epoch:53 val_res:0.761039 +2025-04-19 05:22:15,677 INFO Saving best model at Epoch 53 +2025-04-19 05:22:56,071 INFO Epoch:54 train_loss:1.52268 +2025-04-19 05:23:03,446 INFO Epoch:54 val_res:0.751948 +2025-04-19 05:23:40,026 INFO Epoch:55 train_loss:1.51815 +2025-04-19 05:23:46,258 INFO Epoch:55 val_res:0.754545 +2025-04-19 05:24:24,467 INFO Epoch:56 train_loss:1.51554 +2025-04-19 05:24:30,506 INFO Epoch:56 val_res:0.754545 +2025-04-19 05:25:08,526 INFO Epoch:57 train_loss:1.48923 +2025-04-19 05:25:15,367 INFO Epoch:57 val_res:0.741558 +2025-04-19 05:25:58,150 INFO Epoch:58 train_loss:1.50716 +2025-04-19 05:26:04,711 INFO Epoch:58 val_res:0.731169 +2025-04-19 05:26:40,441 INFO Epoch:59 train_loss:1.54013 +2025-04-19 05:26:46,403 INFO Epoch:59 val_res:0.750649 +2025-04-19 05:27:23,339 INFO Epoch:60 train_loss:1.51642 +2025-04-19 05:27:28,715 INFO Epoch:60 val_res:0.742857 +2025-04-19 05:28:07,840 INFO Epoch:61 train_loss:1.52539 +2025-04-19 05:28:14,478 INFO Epoch:61 val_res:0.733766 +2025-04-19 05:28:53,833 INFO Epoch:62 train_loss:1.49628 +2025-04-19 05:29:00,506 INFO Epoch:62 val_res:0.748052 +2025-04-19 05:29:42,988 INFO Epoch:63 train_loss:1.47385 +2025-04-19 05:29:49,606 INFO Epoch:63 val_res:0.744156 +2025-04-19 05:30:29,136 INFO Epoch:64 train_loss:1.43495 +2025-04-19 05:30:35,133 INFO Epoch:64 val_res:0.755844 +2025-04-19 05:31:08,617 INFO Epoch:65 train_loss:1.44444 +2025-04-19 05:31:14,946 INFO Epoch:65 val_res:0.746753 +2025-04-19 05:31:49,768 INFO Epoch:66 train_loss:1.45283 +2025-04-19 05:31:55,027 INFO Epoch:66 val_res:0.742857 +2025-04-19 05:32:33,094 INFO Epoch:67 train_loss:1.42659 +2025-04-19 05:32:40,606 INFO Epoch:67 val_res:0.746753 +2025-04-19 05:33:24,581 INFO Epoch:68 train_loss:1.44370 +2025-04-19 05:33:32,139 INFO Epoch:68 val_res:0.750649 +2025-04-19 05:34:13,429 INFO Epoch:69 train_loss:1.46101 +2025-04-19 05:34:19,081 INFO Epoch:69 val_res:0.737662 +2025-04-19 05:35:00,256 INFO Epoch:70 train_loss:1.44780 +2025-04-19 05:35:08,716 INFO Epoch:70 val_res:0.751948 +2025-04-19 05:35:49,858 INFO Epoch:71 train_loss:0.82299 +2025-04-19 05:35:57,506 INFO Epoch:71 val_res:0.749351 +2025-04-19 05:36:35,492 INFO Epoch:72 train_loss:0.81096 +2025-04-19 05:36:52,727 INFO Epoch:72 val_res:0.754545 +2025-04-19 05:37:33,162 INFO Epoch:73 train_loss:0.80688 +2025-04-19 05:37:42,957 INFO Epoch:73 val_res:0.748052 +2025-04-19 05:38:21,732 INFO Epoch:74 train_loss:0.79818 +2025-04-19 05:38:28,060 INFO Epoch:74 val_res:0.746753 +2025-04-19 05:39:04,449 INFO Epoch:75 train_loss:0.80204 +2025-04-19 05:39:15,032 INFO Epoch:75 val_res:0.750649 +2025-04-19 05:39:51,655 INFO Epoch:76 train_loss:0.79733 +2025-04-19 05:40:06,290 INFO Epoch:76 val_res:0.750649 +2025-04-19 05:40:43,157 INFO Epoch:77 train_loss:0.79575 +2025-04-19 05:40:55,092 INFO Epoch:77 val_res:0.754545 +2025-04-19 05:41:32,378 INFO Epoch:78 train_loss:0.78721 +2025-04-19 05:41:41,574 INFO Epoch:78 val_res:0.753247 +2025-04-19 05:42:20,785 INFO Epoch:79 train_loss:0.78318 +2025-04-19 05:42:30,332 INFO Epoch:79 val_res:0.745455 +2025-04-19 05:43:05,043 INFO Epoch:80 train_loss:0.79366 +2025-04-19 05:43:18,131 INFO Epoch:80 val_res:0.748052 +2025-04-19 05:43:54,989 INFO Epoch:81 train_loss:0.78823 +2025-04-19 05:44:01,431 INFO Epoch:81 val_res:0.758442 +2025-04-19 05:44:37,159 INFO Epoch:82 train_loss:0.78828 +2025-04-19 05:44:45,489 INFO Epoch:82 val_res:0.754545 +2025-04-19 05:45:21,031 INFO Epoch:83 train_loss:0.78942 +2025-04-19 05:45:29,307 INFO Epoch:83 val_res:0.750649 +2025-04-19 05:46:08,312 INFO Epoch:84 train_loss:0.79129 +2025-04-19 05:46:14,900 INFO Epoch:84 val_res:0.741558 +2025-04-19 05:46:50,424 INFO Epoch:85 train_loss:0.78465 +2025-04-19 05:46:56,937 INFO Epoch:85 val_res:0.745455 +2025-04-19 05:47:33,219 INFO Epoch:86 train_loss:0.77604 +2025-04-19 05:47:38,885 INFO Epoch:86 val_res:0.754545 +2025-04-19 05:48:13,846 INFO Epoch:87 train_loss:0.77522 +2025-04-19 05:48:19,880 INFO Epoch:87 val_res:0.744156 +2025-04-19 05:48:51,377 INFO Epoch:88 train_loss:0.78599 +2025-04-19 05:48:56,981 INFO Epoch:88 val_res:0.737662 +2025-04-19 05:49:34,384 INFO Epoch:89 train_loss:0.79042 +2025-04-19 05:49:40,139 INFO Epoch:89 val_res:0.742857 +2025-04-19 05:50:20,613 INFO Epoch:90 train_loss:0.78296 +2025-04-19 05:50:27,110 INFO Epoch:90 val_res:0.748052 +2025-04-19 05:51:04,994 INFO Epoch:91 train_loss:0.78861 +2025-04-19 05:51:12,416 INFO Epoch:91 val_res:0.753247 +2025-04-19 05:51:51,510 INFO Epoch:92 train_loss:0.78865 +2025-04-19 05:51:57,173 INFO Epoch:92 val_res:0.716883 +2025-04-19 05:52:30,538 INFO Epoch:93 train_loss:0.83226 +2025-04-19 05:52:36,444 INFO Epoch:93 val_res:0.750649 +2025-04-19 05:53:13,634 INFO Epoch:94 train_loss:0.79646 +2025-04-19 05:53:20,669 INFO Epoch:94 val_res:0.748052 +2025-04-19 05:53:58,430 INFO Epoch:95 train_loss:0.83726 +2025-04-19 05:54:04,847 INFO Epoch:95 val_res:0.741558 +2025-04-19 05:54:40,443 INFO Epoch:96 train_loss:0.82912 +2025-04-19 05:54:45,898 INFO Epoch:96 val_res:0.753247 +2025-04-19 05:55:18,486 INFO Epoch:97 train_loss:0.79460 +2025-04-19 05:55:24,077 INFO Epoch:97 val_res:0.746753 +2025-04-19 05:55:56,629 INFO Epoch:98 train_loss:0.78010 +2025-04-19 05:56:02,471 INFO Epoch:98 val_res:0.755844 +2025-04-19 05:56:32,828 INFO Epoch:99 train_loss:0.77061 +2025-04-19 05:56:37,375 INFO Epoch:99 val_res:0.746753 +2025-04-19 05:56:38,659 INFO ===================================== +2025-04-19 05:56:38,660 INFO Start testing... +2025-04-19 05:56:38,661 INFO ===================================== +2025-04-19 05:57:00,693 INFO Incremental step 1 Testing res: 0.725974 +2025-04-19 05:57:00,694 INFO forgetting: 0.161290 +2025-04-19 05:57:00,698 INFO Incremental step: 2 +2025-04-19 05:59:27,775 INFO Epoch:0 train_loss:3.98494 +2025-04-19 05:59:53,939 INFO Epoch:0 val_res:0.504340 +2025-04-19 05:59:53,939 INFO Saving best model at Epoch 0 +2025-04-19 06:01:24,245 INFO Epoch:1 train_loss:1.97680 +2025-04-19 06:01:36,859 INFO Epoch:1 val_res:0.512153 +2025-04-19 06:01:36,860 INFO Saving best model at Epoch 1 +2025-04-19 06:02:42,106 INFO Epoch:2 train_loss:1.57086 +2025-04-19 06:02:49,937 INFO Epoch:2 val_res:0.531250 +2025-04-19 06:02:49,938 INFO Saving best model at Epoch 2 +2025-04-19 06:03:28,191 INFO Epoch:3 train_loss:1.43188 +2025-04-19 06:03:35,831 INFO Epoch:3 val_res:0.530382 +2025-04-19 06:04:10,475 INFO Epoch:4 train_loss:1.38043 +2025-04-19 06:04:17,885 INFO Epoch:4 val_res:0.536458 +2025-04-19 06:04:17,886 INFO Saving best model at Epoch 4 +2025-04-19 06:04:53,469 INFO Epoch:5 train_loss:1.34160 +2025-04-19 06:05:01,237 INFO Epoch:5 val_res:0.540799 +2025-04-19 06:05:01,238 INFO Saving best model at Epoch 5 +2025-04-19 06:05:37,918 INFO Epoch:6 train_loss:1.30318 +2025-04-19 06:05:52,152 INFO Epoch:6 val_res:0.545139 +2025-04-19 06:05:52,152 INFO Saving best model at Epoch 6 +2025-04-19 06:06:31,569 INFO Epoch:7 train_loss:1.28290 +2025-04-19 06:06:45,662 INFO Epoch:7 val_res:0.556424 +2025-04-19 06:06:45,663 INFO Saving best model at Epoch 7 +2025-04-19 06:07:33,933 INFO Epoch:8 train_loss:1.25549 +2025-04-19 06:07:40,958 INFO Epoch:8 val_res:0.562500 +2025-04-19 06:07:40,959 INFO Saving best model at Epoch 8 +2025-04-19 06:08:19,780 INFO Epoch:9 train_loss:1.24009 +2025-04-19 06:08:28,528 INFO Epoch:9 val_res:0.570312 +2025-04-19 06:08:28,529 INFO Saving best model at Epoch 9 +2025-04-19 06:09:09,806 INFO Epoch:10 train_loss:1.21848 +2025-04-19 06:09:18,078 INFO Epoch:10 val_res:0.570312 +2025-04-19 06:09:54,057 INFO Epoch:11 train_loss:1.20424 +2025-04-19 06:10:01,894 INFO Epoch:11 val_res:0.578993 +2025-04-19 06:10:01,895 INFO Saving best model at Epoch 11 +2025-04-19 06:10:40,804 INFO Epoch:12 train_loss:1.18202 +2025-04-19 06:10:49,224 INFO Epoch:12 val_res:0.578125 +2025-04-19 06:11:23,847 INFO Epoch:13 train_loss:1.17189 +2025-04-19 06:11:32,146 INFO Epoch:13 val_res:0.592014 +2025-04-19 06:11:32,147 INFO Saving best model at Epoch 13 +2025-04-19 06:12:11,193 INFO Epoch:14 train_loss:1.15680 +2025-04-19 06:12:19,391 INFO Epoch:14 val_res:0.592882 +2025-04-19 06:12:19,392 INFO Saving best model at Epoch 14 +2025-04-19 06:12:56,819 INFO Epoch:15 train_loss:1.14023 +2025-04-19 06:13:04,669 INFO Epoch:15 val_res:0.595486 +2025-04-19 06:13:04,670 INFO Saving best model at Epoch 15 +2025-04-19 06:13:40,492 INFO Epoch:16 train_loss:1.11850 +2025-04-19 06:13:47,331 INFO Epoch:16 val_res:0.600694 +2025-04-19 06:13:47,332 INFO Saving best model at Epoch 16 +2025-04-19 06:14:22,917 INFO Epoch:17 train_loss:1.11359 +2025-04-19 06:14:31,340 INFO Epoch:17 val_res:0.607639 +2025-04-19 06:14:31,340 INFO Saving best model at Epoch 17 +2025-04-19 06:15:07,948 INFO Epoch:18 train_loss:1.09457 +2025-04-19 06:15:15,987 INFO Epoch:18 val_res:0.611111 +2025-04-19 06:15:15,988 INFO Saving best model at Epoch 18 +2025-04-19 06:15:53,770 INFO Epoch:19 train_loss:1.08432 +2025-04-19 06:16:00,969 INFO Epoch:19 val_res:0.610243 +2025-04-19 06:16:37,517 INFO Epoch:20 train_loss:5.21794 +2025-04-19 06:16:45,914 INFO Epoch:20 val_res:0.573785 +2025-04-19 06:17:23,788 INFO Epoch:21 train_loss:3.93512 +2025-04-19 06:17:32,428 INFO Epoch:21 val_res:0.592882 +2025-04-19 06:18:09,274 INFO Epoch:22 train_loss:2.81847 +2025-04-19 06:18:16,600 INFO Epoch:22 val_res:0.619792 +2025-04-19 06:18:16,600 INFO Saving best model at Epoch 22 +2025-04-19 06:18:58,418 INFO Epoch:23 train_loss:2.46333 +2025-04-19 06:19:06,017 INFO Epoch:23 val_res:0.625868 +2025-04-19 06:19:06,018 INFO Saving best model at Epoch 23 +2025-04-19 06:19:43,463 INFO Epoch:24 train_loss:2.34858 +2025-04-19 06:19:52,075 INFO Epoch:24 val_res:0.631944 +2025-04-19 06:19:52,076 INFO Saving best model at Epoch 24 +2025-04-19 06:20:34,231 INFO Epoch:25 train_loss:2.27975 +2025-04-19 06:20:42,681 INFO Epoch:25 val_res:0.628472 +2025-04-19 06:21:21,711 INFO Epoch:26 train_loss:2.21290 +2025-04-19 06:21:30,727 INFO Epoch:26 val_res:0.628472 +2025-04-19 06:22:07,012 INFO Epoch:27 train_loss:2.15009 +2025-04-19 06:22:15,453 INFO Epoch:27 val_res:0.639757 +2025-04-19 06:22:15,464 INFO Saving best model at Epoch 27 +2025-04-19 06:22:53,693 INFO Epoch:28 train_loss:2.10568 +2025-04-19 06:23:01,484 INFO Epoch:28 val_res:0.638021 +2025-04-19 06:23:39,129 INFO Epoch:29 train_loss:2.05380 +2025-04-19 06:23:47,159 INFO Epoch:29 val_res:0.640625 +2025-04-19 06:23:47,159 INFO Saving best model at Epoch 29 +2025-04-19 06:24:25,293 INFO Epoch:30 train_loss:2.02988 +2025-04-19 06:24:32,745 INFO Epoch:30 val_res:0.644965 +2025-04-19 06:24:32,746 INFO Saving best model at Epoch 30 +2025-04-19 06:25:08,639 INFO Epoch:31 train_loss:1.99147 +2025-04-19 06:25:16,413 INFO Epoch:31 val_res:0.648438 +2025-04-19 06:25:16,414 INFO Saving best model at Epoch 31 +2025-04-19 06:25:54,515 INFO Epoch:32 train_loss:1.97147 +2025-04-19 06:26:02,169 INFO Epoch:32 val_res:0.651910 +2025-04-19 06:26:02,170 INFO Saving best model at Epoch 32 +2025-04-19 06:26:42,335 INFO Epoch:33 train_loss:1.97576 +2025-04-19 06:26:50,483 INFO Epoch:33 val_res:0.658854 +2025-04-19 06:26:50,483 INFO Saving best model at Epoch 33 +2025-04-19 06:27:29,458 INFO Epoch:34 train_loss:1.93580 +2025-04-19 06:27:38,461 INFO Epoch:34 val_res:0.654514 +2025-04-19 06:28:15,970 INFO Epoch:35 train_loss:1.89299 +2025-04-19 06:28:27,257 INFO Epoch:35 val_res:0.662326 +2025-04-19 06:28:27,258 INFO Saving best model at Epoch 35 +2025-04-19 06:29:06,614 INFO Epoch:36 train_loss:1.88282 +2025-04-19 06:29:14,009 INFO Epoch:36 val_res:0.658854 +2025-04-19 06:29:57,320 INFO Epoch:37 train_loss:1.86642 +2025-04-19 06:30:06,146 INFO Epoch:37 val_res:0.658854 +2025-04-19 06:30:40,761 INFO Epoch:38 train_loss:1.80026 +2025-04-19 06:30:49,632 INFO Epoch:38 val_res:0.657118 +2025-04-19 06:31:26,983 INFO Epoch:39 train_loss:1.76653 +2025-04-19 06:31:35,718 INFO Epoch:39 val_res:0.672743 +2025-04-19 06:31:35,720 INFO Saving best model at Epoch 39 +2025-04-19 06:32:14,390 INFO Epoch:40 train_loss:1.76311 +2025-04-19 06:32:22,192 INFO Epoch:40 val_res:0.667535 +2025-04-19 06:32:57,048 INFO Epoch:41 train_loss:1.73818 +2025-04-19 06:33:03,782 INFO Epoch:41 val_res:0.669271 +2025-04-19 06:33:41,562 INFO Epoch:42 train_loss:1.71259 +2025-04-19 06:33:48,315 INFO Epoch:42 val_res:0.670139 +2025-04-19 06:34:28,064 INFO Epoch:43 train_loss:1.74167 +2025-04-19 06:34:36,119 INFO Epoch:43 val_res:0.676215 +2025-04-19 06:34:36,120 INFO Saving best model at Epoch 43 +2025-04-19 06:35:16,493 INFO Epoch:44 train_loss:1.72084 +2025-04-19 06:35:24,243 INFO Epoch:44 val_res:0.671875 +2025-04-19 06:36:00,455 INFO Epoch:45 train_loss:1.69595 +2025-04-19 06:36:09,111 INFO Epoch:45 val_res:0.677951 +2025-04-19 06:36:09,112 INFO Saving best model at Epoch 45 +2025-04-19 06:36:49,645 INFO Epoch:46 train_loss:1.67905 +2025-04-19 06:36:57,621 INFO Epoch:46 val_res:0.680556 +2025-04-19 06:36:57,622 INFO Saving best model at Epoch 46 +2025-04-19 06:37:39,298 INFO Epoch:47 train_loss:1.72148 +2025-04-19 06:37:47,475 INFO Epoch:47 val_res:0.694444 +2025-04-19 06:37:47,478 INFO Saving best model at Epoch 47 +2025-04-19 06:38:28,564 INFO Epoch:48 train_loss:1.69082 +2025-04-19 06:38:36,421 INFO Epoch:48 val_res:0.688368 +2025-04-19 06:39:12,304 INFO Epoch:49 train_loss:1.65990 +2025-04-19 06:39:19,698 INFO Epoch:49 val_res:0.690104 +2025-04-19 06:39:55,030 INFO Epoch:50 train_loss:1.65091 +2025-04-19 06:40:03,543 INFO Epoch:50 val_res:0.686632 +2025-04-19 06:40:40,396 INFO Epoch:51 train_loss:1.64610 +2025-04-19 06:40:49,052 INFO Epoch:51 val_res:0.695312 +2025-04-19 06:40:49,052 INFO Saving best model at Epoch 51 +2025-04-19 06:41:31,418 INFO Epoch:52 train_loss:1.63999 +2025-04-19 06:41:39,939 INFO Epoch:52 val_res:0.690972 +2025-04-19 06:42:16,801 INFO Epoch:53 train_loss:1.61812 +2025-04-19 06:42:24,470 INFO Epoch:53 val_res:0.695312 +2025-04-19 06:43:03,361 INFO Epoch:54 train_loss:1.64301 +2025-04-19 06:43:11,751 INFO Epoch:54 val_res:0.683160 +2025-04-19 06:43:49,733 INFO Epoch:55 train_loss:1.62962 +2025-04-19 06:43:57,921 INFO Epoch:55 val_res:0.696181 +2025-04-19 06:43:57,922 INFO Saving best model at Epoch 55 +2025-04-19 06:44:37,318 INFO Epoch:56 train_loss:1.59008 +2025-04-19 06:44:46,120 INFO Epoch:56 val_res:0.695312 +2025-04-19 06:45:25,922 INFO Epoch:57 train_loss:1.60350 +2025-04-19 06:45:34,024 INFO Epoch:57 val_res:0.684896 +2025-04-19 06:46:13,866 INFO Epoch:58 train_loss:1.58373 +2025-04-19 06:46:22,391 INFO Epoch:58 val_res:0.698785 +2025-04-19 06:46:22,392 INFO Saving best model at Epoch 58 +2025-04-19 06:47:02,380 INFO Epoch:59 train_loss:1.57179 +2025-04-19 06:47:10,249 INFO Epoch:59 val_res:0.697049 +2025-04-19 06:47:48,236 INFO Epoch:60 train_loss:1.55154 +2025-04-19 06:47:56,551 INFO Epoch:60 val_res:0.692708 +2025-04-19 06:48:36,077 INFO Epoch:61 train_loss:1.57029 +2025-04-19 06:48:44,158 INFO Epoch:61 val_res:0.690972 +2025-04-19 06:49:21,030 INFO Epoch:62 train_loss:1.57762 +2025-04-19 06:49:30,181 INFO Epoch:62 val_res:0.690972 +2025-04-19 06:50:07,262 INFO Epoch:63 train_loss:1.56607 +2025-04-19 06:50:15,305 INFO Epoch:63 val_res:0.697917 +2025-04-19 06:50:54,000 INFO Epoch:64 train_loss:1.55225 +2025-04-19 06:51:02,152 INFO Epoch:64 val_res:0.698785 +2025-04-19 06:51:40,302 INFO Epoch:65 train_loss:1.56872 +2025-04-19 06:51:48,300 INFO Epoch:65 val_res:0.689236 +2025-04-19 06:52:29,042 INFO Epoch:66 train_loss:1.59397 +2025-04-19 06:52:37,618 INFO Epoch:66 val_res:0.690972 +2025-04-19 06:53:17,047 INFO Epoch:67 train_loss:1.59293 +2025-04-19 06:53:25,185 INFO Epoch:67 val_res:0.685764 +2025-04-19 06:54:02,845 INFO Epoch:68 train_loss:1.58704 +2025-04-19 06:54:11,008 INFO Epoch:68 val_res:0.690104 +2025-04-19 06:54:49,149 INFO Epoch:69 train_loss:1.51937 +2025-04-19 06:54:57,847 INFO Epoch:69 val_res:0.691840 +2025-04-19 06:55:38,187 INFO Epoch:70 train_loss:1.54910 +2025-04-19 06:55:46,043 INFO Epoch:70 val_res:0.685764 +2025-04-19 06:56:19,004 INFO Epoch:71 train_loss:0.83499 +2025-04-19 06:56:27,393 INFO Epoch:71 val_res:0.694444 +2025-04-19 06:57:05,934 INFO Epoch:72 train_loss:0.81078 +2025-04-19 06:57:14,691 INFO Epoch:72 val_res:0.700521 +2025-04-19 06:57:14,691 INFO Saving best model at Epoch 72 +2025-04-19 06:57:54,787 INFO Epoch:73 train_loss:0.79691 +2025-04-19 06:58:02,536 INFO Epoch:73 val_res:0.701389 +2025-04-19 06:58:02,536 INFO Saving best model at Epoch 73 +2025-04-19 06:58:41,223 INFO Epoch:74 train_loss:0.79048 +2025-04-19 06:58:48,623 INFO Epoch:74 val_res:0.698785 +2025-04-19 06:59:21,418 INFO Epoch:75 train_loss:0.79256 +2025-04-19 06:59:28,542 INFO Epoch:75 val_res:0.700521 +2025-04-19 07:00:02,586 INFO Epoch:76 train_loss:0.78882 +2025-04-19 07:00:10,217 INFO Epoch:76 val_res:0.702257 +2025-04-19 07:00:10,217 INFO Saving best model at Epoch 76 +2025-04-19 07:00:47,261 INFO Epoch:77 train_loss:0.79244 +2025-04-19 07:00:54,814 INFO Epoch:77 val_res:0.700521 +2025-04-19 07:01:29,088 INFO Epoch:78 train_loss:0.78766 +2025-04-19 07:01:36,110 INFO Epoch:78 val_res:0.704861 +2025-04-19 07:01:36,111 INFO Saving best model at Epoch 78 +2025-04-19 07:02:12,843 INFO Epoch:79 train_loss:0.78181 +2025-04-19 07:02:20,167 INFO Epoch:79 val_res:0.699653 +2025-04-19 07:02:53,377 INFO Epoch:80 train_loss:0.78218 +2025-04-19 07:02:59,976 INFO Epoch:80 val_res:0.703125 +2025-04-19 07:03:33,293 INFO Epoch:81 train_loss:0.78248 +2025-04-19 07:03:40,491 INFO Epoch:81 val_res:0.698785 +2025-04-19 07:04:17,748 INFO Epoch:82 train_loss:0.78123 +2025-04-19 07:04:26,416 INFO Epoch:82 val_res:0.703125 +2025-04-19 07:05:03,049 INFO Epoch:83 train_loss:0.77820 +2025-04-19 07:05:11,741 INFO Epoch:83 val_res:0.697049 +2025-04-19 07:05:50,687 INFO Epoch:84 train_loss:0.77979 +2025-04-19 07:05:59,162 INFO Epoch:84 val_res:0.697049 +2025-04-19 07:06:35,946 INFO Epoch:85 train_loss:0.78143 +2025-04-19 07:06:43,960 INFO Epoch:85 val_res:0.697917 +2025-04-19 07:07:21,385 INFO Epoch:86 train_loss:0.78136 +2025-04-19 07:07:29,859 INFO Epoch:86 val_res:0.697917 +2025-04-19 07:08:05,668 INFO Epoch:87 train_loss:0.77522 +2025-04-19 07:08:13,942 INFO Epoch:87 val_res:0.697917 +2025-04-19 07:08:48,459 INFO Epoch:88 train_loss:0.77460 +2025-04-19 07:08:55,433 INFO Epoch:88 val_res:0.698785 +2025-04-19 07:09:31,969 INFO Epoch:89 train_loss:0.77384 +2025-04-19 07:09:40,033 INFO Epoch:89 val_res:0.699653 +2025-04-19 07:10:17,684 INFO Epoch:90 train_loss:0.77162 +2025-04-19 07:10:25,821 INFO Epoch:90 val_res:0.701389 +2025-04-19 07:11:00,518 INFO Epoch:91 train_loss:0.77844 +2025-04-19 07:11:07,983 INFO Epoch:91 val_res:0.697917 +2025-04-19 07:11:40,893 INFO Epoch:92 train_loss:0.77557 +2025-04-19 07:11:48,785 INFO Epoch:92 val_res:0.690972 +2025-04-19 07:12:22,204 INFO Epoch:93 train_loss:0.78292 +2025-04-19 07:12:28,821 INFO Epoch:93 val_res:0.702257 +2025-04-19 07:12:58,296 INFO Epoch:94 train_loss:0.78106 +2025-04-19 07:13:05,061 INFO Epoch:94 val_res:0.703125 +2025-04-19 07:13:43,841 INFO Epoch:95 train_loss:0.78350 +2025-04-19 07:13:52,444 INFO Epoch:95 val_res:0.700521 +2025-04-19 07:14:25,853 INFO Epoch:96 train_loss:0.77319 +2025-04-19 07:14:33,933 INFO Epoch:96 val_res:0.706597 +2025-04-19 07:14:33,933 INFO Saving best model at Epoch 96 +2025-04-19 07:15:08,502 INFO Epoch:97 train_loss:0.77109 +2025-04-19 07:15:18,140 INFO Epoch:97 val_res:0.697049 +2025-04-19 07:15:56,600 INFO Epoch:98 train_loss:0.76836 +2025-04-19 07:16:10,829 INFO Epoch:98 val_res:0.703125 +2025-04-19 07:16:47,966 INFO Epoch:99 train_loss:0.76977 +2025-04-19 07:16:59,102 INFO Epoch:99 val_res:0.698785 +2025-04-19 07:16:59,772 INFO ===================================== +2025-04-19 07:16:59,772 INFO Start testing... +2025-04-19 07:16:59,772 INFO ===================================== +2025-04-19 07:18:20,399 INFO Incremental step 2 Testing res: 0.680243 +2025-04-19 07:18:20,403 INFO forgetting: 0.078220 +2025-04-19 07:18:20,415 INFO Incremental step: 3 +2025-04-19 07:19:15,719 INFO Epoch:0 train_loss:5.04110 +2025-04-19 07:19:42,019 INFO Epoch:0 val_res:0.474708 +2025-04-19 07:19:42,020 INFO Saving best model at Epoch 0 +2025-04-19 07:20:28,446 INFO Epoch:1 train_loss:2.07519 +2025-04-19 07:20:38,885 INFO Epoch:1 val_res:0.510376 +2025-04-19 07:20:38,891 INFO Saving best model at Epoch 1 +2025-04-19 07:21:22,425 INFO Epoch:2 train_loss:1.46717 +2025-04-19 07:21:32,562 INFO Epoch:2 val_res:0.529831 +2025-04-19 07:21:32,568 INFO Saving best model at Epoch 2 +2025-04-19 07:22:15,540 INFO Epoch:3 train_loss:1.30316 +2025-04-19 07:22:25,721 INFO Epoch:3 val_res:0.533074 +2025-04-19 07:22:25,729 INFO Saving best model at Epoch 3 +2025-04-19 07:23:08,724 INFO Epoch:4 train_loss:1.22909 +2025-04-19 07:23:19,463 INFO Epoch:4 val_res:0.534371 +2025-04-19 07:23:19,463 INFO Saving best model at Epoch 4 +2025-04-19 07:24:02,078 INFO Epoch:5 train_loss:1.18290 +2025-04-19 07:24:12,578 INFO Epoch:5 val_res:0.538911 +2025-04-19 07:24:12,580 INFO Saving best model at Epoch 5 +2025-04-19 07:24:54,915 INFO Epoch:6 train_loss:1.15891 +2025-04-19 07:25:05,128 INFO Epoch:6 val_res:0.540856 +2025-04-19 07:25:05,129 INFO Saving best model at Epoch 6 +2025-04-19 07:25:47,638 INFO Epoch:7 train_loss:1.13788 +2025-04-19 07:25:57,815 INFO Epoch:7 val_res:0.544747 +2025-04-19 07:25:57,816 INFO Saving best model at Epoch 7 +2025-04-19 07:26:39,782 INFO Epoch:8 train_loss:1.11308 +2025-04-19 07:26:49,516 INFO Epoch:8 val_res:0.543450 +2025-04-19 07:27:27,982 INFO Epoch:9 train_loss:1.10371 +2025-04-19 07:27:36,763 INFO Epoch:9 val_res:0.547341 +2025-04-19 07:27:36,764 INFO Saving best model at Epoch 9 +2025-04-19 07:28:16,927 INFO Epoch:10 train_loss:1.08555 +2025-04-19 07:28:25,857 INFO Epoch:10 val_res:0.555123 +2025-04-19 07:28:25,863 INFO Saving best model at Epoch 10 +2025-04-19 07:29:04,647 INFO Epoch:11 train_loss:1.06221 +2025-04-19 07:29:13,089 INFO Epoch:11 val_res:0.557717 +2025-04-19 07:29:13,097 INFO Saving best model at Epoch 11 +2025-04-19 07:29:50,872 INFO Epoch:12 train_loss:1.05791 +2025-04-19 07:29:59,390 INFO Epoch:12 val_res:0.562905 +2025-04-19 07:29:59,403 INFO Saving best model at Epoch 12 +2025-04-19 07:30:36,733 INFO Epoch:13 train_loss:1.04848 +2025-04-19 07:30:45,505 INFO Epoch:13 val_res:0.562257 +2025-04-19 07:31:23,061 INFO Epoch:14 train_loss:1.03987 +2025-04-19 07:31:31,362 INFO Epoch:14 val_res:0.569390 +2025-04-19 07:31:31,362 INFO Saving best model at Epoch 14 +2025-04-19 07:32:08,012 INFO Epoch:15 train_loss:1.03410 +2025-04-19 07:32:17,393 INFO Epoch:15 val_res:0.571984 +2025-04-19 07:32:17,400 INFO Saving best model at Epoch 15 +2025-04-19 07:32:55,325 INFO Epoch:16 train_loss:1.02395 +2025-04-19 07:33:03,483 INFO Epoch:16 val_res:0.566796 +2025-04-19 07:33:40,427 INFO Epoch:17 train_loss:1.01002 +2025-04-19 07:33:47,963 INFO Epoch:17 val_res:0.574578 +2025-04-19 07:33:47,969 INFO Saving best model at Epoch 17 +2025-04-19 07:34:24,254 INFO Epoch:18 train_loss:1.00008 +2025-04-19 07:34:32,258 INFO Epoch:18 val_res:0.573930 +2025-04-19 07:35:05,510 INFO Epoch:19 train_loss:0.99077 +2025-04-19 07:35:13,552 INFO Epoch:19 val_res:0.583658 +2025-04-19 07:35:13,558 INFO Saving best model at Epoch 19 +2025-04-19 07:35:51,898 INFO Epoch:20 train_loss:7.74159 +2025-04-19 07:36:00,047 INFO Epoch:20 val_res:0.549287 +2025-04-19 07:36:36,919 INFO Epoch:21 train_loss:4.09530 +2025-04-19 07:36:45,546 INFO Epoch:21 val_res:0.581712 +2025-04-19 07:37:21,799 INFO Epoch:22 train_loss:2.75908 +2025-04-19 07:37:29,858 INFO Epoch:22 val_res:0.599870 +2025-04-19 07:37:29,865 INFO Saving best model at Epoch 22 +2025-04-19 07:38:07,030 INFO Epoch:23 train_loss:2.41968 +2025-04-19 07:38:14,992 INFO Epoch:23 val_res:0.603113 +2025-04-19 07:38:14,999 INFO Saving best model at Epoch 23 +2025-04-19 07:38:52,444 INFO Epoch:24 train_loss:2.28558 +2025-04-19 07:39:00,472 INFO Epoch:24 val_res:0.610895 +2025-04-19 07:39:00,479 INFO Saving best model at Epoch 24 +2025-04-19 07:39:37,884 INFO Epoch:25 train_loss:2.20693 +2025-04-19 07:39:46,798 INFO Epoch:25 val_res:0.610246 +2025-04-19 07:40:22,668 INFO Epoch:26 train_loss:2.16737 +2025-04-19 07:40:31,043 INFO Epoch:26 val_res:0.612840 +2025-04-19 07:40:31,050 INFO Saving best model at Epoch 26 +2025-04-19 07:41:09,277 INFO Epoch:27 train_loss:2.13129 +2025-04-19 07:41:17,896 INFO Epoch:27 val_res:0.621920 +2025-04-19 07:41:17,900 INFO Saving best model at Epoch 27 +2025-04-19 07:41:56,170 INFO Epoch:28 train_loss:2.07732 +2025-04-19 07:42:03,956 INFO Epoch:28 val_res:0.618677 +2025-04-19 07:42:38,920 INFO Epoch:29 train_loss:2.06789 +2025-04-19 07:42:47,621 INFO Epoch:29 val_res:0.621271 +2025-04-19 07:43:22,825 INFO Epoch:30 train_loss:2.02888 +2025-04-19 07:43:31,996 INFO Epoch:30 val_res:0.627756 +2025-04-19 07:43:32,002 INFO Saving best model at Epoch 30 +2025-04-19 07:44:07,921 INFO Epoch:31 train_loss:2.02035 +2025-04-19 07:44:15,920 INFO Epoch:31 val_res:0.627108 +2025-04-19 07:44:53,263 INFO Epoch:32 train_loss:1.97636 +2025-04-19 07:45:01,553 INFO Epoch:32 val_res:0.626459 +2025-04-19 07:45:36,933 INFO Epoch:33 train_loss:1.97299 +2025-04-19 07:45:45,318 INFO Epoch:33 val_res:0.626459 +2025-04-19 07:46:20,632 INFO Epoch:34 train_loss:1.94714 +2025-04-19 07:46:29,043 INFO Epoch:34 val_res:0.640078 +2025-04-19 07:46:29,049 INFO Saving best model at Epoch 34 +2025-04-19 07:47:06,966 INFO Epoch:35 train_loss:1.92043 +2025-04-19 07:47:14,609 INFO Epoch:35 val_res:0.632296 +2025-04-19 07:47:50,462 INFO Epoch:36 train_loss:1.90260 +2025-04-19 07:47:58,112 INFO Epoch:36 val_res:0.643969 +2025-04-19 07:47:58,119 INFO Saving best model at Epoch 36 +2025-04-19 07:48:35,327 INFO Epoch:37 train_loss:1.87120 +2025-04-19 07:48:43,137 INFO Epoch:37 val_res:0.638132 +2025-04-19 07:49:17,871 INFO Epoch:38 train_loss:1.86277 +2025-04-19 07:49:25,648 INFO Epoch:38 val_res:0.643320 +2025-04-19 07:50:03,826 INFO Epoch:39 train_loss:1.83213 +2025-04-19 07:50:11,295 INFO Epoch:39 val_res:0.651102 +2025-04-19 07:50:11,301 INFO Saving best model at Epoch 39 +2025-04-19 07:50:49,661 INFO Epoch:40 train_loss:1.85402 +2025-04-19 07:50:57,014 INFO Epoch:40 val_res:0.649157 +2025-04-19 07:51:31,278 INFO Epoch:41 train_loss:1.83967 +2025-04-19 07:51:39,066 INFO Epoch:41 val_res:0.651102 +2025-04-19 07:52:14,109 INFO Epoch:42 train_loss:1.81770 +2025-04-19 07:52:21,480 INFO Epoch:42 val_res:0.656291 +2025-04-19 07:52:21,487 INFO Saving best model at Epoch 42 +2025-04-19 07:52:59,426 INFO Epoch:43 train_loss:1.80493 +2025-04-19 07:53:06,813 INFO Epoch:43 val_res:0.651751 +2025-04-19 07:53:40,194 INFO Epoch:44 train_loss:1.79796 +2025-04-19 07:53:47,467 INFO Epoch:44 val_res:0.656939 +2025-04-19 07:53:47,467 INFO Saving best model at Epoch 44 +2025-04-19 07:54:22,030 INFO Epoch:45 train_loss:1.80102 +2025-04-19 07:54:29,475 INFO Epoch:45 val_res:0.658885 +2025-04-19 07:54:29,476 INFO Saving best model at Epoch 45 +2025-04-19 07:55:05,836 INFO Epoch:46 train_loss:1.78118 +2025-04-19 07:55:12,933 INFO Epoch:46 val_res:0.654345 +2025-04-19 07:55:47,936 INFO Epoch:47 train_loss:1.79328 +2025-04-19 07:55:54,731 INFO Epoch:47 val_res:0.662776 +2025-04-19 07:55:54,732 INFO Saving best model at Epoch 47 +2025-04-19 07:56:29,482 INFO Epoch:48 train_loss:1.77176 +2025-04-19 07:56:36,841 INFO Epoch:48 val_res:0.659533 +2025-04-19 07:57:10,636 INFO Epoch:49 train_loss:1.76353 +2025-04-19 07:57:17,837 INFO Epoch:49 val_res:0.664073 +2025-04-19 07:57:17,838 INFO Saving best model at Epoch 49 +2025-04-19 07:57:54,944 INFO Epoch:50 train_loss:1.74710 +2025-04-19 07:58:02,353 INFO Epoch:50 val_res:0.656291 +2025-04-19 07:58:36,574 INFO Epoch:51 train_loss:1.72243 +2025-04-19 07:58:44,207 INFO Epoch:51 val_res:0.655642 +2025-04-19 07:59:19,089 INFO Epoch:52 train_loss:1.70436 +2025-04-19 07:59:27,267 INFO Epoch:52 val_res:0.665370 +2025-04-19 07:59:27,273 INFO Saving best model at Epoch 52 +2025-04-19 08:00:04,033 INFO Epoch:53 train_loss:1.69078 +2025-04-19 08:00:11,997 INFO Epoch:53 val_res:0.657588 +2025-04-19 08:00:45,888 INFO Epoch:54 train_loss:1.68979 +2025-04-19 08:00:53,242 INFO Epoch:54 val_res:0.658236 +2025-04-19 08:01:26,242 INFO Epoch:55 train_loss:1.73138 +2025-04-19 08:01:33,773 INFO Epoch:55 val_res:0.662127 +2025-04-19 08:02:07,955 INFO Epoch:56 train_loss:1.68790 +2025-04-19 08:02:15,861 INFO Epoch:56 val_res:0.669909 +2025-04-19 08:02:15,861 INFO Saving best model at Epoch 56 +2025-04-19 08:02:53,761 INFO Epoch:57 train_loss:1.70281 +2025-04-19 08:03:01,155 INFO Epoch:57 val_res:0.656939 +2025-04-19 08:03:34,657 INFO Epoch:58 train_loss:1.68490 +2025-04-19 08:03:43,648 INFO Epoch:58 val_res:0.655642 +2025-04-19 08:04:17,604 INFO Epoch:59 train_loss:1.66156 +2025-04-19 08:04:24,879 INFO Epoch:59 val_res:0.658885 +2025-04-19 08:05:00,156 INFO Epoch:60 train_loss:1.62694 +2025-04-19 08:05:07,523 INFO Epoch:60 val_res:0.658236 +2025-04-19 08:05:40,510 INFO Epoch:61 train_loss:1.61900 +2025-04-19 08:05:47,946 INFO Epoch:61 val_res:0.663424 +2025-04-19 08:06:22,766 INFO Epoch:62 train_loss:1.63715 +2025-04-19 08:06:29,965 INFO Epoch:62 val_res:0.658885 +2025-04-19 08:07:06,074 INFO Epoch:63 train_loss:1.65603 +2025-04-19 08:07:13,102 INFO Epoch:63 val_res:0.657588 +2025-04-19 08:07:48,898 INFO Epoch:64 train_loss:1.63689 +2025-04-19 08:07:56,082 INFO Epoch:64 val_res:0.668612 +2025-04-19 08:08:34,695 INFO Epoch:65 train_loss:1.61724 +2025-04-19 08:08:44,426 INFO Epoch:65 val_res:0.660182 +2025-04-19 08:09:24,263 INFO Epoch:66 train_loss:1.59044 +2025-04-19 08:09:33,293 INFO Epoch:66 val_res:0.661479 +2025-04-19 08:10:15,060 INFO Epoch:67 train_loss:1.59852 +2025-04-19 08:10:24,816 INFO Epoch:67 val_res:0.654345 +2025-04-19 08:11:03,653 INFO Epoch:68 train_loss:1.61202 +2025-04-19 08:11:10,509 INFO Epoch:68 val_res:0.664721 +2025-04-19 08:11:49,210 INFO Epoch:69 train_loss:1.62670 +2025-04-19 08:11:58,145 INFO Epoch:69 val_res:0.656939 +2025-04-19 08:12:37,226 INFO Epoch:70 train_loss:1.61526 +2025-04-19 08:12:46,094 INFO Epoch:70 val_res:0.653048 +2025-04-19 08:13:21,566 INFO Epoch:71 train_loss:0.81452 +2025-04-19 08:13:29,556 INFO Epoch:71 val_res:0.662776 +2025-04-19 08:15:35,786 INFO Epoch:72 train_loss:0.77859 +2025-04-19 08:15:43,636 INFO Epoch:72 val_res:0.664721 +2025-04-19 08:16:20,151 INFO Epoch:73 train_loss:0.76344 +2025-04-19 08:16:29,268 INFO Epoch:73 val_res:0.658236 +2025-04-19 08:17:08,811 INFO Epoch:74 train_loss:0.76381 +2025-04-19 08:17:17,702 INFO Epoch:74 val_res:0.666018 +2025-04-19 08:17:53,615 INFO Epoch:75 train_loss:0.75901 +2025-04-19 08:18:01,469 INFO Epoch:75 val_res:0.662127 +2025-04-19 08:18:36,523 INFO Epoch:76 train_loss:0.76052 +2025-04-19 08:18:45,115 INFO Epoch:76 val_res:0.662127 +2025-04-19 08:19:21,003 INFO Epoch:77 train_loss:0.75486 +2025-04-19 08:19:28,485 INFO Epoch:77 val_res:0.663424 +2025-04-19 08:20:04,207 INFO Epoch:78 train_loss:0.76118 +2025-04-19 08:20:12,501 INFO Epoch:78 val_res:0.658236 +2025-04-19 08:20:53,765 INFO Epoch:79 train_loss:0.75767 +2025-04-19 08:21:03,312 INFO Epoch:79 val_res:0.662127 +2025-04-19 08:21:43,656 INFO Epoch:80 train_loss:0.75691 +2025-04-19 08:21:53,088 INFO Epoch:80 val_res:0.664073 +2025-04-19 08:22:36,264 INFO Epoch:81 train_loss:0.75451 +2025-04-19 08:22:44,672 INFO Epoch:81 val_res:0.658236 +2025-04-19 08:23:26,382 INFO Epoch:82 train_loss:0.75543 +2025-04-19 08:23:35,623 INFO Epoch:82 val_res:0.662127 +2025-04-19 08:24:15,471 INFO Epoch:83 train_loss:0.75138 +2025-04-19 08:24:25,494 INFO Epoch:83 val_res:0.662776 +2025-04-19 08:25:09,329 INFO Epoch:84 train_loss:0.75237 +2025-04-19 08:25:20,404 INFO Epoch:84 val_res:0.663424 +2025-04-19 08:26:11,987 INFO Epoch:85 train_loss:0.75036 +2025-04-19 08:26:21,911 INFO Epoch:85 val_res:0.656939 +2025-04-19 08:27:08,630 INFO Epoch:86 train_loss:0.74859 +2025-04-19 08:27:19,424 INFO Epoch:86 val_res:0.661479 +2025-04-19 08:28:05,345 INFO Epoch:87 train_loss:0.75150 +2025-04-19 08:28:14,147 INFO Epoch:87 val_res:0.658885 +2025-04-19 08:28:58,521 INFO Epoch:88 train_loss:0.74965 +2025-04-19 08:29:20,292 INFO Epoch:88 val_res:0.657588 +2025-04-19 08:30:07,738 INFO Epoch:89 train_loss:0.74820 +2025-04-19 08:30:17,867 INFO Epoch:89 val_res:0.662127 +2025-04-19 08:31:04,851 INFO Epoch:90 train_loss:0.75156 +2025-04-19 08:31:13,632 INFO Epoch:90 val_res:0.664721 +2025-04-19 08:31:57,875 INFO Epoch:91 train_loss:0.75501 +2025-04-19 08:32:07,395 INFO Epoch:91 val_res:0.662127 +2025-04-19 08:32:53,840 INFO Epoch:92 train_loss:0.74557 +2025-04-19 08:33:03,002 INFO Epoch:92 val_res:0.666667 +2025-04-19 08:33:51,089 INFO Epoch:93 train_loss:0.74698 +2025-04-19 08:34:00,105 INFO Epoch:93 val_res:0.662127 +2025-04-19 08:34:47,645 INFO Epoch:94 train_loss:0.75067 +2025-04-19 08:34:56,666 INFO Epoch:94 val_res:0.656939 +2025-04-19 08:35:42,706 INFO Epoch:95 train_loss:0.74543 +2025-04-19 08:35:51,613 INFO Epoch:95 val_res:0.660182 +2025-04-19 08:36:36,510 INFO Epoch:96 train_loss:0.76544 +2025-04-19 08:36:45,895 INFO Epoch:96 val_res:0.659533 +2025-04-19 08:37:29,337 INFO Epoch:97 train_loss:0.75510 +2025-04-19 08:37:37,709 INFO Epoch:97 val_res:0.660182 +2025-04-19 08:38:21,951 INFO Epoch:98 train_loss:0.74825 +2025-04-19 08:38:30,492 INFO Epoch:98 val_res:0.664721 +2025-04-19 08:39:15,191 INFO Epoch:99 train_loss:0.74475 +2025-04-19 08:39:24,471 INFO Epoch:99 val_res:0.657588 +2025-04-19 08:39:25,291 INFO ===================================== +2025-04-19 08:39:25,294 INFO Start testing... +2025-04-19 08:39:25,294 INFO ===================================== +2025-04-19 08:39:37,691 INFO Incremental step 3 Testing res: 0.649838 +2025-04-19 08:39:37,698 INFO forgetting: 0.086905 +2025-04-19 08:39:37,704 INFO Incremental step: 4 +2025-04-19 08:40:48,336 INFO Epoch:0 train_loss:6.90832 +2025-04-19 08:41:20,591 INFO Epoch:0 val_res:0.489471 +2025-04-19 08:41:20,591 INFO Saving best model at Epoch 0 +2025-04-19 08:42:06,134 INFO Epoch:1 train_loss:2.71063 +2025-04-19 08:42:15,721 INFO Epoch:1 val_res:0.524396 +2025-04-19 08:42:15,732 INFO Saving best model at Epoch 1 +2025-04-19 08:42:57,304 INFO Epoch:2 train_loss:1.78331 +2025-04-19 08:43:05,988 INFO Epoch:2 val_res:0.529019 +2025-04-19 08:43:05,992 INFO Saving best model at Epoch 2 +2025-04-19 08:43:48,915 INFO Epoch:3 train_loss:1.51483 +2025-04-19 08:44:00,531 INFO Epoch:3 val_res:0.531073 +2025-04-19 08:44:00,532 INFO Saving best model at Epoch 3 +2025-04-19 08:44:50,255 INFO Epoch:4 train_loss:1.41660 +2025-04-19 08:45:01,202 INFO Epoch:4 val_res:0.534669 +2025-04-19 08:45:01,208 INFO Saving best model at Epoch 4 +2025-04-19 08:45:48,736 INFO Epoch:5 train_loss:1.37629 +2025-04-19 08:46:00,263 INFO Epoch:5 val_res:0.536210 +2025-04-19 08:46:00,278 INFO Saving best model at Epoch 5 +2025-04-19 08:46:50,472 INFO Epoch:6 train_loss:1.34233 +2025-04-19 08:47:02,255 INFO Epoch:6 val_res:0.533128 +2025-04-19 08:47:46,082 INFO Epoch:7 train_loss:1.30140 +2025-04-19 08:47:59,018 INFO Epoch:7 val_res:0.534155 +2025-04-19 08:48:41,742 INFO Epoch:8 train_loss:1.29260 +2025-04-19 08:48:53,691 INFO Epoch:8 val_res:0.538264 +2025-04-19 08:48:53,695 INFO Saving best model at Epoch 8 +2025-04-19 08:49:37,221 INFO Epoch:9 train_loss:1.26931 +2025-04-19 08:49:48,536 INFO Epoch:9 val_res:0.537750 +2025-04-19 08:50:32,015 INFO Epoch:10 train_loss:1.25219 +2025-04-19 08:50:43,416 INFO Epoch:10 val_res:0.537237 +2025-04-19 08:51:23,085 INFO Epoch:11 train_loss:1.22975 +2025-04-19 08:51:32,492 INFO Epoch:11 val_res:0.538778 +2025-04-19 08:51:32,493 INFO Saving best model at Epoch 11 +2025-04-19 08:52:12,445 INFO Epoch:12 train_loss:1.21159 +2025-04-19 08:52:22,370 INFO Epoch:12 val_res:0.537237 +2025-04-19 08:53:00,986 INFO Epoch:13 train_loss:1.20476 +2025-04-19 08:53:10,446 INFO Epoch:13 val_res:0.540318 +2025-04-19 08:53:10,448 INFO Saving best model at Epoch 13 +2025-04-19 08:53:57,162 INFO Epoch:14 train_loss:1.19153 +2025-04-19 08:54:09,394 INFO Epoch:14 val_res:0.537237 +2025-04-19 08:54:55,105 INFO Epoch:15 train_loss:1.17892 +2025-04-19 08:55:06,049 INFO Epoch:15 val_res:0.540832 +2025-04-19 08:55:06,055 INFO Saving best model at Epoch 15 +2025-04-19 08:55:50,785 INFO Epoch:16 train_loss:1.16389 +2025-04-19 08:56:02,048 INFO Epoch:16 val_res:0.536723 +2025-04-19 08:56:45,176 INFO Epoch:17 train_loss:1.14962 +2025-04-19 08:56:56,952 INFO Epoch:17 val_res:0.540832 +2025-04-19 08:57:40,151 INFO Epoch:18 train_loss:1.14002 +2025-04-19 08:57:52,214 INFO Epoch:18 val_res:0.540832 +2025-04-19 08:58:37,582 INFO Epoch:19 train_loss:1.12966 +2025-04-19 08:58:50,061 INFO Epoch:19 val_res:0.543400 +2025-04-19 08:58:50,068 INFO Saving best model at Epoch 19 +2025-04-19 08:59:37,325 INFO Epoch:20 train_loss:4.11210 +2025-04-19 08:59:49,586 INFO Epoch:20 val_res:0.536210 +2025-04-19 09:00:36,632 INFO Epoch:21 train_loss:3.93948 +2025-04-19 09:00:49,191 INFO Epoch:21 val_res:0.527478 +2025-04-19 09:01:36,433 INFO Epoch:22 train_loss:3.18336 +2025-04-19 09:01:47,710 INFO Epoch:22 val_res:0.529019 +2025-04-19 09:02:33,576 INFO Epoch:23 train_loss:2.78892 +2025-04-19 09:02:46,178 INFO Epoch:23 val_res:0.545455 +2025-04-19 09:02:46,186 INFO Saving best model at Epoch 23 +2025-04-19 09:03:33,046 INFO Epoch:24 train_loss:2.65357 +2025-04-19 09:03:44,852 INFO Epoch:24 val_res:0.540832 +2025-04-19 09:04:31,050 INFO Epoch:25 train_loss:2.55714 +2025-04-19 09:04:43,300 INFO Epoch:25 val_res:0.545968 +2025-04-19 09:04:43,307 INFO Saving best model at Epoch 25 +2025-04-19 09:05:31,968 INFO Epoch:26 train_loss:2.46899 +2025-04-19 09:05:43,147 INFO Epoch:26 val_res:0.548536 +2025-04-19 09:05:43,148 INFO Saving best model at Epoch 26 +2025-04-19 09:06:29,803 INFO Epoch:27 train_loss:2.42749 +2025-04-19 09:06:41,421 INFO Epoch:27 val_res:0.546995 +2025-04-19 09:07:27,522 INFO Epoch:28 train_loss:2.41337 +2025-04-19 09:07:39,060 INFO Epoch:28 val_res:0.557268 +2025-04-19 09:07:39,068 INFO Saving best model at Epoch 28 +2025-04-19 09:08:27,905 INFO Epoch:29 train_loss:2.36391 +2025-04-19 09:08:38,724 INFO Epoch:29 val_res:0.551104 +2025-04-19 09:09:28,243 INFO Epoch:30 train_loss:2.31630 +2025-04-19 09:09:40,327 INFO Epoch:30 val_res:0.555213 +2025-04-19 09:10:33,758 INFO Epoch:31 train_loss:2.28327 +2025-04-19 09:10:44,710 INFO Epoch:31 val_res:0.559322 +2025-04-19 09:10:44,713 INFO Saving best model at Epoch 31 +2025-04-19 09:11:38,571 INFO Epoch:32 train_loss:2.25393 +2025-04-19 09:11:49,542 INFO Epoch:32 val_res:0.559836 +2025-04-19 09:11:49,557 INFO Saving best model at Epoch 32 +2025-04-19 09:12:40,288 INFO Epoch:33 train_loss:2.24282 +2025-04-19 09:12:52,089 INFO Epoch:33 val_res:0.569081 +2025-04-19 09:12:52,098 INFO Saving best model at Epoch 33 +2025-04-19 09:13:45,910 INFO Epoch:34 train_loss:2.19569 +2025-04-19 09:13:56,396 INFO Epoch:34 val_res:0.566513 +2025-04-19 09:14:44,490 INFO Epoch:35 train_loss:2.14541 +2025-04-19 09:14:55,228 INFO Epoch:35 val_res:0.575244 +2025-04-19 09:14:55,231 INFO Saving best model at Epoch 35 +2025-04-19 09:15:46,871 INFO Epoch:36 train_loss:2.14551 +2025-04-19 09:15:58,549 INFO Epoch:36 val_res:0.573189 +2025-04-19 09:16:45,197 INFO Epoch:37 train_loss:2.18361 +2025-04-19 09:16:57,435 INFO Epoch:37 val_res:0.576271 +2025-04-19 09:16:57,440 INFO Saving best model at Epoch 37 +2025-04-19 09:17:53,083 INFO Epoch:38 train_loss:2.15987 +2025-04-19 09:18:05,948 INFO Epoch:38 val_res:0.574217 +2025-04-19 09:18:57,749 INFO Epoch:39 train_loss:2.08014 +2025-04-19 09:19:10,002 INFO Epoch:39 val_res:0.582435 +2025-04-19 09:19:10,003 INFO Saving best model at Epoch 39 +2025-04-19 09:20:01,980 INFO Epoch:40 train_loss:2.05960 +2025-04-19 09:20:13,327 INFO Epoch:40 val_res:0.575244 +2025-04-19 09:21:03,762 INFO Epoch:41 train_loss:2.03094 +2025-04-19 09:21:16,704 INFO Epoch:41 val_res:0.579866 +2025-04-19 09:22:10,229 INFO Epoch:42 train_loss:2.02661 +2025-04-19 09:22:21,482 INFO Epoch:42 val_res:0.576271 +2025-04-19 09:23:11,505 INFO Epoch:43 train_loss:2.02448 +2025-04-19 09:23:24,307 INFO Epoch:43 val_res:0.586543 +2025-04-19 09:23:24,308 INFO Saving best model at Epoch 43 +2025-04-19 09:24:19,961 INFO Epoch:44 train_loss:1.95807 +2025-04-19 09:24:31,739 INFO Epoch:44 val_res:0.588598 +2025-04-19 09:24:31,749 INFO Saving best model at Epoch 44 +2025-04-19 09:25:25,285 INFO Epoch:45 train_loss:1.92383 +2025-04-19 09:25:36,384 INFO Epoch:45 val_res:0.591166 +2025-04-19 09:25:36,385 INFO Saving best model at Epoch 45 +2025-04-19 09:26:23,712 INFO Epoch:46 train_loss:1.92435 +2025-04-19 09:26:34,897 INFO Epoch:46 val_res:0.597843 +2025-04-19 09:26:34,904 INFO Saving best model at Epoch 46 +2025-04-19 09:27:29,886 INFO Epoch:47 train_loss:1.88635 +2025-04-19 09:27:40,815 INFO Epoch:47 val_res:0.588598 +2025-04-19 09:28:32,295 INFO Epoch:48 train_loss:1.89231 +2025-04-19 09:28:44,191 INFO Epoch:48 val_res:0.587571 +2025-04-19 09:29:35,464 INFO Epoch:49 train_loss:1.88827 +2025-04-19 09:29:48,075 INFO Epoch:49 val_res:0.597329 +2025-04-19 09:30:39,880 INFO Epoch:50 train_loss:1.88105 +2025-04-19 09:30:51,664 INFO Epoch:50 val_res:0.599384 +2025-04-19 09:30:51,665 INFO Saving best model at Epoch 50 +2025-04-19 09:31:46,150 INFO Epoch:51 train_loss:1.87032 +2025-04-19 09:31:58,086 INFO Epoch:51 val_res:0.591680 +2025-04-19 09:32:48,138 INFO Epoch:52 train_loss:1.87037 +2025-04-19 09:32:59,915 INFO Epoch:52 val_res:0.603493 +2025-04-19 09:32:59,919 INFO Saving best model at Epoch 52 +2025-04-19 09:33:54,387 INFO Epoch:53 train_loss:1.79415 +2025-04-19 09:34:06,239 INFO Epoch:53 val_res:0.606061 +2025-04-19 09:34:06,251 INFO Saving best model at Epoch 53 +2025-04-19 09:34:58,095 INFO Epoch:54 train_loss:1.80266 +2025-04-19 09:35:09,816 INFO Epoch:54 val_res:0.604006 +2025-04-19 09:35:58,416 INFO Epoch:55 train_loss:1.76824 +2025-04-19 09:36:09,086 INFO Epoch:55 val_res:0.605033 +2025-04-19 09:37:00,050 INFO Epoch:56 train_loss:1.78710 +2025-04-19 09:37:11,629 INFO Epoch:56 val_res:0.610683 +2025-04-19 09:37:11,632 INFO Saving best model at Epoch 56 +2025-04-19 09:38:02,916 INFO Epoch:57 train_loss:1.73037 +2025-04-19 09:38:14,200 INFO Epoch:57 val_res:0.607088 +2025-04-19 09:39:00,566 INFO Epoch:58 train_loss:1.73843 +2025-04-19 09:39:11,903 INFO Epoch:58 val_res:0.607601 +2025-04-19 09:39:58,994 INFO Epoch:59 train_loss:1.75201 +2025-04-19 09:40:09,772 INFO Epoch:59 val_res:0.612738 +2025-04-19 09:40:09,776 INFO Saving best model at Epoch 59 +2025-04-19 09:41:05,825 INFO Epoch:60 train_loss:1.77649 +2025-04-19 09:41:18,246 INFO Epoch:60 val_res:0.613251 +2025-04-19 09:41:18,253 INFO Saving best model at Epoch 60 +2025-04-19 09:42:12,843 INFO Epoch:61 train_loss:1.76619 +2025-04-19 09:42:24,972 INFO Epoch:61 val_res:0.615306 +2025-04-19 09:42:24,973 INFO Saving best model at Epoch 61 +2025-04-19 09:43:19,197 INFO Epoch:62 train_loss:1.69841 +2025-04-19 09:43:30,599 INFO Epoch:62 val_res:0.614792 +2025-04-19 09:44:20,693 INFO Epoch:63 train_loss:1.70643 +2025-04-19 09:44:32,864 INFO Epoch:63 val_res:0.611710 +2025-04-19 09:45:25,555 INFO Epoch:64 train_loss:1.67872 +2025-04-19 09:45:37,545 INFO Epoch:64 val_res:0.617874 +2025-04-19 09:45:37,568 INFO Saving best model at Epoch 64 +2025-04-19 09:46:24,252 INFO Epoch:65 train_loss:1.67951 +2025-04-19 09:46:35,621 INFO Epoch:65 val_res:0.610169 +2025-04-19 09:47:29,736 INFO Epoch:66 train_loss:1.73453 +2025-04-19 09:47:42,631 INFO Epoch:66 val_res:0.618387 +2025-04-19 09:47:42,636 INFO Saving best model at Epoch 66 +2025-04-19 09:48:33,597 INFO Epoch:67 train_loss:1.68441 +2025-04-19 09:48:45,616 INFO Epoch:67 val_res:0.616333 +2025-04-19 09:49:35,222 INFO Epoch:68 train_loss:1.68071 +2025-04-19 09:49:47,691 INFO Epoch:68 val_res:0.617360 +2025-04-19 09:50:37,868 INFO Epoch:69 train_loss:1.70329 +2025-04-19 09:50:49,883 INFO Epoch:69 val_res:0.621469 +2025-04-19 09:50:49,889 INFO Saving best model at Epoch 69 +2025-04-19 09:51:38,334 INFO Epoch:70 train_loss:1.69944 +2025-04-19 09:51:48,999 INFO Epoch:70 val_res:0.615819 +2025-04-19 09:52:31,730 INFO Epoch:71 train_loss:0.83457 +2025-04-19 09:52:41,038 INFO Epoch:71 val_res:0.615819 +2025-04-19 09:53:25,793 INFO Epoch:72 train_loss:0.80611 +2025-04-19 09:53:38,067 INFO Epoch:72 val_res:0.616846 +2025-04-19 09:54:26,469 INFO Epoch:73 train_loss:0.78915 +2025-04-19 09:54:38,923 INFO Epoch:73 val_res:0.619415 +2025-04-19 09:55:24,298 INFO Epoch:74 train_loss:0.78372 +2025-04-19 09:55:35,386 INFO Epoch:74 val_res:0.613765 +2025-04-19 09:56:21,650 INFO Epoch:75 train_loss:0.78008 +2025-04-19 09:56:32,540 INFO Epoch:75 val_res:0.616846 +2025-04-19 09:57:16,547 INFO Epoch:76 train_loss:0.77857 +2025-04-19 09:57:27,990 INFO Epoch:76 val_res:0.619415 +2025-04-19 09:58:12,555 INFO Epoch:77 train_loss:0.78089 +2025-04-19 09:58:23,862 INFO Epoch:77 val_res:0.619415 +2025-04-19 09:59:06,971 INFO Epoch:78 train_loss:0.77505 +2025-04-19 09:59:18,499 INFO Epoch:78 val_res:0.618901 +2025-04-19 10:00:01,497 INFO Epoch:79 train_loss:0.77553 +2025-04-19 10:00:11,429 INFO Epoch:79 val_res:0.621983 +2025-04-19 10:00:11,433 INFO Saving best model at Epoch 79 +2025-04-19 10:00:55,598 INFO Epoch:80 train_loss:0.77249 +2025-04-19 10:01:04,976 INFO Epoch:80 val_res:0.618387 +2025-04-19 10:01:47,826 INFO Epoch:81 train_loss:0.77032 +2025-04-19 10:01:59,074 INFO Epoch:81 val_res:0.618387 +2025-04-19 10:02:44,019 INFO Epoch:82 train_loss:0.77173 +2025-04-19 10:02:55,333 INFO Epoch:82 val_res:0.618901 +2025-04-19 10:03:37,969 INFO Epoch:83 train_loss:0.77444 +2025-04-19 10:03:48,478 INFO Epoch:83 val_res:0.614792 +2025-04-19 10:04:30,496 INFO Epoch:84 train_loss:0.76775 +2025-04-19 10:04:41,160 INFO Epoch:84 val_res:0.615306 +2025-04-19 10:05:24,731 INFO Epoch:85 train_loss:0.76814 +2025-04-19 10:05:35,184 INFO Epoch:85 val_res:0.620442 +2025-04-19 10:06:18,230 INFO Epoch:86 train_loss:0.76685 +2025-04-19 10:06:28,413 INFO Epoch:86 val_res:0.621983 +2025-04-19 10:07:07,405 INFO Epoch:87 train_loss:0.77180 +2025-04-19 10:07:16,634 INFO Epoch:87 val_res:0.614278 +2025-04-19 10:07:54,410 INFO Epoch:88 train_loss:0.76834 +2025-04-19 10:08:03,430 INFO Epoch:88 val_res:0.624037 +2025-04-19 10:08:03,436 INFO Saving best model at Epoch 88 +2025-04-19 10:08:44,899 INFO Epoch:89 train_loss:0.76507 +2025-04-19 10:08:54,088 INFO Epoch:89 val_res:0.623523 +2025-04-19 10:09:32,403 INFO Epoch:90 train_loss:0.76997 +2025-04-19 10:09:41,586 INFO Epoch:90 val_res:0.616846 +2025-04-19 10:10:24,116 INFO Epoch:91 train_loss:0.76066 +2025-04-19 10:10:36,916 INFO Epoch:91 val_res:0.624551 +2025-04-19 10:10:36,920 INFO Saving best model at Epoch 91 +2025-04-19 10:11:22,920 INFO Epoch:92 train_loss:0.86457 +2025-04-19 10:11:33,819 INFO Epoch:92 val_res:0.615306 +2025-04-19 10:12:18,508 INFO Epoch:93 train_loss:0.81893 +2025-04-19 10:12:29,216 INFO Epoch:93 val_res:0.620442 +2025-04-19 10:13:11,256 INFO Epoch:94 train_loss:0.81135 +2025-04-19 10:13:23,491 INFO Epoch:94 val_res:0.621983 +2025-04-19 10:14:10,608 INFO Epoch:95 train_loss:0.78368 +2025-04-19 10:14:21,296 INFO Epoch:95 val_res:0.612738 +2025-04-19 10:15:05,307 INFO Epoch:96 train_loss:0.77570 +2025-04-19 10:15:15,510 INFO Epoch:96 val_res:0.619928 +2025-04-19 10:15:56,445 INFO Epoch:97 train_loss:0.78026 +2025-04-19 10:16:06,952 INFO Epoch:97 val_res:0.617874 +2025-04-19 10:16:49,340 INFO Epoch:98 train_loss:0.77355 +2025-04-19 10:16:58,382 INFO Epoch:98 val_res:0.623010 +2025-04-19 10:17:46,542 INFO Epoch:99 train_loss:0.77448 +2025-04-19 10:17:59,396 INFO Epoch:99 val_res:0.619928 +2025-04-19 10:18:00,026 INFO ===================================== +2025-04-19 10:18:00,027 INFO Start testing... +2025-04-19 10:18:00,028 INFO ===================================== +2025-04-19 10:18:12,279 INFO Incremental step 4 Testing res: 0.612870 +2025-04-19 10:18:12,291 INFO forgetting: 0.099394 +2025-04-19 10:18:12,296 INFO Average Accuracy: 0.722990 +2025-04-19 10:18:12,300 INFO Average Forgetting: 0.106453 diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..c8c5f586074ac51c745df3db9eec81c7a37c2891 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..20a2e91e5f33be593ec862abd3238bb77cdbe9b0 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..c5fb1cb545346c8d8c114f230ffc6d298428f78d Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..8c800b8a2e60486974527c5d4f109bd5adec20b5 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..13217bf07674f1a4f56404c2ba9cb5e9e4362343 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..cbe4662faeb2433cd979c0c3b8f1964b6ca5ffb1 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..6777e672a2d4ca833a073134df2bf7a09e347c5c Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..865737d89c1c4a6ceafb2305d9df16d4361a5d7a Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8f262767919fbcce41bba774d981fb366d569983 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a1acc94763b61bae2ccc426f0a8676682e5394e1f2341fa277780f477dce16 +size 114115089 diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..2f8b565611a34c8480729d26cca6071993eaf04e --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0b025d10cebb08e309add8919d8821b0347984ab6e9da39e8207b521a864b2 +size 114179665 diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..22a3da579b82e2bb1dd05d5a4715f0714b2a1e53 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da62ec8c48c1204d91ef1a62740e3e7d14fa1c11c684fd19ac4912772730f3a9 +size 114244369 diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..79aeccc8e8e71feac7a545e9cd7bc6d05a507acf --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0e33a0fef3ab91d968ee3716f2a11c0f754eb69e3fc87f243fa594d2c3af45f +size 114308881 diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/train.log b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..cc80cb18e275eb1eb67aa967e8ac30f6527dcfb0 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_False-seed_0/train.log @@ -0,0 +1,890 @@ +2025-04-18 01:59:24,083 INFO Namespace(class_num_per_step=7, dataset='AVE', e_prompt=False, infer_batch_size=128, inverse=False, inverse_ends=100, inverse_starts=0, lr=0.01, lr_decay=False, max_epoches=100, milestones=[100], modality='audio-visual', num_classes=28, num_workers=1, prompt_dim=768, seed=0, train_batch_size=256, transfer=False, warm=False, weight_decay=0.0001) +2025-04-18 01:59:24,084 INFO Training start time: 2025-04-18 01:59:24.084921 +2025-04-18 02:05:47,007 INFO Incremental step: 0 +2025-04-18 02:06:18,490 INFO Epoch:0 train_loss:1.94366 +2025-04-18 02:07:31,532 INFO Epoch:0 val_res:0.323810 +2025-04-18 02:07:31,532 INFO Saving best model at Epoch 0 +2025-04-18 02:07:39,768 INFO Epoch:1 train_loss:1.81413 +2025-04-18 02:07:40,877 INFO Epoch:1 val_res:0.342857 +2025-04-18 02:07:40,878 INFO Saving best model at Epoch 1 +2025-04-18 02:07:48,746 INFO Epoch:2 train_loss:1.65088 +2025-04-18 02:07:49,608 INFO Epoch:2 val_res:0.466667 +2025-04-18 02:07:49,608 INFO Saving best model at Epoch 2 +2025-04-18 02:07:56,686 INFO Epoch:3 train_loss:1.51719 +2025-04-18 02:07:57,628 INFO Epoch:3 val_res:0.485714 +2025-04-18 02:07:57,628 INFO Saving best model at Epoch 3 +2025-04-18 02:08:04,737 INFO Epoch:4 train_loss:1.36562 +2025-04-18 02:08:05,773 INFO Epoch:4 val_res:0.485714 +2025-04-18 02:08:10,936 INFO Epoch:5 train_loss:1.27456 +2025-04-18 02:08:11,921 INFO Epoch:5 val_res:0.590476 +2025-04-18 02:08:11,922 INFO Saving best model at Epoch 5 +2025-04-18 02:08:19,204 INFO Epoch:6 train_loss:1.18017 +2025-04-18 02:08:20,187 INFO Epoch:6 val_res:0.609524 +2025-04-18 02:08:20,187 INFO Saving best model at Epoch 6 +2025-04-18 02:08:27,289 INFO Epoch:7 train_loss:1.11857 +2025-04-18 02:08:28,266 INFO Epoch:7 val_res:0.561905 +2025-04-18 02:08:33,048 INFO Epoch:8 train_loss:1.05565 +2025-04-18 02:08:34,049 INFO Epoch:8 val_res:0.628571 +2025-04-18 02:08:34,050 INFO Saving best model at Epoch 8 +2025-04-18 02:08:41,327 INFO Epoch:9 train_loss:1.01613 +2025-04-18 02:08:42,388 INFO Epoch:9 val_res:0.609524 +2025-04-18 02:08:48,073 INFO Epoch:10 train_loss:0.94676 +2025-04-18 02:08:49,122 INFO Epoch:10 val_res:0.628571 +2025-04-18 02:08:54,091 INFO Epoch:11 train_loss:0.91281 +2025-04-18 02:08:55,056 INFO Epoch:11 val_res:0.609524 +2025-04-18 02:09:00,023 INFO Epoch:12 train_loss:0.87752 +2025-04-18 02:09:00,895 INFO Epoch:12 val_res:0.676190 +2025-04-18 02:09:00,896 INFO Saving best model at Epoch 12 +2025-04-18 02:09:08,896 INFO Epoch:13 train_loss:0.86002 +2025-04-18 02:09:09,822 INFO Epoch:13 val_res:0.647619 +2025-04-18 02:09:15,231 INFO Epoch:14 train_loss:0.83440 +2025-04-18 02:09:16,184 INFO Epoch:14 val_res:0.685714 +2025-04-18 02:09:16,185 INFO Saving best model at Epoch 14 +2025-04-18 02:09:23,262 INFO Epoch:15 train_loss:0.83222 +2025-04-18 02:09:24,144 INFO Epoch:15 val_res:0.695238 +2025-04-18 02:09:24,144 INFO Saving best model at Epoch 15 +2025-04-18 02:09:30,529 INFO Epoch:16 train_loss:0.78499 +2025-04-18 02:09:31,470 INFO Epoch:16 val_res:0.666667 +2025-04-18 02:09:36,808 INFO Epoch:17 train_loss:0.78663 +2025-04-18 02:09:37,923 INFO Epoch:17 val_res:0.714286 +2025-04-18 02:09:37,923 INFO Saving best model at Epoch 17 +2025-04-18 02:09:44,890 INFO Epoch:18 train_loss:0.76294 +2025-04-18 02:09:45,872 INFO Epoch:18 val_res:0.676190 +2025-04-18 02:09:51,269 INFO Epoch:19 train_loss:0.73460 +2025-04-18 02:09:52,119 INFO Epoch:19 val_res:0.695238 +2025-04-18 02:09:56,768 INFO Epoch:20 train_loss:0.70919 +2025-04-18 02:09:57,644 INFO Epoch:20 val_res:0.704762 +2025-04-18 02:10:02,737 INFO Epoch:21 train_loss:0.69607 +2025-04-18 02:10:03,705 INFO Epoch:21 val_res:0.733333 +2025-04-18 02:10:03,706 INFO Saving best model at Epoch 21 +2025-04-18 02:10:10,634 INFO Epoch:22 train_loss:0.71024 +2025-04-18 02:10:11,524 INFO Epoch:22 val_res:0.695238 +2025-04-18 02:10:17,184 INFO Epoch:23 train_loss:0.70429 +2025-04-18 02:10:18,177 INFO Epoch:23 val_res:0.676190 +2025-04-18 02:10:23,357 INFO Epoch:24 train_loss:0.69884 +2025-04-18 02:10:24,312 INFO Epoch:24 val_res:0.714286 +2025-04-18 02:10:29,086 INFO Epoch:25 train_loss:0.69681 +2025-04-18 02:10:29,937 INFO Epoch:25 val_res:0.685714 +2025-04-18 02:10:35,234 INFO Epoch:26 train_loss:0.68626 +2025-04-18 02:10:36,060 INFO Epoch:26 val_res:0.657143 +2025-04-18 02:10:41,361 INFO Epoch:27 train_loss:0.67970 +2025-04-18 02:10:42,203 INFO Epoch:27 val_res:0.638095 +2025-04-18 02:10:47,094 INFO Epoch:28 train_loss:0.67111 +2025-04-18 02:10:47,967 INFO Epoch:28 val_res:0.714286 +2025-04-18 02:10:53,309 INFO Epoch:29 train_loss:0.65985 +2025-04-18 02:10:54,201 INFO Epoch:29 val_res:0.704762 +2025-04-18 02:10:59,396 INFO Epoch:30 train_loss:0.65739 +2025-04-18 02:11:00,274 INFO Epoch:30 val_res:0.742857 +2025-04-18 02:11:00,274 INFO Saving best model at Epoch 30 +2025-04-18 02:11:07,633 INFO Epoch:31 train_loss:0.63277 +2025-04-18 02:11:08,727 INFO Epoch:31 val_res:0.723810 +2025-04-18 02:11:14,091 INFO Epoch:32 train_loss:0.60224 +2025-04-18 02:11:15,030 INFO Epoch:32 val_res:0.723810 +2025-04-18 02:11:20,007 INFO Epoch:33 train_loss:0.62836 +2025-04-18 02:11:20,971 INFO Epoch:33 val_res:0.742857 +2025-04-18 02:11:26,309 INFO Epoch:34 train_loss:0.62094 +2025-04-18 02:11:27,225 INFO Epoch:34 val_res:0.742857 +2025-04-18 02:11:32,386 INFO Epoch:35 train_loss:0.59332 +2025-04-18 02:11:33,352 INFO Epoch:35 val_res:0.752381 +2025-04-18 02:11:33,352 INFO Saving best model at Epoch 35 +2025-04-18 02:11:39,974 INFO Epoch:36 train_loss:0.56057 +2025-04-18 02:11:40,960 INFO Epoch:36 val_res:0.733333 +2025-04-18 02:11:46,374 INFO Epoch:37 train_loss:0.58499 +2025-04-18 02:11:47,535 INFO Epoch:37 val_res:0.733333 +2025-04-18 02:11:52,810 INFO Epoch:38 train_loss:0.57286 +2025-04-18 02:11:53,775 INFO Epoch:38 val_res:0.723810 +2025-04-18 02:11:58,677 INFO Epoch:39 train_loss:0.57325 +2025-04-18 02:11:59,684 INFO Epoch:39 val_res:0.723810 +2025-04-18 02:12:05,164 INFO Epoch:40 train_loss:0.55130 +2025-04-18 02:12:06,265 INFO Epoch:40 val_res:0.742857 +2025-04-18 02:12:11,917 INFO Epoch:41 train_loss:0.54877 +2025-04-18 02:12:12,900 INFO Epoch:41 val_res:0.752381 +2025-04-18 02:12:18,439 INFO Epoch:42 train_loss:0.54469 +2025-04-18 02:12:19,492 INFO Epoch:42 val_res:0.733333 +2025-04-18 02:12:24,837 INFO Epoch:43 train_loss:0.54767 +2025-04-18 02:12:25,901 INFO Epoch:43 val_res:0.733333 +2025-04-18 02:12:30,969 INFO Epoch:44 train_loss:0.54451 +2025-04-18 02:12:31,940 INFO Epoch:44 val_res:0.704762 +2025-04-18 02:12:37,450 INFO Epoch:45 train_loss:0.54941 +2025-04-18 02:12:38,412 INFO Epoch:45 val_res:0.704762 +2025-04-18 02:12:44,280 INFO Epoch:46 train_loss:0.52713 +2025-04-18 02:12:45,315 INFO Epoch:46 val_res:0.704762 +2025-04-18 02:12:50,521 INFO Epoch:47 train_loss:0.54137 +2025-04-18 02:12:51,587 INFO Epoch:47 val_res:0.733333 +2025-04-18 02:12:56,831 INFO Epoch:48 train_loss:0.51933 +2025-04-18 02:12:57,859 INFO Epoch:48 val_res:0.723810 +2025-04-18 02:13:03,217 INFO Epoch:49 train_loss:0.48752 +2025-04-18 02:13:04,259 INFO Epoch:49 val_res:0.761905 +2025-04-18 02:13:04,259 INFO Saving best model at Epoch 49 +2025-04-18 02:13:11,599 INFO Epoch:50 train_loss:0.49321 +2025-04-18 02:13:12,736 INFO Epoch:50 val_res:0.752381 +2025-04-18 02:13:18,154 INFO Epoch:51 train_loss:0.50473 +2025-04-18 02:13:19,269 INFO Epoch:51 val_res:0.723810 +2025-04-18 02:13:24,354 INFO Epoch:52 train_loss:0.49361 +2025-04-18 02:13:25,409 INFO Epoch:52 val_res:0.771429 +2025-04-18 02:13:25,409 INFO Saving best model at Epoch 52 +2025-04-18 02:13:32,348 INFO Epoch:53 train_loss:0.49045 +2025-04-18 02:13:33,500 INFO Epoch:53 val_res:0.752381 +2025-04-18 02:13:39,255 INFO Epoch:54 train_loss:0.48797 +2025-04-18 02:13:40,327 INFO Epoch:54 val_res:0.733333 +2025-04-18 02:13:45,835 INFO Epoch:55 train_loss:0.49981 +2025-04-18 02:13:46,838 INFO Epoch:55 val_res:0.723810 +2025-04-18 02:13:51,749 INFO Epoch:56 train_loss:0.50274 +2025-04-18 02:13:52,788 INFO Epoch:56 val_res:0.761905 +2025-04-18 02:13:57,716 INFO Epoch:57 train_loss:0.53160 +2025-04-18 02:13:58,593 INFO Epoch:57 val_res:0.666667 +2025-04-18 02:14:03,947 INFO Epoch:58 train_loss:0.51971 +2025-04-18 02:14:05,038 INFO Epoch:58 val_res:0.714286 +2025-04-18 02:14:10,594 INFO Epoch:59 train_loss:0.50277 +2025-04-18 02:14:11,543 INFO Epoch:59 val_res:0.685714 +2025-04-18 02:14:16,368 INFO Epoch:60 train_loss:0.51143 +2025-04-18 02:14:17,351 INFO Epoch:60 val_res:0.714286 +2025-04-18 02:14:22,239 INFO Epoch:61 train_loss:0.51438 +2025-04-18 02:14:23,194 INFO Epoch:61 val_res:0.723810 +2025-04-18 02:14:28,418 INFO Epoch:62 train_loss:0.50994 +2025-04-18 02:14:29,364 INFO Epoch:62 val_res:0.733333 +2025-04-18 02:14:34,704 INFO Epoch:63 train_loss:0.46063 +2025-04-18 02:14:35,672 INFO Epoch:63 val_res:0.752381 +2025-04-18 02:14:40,741 INFO Epoch:64 train_loss:0.46125 +2025-04-18 02:14:41,691 INFO Epoch:64 val_res:0.780952 +2025-04-18 02:14:41,691 INFO Saving best model at Epoch 64 +2025-04-18 02:14:48,240 INFO Epoch:65 train_loss:0.44128 +2025-04-18 02:14:49,141 INFO Epoch:65 val_res:0.742857 +2025-04-18 02:14:54,492 INFO Epoch:66 train_loss:0.46251 +2025-04-18 02:14:55,473 INFO Epoch:66 val_res:0.780952 +2025-04-18 02:15:00,705 INFO Epoch:67 train_loss:0.44230 +2025-04-18 02:15:01,628 INFO Epoch:67 val_res:0.790476 +2025-04-18 02:15:01,628 INFO Saving best model at Epoch 67 +2025-04-18 02:15:08,188 INFO Epoch:68 train_loss:0.42733 +2025-04-18 02:15:09,116 INFO Epoch:68 val_res:0.771429 +2025-04-18 02:15:14,363 INFO Epoch:69 train_loss:0.41541 +2025-04-18 02:15:15,389 INFO Epoch:69 val_res:0.790476 +2025-04-18 02:15:20,482 INFO Epoch:70 train_loss:0.40962 +2025-04-18 02:15:21,458 INFO Epoch:70 val_res:0.752381 +2025-04-18 02:15:26,614 INFO Epoch:71 train_loss:0.42097 +2025-04-18 02:15:27,580 INFO Epoch:71 val_res:0.761905 +2025-04-18 02:15:32,578 INFO Epoch:72 train_loss:0.43746 +2025-04-18 02:15:33,532 INFO Epoch:72 val_res:0.771429 +2025-04-18 02:15:38,516 INFO Epoch:73 train_loss:0.41530 +2025-04-18 02:15:39,386 INFO Epoch:73 val_res:0.780952 +2025-04-18 02:15:44,420 INFO Epoch:74 train_loss:0.41933 +2025-04-18 02:15:45,356 INFO Epoch:74 val_res:0.771429 +2025-04-18 02:15:50,262 INFO Epoch:75 train_loss:0.43234 +2025-04-18 02:15:51,131 INFO Epoch:75 val_res:0.780952 +2025-04-18 02:15:55,977 INFO Epoch:76 train_loss:0.41679 +2025-04-18 02:15:57,004 INFO Epoch:76 val_res:0.771429 +2025-04-18 02:16:01,575 INFO Epoch:77 train_loss:0.40569 +2025-04-18 02:16:02,554 INFO Epoch:77 val_res:0.800000 +2025-04-18 02:16:02,554 INFO Saving best model at Epoch 77 +2025-04-18 02:16:09,258 INFO Epoch:78 train_loss:0.40633 +2025-04-18 02:16:10,231 INFO Epoch:78 val_res:0.752381 +2025-04-18 02:16:15,538 INFO Epoch:79 train_loss:0.39803 +2025-04-18 02:16:16,518 INFO Epoch:79 val_res:0.780952 +2025-04-18 02:16:21,359 INFO Epoch:80 train_loss:0.39496 +2025-04-18 02:16:22,270 INFO Epoch:80 val_res:0.752381 +2025-04-18 02:16:26,846 INFO Epoch:81 train_loss:0.37422 +2025-04-18 02:16:27,775 INFO Epoch:81 val_res:0.752381 +2025-04-18 02:16:32,561 INFO Epoch:82 train_loss:0.39512 +2025-04-18 02:16:33,522 INFO Epoch:82 val_res:0.752381 +2025-04-18 02:16:38,759 INFO Epoch:83 train_loss:0.38352 +2025-04-18 02:16:39,746 INFO Epoch:83 val_res:0.780952 +2025-04-18 02:16:44,779 INFO Epoch:84 train_loss:0.39437 +2025-04-18 02:16:45,785 INFO Epoch:84 val_res:0.780952 +2025-04-18 02:16:50,613 INFO Epoch:85 train_loss:0.40136 +2025-04-18 02:16:51,476 INFO Epoch:85 val_res:0.723810 +2025-04-18 02:16:56,164 INFO Epoch:86 train_loss:0.38368 +2025-04-18 02:16:57,074 INFO Epoch:86 val_res:0.771429 +2025-04-18 02:17:02,047 INFO Epoch:87 train_loss:0.37420 +2025-04-18 02:17:03,042 INFO Epoch:87 val_res:0.790476 +2025-04-18 02:17:08,323 INFO Epoch:88 train_loss:0.36540 +2025-04-18 02:17:09,276 INFO Epoch:88 val_res:0.800000 +2025-04-18 02:17:14,025 INFO Epoch:89 train_loss:0.36395 +2025-04-18 02:17:14,929 INFO Epoch:89 val_res:0.771429 +2025-04-18 02:17:19,683 INFO Epoch:90 train_loss:0.36680 +2025-04-18 02:17:20,716 INFO Epoch:90 val_res:0.809524 +2025-04-18 02:17:20,716 INFO Saving best model at Epoch 90 +2025-04-18 02:17:28,743 INFO Epoch:91 train_loss:0.35851 +2025-04-18 02:17:29,644 INFO Epoch:91 val_res:0.761905 +2025-04-18 02:17:34,858 INFO Epoch:92 train_loss:0.36404 +2025-04-18 02:17:35,816 INFO Epoch:92 val_res:0.752381 +2025-04-18 02:17:40,804 INFO Epoch:93 train_loss:0.37612 +2025-04-18 02:17:41,796 INFO Epoch:93 val_res:0.809524 +2025-04-18 02:17:46,915 INFO Epoch:94 train_loss:0.34500 +2025-04-18 02:17:47,868 INFO Epoch:94 val_res:0.809524 +2025-04-18 02:17:52,861 INFO Epoch:95 train_loss:0.33947 +2025-04-18 02:17:53,862 INFO Epoch:95 val_res:0.780952 +2025-04-18 02:17:59,012 INFO Epoch:96 train_loss:0.33773 +2025-04-18 02:17:59,937 INFO Epoch:96 val_res:0.790476 +2025-04-18 02:18:04,761 INFO Epoch:97 train_loss:0.35440 +2025-04-18 02:18:05,748 INFO Epoch:97 val_res:0.790476 +2025-04-18 02:18:10,608 INFO Epoch:98 train_loss:0.37487 +2025-04-18 02:18:11,542 INFO Epoch:98 val_res:0.771429 +2025-04-18 02:18:16,598 INFO Epoch:99 train_loss:0.38234 +2025-04-18 02:18:17,452 INFO Epoch:99 val_res:0.800000 +2025-04-18 02:18:25,286 INFO ===================================== +2025-04-18 02:18:25,287 INFO Start testing... +2025-04-18 02:18:25,288 INFO ===================================== +2025-04-18 02:18:30,386 INFO Incremental step 0 Testing res: 0.750000 +2025-04-18 02:18:30,388 INFO Incremental step: 1 +2025-04-18 02:20:55,758 INFO Epoch:0 train_loss:1.85418 +2025-04-18 02:24:11,255 INFO Epoch:0 val_res:0.403756 +2025-04-18 02:24:11,256 INFO Saving best model at Epoch 0 +2025-04-18 02:24:19,274 INFO Epoch:1 train_loss:1.60670 +2025-04-18 02:24:20,603 INFO Epoch:1 val_res:0.403756 +2025-04-18 02:24:25,831 INFO Epoch:2 train_loss:1.40899 +2025-04-18 02:24:27,228 INFO Epoch:2 val_res:0.413146 +2025-04-18 02:24:27,229 INFO Saving best model at Epoch 2 +2025-04-18 02:24:34,143 INFO Epoch:3 train_loss:1.27047 +2025-04-18 02:24:35,556 INFO Epoch:3 val_res:0.417840 +2025-04-18 02:24:35,557 INFO Saving best model at Epoch 3 +2025-04-18 02:24:42,820 INFO Epoch:4 train_loss:1.19731 +2025-04-18 02:24:44,231 INFO Epoch:4 val_res:0.436620 +2025-04-18 02:24:44,232 INFO Saving best model at Epoch 4 +2025-04-18 02:24:51,194 INFO Epoch:5 train_loss:1.10155 +2025-04-18 02:24:52,549 INFO Epoch:5 val_res:0.446009 +2025-04-18 02:24:52,549 INFO Saving best model at Epoch 5 +2025-04-18 02:25:00,103 INFO Epoch:6 train_loss:1.03720 +2025-04-18 02:25:01,432 INFO Epoch:6 val_res:0.446009 +2025-04-18 02:25:07,123 INFO Epoch:7 train_loss:0.98440 +2025-04-18 02:25:08,491 INFO Epoch:7 val_res:0.431925 +2025-04-18 02:25:13,994 INFO Epoch:8 train_loss:0.93383 +2025-04-18 02:25:15,453 INFO Epoch:8 val_res:0.422535 +2025-04-18 02:25:20,572 INFO Epoch:9 train_loss:0.88420 +2025-04-18 02:25:21,901 INFO Epoch:9 val_res:0.431925 +2025-04-18 02:25:26,912 INFO Epoch:10 train_loss:0.82843 +2025-04-18 02:25:28,266 INFO Epoch:10 val_res:0.455399 +2025-04-18 02:25:28,267 INFO Saving best model at Epoch 10 +2025-04-18 02:25:35,229 INFO Epoch:11 train_loss:0.81316 +2025-04-18 02:25:36,548 INFO Epoch:11 val_res:0.469484 +2025-04-18 02:25:36,548 INFO Saving best model at Epoch 11 +2025-04-18 02:25:43,358 INFO Epoch:12 train_loss:0.78823 +2025-04-18 02:25:44,749 INFO Epoch:12 val_res:0.469484 +2025-04-18 02:25:50,216 INFO Epoch:13 train_loss:0.76282 +2025-04-18 02:25:51,623 INFO Epoch:13 val_res:0.478873 +2025-04-18 02:25:51,623 INFO Saving best model at Epoch 13 +2025-04-18 02:25:58,797 INFO Epoch:14 train_loss:0.73233 +2025-04-18 02:26:00,131 INFO Epoch:14 val_res:0.478873 +2025-04-18 02:26:05,287 INFO Epoch:15 train_loss:0.73956 +2025-04-18 02:26:06,748 INFO Epoch:15 val_res:0.483568 +2025-04-18 02:26:06,749 INFO Saving best model at Epoch 15 +2025-04-18 02:26:13,596 INFO Epoch:16 train_loss:0.71062 +2025-04-18 02:26:14,987 INFO Epoch:16 val_res:0.446009 +2025-04-18 02:26:19,995 INFO Epoch:17 train_loss:0.70847 +2025-04-18 02:26:21,376 INFO Epoch:17 val_res:0.530516 +2025-04-18 02:26:21,376 INFO Saving best model at Epoch 17 +2025-04-18 02:26:28,428 INFO Epoch:18 train_loss:0.68087 +2025-04-18 02:26:29,803 INFO Epoch:18 val_res:0.539906 +2025-04-18 02:26:29,803 INFO Saving best model at Epoch 18 +2025-04-18 02:26:36,664 INFO Epoch:19 train_loss:0.66747 +2025-04-18 02:26:38,097 INFO Epoch:19 val_res:0.530516 +2025-04-18 02:26:43,534 INFO Epoch:20 train_loss:0.64030 +2025-04-18 02:26:45,015 INFO Epoch:20 val_res:0.577465 +2025-04-18 02:26:45,015 INFO Saving best model at Epoch 20 +2025-04-18 02:26:52,278 INFO Epoch:21 train_loss:0.64414 +2025-04-18 02:26:53,623 INFO Epoch:21 val_res:0.568075 +2025-04-18 02:26:59,064 INFO Epoch:22 train_loss:0.60422 +2025-04-18 02:27:00,454 INFO Epoch:22 val_res:0.553991 +2025-04-18 02:27:05,878 INFO Epoch:23 train_loss:0.62579 +2025-04-18 02:27:07,248 INFO Epoch:23 val_res:0.568075 +2025-04-18 02:27:12,371 INFO Epoch:24 train_loss:0.61131 +2025-04-18 02:27:13,750 INFO Epoch:24 val_res:0.572770 +2025-04-18 02:27:19,012 INFO Epoch:25 train_loss:0.59289 +2025-04-18 02:27:20,438 INFO Epoch:25 val_res:0.544601 +2025-04-18 02:27:25,581 INFO Epoch:26 train_loss:0.57548 +2025-04-18 02:27:26,979 INFO Epoch:26 val_res:0.568075 +2025-04-18 02:27:32,430 INFO Epoch:27 train_loss:0.57465 +2025-04-18 02:27:33,910 INFO Epoch:27 val_res:0.558685 +2025-04-18 02:27:39,617 INFO Epoch:28 train_loss:0.55590 +2025-04-18 02:27:41,026 INFO Epoch:28 val_res:0.553991 +2025-04-18 02:27:46,425 INFO Epoch:29 train_loss:0.53762 +2025-04-18 02:27:47,869 INFO Epoch:29 val_res:0.572770 +2025-04-18 02:27:53,071 INFO Epoch:30 train_loss:0.55231 +2025-04-18 02:27:54,448 INFO Epoch:30 val_res:0.605634 +2025-04-18 02:27:54,449 INFO Saving best model at Epoch 30 +2025-04-18 02:28:01,818 INFO Epoch:31 train_loss:0.52944 +2025-04-18 02:28:03,217 INFO Epoch:31 val_res:0.596244 +2025-04-18 02:28:08,751 INFO Epoch:32 train_loss:0.53150 +2025-04-18 02:28:10,198 INFO Epoch:32 val_res:0.591549 +2025-04-18 02:28:15,861 INFO Epoch:33 train_loss:0.54329 +2025-04-18 02:28:17,260 INFO Epoch:33 val_res:0.563380 +2025-04-18 02:28:22,784 INFO Epoch:34 train_loss:0.53324 +2025-04-18 02:28:24,196 INFO Epoch:34 val_res:0.586854 +2025-04-18 02:28:29,333 INFO Epoch:35 train_loss:0.50406 +2025-04-18 02:28:30,720 INFO Epoch:35 val_res:0.605634 +2025-04-18 02:28:35,947 INFO Epoch:36 train_loss:0.51500 +2025-04-18 02:28:37,380 INFO Epoch:36 val_res:0.586854 +2025-04-18 02:28:43,037 INFO Epoch:37 train_loss:0.51349 +2025-04-18 02:28:44,383 INFO Epoch:37 val_res:0.586854 +2025-04-18 02:28:50,030 INFO Epoch:38 train_loss:0.48725 +2025-04-18 02:28:51,401 INFO Epoch:38 val_res:0.596244 +2025-04-18 02:28:56,694 INFO Epoch:39 train_loss:0.49693 +2025-04-18 02:28:58,062 INFO Epoch:39 val_res:0.596244 +2025-04-18 02:29:03,094 INFO Epoch:40 train_loss:0.49407 +2025-04-18 02:29:04,483 INFO Epoch:40 val_res:0.586854 +2025-04-18 02:29:09,685 INFO Epoch:41 train_loss:0.47356 +2025-04-18 02:29:11,084 INFO Epoch:41 val_res:0.615023 +2025-04-18 02:29:11,085 INFO Saving best model at Epoch 41 +2025-04-18 02:29:18,799 INFO Epoch:42 train_loss:0.45471 +2025-04-18 02:29:20,149 INFO Epoch:42 val_res:0.615023 +2025-04-18 02:29:26,051 INFO Epoch:43 train_loss:0.46697 +2025-04-18 02:29:27,517 INFO Epoch:43 val_res:0.605634 +2025-04-18 02:29:32,779 INFO Epoch:44 train_loss:0.45318 +2025-04-18 02:29:34,200 INFO Epoch:44 val_res:0.610329 +2025-04-18 02:29:39,671 INFO Epoch:45 train_loss:0.45449 +2025-04-18 02:29:41,101 INFO Epoch:45 val_res:0.610329 +2025-04-18 02:29:46,297 INFO Epoch:46 train_loss:0.44867 +2025-04-18 02:29:47,723 INFO Epoch:46 val_res:0.596244 +2025-04-18 02:29:53,021 INFO Epoch:47 train_loss:0.45071 +2025-04-18 02:29:54,400 INFO Epoch:47 val_res:0.605634 +2025-04-18 02:29:59,844 INFO Epoch:48 train_loss:0.46100 +2025-04-18 02:30:01,275 INFO Epoch:48 val_res:0.619718 +2025-04-18 02:30:01,275 INFO Saving best model at Epoch 48 +2025-04-18 02:30:08,160 INFO Epoch:49 train_loss:0.44436 +2025-04-18 02:30:09,548 INFO Epoch:49 val_res:0.615023 +2025-04-18 02:30:14,891 INFO Epoch:50 train_loss:0.42510 +2025-04-18 02:30:16,354 INFO Epoch:50 val_res:0.596244 +2025-04-18 02:30:21,446 INFO Epoch:51 train_loss:0.42514 +2025-04-18 02:30:22,809 INFO Epoch:51 val_res:0.605634 +2025-04-18 02:30:27,935 INFO Epoch:52 train_loss:0.42043 +2025-04-18 02:30:29,330 INFO Epoch:52 val_res:0.615023 +2025-04-18 02:30:34,483 INFO Epoch:53 train_loss:0.43615 +2025-04-18 02:30:35,872 INFO Epoch:53 val_res:0.633803 +2025-04-18 02:30:35,873 INFO Saving best model at Epoch 53 +2025-04-18 02:30:42,954 INFO Epoch:54 train_loss:0.41019 +2025-04-18 02:30:44,334 INFO Epoch:54 val_res:0.624413 +2025-04-18 02:30:50,142 INFO Epoch:55 train_loss:0.41313 +2025-04-18 02:30:51,525 INFO Epoch:55 val_res:0.619718 +2025-04-18 02:30:56,742 INFO Epoch:56 train_loss:0.39788 +2025-04-18 02:30:58,159 INFO Epoch:56 val_res:0.633803 +2025-04-18 02:31:03,239 INFO Epoch:57 train_loss:0.42556 +2025-04-18 02:31:04,562 INFO Epoch:57 val_res:0.615023 +2025-04-18 02:31:09,792 INFO Epoch:58 train_loss:0.40907 +2025-04-18 02:31:11,137 INFO Epoch:58 val_res:0.638498 +2025-04-18 02:31:11,138 INFO Saving best model at Epoch 58 +2025-04-18 02:31:19,242 INFO Epoch:59 train_loss:0.40127 +2025-04-18 02:31:20,686 INFO Epoch:59 val_res:0.605634 +2025-04-18 02:31:26,385 INFO Epoch:60 train_loss:0.38768 +2025-04-18 02:31:27,745 INFO Epoch:60 val_res:0.629108 +2025-04-18 02:31:32,845 INFO Epoch:61 train_loss:0.40039 +2025-04-18 02:31:34,211 INFO Epoch:61 val_res:0.638498 +2025-04-18 02:31:39,412 INFO Epoch:62 train_loss:0.40431 +2025-04-18 02:31:40,866 INFO Epoch:62 val_res:0.610329 +2025-04-18 02:31:46,238 INFO Epoch:63 train_loss:0.41898 +2025-04-18 02:31:47,659 INFO Epoch:63 val_res:0.629108 +2025-04-18 02:31:53,347 INFO Epoch:64 train_loss:0.40071 +2025-04-18 02:31:54,778 INFO Epoch:64 val_res:0.629108 +2025-04-18 02:32:00,248 INFO Epoch:65 train_loss:0.39737 +2025-04-18 02:32:01,614 INFO Epoch:65 val_res:0.629108 +2025-04-18 02:32:06,728 INFO Epoch:66 train_loss:0.38659 +2025-04-18 02:32:08,167 INFO Epoch:66 val_res:0.605634 +2025-04-18 02:32:13,321 INFO Epoch:67 train_loss:0.36990 +2025-04-18 02:32:14,720 INFO Epoch:67 val_res:0.624413 +2025-04-18 02:32:20,642 INFO Epoch:68 train_loss:0.36013 +2025-04-18 02:32:21,993 INFO Epoch:68 val_res:0.629108 +2025-04-18 02:32:27,511 INFO Epoch:69 train_loss:0.35193 +2025-04-18 02:32:28,936 INFO Epoch:69 val_res:0.633803 +2025-04-18 02:32:34,393 INFO Epoch:70 train_loss:0.38499 +2025-04-18 02:32:35,752 INFO Epoch:70 val_res:0.610329 +2025-04-18 02:32:41,118 INFO Epoch:71 train_loss:0.37895 +2025-04-18 02:32:42,458 INFO Epoch:71 val_res:0.610329 +2025-04-18 02:32:48,134 INFO Epoch:72 train_loss:0.41739 +2025-04-18 02:32:49,450 INFO Epoch:72 val_res:0.629108 +2025-04-18 02:32:54,972 INFO Epoch:73 train_loss:0.38957 +2025-04-18 02:32:56,260 INFO Epoch:73 val_res:0.610329 +2025-04-18 02:33:02,112 INFO Epoch:74 train_loss:0.34955 +2025-04-18 02:33:03,396 INFO Epoch:74 val_res:0.596244 +2025-04-18 02:33:08,920 INFO Epoch:75 train_loss:0.36986 +2025-04-18 02:33:10,198 INFO Epoch:75 val_res:0.610329 +2025-04-18 02:33:15,169 INFO Epoch:76 train_loss:0.33838 +2025-04-18 02:33:16,513 INFO Epoch:76 val_res:0.615023 +2025-04-18 02:33:21,735 INFO Epoch:77 train_loss:0.33711 +2025-04-18 02:33:23,001 INFO Epoch:77 val_res:0.629108 +2025-04-18 02:33:28,168 INFO Epoch:78 train_loss:0.35316 +2025-04-18 02:33:29,475 INFO Epoch:78 val_res:0.605634 +2025-04-18 02:33:34,603 INFO Epoch:79 train_loss:0.34044 +2025-04-18 02:33:35,870 INFO Epoch:79 val_res:0.586854 +2025-04-18 02:33:41,021 INFO Epoch:80 train_loss:0.33310 +2025-04-18 02:33:42,319 INFO Epoch:80 val_res:0.600939 +2025-04-18 02:33:47,964 INFO Epoch:81 train_loss:0.33860 +2025-04-18 02:33:49,251 INFO Epoch:81 val_res:0.633803 +2025-04-18 02:33:54,294 INFO Epoch:82 train_loss:0.36049 +2025-04-18 02:33:55,574 INFO Epoch:82 val_res:0.610329 +2025-04-18 02:34:00,862 INFO Epoch:83 train_loss:0.33335 +2025-04-18 02:34:02,233 INFO Epoch:83 val_res:0.591549 +2025-04-18 02:34:07,168 INFO Epoch:84 train_loss:0.33755 +2025-04-18 02:34:08,538 INFO Epoch:84 val_res:0.633803 +2025-04-18 02:34:13,813 INFO Epoch:85 train_loss:0.32730 +2025-04-18 02:34:15,161 INFO Epoch:85 val_res:0.591549 +2025-04-18 02:34:20,367 INFO Epoch:86 train_loss:0.34080 +2025-04-18 02:34:21,659 INFO Epoch:86 val_res:0.610329 +2025-04-18 02:34:27,216 INFO Epoch:87 train_loss:0.33522 +2025-04-18 02:34:28,521 INFO Epoch:87 val_res:0.610329 +2025-04-18 02:34:33,545 INFO Epoch:88 train_loss:0.33296 +2025-04-18 02:34:34,824 INFO Epoch:88 val_res:0.624413 +2025-04-18 02:34:39,801 INFO Epoch:89 train_loss:0.33436 +2025-04-18 02:34:41,083 INFO Epoch:89 val_res:0.619718 +2025-04-18 02:34:46,330 INFO Epoch:90 train_loss:0.34360 +2025-04-18 02:34:47,690 INFO Epoch:90 val_res:0.652582 +2025-04-18 02:34:47,690 INFO Saving best model at Epoch 90 +2025-04-18 02:34:55,275 INFO Epoch:91 train_loss:0.33107 +2025-04-18 02:34:56,597 INFO Epoch:91 val_res:0.605634 +2025-04-18 02:35:01,375 INFO Epoch:92 train_loss:0.33808 +2025-04-18 02:35:02,677 INFO Epoch:92 val_res:0.610329 +2025-04-18 02:35:07,706 INFO Epoch:93 train_loss:0.31665 +2025-04-18 02:35:09,068 INFO Epoch:93 val_res:0.619718 +2025-04-18 02:35:14,117 INFO Epoch:94 train_loss:0.30691 +2025-04-18 02:35:15,389 INFO Epoch:94 val_res:0.591549 +2025-04-18 02:35:20,478 INFO Epoch:95 train_loss:0.29959 +2025-04-18 02:35:21,740 INFO Epoch:95 val_res:0.619718 +2025-04-18 02:35:26,757 INFO Epoch:96 train_loss:0.29601 +2025-04-18 02:35:28,026 INFO Epoch:96 val_res:0.619718 +2025-04-18 02:35:33,803 INFO Epoch:97 train_loss:0.29919 +2025-04-18 02:35:35,132 INFO Epoch:97 val_res:0.619718 +2025-04-18 02:35:40,301 INFO Epoch:98 train_loss:0.29451 +2025-04-18 02:35:41,646 INFO Epoch:98 val_res:0.615023 +2025-04-18 02:35:46,820 INFO Epoch:99 train_loss:0.28115 +2025-04-18 02:35:48,232 INFO Epoch:99 val_res:0.610329 +2025-04-18 02:35:55,930 INFO ===================================== +2025-04-18 02:35:55,930 INFO Start testing... +2025-04-18 02:35:55,930 INFO ===================================== +2025-04-18 02:36:00,806 INFO Incremental step 1 Testing res: 0.609524 +2025-04-18 02:36:00,807 INFO forgetting: 0.269231 +2025-04-18 02:36:00,808 INFO Incremental step: 2 +2025-04-18 02:39:08,430 INFO Epoch:0 train_loss:1.87128 +2025-04-18 02:39:26,007 INFO Epoch:0 val_res:0.439103 +2025-04-18 02:39:26,008 INFO Saving best model at Epoch 0 +2025-04-18 02:39:36,132 INFO Epoch:1 train_loss:1.62622 +2025-04-18 02:39:38,143 INFO Epoch:1 val_res:0.416667 +2025-04-18 02:39:43,771 INFO Epoch:2 train_loss:1.59547 +2025-04-18 02:39:45,716 INFO Epoch:2 val_res:0.355769 +2025-04-18 02:39:50,780 INFO Epoch:3 train_loss:2.37137 +2025-04-18 02:39:52,786 INFO Epoch:3 val_res:0.326923 +2025-04-18 02:39:57,903 INFO Epoch:4 train_loss:3.08112 +2025-04-18 02:39:59,941 INFO Epoch:4 val_res:0.323718 +2025-04-18 02:40:05,278 INFO Epoch:5 train_loss:2.97242 +2025-04-18 02:40:07,139 INFO Epoch:5 val_res:0.375000 +2025-04-18 02:40:12,066 INFO Epoch:6 train_loss:2.47430 +2025-04-18 02:40:14,031 INFO Epoch:6 val_res:0.416667 +2025-04-18 02:40:19,233 INFO Epoch:7 train_loss:1.50054 +2025-04-18 02:40:21,213 INFO Epoch:7 val_res:0.442308 +2025-04-18 02:40:21,213 INFO Saving best model at Epoch 7 +2025-04-18 02:40:29,198 INFO Epoch:8 train_loss:1.26354 +2025-04-18 02:40:31,088 INFO Epoch:8 val_res:0.426282 +2025-04-18 02:40:36,181 INFO Epoch:9 train_loss:1.34869 +2025-04-18 02:40:38,086 INFO Epoch:9 val_res:0.407051 +2025-04-18 02:40:43,322 INFO Epoch:10 train_loss:1.53850 +2025-04-18 02:40:45,178 INFO Epoch:10 val_res:0.368590 +2025-04-18 02:40:50,119 INFO Epoch:11 train_loss:1.72676 +2025-04-18 02:40:52,036 INFO Epoch:11 val_res:0.371795 +2025-04-18 02:40:57,034 INFO Epoch:12 train_loss:1.79398 +2025-04-18 02:40:58,974 INFO Epoch:12 val_res:0.397436 +2025-04-18 02:41:04,033 INFO Epoch:13 train_loss:1.73883 +2025-04-18 02:41:05,854 INFO Epoch:13 val_res:0.387821 +2025-04-18 02:41:10,907 INFO Epoch:14 train_loss:1.63548 +2025-04-18 02:41:12,755 INFO Epoch:14 val_res:0.407051 +2025-04-18 02:41:18,063 INFO Epoch:15 train_loss:1.51547 +2025-04-18 02:41:19,999 INFO Epoch:15 val_res:0.416667 +2025-04-18 02:41:25,109 INFO Epoch:16 train_loss:1.40911 +2025-04-18 02:41:27,057 INFO Epoch:16 val_res:0.378205 +2025-04-18 02:41:32,226 INFO Epoch:17 train_loss:1.57500 +2025-04-18 02:41:34,140 INFO Epoch:17 val_res:0.397436 +2025-04-18 02:41:39,361 INFO Epoch:18 train_loss:1.16852 +2025-04-18 02:41:41,231 INFO Epoch:18 val_res:0.407051 +2025-04-18 02:41:46,291 INFO Epoch:19 train_loss:1.54133 +2025-04-18 02:41:48,106 INFO Epoch:19 val_res:0.429487 +2025-04-18 02:41:53,267 INFO Epoch:20 train_loss:1.26383 +2025-04-18 02:41:55,273 INFO Epoch:20 val_res:0.426282 +2025-04-18 02:42:00,202 INFO Epoch:21 train_loss:1.31442 +2025-04-18 02:42:02,071 INFO Epoch:21 val_res:0.416667 +2025-04-18 02:42:06,979 INFO Epoch:22 train_loss:1.10865 +2025-04-18 02:42:08,962 INFO Epoch:22 val_res:0.410256 +2025-04-18 02:42:14,129 INFO Epoch:23 train_loss:1.16828 +2025-04-18 02:42:16,026 INFO Epoch:23 val_res:0.429487 +2025-04-18 02:42:21,227 INFO Epoch:24 train_loss:1.05415 +2025-04-18 02:42:23,062 INFO Epoch:24 val_res:0.451923 +2025-04-18 02:42:23,063 INFO Saving best model at Epoch 24 +2025-04-18 02:42:29,918 INFO Epoch:25 train_loss:1.12220 +2025-04-18 02:42:31,845 INFO Epoch:25 val_res:0.416667 +2025-04-18 02:42:37,152 INFO Epoch:26 train_loss:0.96268 +2025-04-18 02:42:39,044 INFO Epoch:26 val_res:0.413462 +2025-04-18 02:42:44,118 INFO Epoch:27 train_loss:1.05375 +2025-04-18 02:42:45,961 INFO Epoch:27 val_res:0.426282 +2025-04-18 02:42:51,258 INFO Epoch:28 train_loss:0.93067 +2025-04-18 02:42:53,279 INFO Epoch:28 val_res:0.458333 +2025-04-18 02:42:53,280 INFO Saving best model at Epoch 28 +2025-04-18 02:42:59,950 INFO Epoch:29 train_loss:0.80548 +2025-04-18 02:43:01,902 INFO Epoch:29 val_res:0.445513 +2025-04-18 02:43:06,937 INFO Epoch:30 train_loss:0.77365 +2025-04-18 02:43:08,878 INFO Epoch:30 val_res:0.464744 +2025-04-18 02:43:08,879 INFO Saving best model at Epoch 30 +2025-04-18 02:43:15,492 INFO Epoch:31 train_loss:0.70817 +2025-04-18 02:43:17,282 INFO Epoch:31 val_res:0.458333 +2025-04-18 02:43:22,439 INFO Epoch:32 train_loss:0.68399 +2025-04-18 02:43:24,437 INFO Epoch:32 val_res:0.451923 +2025-04-18 02:43:30,064 INFO Epoch:33 train_loss:0.65605 +2025-04-18 02:43:32,026 INFO Epoch:33 val_res:0.455128 +2025-04-18 02:43:37,524 INFO Epoch:34 train_loss:0.64325 +2025-04-18 02:43:39,439 INFO Epoch:34 val_res:0.435897 +2025-04-18 02:43:44,767 INFO Epoch:35 train_loss:0.59960 +2025-04-18 02:43:46,766 INFO Epoch:35 val_res:0.439103 +2025-04-18 02:43:52,214 INFO Epoch:36 train_loss:0.60572 +2025-04-18 02:43:54,231 INFO Epoch:36 val_res:0.445513 +2025-04-18 02:43:59,666 INFO Epoch:37 train_loss:0.59199 +2025-04-18 02:44:01,551 INFO Epoch:37 val_res:0.451923 +2025-04-18 02:44:07,737 INFO Epoch:38 train_loss:0.56705 +2025-04-18 02:44:09,620 INFO Epoch:38 val_res:0.445513 +2025-04-18 02:44:15,406 INFO Epoch:39 train_loss:0.54641 +2025-04-18 02:44:17,342 INFO Epoch:39 val_res:0.442308 +2025-04-18 02:44:22,690 INFO Epoch:40 train_loss:0.54289 +2025-04-18 02:44:24,489 INFO Epoch:40 val_res:0.442308 +2025-04-18 02:44:29,906 INFO Epoch:41 train_loss:0.51844 +2025-04-18 02:44:31,789 INFO Epoch:41 val_res:0.439103 +2025-04-18 02:44:37,494 INFO Epoch:42 train_loss:0.51105 +2025-04-18 02:44:39,437 INFO Epoch:42 val_res:0.451923 +2025-04-18 02:44:45,298 INFO Epoch:43 train_loss:0.50778 +2025-04-18 02:44:47,237 INFO Epoch:43 val_res:0.432692 +2025-04-18 02:44:52,928 INFO Epoch:44 train_loss:0.51348 +2025-04-18 02:44:54,998 INFO Epoch:44 val_res:0.410256 +2025-04-18 02:45:00,011 INFO Epoch:45 train_loss:0.52461 +2025-04-18 02:45:01,910 INFO Epoch:45 val_res:0.432692 +2025-04-18 02:45:07,105 INFO Epoch:46 train_loss:0.48259 +2025-04-18 02:45:09,069 INFO Epoch:46 val_res:0.451923 +2025-04-18 02:45:14,739 INFO Epoch:47 train_loss:0.48198 +2025-04-18 02:45:16,776 INFO Epoch:47 val_res:0.464744 +2025-04-18 02:45:22,699 INFO Epoch:48 train_loss:0.49092 +2025-04-18 02:45:24,527 INFO Epoch:48 val_res:0.464744 +2025-04-18 02:45:29,842 INFO Epoch:49 train_loss:0.46950 +2025-04-18 02:45:31,769 INFO Epoch:49 val_res:0.445513 +2025-04-18 02:45:37,109 INFO Epoch:50 train_loss:0.47067 +2025-04-18 02:45:39,067 INFO Epoch:50 val_res:0.471154 +2025-04-18 02:45:39,068 INFO Saving best model at Epoch 50 +2025-04-18 02:45:46,504 INFO Epoch:51 train_loss:0.45590 +2025-04-18 02:45:49,124 INFO Epoch:51 val_res:0.442308 +2025-04-18 02:45:54,480 INFO Epoch:52 train_loss:0.46517 +2025-04-18 02:45:56,778 INFO Epoch:52 val_res:0.461538 +2025-04-18 02:46:03,432 INFO Epoch:53 train_loss:0.45440 +2025-04-18 02:46:05,650 INFO Epoch:53 val_res:0.461538 +2025-04-18 02:46:11,542 INFO Epoch:54 train_loss:0.44242 +2025-04-18 02:46:13,420 INFO Epoch:54 val_res:0.448718 +2025-04-18 02:46:18,624 INFO Epoch:55 train_loss:0.43760 +2025-04-18 02:46:20,737 INFO Epoch:55 val_res:0.461538 +2025-04-18 02:46:26,915 INFO Epoch:56 train_loss:0.43185 +2025-04-18 02:46:29,040 INFO Epoch:56 val_res:0.464744 +2025-04-18 02:46:34,789 INFO Epoch:57 train_loss:0.42875 +2025-04-18 02:46:37,357 INFO Epoch:57 val_res:0.471154 +2025-04-18 02:46:42,998 INFO Epoch:58 train_loss:0.41890 +2025-04-18 02:46:44,989 INFO Epoch:58 val_res:0.467949 +2025-04-18 02:46:50,389 INFO Epoch:59 train_loss:0.42270 +2025-04-18 02:46:52,295 INFO Epoch:59 val_res:0.467949 +2025-04-18 02:46:57,789 INFO Epoch:60 train_loss:0.42491 +2025-04-18 02:46:59,719 INFO Epoch:60 val_res:0.477564 +2025-04-18 02:46:59,719 INFO Saving best model at Epoch 60 +2025-04-18 02:47:07,813 INFO Epoch:61 train_loss:0.41524 +2025-04-18 02:47:09,761 INFO Epoch:61 val_res:0.464744 +2025-04-18 02:47:15,383 INFO Epoch:62 train_loss:0.40937 +2025-04-18 02:47:17,378 INFO Epoch:62 val_res:0.464744 +2025-04-18 02:47:22,908 INFO Epoch:63 train_loss:0.40217 +2025-04-18 02:47:24,749 INFO Epoch:63 val_res:0.464744 +2025-04-18 02:47:30,118 INFO Epoch:64 train_loss:0.38139 +2025-04-18 02:47:32,123 INFO Epoch:64 val_res:0.471154 +2025-04-18 02:47:37,424 INFO Epoch:65 train_loss:0.36797 +2025-04-18 02:47:39,338 INFO Epoch:65 val_res:0.474359 +2025-04-18 02:47:44,812 INFO Epoch:66 train_loss:0.37693 +2025-04-18 02:47:46,778 INFO Epoch:66 val_res:0.474359 +2025-04-18 02:47:52,425 INFO Epoch:67 train_loss:0.36787 +2025-04-18 02:47:54,403 INFO Epoch:67 val_res:0.477564 +2025-04-18 02:47:59,770 INFO Epoch:68 train_loss:0.38381 +2025-04-18 02:48:01,641 INFO Epoch:68 val_res:0.483974 +2025-04-18 02:48:01,641 INFO Saving best model at Epoch 68 +2025-04-18 02:48:08,877 INFO Epoch:69 train_loss:0.36654 +2025-04-18 02:48:10,986 INFO Epoch:69 val_res:0.483974 +2025-04-18 02:48:16,394 INFO Epoch:70 train_loss:0.36309 +2025-04-18 02:48:18,397 INFO Epoch:70 val_res:0.467949 +2025-04-18 02:48:24,071 INFO Epoch:71 train_loss:0.38157 +2025-04-18 02:48:26,142 INFO Epoch:71 val_res:0.477564 +2025-04-18 02:48:32,269 INFO Epoch:72 train_loss:0.37316 +2025-04-18 02:48:34,317 INFO Epoch:72 val_res:0.483974 +2025-04-18 02:48:40,133 INFO Epoch:73 train_loss:0.37320 +2025-04-18 02:48:42,151 INFO Epoch:73 val_res:0.487179 +2025-04-18 02:48:42,151 INFO Saving best model at Epoch 73 +2025-04-18 02:48:49,313 INFO Epoch:74 train_loss:0.34268 +2025-04-18 02:48:51,320 INFO Epoch:74 val_res:0.451923 +2025-04-18 02:48:56,627 INFO Epoch:75 train_loss:0.35214 +2025-04-18 02:48:58,900 INFO Epoch:75 val_res:0.509615 +2025-04-18 02:48:58,901 INFO Saving best model at Epoch 75 +2025-04-18 02:49:05,684 INFO Epoch:76 train_loss:0.36200 +2025-04-18 02:49:07,669 INFO Epoch:76 val_res:0.474359 +2025-04-18 02:49:13,127 INFO Epoch:77 train_loss:0.36338 +2025-04-18 02:49:15,108 INFO Epoch:77 val_res:0.490385 +2025-04-18 02:49:20,549 INFO Epoch:78 train_loss:0.34741 +2025-04-18 02:49:22,539 INFO Epoch:78 val_res:0.493590 +2025-04-18 02:49:27,990 INFO Epoch:79 train_loss:0.35401 +2025-04-18 02:49:29,937 INFO Epoch:79 val_res:0.483974 +2025-04-18 02:49:35,346 INFO Epoch:80 train_loss:0.34776 +2025-04-18 02:49:37,272 INFO Epoch:80 val_res:0.471154 +2025-04-18 02:49:42,701 INFO Epoch:81 train_loss:0.33028 +2025-04-18 02:49:44,694 INFO Epoch:81 val_res:0.483974 +2025-04-18 02:49:50,288 INFO Epoch:82 train_loss:0.33810 +2025-04-18 02:49:52,228 INFO Epoch:82 val_res:0.464744 +2025-04-18 02:49:57,507 INFO Epoch:83 train_loss:0.32797 +2025-04-18 02:49:59,497 INFO Epoch:83 val_res:0.490385 +2025-04-18 02:50:04,669 INFO Epoch:84 train_loss:0.32141 +2025-04-18 02:50:06,624 INFO Epoch:84 val_res:0.506410 +2025-04-18 02:50:12,334 INFO Epoch:85 train_loss:0.32297 +2025-04-18 02:50:14,316 INFO Epoch:85 val_res:0.487179 +2025-04-18 02:50:19,862 INFO Epoch:86 train_loss:0.31044 +2025-04-18 02:50:21,818 INFO Epoch:86 val_res:0.490385 +2025-04-18 02:50:27,477 INFO Epoch:87 train_loss:0.30471 +2025-04-18 02:50:29,395 INFO Epoch:87 val_res:0.461538 +2025-04-18 02:50:34,538 INFO Epoch:88 train_loss:0.31252 +2025-04-18 02:50:36,429 INFO Epoch:88 val_res:0.467949 +2025-04-18 02:50:41,591 INFO Epoch:89 train_loss:0.34785 +2025-04-18 02:50:43,496 INFO Epoch:89 val_res:0.496795 +2025-04-18 02:50:48,881 INFO Epoch:90 train_loss:0.30088 +2025-04-18 02:50:50,894 INFO Epoch:90 val_res:0.483974 +2025-04-18 02:50:56,773 INFO Epoch:91 train_loss:0.31536 +2025-04-18 02:50:58,825 INFO Epoch:91 val_res:0.487179 +2025-04-18 02:51:04,240 INFO Epoch:92 train_loss:0.30170 +2025-04-18 02:51:06,285 INFO Epoch:92 val_res:0.487179 +2025-04-18 02:51:11,721 INFO Epoch:93 train_loss:0.30960 +2025-04-18 02:51:13,626 INFO Epoch:93 val_res:0.474359 +2025-04-18 02:51:18,854 INFO Epoch:94 train_loss:0.33620 +2025-04-18 02:51:21,118 INFO Epoch:94 val_res:0.490385 +2025-04-18 02:51:26,582 INFO Epoch:95 train_loss:0.30817 +2025-04-18 02:51:28,525 INFO Epoch:95 val_res:0.474359 +2025-04-18 02:51:34,058 INFO Epoch:96 train_loss:0.30435 +2025-04-18 02:51:36,152 INFO Epoch:96 val_res:0.487179 +2025-04-18 02:51:41,549 INFO Epoch:97 train_loss:0.33117 +2025-04-18 02:51:43,384 INFO Epoch:97 val_res:0.458333 +2025-04-18 02:51:48,881 INFO Epoch:98 train_loss:0.32084 +2025-04-18 02:51:50,884 INFO Epoch:98 val_res:0.509615 +2025-04-18 02:51:56,610 INFO Epoch:99 train_loss:0.33157 +2025-04-18 02:51:58,541 INFO Epoch:99 val_res:0.487179 +2025-04-18 02:52:06,706 INFO ===================================== +2025-04-18 02:52:06,707 INFO Start testing... +2025-04-18 02:52:06,707 INFO ===================================== +2025-04-18 02:52:12,346 INFO Incremental step 2 Testing res: 0.447619 +2025-04-18 02:52:12,347 INFO forgetting: 0.292090 +2025-04-18 02:52:12,348 INFO Incremental step: 3 +2025-04-18 02:52:50,779 INFO Epoch:0 train_loss:1.86350 +2025-04-18 02:53:11,359 INFO Epoch:0 val_res:0.406650 +2025-04-18 02:53:11,359 INFO Saving best model at Epoch 0 +2025-04-18 02:53:17,574 INFO Epoch:1 train_loss:1.57457 +2025-04-18 02:53:20,600 INFO Epoch:1 val_res:0.404092 +2025-04-18 02:53:25,242 INFO Epoch:2 train_loss:1.35005 +2025-04-18 02:53:27,933 INFO Epoch:2 val_res:0.404092 +2025-04-18 02:53:32,965 INFO Epoch:3 train_loss:1.10476 +2025-04-18 02:53:35,838 INFO Epoch:3 val_res:0.404092 +2025-04-18 02:53:40,196 INFO Epoch:4 train_loss:0.96531 +2025-04-18 02:53:43,029 INFO Epoch:4 val_res:0.401535 +2025-04-18 02:53:47,363 INFO Epoch:5 train_loss:0.89444 +2025-04-18 02:53:49,907 INFO Epoch:5 val_res:0.406650 +2025-04-18 02:53:54,112 INFO Epoch:6 train_loss:0.83998 +2025-04-18 02:53:56,637 INFO Epoch:6 val_res:0.409207 +2025-04-18 02:53:56,638 INFO Saving best model at Epoch 6 +2025-04-18 02:54:08,859 INFO Epoch:7 train_loss:0.79418 +2025-04-18 02:54:11,480 INFO Epoch:7 val_res:0.411765 +2025-04-18 02:54:11,481 INFO Saving best model at Epoch 7 +2025-04-18 02:54:17,411 INFO Epoch:8 train_loss:0.72208 +2025-04-18 02:54:20,032 INFO Epoch:8 val_res:0.406650 +2025-04-18 02:54:23,915 INFO Epoch:9 train_loss:0.69085 +2025-04-18 02:54:26,617 INFO Epoch:9 val_res:0.398977 +2025-04-18 02:54:30,696 INFO Epoch:10 train_loss:0.65718 +2025-04-18 02:54:33,303 INFO Epoch:10 val_res:0.401535 +2025-04-18 02:54:37,349 INFO Epoch:11 train_loss:0.66692 +2025-04-18 02:54:39,981 INFO Epoch:11 val_res:0.391304 +2025-04-18 02:54:44,042 INFO Epoch:12 train_loss:0.68409 +2025-04-18 02:54:46,680 INFO Epoch:12 val_res:0.401535 +2025-04-18 02:54:50,777 INFO Epoch:13 train_loss:0.65421 +2025-04-18 02:54:53,304 INFO Epoch:13 val_res:0.409207 +2025-04-18 02:54:57,528 INFO Epoch:14 train_loss:0.61457 +2025-04-18 02:55:00,046 INFO Epoch:14 val_res:0.421995 +2025-04-18 02:55:00,046 INFO Saving best model at Epoch 14 +2025-04-18 02:55:09,178 INFO Epoch:15 train_loss:0.58870 +2025-04-18 02:55:11,731 INFO Epoch:15 val_res:0.398977 +2025-04-18 02:55:15,832 INFO Epoch:16 train_loss:0.68139 +2025-04-18 02:55:18,361 INFO Epoch:16 val_res:0.398977 +2025-04-18 02:55:22,433 INFO Epoch:17 train_loss:0.59368 +2025-04-18 02:55:24,858 INFO Epoch:17 val_res:0.416880 +2025-04-18 02:55:28,775 INFO Epoch:18 train_loss:0.57098 +2025-04-18 02:55:31,158 INFO Epoch:18 val_res:0.414322 +2025-04-18 02:55:35,377 INFO Epoch:19 train_loss:0.56359 +2025-04-18 02:55:37,900 INFO Epoch:19 val_res:0.409207 +2025-04-18 02:55:41,867 INFO Epoch:20 train_loss:0.55782 +2025-04-18 02:55:44,450 INFO Epoch:20 val_res:0.424552 +2025-04-18 02:55:44,450 INFO Saving best model at Epoch 20 +2025-04-18 02:55:50,229 INFO Epoch:21 train_loss:0.51938 +2025-04-18 02:55:52,816 INFO Epoch:21 val_res:0.421995 +2025-04-18 02:55:56,837 INFO Epoch:22 train_loss:0.56540 +2025-04-18 02:55:59,306 INFO Epoch:22 val_res:0.419437 +2025-04-18 02:56:03,365 INFO Epoch:23 train_loss:0.51839 +2025-04-18 02:56:05,963 INFO Epoch:23 val_res:0.419437 +2025-04-18 02:56:10,172 INFO Epoch:24 train_loss:0.52001 +2025-04-18 02:56:12,773 INFO Epoch:24 val_res:0.427110 +2025-04-18 02:56:12,773 INFO Saving best model at Epoch 24 +2025-04-18 02:56:18,619 INFO Epoch:25 train_loss:0.50719 +2025-04-18 02:56:21,260 INFO Epoch:25 val_res:0.419437 +2025-04-18 02:56:25,284 INFO Epoch:26 train_loss:0.48779 +2025-04-18 02:56:27,748 INFO Epoch:26 val_res:0.416880 +2025-04-18 02:56:31,935 INFO Epoch:27 train_loss:0.49134 +2025-04-18 02:56:34,462 INFO Epoch:27 val_res:0.416880 +2025-04-18 02:56:38,951 INFO Epoch:28 train_loss:0.48065 +2025-04-18 02:56:41,530 INFO Epoch:28 val_res:0.427110 +2025-04-18 02:56:45,699 INFO Epoch:29 train_loss:0.47299 +2025-04-18 02:56:48,346 INFO Epoch:29 val_res:0.421995 +2025-04-18 02:56:52,804 INFO Epoch:30 train_loss:0.46879 +2025-04-18 02:56:55,450 INFO Epoch:30 val_res:0.424552 +2025-04-18 02:56:59,815 INFO Epoch:31 train_loss:0.47816 +2025-04-18 02:57:02,447 INFO Epoch:31 val_res:0.424552 +2025-04-18 02:57:07,091 INFO Epoch:32 train_loss:0.46420 +2025-04-18 02:57:09,630 INFO Epoch:32 val_res:0.424552 +2025-04-18 02:57:13,742 INFO Epoch:33 train_loss:0.46009 +2025-04-18 02:57:16,425 INFO Epoch:33 val_res:0.429668 +2025-04-18 02:57:16,426 INFO Saving best model at Epoch 33 +2025-04-18 02:57:23,424 INFO Epoch:34 train_loss:0.45761 +2025-04-18 02:57:26,064 INFO Epoch:34 val_res:0.414322 +2025-04-18 02:57:30,280 INFO Epoch:35 train_loss:0.47016 +2025-04-18 02:57:32,865 INFO Epoch:35 val_res:0.427110 +2025-04-18 02:57:37,416 INFO Epoch:36 train_loss:0.47552 +2025-04-18 02:57:40,073 INFO Epoch:36 val_res:0.429668 +2025-04-18 02:57:44,621 INFO Epoch:37 train_loss:0.48730 +2025-04-18 02:57:47,151 INFO Epoch:37 val_res:0.424552 +2025-04-18 02:57:51,485 INFO Epoch:38 train_loss:0.44195 +2025-04-18 02:57:54,130 INFO Epoch:38 val_res:0.434783 +2025-04-18 02:57:54,131 INFO Saving best model at Epoch 38 +2025-04-18 02:58:01,248 INFO Epoch:39 train_loss:0.50631 +2025-04-18 02:58:03,697 INFO Epoch:39 val_res:0.427110 +2025-04-18 02:58:07,923 INFO Epoch:40 train_loss:0.44537 +2025-04-18 02:58:10,448 INFO Epoch:40 val_res:0.419437 +2025-04-18 02:58:14,639 INFO Epoch:41 train_loss:0.48842 +2025-04-18 02:58:17,118 INFO Epoch:41 val_res:0.427110 +2025-04-18 02:58:21,289 INFO Epoch:42 train_loss:0.45770 +2025-04-18 02:58:23,981 INFO Epoch:42 val_res:0.416880 +2025-04-18 02:58:28,369 INFO Epoch:43 train_loss:0.40907 +2025-04-18 02:58:31,056 INFO Epoch:43 val_res:0.429668 +2025-04-18 02:58:35,266 INFO Epoch:44 train_loss:0.44842 +2025-04-18 02:58:37,879 INFO Epoch:44 val_res:0.429668 +2025-04-18 02:58:42,083 INFO Epoch:45 train_loss:0.40663 +2025-04-18 02:58:44,682 INFO Epoch:45 val_res:0.424552 +2025-04-18 02:58:48,896 INFO Epoch:46 train_loss:0.42378 +2025-04-18 02:58:51,510 INFO Epoch:46 val_res:0.427110 +2025-04-18 02:58:55,697 INFO Epoch:47 train_loss:0.39627 +2025-04-18 02:58:58,230 INFO Epoch:47 val_res:0.427110 +2025-04-18 02:59:02,301 INFO Epoch:48 train_loss:0.39300 +2025-04-18 02:59:04,950 INFO Epoch:48 val_res:0.437340 +2025-04-18 02:59:04,950 INFO Saving best model at Epoch 48 +2025-04-18 02:59:12,007 INFO Epoch:49 train_loss:0.41018 +2025-04-18 02:59:14,468 INFO Epoch:49 val_res:0.434783 +2025-04-18 02:59:18,598 INFO Epoch:50 train_loss:0.40633 +2025-04-18 02:59:21,106 INFO Epoch:50 val_res:0.434783 +2025-04-18 02:59:25,297 INFO Epoch:51 train_loss:0.38683 +2025-04-18 02:59:27,721 INFO Epoch:51 val_res:0.442455 +2025-04-18 02:59:27,721 INFO Saving best model at Epoch 51 +2025-04-18 02:59:33,940 INFO Epoch:52 train_loss:0.40114 +2025-04-18 02:59:36,459 INFO Epoch:52 val_res:0.439898 +2025-04-18 02:59:40,883 INFO Epoch:53 train_loss:0.41616 +2025-04-18 02:59:43,522 INFO Epoch:53 val_res:0.445013 +2025-04-18 02:59:43,523 INFO Saving best model at Epoch 53 +2025-04-18 02:59:51,179 INFO Epoch:54 train_loss:0.36513 +2025-04-18 02:59:53,816 INFO Epoch:54 val_res:0.432225 +2025-04-18 02:59:57,820 INFO Epoch:55 train_loss:0.40130 +2025-04-18 03:00:00,781 INFO Epoch:55 val_res:0.427110 +2025-04-18 03:00:04,931 INFO Epoch:56 train_loss:0.39725 +2025-04-18 03:00:07,453 INFO Epoch:56 val_res:0.445013 +2025-04-18 03:00:11,765 INFO Epoch:57 train_loss:0.37317 +2025-04-18 03:00:14,292 INFO Epoch:57 val_res:0.442455 +2025-04-18 03:00:18,457 INFO Epoch:58 train_loss:0.36958 +2025-04-18 03:00:21,271 INFO Epoch:58 val_res:0.442455 +2025-04-18 03:00:25,334 INFO Epoch:59 train_loss:0.36922 +2025-04-18 03:00:27,855 INFO Epoch:59 val_res:0.439898 +2025-04-18 03:00:31,898 INFO Epoch:60 train_loss:0.35727 +2025-04-18 03:00:34,376 INFO Epoch:60 val_res:0.437340 +2025-04-18 03:00:38,537 INFO Epoch:61 train_loss:0.36087 +2025-04-18 03:00:41,021 INFO Epoch:61 val_res:0.437340 +2025-04-18 03:00:45,202 INFO Epoch:62 train_loss:0.39513 +2025-04-18 03:00:47,666 INFO Epoch:62 val_res:0.447570 +2025-04-18 03:00:47,666 INFO Saving best model at Epoch 62 +2025-04-18 03:00:53,584 INFO Epoch:63 train_loss:0.33457 +2025-04-18 03:00:56,146 INFO Epoch:63 val_res:0.442455 +2025-04-18 03:01:00,574 INFO Epoch:64 train_loss:0.35250 +2025-04-18 03:01:03,143 INFO Epoch:64 val_res:0.442455 +2025-04-18 03:01:07,090 INFO Epoch:65 train_loss:0.34497 +2025-04-18 03:01:09,616 INFO Epoch:65 val_res:0.434783 +2025-04-18 03:01:13,771 INFO Epoch:66 train_loss:0.34895 +2025-04-18 03:01:16,756 INFO Epoch:66 val_res:0.452685 +2025-04-18 03:01:16,756 INFO Saving best model at Epoch 66 +2025-04-18 03:01:23,545 INFO Epoch:67 train_loss:0.35442 +2025-04-18 03:01:26,346 INFO Epoch:67 val_res:0.447570 +2025-04-18 03:01:30,663 INFO Epoch:68 train_loss:0.34160 +2025-04-18 03:01:33,245 INFO Epoch:68 val_res:0.447570 +2025-04-18 03:01:37,179 INFO Epoch:69 train_loss:0.31712 +2025-04-18 03:01:39,616 INFO Epoch:69 val_res:0.442455 +2025-04-18 03:01:43,691 INFO Epoch:70 train_loss:0.31879 +2025-04-18 03:01:46,191 INFO Epoch:70 val_res:0.455243 +2025-04-18 03:01:46,191 INFO Saving best model at Epoch 70 +2025-04-18 03:01:52,189 INFO Epoch:71 train_loss:0.34785 +2025-04-18 03:01:54,696 INFO Epoch:71 val_res:0.445013 +2025-04-18 03:01:59,057 INFO Epoch:72 train_loss:0.34268 +2025-04-18 03:02:01,663 INFO Epoch:72 val_res:0.427110 +2025-04-18 03:02:05,910 INFO Epoch:73 train_loss:0.33739 +2025-04-18 03:02:08,627 INFO Epoch:73 val_res:0.432225 +2025-04-18 03:02:12,872 INFO Epoch:74 train_loss:0.34613 +2025-04-18 03:02:15,418 INFO Epoch:74 val_res:0.442455 +2025-04-18 03:02:19,862 INFO Epoch:75 train_loss:0.34516 +2025-04-18 03:02:22,400 INFO Epoch:75 val_res:0.434783 +2025-04-18 03:02:26,654 INFO Epoch:76 train_loss:0.35111 +2025-04-18 03:02:29,221 INFO Epoch:76 val_res:0.442455 +2025-04-18 03:02:33,348 INFO Epoch:77 train_loss:0.32742 +2025-04-18 03:02:35,888 INFO Epoch:77 val_res:0.432225 +2025-04-18 03:02:39,990 INFO Epoch:78 train_loss:0.30857 +2025-04-18 03:02:42,568 INFO Epoch:78 val_res:0.462916 +2025-04-18 03:02:42,569 INFO Saving best model at Epoch 78 +2025-04-18 03:02:48,210 INFO Epoch:79 train_loss:0.33154 +2025-04-18 03:02:50,786 INFO Epoch:79 val_res:0.437340 +2025-04-18 03:02:54,881 INFO Epoch:80 train_loss:0.31961 +2025-04-18 03:02:57,434 INFO Epoch:80 val_res:0.442455 +2025-04-18 03:03:01,502 INFO Epoch:81 train_loss:0.30089 +2025-04-18 03:03:03,971 INFO Epoch:81 val_res:0.439898 +2025-04-18 03:03:08,148 INFO Epoch:82 train_loss:0.29145 +2025-04-18 03:03:10,647 INFO Epoch:82 val_res:0.421995 +2025-04-18 03:03:14,772 INFO Epoch:83 train_loss:0.32329 +2025-04-18 03:03:17,258 INFO Epoch:83 val_res:0.434783 +2025-04-18 03:03:21,473 INFO Epoch:84 train_loss:0.29541 +2025-04-18 03:03:24,031 INFO Epoch:84 val_res:0.432225 +2025-04-18 03:03:28,335 INFO Epoch:85 train_loss:0.28702 +2025-04-18 03:03:31,116 INFO Epoch:85 val_res:0.450128 +2025-04-18 03:03:35,259 INFO Epoch:86 train_loss:0.31033 +2025-04-18 03:03:37,947 INFO Epoch:86 val_res:0.432225 +2025-04-18 03:03:42,069 INFO Epoch:87 train_loss:0.28859 +2025-04-18 03:03:44,621 INFO Epoch:87 val_res:0.434783 +2025-04-18 03:03:48,466 INFO Epoch:88 train_loss:0.29507 +2025-04-18 03:03:50,963 INFO Epoch:88 val_res:0.429668 +2025-04-18 03:03:55,273 INFO Epoch:89 train_loss:0.30361 +2025-04-18 03:03:57,810 INFO Epoch:89 val_res:0.427110 +2025-04-18 03:04:02,083 INFO Epoch:90 train_loss:0.31645 +2025-04-18 03:04:04,865 INFO Epoch:90 val_res:0.439898 +2025-04-18 03:04:09,190 INFO Epoch:91 train_loss:0.28876 +2025-04-18 03:04:11,694 INFO Epoch:91 val_res:0.442455 +2025-04-18 03:04:15,918 INFO Epoch:92 train_loss:0.29982 +2025-04-18 03:04:18,541 INFO Epoch:92 val_res:0.434783 +2025-04-18 03:04:22,887 INFO Epoch:93 train_loss:0.29046 +2025-04-18 03:04:25,298 INFO Epoch:93 val_res:0.432225 +2025-04-18 03:04:29,370 INFO Epoch:94 train_loss:0.31631 +2025-04-18 03:04:32,024 INFO Epoch:94 val_res:0.434783 +2025-04-18 03:04:36,392 INFO Epoch:95 train_loss:0.29263 +2025-04-18 03:04:39,249 INFO Epoch:95 val_res:0.434783 +2025-04-18 03:04:43,421 INFO Epoch:96 train_loss:0.26044 +2025-04-18 03:04:45,973 INFO Epoch:96 val_res:0.414322 +2025-04-18 03:04:49,896 INFO Epoch:97 train_loss:0.30636 +2025-04-18 03:04:52,369 INFO Epoch:97 val_res:0.419437 +2025-04-18 03:04:57,101 INFO Epoch:98 train_loss:0.28474 +2025-04-18 03:04:59,492 INFO Epoch:98 val_res:0.427110 +2025-04-18 03:05:03,583 INFO Epoch:99 train_loss:0.27181 +2025-04-18 03:05:06,158 INFO Epoch:99 val_res:0.437340 +2025-04-18 03:05:14,642 INFO ===================================== +2025-04-18 03:05:14,643 INFO Start testing... +2025-04-18 03:05:14,643 INFO ===================================== +2025-04-18 03:05:21,473 INFO Incremental step 3 Testing res: 0.383249 +2025-04-18 03:05:21,475 INFO forgetting: 0.270740 +2025-04-18 03:05:21,476 INFO Average Accuracy: 0.547606 +2025-04-18 03:05:21,476 INFO Average Forgetting: 0.277354 diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..71e62b2ad093488033379cde1c93dbf487171275 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..834449f3c105683b4bf45cd48f1fee0ce9ed423f Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..ba74019ed2a57cdf2e12791518676c09c3bd838f Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..1c236b4d3377268e7526b5a942aa68634c3c2613 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..cf2fd04ba236947a25235c703548bd3d3dfc98f8 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..312e29999da78ac030912ab3d5390583da59713a Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..e289e9bd6fdb29ecfac80788bef8a55073fbc2c4 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..8152aaaf4aceb7001df05512bda0ab861cd97f9d Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..606b36f2a260f54286761754555570fb82915bfa --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ffb30326a890ed15f199ce5577e76083ee2d02c61e3318e2bd632ed84d292d +size 114115089 diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b87ed1af61a38d233315432e3f74d9f2e1669e34 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf6bf6536e066765920713d7e835ec04f119d5fff250aacd3aca548aab0079fa +size 114179665 diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ae7a02acc08c717a9ee72ea652ebfb4dc9afca2a --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba7c8ed8944a9afc3182c2603ebf00f8e1f92d12d0d9d6bb481f0a8addd7d76 +size 114244369 diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..97e3c9823481a2276729bac53a89e9eaaa85fcd9 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dbe4a6629583db46558808026e752e6d300807c60e70a8b157222bbafe2832b +size 114308881 diff --git a/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/train.log b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..da27785855359f471dc8c17f583032038b1ed16d --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/AVE/audio-visual/use-inverse_True-seed_0/train.log @@ -0,0 +1,879 @@ +2025-04-18 01:59:24,027 INFO Namespace(class_num_per_step=7, dataset='AVE', e_prompt=False, infer_batch_size=128, inverse=True, inverse_ends=100, inverse_starts=0, lr=0.01, lr_decay=False, max_epoches=100, milestones=[100], modality='audio-visual', num_classes=28, num_workers=1, prompt_dim=768, seed=0, train_batch_size=256, transfer=False, warm=False, weight_decay=0.0001) +2025-04-18 01:59:24,029 INFO Training start time: 2025-04-18 01:59:24.029295 +2025-04-18 02:05:47,077 INFO Incremental step: 0 +2025-04-18 02:06:19,078 INFO Epoch:0 train_loss:5.79097 +2025-04-18 02:07:31,702 INFO Epoch:0 val_res:0.304762 +2025-04-18 02:07:31,703 INFO Saving best model at Epoch 0 +2025-04-18 02:07:40,445 INFO Epoch:1 train_loss:5.47550 +2025-04-18 02:07:41,479 INFO Epoch:1 val_res:0.371429 +2025-04-18 02:07:41,479 INFO Saving best model at Epoch 1 +2025-04-18 02:07:49,887 INFO Epoch:2 train_loss:5.16405 +2025-04-18 02:07:50,848 INFO Epoch:2 val_res:0.438095 +2025-04-18 02:07:50,848 INFO Saving best model at Epoch 2 +2025-04-18 02:07:58,182 INFO Epoch:3 train_loss:4.85723 +2025-04-18 02:07:59,182 INFO Epoch:3 val_res:0.523810 +2025-04-18 02:07:59,182 INFO Saving best model at Epoch 3 +2025-04-18 02:08:06,502 INFO Epoch:4 train_loss:4.49728 +2025-04-18 02:08:07,417 INFO Epoch:4 val_res:0.457143 +2025-04-18 02:08:13,041 INFO Epoch:5 train_loss:4.23763 +2025-04-18 02:08:13,980 INFO Epoch:5 val_res:0.571429 +2025-04-18 02:08:13,980 INFO Saving best model at Epoch 5 +2025-04-18 02:08:22,189 INFO Epoch:6 train_loss:3.98139 +2025-04-18 02:08:23,339 INFO Epoch:6 val_res:0.542857 +2025-04-18 02:08:29,853 INFO Epoch:7 train_loss:3.81053 +2025-04-18 02:08:30,859 INFO Epoch:7 val_res:0.542857 +2025-04-18 02:08:36,081 INFO Epoch:8 train_loss:3.62186 +2025-04-18 02:08:37,193 INFO Epoch:8 val_res:0.600000 +2025-04-18 02:08:37,193 INFO Saving best model at Epoch 8 +2025-04-18 02:08:44,920 INFO Epoch:9 train_loss:3.48063 +2025-04-18 02:08:45,911 INFO Epoch:9 val_res:0.704762 +2025-04-18 02:08:45,912 INFO Saving best model at Epoch 9 +2025-04-18 02:08:54,111 INFO Epoch:10 train_loss:3.30581 +2025-04-18 02:08:54,982 INFO Epoch:10 val_res:0.723810 +2025-04-18 02:08:54,982 INFO Saving best model at Epoch 10 +2025-04-18 02:09:02,789 INFO Epoch:11 train_loss:3.24480 +2025-04-18 02:09:03,770 INFO Epoch:11 val_res:0.666667 +2025-04-18 02:09:09,343 INFO Epoch:12 train_loss:3.10125 +2025-04-18 02:09:10,255 INFO Epoch:12 val_res:0.657143 +2025-04-18 02:09:16,055 INFO Epoch:13 train_loss:3.04735 +2025-04-18 02:09:17,031 INFO Epoch:13 val_res:0.695238 +2025-04-18 02:09:24,211 INFO Epoch:14 train_loss:2.95337 +2025-04-18 02:09:25,168 INFO Epoch:14 val_res:0.638095 +2025-04-18 02:09:31,101 INFO Epoch:15 train_loss:2.92027 +2025-04-18 02:09:32,212 INFO Epoch:15 val_res:0.657143 +2025-04-18 02:09:38,346 INFO Epoch:16 train_loss:2.84665 +2025-04-18 02:09:39,242 INFO Epoch:16 val_res:0.676190 +2025-04-18 02:09:44,948 INFO Epoch:17 train_loss:2.80102 +2025-04-18 02:09:45,872 INFO Epoch:17 val_res:0.723810 +2025-04-18 02:09:51,925 INFO Epoch:18 train_loss:2.73080 +2025-04-18 02:09:52,862 INFO Epoch:18 val_res:0.714286 +2025-04-18 02:09:58,166 INFO Epoch:19 train_loss:2.67189 +2025-04-18 02:09:59,047 INFO Epoch:19 val_res:0.714286 +2025-04-18 02:10:04,138 INFO Epoch:20 train_loss:2.62056 +2025-04-18 02:10:05,083 INFO Epoch:20 val_res:0.723810 +2025-04-18 02:10:10,804 INFO Epoch:21 train_loss:2.58886 +2025-04-18 02:10:11,805 INFO Epoch:21 val_res:0.704762 +2025-04-18 02:10:17,760 INFO Epoch:22 train_loss:2.58273 +2025-04-18 02:10:18,828 INFO Epoch:22 val_res:0.666667 +2025-04-18 02:10:24,098 INFO Epoch:23 train_loss:2.54518 +2025-04-18 02:10:24,996 INFO Epoch:23 val_res:0.628571 +2025-04-18 02:10:30,096 INFO Epoch:24 train_loss:2.59948 +2025-04-18 02:10:31,028 INFO Epoch:24 val_res:0.685714 +2025-04-18 02:10:36,768 INFO Epoch:25 train_loss:2.58085 +2025-04-18 02:10:37,661 INFO Epoch:25 val_res:0.695238 +2025-04-18 02:10:43,341 INFO Epoch:26 train_loss:2.44645 +2025-04-18 02:10:44,183 INFO Epoch:26 val_res:0.685714 +2025-04-18 02:10:49,728 INFO Epoch:27 train_loss:2.39247 +2025-04-18 02:10:50,645 INFO Epoch:27 val_res:0.695238 +2025-04-18 02:10:56,155 INFO Epoch:28 train_loss:2.37079 +2025-04-18 02:10:57,005 INFO Epoch:28 val_res:0.714286 +2025-04-18 02:11:02,776 INFO Epoch:29 train_loss:2.35517 +2025-04-18 02:11:03,788 INFO Epoch:29 val_res:0.666667 +2025-04-18 02:11:10,227 INFO Epoch:30 train_loss:2.29290 +2025-04-18 02:11:11,189 INFO Epoch:30 val_res:0.695238 +2025-04-18 02:11:16,882 INFO Epoch:31 train_loss:2.28190 +2025-04-18 02:11:17,740 INFO Epoch:31 val_res:0.714286 +2025-04-18 02:11:22,926 INFO Epoch:32 train_loss:2.20210 +2025-04-18 02:11:23,898 INFO Epoch:32 val_res:0.723810 +2025-04-18 02:11:29,431 INFO Epoch:33 train_loss:2.19707 +2025-04-18 02:11:30,465 INFO Epoch:33 val_res:0.714286 +2025-04-18 02:11:36,191 INFO Epoch:34 train_loss:2.19700 +2025-04-18 02:11:37,153 INFO Epoch:34 val_res:0.704762 +2025-04-18 02:11:43,570 INFO Epoch:35 train_loss:2.17686 +2025-04-18 02:11:44,506 INFO Epoch:35 val_res:0.752381 +2025-04-18 02:11:44,506 INFO Saving best model at Epoch 35 +2025-04-18 02:11:51,696 INFO Epoch:36 train_loss:2.13532 +2025-04-18 02:11:52,653 INFO Epoch:36 val_res:0.742857 +2025-04-18 02:11:57,875 INFO Epoch:37 train_loss:2.16024 +2025-04-18 02:11:58,791 INFO Epoch:37 val_res:0.733333 +2025-04-18 02:12:04,752 INFO Epoch:38 train_loss:2.09642 +2025-04-18 02:12:05,859 INFO Epoch:38 val_res:0.733333 +2025-04-18 02:12:11,860 INFO Epoch:39 train_loss:2.11613 +2025-04-18 02:12:12,700 INFO Epoch:39 val_res:0.752381 +2025-04-18 02:12:18,374 INFO Epoch:40 train_loss:2.14881 +2025-04-18 02:12:19,313 INFO Epoch:40 val_res:0.761905 +2025-04-18 02:12:19,313 INFO Saving best model at Epoch 40 +2025-04-18 02:12:26,758 INFO Epoch:41 train_loss:2.08009 +2025-04-18 02:12:27,880 INFO Epoch:41 val_res:0.685714 +2025-04-18 02:12:33,365 INFO Epoch:42 train_loss:2.13785 +2025-04-18 02:12:34,294 INFO Epoch:42 val_res:0.752381 +2025-04-18 02:12:40,240 INFO Epoch:43 train_loss:2.07551 +2025-04-18 02:12:41,244 INFO Epoch:43 val_res:0.704762 +2025-04-18 02:12:47,192 INFO Epoch:44 train_loss:2.02686 +2025-04-18 02:12:48,216 INFO Epoch:44 val_res:0.742857 +2025-04-18 02:12:53,830 INFO Epoch:45 train_loss:2.06909 +2025-04-18 02:12:54,759 INFO Epoch:45 val_res:0.704762 +2025-04-18 02:13:00,246 INFO Epoch:46 train_loss:1.99788 +2025-04-18 02:13:01,241 INFO Epoch:46 val_res:0.714286 +2025-04-18 02:13:07,402 INFO Epoch:47 train_loss:2.08221 +2025-04-18 02:13:08,303 INFO Epoch:47 val_res:0.676190 +2025-04-18 02:13:14,556 INFO Epoch:48 train_loss:2.05656 +2025-04-18 02:13:15,561 INFO Epoch:48 val_res:0.723810 +2025-04-18 02:13:21,021 INFO Epoch:49 train_loss:1.95162 +2025-04-18 02:13:21,971 INFO Epoch:49 val_res:0.714286 +2025-04-18 02:13:27,155 INFO Epoch:50 train_loss:1.96530 +2025-04-18 02:13:28,274 INFO Epoch:50 val_res:0.771429 +2025-04-18 02:13:28,274 INFO Saving best model at Epoch 50 +2025-04-18 02:13:35,994 INFO Epoch:51 train_loss:2.01556 +2025-04-18 02:13:37,037 INFO Epoch:51 val_res:0.676190 +2025-04-18 02:13:43,056 INFO Epoch:52 train_loss:1.95965 +2025-04-18 02:13:44,063 INFO Epoch:52 val_res:0.761905 +2025-04-18 02:13:49,472 INFO Epoch:53 train_loss:1.91746 +2025-04-18 02:13:50,370 INFO Epoch:53 val_res:0.771429 +2025-04-18 02:13:55,483 INFO Epoch:54 train_loss:1.92062 +2025-04-18 02:13:56,287 INFO Epoch:54 val_res:0.780952 +2025-04-18 02:13:56,287 INFO Saving best model at Epoch 54 +2025-04-18 02:14:03,247 INFO Epoch:55 train_loss:1.89036 +2025-04-18 02:14:04,152 INFO Epoch:55 val_res:0.685714 +2025-04-18 02:14:09,856 INFO Epoch:56 train_loss:1.87514 +2025-04-18 02:14:10,774 INFO Epoch:56 val_res:0.733333 +2025-04-18 02:14:16,310 INFO Epoch:57 train_loss:1.84230 +2025-04-18 02:14:17,225 INFO Epoch:57 val_res:0.628571 +2025-04-18 02:14:22,715 INFO Epoch:58 train_loss:1.97380 +2025-04-18 02:14:23,624 INFO Epoch:58 val_res:0.685714 +2025-04-18 02:14:28,706 INFO Epoch:59 train_loss:1.88954 +2025-04-18 02:14:29,595 INFO Epoch:59 val_res:0.733333 +2025-04-18 02:14:34,945 INFO Epoch:60 train_loss:1.93899 +2025-04-18 02:14:35,845 INFO Epoch:60 val_res:0.704762 +2025-04-18 02:14:41,713 INFO Epoch:61 train_loss:1.96417 +2025-04-18 02:14:42,649 INFO Epoch:61 val_res:0.685714 +2025-04-18 02:14:48,612 INFO Epoch:62 train_loss:2.01533 +2025-04-18 02:14:49,542 INFO Epoch:62 val_res:0.695238 +2025-04-18 02:14:54,581 INFO Epoch:63 train_loss:2.03210 +2025-04-18 02:14:55,512 INFO Epoch:63 val_res:0.704762 +2025-04-18 02:15:00,522 INFO Epoch:64 train_loss:1.96892 +2025-04-18 02:15:01,406 INFO Epoch:64 val_res:0.761905 +2025-04-18 02:15:06,930 INFO Epoch:65 train_loss:1.89257 +2025-04-18 02:15:07,873 INFO Epoch:65 val_res:0.742857 +2025-04-18 02:15:13,628 INFO Epoch:66 train_loss:1.98213 +2025-04-18 02:15:14,530 INFO Epoch:66 val_res:0.695238 +2025-04-18 02:15:19,853 INFO Epoch:67 train_loss:2.02356 +2025-04-18 02:15:20,725 INFO Epoch:67 val_res:0.676190 +2025-04-18 02:15:25,855 INFO Epoch:68 train_loss:1.99283 +2025-04-18 02:15:26,769 INFO Epoch:68 val_res:0.723810 +2025-04-18 02:15:32,308 INFO Epoch:69 train_loss:1.92011 +2025-04-18 02:15:33,255 INFO Epoch:69 val_res:0.733333 +2025-04-18 02:15:39,216 INFO Epoch:70 train_loss:1.91187 +2025-04-18 02:15:40,126 INFO Epoch:70 val_res:0.742857 +2025-04-18 02:15:45,504 INFO Epoch:71 train_loss:1.87435 +2025-04-18 02:15:46,419 INFO Epoch:71 val_res:0.695238 +2025-04-18 02:15:51,797 INFO Epoch:72 train_loss:1.83637 +2025-04-18 02:15:52,716 INFO Epoch:72 val_res:0.714286 +2025-04-18 02:15:57,752 INFO Epoch:73 train_loss:1.94095 +2025-04-18 02:15:58,671 INFO Epoch:73 val_res:0.771429 +2025-04-18 02:16:04,152 INFO Epoch:74 train_loss:1.78313 +2025-04-18 02:16:05,048 INFO Epoch:74 val_res:0.704762 +2025-04-18 02:16:10,787 INFO Epoch:75 train_loss:1.76183 +2025-04-18 02:16:11,677 INFO Epoch:75 val_res:0.771429 +2025-04-18 02:16:17,048 INFO Epoch:76 train_loss:1.70017 +2025-04-18 02:16:17,978 INFO Epoch:76 val_res:0.771429 +2025-04-18 02:16:23,076 INFO Epoch:77 train_loss:1.65427 +2025-04-18 02:16:23,953 INFO Epoch:77 val_res:0.761905 +2025-04-18 02:16:29,237 INFO Epoch:78 train_loss:1.66926 +2025-04-18 02:16:30,139 INFO Epoch:78 val_res:0.714286 +2025-04-18 02:16:35,703 INFO Epoch:79 train_loss:1.64148 +2025-04-18 02:16:36,572 INFO Epoch:79 val_res:0.771429 +2025-04-18 02:16:42,066 INFO Epoch:80 train_loss:1.65630 +2025-04-18 02:16:43,004 INFO Epoch:80 val_res:0.742857 +2025-04-18 02:16:48,373 INFO Epoch:81 train_loss:1.59167 +2025-04-18 02:16:49,267 INFO Epoch:81 val_res:0.771429 +2025-04-18 02:16:54,513 INFO Epoch:82 train_loss:1.62388 +2025-04-18 02:16:55,365 INFO Epoch:82 val_res:0.752381 +2025-04-18 02:17:00,792 INFO Epoch:83 train_loss:1.62871 +2025-04-18 02:17:01,718 INFO Epoch:83 val_res:0.800000 +2025-04-18 02:17:01,718 INFO Saving best model at Epoch 83 +2025-04-18 02:17:09,107 INFO Epoch:84 train_loss:1.60769 +2025-04-18 02:17:10,006 INFO Epoch:84 val_res:0.800000 +2025-04-18 02:17:15,227 INFO Epoch:85 train_loss:1.67427 +2025-04-18 02:17:16,145 INFO Epoch:85 val_res:0.704762 +2025-04-18 02:17:21,476 INFO Epoch:86 train_loss:1.61333 +2025-04-18 02:17:22,424 INFO Epoch:86 val_res:0.809524 +2025-04-18 02:17:22,424 INFO Saving best model at Epoch 86 +2025-04-18 02:17:29,763 INFO Epoch:87 train_loss:1.56818 +2025-04-18 02:17:30,580 INFO Epoch:87 val_res:0.800000 +2025-04-18 02:17:36,270 INFO Epoch:88 train_loss:1.63791 +2025-04-18 02:17:37,225 INFO Epoch:88 val_res:0.742857 +2025-04-18 02:17:42,912 INFO Epoch:89 train_loss:1.58068 +2025-04-18 02:17:43,792 INFO Epoch:89 val_res:0.723810 +2025-04-18 02:17:48,999 INFO Epoch:90 train_loss:1.56957 +2025-04-18 02:17:49,864 INFO Epoch:90 val_res:0.761905 +2025-04-18 02:17:54,958 INFO Epoch:91 train_loss:1.55027 +2025-04-18 02:17:55,861 INFO Epoch:91 val_res:0.752381 +2025-04-18 02:18:01,827 INFO Epoch:92 train_loss:1.53301 +2025-04-18 02:18:02,703 INFO Epoch:92 val_res:0.723810 +2025-04-18 02:18:08,220 INFO Epoch:93 train_loss:1.52874 +2025-04-18 02:18:09,121 INFO Epoch:93 val_res:0.819048 +2025-04-18 02:18:09,122 INFO Saving best model at Epoch 93 +2025-04-18 02:18:16,425 INFO Epoch:94 train_loss:1.49914 +2025-04-18 02:18:17,320 INFO Epoch:94 val_res:0.790476 +2025-04-18 02:18:22,679 INFO Epoch:95 train_loss:1.49462 +2025-04-18 02:18:23,737 INFO Epoch:95 val_res:0.809524 +2025-04-18 02:18:29,197 INFO Epoch:96 train_loss:1.44943 +2025-04-18 02:18:30,259 INFO Epoch:96 val_res:0.771429 +2025-04-18 02:18:35,784 INFO Epoch:97 train_loss:1.51112 +2025-04-18 02:18:36,824 INFO Epoch:97 val_res:0.742857 +2025-04-18 02:18:42,297 INFO Epoch:98 train_loss:1.56470 +2025-04-18 02:18:43,196 INFO Epoch:98 val_res:0.714286 +2025-04-18 02:18:49,212 INFO Epoch:99 train_loss:1.60568 +2025-04-18 02:18:50,129 INFO Epoch:99 val_res:0.800000 +2025-04-18 02:18:57,946 INFO ===================================== +2025-04-18 02:18:57,946 INFO Start testing... +2025-04-18 02:18:57,946 INFO ===================================== +2025-04-18 02:19:02,648 INFO Incremental step 0 Testing res: 0.788462 +2025-04-18 02:19:02,650 INFO Incremental step: 1 +2025-04-18 02:20:57,824 INFO Epoch:0 train_loss:5.69975 +2025-04-18 02:24:10,632 INFO Epoch:0 val_res:0.389671 +2025-04-18 02:24:10,633 INFO Saving best model at Epoch 0 +2025-04-18 02:24:19,449 INFO Epoch:1 train_loss:5.22986 +2025-04-18 02:24:20,839 INFO Epoch:1 val_res:0.389671 +2025-04-18 02:24:27,489 INFO Epoch:2 train_loss:4.61064 +2025-04-18 02:24:29,010 INFO Epoch:2 val_res:0.399061 +2025-04-18 02:24:29,010 INFO Saving best model at Epoch 2 +2025-04-18 02:24:36,302 INFO Epoch:3 train_loss:5.09704 +2025-04-18 02:24:37,806 INFO Epoch:3 val_res:0.352113 +2025-04-18 02:24:43,109 INFO Epoch:4 train_loss:5.03624 +2025-04-18 02:24:44,557 INFO Epoch:4 val_res:0.384977 +2025-04-18 02:24:49,831 INFO Epoch:5 train_loss:4.17505 +2025-04-18 02:24:51,329 INFO Epoch:5 val_res:0.413146 +2025-04-18 02:24:51,330 INFO Saving best model at Epoch 5 +2025-04-18 02:24:58,721 INFO Epoch:6 train_loss:3.76301 +2025-04-18 02:25:00,074 INFO Epoch:6 val_res:0.422535 +2025-04-18 02:25:00,074 INFO Saving best model at Epoch 6 +2025-04-18 02:25:07,240 INFO Epoch:7 train_loss:3.81831 +2025-04-18 02:25:08,735 INFO Epoch:7 val_res:0.408451 +2025-04-18 02:25:14,199 INFO Epoch:8 train_loss:3.59431 +2025-04-18 02:25:15,615 INFO Epoch:8 val_res:0.403756 +2025-04-18 02:25:20,715 INFO Epoch:9 train_loss:3.47202 +2025-04-18 02:25:22,105 INFO Epoch:9 val_res:0.417840 +2025-04-18 02:25:27,008 INFO Epoch:10 train_loss:3.36124 +2025-04-18 02:25:28,446 INFO Epoch:10 val_res:0.422535 +2025-04-18 02:25:34,013 INFO Epoch:11 train_loss:3.10037 +2025-04-18 02:25:35,425 INFO Epoch:11 val_res:0.417840 +2025-04-18 02:25:41,042 INFO Epoch:12 train_loss:3.15262 +2025-04-18 02:25:42,527 INFO Epoch:12 val_res:0.413146 +2025-04-18 02:25:48,045 INFO Epoch:13 train_loss:3.11889 +2025-04-18 02:25:49,530 INFO Epoch:13 val_res:0.417840 +2025-04-18 02:25:54,805 INFO Epoch:14 train_loss:3.38740 +2025-04-18 02:25:56,188 INFO Epoch:14 val_res:0.427230 +2025-04-18 02:25:56,188 INFO Saving best model at Epoch 14 +2025-04-18 02:26:03,145 INFO Epoch:15 train_loss:3.47676 +2025-04-18 02:26:04,600 INFO Epoch:15 val_res:0.431925 +2025-04-18 02:26:04,601 INFO Saving best model at Epoch 15 +2025-04-18 02:26:11,883 INFO Epoch:16 train_loss:3.38746 +2025-04-18 02:26:13,245 INFO Epoch:16 val_res:0.436620 +2025-04-18 02:26:13,245 INFO Saving best model at Epoch 16 +2025-04-18 02:26:20,402 INFO Epoch:17 train_loss:3.12140 +2025-04-18 02:26:21,860 INFO Epoch:17 val_res:0.413146 +2025-04-18 02:26:27,520 INFO Epoch:18 train_loss:3.30583 +2025-04-18 02:26:28,847 INFO Epoch:18 val_res:0.427230 +2025-04-18 02:26:34,038 INFO Epoch:19 train_loss:3.26191 +2025-04-18 02:26:35,457 INFO Epoch:19 val_res:0.441315 +2025-04-18 02:26:35,457 INFO Saving best model at Epoch 19 +2025-04-18 02:26:42,226 INFO Epoch:20 train_loss:2.98828 +2025-04-18 02:26:43,702 INFO Epoch:20 val_res:0.488263 +2025-04-18 02:26:43,703 INFO Saving best model at Epoch 20 +2025-04-18 02:26:51,034 INFO Epoch:21 train_loss:3.25021 +2025-04-18 02:26:52,445 INFO Epoch:21 val_res:0.413146 +2025-04-18 02:26:58,172 INFO Epoch:22 train_loss:3.18253 +2025-04-18 02:26:59,544 INFO Epoch:22 val_res:0.497653 +2025-04-18 02:26:59,544 INFO Saving best model at Epoch 22 +2025-04-18 02:27:06,552 INFO Epoch:23 train_loss:2.96706 +2025-04-18 02:27:07,918 INFO Epoch:23 val_res:0.474178 +2025-04-18 02:27:13,243 INFO Epoch:24 train_loss:2.90323 +2025-04-18 02:27:14,635 INFO Epoch:24 val_res:0.507042 +2025-04-18 02:27:14,635 INFO Saving best model at Epoch 24 +2025-04-18 02:27:21,225 INFO Epoch:25 train_loss:3.02959 +2025-04-18 02:27:22,547 INFO Epoch:25 val_res:0.464789 +2025-04-18 02:27:27,732 INFO Epoch:26 train_loss:2.84686 +2025-04-18 02:27:29,044 INFO Epoch:26 val_res:0.455399 +2025-04-18 02:27:34,448 INFO Epoch:27 train_loss:2.90790 +2025-04-18 02:27:35,798 INFO Epoch:27 val_res:0.507042 +2025-04-18 02:27:41,560 INFO Epoch:28 train_loss:2.74267 +2025-04-18 02:27:42,901 INFO Epoch:28 val_res:0.516432 +2025-04-18 02:27:42,901 INFO Saving best model at Epoch 28 +2025-04-18 02:27:50,830 INFO Epoch:29 train_loss:2.72203 +2025-04-18 02:27:52,158 INFO Epoch:29 val_res:0.474178 +2025-04-18 02:27:57,473 INFO Epoch:30 train_loss:2.74955 +2025-04-18 02:27:58,774 INFO Epoch:30 val_res:0.492958 +2025-04-18 02:28:03,876 INFO Epoch:31 train_loss:2.61788 +2025-04-18 02:28:05,229 INFO Epoch:31 val_res:0.544601 +2025-04-18 02:28:05,229 INFO Saving best model at Epoch 31 +2025-04-18 02:28:12,721 INFO Epoch:32 train_loss:2.62083 +2025-04-18 02:28:14,133 INFO Epoch:32 val_res:0.572770 +2025-04-18 02:28:14,133 INFO Saving best model at Epoch 32 +2025-04-18 02:28:22,150 INFO Epoch:33 train_loss:2.70424 +2025-04-18 02:28:23,522 INFO Epoch:33 val_res:0.497653 +2025-04-18 02:28:29,043 INFO Epoch:34 train_loss:2.64233 +2025-04-18 02:28:30,404 INFO Epoch:34 val_res:0.492958 +2025-04-18 02:28:35,588 INFO Epoch:35 train_loss:2.56006 +2025-04-18 02:28:37,034 INFO Epoch:35 val_res:0.549296 +2025-04-18 02:28:42,109 INFO Epoch:36 train_loss:2.67292 +2025-04-18 02:28:43,439 INFO Epoch:36 val_res:0.521127 +2025-04-18 02:28:48,854 INFO Epoch:37 train_loss:2.63355 +2025-04-18 02:28:50,258 INFO Epoch:37 val_res:0.525822 +2025-04-18 02:28:55,911 INFO Epoch:38 train_loss:2.56647 +2025-04-18 02:28:57,181 INFO Epoch:38 val_res:0.521127 +2025-04-18 02:29:02,707 INFO Epoch:39 train_loss:2.74135 +2025-04-18 02:29:04,139 INFO Epoch:39 val_res:0.563380 +2025-04-18 02:29:09,161 INFO Epoch:40 train_loss:2.68552 +2025-04-18 02:29:10,533 INFO Epoch:40 val_res:0.549296 +2025-04-18 02:29:15,821 INFO Epoch:41 train_loss:2.54054 +2025-04-18 02:29:17,181 INFO Epoch:41 val_res:0.535211 +2025-04-18 02:29:22,608 INFO Epoch:42 train_loss:2.45710 +2025-04-18 02:29:24,034 INFO Epoch:42 val_res:0.582160 +2025-04-18 02:29:24,035 INFO Saving best model at Epoch 42 +2025-04-18 02:29:32,018 INFO Epoch:43 train_loss:2.32814 +2025-04-18 02:29:33,346 INFO Epoch:43 val_res:0.535211 +2025-04-18 02:29:38,952 INFO Epoch:44 train_loss:2.29140 +2025-04-18 02:29:40,314 INFO Epoch:44 val_res:0.535211 +2025-04-18 02:29:45,464 INFO Epoch:45 train_loss:2.25586 +2025-04-18 02:29:46,834 INFO Epoch:45 val_res:0.535211 +2025-04-18 02:29:51,840 INFO Epoch:46 train_loss:2.18508 +2025-04-18 02:29:53,269 INFO Epoch:46 val_res:0.544601 +2025-04-18 02:29:58,576 INFO Epoch:47 train_loss:2.17375 +2025-04-18 02:29:59,931 INFO Epoch:47 val_res:0.568075 +2025-04-18 02:30:05,450 INFO Epoch:48 train_loss:2.11755 +2025-04-18 02:30:06,853 INFO Epoch:48 val_res:0.572770 +2025-04-18 02:30:12,328 INFO Epoch:49 train_loss:2.14436 +2025-04-18 02:30:13,725 INFO Epoch:49 val_res:0.553991 +2025-04-18 02:30:18,832 INFO Epoch:50 train_loss:2.06758 +2025-04-18 02:30:20,183 INFO Epoch:50 val_res:0.586854 +2025-04-18 02:30:20,184 INFO Saving best model at Epoch 50 +2025-04-18 02:30:26,947 INFO Epoch:51 train_loss:2.05698 +2025-04-18 02:30:28,451 INFO Epoch:51 val_res:0.553991 +2025-04-18 02:30:33,749 INFO Epoch:52 train_loss:1.97335 +2025-04-18 02:30:35,152 INFO Epoch:52 val_res:0.572770 +2025-04-18 02:30:40,768 INFO Epoch:53 train_loss:1.96491 +2025-04-18 02:30:42,212 INFO Epoch:53 val_res:0.596244 +2025-04-18 02:30:42,212 INFO Saving best model at Epoch 53 +2025-04-18 02:30:49,333 INFO Epoch:54 train_loss:1.89223 +2025-04-18 02:30:50,706 INFO Epoch:54 val_res:0.591549 +2025-04-18 02:30:55,756 INFO Epoch:55 train_loss:1.88526 +2025-04-18 02:30:57,273 INFO Epoch:55 val_res:0.563380 +2025-04-18 02:31:02,399 INFO Epoch:56 train_loss:1.86683 +2025-04-18 02:31:03,749 INFO Epoch:56 val_res:0.586854 +2025-04-18 02:31:08,877 INFO Epoch:57 train_loss:1.92619 +2025-04-18 02:31:10,432 INFO Epoch:57 val_res:0.568075 +2025-04-18 02:31:15,954 INFO Epoch:58 train_loss:1.91856 +2025-04-18 02:31:17,389 INFO Epoch:58 val_res:0.553991 +2025-04-18 02:31:23,166 INFO Epoch:59 train_loss:1.96989 +2025-04-18 02:31:24,534 INFO Epoch:59 val_res:0.582160 +2025-04-18 02:31:29,789 INFO Epoch:60 train_loss:1.88262 +2025-04-18 02:31:31,198 INFO Epoch:60 val_res:0.596244 +2025-04-18 02:31:36,363 INFO Epoch:61 train_loss:1.92759 +2025-04-18 02:31:37,791 INFO Epoch:61 val_res:0.596244 +2025-04-18 02:31:43,149 INFO Epoch:62 train_loss:1.90105 +2025-04-18 02:31:44,580 INFO Epoch:62 val_res:0.577465 +2025-04-18 02:31:50,210 INFO Epoch:63 train_loss:1.97014 +2025-04-18 02:31:51,574 INFO Epoch:63 val_res:0.582160 +2025-04-18 02:31:57,315 INFO Epoch:64 train_loss:2.07777 +2025-04-18 02:31:58,781 INFO Epoch:64 val_res:0.563380 +2025-04-18 02:32:03,816 INFO Epoch:65 train_loss:2.04507 +2025-04-18 02:32:05,202 INFO Epoch:65 val_res:0.577465 +2025-04-18 02:32:10,463 INFO Epoch:66 train_loss:1.82239 +2025-04-18 02:32:11,955 INFO Epoch:66 val_res:0.558685 +2025-04-18 02:32:17,427 INFO Epoch:67 train_loss:1.85564 +2025-04-18 02:32:18,853 INFO Epoch:67 val_res:0.577465 +2025-04-18 02:32:24,353 INFO Epoch:68 train_loss:1.97975 +2025-04-18 02:32:25,782 INFO Epoch:68 val_res:0.563380 +2025-04-18 02:32:31,747 INFO Epoch:69 train_loss:1.89124 +2025-04-18 02:32:33,238 INFO Epoch:69 val_res:0.558685 +2025-04-18 02:32:38,616 INFO Epoch:70 train_loss:1.88519 +2025-04-18 02:32:40,033 INFO Epoch:70 val_res:0.586854 +2025-04-18 02:32:45,324 INFO Epoch:71 train_loss:1.92499 +2025-04-18 02:32:46,698 INFO Epoch:71 val_res:0.586854 +2025-04-18 02:32:52,137 INFO Epoch:72 train_loss:1.98159 +2025-04-18 02:32:53,483 INFO Epoch:72 val_res:0.544601 +2025-04-18 02:32:59,234 INFO Epoch:73 train_loss:1.93870 +2025-04-18 02:33:00,602 INFO Epoch:73 val_res:0.582160 +2025-04-18 02:33:06,165 INFO Epoch:74 train_loss:1.70884 +2025-04-18 02:33:07,463 INFO Epoch:74 val_res:0.605634 +2025-04-18 02:33:07,463 INFO Saving best model at Epoch 74 +2025-04-18 02:33:14,988 INFO Epoch:75 train_loss:1.79875 +2025-04-18 02:33:16,335 INFO Epoch:75 val_res:0.605634 +2025-04-18 02:33:21,726 INFO Epoch:76 train_loss:1.66267 +2025-04-18 02:33:23,117 INFO Epoch:76 val_res:0.596244 +2025-04-18 02:33:28,607 INFO Epoch:77 train_loss:1.70219 +2025-04-18 02:33:29,948 INFO Epoch:77 val_res:0.600939 +2025-04-18 02:33:35,588 INFO Epoch:78 train_loss:1.67503 +2025-04-18 02:33:36,955 INFO Epoch:78 val_res:0.600939 +2025-04-18 02:33:42,521 INFO Epoch:79 train_loss:1.62583 +2025-04-18 02:33:43,910 INFO Epoch:79 val_res:0.591549 +2025-04-18 02:33:48,979 INFO Epoch:80 train_loss:1.61104 +2025-04-18 02:33:50,374 INFO Epoch:80 val_res:0.577465 +2025-04-18 02:33:55,378 INFO Epoch:81 train_loss:1.60215 +2025-04-18 02:33:56,763 INFO Epoch:81 val_res:0.582160 +2025-04-18 02:34:02,172 INFO Epoch:82 train_loss:1.53848 +2025-04-18 02:34:03,549 INFO Epoch:82 val_res:0.615023 +2025-04-18 02:34:03,549 INFO Saving best model at Epoch 82 +2025-04-18 02:34:11,875 INFO Epoch:83 train_loss:1.50278 +2025-04-18 02:34:13,247 INFO Epoch:83 val_res:0.600939 +2025-04-18 02:34:19,317 INFO Epoch:84 train_loss:1.47829 +2025-04-18 02:34:20,702 INFO Epoch:84 val_res:0.633803 +2025-04-18 02:34:20,702 INFO Saving best model at Epoch 84 +2025-04-18 02:34:28,656 INFO Epoch:85 train_loss:1.48651 +2025-04-18 02:34:30,103 INFO Epoch:85 val_res:0.600939 +2025-04-18 02:34:35,217 INFO Epoch:86 train_loss:1.55263 +2025-04-18 02:34:36,579 INFO Epoch:86 val_res:0.605634 +2025-04-18 02:34:41,956 INFO Epoch:87 train_loss:1.50470 +2025-04-18 02:34:43,543 INFO Epoch:87 val_res:0.591549 +2025-04-18 02:34:49,467 INFO Epoch:88 train_loss:1.47728 +2025-04-18 02:34:50,847 INFO Epoch:88 val_res:0.605634 +2025-04-18 02:34:56,505 INFO Epoch:89 train_loss:1.48181 +2025-04-18 02:34:58,002 INFO Epoch:89 val_res:0.605634 +2025-04-18 02:35:03,221 INFO Epoch:90 train_loss:1.47682 +2025-04-18 02:35:04,607 INFO Epoch:90 val_res:0.615023 +2025-04-18 02:35:10,028 INFO Epoch:91 train_loss:1.51362 +2025-04-18 02:35:11,405 INFO Epoch:91 val_res:0.596244 +2025-04-18 02:35:16,811 INFO Epoch:92 train_loss:1.50481 +2025-04-18 02:35:18,185 INFO Epoch:92 val_res:0.586854 +2025-04-18 02:35:23,727 INFO Epoch:93 train_loss:1.42305 +2025-04-18 02:35:25,185 INFO Epoch:93 val_res:0.596244 +2025-04-18 02:35:30,544 INFO Epoch:94 train_loss:1.48468 +2025-04-18 02:35:31,974 INFO Epoch:94 val_res:0.605634 +2025-04-18 02:35:37,394 INFO Epoch:95 train_loss:1.41672 +2025-04-18 02:35:38,765 INFO Epoch:95 val_res:0.624413 +2025-04-18 02:35:43,988 INFO Epoch:96 train_loss:1.35712 +2025-04-18 02:35:45,367 INFO Epoch:96 val_res:0.638498 +2025-04-18 02:35:45,367 INFO Saving best model at Epoch 96 +2025-04-18 02:35:53,348 INFO Epoch:97 train_loss:1.40286 +2025-04-18 02:35:54,704 INFO Epoch:97 val_res:0.600939 +2025-04-18 02:36:00,721 INFO Epoch:98 train_loss:1.38770 +2025-04-18 02:36:01,962 INFO Epoch:98 val_res:0.596244 +2025-04-18 02:36:07,647 INFO Epoch:99 train_loss:1.28778 +2025-04-18 02:36:09,201 INFO Epoch:99 val_res:0.615023 +2025-04-18 02:36:17,040 INFO ===================================== +2025-04-18 02:36:17,040 INFO Start testing... +2025-04-18 02:36:17,041 INFO ===================================== +2025-04-18 02:36:22,164 INFO Incremental step 1 Testing res: 0.633333 +2025-04-18 02:36:22,165 INFO forgetting: 0.201923 +2025-04-18 02:36:22,167 INFO Incremental step: 2 +2025-04-18 02:39:07,346 INFO Epoch:0 train_loss:5.69106 +2025-04-18 02:39:25,205 INFO Epoch:0 val_res:0.387821 +2025-04-18 02:39:25,206 INFO Saving best model at Epoch 0 +2025-04-18 02:39:35,852 INFO Epoch:1 train_loss:5.50981 +2025-04-18 02:39:37,977 INFO Epoch:1 val_res:0.419872 +2025-04-18 02:39:37,978 INFO Saving best model at Epoch 1 +2025-04-18 02:39:45,745 INFO Epoch:2 train_loss:5.10274 +2025-04-18 02:39:47,848 INFO Epoch:2 val_res:0.423077 +2025-04-18 02:39:47,849 INFO Saving best model at Epoch 2 +2025-04-18 02:39:55,703 INFO Epoch:3 train_loss:5.69465 +2025-04-18 02:39:57,874 INFO Epoch:3 val_res:0.439103 +2025-04-18 02:39:57,874 INFO Saving best model at Epoch 3 +2025-04-18 02:40:05,710 INFO Epoch:4 train_loss:4.58231 +2025-04-18 02:40:07,750 INFO Epoch:4 val_res:0.448718 +2025-04-18 02:40:07,751 INFO Saving best model at Epoch 4 +2025-04-18 02:40:15,155 INFO Epoch:5 train_loss:4.33153 +2025-04-18 02:40:17,370 INFO Epoch:5 val_res:0.423077 +2025-04-18 02:40:22,545 INFO Epoch:6 train_loss:5.15290 +2025-04-18 02:40:24,708 INFO Epoch:6 val_res:0.423077 +2025-04-18 02:40:30,027 INFO Epoch:7 train_loss:5.14839 +2025-04-18 02:40:32,093 INFO Epoch:7 val_res:0.416667 +2025-04-18 02:40:37,439 INFO Epoch:8 train_loss:5.45497 +2025-04-18 02:40:39,495 INFO Epoch:8 val_res:0.432692 +2025-04-18 02:40:44,998 INFO Epoch:9 train_loss:5.18716 +2025-04-18 02:40:47,053 INFO Epoch:9 val_res:0.407051 +2025-04-18 02:40:52,506 INFO Epoch:10 train_loss:4.25461 +2025-04-18 02:40:54,559 INFO Epoch:10 val_res:0.426282 +2025-04-18 02:41:00,153 INFO Epoch:11 train_loss:3.90226 +2025-04-18 02:41:02,122 INFO Epoch:11 val_res:0.445513 +2025-04-18 02:41:07,806 INFO Epoch:12 train_loss:4.26356 +2025-04-18 02:41:09,852 INFO Epoch:12 val_res:0.410256 +2025-04-18 02:41:15,033 INFO Epoch:13 train_loss:3.55489 +2025-04-18 02:41:17,061 INFO Epoch:13 val_res:0.426282 +2025-04-18 02:41:22,343 INFO Epoch:14 train_loss:3.61302 +2025-04-18 02:41:24,460 INFO Epoch:14 val_res:0.464744 +2025-04-18 02:41:24,460 INFO Saving best model at Epoch 14 +2025-04-18 02:41:31,588 INFO Epoch:15 train_loss:3.17989 +2025-04-18 02:41:33,602 INFO Epoch:15 val_res:0.442308 +2025-04-18 02:41:39,288 INFO Epoch:16 train_loss:3.67866 +2025-04-18 02:41:41,151 INFO Epoch:16 val_res:0.413462 +2025-04-18 02:41:46,768 INFO Epoch:17 train_loss:3.90100 +2025-04-18 02:41:48,684 INFO Epoch:17 val_res:0.461538 +2025-04-18 02:41:54,113 INFO Epoch:18 train_loss:3.87724 +2025-04-18 02:41:56,062 INFO Epoch:18 val_res:0.397436 +2025-04-18 02:42:01,559 INFO Epoch:19 train_loss:3.65477 +2025-04-18 02:42:03,591 INFO Epoch:19 val_res:0.416667 +2025-04-18 02:42:08,932 INFO Epoch:20 train_loss:3.25544 +2025-04-18 02:42:10,871 INFO Epoch:20 val_res:0.435897 +2025-04-18 02:42:16,183 INFO Epoch:21 train_loss:3.30387 +2025-04-18 02:42:18,112 INFO Epoch:21 val_res:0.432692 +2025-04-18 02:42:23,372 INFO Epoch:22 train_loss:3.37743 +2025-04-18 02:42:25,296 INFO Epoch:22 val_res:0.423077 +2025-04-18 02:42:30,626 INFO Epoch:23 train_loss:3.53077 +2025-04-18 02:42:32,498 INFO Epoch:23 val_res:0.426282 +2025-04-18 02:42:37,933 INFO Epoch:24 train_loss:3.33411 +2025-04-18 02:42:39,885 INFO Epoch:24 val_res:0.426282 +2025-04-18 02:42:45,134 INFO Epoch:25 train_loss:3.02028 +2025-04-18 02:42:47,036 INFO Epoch:25 val_res:0.410256 +2025-04-18 02:42:52,814 INFO Epoch:26 train_loss:3.57277 +2025-04-18 02:42:54,816 INFO Epoch:26 val_res:0.439103 +2025-04-18 02:43:00,375 INFO Epoch:27 train_loss:3.23444 +2025-04-18 02:43:02,311 INFO Epoch:27 val_res:0.448718 +2025-04-18 02:43:07,538 INFO Epoch:28 train_loss:3.22558 +2025-04-18 02:43:09,497 INFO Epoch:28 val_res:0.451923 +2025-04-18 02:43:14,995 INFO Epoch:29 train_loss:2.93064 +2025-04-18 02:43:16,928 INFO Epoch:29 val_res:0.455128 +2025-04-18 02:43:22,220 INFO Epoch:30 train_loss:2.80216 +2025-04-18 02:43:24,118 INFO Epoch:30 val_res:0.448718 +2025-04-18 02:43:29,506 INFO Epoch:31 train_loss:2.52155 +2025-04-18 02:43:31,487 INFO Epoch:31 val_res:0.458333 +2025-04-18 02:43:37,082 INFO Epoch:32 train_loss:2.62435 +2025-04-18 02:43:39,077 INFO Epoch:32 val_res:0.426282 +2025-04-18 02:43:44,601 INFO Epoch:33 train_loss:2.52277 +2025-04-18 02:43:46,571 INFO Epoch:33 val_res:0.419872 +2025-04-18 02:43:52,342 INFO Epoch:34 train_loss:2.64300 +2025-04-18 02:43:54,330 INFO Epoch:34 val_res:0.467949 +2025-04-18 02:43:54,330 INFO Saving best model at Epoch 34 +2025-04-18 02:44:01,358 INFO Epoch:35 train_loss:2.52300 +2025-04-18 02:44:03,306 INFO Epoch:35 val_res:0.461538 +2025-04-18 02:44:08,903 INFO Epoch:36 train_loss:2.52978 +2025-04-18 02:44:10,830 INFO Epoch:36 val_res:0.426282 +2025-04-18 02:44:16,356 INFO Epoch:37 train_loss:2.49893 +2025-04-18 02:44:18,280 INFO Epoch:37 val_res:0.439103 +2025-04-18 02:44:23,909 INFO Epoch:38 train_loss:2.44187 +2025-04-18 02:44:25,970 INFO Epoch:38 val_res:0.487179 +2025-04-18 02:44:25,970 INFO Saving best model at Epoch 38 +2025-04-18 02:44:32,828 INFO Epoch:39 train_loss:2.46998 +2025-04-18 02:44:34,798 INFO Epoch:39 val_res:0.394231 +2025-04-18 02:44:40,047 INFO Epoch:40 train_loss:3.12447 +2025-04-18 02:44:42,072 INFO Epoch:40 val_res:0.448718 +2025-04-18 02:44:47,468 INFO Epoch:41 train_loss:3.22085 +2025-04-18 02:44:49,506 INFO Epoch:41 val_res:0.445513 +2025-04-18 02:44:54,934 INFO Epoch:42 train_loss:2.48964 +2025-04-18 02:44:56,892 INFO Epoch:42 val_res:0.439103 +2025-04-18 02:45:02,248 INFO Epoch:43 train_loss:3.17382 +2025-04-18 02:45:04,225 INFO Epoch:43 val_res:0.445513 +2025-04-18 02:45:09,692 INFO Epoch:44 train_loss:2.71422 +2025-04-18 02:45:11,571 INFO Epoch:44 val_res:0.451923 +2025-04-18 02:45:16,891 INFO Epoch:45 train_loss:2.43911 +2025-04-18 02:45:18,756 INFO Epoch:45 val_res:0.458333 +2025-04-18 02:45:24,136 INFO Epoch:46 train_loss:2.42714 +2025-04-18 02:45:26,032 INFO Epoch:46 val_res:0.480769 +2025-04-18 02:45:31,267 INFO Epoch:47 train_loss:2.32314 +2025-04-18 02:45:33,255 INFO Epoch:47 val_res:0.455128 +2025-04-18 02:45:38,676 INFO Epoch:48 train_loss:2.39152 +2025-04-18 02:45:40,627 INFO Epoch:48 val_res:0.467949 +2025-04-18 02:45:46,310 INFO Epoch:49 train_loss:2.39984 +2025-04-18 02:45:49,208 INFO Epoch:49 val_res:0.467949 +2025-04-18 02:45:55,088 INFO Epoch:50 train_loss:2.29076 +2025-04-18 02:45:57,641 INFO Epoch:50 val_res:0.448718 +2025-04-18 02:46:04,117 INFO Epoch:51 train_loss:2.37110 +2025-04-18 02:46:06,424 INFO Epoch:51 val_res:0.455128 +2025-04-18 02:46:12,340 INFO Epoch:52 train_loss:2.20993 +2025-04-18 02:46:14,461 INFO Epoch:52 val_res:0.419872 +2025-04-18 02:46:20,519 INFO Epoch:53 train_loss:2.46514 +2025-04-18 02:46:22,522 INFO Epoch:53 val_res:0.458333 +2025-04-18 02:46:28,560 INFO Epoch:54 train_loss:2.40672 +2025-04-18 02:46:31,048 INFO Epoch:54 val_res:0.464744 +2025-04-18 02:46:38,530 INFO Epoch:55 train_loss:2.87895 +2025-04-18 02:46:41,081 INFO Epoch:55 val_res:0.483974 +2025-04-18 02:46:46,998 INFO Epoch:56 train_loss:2.53967 +2025-04-18 02:46:49,119 INFO Epoch:56 val_res:0.451923 +2025-04-18 02:46:54,704 INFO Epoch:57 train_loss:2.25815 +2025-04-18 02:46:56,897 INFO Epoch:57 val_res:0.461538 +2025-04-18 02:47:02,941 INFO Epoch:58 train_loss:2.16800 +2025-04-18 02:47:05,441 INFO Epoch:58 val_res:0.493590 +2025-04-18 02:47:05,441 INFO Saving best model at Epoch 58 +2025-04-18 02:47:13,748 INFO Epoch:59 train_loss:2.13594 +2025-04-18 02:47:16,029 INFO Epoch:59 val_res:0.445513 +2025-04-18 02:47:21,946 INFO Epoch:60 train_loss:2.12958 +2025-04-18 02:47:23,918 INFO Epoch:60 val_res:0.493590 +2025-04-18 02:47:29,908 INFO Epoch:61 train_loss:2.08290 +2025-04-18 02:47:32,327 INFO Epoch:61 val_res:0.451923 +2025-04-18 02:47:38,918 INFO Epoch:62 train_loss:2.19771 +2025-04-18 02:47:41,319 INFO Epoch:62 val_res:0.471154 +2025-04-18 02:47:47,390 INFO Epoch:63 train_loss:2.05461 +2025-04-18 02:47:49,437 INFO Epoch:63 val_res:0.483974 +2025-04-18 02:47:55,340 INFO Epoch:64 train_loss:2.03223 +2025-04-18 02:47:57,728 INFO Epoch:64 val_res:0.493590 +2025-04-18 02:48:03,356 INFO Epoch:65 train_loss:2.10911 +2025-04-18 02:48:05,509 INFO Epoch:65 val_res:0.461538 +2025-04-18 02:48:12,113 INFO Epoch:66 train_loss:2.08396 +2025-04-18 02:48:14,326 INFO Epoch:66 val_res:0.480769 +2025-04-18 02:48:20,589 INFO Epoch:67 train_loss:1.99289 +2025-04-18 02:48:22,746 INFO Epoch:67 val_res:0.496795 +2025-04-18 02:48:22,746 INFO Saving best model at Epoch 67 +2025-04-18 02:48:30,959 INFO Epoch:68 train_loss:1.99340 +2025-04-18 02:48:33,090 INFO Epoch:68 val_res:0.471154 +2025-04-18 02:48:39,602 INFO Epoch:69 train_loss:1.91180 +2025-04-18 02:48:41,866 INFO Epoch:69 val_res:0.487179 +2025-04-18 02:48:47,503 INFO Epoch:70 train_loss:1.92816 +2025-04-18 02:48:49,444 INFO Epoch:70 val_res:0.487179 +2025-04-18 02:48:55,726 INFO Epoch:71 train_loss:1.83739 +2025-04-18 02:48:58,041 INFO Epoch:71 val_res:0.477564 +2025-04-18 02:49:04,157 INFO Epoch:72 train_loss:1.76795 +2025-04-18 02:49:06,173 INFO Epoch:72 val_res:0.506410 +2025-04-18 02:49:06,173 INFO Saving best model at Epoch 72 +2025-04-18 02:49:14,292 INFO Epoch:73 train_loss:1.84084 +2025-04-18 02:49:16,540 INFO Epoch:73 val_res:0.535256 +2025-04-18 02:49:16,540 INFO Saving best model at Epoch 73 +2025-04-18 02:49:25,560 INFO Epoch:74 train_loss:1.70289 +2025-04-18 02:49:27,911 INFO Epoch:74 val_res:0.500000 +2025-04-18 02:49:33,894 INFO Epoch:75 train_loss:1.73701 +2025-04-18 02:49:36,154 INFO Epoch:75 val_res:0.493590 +2025-04-18 02:49:42,005 INFO Epoch:76 train_loss:1.65681 +2025-04-18 02:49:44,087 INFO Epoch:76 val_res:0.483974 +2025-04-18 02:49:50,560 INFO Epoch:77 train_loss:1.64015 +2025-04-18 02:49:52,849 INFO Epoch:77 val_res:0.500000 +2025-04-18 02:49:59,209 INFO Epoch:78 train_loss:1.68202 +2025-04-18 02:50:01,321 INFO Epoch:78 val_res:0.496795 +2025-04-18 02:50:07,553 INFO Epoch:79 train_loss:1.66301 +2025-04-18 02:50:09,867 INFO Epoch:79 val_res:0.509615 +2025-04-18 02:50:15,936 INFO Epoch:80 train_loss:1.73347 +2025-04-18 02:50:18,335 INFO Epoch:80 val_res:0.500000 +2025-04-18 02:50:24,241 INFO Epoch:81 train_loss:1.63096 +2025-04-18 02:50:26,494 INFO Epoch:81 val_res:0.496795 +2025-04-18 02:50:32,227 INFO Epoch:82 train_loss:1.67670 +2025-04-18 02:50:34,313 INFO Epoch:82 val_res:0.503205 +2025-04-18 02:50:40,254 INFO Epoch:83 train_loss:1.65076 +2025-04-18 02:50:42,346 INFO Epoch:83 val_res:0.532051 +2025-04-18 02:50:49,211 INFO Epoch:84 train_loss:1.68847 +2025-04-18 02:50:51,613 INFO Epoch:84 val_res:0.509615 +2025-04-18 02:50:58,248 INFO Epoch:85 train_loss:1.57422 +2025-04-18 02:51:00,539 INFO Epoch:85 val_res:0.493590 +2025-04-18 02:51:06,555 INFO Epoch:86 train_loss:1.55817 +2025-04-18 02:51:08,746 INFO Epoch:86 val_res:0.503205 +2025-04-18 02:51:14,682 INFO Epoch:87 train_loss:1.54397 +2025-04-18 02:51:16,656 INFO Epoch:87 val_res:0.496795 +2025-04-18 02:51:23,515 INFO Epoch:88 train_loss:1.53895 +2025-04-18 02:51:25,952 INFO Epoch:88 val_res:0.509615 +2025-04-18 02:51:32,228 INFO Epoch:89 train_loss:1.60387 +2025-04-18 02:51:34,416 INFO Epoch:89 val_res:0.509615 +2025-04-18 02:51:40,416 INFO Epoch:90 train_loss:1.45527 +2025-04-18 02:51:42,607 INFO Epoch:90 val_res:0.516026 +2025-04-18 02:51:48,583 INFO Epoch:91 train_loss:1.46436 +2025-04-18 02:51:50,695 INFO Epoch:91 val_res:0.490385 +2025-04-18 02:51:57,737 INFO Epoch:92 train_loss:1.52383 +2025-04-18 02:51:59,953 INFO Epoch:92 val_res:0.516026 +2025-04-18 02:52:06,353 INFO Epoch:93 train_loss:1.47666 +2025-04-18 02:52:08,463 INFO Epoch:93 val_res:0.493590 +2025-04-18 02:52:14,332 INFO Epoch:94 train_loss:1.52851 +2025-04-18 02:52:16,632 INFO Epoch:94 val_res:0.512821 +2025-04-18 02:52:22,918 INFO Epoch:95 train_loss:1.48866 +2025-04-18 02:52:25,616 INFO Epoch:95 val_res:0.512821 +2025-04-18 02:52:32,121 INFO Epoch:96 train_loss:1.47352 +2025-04-18 02:52:34,703 INFO Epoch:96 val_res:0.496795 +2025-04-18 02:52:41,012 INFO Epoch:97 train_loss:1.57788 +2025-04-18 02:52:43,022 INFO Epoch:97 val_res:0.493590 +2025-04-18 02:52:49,253 INFO Epoch:98 train_loss:1.50324 +2025-04-18 02:52:51,256 INFO Epoch:98 val_res:0.519231 +2025-04-18 02:52:57,705 INFO Epoch:99 train_loss:1.74103 +2025-04-18 02:52:59,935 INFO Epoch:99 val_res:0.512821 +2025-04-18 02:53:07,953 INFO ===================================== +2025-04-18 02:53:07,953 INFO Start testing... +2025-04-18 02:53:07,953 INFO ===================================== +2025-04-18 02:53:15,903 INFO Incremental step 2 Testing res: 0.469841 +2025-04-18 02:53:15,905 INFO forgetting: 0.200562 +2025-04-18 02:53:15,906 INFO Incremental step: 3 +2025-04-18 02:53:38,464 INFO Epoch:0 train_loss:5.70956 +2025-04-18 02:53:57,786 INFO Epoch:0 val_res:0.429668 +2025-04-18 02:53:57,787 INFO Saving best model at Epoch 0 +2025-04-18 02:54:09,704 INFO Epoch:1 train_loss:4.71818 +2025-04-18 02:54:12,281 INFO Epoch:1 val_res:0.419437 +2025-04-18 02:54:16,992 INFO Epoch:2 train_loss:3.98383 +2025-04-18 02:54:19,472 INFO Epoch:2 val_res:0.409207 +2025-04-18 02:54:23,659 INFO Epoch:3 train_loss:3.38394 +2025-04-18 02:54:26,169 INFO Epoch:3 val_res:0.406650 +2025-04-18 02:54:30,511 INFO Epoch:4 train_loss:3.23143 +2025-04-18 02:54:32,964 INFO Epoch:4 val_res:0.419437 +2025-04-18 02:54:37,564 INFO Epoch:5 train_loss:2.97028 +2025-04-18 02:54:40,240 INFO Epoch:5 val_res:0.396419 +2025-04-18 02:54:44,370 INFO Epoch:6 train_loss:2.80065 +2025-04-18 02:54:47,076 INFO Epoch:6 val_res:0.401535 +2025-04-18 02:54:51,227 INFO Epoch:7 train_loss:2.84864 +2025-04-18 02:54:53,654 INFO Epoch:7 val_res:0.416880 +2025-04-18 02:54:57,677 INFO Epoch:8 train_loss:2.65473 +2025-04-18 02:55:00,163 INFO Epoch:8 val_res:0.409207 +2025-04-18 02:55:04,430 INFO Epoch:9 train_loss:2.59221 +2025-04-18 02:55:07,000 INFO Epoch:9 val_res:0.427110 +2025-04-18 02:55:10,949 INFO Epoch:10 train_loss:2.71454 +2025-04-18 02:55:13,904 INFO Epoch:10 val_res:0.401535 +2025-04-18 02:55:18,053 INFO Epoch:11 train_loss:2.74796 +2025-04-18 02:55:20,694 INFO Epoch:11 val_res:0.393862 +2025-04-18 02:55:24,804 INFO Epoch:12 train_loss:2.95413 +2025-04-18 02:55:27,285 INFO Epoch:12 val_res:0.421995 +2025-04-18 02:55:31,504 INFO Epoch:13 train_loss:2.90507 +2025-04-18 02:55:33,997 INFO Epoch:13 val_res:0.391304 +2025-04-18 02:55:38,091 INFO Epoch:14 train_loss:2.68177 +2025-04-18 02:55:40,594 INFO Epoch:14 val_res:0.442455 +2025-04-18 02:55:40,594 INFO Saving best model at Epoch 14 +2025-04-18 02:55:47,053 INFO Epoch:15 train_loss:2.57450 +2025-04-18 02:55:49,693 INFO Epoch:15 val_res:0.411765 +2025-04-18 02:55:53,769 INFO Epoch:16 train_loss:2.70590 +2025-04-18 02:55:56,166 INFO Epoch:16 val_res:0.414322 +2025-04-18 02:56:00,234 INFO Epoch:17 train_loss:2.50197 +2025-04-18 02:56:02,656 INFO Epoch:17 val_res:0.421995 +2025-04-18 02:56:07,202 INFO Epoch:18 train_loss:2.31894 +2025-04-18 02:56:09,823 INFO Epoch:18 val_res:0.414322 +2025-04-18 02:56:13,897 INFO Epoch:19 train_loss:2.43234 +2025-04-18 02:56:16,816 INFO Epoch:19 val_res:0.424552 +2025-04-18 02:56:21,201 INFO Epoch:20 train_loss:2.36049 +2025-04-18 02:56:23,687 INFO Epoch:20 val_res:0.398977 +2025-04-18 02:56:27,836 INFO Epoch:21 train_loss:2.23026 +2025-04-18 02:56:30,205 INFO Epoch:21 val_res:0.429668 +2025-04-18 02:56:34,230 INFO Epoch:22 train_loss:2.27857 +2025-04-18 02:56:36,773 INFO Epoch:22 val_res:0.370844 +2025-04-18 02:56:40,985 INFO Epoch:23 train_loss:2.30681 +2025-04-18 02:56:43,683 INFO Epoch:23 val_res:0.416880 +2025-04-18 02:56:48,254 INFO Epoch:24 train_loss:2.39430 +2025-04-18 02:56:50,959 INFO Epoch:24 val_res:0.406650 +2025-04-18 02:56:55,844 INFO Epoch:25 train_loss:2.21171 +2025-04-18 02:56:58,463 INFO Epoch:25 val_res:0.404092 +2025-04-18 02:57:02,848 INFO Epoch:26 train_loss:2.11245 +2025-04-18 02:57:05,314 INFO Epoch:26 val_res:0.416880 +2025-04-18 02:57:09,705 INFO Epoch:27 train_loss:2.06675 +2025-04-18 02:57:12,196 INFO Epoch:27 val_res:0.396419 +2025-04-18 02:57:16,561 INFO Epoch:28 train_loss:2.01792 +2025-04-18 02:57:19,196 INFO Epoch:28 val_res:0.424552 +2025-04-18 02:57:23,332 INFO Epoch:29 train_loss:2.16648 +2025-04-18 02:57:25,940 INFO Epoch:29 val_res:0.404092 +2025-04-18 02:57:30,364 INFO Epoch:30 train_loss:2.60047 +2025-04-18 02:57:32,974 INFO Epoch:30 val_res:0.411765 +2025-04-18 02:57:37,333 INFO Epoch:31 train_loss:2.11494 +2025-04-18 02:57:39,902 INFO Epoch:31 val_res:0.404092 +2025-04-18 02:57:44,530 INFO Epoch:32 train_loss:2.35005 +2025-04-18 02:57:46,940 INFO Epoch:32 val_res:0.396419 +2025-04-18 02:57:51,138 INFO Epoch:33 train_loss:2.50254 +2025-04-18 02:57:53,888 INFO Epoch:33 val_res:0.383632 +2025-04-18 02:57:57,960 INFO Epoch:34 train_loss:2.13241 +2025-04-18 02:58:00,490 INFO Epoch:34 val_res:0.411765 +2025-04-18 02:58:05,140 INFO Epoch:35 train_loss:2.12538 +2025-04-18 02:58:07,828 INFO Epoch:35 val_res:0.388747 +2025-04-18 02:58:12,355 INFO Epoch:36 train_loss:2.42588 +2025-04-18 02:58:14,936 INFO Epoch:36 val_res:0.424552 +2025-04-18 02:58:19,154 INFO Epoch:37 train_loss:2.21546 +2025-04-18 02:58:21,679 INFO Epoch:37 val_res:0.411765 +2025-04-18 02:58:25,827 INFO Epoch:38 train_loss:2.14396 +2025-04-18 02:58:28,665 INFO Epoch:38 val_res:0.419437 +2025-04-18 02:58:32,713 INFO Epoch:39 train_loss:2.19771 +2025-04-18 02:58:35,167 INFO Epoch:39 val_res:0.398977 +2025-04-18 02:58:39,707 INFO Epoch:40 train_loss:1.99194 +2025-04-18 02:58:42,562 INFO Epoch:40 val_res:0.406650 +2025-04-18 02:58:46,704 INFO Epoch:41 train_loss:1.98930 +2025-04-18 02:58:49,346 INFO Epoch:41 val_res:0.419437 +2025-04-18 02:58:53,372 INFO Epoch:42 train_loss:1.80334 +2025-04-18 02:58:55,871 INFO Epoch:42 val_res:0.424552 +2025-04-18 02:58:59,873 INFO Epoch:43 train_loss:1.94573 +2025-04-18 02:59:02,369 INFO Epoch:43 val_res:0.388747 +2025-04-18 02:59:06,495 INFO Epoch:44 train_loss:2.31231 +2025-04-18 02:59:08,844 INFO Epoch:44 val_res:0.414322 +2025-04-18 02:59:13,027 INFO Epoch:45 train_loss:1.89478 +2025-04-18 02:59:15,567 INFO Epoch:45 val_res:0.419437 +2025-04-18 02:59:20,221 INFO Epoch:46 train_loss:2.01757 +2025-04-18 02:59:22,758 INFO Epoch:46 val_res:0.398977 +2025-04-18 02:59:27,041 INFO Epoch:47 train_loss:2.13845 +2025-04-18 02:59:29,518 INFO Epoch:47 val_res:0.416880 +2025-04-18 02:59:33,658 INFO Epoch:48 train_loss:2.02714 +2025-04-18 02:59:36,202 INFO Epoch:48 val_res:0.391304 +2025-04-18 02:59:40,561 INFO Epoch:49 train_loss:2.05067 +2025-04-18 02:59:43,053 INFO Epoch:49 val_res:0.416880 +2025-04-18 02:59:46,960 INFO Epoch:50 train_loss:2.08917 +2025-04-18 02:59:49,646 INFO Epoch:50 val_res:0.398977 +2025-04-18 02:59:54,122 INFO Epoch:51 train_loss:2.08593 +2025-04-18 02:59:56,795 INFO Epoch:51 val_res:0.388747 +2025-04-18 03:00:01,228 INFO Epoch:52 train_loss:2.19475 +2025-04-18 03:00:03,658 INFO Epoch:52 val_res:0.434783 +2025-04-18 03:00:07,518 INFO Epoch:53 train_loss:2.13703 +2025-04-18 03:00:10,034 INFO Epoch:53 val_res:0.414322 +2025-04-18 03:00:14,010 INFO Epoch:54 train_loss:2.12095 +2025-04-18 03:00:16,508 INFO Epoch:54 val_res:0.396419 +2025-04-18 03:00:21,020 INFO Epoch:55 train_loss:2.20571 +2025-04-18 03:00:24,022 INFO Epoch:55 val_res:0.427110 +2025-04-18 03:00:28,190 INFO Epoch:56 train_loss:2.03623 +2025-04-18 03:00:30,771 INFO Epoch:56 val_res:0.409207 +2025-04-18 03:00:35,019 INFO Epoch:57 train_loss:1.77982 +2025-04-18 03:00:37,462 INFO Epoch:57 val_res:0.393862 +2025-04-18 03:00:41,476 INFO Epoch:58 train_loss:1.87481 +2025-04-18 03:00:44,201 INFO Epoch:58 val_res:0.419437 +2025-04-18 03:00:48,159 INFO Epoch:59 train_loss:1.81465 +2025-04-18 03:00:50,616 INFO Epoch:59 val_res:0.419437 +2025-04-18 03:00:55,046 INFO Epoch:60 train_loss:1.86625 +2025-04-18 03:00:57,524 INFO Epoch:60 val_res:0.404092 +2025-04-18 03:01:02,029 INFO Epoch:61 train_loss:1.97557 +2025-04-18 03:01:04,482 INFO Epoch:61 val_res:0.421995 +2025-04-18 03:01:08,685 INFO Epoch:62 train_loss:1.96323 +2025-04-18 03:01:11,267 INFO Epoch:62 val_res:0.419437 +2025-04-18 03:01:15,273 INFO Epoch:63 train_loss:1.78955 +2025-04-18 03:01:17,738 INFO Epoch:63 val_res:0.411765 +2025-04-18 03:01:22,107 INFO Epoch:64 train_loss:1.80279 +2025-04-18 03:01:24,671 INFO Epoch:64 val_res:0.429668 +2025-04-18 03:01:28,946 INFO Epoch:65 train_loss:1.76765 +2025-04-18 03:01:31,552 INFO Epoch:65 val_res:0.437340 +2025-04-18 03:01:35,671 INFO Epoch:66 train_loss:1.90898 +2025-04-18 03:01:38,306 INFO Epoch:66 val_res:0.419437 +2025-04-18 03:01:42,447 INFO Epoch:67 train_loss:1.94034 +2025-04-18 03:01:45,002 INFO Epoch:67 val_res:0.421995 +2025-04-18 03:01:49,210 INFO Epoch:68 train_loss:1.81623 +2025-04-18 03:01:51,768 INFO Epoch:68 val_res:0.447570 +2025-04-18 03:01:51,769 INFO Saving best model at Epoch 68 +2025-04-18 03:01:59,505 INFO Epoch:69 train_loss:1.64375 +2025-04-18 03:02:02,041 INFO Epoch:69 val_res:0.404092 +2025-04-18 03:02:06,192 INFO Epoch:70 train_loss:1.69132 +2025-04-18 03:02:08,646 INFO Epoch:70 val_res:0.442455 +2025-04-18 03:02:12,709 INFO Epoch:71 train_loss:1.75117 +2025-04-18 03:02:15,536 INFO Epoch:71 val_res:0.424552 +2025-04-18 03:02:19,753 INFO Epoch:72 train_loss:1.89126 +2025-04-18 03:02:22,208 INFO Epoch:72 val_res:0.419437 +2025-04-18 03:02:26,776 INFO Epoch:73 train_loss:1.79207 +2025-04-18 03:02:29,268 INFO Epoch:73 val_res:0.416880 +2025-04-18 03:02:33,433 INFO Epoch:74 train_loss:1.85189 +2025-04-18 03:02:35,973 INFO Epoch:74 val_res:0.401535 +2025-04-18 03:02:40,333 INFO Epoch:75 train_loss:2.13424 +2025-04-18 03:02:42,869 INFO Epoch:75 val_res:0.427110 +2025-04-18 03:02:47,219 INFO Epoch:76 train_loss:1.96950 +2025-04-18 03:02:49,840 INFO Epoch:76 val_res:0.401535 +2025-04-18 03:02:53,988 INFO Epoch:77 train_loss:1.79944 +2025-04-18 03:02:56,538 INFO Epoch:77 val_res:0.429668 +2025-04-18 03:03:00,872 INFO Epoch:78 train_loss:1.78694 +2025-04-18 03:03:03,391 INFO Epoch:78 val_res:0.427110 +2025-04-18 03:03:07,497 INFO Epoch:79 train_loss:1.84189 +2025-04-18 03:03:10,088 INFO Epoch:79 val_res:0.450128 +2025-04-18 03:03:10,088 INFO Saving best model at Epoch 79 +2025-04-18 03:03:16,185 INFO Epoch:80 train_loss:1.82201 +2025-04-18 03:03:18,888 INFO Epoch:80 val_res:0.409207 +2025-04-18 03:03:23,201 INFO Epoch:81 train_loss:1.84132 +2025-04-18 03:03:25,667 INFO Epoch:81 val_res:0.411765 +2025-04-18 03:03:30,205 INFO Epoch:82 train_loss:1.84022 +2025-04-18 03:03:33,154 INFO Epoch:82 val_res:0.421995 +2025-04-18 03:03:37,584 INFO Epoch:83 train_loss:1.81408 +2025-04-18 03:03:40,214 INFO Epoch:83 val_res:0.406650 +2025-04-18 03:03:44,366 INFO Epoch:84 train_loss:1.61289 +2025-04-18 03:03:46,888 INFO Epoch:84 val_res:0.414322 +2025-04-18 03:03:51,272 INFO Epoch:85 train_loss:1.65245 +2025-04-18 03:03:53,739 INFO Epoch:85 val_res:0.409207 +2025-04-18 03:03:58,439 INFO Epoch:86 train_loss:2.17003 +2025-04-18 03:04:01,190 INFO Epoch:86 val_res:0.429668 +2025-04-18 03:04:05,508 INFO Epoch:87 train_loss:1.62482 +2025-04-18 03:04:08,274 INFO Epoch:87 val_res:0.416880 +2025-04-18 03:04:12,447 INFO Epoch:88 train_loss:1.73879 +2025-04-18 03:04:15,106 INFO Epoch:88 val_res:0.427110 +2025-04-18 03:04:19,192 INFO Epoch:89 train_loss:1.84795 +2025-04-18 03:04:21,691 INFO Epoch:89 val_res:0.401535 +2025-04-18 03:04:25,882 INFO Epoch:90 train_loss:1.92525 +2025-04-18 03:04:28,395 INFO Epoch:90 val_res:0.419437 +2025-04-18 03:04:33,118 INFO Epoch:91 train_loss:1.78575 +2025-04-18 03:04:35,896 INFO Epoch:91 val_res:0.411765 +2025-04-18 03:04:40,193 INFO Epoch:92 train_loss:1.74121 +2025-04-18 03:04:42,678 INFO Epoch:92 val_res:0.442455 +2025-04-18 03:04:46,631 INFO Epoch:93 train_loss:1.79159 +2025-04-18 03:04:49,154 INFO Epoch:93 val_res:0.406650 +2025-04-18 03:04:53,044 INFO Epoch:94 train_loss:1.78560 +2025-04-18 03:04:55,529 INFO Epoch:94 val_res:0.421995 +2025-04-18 03:05:00,374 INFO Epoch:95 train_loss:1.61971 +2025-04-18 03:05:03,232 INFO Epoch:95 val_res:0.401535 +2025-04-18 03:05:08,178 INFO Epoch:96 train_loss:1.61066 +2025-04-18 03:05:11,187 INFO Epoch:96 val_res:0.421995 +2025-04-18 03:05:16,164 INFO Epoch:97 train_loss:1.69572 +2025-04-18 03:05:18,906 INFO Epoch:97 val_res:0.404092 +2025-04-18 03:05:23,424 INFO Epoch:98 train_loss:1.58189 +2025-04-18 03:05:26,454 INFO Epoch:98 val_res:0.414322 +2025-04-18 03:05:30,913 INFO Epoch:99 train_loss:1.76605 +2025-04-18 03:05:33,657 INFO Epoch:99 val_res:0.419437 +2025-04-18 03:05:42,390 INFO ===================================== +2025-04-18 03:05:42,391 INFO Start testing... +2025-04-18 03:05:42,391 INFO ===================================== +2025-04-18 03:05:49,673 INFO Incremental step 3 Testing res: 0.403553 +2025-04-18 03:05:49,675 INFO forgetting: 0.200411 +2025-04-18 03:05:49,678 INFO Average Accuracy: 0.573691 +2025-04-18 03:05:49,679 INFO Average Forgetting: 0.200965 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..a32c1dd4a37c4e3e658f7d517fad45178c758b8b Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..c7a5072a28943195bfce73f9273da313ab5bb6b6 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..3de2c03f7d16f88eebb17722e5bc5200b00e702b Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..ff6a8d28fed74c35b738f54b5779822d8a651ccd Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..d9e9b653f9d83e8ea3784b62d17e8c009391a112 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_5.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..35a07eb8d1c5abf094cfcdfb198ba999d5183e14 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_5.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_6.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..f159b76761978c697effb18a7c6868cb0eba7171 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_6.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_7.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..22e89417a877ab10a5b2034b9813a88d15c74fbc Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_7.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_8.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..7f28bd2564a2e950fd46a52e8df77144c4db3f1a Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_8.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_9.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..de5003fbc9eb92de0aeaaf381d963cebde784fef Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_9.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..0c15b85f0a5cb7c42a2a6b726231832f229739ec Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..cc6c86cb9abdfcb69d5d4d8dccc987e643c48db8 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..102f1c950b826961b0987601c235e5729b185bd3 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..92aa0c011cd82f9057814d166d8fda8079560172 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..93568c81ff9787053da781d0336d74e8fd192f9e Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_5.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..9d785a6e1b12dafc8c7697dbb2b417bc96034b8b Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_5.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_6.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..a822c23b04bdd22c78081c3aadfd5239ef8d47e8 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_6.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_7.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..7d01019b3660b8f82a847c3e05448119fdbdb015 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_7.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_8.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..424778a9fb31a85dc463d22fe96ee90a4809da94 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_8.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_9.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..15bea8ad13c8a3b037203810d3c16cf98d1dd132 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_9.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ec548f2bf7501f6a130bffcc691daf6ba0e7c8fb --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebdd11e58af707d2fd94c86865d37ab4040e4c816aac368f0095c852b7db8618 +size 114142801 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..4afe3fbbdaaee9269c0824de402c02d2c2b064a5 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6687e4561bc7db4d0eb6815963ff012d60597a3114d8e1950c8fc47d929e76b8 +size 114235153 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..d0991f4fc83a5dffc5217fa39767d4fee865c112 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d9f82185a28ded76e8acd7f3aed20b52fdcceddf4bc4b784ee6e401946c8c0 +size 114327313 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..e5d67305c6f3c5edb0aea08af2a8546e3ef25e54 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:444d428e9ebdfc445906831e6c811696cb0922ab5bb7a7ddd864378a7da0a762 +size 114419665 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..15211ddec7df54c6180d6f8ffd5727568510d984 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9a347ccc623001b8c649527e5d9ac4c4dd6b7a6c50cc38085e0c6833f467c4d +size 114512017 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_5_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_5_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..49150f94a3e4b8a92f3d3492e4e2f78ddf878126 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_5_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0ad2de96e66bd68709e9247e5ac1e276865133394c331e8dfe76d0de4164b0f +size 114604177 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_6_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_6_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f46edd151714f504af62b08447f6ab2fdddb47cf --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_6_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd9ee8faf90f45248a8b1a44d5c586f93811f97e8252e8953d7eb8cd56d17ce7 +size 114696529 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_7_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_7_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8e61096feee64051f603712fb1661ab855f49e49 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_7_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aa32fe1f20b2a96b9ee62d8813f503e6ec3cffe7fe0c43fb9ca5c33e19e12f7 +size 114788881 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_8_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_8_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b1421d8466388752eb382604f7263a16135f0720 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_8_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c564fc2f0fcae53d40d7d631aa31ca33a8da504a11df183050dc35d3dbc65f8b +size 114881041 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_9_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_9_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..86e07cadecf34e2f77ca9c7d806b4dd9c1a32a6d --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_9_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e74c07e896ec3667e4c1e3d70167fc7a9297e10221e45c1fbdebb8d6d34357ae +size 114973393 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/train.log b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..e32894b7c0adff3a45b283bb34657aa6d6eba69d --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/train.log @@ -0,0 +1,2270 @@ +2025-04-19 03:52:32,805 INFO Namespace(class_num_per_step=10, dataset='VGGSound_100', e_prompt=False, infer_batch_size=128, inverse=False, inverse_ends=100, inverse_starts=0, lr=0.001, lr_decay=False, max_epoches=100, milestones=[100], modality='audio-visual', num_classes=100, num_workers=4, prompt_dim=768, seed=0, train_batch_size=256, transfer=False, warm=False, weight_decay=0.0001) +2025-04-19 03:52:32,806 INFO Training start time: 2025-04-19 03:52:32.806320 +2025-04-19 03:52:33,628 INFO Incremental step: 0 +2025-04-19 03:52:57,773 INFO Epoch:0 train_loss:1.57833 +2025-04-19 03:53:00,777 INFO Epoch:0 val_res:0.566000 +2025-04-19 03:53:00,777 INFO Saving best model at Epoch 0 +2025-04-19 03:53:16,302 INFO Epoch:1 train_loss:0.68135 +2025-04-19 03:53:18,645 INFO Epoch:1 val_res:0.718000 +2025-04-19 03:53:18,645 INFO Saving best model at Epoch 1 +2025-04-19 03:53:36,808 INFO Epoch:2 train_loss:0.43893 +2025-04-19 03:53:39,263 INFO Epoch:2 val_res:0.760000 +2025-04-19 03:53:39,264 INFO Saving best model at Epoch 2 +2025-04-19 03:53:54,796 INFO Epoch:3 train_loss:0.32675 +2025-04-19 03:53:57,142 INFO Epoch:3 val_res:0.814000 +2025-04-19 03:53:57,142 INFO Saving best model at Epoch 3 +2025-04-19 03:54:12,719 INFO Epoch:4 train_loss:0.26638 +2025-04-19 03:54:15,075 INFO Epoch:4 val_res:0.794000 +2025-04-19 03:54:29,720 INFO Epoch:5 train_loss:0.22597 +2025-04-19 03:54:31,955 INFO Epoch:5 val_res:0.816000 +2025-04-19 03:54:31,956 INFO Saving best model at Epoch 5 +2025-04-19 03:54:47,569 INFO Epoch:6 train_loss:0.18935 +2025-04-19 03:54:50,050 INFO Epoch:6 val_res:0.800000 +2025-04-19 03:55:04,355 INFO Epoch:7 train_loss:0.16873 +2025-04-19 03:55:06,888 INFO Epoch:7 val_res:0.842000 +2025-04-19 03:55:06,889 INFO Saving best model at Epoch 7 +2025-04-19 03:55:22,734 INFO Epoch:8 train_loss:0.14080 +2025-04-19 03:55:25,041 INFO Epoch:8 val_res:0.854000 +2025-04-19 03:55:25,042 INFO Saving best model at Epoch 8 +2025-04-19 03:55:40,880 INFO Epoch:9 train_loss:0.12211 +2025-04-19 03:55:43,394 INFO Epoch:9 val_res:0.850000 +2025-04-19 03:55:57,200 INFO Epoch:10 train_loss:0.11082 +2025-04-19 03:55:59,548 INFO Epoch:10 val_res:0.850000 +2025-04-19 03:56:13,488 INFO Epoch:11 train_loss:0.09948 +2025-04-19 03:56:15,913 INFO Epoch:11 val_res:0.850000 +2025-04-19 03:56:29,099 INFO Epoch:12 train_loss:0.08492 +2025-04-19 03:56:31,575 INFO Epoch:12 val_res:0.878000 +2025-04-19 03:56:31,575 INFO Saving best model at Epoch 12 +2025-04-19 03:56:46,082 INFO Epoch:13 train_loss:0.07938 +2025-04-19 03:56:48,735 INFO Epoch:13 val_res:0.872000 +2025-04-19 03:57:01,906 INFO Epoch:14 train_loss:0.06874 +2025-04-19 03:57:04,111 INFO Epoch:14 val_res:0.880000 +2025-04-19 03:57:04,111 INFO Saving best model at Epoch 14 +2025-04-19 03:57:19,596 INFO Epoch:15 train_loss:0.06896 +2025-04-19 03:57:22,022 INFO Epoch:15 val_res:0.864000 +2025-04-19 03:57:35,201 INFO Epoch:16 train_loss:0.05633 +2025-04-19 03:57:37,495 INFO Epoch:16 val_res:0.880000 +2025-04-19 03:57:50,917 INFO Epoch:17 train_loss:0.05432 +2025-04-19 03:57:53,223 INFO Epoch:17 val_res:0.880000 +2025-04-19 03:58:06,907 INFO Epoch:18 train_loss:0.05192 +2025-04-19 03:58:09,325 INFO Epoch:18 val_res:0.860000 +2025-04-19 03:58:22,858 INFO Epoch:19 train_loss:0.04799 +2025-04-19 03:58:25,152 INFO Epoch:19 val_res:0.894000 +2025-04-19 03:58:25,153 INFO Saving best model at Epoch 19 +2025-04-19 03:58:40,406 INFO Epoch:20 train_loss:0.04055 +2025-04-19 03:58:42,705 INFO Epoch:20 val_res:0.874000 +2025-04-19 03:58:56,260 INFO Epoch:21 train_loss:0.03702 +2025-04-19 03:58:58,737 INFO Epoch:21 val_res:0.878000 +2025-04-19 03:59:12,357 INFO Epoch:22 train_loss:0.03772 +2025-04-19 03:59:14,676 INFO Epoch:22 val_res:0.870000 +2025-04-19 03:59:28,029 INFO Epoch:23 train_loss:0.03025 +2025-04-19 03:59:30,397 INFO Epoch:23 val_res:0.878000 +2025-04-19 03:59:43,970 INFO Epoch:24 train_loss:0.03009 +2025-04-19 03:59:46,268 INFO Epoch:24 val_res:0.868000 +2025-04-19 03:59:59,819 INFO Epoch:25 train_loss:0.03152 +2025-04-19 04:00:02,232 INFO Epoch:25 val_res:0.874000 +2025-04-19 04:00:15,328 INFO Epoch:26 train_loss:0.02550 +2025-04-19 04:00:17,570 INFO Epoch:26 val_res:0.868000 +2025-04-19 04:00:31,584 INFO Epoch:27 train_loss:0.02292 +2025-04-19 04:00:34,119 INFO Epoch:27 val_res:0.888000 +2025-04-19 04:00:47,669 INFO Epoch:28 train_loss:0.02158 +2025-04-19 04:00:50,122 INFO Epoch:28 val_res:0.886000 +2025-04-19 04:01:03,540 INFO Epoch:29 train_loss:0.02141 +2025-04-19 04:01:05,899 INFO Epoch:29 val_res:0.886000 +2025-04-19 04:01:19,736 INFO Epoch:30 train_loss:0.02026 +2025-04-19 04:01:22,046 INFO Epoch:30 val_res:0.890000 +2025-04-19 04:01:35,880 INFO Epoch:31 train_loss:0.01820 +2025-04-19 04:01:38,265 INFO Epoch:31 val_res:0.880000 +2025-04-19 04:01:51,863 INFO Epoch:32 train_loss:0.02193 +2025-04-19 04:01:54,242 INFO Epoch:32 val_res:0.886000 +2025-04-19 04:02:08,132 INFO Epoch:33 train_loss:0.01989 +2025-04-19 04:02:10,605 INFO Epoch:33 val_res:0.882000 +2025-04-19 04:02:24,786 INFO Epoch:34 train_loss:0.01837 +2025-04-19 04:02:27,307 INFO Epoch:34 val_res:0.886000 +2025-04-19 04:02:41,077 INFO Epoch:35 train_loss:0.01960 +2025-04-19 04:02:43,586 INFO Epoch:35 val_res:0.896000 +2025-04-19 04:02:43,586 INFO Saving best model at Epoch 35 +2025-04-19 04:02:58,269 INFO Epoch:36 train_loss:0.03499 +2025-04-19 04:03:00,553 INFO Epoch:36 val_res:0.844000 +2025-04-19 04:03:13,941 INFO Epoch:37 train_loss:0.03164 +2025-04-19 04:03:16,316 INFO Epoch:37 val_res:0.888000 +2025-04-19 04:03:29,426 INFO Epoch:38 train_loss:0.02363 +2025-04-19 04:03:31,713 INFO Epoch:38 val_res:0.854000 +2025-04-19 04:03:44,626 INFO Epoch:39 train_loss:0.03960 +2025-04-19 04:03:46,811 INFO Epoch:39 val_res:0.886000 +2025-04-19 04:03:59,987 INFO Epoch:40 train_loss:0.04674 +2025-04-19 04:04:02,497 INFO Epoch:40 val_res:0.850000 +2025-04-19 04:04:15,878 INFO Epoch:41 train_loss:0.03982 +2025-04-19 04:04:18,241 INFO Epoch:41 val_res:0.878000 +2025-04-19 04:04:31,684 INFO Epoch:42 train_loss:0.04199 +2025-04-19 04:04:33,910 INFO Epoch:42 val_res:0.826000 +2025-04-19 04:04:47,014 INFO Epoch:43 train_loss:0.04512 +2025-04-19 04:04:49,393 INFO Epoch:43 val_res:0.890000 +2025-04-19 04:05:02,958 INFO Epoch:44 train_loss:0.01358 +2025-04-19 04:05:05,210 INFO Epoch:44 val_res:0.878000 +2025-04-19 04:05:18,061 INFO Epoch:45 train_loss:0.01693 +2025-04-19 04:05:20,411 INFO Epoch:45 val_res:0.872000 +2025-04-19 04:05:33,321 INFO Epoch:46 train_loss:0.01615 +2025-04-19 04:05:35,686 INFO Epoch:46 val_res:0.876000 +2025-04-19 04:05:49,325 INFO Epoch:47 train_loss:0.01003 +2025-04-19 04:05:51,616 INFO Epoch:47 val_res:0.874000 +2025-04-19 04:06:04,826 INFO Epoch:48 train_loss:0.00787 +2025-04-19 04:06:07,158 INFO Epoch:48 val_res:0.884000 +2025-04-19 04:06:20,124 INFO Epoch:49 train_loss:0.00872 +2025-04-19 04:06:22,412 INFO Epoch:49 val_res:0.886000 +2025-04-19 04:06:35,070 INFO Epoch:50 train_loss:0.00930 +2025-04-19 04:06:37,227 INFO Epoch:50 val_res:0.890000 +2025-04-19 04:06:50,746 INFO Epoch:51 train_loss:0.00960 +2025-04-19 04:06:53,016 INFO Epoch:51 val_res:0.884000 +2025-04-19 04:07:05,761 INFO Epoch:52 train_loss:0.00920 +2025-04-19 04:07:08,171 INFO Epoch:52 val_res:0.880000 +2025-04-19 04:07:21,500 INFO Epoch:53 train_loss:0.00911 +2025-04-19 04:07:24,097 INFO Epoch:53 val_res:0.878000 +2025-04-19 04:07:37,454 INFO Epoch:54 train_loss:0.01045 +2025-04-19 04:07:39,581 INFO Epoch:54 val_res:0.874000 +2025-04-19 04:07:52,348 INFO Epoch:55 train_loss:0.00858 +2025-04-19 04:07:54,789 INFO Epoch:55 val_res:0.904000 +2025-04-19 04:07:54,789 INFO Saving best model at Epoch 55 +2025-04-19 04:08:08,943 INFO Epoch:56 train_loss:0.00871 +2025-04-19 04:08:11,189 INFO Epoch:56 val_res:0.892000 +2025-04-19 04:08:23,534 INFO Epoch:57 train_loss:0.00773 +2025-04-19 04:08:25,918 INFO Epoch:57 val_res:0.882000 +2025-04-19 04:08:38,233 INFO Epoch:58 train_loss:0.00809 +2025-04-19 04:08:40,897 INFO Epoch:58 val_res:0.892000 +2025-04-19 04:08:53,130 INFO Epoch:59 train_loss:0.00792 +2025-04-19 04:08:55,337 INFO Epoch:59 val_res:0.884000 +2025-04-19 04:09:07,549 INFO Epoch:60 train_loss:0.00943 +2025-04-19 04:09:09,768 INFO Epoch:60 val_res:0.878000 +2025-04-19 04:09:22,229 INFO Epoch:61 train_loss:0.00851 +2025-04-19 04:09:24,510 INFO Epoch:61 val_res:0.892000 +2025-04-19 04:09:37,159 INFO Epoch:62 train_loss:0.00975 +2025-04-19 04:09:39,383 INFO Epoch:62 val_res:0.882000 +2025-04-19 04:09:51,991 INFO Epoch:63 train_loss:0.00975 +2025-04-19 04:09:54,176 INFO Epoch:63 val_res:0.890000 +2025-04-19 04:10:06,804 INFO Epoch:64 train_loss:0.00896 +2025-04-19 04:10:08,922 INFO Epoch:64 val_res:0.880000 +2025-04-19 04:10:21,635 INFO Epoch:65 train_loss:0.00773 +2025-04-19 04:10:23,701 INFO Epoch:65 val_res:0.886000 +2025-04-19 04:10:36,454 INFO Epoch:66 train_loss:0.00757 +2025-04-19 04:10:38,631 INFO Epoch:66 val_res:0.886000 +2025-04-19 04:10:51,159 INFO Epoch:67 train_loss:0.00688 +2025-04-19 04:10:53,328 INFO Epoch:67 val_res:0.882000 +2025-04-19 04:11:05,918 INFO Epoch:68 train_loss:0.00842 +2025-04-19 04:11:08,097 INFO Epoch:68 val_res:0.880000 +2025-04-19 04:11:20,708 INFO Epoch:69 train_loss:0.00819 +2025-04-19 04:11:22,954 INFO Epoch:69 val_res:0.896000 +2025-04-19 04:11:35,316 INFO Epoch:70 train_loss:0.00967 +2025-04-19 04:11:37,553 INFO Epoch:70 val_res:0.890000 +2025-04-19 04:11:49,954 INFO Epoch:71 train_loss:0.00807 +2025-04-19 04:11:52,129 INFO Epoch:71 val_res:0.876000 +2025-04-19 04:12:04,689 INFO Epoch:72 train_loss:0.03392 +2025-04-19 04:12:06,755 INFO Epoch:72 val_res:0.868000 +2025-04-19 04:12:19,595 INFO Epoch:73 train_loss:1.02883 +2025-04-19 04:12:21,793 INFO Epoch:73 val_res:0.726000 +2025-04-19 04:12:34,322 INFO Epoch:74 train_loss:0.36634 +2025-04-19 04:12:36,400 INFO Epoch:74 val_res:0.820000 +2025-04-19 04:12:49,051 INFO Epoch:75 train_loss:0.08752 +2025-04-19 04:12:51,267 INFO Epoch:75 val_res:0.868000 +2025-04-19 04:13:03,677 INFO Epoch:76 train_loss:0.02406 +2025-04-19 04:13:05,904 INFO Epoch:76 val_res:0.882000 +2025-04-19 04:13:18,348 INFO Epoch:77 train_loss:0.01029 +2025-04-19 04:13:20,626 INFO Epoch:77 val_res:0.882000 +2025-04-19 04:13:33,168 INFO Epoch:78 train_loss:0.00665 +2025-04-19 04:13:35,381 INFO Epoch:78 val_res:0.892000 +2025-04-19 04:13:47,900 INFO Epoch:79 train_loss:0.00641 +2025-04-19 04:13:50,032 INFO Epoch:79 val_res:0.896000 +2025-04-19 04:14:02,448 INFO Epoch:80 train_loss:0.00621 +2025-04-19 04:14:04,749 INFO Epoch:80 val_res:0.884000 +2025-04-19 04:14:16,924 INFO Epoch:81 train_loss:0.00490 +2025-04-19 04:14:19,162 INFO Epoch:81 val_res:0.878000 +2025-04-19 04:14:31,656 INFO Epoch:82 train_loss:0.00477 +2025-04-19 04:14:33,870 INFO Epoch:82 val_res:0.880000 +2025-04-19 04:14:46,168 INFO Epoch:83 train_loss:0.00474 +2025-04-19 04:14:48,375 INFO Epoch:83 val_res:0.890000 +2025-04-19 04:15:01,039 INFO Epoch:84 train_loss:0.00468 +2025-04-19 04:15:03,247 INFO Epoch:84 val_res:0.886000 +2025-04-19 04:15:15,873 INFO Epoch:85 train_loss:0.00462 +2025-04-19 04:15:18,084 INFO Epoch:85 val_res:0.880000 +2025-04-19 04:15:30,687 INFO Epoch:86 train_loss:0.00462 +2025-04-19 04:15:32,876 INFO Epoch:86 val_res:0.886000 +2025-04-19 04:15:45,405 INFO Epoch:87 train_loss:0.00464 +2025-04-19 04:15:47,511 INFO Epoch:87 val_res:0.888000 +2025-04-19 04:16:00,314 INFO Epoch:88 train_loss:0.00489 +2025-04-19 04:16:02,415 INFO Epoch:88 val_res:0.874000 +2025-04-19 04:16:15,059 INFO Epoch:89 train_loss:0.00495 +2025-04-19 04:16:17,161 INFO Epoch:89 val_res:0.874000 +2025-04-19 04:16:29,627 INFO Epoch:90 train_loss:0.00525 +2025-04-19 04:16:31,805 INFO Epoch:90 val_res:0.894000 +2025-04-19 04:16:44,278 INFO Epoch:91 train_loss:0.00546 +2025-04-19 04:16:46,377 INFO Epoch:91 val_res:0.878000 +2025-04-19 04:16:58,624 INFO Epoch:92 train_loss:0.00500 +2025-04-19 04:17:00,909 INFO Epoch:92 val_res:0.880000 +2025-04-19 04:17:13,238 INFO Epoch:93 train_loss:0.00509 +2025-04-19 04:17:15,392 INFO Epoch:93 val_res:0.888000 +2025-04-19 04:17:27,917 INFO Epoch:94 train_loss:0.00488 +2025-04-19 04:17:30,067 INFO Epoch:94 val_res:0.876000 +2025-04-19 04:17:42,673 INFO Epoch:95 train_loss:0.00512 +2025-04-19 04:17:44,804 INFO Epoch:95 val_res:0.878000 +2025-04-19 04:17:57,373 INFO Epoch:96 train_loss:0.00509 +2025-04-19 04:17:59,495 INFO Epoch:96 val_res:0.880000 +2025-04-19 04:18:11,985 INFO Epoch:97 train_loss:0.00508 +2025-04-19 04:18:14,122 INFO Epoch:97 val_res:0.872000 +2025-04-19 04:18:26,263 INFO Epoch:98 train_loss:0.00530 +2025-04-19 04:18:28,471 INFO Epoch:98 val_res:0.888000 +2025-04-19 04:18:40,742 INFO Epoch:99 train_loss:0.00515 +2025-04-19 04:18:42,972 INFO Epoch:99 val_res:0.882000 +2025-04-19 04:18:43,724 INFO ===================================== +2025-04-19 04:18:43,725 INFO Start testing... +2025-04-19 04:18:43,725 INFO ===================================== +2025-04-19 04:18:46,558 INFO Incremental step 0 Testing res: 0.912000 +2025-04-19 04:18:46,560 INFO Incremental step: 1 +2025-04-19 04:19:00,514 INFO Epoch:0 train_loss:1.80356 +2025-04-19 04:19:04,666 INFO Epoch:0 val_res:0.458000 +2025-04-19 04:19:04,666 INFO Saving best model at Epoch 0 +2025-04-19 04:19:20,629 INFO Epoch:1 train_loss:0.73893 +2025-04-19 04:19:24,384 INFO Epoch:1 val_res:0.492000 +2025-04-19 04:19:24,385 INFO Saving best model at Epoch 1 +2025-04-19 04:19:38,849 INFO Epoch:2 train_loss:0.50737 +2025-04-19 04:19:42,179 INFO Epoch:2 val_res:0.534000 +2025-04-19 04:19:42,179 INFO Saving best model at Epoch 2 +2025-04-19 04:19:55,625 INFO Epoch:3 train_loss:0.40943 +2025-04-19 04:19:58,948 INFO Epoch:3 val_res:0.561000 +2025-04-19 04:19:58,949 INFO Saving best model at Epoch 3 +2025-04-19 04:20:12,279 INFO Epoch:4 train_loss:0.36640 +2025-04-19 04:20:15,684 INFO Epoch:4 val_res:0.572000 +2025-04-19 04:20:15,685 INFO Saving best model at Epoch 4 +2025-04-19 04:20:29,179 INFO Epoch:5 train_loss:0.31792 +2025-04-19 04:20:32,737 INFO Epoch:5 val_res:0.596000 +2025-04-19 04:20:32,738 INFO Saving best model at Epoch 5 +2025-04-19 04:20:46,078 INFO Epoch:6 train_loss:0.28123 +2025-04-19 04:20:49,640 INFO Epoch:6 val_res:0.604000 +2025-04-19 04:20:49,641 INFO Saving best model at Epoch 6 +2025-04-19 04:21:03,254 INFO Epoch:7 train_loss:0.25326 +2025-04-19 04:21:06,850 INFO Epoch:7 val_res:0.626000 +2025-04-19 04:21:06,850 INFO Saving best model at Epoch 7 +2025-04-19 04:21:21,008 INFO Epoch:8 train_loss:0.23459 +2025-04-19 04:21:24,573 INFO Epoch:8 val_res:0.645000 +2025-04-19 04:21:24,574 INFO Saving best model at Epoch 8 +2025-04-19 04:21:37,974 INFO Epoch:9 train_loss:0.21535 +2025-04-19 04:21:41,470 INFO Epoch:9 val_res:0.657000 +2025-04-19 04:21:41,470 INFO Saving best model at Epoch 9 +2025-04-19 04:21:55,734 INFO Epoch:10 train_loss:0.19074 +2025-04-19 04:21:59,170 INFO Epoch:10 val_res:0.676000 +2025-04-19 04:21:59,171 INFO Saving best model at Epoch 10 +2025-04-19 04:22:13,314 INFO Epoch:11 train_loss:0.17201 +2025-04-19 04:22:16,888 INFO Epoch:11 val_res:0.686000 +2025-04-19 04:22:16,889 INFO Saving best model at Epoch 11 +2025-04-19 04:22:31,192 INFO Epoch:12 train_loss:0.15271 +2025-04-19 04:22:34,394 INFO Epoch:12 val_res:0.696000 +2025-04-19 04:22:34,394 INFO Saving best model at Epoch 12 +2025-04-19 04:22:48,353 INFO Epoch:13 train_loss:0.13728 +2025-04-19 04:22:51,767 INFO Epoch:13 val_res:0.707000 +2025-04-19 04:22:51,767 INFO Saving best model at Epoch 13 +2025-04-19 04:23:06,193 INFO Epoch:14 train_loss:0.12623 +2025-04-19 04:23:09,732 INFO Epoch:14 val_res:0.717000 +2025-04-19 04:23:09,732 INFO Saving best model at Epoch 14 +2025-04-19 04:23:23,517 INFO Epoch:15 train_loss:0.11553 +2025-04-19 04:23:27,015 INFO Epoch:15 val_res:0.733000 +2025-04-19 04:23:27,016 INFO Saving best model at Epoch 15 +2025-04-19 04:23:41,934 INFO Epoch:16 train_loss:0.09671 +2025-04-19 04:23:45,630 INFO Epoch:16 val_res:0.737000 +2025-04-19 04:23:45,630 INFO Saving best model at Epoch 16 +2025-04-19 04:23:59,264 INFO Epoch:17 train_loss:0.09087 +2025-04-19 04:24:02,814 INFO Epoch:17 val_res:0.751000 +2025-04-19 04:24:02,815 INFO Saving best model at Epoch 17 +2025-04-19 04:24:18,144 INFO Epoch:18 train_loss:0.08954 +2025-04-19 04:24:21,613 INFO Epoch:18 val_res:0.749000 +2025-04-19 04:24:33,895 INFO Epoch:19 train_loss:0.07652 +2025-04-19 04:24:37,593 INFO Epoch:19 val_res:0.750000 +2025-04-19 04:24:49,683 INFO Epoch:20 train_loss:0.07320 +2025-04-19 04:24:53,137 INFO Epoch:20 val_res:0.763000 +2025-04-19 04:24:53,137 INFO Saving best model at Epoch 20 +2025-04-19 04:25:07,319 INFO Epoch:21 train_loss:0.06469 +2025-04-19 04:25:10,738 INFO Epoch:21 val_res:0.767000 +2025-04-19 04:25:10,738 INFO Saving best model at Epoch 21 +2025-04-19 04:25:24,312 INFO Epoch:22 train_loss:0.06530 +2025-04-19 04:25:27,893 INFO Epoch:22 val_res:0.788000 +2025-04-19 04:25:27,893 INFO Saving best model at Epoch 22 +2025-04-19 04:25:42,219 INFO Epoch:23 train_loss:0.06658 +2025-04-19 04:25:45,724 INFO Epoch:23 val_res:0.778000 +2025-04-19 04:25:58,214 INFO Epoch:24 train_loss:0.09856 +2025-04-19 04:26:01,723 INFO Epoch:24 val_res:0.773000 +2025-04-19 04:26:13,972 INFO Epoch:25 train_loss:0.10888 +2025-04-19 04:26:17,491 INFO Epoch:25 val_res:0.785000 +2025-04-19 04:26:29,681 INFO Epoch:26 train_loss:0.06116 +2025-04-19 04:26:32,956 INFO Epoch:26 val_res:0.799000 +2025-04-19 04:26:32,956 INFO Saving best model at Epoch 26 +2025-04-19 04:26:47,288 INFO Epoch:27 train_loss:0.04447 +2025-04-19 04:26:50,842 INFO Epoch:27 val_res:0.801000 +2025-04-19 04:26:50,842 INFO Saving best model at Epoch 27 +2025-04-19 04:27:06,066 INFO Epoch:28 train_loss:0.04378 +2025-04-19 04:27:09,566 INFO Epoch:28 val_res:0.790000 +2025-04-19 04:27:21,899 INFO Epoch:29 train_loss:0.03913 +2025-04-19 04:27:25,440 INFO Epoch:29 val_res:0.801000 +2025-04-19 04:27:37,676 INFO Epoch:30 train_loss:0.03403 +2025-04-19 04:27:41,188 INFO Epoch:30 val_res:0.802000 +2025-04-19 04:27:41,188 INFO Saving best model at Epoch 30 +2025-04-19 04:27:54,637 INFO Epoch:31 train_loss:0.03342 +2025-04-19 04:27:58,240 INFO Epoch:31 val_res:0.794000 +2025-04-19 04:28:10,503 INFO Epoch:32 train_loss:0.02890 +2025-04-19 04:28:14,320 INFO Epoch:32 val_res:0.803000 +2025-04-19 04:28:14,320 INFO Saving best model at Epoch 32 +2025-04-19 04:28:28,048 INFO Epoch:33 train_loss:0.02897 +2025-04-19 04:28:31,654 INFO Epoch:33 val_res:0.802000 +2025-04-19 04:28:44,288 INFO Epoch:34 train_loss:0.02885 +2025-04-19 04:28:47,799 INFO Epoch:34 val_res:0.804000 +2025-04-19 04:28:47,799 INFO Saving best model at Epoch 34 +2025-04-19 04:29:01,555 INFO Epoch:35 train_loss:0.02556 +2025-04-19 04:29:05,129 INFO Epoch:35 val_res:0.801000 +2025-04-19 04:29:17,964 INFO Epoch:36 train_loss:0.02848 +2025-04-19 04:29:21,522 INFO Epoch:36 val_res:0.795000 +2025-04-19 04:29:33,485 INFO Epoch:37 train_loss:0.03508 +2025-04-19 04:29:36,990 INFO Epoch:37 val_res:0.813000 +2025-04-19 04:29:36,990 INFO Saving best model at Epoch 37 +2025-04-19 04:29:51,211 INFO Epoch:38 train_loss:0.04128 +2025-04-19 04:29:55,027 INFO Epoch:38 val_res:0.793000 +2025-04-19 04:30:07,106 INFO Epoch:39 train_loss:0.03996 +2025-04-19 04:30:10,529 INFO Epoch:39 val_res:0.804000 +2025-04-19 04:30:22,525 INFO Epoch:40 train_loss:0.03304 +2025-04-19 04:30:26,137 INFO Epoch:40 val_res:0.799000 +2025-04-19 04:30:39,082 INFO Epoch:41 train_loss:0.02832 +2025-04-19 04:30:42,374 INFO Epoch:41 val_res:0.811000 +2025-04-19 04:30:54,051 INFO Epoch:42 train_loss:0.02120 +2025-04-19 04:30:57,547 INFO Epoch:42 val_res:0.798000 +2025-04-19 04:31:10,726 INFO Epoch:43 train_loss:0.02604 +2025-04-19 04:31:14,304 INFO Epoch:43 val_res:0.802000 +2025-04-19 04:31:25,788 INFO Epoch:44 train_loss:0.02759 +2025-04-19 04:31:29,253 INFO Epoch:44 val_res:0.801000 +2025-04-19 04:31:41,939 INFO Epoch:45 train_loss:0.03088 +2025-04-19 04:31:45,833 INFO Epoch:45 val_res:0.806000 +2025-04-19 04:31:57,952 INFO Epoch:46 train_loss:0.03173 +2025-04-19 04:32:01,260 INFO Epoch:46 val_res:0.812000 +2025-04-19 04:32:13,711 INFO Epoch:47 train_loss:0.05141 +2025-04-19 04:32:17,122 INFO Epoch:47 val_res:0.795000 +2025-04-19 04:32:29,795 INFO Epoch:48 train_loss:0.04936 +2025-04-19 04:32:33,155 INFO Epoch:48 val_res:0.803000 +2025-04-19 04:32:45,078 INFO Epoch:49 train_loss:0.06517 +2025-04-19 04:32:48,731 INFO Epoch:49 val_res:0.798000 +2025-04-19 04:33:01,638 INFO Epoch:50 train_loss:0.08346 +2025-04-19 04:33:05,433 INFO Epoch:50 val_res:0.804000 +2025-04-19 04:33:16,890 INFO Epoch:51 train_loss:0.04581 +2025-04-19 04:33:20,334 INFO Epoch:51 val_res:0.805000 +2025-04-19 04:33:32,920 INFO Epoch:52 train_loss:0.02742 +2025-04-19 04:33:36,643 INFO Epoch:52 val_res:0.808000 +2025-04-19 04:33:48,883 INFO Epoch:53 train_loss:0.02333 +2025-04-19 04:33:52,335 INFO Epoch:53 val_res:0.802000 +2025-04-19 04:34:04,360 INFO Epoch:54 train_loss:0.02167 +2025-04-19 04:34:08,009 INFO Epoch:54 val_res:0.808000 +2025-04-19 04:34:20,993 INFO Epoch:55 train_loss:0.01686 +2025-04-19 04:34:24,336 INFO Epoch:55 val_res:0.813000 +2025-04-19 04:34:35,990 INFO Epoch:56 train_loss:0.01709 +2025-04-19 04:34:39,576 INFO Epoch:56 val_res:0.803000 +2025-04-19 04:34:52,357 INFO Epoch:57 train_loss:0.01746 +2025-04-19 04:34:56,073 INFO Epoch:57 val_res:0.799000 +2025-04-19 04:35:07,998 INFO Epoch:58 train_loss:0.01771 +2025-04-19 04:35:11,244 INFO Epoch:58 val_res:0.798000 +2025-04-19 04:35:23,741 INFO Epoch:59 train_loss:0.01907 +2025-04-19 04:35:27,395 INFO Epoch:59 val_res:0.805000 +2025-04-19 04:35:39,928 INFO Epoch:60 train_loss:0.01768 +2025-04-19 04:35:43,334 INFO Epoch:60 val_res:0.801000 +2025-04-19 04:35:55,397 INFO Epoch:61 train_loss:0.01616 +2025-04-19 04:35:59,145 INFO Epoch:61 val_res:0.800000 +2025-04-19 04:36:11,781 INFO Epoch:62 train_loss:0.01621 +2025-04-19 04:36:15,293 INFO Epoch:62 val_res:0.801000 +2025-04-19 04:36:27,271 INFO Epoch:63 train_loss:0.01654 +2025-04-19 04:36:30,865 INFO Epoch:63 val_res:0.804000 +2025-04-19 04:36:43,554 INFO Epoch:64 train_loss:0.02564 +2025-04-19 04:36:47,055 INFO Epoch:64 val_res:0.800000 +2025-04-19 04:36:59,352 INFO Epoch:65 train_loss:0.02548 +2025-04-19 04:37:02,967 INFO Epoch:65 val_res:0.800000 +2025-04-19 04:37:15,949 INFO Epoch:66 train_loss:0.02755 +2025-04-19 04:37:19,390 INFO Epoch:66 val_res:0.798000 +2025-04-19 04:37:32,125 INFO Epoch:67 train_loss:0.05577 +2025-04-19 04:37:35,689 INFO Epoch:67 val_res:0.798000 +2025-04-19 04:37:48,389 INFO Epoch:68 train_loss:0.05492 +2025-04-19 04:37:51,928 INFO Epoch:68 val_res:0.786000 +2025-04-19 04:38:04,368 INFO Epoch:69 train_loss:0.08023 +2025-04-19 04:38:07,959 INFO Epoch:69 val_res:0.791000 +2025-04-19 04:38:20,469 INFO Epoch:70 train_loss:0.04116 +2025-04-19 04:38:24,114 INFO Epoch:70 val_res:0.795000 +2025-04-19 04:38:36,571 INFO Epoch:71 train_loss:0.03314 +2025-04-19 04:38:40,336 INFO Epoch:71 val_res:0.796000 +2025-04-19 04:38:52,687 INFO Epoch:72 train_loss:0.03521 +2025-04-19 04:38:56,235 INFO Epoch:72 val_res:0.805000 +2025-04-19 04:39:08,344 INFO Epoch:73 train_loss:0.02533 +2025-04-19 04:39:12,030 INFO Epoch:73 val_res:0.790000 +2025-04-19 04:39:24,345 INFO Epoch:74 train_loss:0.02248 +2025-04-19 04:39:27,800 INFO Epoch:74 val_res:0.791000 +2025-04-19 04:39:40,060 INFO Epoch:75 train_loss:0.01783 +2025-04-19 04:39:43,511 INFO Epoch:75 val_res:0.794000 +2025-04-19 04:39:56,011 INFO Epoch:76 train_loss:0.02286 +2025-04-19 04:39:59,556 INFO Epoch:76 val_res:0.797000 +2025-04-19 04:40:11,756 INFO Epoch:77 train_loss:0.02615 +2025-04-19 04:40:15,307 INFO Epoch:77 val_res:0.800000 +2025-04-19 04:40:28,051 INFO Epoch:78 train_loss:0.02614 +2025-04-19 04:40:31,825 INFO Epoch:78 val_res:0.795000 +2025-04-19 04:40:44,376 INFO Epoch:79 train_loss:0.01666 +2025-04-19 04:40:47,862 INFO Epoch:79 val_res:0.796000 +2025-04-19 04:41:00,368 INFO Epoch:80 train_loss:0.01454 +2025-04-19 04:41:04,117 INFO Epoch:80 val_res:0.799000 +2025-04-19 04:41:16,852 INFO Epoch:81 train_loss:0.01702 +2025-04-19 04:41:20,307 INFO Epoch:81 val_res:0.798000 +2025-04-19 04:41:32,320 INFO Epoch:82 train_loss:0.01637 +2025-04-19 04:41:35,997 INFO Epoch:82 val_res:0.793000 +2025-04-19 04:41:48,865 INFO Epoch:83 train_loss:0.01596 +2025-04-19 04:41:52,501 INFO Epoch:83 val_res:0.797000 +2025-04-19 04:42:04,446 INFO Epoch:84 train_loss:0.01983 +2025-04-19 04:42:07,807 INFO Epoch:84 val_res:0.793000 +2025-04-19 04:42:20,974 INFO Epoch:85 train_loss:0.10597 +2025-04-19 04:42:24,537 INFO Epoch:85 val_res:0.775000 +2025-04-19 04:42:36,855 INFO Epoch:86 train_loss:0.20122 +2025-04-19 04:42:40,201 INFO Epoch:86 val_res:0.763000 +2025-04-19 04:42:53,118 INFO Epoch:87 train_loss:0.08109 +2025-04-19 04:42:56,927 INFO Epoch:87 val_res:0.775000 +2025-04-19 04:43:09,041 INFO Epoch:88 train_loss:0.06710 +2025-04-19 04:43:12,520 INFO Epoch:88 val_res:0.735000 +2025-04-19 04:43:24,870 INFO Epoch:89 train_loss:0.10253 +2025-04-19 04:43:28,517 INFO Epoch:89 val_res:0.745000 +2025-04-19 04:43:41,097 INFO Epoch:90 train_loss:0.12930 +2025-04-19 04:43:44,314 INFO Epoch:90 val_res:0.734000 +2025-04-19 04:43:56,564 INFO Epoch:91 train_loss:0.07893 +2025-04-19 04:44:00,244 INFO Epoch:91 val_res:0.751000 +2025-04-19 04:44:14,249 INFO Epoch:92 train_loss:0.04126 +2025-04-19 04:44:17,623 INFO Epoch:92 val_res:0.729000 +2025-04-19 04:44:29,592 INFO Epoch:93 train_loss:0.02519 +2025-04-19 04:44:33,100 INFO Epoch:93 val_res:0.734000 +2025-04-19 04:44:46,377 INFO Epoch:94 train_loss:0.01626 +2025-04-19 04:44:50,046 INFO Epoch:94 val_res:0.754000 +2025-04-19 04:45:01,477 INFO Epoch:95 train_loss:0.01119 +2025-04-19 04:45:05,036 INFO Epoch:95 val_res:0.767000 +2025-04-19 04:45:18,236 INFO Epoch:96 train_loss:0.00981 +2025-04-19 04:45:21,937 INFO Epoch:96 val_res:0.764000 +2025-04-19 04:45:33,867 INFO Epoch:97 train_loss:0.00880 +2025-04-19 04:45:37,258 INFO Epoch:97 val_res:0.767000 +2025-04-19 04:45:50,233 INFO Epoch:98 train_loss:0.00793 +2025-04-19 04:45:53,850 INFO Epoch:98 val_res:0.770000 +2025-04-19 04:46:06,040 INFO Epoch:99 train_loss:0.00801 +2025-04-19 04:46:09,710 INFO Epoch:99 val_res:0.771000 +2025-04-19 04:46:10,444 INFO ===================================== +2025-04-19 04:46:10,445 INFO Start testing... +2025-04-19 04:46:10,445 INFO ===================================== +2025-04-19 04:46:20,396 INFO Incremental step 1 Testing res: 0.786000 +2025-04-19 04:46:20,397 INFO forgetting: 0.122000 +2025-04-19 04:46:20,399 INFO Incremental step: 2 +2025-04-19 04:46:44,472 INFO Epoch:0 train_loss:2.09003 +2025-04-19 04:47:08,657 INFO Epoch:0 val_res:0.508000 +2025-04-19 04:47:08,658 INFO Saving best model at Epoch 0 +2025-04-19 04:47:27,104 INFO Epoch:1 train_loss:0.70846 +2025-04-19 04:47:31,978 INFO Epoch:1 val_res:0.536667 +2025-04-19 04:47:31,978 INFO Saving best model at Epoch 1 +2025-04-19 04:47:50,208 INFO Epoch:2 train_loss:0.46420 +2025-04-19 04:47:54,920 INFO Epoch:2 val_res:0.562000 +2025-04-19 04:47:54,920 INFO Saving best model at Epoch 2 +2025-04-19 04:48:11,988 INFO Epoch:3 train_loss:0.37539 +2025-04-19 04:48:16,998 INFO Epoch:3 val_res:0.564000 +2025-04-19 04:48:16,999 INFO Saving best model at Epoch 3 +2025-04-19 04:48:34,546 INFO Epoch:4 train_loss:0.32256 +2025-04-19 04:48:39,669 INFO Epoch:4 val_res:0.584000 +2025-04-19 04:48:39,669 INFO Saving best model at Epoch 4 +2025-04-19 04:48:56,731 INFO Epoch:5 train_loss:0.28095 +2025-04-19 04:49:01,898 INFO Epoch:5 val_res:0.595333 +2025-04-19 04:49:01,905 INFO Saving best model at Epoch 5 +2025-04-19 04:49:19,087 INFO Epoch:6 train_loss:0.24820 +2025-04-19 04:49:23,980 INFO Epoch:6 val_res:0.598000 +2025-04-19 04:49:23,981 INFO Saving best model at Epoch 6 +2025-04-19 04:49:41,580 INFO Epoch:7 train_loss:0.22062 +2025-04-19 04:49:46,393 INFO Epoch:7 val_res:0.600000 +2025-04-19 04:49:46,394 INFO Saving best model at Epoch 7 +2025-04-19 04:50:03,618 INFO Epoch:8 train_loss:0.20266 +2025-04-19 04:50:08,778 INFO Epoch:8 val_res:0.615333 +2025-04-19 04:50:08,778 INFO Saving best model at Epoch 8 +2025-04-19 04:50:26,091 INFO Epoch:9 train_loss:0.18186 +2025-04-19 04:50:31,148 INFO Epoch:9 val_res:0.616000 +2025-04-19 04:50:31,148 INFO Saving best model at Epoch 9 +2025-04-19 04:50:48,268 INFO Epoch:10 train_loss:0.16636 +2025-04-19 04:50:53,404 INFO Epoch:10 val_res:0.628667 +2025-04-19 04:50:53,404 INFO Saving best model at Epoch 10 +2025-04-19 04:51:10,456 INFO Epoch:11 train_loss:0.14985 +2025-04-19 04:51:15,229 INFO Epoch:11 val_res:0.636000 +2025-04-19 04:51:15,229 INFO Saving best model at Epoch 11 +2025-04-19 04:51:33,469 INFO Epoch:12 train_loss:0.14052 +2025-04-19 04:51:37,979 INFO Epoch:12 val_res:0.652000 +2025-04-19 04:51:37,979 INFO Saving best model at Epoch 12 +2025-04-19 04:51:55,240 INFO Epoch:13 train_loss:0.14321 +2025-04-19 04:52:00,146 INFO Epoch:13 val_res:0.644667 +2025-04-19 04:52:15,646 INFO Epoch:14 train_loss:0.13117 +2025-04-19 04:52:20,408 INFO Epoch:14 val_res:0.658000 +2025-04-19 04:52:20,408 INFO Saving best model at Epoch 14 +2025-04-19 04:52:38,084 INFO Epoch:15 train_loss:0.12339 +2025-04-19 04:52:43,501 INFO Epoch:15 val_res:0.670667 +2025-04-19 04:52:43,501 INFO Saving best model at Epoch 15 +2025-04-19 04:53:00,329 INFO Epoch:16 train_loss:0.10508 +2025-04-19 04:53:05,391 INFO Epoch:16 val_res:0.675333 +2025-04-19 04:53:05,391 INFO Saving best model at Epoch 16 +2025-04-19 04:53:23,136 INFO Epoch:17 train_loss:0.08658 +2025-04-19 04:53:27,897 INFO Epoch:17 val_res:0.681333 +2025-04-19 04:53:27,897 INFO Saving best model at Epoch 17 +2025-04-19 04:53:44,823 INFO Epoch:18 train_loss:0.07997 +2025-04-19 04:53:50,130 INFO Epoch:18 val_res:0.686000 +2025-04-19 04:53:50,130 INFO Saving best model at Epoch 18 +2025-04-19 04:54:07,561 INFO Epoch:19 train_loss:0.07150 +2025-04-19 04:54:12,503 INFO Epoch:19 val_res:0.688667 +2025-04-19 04:54:12,503 INFO Saving best model at Epoch 19 +2025-04-19 04:54:32,265 INFO Epoch:20 train_loss:0.06600 +2025-04-19 04:54:37,157 INFO Epoch:20 val_res:0.679333 +2025-04-19 04:54:52,746 INFO Epoch:21 train_loss:0.06821 +2025-04-19 04:54:57,947 INFO Epoch:21 val_res:0.691333 +2025-04-19 04:54:57,947 INFO Saving best model at Epoch 21 +2025-04-19 04:55:15,695 INFO Epoch:22 train_loss:0.06632 +2025-04-19 04:55:20,339 INFO Epoch:22 val_res:0.689333 +2025-04-19 04:55:36,825 INFO Epoch:23 train_loss:0.05379 +2025-04-19 04:55:41,782 INFO Epoch:23 val_res:0.700667 +2025-04-19 04:55:41,782 INFO Saving best model at Epoch 23 +2025-04-19 04:55:59,029 INFO Epoch:24 train_loss:0.05782 +2025-04-19 04:56:03,977 INFO Epoch:24 val_res:0.699333 +2025-04-19 04:56:19,840 INFO Epoch:25 train_loss:0.06575 +2025-04-19 04:56:24,912 INFO Epoch:25 val_res:0.698667 +2025-04-19 04:56:40,390 INFO Epoch:26 train_loss:0.05916 +2025-04-19 04:56:45,315 INFO Epoch:26 val_res:0.695333 +2025-04-19 04:57:00,901 INFO Epoch:27 train_loss:0.06599 +2025-04-19 04:57:06,374 INFO Epoch:27 val_res:0.706000 +2025-04-19 04:57:06,374 INFO Saving best model at Epoch 27 +2025-04-19 04:57:24,100 INFO Epoch:28 train_loss:0.06000 +2025-04-19 04:57:28,934 INFO Epoch:28 val_res:0.692667 +2025-04-19 04:57:45,030 INFO Epoch:29 train_loss:0.05558 +2025-04-19 04:57:49,730 INFO Epoch:29 val_res:0.704667 +2025-04-19 04:58:04,822 INFO Epoch:30 train_loss:0.05501 +2025-04-19 04:58:09,655 INFO Epoch:30 val_res:0.700667 +2025-04-19 04:58:25,614 INFO Epoch:31 train_loss:0.04050 +2025-04-19 04:58:30,357 INFO Epoch:31 val_res:0.692667 +2025-04-19 04:58:45,115 INFO Epoch:32 train_loss:0.04353 +2025-04-19 04:58:50,386 INFO Epoch:32 val_res:0.702667 +2025-04-19 04:59:06,282 INFO Epoch:33 train_loss:0.05487 +2025-04-19 04:59:10,802 INFO Epoch:33 val_res:0.692667 +2025-04-19 04:59:26,330 INFO Epoch:34 train_loss:0.05476 +2025-04-19 04:59:31,706 INFO Epoch:34 val_res:0.704000 +2025-04-19 04:59:47,424 INFO Epoch:35 train_loss:0.03595 +2025-04-19 04:59:52,093 INFO Epoch:35 val_res:0.711333 +2025-04-19 04:59:52,093 INFO Saving best model at Epoch 35 +2025-04-19 05:00:09,765 INFO Epoch:36 train_loss:0.02989 +2025-04-19 05:00:14,909 INFO Epoch:36 val_res:0.700000 +2025-04-19 05:00:30,092 INFO Epoch:37 train_loss:0.02722 +2025-04-19 05:00:34,760 INFO Epoch:37 val_res:0.704000 +2025-04-19 05:00:50,907 INFO Epoch:38 train_loss:0.02721 +2025-04-19 05:00:55,771 INFO Epoch:38 val_res:0.701333 +2025-04-19 05:01:10,893 INFO Epoch:39 train_loss:0.04022 +2025-04-19 05:01:15,810 INFO Epoch:39 val_res:0.695333 +2025-04-19 05:01:31,405 INFO Epoch:40 train_loss:0.05037 +2025-04-19 05:01:36,189 INFO Epoch:40 val_res:0.702667 +2025-04-19 05:01:51,435 INFO Epoch:41 train_loss:0.05580 +2025-04-19 05:01:56,445 INFO Epoch:41 val_res:0.704667 +2025-04-19 05:02:11,869 INFO Epoch:42 train_loss:0.07152 +2025-04-19 05:02:16,538 INFO Epoch:42 val_res:0.705333 +2025-04-19 05:02:32,052 INFO Epoch:43 train_loss:0.10315 +2025-04-19 05:02:37,309 INFO Epoch:43 val_res:0.696000 +2025-04-19 05:02:53,136 INFO Epoch:44 train_loss:0.10538 +2025-04-19 05:02:58,025 INFO Epoch:44 val_res:0.694000 +2025-04-19 05:03:14,036 INFO Epoch:45 train_loss:0.08314 +2025-04-19 05:03:19,134 INFO Epoch:45 val_res:0.701333 +2025-04-19 05:03:35,063 INFO Epoch:46 train_loss:0.04631 +2025-04-19 05:03:39,979 INFO Epoch:46 val_res:0.706000 +2025-04-19 05:03:56,631 INFO Epoch:47 train_loss:0.03258 +2025-04-19 05:04:01,477 INFO Epoch:47 val_res:0.702000 +2025-04-19 05:04:16,431 INFO Epoch:48 train_loss:0.02886 +2025-04-19 05:04:21,469 INFO Epoch:48 val_res:0.696000 +2025-04-19 05:04:36,855 INFO Epoch:49 train_loss:0.02112 +2025-04-19 05:04:41,341 INFO Epoch:49 val_res:0.706000 +2025-04-19 05:04:56,509 INFO Epoch:50 train_loss:0.01779 +2025-04-19 05:05:01,861 INFO Epoch:50 val_res:0.705333 +2025-04-19 05:05:16,447 INFO Epoch:51 train_loss:0.01986 +2025-04-19 05:05:21,171 INFO Epoch:51 val_res:0.686000 +2025-04-19 05:05:36,377 INFO Epoch:52 train_loss:0.01958 +2025-04-19 05:05:41,460 INFO Epoch:52 val_res:0.705333 +2025-04-19 05:05:55,900 INFO Epoch:53 train_loss:0.02614 +2025-04-19 05:06:00,915 INFO Epoch:53 val_res:0.703333 +2025-04-19 05:06:16,175 INFO Epoch:54 train_loss:0.02872 +2025-04-19 05:06:21,204 INFO Epoch:54 val_res:0.701333 +2025-04-19 05:06:35,060 INFO Epoch:55 train_loss:0.02877 +2025-04-19 05:06:40,161 INFO Epoch:55 val_res:0.702000 +2025-04-19 05:06:55,512 INFO Epoch:56 train_loss:0.03232 +2025-04-19 05:07:00,617 INFO Epoch:56 val_res:0.696000 +2025-04-19 05:07:15,139 INFO Epoch:57 train_loss:0.02492 +2025-04-19 05:07:20,178 INFO Epoch:57 val_res:0.696667 +2025-04-19 05:07:35,221 INFO Epoch:58 train_loss:0.03091 +2025-04-19 05:07:39,778 INFO Epoch:58 val_res:0.684000 +2025-04-19 05:07:55,042 INFO Epoch:59 train_loss:0.02870 +2025-04-19 05:08:00,251 INFO Epoch:59 val_res:0.692667 +2025-04-19 05:08:15,404 INFO Epoch:60 train_loss:0.02512 +2025-04-19 05:08:20,107 INFO Epoch:60 val_res:0.700667 +2025-04-19 05:08:35,659 INFO Epoch:61 train_loss:0.04475 +2025-04-19 05:08:40,307 INFO Epoch:61 val_res:0.687333 +2025-04-19 05:08:54,504 INFO Epoch:62 train_loss:0.26415 +2025-04-19 05:08:59,598 INFO Epoch:62 val_res:0.686667 +2025-04-19 05:09:15,221 INFO Epoch:63 train_loss:0.16701 +2025-04-19 05:09:19,911 INFO Epoch:63 val_res:0.694667 +2025-04-19 05:09:34,968 INFO Epoch:64 train_loss:0.08059 +2025-04-19 05:09:40,536 INFO Epoch:64 val_res:0.691333 +2025-04-19 05:09:55,048 INFO Epoch:65 train_loss:0.04370 +2025-04-19 05:10:00,033 INFO Epoch:65 val_res:0.686667 +2025-04-19 05:10:15,717 INFO Epoch:66 train_loss:0.02682 +2025-04-19 05:10:20,802 INFO Epoch:66 val_res:0.686667 +2025-04-19 05:10:34,993 INFO Epoch:67 train_loss:0.02102 +2025-04-19 05:10:40,068 INFO Epoch:67 val_res:0.692667 +2025-04-19 05:10:55,324 INFO Epoch:68 train_loss:0.01743 +2025-04-19 05:11:00,009 INFO Epoch:68 val_res:0.692000 +2025-04-19 05:11:14,907 INFO Epoch:69 train_loss:0.01676 +2025-04-19 05:11:20,302 INFO Epoch:69 val_res:0.688667 +2025-04-19 05:11:34,912 INFO Epoch:70 train_loss:0.01451 +2025-04-19 05:11:39,857 INFO Epoch:70 val_res:0.696667 +2025-04-19 05:11:55,173 INFO Epoch:71 train_loss:0.01494 +2025-04-19 05:12:00,185 INFO Epoch:71 val_res:0.683333 +2025-04-19 05:12:13,918 INFO Epoch:72 train_loss:0.01579 +2025-04-19 05:12:19,012 INFO Epoch:72 val_res:0.683333 +2025-04-19 05:12:34,331 INFO Epoch:73 train_loss:0.01527 +2025-04-19 05:12:39,275 INFO Epoch:73 val_res:0.691333 +2025-04-19 05:12:53,527 INFO Epoch:74 train_loss:0.01470 +2025-04-19 05:12:58,918 INFO Epoch:74 val_res:0.684667 +2025-04-19 05:13:14,066 INFO Epoch:75 train_loss:0.02072 +2025-04-19 05:13:18,750 INFO Epoch:75 val_res:0.689333 +2025-04-19 05:13:34,302 INFO Epoch:76 train_loss:0.02357 +2025-04-19 05:13:39,606 INFO Epoch:76 val_res:0.682667 +2025-04-19 05:13:54,835 INFO Epoch:77 train_loss:0.02564 +2025-04-19 05:14:00,008 INFO Epoch:77 val_res:0.684000 +2025-04-19 05:14:16,135 INFO Epoch:78 train_loss:0.02292 +2025-04-19 05:14:20,909 INFO Epoch:78 val_res:0.677333 +2025-04-19 05:14:35,219 INFO Epoch:79 train_loss:0.02223 +2025-04-19 05:14:40,072 INFO Epoch:79 val_res:0.678000 +2025-04-19 05:14:55,461 INFO Epoch:80 train_loss:0.02992 +2025-04-19 05:15:00,016 INFO Epoch:80 val_res:0.681333 +2025-04-19 05:15:14,529 INFO Epoch:81 train_loss:0.03234 +2025-04-19 05:15:19,556 INFO Epoch:81 val_res:0.682000 +2025-04-19 05:15:34,015 INFO Epoch:82 train_loss:0.04353 +2025-04-19 05:15:38,750 INFO Epoch:82 val_res:0.683333 +2025-04-19 05:15:54,005 INFO Epoch:83 train_loss:0.05690 +2025-04-19 05:15:59,392 INFO Epoch:83 val_res:0.680000 +2025-04-19 05:16:13,164 INFO Epoch:84 train_loss:0.04204 +2025-04-19 05:16:18,166 INFO Epoch:84 val_res:0.683333 +2025-04-19 05:16:33,456 INFO Epoch:85 train_loss:0.02810 +2025-04-19 05:16:38,073 INFO Epoch:85 val_res:0.678000 +2025-04-19 05:16:52,198 INFO Epoch:86 train_loss:0.01772 +2025-04-19 05:16:57,421 INFO Epoch:86 val_res:0.679333 +2025-04-19 05:17:12,178 INFO Epoch:87 train_loss:0.02282 +2025-04-19 05:17:16,834 INFO Epoch:87 val_res:0.670000 +2025-04-19 05:17:31,635 INFO Epoch:88 train_loss:0.02366 +2025-04-19 05:17:37,011 INFO Epoch:88 val_res:0.678667 +2025-04-19 05:17:51,484 INFO Epoch:89 train_loss:0.03156 +2025-04-19 05:17:56,401 INFO Epoch:89 val_res:0.677333 +2025-04-19 05:18:11,306 INFO Epoch:90 train_loss:0.03771 +2025-04-19 05:18:16,656 INFO Epoch:90 val_res:0.678667 +2025-04-19 05:18:30,104 INFO Epoch:91 train_loss:0.03187 +2025-04-19 05:18:35,117 INFO Epoch:91 val_res:0.672667 +2025-04-19 05:18:50,324 INFO Epoch:92 train_loss:0.02627 +2025-04-19 05:18:55,062 INFO Epoch:92 val_res:0.674667 +2025-04-19 05:19:09,419 INFO Epoch:93 train_loss:0.02140 +2025-04-19 05:19:14,533 INFO Epoch:93 val_res:0.680667 +2025-04-19 05:19:29,209 INFO Epoch:94 train_loss:0.01946 +2025-04-19 05:19:33,804 INFO Epoch:94 val_res:0.672000 +2025-04-19 05:19:48,887 INFO Epoch:95 train_loss:0.01707 +2025-04-19 05:19:53,851 INFO Epoch:95 val_res:0.674667 +2025-04-19 05:20:08,103 INFO Epoch:96 train_loss:0.03052 +2025-04-19 05:20:13,009 INFO Epoch:96 val_res:0.672667 +2025-04-19 05:20:28,558 INFO Epoch:97 train_loss:0.02944 +2025-04-19 05:20:33,327 INFO Epoch:97 val_res:0.674667 +2025-04-19 05:20:47,991 INFO Epoch:98 train_loss:0.06898 +2025-04-19 05:20:52,739 INFO Epoch:98 val_res:0.672667 +2025-04-19 05:21:07,399 INFO Epoch:99 train_loss:0.07035 +2025-04-19 05:21:12,247 INFO Epoch:99 val_res:0.668000 +2025-04-19 05:21:12,970 INFO ===================================== +2025-04-19 05:21:12,971 INFO Start testing... +2025-04-19 05:21:12,971 INFO ===================================== +2025-04-19 05:21:37,625 INFO Incremental step 2 Testing res: 0.702000 +2025-04-19 05:21:37,626 INFO forgetting: 0.150000 +2025-04-19 05:21:37,628 INFO Incremental step: 3 +2025-04-19 05:22:03,063 INFO Epoch:0 train_loss:2.44476 +2025-04-19 05:22:28,312 INFO Epoch:0 val_res:0.513500 +2025-04-19 05:22:28,313 INFO Saving best model at Epoch 0 +2025-04-19 05:22:45,178 INFO Epoch:1 train_loss:0.87938 +2025-04-19 05:22:51,908 INFO Epoch:1 val_res:0.530500 +2025-04-19 05:22:51,908 INFO Saving best model at Epoch 1 +2025-04-19 05:23:08,335 INFO Epoch:2 train_loss:0.63279 +2025-04-19 05:23:14,930 INFO Epoch:2 val_res:0.524500 +2025-04-19 05:23:29,607 INFO Epoch:3 train_loss:0.53294 +2025-04-19 05:23:36,105 INFO Epoch:3 val_res:0.527500 +2025-04-19 05:23:50,818 INFO Epoch:4 train_loss:0.47625 +2025-04-19 05:23:57,199 INFO Epoch:4 val_res:0.530000 +2025-04-19 05:24:12,326 INFO Epoch:5 train_loss:0.43819 +2025-04-19 05:24:19,101 INFO Epoch:5 val_res:0.532000 +2025-04-19 05:24:19,102 INFO Saving best model at Epoch 5 +2025-04-19 05:24:34,743 INFO Epoch:6 train_loss:0.40123 +2025-04-19 05:24:41,208 INFO Epoch:6 val_res:0.537500 +2025-04-19 05:24:41,209 INFO Saving best model at Epoch 6 +2025-04-19 05:24:57,865 INFO Epoch:7 train_loss:0.37534 +2025-04-19 05:25:03,984 INFO Epoch:7 val_res:0.539500 +2025-04-19 05:25:03,985 INFO Saving best model at Epoch 7 +2025-04-19 05:25:20,908 INFO Epoch:8 train_loss:0.35904 +2025-04-19 05:25:27,519 INFO Epoch:8 val_res:0.542000 +2025-04-19 05:25:27,519 INFO Saving best model at Epoch 8 +2025-04-19 05:25:43,456 INFO Epoch:9 train_loss:0.32084 +2025-04-19 05:25:49,524 INFO Epoch:9 val_res:0.547000 +2025-04-19 05:25:49,524 INFO Saving best model at Epoch 9 +2025-04-19 05:26:05,713 INFO Epoch:10 train_loss:0.30128 +2025-04-19 05:26:12,667 INFO Epoch:10 val_res:0.555500 +2025-04-19 05:26:12,667 INFO Saving best model at Epoch 10 +2025-04-19 05:26:28,123 INFO Epoch:11 train_loss:0.28340 +2025-04-19 05:26:34,287 INFO Epoch:11 val_res:0.562500 +2025-04-19 05:26:34,288 INFO Saving best model at Epoch 11 +2025-04-19 05:26:50,971 INFO Epoch:12 train_loss:0.26336 +2025-04-19 05:26:57,454 INFO Epoch:12 val_res:0.567500 +2025-04-19 05:26:57,454 INFO Saving best model at Epoch 12 +2025-04-19 05:27:13,798 INFO Epoch:13 train_loss:0.24537 +2025-04-19 05:27:20,275 INFO Epoch:13 val_res:0.580500 +2025-04-19 05:27:20,275 INFO Saving best model at Epoch 13 +2025-04-19 05:27:37,232 INFO Epoch:14 train_loss:0.23536 +2025-04-19 05:27:43,250 INFO Epoch:14 val_res:0.580000 +2025-04-19 05:27:57,139 INFO Epoch:15 train_loss:0.22658 +2025-04-19 05:28:03,611 INFO Epoch:15 val_res:0.586000 +2025-04-19 05:28:03,612 INFO Saving best model at Epoch 15 +2025-04-19 05:28:20,357 INFO Epoch:16 train_loss:0.21615 +2025-04-19 05:28:26,644 INFO Epoch:16 val_res:0.587000 +2025-04-19 05:28:26,645 INFO Saving best model at Epoch 16 +2025-04-19 05:28:42,859 INFO Epoch:17 train_loss:0.18876 +2025-04-19 05:28:49,437 INFO Epoch:17 val_res:0.596000 +2025-04-19 05:28:49,444 INFO Saving best model at Epoch 17 +2025-04-19 05:29:05,928 INFO Epoch:18 train_loss:0.17358 +2025-04-19 05:29:11,629 INFO Epoch:18 val_res:0.599000 +2025-04-19 05:29:11,629 INFO Saving best model at Epoch 18 +2025-04-19 05:29:28,783 INFO Epoch:19 train_loss:0.17183 +2025-04-19 05:29:35,421 INFO Epoch:19 val_res:0.591500 +2025-04-19 05:29:49,721 INFO Epoch:20 train_loss:0.17336 +2025-04-19 05:29:55,803 INFO Epoch:20 val_res:0.609000 +2025-04-19 05:29:55,803 INFO Saving best model at Epoch 20 +2025-04-19 05:30:14,526 INFO Epoch:21 train_loss:0.15122 +2025-04-19 05:30:21,358 INFO Epoch:21 val_res:0.607000 +2025-04-19 05:30:36,121 INFO Epoch:22 train_loss:0.13727 +2025-04-19 05:30:42,725 INFO Epoch:22 val_res:0.605000 +2025-04-19 05:30:58,642 INFO Epoch:23 train_loss:0.11649 +2025-04-19 05:31:04,971 INFO Epoch:23 val_res:0.609000 +2025-04-19 05:31:19,351 INFO Epoch:24 train_loss:0.11332 +2025-04-19 05:31:25,650 INFO Epoch:24 val_res:0.611500 +2025-04-19 05:31:25,650 INFO Saving best model at Epoch 24 +2025-04-19 05:31:42,129 INFO Epoch:25 train_loss:0.11337 +2025-04-19 05:31:48,360 INFO Epoch:25 val_res:0.608000 +2025-04-19 05:32:03,163 INFO Epoch:26 train_loss:0.11505 +2025-04-19 05:32:09,582 INFO Epoch:26 val_res:0.616000 +2025-04-19 05:32:09,582 INFO Saving best model at Epoch 26 +2025-04-19 05:32:26,000 INFO Epoch:27 train_loss:0.08967 +2025-04-19 05:32:32,055 INFO Epoch:27 val_res:0.612500 +2025-04-19 05:32:47,017 INFO Epoch:28 train_loss:0.07825 +2025-04-19 05:32:53,352 INFO Epoch:28 val_res:0.608500 +2025-04-19 05:33:07,869 INFO Epoch:29 train_loss:0.08141 +2025-04-19 05:33:13,907 INFO Epoch:29 val_res:0.617000 +2025-04-19 05:33:13,907 INFO Saving best model at Epoch 29 +2025-04-19 05:33:30,848 INFO Epoch:30 train_loss:0.07650 +2025-04-19 05:33:37,333 INFO Epoch:30 val_res:0.612000 +2025-04-19 05:33:51,548 INFO Epoch:31 train_loss:0.11476 +2025-04-19 05:33:57,897 INFO Epoch:31 val_res:0.610500 +2025-04-19 05:34:13,209 INFO Epoch:32 train_loss:0.10679 +2025-04-19 05:34:19,524 INFO Epoch:32 val_res:0.622500 +2025-04-19 05:34:19,524 INFO Saving best model at Epoch 32 +2025-04-19 05:34:35,963 INFO Epoch:33 train_loss:0.06734 +2025-04-19 05:34:42,453 INFO Epoch:33 val_res:0.617000 +2025-04-19 05:34:57,802 INFO Epoch:34 train_loss:0.05736 +2025-04-19 05:35:04,316 INFO Epoch:34 val_res:0.623500 +2025-04-19 05:35:04,316 INFO Saving best model at Epoch 34 +2025-04-19 05:35:20,136 INFO Epoch:35 train_loss:0.05497 +2025-04-19 05:35:26,595 INFO Epoch:35 val_res:0.615500 +2025-04-19 05:35:41,548 INFO Epoch:36 train_loss:0.05041 +2025-04-19 05:35:47,820 INFO Epoch:36 val_res:0.619500 +2025-04-19 05:36:02,439 INFO Epoch:37 train_loss:0.04722 +2025-04-19 05:36:08,972 INFO Epoch:37 val_res:0.606000 +2025-04-19 05:36:23,979 INFO Epoch:38 train_loss:0.05102 +2025-04-19 05:36:29,843 INFO Epoch:38 val_res:0.624500 +2025-04-19 05:36:29,843 INFO Saving best model at Epoch 38 +2025-04-19 05:36:46,857 INFO Epoch:39 train_loss:0.06347 +2025-04-19 05:36:52,863 INFO Epoch:39 val_res:0.607500 +2025-04-19 05:37:07,723 INFO Epoch:40 train_loss:0.06272 +2025-04-19 05:37:13,782 INFO Epoch:40 val_res:0.615500 +2025-04-19 05:37:28,888 INFO Epoch:41 train_loss:0.08071 +2025-04-19 05:37:35,013 INFO Epoch:41 val_res:0.613500 +2025-04-19 05:37:49,755 INFO Epoch:42 train_loss:0.06131 +2025-04-19 05:37:55,920 INFO Epoch:42 val_res:0.618000 +2025-04-19 05:38:10,796 INFO Epoch:43 train_loss:0.05567 +2025-04-19 05:38:17,081 INFO Epoch:43 val_res:0.615500 +2025-04-19 05:38:31,890 INFO Epoch:44 train_loss:0.04756 +2025-04-19 05:38:38,409 INFO Epoch:44 val_res:0.607000 +2025-04-19 05:38:53,086 INFO Epoch:45 train_loss:0.04629 +2025-04-19 05:38:59,607 INFO Epoch:45 val_res:0.606000 +2025-04-19 05:39:14,609 INFO Epoch:46 train_loss:0.07547 +2025-04-19 05:39:21,090 INFO Epoch:46 val_res:0.595500 +2025-04-19 05:39:35,346 INFO Epoch:47 train_loss:0.06604 +2025-04-19 05:39:41,698 INFO Epoch:47 val_res:0.603500 +2025-04-19 05:39:56,628 INFO Epoch:48 train_loss:0.05375 +2025-04-19 05:40:03,388 INFO Epoch:48 val_res:0.607000 +2025-04-19 05:40:17,836 INFO Epoch:49 train_loss:0.04326 +2025-04-19 05:40:24,680 INFO Epoch:49 val_res:0.602500 +2025-04-19 05:40:39,857 INFO Epoch:50 train_loss:0.04033 +2025-04-19 05:40:46,268 INFO Epoch:50 val_res:0.597000 +2025-04-19 05:41:00,969 INFO Epoch:51 train_loss:0.05368 +2025-04-19 05:41:07,490 INFO Epoch:51 val_res:0.601000 +2025-04-19 05:41:22,035 INFO Epoch:52 train_loss:0.05347 +2025-04-19 05:41:28,241 INFO Epoch:52 val_res:0.592500 +2025-04-19 05:41:43,189 INFO Epoch:53 train_loss:0.05002 +2025-04-19 05:41:49,676 INFO Epoch:53 val_res:0.600000 +2025-04-19 05:42:04,137 INFO Epoch:54 train_loss:0.05116 +2025-04-19 05:42:10,153 INFO Epoch:54 val_res:0.589000 +2025-04-19 05:42:25,142 INFO Epoch:55 train_loss:0.04707 +2025-04-19 05:42:31,321 INFO Epoch:55 val_res:0.586000 +2025-04-19 05:42:45,972 INFO Epoch:56 train_loss:0.04431 +2025-04-19 05:42:51,991 INFO Epoch:56 val_res:0.593000 +2025-04-19 05:43:07,498 INFO Epoch:57 train_loss:0.03540 +2025-04-19 05:43:14,026 INFO Epoch:57 val_res:0.599000 +2025-04-19 05:43:28,857 INFO Epoch:58 train_loss:0.03364 +2025-04-19 05:43:35,457 INFO Epoch:58 val_res:0.580000 +2025-04-19 05:43:50,914 INFO Epoch:59 train_loss:0.04230 +2025-04-19 05:43:56,958 INFO Epoch:59 val_res:0.579500 +2025-04-19 05:44:11,979 INFO Epoch:60 train_loss:0.03617 +2025-04-19 05:44:18,675 INFO Epoch:60 val_res:0.588000 +2025-04-19 05:44:33,425 INFO Epoch:61 train_loss:0.08394 +2025-04-19 05:44:39,385 INFO Epoch:61 val_res:0.575500 +2025-04-19 05:44:53,811 INFO Epoch:62 train_loss:0.12650 +2025-04-19 05:45:00,612 INFO Epoch:62 val_res:0.584500 +2025-04-19 05:45:14,984 INFO Epoch:63 train_loss:0.07651 +2025-04-19 05:45:21,127 INFO Epoch:63 val_res:0.574000 +2025-04-19 05:45:36,211 INFO Epoch:64 train_loss:0.05596 +2025-04-19 05:45:42,808 INFO Epoch:64 val_res:0.583000 +2025-04-19 05:45:57,054 INFO Epoch:65 train_loss:0.04311 +2025-04-19 05:46:03,433 INFO Epoch:65 val_res:0.574500 +2025-04-19 05:46:18,559 INFO Epoch:66 train_loss:0.04823 +2025-04-19 05:46:25,077 INFO Epoch:66 val_res:0.584000 +2025-04-19 05:46:39,168 INFO Epoch:67 train_loss:0.04357 +2025-04-19 05:46:45,883 INFO Epoch:67 val_res:0.578500 +2025-04-19 05:47:01,441 INFO Epoch:68 train_loss:0.03401 +2025-04-19 05:47:07,843 INFO Epoch:68 val_res:0.576500 +2025-04-19 05:47:22,286 INFO Epoch:69 train_loss:0.03093 +2025-04-19 05:47:29,273 INFO Epoch:69 val_res:0.587500 +2025-04-19 05:47:44,846 INFO Epoch:70 train_loss:0.02734 +2025-04-19 05:47:50,746 INFO Epoch:70 val_res:0.570000 +2025-04-19 05:48:05,615 INFO Epoch:71 train_loss:0.02976 +2025-04-19 05:48:12,117 INFO Epoch:71 val_res:0.583500 +2025-04-19 05:48:26,883 INFO Epoch:72 train_loss:0.02458 +2025-04-19 05:48:32,740 INFO Epoch:72 val_res:0.577500 +2025-04-19 05:48:48,300 INFO Epoch:73 train_loss:0.02436 +2025-04-19 05:48:55,076 INFO Epoch:73 val_res:0.573500 +2025-04-19 05:49:09,585 INFO Epoch:74 train_loss:0.03256 +2025-04-19 05:49:15,982 INFO Epoch:74 val_res:0.573500 +2025-04-19 05:49:31,872 INFO Epoch:75 train_loss:0.07474 +2025-04-19 05:49:37,827 INFO Epoch:75 val_res:0.573500 +2025-04-19 05:49:52,064 INFO Epoch:76 train_loss:0.06465 +2025-04-19 05:49:58,712 INFO Epoch:76 val_res:0.573500 +2025-04-19 05:50:14,058 INFO Epoch:77 train_loss:0.05685 +2025-04-19 05:50:20,044 INFO Epoch:77 val_res:0.573000 +2025-04-19 05:50:34,722 INFO Epoch:78 train_loss:0.04528 +2025-04-19 05:50:41,461 INFO Epoch:78 val_res:0.579500 +2025-04-19 05:50:56,075 INFO Epoch:79 train_loss:0.03910 +2025-04-19 05:51:02,190 INFO Epoch:79 val_res:0.566000 +2025-04-19 05:51:17,267 INFO Epoch:80 train_loss:0.03263 +2025-04-19 05:51:23,924 INFO Epoch:80 val_res:0.561500 +2025-04-19 05:51:38,005 INFO Epoch:81 train_loss:0.02987 +2025-04-19 05:51:44,477 INFO Epoch:81 val_res:0.564000 +2025-04-19 05:51:59,899 INFO Epoch:82 train_loss:0.03481 +2025-04-19 05:52:06,543 INFO Epoch:82 val_res:0.566500 +2025-04-19 05:52:20,753 INFO Epoch:83 train_loss:0.07694 +2025-04-19 05:52:27,122 INFO Epoch:83 val_res:0.568000 +2025-04-19 05:52:42,793 INFO Epoch:84 train_loss:0.06034 +2025-04-19 05:52:49,555 INFO Epoch:84 val_res:0.567000 +2025-04-19 05:53:03,798 INFO Epoch:85 train_loss:0.04474 +2025-04-19 05:53:10,718 INFO Epoch:85 val_res:0.569500 +2025-04-19 05:53:25,677 INFO Epoch:86 train_loss:0.04225 +2025-04-19 05:53:32,291 INFO Epoch:86 val_res:0.562000 +2025-04-19 05:53:46,960 INFO Epoch:87 train_loss:0.03363 +2025-04-19 05:53:53,756 INFO Epoch:87 val_res:0.571500 +2025-04-19 05:54:08,404 INFO Epoch:88 train_loss:0.02469 +2025-04-19 05:54:14,534 INFO Epoch:88 val_res:0.566500 +2025-04-19 05:54:29,606 INFO Epoch:89 train_loss:0.03311 +2025-04-19 05:54:35,834 INFO Epoch:89 val_res:0.557500 +2025-04-19 05:54:50,789 INFO Epoch:90 train_loss:0.03682 +2025-04-19 05:54:56,924 INFO Epoch:90 val_res:0.562500 +2025-04-19 05:55:12,060 INFO Epoch:91 train_loss:0.04952 +2025-04-19 05:55:18,159 INFO Epoch:91 val_res:0.575500 +2025-04-19 05:55:33,212 INFO Epoch:92 train_loss:0.11885 +2025-04-19 05:55:39,597 INFO Epoch:92 val_res:0.548500 +2025-04-19 05:55:54,237 INFO Epoch:93 train_loss:0.09181 +2025-04-19 05:56:00,708 INFO Epoch:93 val_res:0.559500 +2025-04-19 05:56:15,429 INFO Epoch:94 train_loss:0.06363 +2025-04-19 05:56:21,940 INFO Epoch:94 val_res:0.554000 +2025-04-19 05:56:36,117 INFO Epoch:95 train_loss:0.03345 +2025-04-19 05:56:42,745 INFO Epoch:95 val_res:0.559000 +2025-04-19 05:56:57,420 INFO Epoch:96 train_loss:0.03085 +2025-04-19 05:57:03,614 INFO Epoch:96 val_res:0.550500 +2025-04-19 05:57:18,396 INFO Epoch:97 train_loss:0.03724 +2025-04-19 05:57:24,746 INFO Epoch:97 val_res:0.554500 +2025-04-19 05:57:39,125 INFO Epoch:98 train_loss:0.04843 +2025-04-19 05:57:45,532 INFO Epoch:98 val_res:0.551000 +2025-04-19 05:58:00,979 INFO Epoch:99 train_loss:0.07646 +2025-04-19 05:58:07,356 INFO Epoch:99 val_res:0.551500 +2025-04-19 05:58:08,101 INFO ===================================== +2025-04-19 05:58:08,101 INFO Start testing... +2025-04-19 05:58:08,101 INFO ===================================== +2025-04-19 05:58:20,518 INFO Incremental step 3 Testing res: 0.610500 +2025-04-19 05:58:20,520 INFO forgetting: 0.184667 +2025-04-19 05:58:20,521 INFO Incremental step: 4 +2025-04-19 05:59:08,746 INFO Epoch:0 train_loss:2.76141 +2025-04-19 05:59:28,902 INFO Epoch:0 val_res:0.492400 +2025-04-19 05:59:28,902 INFO Saving best model at Epoch 0 +2025-04-19 05:59:45,682 INFO Epoch:1 train_loss:0.93493 +2025-04-19 05:59:53,810 INFO Epoch:1 val_res:0.496000 +2025-04-19 05:59:53,810 INFO Saving best model at Epoch 1 +2025-04-19 06:00:11,026 INFO Epoch:2 train_loss:0.59951 +2025-04-19 06:00:18,212 INFO Epoch:2 val_res:0.493600 +2025-04-19 06:00:33,220 INFO Epoch:3 train_loss:0.47847 +2025-04-19 06:00:41,190 INFO Epoch:3 val_res:0.496000 +2025-04-19 06:00:55,609 INFO Epoch:4 train_loss:0.41291 +2025-04-19 06:01:03,072 INFO Epoch:4 val_res:0.498000 +2025-04-19 06:01:03,073 INFO Saving best model at Epoch 4 +2025-04-19 06:01:20,100 INFO Epoch:5 train_loss:0.36861 +2025-04-19 06:01:27,584 INFO Epoch:5 val_res:0.503200 +2025-04-19 06:01:27,584 INFO Saving best model at Epoch 5 +2025-04-19 06:01:42,954 INFO Epoch:6 train_loss:0.33262 +2025-04-19 06:01:51,156 INFO Epoch:6 val_res:0.504000 +2025-04-19 06:01:51,157 INFO Saving best model at Epoch 6 +2025-04-19 06:02:07,877 INFO Epoch:7 train_loss:0.30461 +2025-04-19 06:02:15,273 INFO Epoch:7 val_res:0.506800 +2025-04-19 06:02:15,274 INFO Saving best model at Epoch 7 +2025-04-19 06:02:32,180 INFO Epoch:8 train_loss:0.28076 +2025-04-19 06:02:40,374 INFO Epoch:8 val_res:0.508400 +2025-04-19 06:02:40,374 INFO Saving best model at Epoch 8 +2025-04-19 06:02:56,766 INFO Epoch:9 train_loss:0.28869 +2025-04-19 06:03:04,702 INFO Epoch:9 val_res:0.512000 +2025-04-19 06:03:04,703 INFO Saving best model at Epoch 9 +2025-04-19 06:03:21,464 INFO Epoch:10 train_loss:0.23787 +2025-04-19 06:03:29,402 INFO Epoch:10 val_res:0.514400 +2025-04-19 06:03:29,402 INFO Saving best model at Epoch 10 +2025-04-19 06:03:45,598 INFO Epoch:11 train_loss:0.23619 +2025-04-19 06:03:53,876 INFO Epoch:11 val_res:0.515200 +2025-04-19 06:03:53,877 INFO Saving best model at Epoch 11 +2025-04-19 06:04:09,914 INFO Epoch:12 train_loss:0.21959 +2025-04-19 06:04:17,495 INFO Epoch:12 val_res:0.520800 +2025-04-19 06:04:17,496 INFO Saving best model at Epoch 12 +2025-04-19 06:04:33,806 INFO Epoch:13 train_loss:0.19721 +2025-04-19 06:04:42,386 INFO Epoch:13 val_res:0.520400 +2025-04-19 06:04:55,489 INFO Epoch:14 train_loss:0.18836 +2025-04-19 06:05:03,820 INFO Epoch:14 val_res:0.524400 +2025-04-19 06:05:03,821 INFO Saving best model at Epoch 14 +2025-04-19 06:05:20,567 INFO Epoch:15 train_loss:0.18785 +2025-04-19 06:05:29,044 INFO Epoch:15 val_res:0.528000 +2025-04-19 06:05:29,044 INFO Saving best model at Epoch 15 +2025-04-19 06:05:44,976 INFO Epoch:16 train_loss:0.17316 +2025-04-19 06:05:53,637 INFO Epoch:16 val_res:0.530000 +2025-04-19 06:05:53,637 INFO Saving best model at Epoch 16 +2025-04-19 06:06:10,618 INFO Epoch:17 train_loss:0.15968 +2025-04-19 06:06:18,442 INFO Epoch:17 val_res:0.528800 +2025-04-19 06:06:33,230 INFO Epoch:18 train_loss:0.16466 +2025-04-19 06:06:41,627 INFO Epoch:18 val_res:0.535200 +2025-04-19 06:06:41,627 INFO Saving best model at Epoch 18 +2025-04-19 06:06:56,988 INFO Epoch:19 train_loss:0.15043 +2025-04-19 06:07:05,382 INFO Epoch:19 val_res:0.542000 +2025-04-19 06:07:05,382 INFO Saving best model at Epoch 19 +2025-04-19 06:07:22,112 INFO Epoch:20 train_loss:0.13147 +2025-04-19 06:07:29,224 INFO Epoch:20 val_res:0.545200 +2025-04-19 06:07:29,224 INFO Saving best model at Epoch 20 +2025-04-19 06:07:44,925 INFO Epoch:21 train_loss:0.11919 +2025-04-19 06:07:53,346 INFO Epoch:21 val_res:0.545600 +2025-04-19 06:07:53,346 INFO Saving best model at Epoch 21 +2025-04-19 06:08:09,094 INFO Epoch:22 train_loss:0.10829 +2025-04-19 06:08:17,031 INFO Epoch:22 val_res:0.544400 +2025-04-19 06:08:31,851 INFO Epoch:23 train_loss:0.12669 +2025-04-19 06:08:40,178 INFO Epoch:23 val_res:0.547200 +2025-04-19 06:08:40,179 INFO Saving best model at Epoch 23 +2025-04-19 06:08:55,250 INFO Epoch:24 train_loss:0.12972 +2025-04-19 06:09:03,404 INFO Epoch:24 val_res:0.549200 +2025-04-19 06:09:03,411 INFO Saving best model at Epoch 24 +2025-04-19 06:09:20,578 INFO Epoch:25 train_loss:0.10304 +2025-04-19 06:09:28,074 INFO Epoch:25 val_res:0.549600 +2025-04-19 06:09:28,074 INFO Saving best model at Epoch 25 +2025-04-19 06:09:44,896 INFO Epoch:26 train_loss:0.09277 +2025-04-19 06:09:53,000 INFO Epoch:26 val_res:0.550800 +2025-04-19 06:09:53,000 INFO Saving best model at Epoch 26 +2025-04-19 06:10:09,553 INFO Epoch:27 train_loss:0.08125 +2025-04-19 06:10:17,278 INFO Epoch:27 val_res:0.548400 +2025-04-19 06:10:32,058 INFO Epoch:28 train_loss:0.11047 +2025-04-19 06:10:40,252 INFO Epoch:28 val_res:0.548000 +2025-04-19 06:10:54,044 INFO Epoch:29 train_loss:0.12565 +2025-04-19 06:11:02,587 INFO Epoch:29 val_res:0.550400 +2025-04-19 06:11:16,775 INFO Epoch:30 train_loss:0.15404 +2025-04-19 06:11:24,286 INFO Epoch:30 val_res:0.554000 +2025-04-19 06:11:24,287 INFO Saving best model at Epoch 30 +2025-04-19 06:11:40,050 INFO Epoch:31 train_loss:0.12996 +2025-04-19 06:11:48,054 INFO Epoch:31 val_res:0.555600 +2025-04-19 06:11:48,055 INFO Saving best model at Epoch 31 +2025-04-19 06:12:04,269 INFO Epoch:32 train_loss:0.10086 +2025-04-19 06:12:12,127 INFO Epoch:32 val_res:0.555200 +2025-04-19 06:12:26,442 INFO Epoch:33 train_loss:0.07463 +2025-04-19 06:12:34,090 INFO Epoch:33 val_res:0.548000 +2025-04-19 06:12:48,953 INFO Epoch:34 train_loss:0.06427 +2025-04-19 06:12:56,860 INFO Epoch:34 val_res:0.557600 +2025-04-19 06:12:56,860 INFO Saving best model at Epoch 34 +2025-04-19 06:13:14,310 INFO Epoch:35 train_loss:0.05323 +2025-04-19 06:13:22,058 INFO Epoch:35 val_res:0.552400 +2025-04-19 06:13:37,047 INFO Epoch:36 train_loss:0.04570 +2025-04-19 06:13:44,781 INFO Epoch:36 val_res:0.551600 +2025-04-19 06:13:59,296 INFO Epoch:37 train_loss:0.04300 +2025-04-19 06:14:07,175 INFO Epoch:37 val_res:0.554800 +2025-04-19 06:14:21,086 INFO Epoch:38 train_loss:0.04451 +2025-04-19 06:14:28,761 INFO Epoch:38 val_res:0.554000 +2025-04-19 06:14:43,301 INFO Epoch:39 train_loss:0.04129 +2025-04-19 06:14:51,353 INFO Epoch:39 val_res:0.553600 +2025-04-19 06:15:05,949 INFO Epoch:40 train_loss:0.04230 +2025-04-19 06:15:13,555 INFO Epoch:40 val_res:0.550000 +2025-04-19 06:15:28,794 INFO Epoch:41 train_loss:0.04786 +2025-04-19 06:15:36,454 INFO Epoch:41 val_res:0.556800 +2025-04-19 06:15:51,624 INFO Epoch:42 train_loss:0.04697 +2025-04-19 06:15:59,528 INFO Epoch:42 val_res:0.553200 +2025-04-19 06:16:14,792 INFO Epoch:43 train_loss:0.06008 +2025-04-19 06:16:22,456 INFO Epoch:43 val_res:0.554000 +2025-04-19 06:16:37,245 INFO Epoch:44 train_loss:0.10008 +2025-04-19 06:16:45,114 INFO Epoch:44 val_res:0.553600 +2025-04-19 06:16:59,501 INFO Epoch:45 train_loss:0.11491 +2025-04-19 06:17:07,267 INFO Epoch:45 val_res:0.548400 +2025-04-19 06:17:22,328 INFO Epoch:46 train_loss:0.09900 +2025-04-19 06:17:30,286 INFO Epoch:46 val_res:0.551600 +2025-04-19 06:17:44,780 INFO Epoch:47 train_loss:0.06484 +2025-04-19 06:17:53,151 INFO Epoch:47 val_res:0.552800 +2025-04-19 06:18:07,736 INFO Epoch:48 train_loss:0.06433 +2025-04-19 06:18:15,303 INFO Epoch:48 val_res:0.544000 +2025-04-19 06:18:29,468 INFO Epoch:49 train_loss:0.04424 +2025-04-19 06:18:37,791 INFO Epoch:49 val_res:0.549600 +2025-04-19 06:18:51,772 INFO Epoch:50 train_loss:0.04236 +2025-04-19 06:18:59,802 INFO Epoch:50 val_res:0.551200 +2025-04-19 06:19:15,148 INFO Epoch:51 train_loss:0.03897 +2025-04-19 06:19:22,953 INFO Epoch:51 val_res:0.548400 +2025-04-19 06:19:36,347 INFO Epoch:52 train_loss:0.03712 +2025-04-19 06:19:44,397 INFO Epoch:52 val_res:0.546400 +2025-04-19 06:19:59,038 INFO Epoch:53 train_loss:0.03938 +2025-04-19 06:20:06,546 INFO Epoch:53 val_res:0.544800 +2025-04-19 06:20:20,684 INFO Epoch:54 train_loss:0.07389 +2025-04-19 06:20:29,105 INFO Epoch:54 val_res:0.552800 +2025-04-19 06:20:44,369 INFO Epoch:55 train_loss:0.07134 +2025-04-19 06:20:51,985 INFO Epoch:55 val_res:0.550800 +2025-04-19 06:21:07,438 INFO Epoch:56 train_loss:0.04723 +2025-04-19 06:21:16,212 INFO Epoch:56 val_res:0.541200 +2025-04-19 06:21:30,549 INFO Epoch:57 train_loss:0.03921 +2025-04-19 06:21:38,356 INFO Epoch:57 val_res:0.545600 +2025-04-19 06:21:54,225 INFO Epoch:58 train_loss:0.03952 +2025-04-19 06:22:01,833 INFO Epoch:58 val_res:0.542800 +2025-04-19 06:22:16,002 INFO Epoch:59 train_loss:0.04189 +2025-04-19 06:22:24,278 INFO Epoch:59 val_res:0.542800 +2025-04-19 06:22:39,471 INFO Epoch:60 train_loss:0.03985 +2025-04-19 06:22:46,850 INFO Epoch:60 val_res:0.539600 +2025-04-19 06:23:01,445 INFO Epoch:61 train_loss:0.04160 +2025-04-19 06:23:09,815 INFO Epoch:61 val_res:0.541600 +2025-04-19 06:23:24,472 INFO Epoch:62 train_loss:0.07251 +2025-04-19 06:23:32,013 INFO Epoch:62 val_res:0.539600 +2025-04-19 06:23:46,764 INFO Epoch:63 train_loss:0.06036 +2025-04-19 06:23:55,001 INFO Epoch:63 val_res:0.540400 +2025-04-19 06:24:08,597 INFO Epoch:64 train_loss:0.04291 +2025-04-19 06:24:16,550 INFO Epoch:64 val_res:0.542800 +2025-04-19 06:24:31,478 INFO Epoch:65 train_loss:0.05187 +2025-04-19 06:24:39,576 INFO Epoch:65 val_res:0.537200 +2025-04-19 06:24:53,574 INFO Epoch:66 train_loss:0.06168 +2025-04-19 06:25:02,121 INFO Epoch:66 val_res:0.532800 +2025-04-19 06:25:16,798 INFO Epoch:67 train_loss:0.08087 +2025-04-19 06:25:24,864 INFO Epoch:67 val_res:0.534000 +2025-04-19 06:25:39,442 INFO Epoch:68 train_loss:0.07909 +2025-04-19 06:25:47,878 INFO Epoch:68 val_res:0.529600 +2025-04-19 06:26:03,253 INFO Epoch:69 train_loss:0.04937 +2025-04-19 06:26:11,545 INFO Epoch:69 val_res:0.534000 +2025-04-19 06:26:26,326 INFO Epoch:70 train_loss:0.04228 +2025-04-19 06:26:34,756 INFO Epoch:70 val_res:0.536000 +2025-04-19 06:26:49,096 INFO Epoch:71 train_loss:0.04208 +2025-04-19 06:26:57,249 INFO Epoch:71 val_res:0.535600 +2025-04-19 06:27:12,179 INFO Epoch:72 train_loss:0.03840 +2025-04-19 06:27:20,521 INFO Epoch:72 val_res:0.536400 +2025-04-19 06:27:35,263 INFO Epoch:73 train_loss:0.03715 +2025-04-19 06:27:43,533 INFO Epoch:73 val_res:0.532800 +2025-04-19 06:27:58,364 INFO Epoch:74 train_loss:0.04149 +2025-04-19 06:28:06,954 INFO Epoch:74 val_res:0.532800 +2025-04-19 06:28:21,676 INFO Epoch:75 train_loss:0.04855 +2025-04-19 06:28:29,612 INFO Epoch:75 val_res:0.537200 +2025-04-19 06:28:44,428 INFO Epoch:76 train_loss:0.05990 +2025-04-19 06:28:52,677 INFO Epoch:76 val_res:0.531200 +2025-04-19 06:29:07,443 INFO Epoch:77 train_loss:0.04603 +2025-04-19 06:29:14,970 INFO Epoch:77 val_res:0.529600 +2025-04-19 06:29:29,578 INFO Epoch:78 train_loss:0.03764 +2025-04-19 06:29:37,711 INFO Epoch:78 val_res:0.529600 +2025-04-19 06:29:51,799 INFO Epoch:79 train_loss:0.03201 +2025-04-19 06:29:59,448 INFO Epoch:79 val_res:0.530400 +2025-04-19 06:30:14,105 INFO Epoch:80 train_loss:0.03877 +2025-04-19 06:30:22,397 INFO Epoch:80 val_res:0.523600 +2025-04-19 06:30:37,244 INFO Epoch:81 train_loss:0.05130 +2025-04-19 06:30:44,616 INFO Epoch:81 val_res:0.521600 +2025-04-19 06:30:58,895 INFO Epoch:82 train_loss:0.08062 +2025-04-19 06:31:07,006 INFO Epoch:82 val_res:0.530800 +2025-04-19 06:31:20,705 INFO Epoch:83 train_loss:0.07292 +2025-04-19 06:31:28,932 INFO Epoch:83 val_res:0.523200 +2025-04-19 06:31:43,706 INFO Epoch:84 train_loss:0.04846 +2025-04-19 06:31:52,105 INFO Epoch:84 val_res:0.522800 +2025-04-19 06:32:06,386 INFO Epoch:85 train_loss:0.04808 +2025-04-19 06:32:13,846 INFO Epoch:85 val_res:0.526800 +2025-04-19 06:32:28,788 INFO Epoch:86 train_loss:0.04687 +2025-04-19 06:32:37,040 INFO Epoch:86 val_res:0.525600 +2025-04-19 06:32:51,480 INFO Epoch:87 train_loss:0.04297 +2025-04-19 06:32:58,999 INFO Epoch:87 val_res:0.519200 +2025-04-19 06:33:14,375 INFO Epoch:88 train_loss:0.05278 +2025-04-19 06:33:22,251 INFO Epoch:88 val_res:0.525200 +2025-04-19 06:33:36,944 INFO Epoch:89 train_loss:0.05443 +2025-04-19 06:33:44,717 INFO Epoch:89 val_res:0.526000 +2025-04-19 06:33:59,818 INFO Epoch:90 train_loss:0.04903 +2025-04-19 06:34:07,657 INFO Epoch:90 val_res:0.512400 +2025-04-19 06:34:22,173 INFO Epoch:91 train_loss:0.04518 +2025-04-19 06:34:29,698 INFO Epoch:91 val_res:0.517200 +2025-04-19 06:34:44,835 INFO Epoch:92 train_loss:0.03856 +2025-04-19 06:34:52,671 INFO Epoch:92 val_res:0.517200 +2025-04-19 06:35:07,300 INFO Epoch:93 train_loss:0.03521 +2025-04-19 06:35:15,242 INFO Epoch:93 val_res:0.516400 +2025-04-19 06:35:30,101 INFO Epoch:94 train_loss:0.08633 +2025-04-19 06:35:37,932 INFO Epoch:94 val_res:0.520000 +2025-04-19 06:35:52,354 INFO Epoch:95 train_loss:0.06025 +2025-04-19 06:36:00,666 INFO Epoch:95 val_res:0.512000 +2025-04-19 06:36:15,033 INFO Epoch:96 train_loss:0.05124 +2025-04-19 06:36:23,058 INFO Epoch:96 val_res:0.515600 +2025-04-19 06:36:37,550 INFO Epoch:97 train_loss:0.03883 +2025-04-19 06:36:45,765 INFO Epoch:97 val_res:0.512400 +2025-04-19 06:37:00,630 INFO Epoch:98 train_loss:0.03262 +2025-04-19 06:37:08,875 INFO Epoch:98 val_res:0.512000 +2025-04-19 06:37:23,610 INFO Epoch:99 train_loss:0.03253 +2025-04-19 06:37:31,416 INFO Epoch:99 val_res:0.514800 +2025-04-19 06:37:32,255 INFO ===================================== +2025-04-19 06:37:32,256 INFO Start testing... +2025-04-19 06:37:32,256 INFO ===================================== +2025-04-19 06:37:42,473 INFO Incremental step 4 Testing res: 0.555200 +2025-04-19 06:37:42,475 INFO forgetting: 0.192500 +2025-04-19 06:37:42,477 INFO Incremental step: 5 +2025-04-19 06:39:09,586 INFO Epoch:0 train_loss:3.51730 +2025-04-19 06:39:26,604 INFO Epoch:0 val_res:0.443667 +2025-04-19 06:39:26,605 INFO Saving best model at Epoch 0 +2025-04-19 06:39:42,960 INFO Epoch:1 train_loss:1.00689 +2025-04-19 06:39:52,915 INFO Epoch:1 val_res:0.459000 +2025-04-19 06:39:52,915 INFO Saving best model at Epoch 1 +2025-04-19 06:40:09,762 INFO Epoch:2 train_loss:0.59304 +2025-04-19 06:40:19,386 INFO Epoch:2 val_res:0.460667 +2025-04-19 06:40:19,387 INFO Saving best model at Epoch 2 +2025-04-19 06:40:35,976 INFO Epoch:3 train_loss:0.45268 +2025-04-19 06:40:46,658 INFO Epoch:3 val_res:0.460667 +2025-04-19 06:41:01,200 INFO Epoch:4 train_loss:0.39735 +2025-04-19 06:41:11,912 INFO Epoch:4 val_res:0.458667 +2025-04-19 06:41:26,844 INFO Epoch:5 train_loss:0.36141 +2025-04-19 06:41:38,261 INFO Epoch:5 val_res:0.460667 +2025-04-19 06:41:52,468 INFO Epoch:6 train_loss:0.33118 +2025-04-19 06:42:03,523 INFO Epoch:6 val_res:0.462333 +2025-04-19 06:42:03,523 INFO Saving best model at Epoch 6 +2025-04-19 06:42:20,500 INFO Epoch:7 train_loss:0.30809 +2025-04-19 06:42:30,892 INFO Epoch:7 val_res:0.463000 +2025-04-19 06:42:30,892 INFO Saving best model at Epoch 7 +2025-04-19 06:42:48,563 INFO Epoch:8 train_loss:0.29048 +2025-04-19 06:42:59,689 INFO Epoch:8 val_res:0.462000 +2025-04-19 06:43:14,359 INFO Epoch:9 train_loss:0.27508 +2025-04-19 06:43:25,318 INFO Epoch:9 val_res:0.464000 +2025-04-19 06:43:25,318 INFO Saving best model at Epoch 9 +2025-04-19 06:43:42,388 INFO Epoch:10 train_loss:0.25552 +2025-04-19 06:43:53,933 INFO Epoch:10 val_res:0.469000 +2025-04-19 06:43:53,933 INFO Saving best model at Epoch 10 +2025-04-19 06:44:11,650 INFO Epoch:11 train_loss:0.23874 +2025-04-19 06:44:23,018 INFO Epoch:11 val_res:0.468000 +2025-04-19 06:44:38,411 INFO Epoch:12 train_loss:0.22992 +2025-04-19 06:44:49,075 INFO Epoch:12 val_res:0.468333 +2025-04-19 06:45:04,302 INFO Epoch:13 train_loss:0.21592 +2025-04-19 06:45:15,994 INFO Epoch:13 val_res:0.472667 +2025-04-19 06:45:15,995 INFO Saving best model at Epoch 13 +2025-04-19 06:45:32,758 INFO Epoch:14 train_loss:0.20333 +2025-04-19 06:45:43,383 INFO Epoch:14 val_res:0.475667 +2025-04-19 06:45:43,384 INFO Saving best model at Epoch 14 +2025-04-19 06:46:00,010 INFO Epoch:15 train_loss:0.19430 +2025-04-19 06:46:11,345 INFO Epoch:15 val_res:0.476000 +2025-04-19 06:46:11,346 INFO Saving best model at Epoch 15 +2025-04-19 06:46:27,375 INFO Epoch:16 train_loss:0.18308 +2025-04-19 06:46:38,557 INFO Epoch:16 val_res:0.481667 +2025-04-19 06:46:38,558 INFO Saving best model at Epoch 16 +2025-04-19 06:46:56,361 INFO Epoch:17 train_loss:0.17207 +2025-04-19 06:47:07,047 INFO Epoch:17 val_res:0.483667 +2025-04-19 06:47:07,048 INFO Saving best model at Epoch 17 +2025-04-19 06:47:24,012 INFO Epoch:18 train_loss:0.15972 +2025-04-19 06:47:35,670 INFO Epoch:18 val_res:0.486000 +2025-04-19 06:47:35,671 INFO Saving best model at Epoch 18 +2025-04-19 06:47:52,320 INFO Epoch:19 train_loss:0.15471 +2025-04-19 06:48:03,100 INFO Epoch:19 val_res:0.487667 +2025-04-19 06:48:03,100 INFO Saving best model at Epoch 19 +2025-04-19 06:48:20,198 INFO Epoch:20 train_loss:0.15118 +2025-04-19 06:48:31,934 INFO Epoch:20 val_res:0.492667 +2025-04-19 06:48:31,934 INFO Saving best model at Epoch 20 +2025-04-19 06:48:48,300 INFO Epoch:21 train_loss:0.14559 +2025-04-19 06:48:59,307 INFO Epoch:21 val_res:0.499333 +2025-04-19 06:48:59,307 INFO Saving best model at Epoch 21 +2025-04-19 06:49:16,303 INFO Epoch:22 train_loss:0.14002 +2025-04-19 06:49:26,904 INFO Epoch:22 val_res:0.497333 +2025-04-19 06:49:41,472 INFO Epoch:23 train_loss:0.12933 +2025-04-19 06:49:52,495 INFO Epoch:23 val_res:0.497667 +2025-04-19 06:50:08,565 INFO Epoch:24 train_loss:0.11394 +2025-04-19 06:50:18,608 INFO Epoch:24 val_res:0.496667 +2025-04-19 06:50:34,201 INFO Epoch:25 train_loss:0.13791 +2025-04-19 06:50:44,450 INFO Epoch:25 val_res:0.500333 +2025-04-19 06:50:44,451 INFO Saving best model at Epoch 25 +2025-04-19 06:50:59,207 INFO Epoch:26 train_loss:0.12247 +2025-04-19 06:51:08,602 INFO Epoch:26 val_res:0.501667 +2025-04-19 06:51:08,603 INFO Saving best model at Epoch 26 +2025-04-19 06:51:23,407 INFO Epoch:27 train_loss:0.09870 +2025-04-19 06:51:32,713 INFO Epoch:27 val_res:0.509333 +2025-04-19 06:51:32,714 INFO Saving best model at Epoch 27 +2025-04-19 06:51:47,071 INFO Epoch:28 train_loss:0.09461 +2025-04-19 06:51:56,618 INFO Epoch:28 val_res:0.503333 +2025-04-19 06:52:09,798 INFO Epoch:29 train_loss:0.08667 +2025-04-19 06:52:18,555 INFO Epoch:29 val_res:0.506667 +2025-04-19 06:52:32,119 INFO Epoch:30 train_loss:0.07906 +2025-04-19 06:52:41,787 INFO Epoch:30 val_res:0.503333 +2025-04-19 06:52:56,370 INFO Epoch:31 train_loss:0.08681 +2025-04-19 06:53:06,516 INFO Epoch:31 val_res:0.508667 +2025-04-19 06:53:20,397 INFO Epoch:32 train_loss:0.11058 +2025-04-19 06:53:30,558 INFO Epoch:32 val_res:0.505667 +2025-04-19 06:53:44,953 INFO Epoch:33 train_loss:0.08036 +2025-04-19 06:53:55,034 INFO Epoch:33 val_res:0.508000 +2025-04-19 06:54:09,311 INFO Epoch:34 train_loss:0.07291 +2025-04-19 06:54:19,864 INFO Epoch:34 val_res:0.509000 +2025-04-19 06:54:34,372 INFO Epoch:35 train_loss:0.07080 +2025-04-19 06:54:44,194 INFO Epoch:35 val_res:0.510333 +2025-04-19 06:54:44,195 INFO Saving best model at Epoch 35 +2025-04-19 06:55:00,307 INFO Epoch:36 train_loss:0.07452 +2025-04-19 06:55:09,883 INFO Epoch:36 val_res:0.509667 +2025-04-19 06:55:24,654 INFO Epoch:37 train_loss:0.07241 +2025-04-19 06:55:34,373 INFO Epoch:37 val_res:0.507667 +2025-04-19 06:55:49,805 INFO Epoch:38 train_loss:0.06606 +2025-04-19 06:55:59,764 INFO Epoch:38 val_res:0.509333 +2025-04-19 06:56:14,676 INFO Epoch:39 train_loss:0.06108 +2025-04-19 06:56:25,191 INFO Epoch:39 val_res:0.509667 +2025-04-19 06:56:39,961 INFO Epoch:40 train_loss:0.07161 +2025-04-19 06:56:49,779 INFO Epoch:40 val_res:0.504333 +2025-04-19 06:57:04,164 INFO Epoch:41 train_loss:0.10227 +2025-04-19 06:57:14,292 INFO Epoch:41 val_res:0.508667 +2025-04-19 06:57:29,107 INFO Epoch:42 train_loss:0.08031 +2025-04-19 06:57:39,671 INFO Epoch:42 val_res:0.504333 +2025-04-19 06:57:54,094 INFO Epoch:43 train_loss:0.10117 +2025-04-19 06:58:04,609 INFO Epoch:43 val_res:0.503000 +2025-04-19 06:58:19,745 INFO Epoch:44 train_loss:0.12422 +2025-04-19 06:58:30,233 INFO Epoch:44 val_res:0.503667 +2025-04-19 06:58:44,903 INFO Epoch:45 train_loss:0.08589 +2025-04-19 06:58:54,718 INFO Epoch:45 val_res:0.501000 +2025-04-19 06:59:09,894 INFO Epoch:46 train_loss:0.06332 +2025-04-19 06:59:20,348 INFO Epoch:46 val_res:0.500667 +2025-04-19 06:59:35,314 INFO Epoch:47 train_loss:0.04407 +2025-04-19 06:59:45,497 INFO Epoch:47 val_res:0.494000 +2025-04-19 07:00:00,645 INFO Epoch:48 train_loss:0.03795 +2025-04-19 07:00:10,898 INFO Epoch:48 val_res:0.498000 +2025-04-19 07:00:25,023 INFO Epoch:49 train_loss:0.03323 +2025-04-19 07:00:35,668 INFO Epoch:49 val_res:0.501333 +2025-04-19 07:00:50,275 INFO Epoch:50 train_loss:0.03385 +2025-04-19 07:01:01,134 INFO Epoch:50 val_res:0.502667 +2025-04-19 07:01:15,710 INFO Epoch:51 train_loss:0.03445 +2025-04-19 07:01:25,957 INFO Epoch:51 val_res:0.493667 +2025-04-19 07:01:40,398 INFO Epoch:52 train_loss:0.03711 +2025-04-19 07:01:51,162 INFO Epoch:52 val_res:0.495000 +2025-04-19 07:02:05,985 INFO Epoch:53 train_loss:0.03463 +2025-04-19 07:02:16,825 INFO Epoch:53 val_res:0.492000 +2025-04-19 07:02:31,685 INFO Epoch:54 train_loss:0.03565 +2025-04-19 07:02:43,000 INFO Epoch:54 val_res:0.493333 +2025-04-19 07:02:58,551 INFO Epoch:55 train_loss:0.06288 +2025-04-19 07:03:08,859 INFO Epoch:55 val_res:0.491000 +2025-04-19 07:03:23,429 INFO Epoch:56 train_loss:0.05251 +2025-04-19 07:03:34,097 INFO Epoch:56 val_res:0.488667 +2025-04-19 07:03:48,652 INFO Epoch:57 train_loss:0.04089 +2025-04-19 07:03:59,077 INFO Epoch:57 val_res:0.489667 +2025-04-19 07:04:13,994 INFO Epoch:58 train_loss:0.05001 +2025-04-19 07:04:24,707 INFO Epoch:58 val_res:0.488000 +2025-04-19 07:04:39,370 INFO Epoch:59 train_loss:0.06864 +2025-04-19 07:04:49,346 INFO Epoch:59 val_res:0.487667 +2025-04-19 07:05:04,913 INFO Epoch:60 train_loss:0.07727 +2025-04-19 07:05:15,030 INFO Epoch:60 val_res:0.482667 +2025-04-19 07:05:29,422 INFO Epoch:61 train_loss:0.09564 +2025-04-19 07:05:39,698 INFO Epoch:61 val_res:0.487333 +2025-04-19 07:05:54,642 INFO Epoch:62 train_loss:0.07564 +2025-04-19 07:06:04,388 INFO Epoch:62 val_res:0.487000 +2025-04-19 07:06:19,689 INFO Epoch:63 train_loss:0.05585 +2025-04-19 07:06:30,525 INFO Epoch:63 val_res:0.483000 +2025-04-19 07:06:45,317 INFO Epoch:64 train_loss:0.03865 +2025-04-19 07:06:55,392 INFO Epoch:64 val_res:0.481000 +2025-04-19 07:07:10,563 INFO Epoch:65 train_loss:0.04190 +2025-04-19 07:07:21,242 INFO Epoch:65 val_res:0.481000 +2025-04-19 07:07:35,947 INFO Epoch:66 train_loss:0.04536 +2025-04-19 07:07:46,415 INFO Epoch:66 val_res:0.480333 +2025-04-19 07:08:01,840 INFO Epoch:67 train_loss:0.03964 +2025-04-19 07:08:13,022 INFO Epoch:67 val_res:0.475333 +2025-04-19 07:08:28,028 INFO Epoch:68 train_loss:0.03137 +2025-04-19 07:08:39,840 INFO Epoch:68 val_res:0.480000 +2025-04-19 07:08:55,431 INFO Epoch:69 train_loss:0.03502 +2025-04-19 07:09:05,527 INFO Epoch:69 val_res:0.483000 +2025-04-19 07:09:20,678 INFO Epoch:70 train_loss:0.03542 +2025-04-19 07:09:31,594 INFO Epoch:70 val_res:0.482000 +2025-04-19 07:09:47,071 INFO Epoch:71 train_loss:0.03097 +2025-04-19 07:09:57,385 INFO Epoch:71 val_res:0.476333 +2025-04-19 07:10:14,015 INFO Epoch:72 train_loss:0.05760 +2025-04-19 07:10:24,609 INFO Epoch:72 val_res:0.473000 +2025-04-19 07:10:39,580 INFO Epoch:73 train_loss:0.10000 +2025-04-19 07:10:49,978 INFO Epoch:73 val_res:0.484667 +2025-04-19 07:11:05,886 INFO Epoch:74 train_loss:0.08185 +2025-04-19 07:11:16,418 INFO Epoch:74 val_res:0.475000 +2025-04-19 07:11:31,050 INFO Epoch:75 train_loss:0.05734 +2025-04-19 07:11:41,554 INFO Epoch:75 val_res:0.470000 +2025-04-19 07:11:57,656 INFO Epoch:76 train_loss:0.07194 +2025-04-19 07:12:07,809 INFO Epoch:76 val_res:0.470000 +2025-04-19 07:12:23,663 INFO Epoch:77 train_loss:0.05683 +2025-04-19 07:12:34,815 INFO Epoch:77 val_res:0.469667 +2025-04-19 07:12:49,829 INFO Epoch:78 train_loss:0.04447 +2025-04-19 07:12:59,425 INFO Epoch:78 val_res:0.467333 +2025-04-19 07:13:15,077 INFO Epoch:79 train_loss:0.04936 +2025-04-19 07:13:25,358 INFO Epoch:79 val_res:0.466000 +2025-04-19 07:13:39,898 INFO Epoch:80 train_loss:0.04823 +2025-04-19 07:13:50,717 INFO Epoch:80 val_res:0.468667 +2025-04-19 07:14:05,950 INFO Epoch:81 train_loss:0.04444 +2025-04-19 07:14:16,406 INFO Epoch:81 val_res:0.475000 +2025-04-19 07:14:31,220 INFO Epoch:82 train_loss:0.03260 +2025-04-19 07:14:42,042 INFO Epoch:82 val_res:0.468000 +2025-04-19 07:14:57,613 INFO Epoch:83 train_loss:0.03191 +2025-04-19 07:15:07,597 INFO Epoch:83 val_res:0.469667 +2025-04-19 07:15:22,575 INFO Epoch:84 train_loss:0.03598 +2025-04-19 07:15:32,941 INFO Epoch:84 val_res:0.464333 +2025-04-19 07:15:47,810 INFO Epoch:85 train_loss:0.04560 +2025-04-19 07:15:57,862 INFO Epoch:85 val_res:0.462333 +2025-04-19 07:16:13,426 INFO Epoch:86 train_loss:0.07490 +2025-04-19 07:16:24,026 INFO Epoch:86 val_res:0.460000 +2025-04-19 07:16:38,421 INFO Epoch:87 train_loss:0.08269 +2025-04-19 07:16:49,085 INFO Epoch:87 val_res:0.461667 +2025-04-19 07:17:04,579 INFO Epoch:88 train_loss:0.05617 +2025-04-19 07:17:14,309 INFO Epoch:88 val_res:0.459667 +2025-04-19 07:17:29,136 INFO Epoch:89 train_loss:0.04272 +2025-04-19 07:17:40,129 INFO Epoch:89 val_res:0.462667 +2025-04-19 07:17:55,730 INFO Epoch:90 train_loss:0.03791 +2025-04-19 07:18:05,274 INFO Epoch:90 val_res:0.460667 +2025-04-19 07:18:20,661 INFO Epoch:91 train_loss:0.04752 +2025-04-19 07:18:30,836 INFO Epoch:91 val_res:0.462000 +2025-04-19 07:18:45,386 INFO Epoch:92 train_loss:0.05990 +2025-04-19 07:18:56,030 INFO Epoch:92 val_res:0.460333 +2025-04-19 07:19:11,275 INFO Epoch:93 train_loss:0.05503 +2025-04-19 07:19:22,264 INFO Epoch:93 val_res:0.456333 +2025-04-19 07:19:36,556 INFO Epoch:94 train_loss:0.04090 +2025-04-19 07:19:47,738 INFO Epoch:94 val_res:0.456333 +2025-04-19 07:20:03,979 INFO Epoch:95 train_loss:0.03661 +2025-04-19 07:20:14,490 INFO Epoch:95 val_res:0.458333 +2025-04-19 07:20:29,909 INFO Epoch:96 train_loss:0.03046 +2025-04-19 07:20:40,767 INFO Epoch:96 val_res:0.459667 +2025-04-19 07:20:55,958 INFO Epoch:97 train_loss:0.05234 +2025-04-19 07:21:06,813 INFO Epoch:97 val_res:0.461000 +2025-04-19 07:21:22,311 INFO Epoch:98 train_loss:0.07535 +2025-04-19 07:21:32,989 INFO Epoch:98 val_res:0.458333 +2025-04-19 07:21:47,855 INFO Epoch:99 train_loss:0.05212 +2025-04-19 07:21:58,653 INFO Epoch:99 val_res:0.451667 +2025-04-19 07:21:59,345 INFO ===================================== +2025-04-19 07:21:59,346 INFO Start testing... +2025-04-19 07:21:59,346 INFO ===================================== +2025-04-19 07:22:25,985 INFO Incremental step 5 Testing res: 0.509000 +2025-04-19 07:22:25,988 INFO forgetting: 0.201600 +2025-04-19 07:22:25,989 INFO Incremental step: 6 +2025-04-19 07:25:34,299 INFO Epoch:0 train_loss:3.00776 +2025-04-19 07:25:55,928 INFO Epoch:0 val_res:0.428286 +2025-04-19 07:25:55,929 INFO Saving best model at Epoch 0 +2025-04-19 07:26:16,936 INFO Epoch:1 train_loss:0.74273 +2025-04-19 07:26:30,002 INFO Epoch:1 val_res:0.433143 +2025-04-19 07:26:30,003 INFO Saving best model at Epoch 1 +2025-04-19 07:26:50,723 INFO Epoch:2 train_loss:0.39750 +2025-04-19 07:27:03,471 INFO Epoch:2 val_res:0.437143 +2025-04-19 07:27:03,471 INFO Saving best model at Epoch 2 +2025-04-19 07:27:23,095 INFO Epoch:3 train_loss:0.30837 +2025-04-19 07:27:36,184 INFO Epoch:3 val_res:0.441714 +2025-04-19 07:27:36,184 INFO Saving best model at Epoch 3 +2025-04-19 07:27:55,215 INFO Epoch:4 train_loss:0.26561 +2025-04-19 07:28:08,616 INFO Epoch:4 val_res:0.445429 +2025-04-19 07:28:08,616 INFO Saving best model at Epoch 4 +2025-04-19 07:28:28,485 INFO Epoch:5 train_loss:0.24217 +2025-04-19 07:28:41,308 INFO Epoch:5 val_res:0.444571 +2025-04-19 07:29:00,191 INFO Epoch:6 train_loss:0.22256 +2025-04-19 07:29:13,687 INFO Epoch:6 val_res:0.446857 +2025-04-19 07:29:13,688 INFO Saving best model at Epoch 6 +2025-04-19 07:29:33,347 INFO Epoch:7 train_loss:0.20598 +2025-04-19 07:29:47,035 INFO Epoch:7 val_res:0.448857 +2025-04-19 07:29:47,035 INFO Saving best model at Epoch 7 +2025-04-19 07:30:06,134 INFO Epoch:8 train_loss:0.19403 +2025-04-19 07:30:19,146 INFO Epoch:8 val_res:0.451714 +2025-04-19 07:30:19,146 INFO Saving best model at Epoch 8 +2025-04-19 07:30:38,941 INFO Epoch:9 train_loss:0.18249 +2025-04-19 07:30:52,039 INFO Epoch:9 val_res:0.453714 +2025-04-19 07:30:52,040 INFO Saving best model at Epoch 9 +2025-04-19 07:31:10,893 INFO Epoch:10 train_loss:0.16967 +2025-04-19 07:31:25,160 INFO Epoch:10 val_res:0.454857 +2025-04-19 07:31:25,160 INFO Saving best model at Epoch 10 +2025-04-19 07:31:44,418 INFO Epoch:11 train_loss:0.16098 +2025-04-19 07:31:57,914 INFO Epoch:11 val_res:0.458571 +2025-04-19 07:31:57,915 INFO Saving best model at Epoch 11 +2025-04-19 07:32:17,365 INFO Epoch:12 train_loss:0.15351 +2025-04-19 07:32:31,330 INFO Epoch:12 val_res:0.461714 +2025-04-19 07:32:31,330 INFO Saving best model at Epoch 12 +2025-04-19 07:32:50,194 INFO Epoch:13 train_loss:0.14761 +2025-04-19 07:33:04,110 INFO Epoch:13 val_res:0.464857 +2025-04-19 07:33:04,111 INFO Saving best model at Epoch 13 +2025-04-19 07:33:23,376 INFO Epoch:14 train_loss:0.13918 +2025-04-19 07:33:35,759 INFO Epoch:14 val_res:0.464571 +2025-04-19 07:33:52,703 INFO Epoch:15 train_loss:0.13560 +2025-04-19 07:34:04,595 INFO Epoch:15 val_res:0.467143 +2025-04-19 07:34:04,595 INFO Saving best model at Epoch 15 +2025-04-19 07:34:23,083 INFO Epoch:16 train_loss:0.14866 +2025-04-19 07:34:36,235 INFO Epoch:16 val_res:0.472000 +2025-04-19 07:34:36,235 INFO Saving best model at Epoch 16 +2025-04-19 07:34:54,499 INFO Epoch:17 train_loss:0.15739 +2025-04-19 07:35:07,741 INFO Epoch:17 val_res:0.472286 +2025-04-19 07:35:07,741 INFO Saving best model at Epoch 17 +2025-04-19 07:35:26,719 INFO Epoch:18 train_loss:0.13408 +2025-04-19 07:35:38,754 INFO Epoch:18 val_res:0.476286 +2025-04-19 07:35:38,755 INFO Saving best model at Epoch 18 +2025-04-19 07:35:57,424 INFO Epoch:19 train_loss:0.11750 +2025-04-19 07:36:10,358 INFO Epoch:19 val_res:0.479429 +2025-04-19 07:36:10,359 INFO Saving best model at Epoch 19 +2025-04-19 07:36:28,373 INFO Epoch:20 train_loss:0.11130 +2025-04-19 07:36:41,978 INFO Epoch:20 val_res:0.480286 +2025-04-19 07:36:41,979 INFO Saving best model at Epoch 20 +2025-04-19 07:37:00,537 INFO Epoch:21 train_loss:0.10097 +2025-04-19 07:37:13,274 INFO Epoch:21 val_res:0.482286 +2025-04-19 07:37:13,275 INFO Saving best model at Epoch 21 +2025-04-19 07:37:31,855 INFO Epoch:22 train_loss:0.10442 +2025-04-19 07:37:42,757 INFO Epoch:22 val_res:0.487143 +2025-04-19 07:37:42,757 INFO Saving best model at Epoch 22 +2025-04-19 07:37:59,217 INFO Epoch:23 train_loss:0.10533 +2025-04-19 07:38:09,937 INFO Epoch:23 val_res:0.486857 +2025-04-19 07:38:25,707 INFO Epoch:24 train_loss:0.13927 +2025-04-19 07:38:36,133 INFO Epoch:24 val_res:0.492000 +2025-04-19 07:38:36,133 INFO Saving best model at Epoch 24 +2025-04-19 07:38:52,700 INFO Epoch:25 train_loss:0.14392 +2025-04-19 07:39:04,985 INFO Epoch:25 val_res:0.490571 +2025-04-19 07:39:19,723 INFO Epoch:26 train_loss:0.10705 +2025-04-19 07:39:32,257 INFO Epoch:26 val_res:0.489429 +2025-04-19 07:39:48,988 INFO Epoch:27 train_loss:0.10129 +2025-04-19 07:40:01,874 INFO Epoch:27 val_res:0.495143 +2025-04-19 07:40:01,874 INFO Saving best model at Epoch 27 +2025-04-19 07:40:19,541 INFO Epoch:28 train_loss:0.08085 +2025-04-19 07:40:31,619 INFO Epoch:28 val_res:0.496000 +2025-04-19 07:40:31,620 INFO Saving best model at Epoch 28 +2025-04-19 07:40:50,318 INFO Epoch:29 train_loss:0.07190 +2025-04-19 07:41:01,058 INFO Epoch:29 val_res:0.495429 +2025-04-19 07:41:17,060 INFO Epoch:30 train_loss:0.07871 +2025-04-19 07:41:29,356 INFO Epoch:30 val_res:0.490571 +2025-04-19 07:41:45,247 INFO Epoch:31 train_loss:0.08388 +2025-04-19 07:41:57,712 INFO Epoch:31 val_res:0.495429 +2025-04-19 07:42:14,300 INFO Epoch:32 train_loss:0.09104 +2025-04-19 07:42:26,358 INFO Epoch:32 val_res:0.494571 +2025-04-19 07:42:42,696 INFO Epoch:33 train_loss:0.08814 +2025-04-19 07:42:56,159 INFO Epoch:33 val_res:0.494286 +2025-04-19 07:43:13,058 INFO Epoch:34 train_loss:0.07679 +2025-04-19 07:43:26,573 INFO Epoch:34 val_res:0.496857 +2025-04-19 07:43:26,573 INFO Saving best model at Epoch 34 +2025-04-19 07:43:45,349 INFO Epoch:35 train_loss:0.07629 +2025-04-19 07:43:58,391 INFO Epoch:35 val_res:0.492857 +2025-04-19 07:44:16,205 INFO Epoch:36 train_loss:0.06245 +2025-04-19 07:44:28,525 INFO Epoch:36 val_res:0.489143 +2025-04-19 07:44:45,915 INFO Epoch:37 train_loss:0.06462 +2025-04-19 07:44:58,513 INFO Epoch:37 val_res:0.494857 +2025-04-19 07:45:15,128 INFO Epoch:38 train_loss:0.05792 +2025-04-19 07:45:26,142 INFO Epoch:38 val_res:0.496286 +2025-04-19 07:45:40,466 INFO Epoch:39 train_loss:0.06184 +2025-04-19 07:45:51,559 INFO Epoch:39 val_res:0.495143 +2025-04-19 07:46:05,472 INFO Epoch:40 train_loss:0.07499 +2025-04-19 07:46:16,618 INFO Epoch:40 val_res:0.494857 +2025-04-19 07:46:31,454 INFO Epoch:41 train_loss:0.08089 +2025-04-19 07:46:41,765 INFO Epoch:41 val_res:0.488857 +2025-04-19 07:46:55,567 INFO Epoch:42 train_loss:0.06283 +2025-04-19 07:47:06,619 INFO Epoch:42 val_res:0.488286 +2025-04-19 07:47:20,347 INFO Epoch:43 train_loss:0.07581 +2025-04-19 07:47:30,152 INFO Epoch:43 val_res:0.491714 +2025-04-19 07:47:44,739 INFO Epoch:44 train_loss:0.08638 +2025-04-19 07:47:55,551 INFO Epoch:44 val_res:0.484857 +2025-04-19 07:48:08,946 INFO Epoch:45 train_loss:0.11704 +2025-04-19 07:48:19,937 INFO Epoch:45 val_res:0.489429 +2025-04-19 07:48:34,386 INFO Epoch:46 train_loss:0.09798 +2025-04-19 07:48:44,749 INFO Epoch:46 val_res:0.487714 +2025-04-19 07:48:58,727 INFO Epoch:47 train_loss:0.06505 +2025-04-19 07:49:10,353 INFO Epoch:47 val_res:0.482286 +2025-04-19 07:49:24,118 INFO Epoch:48 train_loss:0.04825 +2025-04-19 07:49:35,024 INFO Epoch:48 val_res:0.482857 +2025-04-19 07:49:48,980 INFO Epoch:49 train_loss:0.04097 +2025-04-19 07:49:59,878 INFO Epoch:49 val_res:0.481143 +2025-04-19 07:50:13,332 INFO Epoch:50 train_loss:0.04458 +2025-04-19 07:50:24,724 INFO Epoch:50 val_res:0.483429 +2025-04-19 07:50:38,891 INFO Epoch:51 train_loss:0.04184 +2025-04-19 07:50:50,184 INFO Epoch:51 val_res:0.478000 +2025-04-19 07:51:04,136 INFO Epoch:52 train_loss:0.04769 +2025-04-19 07:51:15,749 INFO Epoch:52 val_res:0.481714 +2025-04-19 07:51:30,921 INFO Epoch:53 train_loss:0.05612 +2025-04-19 07:51:42,265 INFO Epoch:53 val_res:0.479143 +2025-04-19 07:51:56,678 INFO Epoch:54 train_loss:0.04330 +2025-04-19 07:52:07,870 INFO Epoch:54 val_res:0.473714 +2025-04-19 07:52:21,387 INFO Epoch:55 train_loss:0.06193 +2025-04-19 07:52:32,606 INFO Epoch:55 val_res:0.474857 +2025-04-19 07:52:46,496 INFO Epoch:56 train_loss:0.06117 +2025-04-19 07:52:57,908 INFO Epoch:56 val_res:0.474286 +2025-04-19 07:53:12,212 INFO Epoch:57 train_loss:0.06068 +2025-04-19 07:53:23,341 INFO Epoch:57 val_res:0.475143 +2025-04-19 07:53:37,020 INFO Epoch:58 train_loss:0.06508 +2025-04-19 07:53:47,790 INFO Epoch:58 val_res:0.472286 +2025-04-19 07:54:01,507 INFO Epoch:59 train_loss:0.06315 +2025-04-19 07:54:12,329 INFO Epoch:59 val_res:0.467143 +2025-04-19 07:54:26,351 INFO Epoch:60 train_loss:0.08263 +2025-04-19 07:54:36,784 INFO Epoch:60 val_res:0.460857 +2025-04-19 07:54:50,994 INFO Epoch:61 train_loss:0.06508 +2025-04-19 07:55:01,429 INFO Epoch:61 val_res:0.466286 +2025-04-19 07:55:16,158 INFO Epoch:62 train_loss:0.04703 +2025-04-19 07:55:26,979 INFO Epoch:62 val_res:0.465714 +2025-04-19 07:55:41,357 INFO Epoch:63 train_loss:0.03815 +2025-04-19 07:55:52,740 INFO Epoch:63 val_res:0.468571 +2025-04-19 07:56:07,752 INFO Epoch:64 train_loss:0.05220 +2025-04-19 07:56:18,444 INFO Epoch:64 val_res:0.468571 +2025-04-19 07:56:33,743 INFO Epoch:65 train_loss:0.09305 +2025-04-19 07:56:44,747 INFO Epoch:65 val_res:0.462857 +2025-04-19 07:56:58,177 INFO Epoch:66 train_loss:0.12832 +2025-04-19 07:57:08,644 INFO Epoch:66 val_res:0.460000 +2025-04-19 07:57:23,270 INFO Epoch:67 train_loss:0.07623 +2025-04-19 07:57:33,794 INFO Epoch:67 val_res:0.458571 +2025-04-19 07:57:47,486 INFO Epoch:68 train_loss:0.04913 +2025-04-19 07:57:58,672 INFO Epoch:68 val_res:0.463429 +2025-04-19 07:58:12,675 INFO Epoch:69 train_loss:0.03951 +2025-04-19 07:58:22,748 INFO Epoch:69 val_res:0.459714 +2025-04-19 07:58:36,333 INFO Epoch:70 train_loss:0.03412 +2025-04-19 07:58:47,575 INFO Epoch:70 val_res:0.454857 +2025-04-19 07:59:01,024 INFO Epoch:71 train_loss:0.03501 +2025-04-19 07:59:11,484 INFO Epoch:71 val_res:0.456857 +2025-04-19 07:59:26,154 INFO Epoch:72 train_loss:0.04158 +2025-04-19 07:59:37,779 INFO Epoch:72 val_res:0.452857 +2025-04-19 07:59:50,934 INFO Epoch:73 train_loss:0.03683 +2025-04-19 08:00:02,001 INFO Epoch:73 val_res:0.454857 +2025-04-19 08:00:16,139 INFO Epoch:74 train_loss:0.04188 +2025-04-19 08:00:26,444 INFO Epoch:74 val_res:0.453429 +2025-04-19 08:00:40,239 INFO Epoch:75 train_loss:0.04093 +2025-04-19 08:00:51,849 INFO Epoch:75 val_res:0.453714 +2025-04-19 08:01:05,068 INFO Epoch:76 train_loss:0.10578 +2025-04-19 08:01:15,402 INFO Epoch:76 val_res:0.446857 +2025-04-19 08:01:29,934 INFO Epoch:77 train_loss:0.08392 +2025-04-19 08:01:40,647 INFO Epoch:77 val_res:0.449429 +2025-04-19 08:01:53,743 INFO Epoch:78 train_loss:0.05394 +2025-04-19 08:02:03,978 INFO Epoch:78 val_res:0.450000 +2025-04-19 08:02:18,729 INFO Epoch:79 train_loss:0.04365 +2025-04-19 08:02:28,466 INFO Epoch:79 val_res:0.445429 +2025-04-19 08:02:42,184 INFO Epoch:80 train_loss:0.04098 +2025-04-19 08:02:53,485 INFO Epoch:80 val_res:0.445429 +2025-04-19 08:03:07,311 INFO Epoch:81 train_loss:0.04335 +2025-04-19 08:03:17,555 INFO Epoch:81 val_res:0.444286 +2025-04-19 08:03:31,408 INFO Epoch:82 train_loss:0.04390 +2025-04-19 08:03:43,139 INFO Epoch:82 val_res:0.439143 +2025-04-19 08:03:56,120 INFO Epoch:83 train_loss:0.05298 +2025-04-19 08:04:06,102 INFO Epoch:83 val_res:0.444571 +2025-04-19 08:04:20,048 INFO Epoch:84 train_loss:0.05215 +2025-04-19 08:04:30,908 INFO Epoch:84 val_res:0.440857 +2025-04-19 08:04:43,978 INFO Epoch:85 train_loss:0.04660 +2025-04-19 08:04:54,709 INFO Epoch:85 val_res:0.439714 +2025-04-19 08:05:09,050 INFO Epoch:86 train_loss:0.05346 +2025-04-19 08:05:19,193 INFO Epoch:86 val_res:0.440857 +2025-04-19 08:05:32,393 INFO Epoch:87 train_loss:0.10430 +2025-04-19 08:05:43,783 INFO Epoch:87 val_res:0.433714 +2025-04-19 08:05:57,553 INFO Epoch:88 train_loss:0.13827 +2025-04-19 08:06:07,861 INFO Epoch:88 val_res:0.436286 +2025-04-19 08:06:22,005 INFO Epoch:89 train_loss:0.08821 +2025-04-19 08:06:33,913 INFO Epoch:89 val_res:0.433143 +2025-04-19 08:06:47,417 INFO Epoch:90 train_loss:0.05742 +2025-04-19 08:06:57,696 INFO Epoch:90 val_res:0.435714 +2025-04-19 08:07:12,479 INFO Epoch:91 train_loss:0.03764 +2025-04-19 08:07:23,205 INFO Epoch:91 val_res:0.435714 +2025-04-19 08:07:36,487 INFO Epoch:92 train_loss:0.02965 +2025-04-19 08:07:47,425 INFO Epoch:92 val_res:0.434000 +2025-04-19 08:08:01,977 INFO Epoch:93 train_loss:0.02437 +2025-04-19 08:08:12,207 INFO Epoch:93 val_res:0.432571 +2025-04-19 08:08:26,712 INFO Epoch:94 train_loss:0.02376 +2025-04-19 08:08:37,568 INFO Epoch:94 val_res:0.431143 +2025-04-19 08:08:51,428 INFO Epoch:95 train_loss:0.03158 +2025-04-19 08:09:02,127 INFO Epoch:95 val_res:0.432286 +2025-04-19 08:09:16,703 INFO Epoch:96 train_loss:0.04751 +2025-04-19 08:09:27,437 INFO Epoch:96 val_res:0.434286 +2025-04-19 08:09:41,218 INFO Epoch:97 train_loss:0.04289 +2025-04-19 08:09:52,420 INFO Epoch:97 val_res:0.428571 +2025-04-19 08:10:06,337 INFO Epoch:98 train_loss:0.06931 +2025-04-19 08:10:16,538 INFO Epoch:98 val_res:0.430571 +2025-04-19 08:10:30,787 INFO Epoch:99 train_loss:0.06158 +2025-04-19 08:10:41,357 INFO Epoch:99 val_res:0.425714 +2025-04-19 08:10:42,412 INFO ===================================== +2025-04-19 08:10:42,413 INFO Start testing... +2025-04-19 08:10:42,413 INFO ===================================== +2025-04-19 08:11:13,684 INFO Incremental step 6 Testing res: 0.492286 +2025-04-19 08:11:13,687 INFO forgetting: 0.205333 +2025-04-19 08:11:13,689 INFO Incremental step: 7 +2025-04-19 08:14:52,530 INFO Epoch:0 train_loss:2.54561 +2025-04-19 08:15:20,535 INFO Epoch:0 val_res:0.425500 +2025-04-19 08:15:20,536 INFO Saving best model at Epoch 0 +2025-04-19 08:15:45,956 INFO Epoch:1 train_loss:0.80182 +2025-04-19 08:15:58,145 INFO Epoch:1 val_res:0.435250 +2025-04-19 08:15:58,145 INFO Saving best model at Epoch 1 +2025-04-19 08:16:20,983 INFO Epoch:2 train_loss:0.57521 +2025-04-19 08:16:34,471 INFO Epoch:2 val_res:0.434000 +2025-04-19 08:16:54,576 INFO Epoch:3 train_loss:0.49421 +2025-04-19 08:17:08,113 INFO Epoch:3 val_res:0.434500 +2025-04-19 08:17:27,803 INFO Epoch:4 train_loss:0.44135 +2025-04-19 08:17:41,134 INFO Epoch:4 val_res:0.434500 +2025-04-19 08:18:02,135 INFO Epoch:5 train_loss:0.40612 +2025-04-19 08:18:15,035 INFO Epoch:5 val_res:0.436750 +2025-04-19 08:18:15,035 INFO Saving best model at Epoch 5 +2025-04-19 08:18:37,635 INFO Epoch:6 train_loss:0.37195 +2025-04-19 08:18:51,407 INFO Epoch:6 val_res:0.437500 +2025-04-19 08:18:51,407 INFO Saving best model at Epoch 6 +2025-04-19 08:19:13,328 INFO Epoch:7 train_loss:0.34836 +2025-04-19 08:19:27,531 INFO Epoch:7 val_res:0.439750 +2025-04-19 08:19:27,532 INFO Saving best model at Epoch 7 +2025-04-19 08:19:49,064 INFO Epoch:8 train_loss:0.33082 +2025-04-19 08:20:02,705 INFO Epoch:8 val_res:0.442250 +2025-04-19 08:20:02,705 INFO Saving best model at Epoch 8 +2025-04-19 08:20:24,295 INFO Epoch:9 train_loss:0.30801 +2025-04-19 08:20:37,041 INFO Epoch:9 val_res:0.444500 +2025-04-19 08:20:37,041 INFO Saving best model at Epoch 9 +2025-04-19 08:20:59,023 INFO Epoch:10 train_loss:0.28191 +2025-04-19 08:21:11,668 INFO Epoch:10 val_res:0.448500 +2025-04-19 08:21:11,669 INFO Saving best model at Epoch 10 +2025-04-19 08:21:34,224 INFO Epoch:11 train_loss:0.29293 +2025-04-19 08:21:48,002 INFO Epoch:11 val_res:0.449750 +2025-04-19 08:21:48,002 INFO Saving best model at Epoch 11 +2025-04-19 08:22:09,902 INFO Epoch:12 train_loss:0.26186 +2025-04-19 08:22:23,885 INFO Epoch:12 val_res:0.448000 +2025-04-19 08:22:43,364 INFO Epoch:13 train_loss:0.23090 +2025-04-19 08:22:57,382 INFO Epoch:13 val_res:0.454750 +2025-04-19 08:22:57,382 INFO Saving best model at Epoch 13 +2025-04-19 08:23:19,635 INFO Epoch:14 train_loss:0.24133 +2025-04-19 08:23:32,554 INFO Epoch:14 val_res:0.454000 +2025-04-19 08:23:53,102 INFO Epoch:15 train_loss:0.23134 +2025-04-19 08:24:06,329 INFO Epoch:15 val_res:0.459000 +2025-04-19 08:24:06,330 INFO Saving best model at Epoch 15 +2025-04-19 08:24:28,176 INFO Epoch:16 train_loss:0.21902 +2025-04-19 08:24:41,347 INFO Epoch:16 val_res:0.461750 +2025-04-19 08:24:41,348 INFO Saving best model at Epoch 16 +2025-04-19 08:25:03,313 INFO Epoch:17 train_loss:0.20613 +2025-04-19 08:25:15,970 INFO Epoch:17 val_res:0.464000 +2025-04-19 08:25:15,971 INFO Saving best model at Epoch 17 +2025-04-19 08:25:35,911 INFO Epoch:18 train_loss:0.22492 +2025-04-19 08:25:47,785 INFO Epoch:18 val_res:0.467250 +2025-04-19 08:25:47,785 INFO Saving best model at Epoch 18 +2025-04-19 08:26:07,070 INFO Epoch:19 train_loss:0.17815 +2025-04-19 08:26:19,597 INFO Epoch:19 val_res:0.468500 +2025-04-19 08:26:19,597 INFO Saving best model at Epoch 19 +2025-04-19 08:26:39,441 INFO Epoch:20 train_loss:0.15684 +2025-04-19 08:26:52,527 INFO Epoch:20 val_res:0.470250 +2025-04-19 08:26:52,533 INFO Saving best model at Epoch 20 +2025-04-19 08:27:14,151 INFO Epoch:21 train_loss:0.15021 +2025-04-19 08:27:26,356 INFO Epoch:21 val_res:0.472250 +2025-04-19 08:27:26,357 INFO Saving best model at Epoch 21 +2025-04-19 08:27:47,064 INFO Epoch:22 train_loss:0.13262 +2025-04-19 08:27:59,807 INFO Epoch:22 val_res:0.471750 +2025-04-19 08:28:19,380 INFO Epoch:23 train_loss:0.11932 +2025-04-19 08:28:31,943 INFO Epoch:23 val_res:0.475500 +2025-04-19 08:28:31,944 INFO Saving best model at Epoch 23 +2025-04-19 08:28:53,471 INFO Epoch:24 train_loss:0.16308 +2025-04-19 08:29:05,996 INFO Epoch:24 val_res:0.481750 +2025-04-19 08:29:05,996 INFO Saving best model at Epoch 24 +2025-04-19 08:29:28,098 INFO Epoch:25 train_loss:0.16978 +2025-04-19 08:29:40,595 INFO Epoch:25 val_res:0.477250 +2025-04-19 08:30:01,041 INFO Epoch:26 train_loss:0.12237 +2025-04-19 08:30:12,762 INFO Epoch:26 val_res:0.478500 +2025-04-19 08:30:32,570 INFO Epoch:27 train_loss:0.12446 +2025-04-19 08:30:45,447 INFO Epoch:27 val_res:0.478500 +2025-04-19 08:31:04,195 INFO Epoch:28 train_loss:0.10593 +2025-04-19 08:31:17,822 INFO Epoch:28 val_res:0.479000 +2025-04-19 08:31:37,295 INFO Epoch:29 train_loss:0.09996 +2025-04-19 08:31:51,315 INFO Epoch:29 val_res:0.478250 +2025-04-19 08:32:11,086 INFO Epoch:30 train_loss:0.10194 +2025-04-19 08:32:25,105 INFO Epoch:30 val_res:0.474000 +2025-04-19 08:32:44,849 INFO Epoch:31 train_loss:0.11123 +2025-04-19 08:32:57,985 INFO Epoch:31 val_res:0.477000 +2025-04-19 08:33:18,274 INFO Epoch:32 train_loss:0.10290 +2025-04-19 08:33:31,137 INFO Epoch:32 val_res:0.473250 +2025-04-19 08:33:51,759 INFO Epoch:33 train_loss:0.10015 +2025-04-19 08:34:04,530 INFO Epoch:33 val_res:0.473500 +2025-04-19 08:34:25,655 INFO Epoch:34 train_loss:0.13073 +2025-04-19 08:34:38,100 INFO Epoch:34 val_res:0.474250 +2025-04-19 08:34:58,641 INFO Epoch:35 train_loss:0.09570 +2025-04-19 08:35:11,826 INFO Epoch:35 val_res:0.474750 +2025-04-19 08:35:30,877 INFO Epoch:36 train_loss:0.10404 +2025-04-19 08:35:43,578 INFO Epoch:36 val_res:0.472750 +2025-04-19 08:36:03,681 INFO Epoch:37 train_loss:0.10706 +2025-04-19 08:36:15,962 INFO Epoch:37 val_res:0.470750 +2025-04-19 08:36:36,348 INFO Epoch:38 train_loss:0.08797 +2025-04-19 08:36:49,625 INFO Epoch:38 val_res:0.468250 +2025-04-19 08:37:09,117 INFO Epoch:39 train_loss:0.06761 +2025-04-19 08:37:23,634 INFO Epoch:39 val_res:0.471000 +2025-04-19 08:37:42,692 INFO Epoch:40 train_loss:0.08146 +2025-04-19 08:37:56,844 INFO Epoch:40 val_res:0.471000 +2025-04-19 08:38:16,908 INFO Epoch:41 train_loss:0.07968 +2025-04-19 08:38:30,226 INFO Epoch:41 val_res:0.471750 +2025-04-19 08:38:50,568 INFO Epoch:42 train_loss:0.08242 +2025-04-19 08:39:03,277 INFO Epoch:42 val_res:0.469250 +2025-04-19 08:39:22,892 INFO Epoch:43 train_loss:0.10690 +2025-04-19 08:39:36,329 INFO Epoch:43 val_res:0.463250 +2025-04-19 08:39:55,638 INFO Epoch:44 train_loss:0.12430 +2025-04-19 08:40:08,727 INFO Epoch:44 val_res:0.467750 +2025-04-19 08:40:29,616 INFO Epoch:45 train_loss:0.08589 +2025-04-19 08:40:42,741 INFO Epoch:45 val_res:0.470500 +2025-04-19 08:41:03,579 INFO Epoch:46 train_loss:0.07148 +2025-04-19 08:41:15,977 INFO Epoch:46 val_res:0.466000 +2025-04-19 08:41:35,772 INFO Epoch:47 train_loss:0.05959 +2025-04-19 08:41:49,736 INFO Epoch:47 val_res:0.467000 +2025-04-19 08:42:09,367 INFO Epoch:48 train_loss:0.05297 +2025-04-19 08:42:22,928 INFO Epoch:48 val_res:0.466250 +2025-04-19 08:42:43,256 INFO Epoch:49 train_loss:0.05664 +2025-04-19 08:42:55,879 INFO Epoch:49 val_res:0.469000 +2025-04-19 08:43:16,132 INFO Epoch:50 train_loss:0.06477 +2025-04-19 08:43:28,760 INFO Epoch:50 val_res:0.462750 +2025-04-19 08:43:48,505 INFO Epoch:51 train_loss:0.08672 +2025-04-19 08:44:01,928 INFO Epoch:51 val_res:0.464000 +2025-04-19 08:44:21,096 INFO Epoch:52 train_loss:0.06346 +2025-04-19 08:44:34,725 INFO Epoch:52 val_res:0.463250 +2025-04-19 08:44:54,987 INFO Epoch:53 train_loss:0.08819 +2025-04-19 08:45:07,979 INFO Epoch:53 val_res:0.462000 +2025-04-19 08:45:28,123 INFO Epoch:54 train_loss:0.11084 +2025-04-19 08:45:41,866 INFO Epoch:54 val_res:0.462000 +2025-04-19 08:46:01,024 INFO Epoch:55 train_loss:0.10750 +2025-04-19 08:46:15,816 INFO Epoch:55 val_res:0.459250 +2025-04-19 08:46:34,774 INFO Epoch:56 train_loss:0.06889 +2025-04-19 08:46:49,139 INFO Epoch:56 val_res:0.460000 +2025-04-19 08:47:09,031 INFO Epoch:57 train_loss:0.04789 +2025-04-19 08:47:21,905 INFO Epoch:57 val_res:0.461250 +2025-04-19 08:47:42,024 INFO Epoch:58 train_loss:0.05291 +2025-04-19 08:47:54,870 INFO Epoch:58 val_res:0.462250 +2025-04-19 08:48:14,677 INFO Epoch:59 train_loss:0.05343 +2025-04-19 08:48:28,662 INFO Epoch:59 val_res:0.454250 +2025-04-19 08:48:48,622 INFO Epoch:60 train_loss:0.04643 +2025-04-19 08:49:02,016 INFO Epoch:60 val_res:0.457750 +2025-04-19 08:49:23,530 INFO Epoch:61 train_loss:0.05105 +2025-04-19 08:49:36,346 INFO Epoch:61 val_res:0.454000 +2025-04-19 08:49:57,714 INFO Epoch:62 train_loss:0.08879 +2025-04-19 08:50:10,906 INFO Epoch:62 val_res:0.453500 +2025-04-19 08:50:31,410 INFO Epoch:63 train_loss:0.09262 +2025-04-19 08:50:45,020 INFO Epoch:63 val_res:0.452250 +2025-04-19 08:51:05,094 INFO Epoch:64 train_loss:0.06382 +2025-04-19 08:51:18,311 INFO Epoch:64 val_res:0.450500 +2025-04-19 08:51:38,868 INFO Epoch:65 train_loss:0.06767 +2025-04-19 08:51:51,461 INFO Epoch:65 val_res:0.452750 +2025-04-19 08:52:12,629 INFO Epoch:66 train_loss:0.08169 +2025-04-19 08:52:26,188 INFO Epoch:66 val_res:0.454000 +2025-04-19 08:52:46,119 INFO Epoch:67 train_loss:0.08895 +2025-04-19 08:53:00,627 INFO Epoch:67 val_res:0.447500 +2025-04-19 08:53:21,179 INFO Epoch:68 train_loss:0.05395 +2025-04-19 08:53:34,430 INFO Epoch:68 val_res:0.446250 +2025-04-19 08:53:54,779 INFO Epoch:69 train_loss:0.05120 +2025-04-19 08:54:09,056 INFO Epoch:69 val_res:0.450250 +2025-04-19 08:54:29,299 INFO Epoch:70 train_loss:0.10570 +2025-04-19 08:54:43,952 INFO Epoch:70 val_res:0.445500 +2025-04-19 08:55:03,440 INFO Epoch:71 train_loss:0.06906 +2025-04-19 08:55:17,603 INFO Epoch:71 val_res:0.445500 +2025-04-19 08:55:38,440 INFO Epoch:72 train_loss:0.07009 +2025-04-19 08:55:51,363 INFO Epoch:72 val_res:0.442500 +2025-04-19 08:56:12,465 INFO Epoch:73 train_loss:0.04970 +2025-04-19 08:56:25,005 INFO Epoch:73 val_res:0.445750 +2025-04-19 08:56:45,439 INFO Epoch:74 train_loss:0.04508 +2025-04-19 08:56:58,938 INFO Epoch:74 val_res:0.444250 +2025-04-19 08:57:19,034 INFO Epoch:75 train_loss:0.04145 +2025-04-19 08:57:32,568 INFO Epoch:75 val_res:0.442750 +2025-04-19 08:57:53,470 INFO Epoch:76 train_loss:0.05323 +2025-04-19 08:58:05,835 INFO Epoch:76 val_res:0.440000 +2025-04-19 08:58:26,843 INFO Epoch:77 train_loss:0.07214 +2025-04-19 08:58:39,940 INFO Epoch:77 val_res:0.442750 +2025-04-19 08:59:00,061 INFO Epoch:78 train_loss:0.07293 +2025-04-19 08:59:12,825 INFO Epoch:78 val_res:0.443000 +2025-04-19 08:59:33,293 INFO Epoch:79 train_loss:0.10279 +2025-04-19 08:59:47,454 INFO Epoch:79 val_res:0.438500 +2025-04-19 09:00:06,849 INFO Epoch:80 train_loss:0.08462 +2025-04-19 09:00:20,597 INFO Epoch:80 val_res:0.436750 +2025-04-19 09:00:39,630 INFO Epoch:81 train_loss:0.06101 +2025-04-19 09:00:53,613 INFO Epoch:81 val_res:0.438000 +2025-04-19 09:01:13,714 INFO Epoch:82 train_loss:0.06179 +2025-04-19 09:01:27,194 INFO Epoch:82 val_res:0.437750 +2025-04-19 09:01:47,598 INFO Epoch:83 train_loss:0.05982 +2025-04-19 09:02:01,344 INFO Epoch:83 val_res:0.438000 +2025-04-19 09:02:20,758 INFO Epoch:84 train_loss:0.03750 +2025-04-19 09:02:34,354 INFO Epoch:84 val_res:0.436250 +2025-04-19 09:02:54,896 INFO Epoch:85 train_loss:0.04078 +2025-04-19 09:03:07,962 INFO Epoch:85 val_res:0.434500 +2025-04-19 09:03:29,124 INFO Epoch:86 train_loss:0.04213 +2025-04-19 09:03:41,702 INFO Epoch:86 val_res:0.435750 +2025-04-19 09:04:01,350 INFO Epoch:87 train_loss:0.04460 +2025-04-19 09:04:13,846 INFO Epoch:87 val_res:0.435500 +2025-04-19 09:04:31,178 INFO Epoch:88 train_loss:0.09660 +2025-04-19 09:04:44,270 INFO Epoch:88 val_res:0.433250 +2025-04-19 09:05:02,654 INFO Epoch:89 train_loss:0.07785 +2025-04-19 09:05:15,160 INFO Epoch:89 val_res:0.428500 +2025-04-19 09:05:34,143 INFO Epoch:90 train_loss:0.05460 +2025-04-19 09:05:46,097 INFO Epoch:90 val_res:0.430500 +2025-04-19 09:06:04,461 INFO Epoch:91 train_loss:0.05610 +2025-04-19 09:06:17,626 INFO Epoch:91 val_res:0.429250 +2025-04-19 09:06:36,230 INFO Epoch:92 train_loss:0.08666 +2025-04-19 09:06:49,305 INFO Epoch:92 val_res:0.425250 +2025-04-19 09:07:08,046 INFO Epoch:93 train_loss:0.10276 +2025-04-19 09:07:20,093 INFO Epoch:93 val_res:0.426500 +2025-04-19 09:07:38,954 INFO Epoch:94 train_loss:0.05597 +2025-04-19 09:07:50,627 INFO Epoch:94 val_res:0.430000 +2025-04-19 09:08:08,317 INFO Epoch:95 train_loss:0.05601 +2025-04-19 09:08:20,758 INFO Epoch:95 val_res:0.423750 +2025-04-19 09:08:37,762 INFO Epoch:96 train_loss:0.07079 +2025-04-19 09:08:49,399 INFO Epoch:96 val_res:0.418000 +2025-04-19 09:09:07,712 INFO Epoch:97 train_loss:0.07181 +2025-04-19 09:09:18,922 INFO Epoch:97 val_res:0.423500 +2025-04-19 09:09:37,395 INFO Epoch:98 train_loss:0.05661 +2025-04-19 09:09:49,311 INFO Epoch:98 val_res:0.422500 +2025-04-19 09:10:06,746 INFO Epoch:99 train_loss:0.06134 +2025-04-19 09:10:19,261 INFO Epoch:99 val_res:0.425750 +2025-04-19 09:10:20,045 INFO ===================================== +2025-04-19 09:10:20,045 INFO Start testing... +2025-04-19 09:10:20,046 INFO ===================================== +2025-04-19 09:10:50,317 INFO Incremental step 7 Testing res: 0.470500 +2025-04-19 09:10:50,320 INFO forgetting: 0.195143 +2025-04-19 09:10:50,322 INFO Incremental step: 8 +2025-04-19 09:13:53,340 INFO Epoch:0 train_loss:2.54788 +2025-04-19 09:14:07,591 INFO Epoch:0 val_res:0.410889 +2025-04-19 09:14:07,592 INFO Saving best model at Epoch 0 +2025-04-19 09:14:25,629 INFO Epoch:1 train_loss:0.67900 +2025-04-19 09:14:39,718 INFO Epoch:1 val_res:0.423778 +2025-04-19 09:14:39,718 INFO Saving best model at Epoch 1 +2025-04-19 09:14:57,339 INFO Epoch:2 train_loss:0.40984 +2025-04-19 09:15:11,422 INFO Epoch:2 val_res:0.426222 +2025-04-19 09:15:11,422 INFO Saving best model at Epoch 2 +2025-04-19 09:15:27,453 INFO Epoch:3 train_loss:0.32799 +2025-04-19 09:15:41,268 INFO Epoch:3 val_res:0.425333 +2025-04-19 09:15:55,933 INFO Epoch:4 train_loss:0.29147 +2025-04-19 09:16:10,209 INFO Epoch:4 val_res:0.429333 +2025-04-19 09:16:10,209 INFO Saving best model at Epoch 4 +2025-04-19 09:16:26,040 INFO Epoch:5 train_loss:0.26660 +2025-04-19 09:16:40,452 INFO Epoch:5 val_res:0.429556 +2025-04-19 09:16:40,452 INFO Saving best model at Epoch 5 +2025-04-19 09:16:55,911 INFO Epoch:6 train_loss:0.24524 +2025-04-19 09:17:09,537 INFO Epoch:6 val_res:0.429333 +2025-04-19 09:17:24,592 INFO Epoch:7 train_loss:0.22669 +2025-04-19 09:17:37,910 INFO Epoch:7 val_res:0.431333 +2025-04-19 09:17:37,910 INFO Saving best model at Epoch 7 +2025-04-19 09:17:53,954 INFO Epoch:8 train_loss:0.21386 +2025-04-19 09:18:07,766 INFO Epoch:8 val_res:0.434444 +2025-04-19 09:18:07,766 INFO Saving best model at Epoch 8 +2025-04-19 09:18:23,672 INFO Epoch:9 train_loss:0.20685 +2025-04-19 09:18:36,756 INFO Epoch:9 val_res:0.436000 +2025-04-19 09:18:36,757 INFO Saving best model at Epoch 9 +2025-04-19 09:18:53,354 INFO Epoch:10 train_loss:0.20774 +2025-04-19 09:19:06,331 INFO Epoch:10 val_res:0.437556 +2025-04-19 09:19:06,331 INFO Saving best model at Epoch 10 +2025-04-19 09:19:23,200 INFO Epoch:11 train_loss:0.19739 +2025-04-19 09:19:36,986 INFO Epoch:11 val_res:0.440667 +2025-04-19 09:19:36,986 INFO Saving best model at Epoch 11 +2025-04-19 09:19:53,838 INFO Epoch:12 train_loss:0.17613 +2025-04-19 09:20:07,823 INFO Epoch:12 val_res:0.438222 +2025-04-19 09:20:22,994 INFO Epoch:13 train_loss:0.16600 +2025-04-19 09:20:36,143 INFO Epoch:13 val_res:0.441778 +2025-04-19 09:20:36,143 INFO Saving best model at Epoch 13 +2025-04-19 09:20:53,304 INFO Epoch:14 train_loss:0.17096 +2025-04-19 09:21:06,427 INFO Epoch:14 val_res:0.442444 +2025-04-19 09:21:06,427 INFO Saving best model at Epoch 14 +2025-04-19 09:21:22,647 INFO Epoch:15 train_loss:0.16535 +2025-04-19 09:21:36,673 INFO Epoch:15 val_res:0.443333 +2025-04-19 09:21:36,674 INFO Saving best model at Epoch 15 +2025-04-19 09:21:52,998 INFO Epoch:16 train_loss:0.17704 +2025-04-19 09:22:07,021 INFO Epoch:16 val_res:0.445778 +2025-04-19 09:22:07,022 INFO Saving best model at Epoch 16 +2025-04-19 09:22:24,020 INFO Epoch:17 train_loss:0.15296 +2025-04-19 09:22:37,484 INFO Epoch:17 val_res:0.444222 +2025-04-19 09:22:52,571 INFO Epoch:18 train_loss:0.13703 +2025-04-19 09:23:06,796 INFO Epoch:18 val_res:0.448000 +2025-04-19 09:23:06,796 INFO Saving best model at Epoch 18 +2025-04-19 09:23:23,479 INFO Epoch:19 train_loss:0.12874 +2025-04-19 09:23:37,568 INFO Epoch:19 val_res:0.448444 +2025-04-19 09:23:37,568 INFO Saving best model at Epoch 19 +2025-04-19 09:23:54,012 INFO Epoch:20 train_loss:0.15866 +2025-04-19 09:24:07,928 INFO Epoch:20 val_res:0.448000 +2025-04-19 09:24:22,721 INFO Epoch:21 train_loss:0.16182 +2025-04-19 09:24:35,899 INFO Epoch:21 val_res:0.448222 +2025-04-19 09:24:50,062 INFO Epoch:22 train_loss:0.13178 +2025-04-19 09:25:02,960 INFO Epoch:22 val_res:0.450000 +2025-04-19 09:25:02,960 INFO Saving best model at Epoch 22 +2025-04-19 09:25:18,656 INFO Epoch:23 train_loss:0.13812 +2025-04-19 09:25:31,984 INFO Epoch:23 val_res:0.446667 +2025-04-19 09:25:45,860 INFO Epoch:24 train_loss:0.10837 +2025-04-19 09:25:58,642 INFO Epoch:24 val_res:0.445778 +2025-04-19 09:26:12,348 INFO Epoch:25 train_loss:0.09166 +2025-04-19 09:26:25,643 INFO Epoch:25 val_res:0.443333 +2025-04-19 09:26:39,935 INFO Epoch:26 train_loss:0.09327 +2025-04-19 09:26:53,257 INFO Epoch:26 val_res:0.444444 +2025-04-19 09:27:07,235 INFO Epoch:27 train_loss:0.08382 +2025-04-19 09:27:20,370 INFO Epoch:27 val_res:0.443111 +2025-04-19 09:27:34,652 INFO Epoch:28 train_loss:0.08030 +2025-04-19 09:27:47,248 INFO Epoch:28 val_res:0.443111 +2025-04-19 09:28:01,400 INFO Epoch:29 train_loss:0.09738 +2025-04-19 09:28:14,118 INFO Epoch:29 val_res:0.440667 +2025-04-19 09:28:28,078 INFO Epoch:30 train_loss:0.09402 +2025-04-19 09:28:41,458 INFO Epoch:30 val_res:0.443111 +2025-04-19 09:28:54,956 INFO Epoch:31 train_loss:0.09608 +2025-04-19 09:29:07,960 INFO Epoch:31 val_res:0.444222 +2025-04-19 09:29:22,136 INFO Epoch:32 train_loss:0.11518 +2025-04-19 09:29:35,207 INFO Epoch:32 val_res:0.439556 +2025-04-19 09:29:49,092 INFO Epoch:33 train_loss:0.09376 +2025-04-19 09:30:02,864 INFO Epoch:33 val_res:0.439778 +2025-04-19 09:30:16,621 INFO Epoch:34 train_loss:0.09081 +2025-04-19 09:30:30,614 INFO Epoch:34 val_res:0.439333 +2025-04-19 09:30:44,787 INFO Epoch:35 train_loss:0.08497 +2025-04-19 09:30:57,536 INFO Epoch:35 val_res:0.435556 +2025-04-19 09:31:11,921 INFO Epoch:36 train_loss:0.06663 +2025-04-19 09:31:25,050 INFO Epoch:36 val_res:0.434889 +2025-04-19 09:31:38,929 INFO Epoch:37 train_loss:0.06138 +2025-04-19 09:31:52,767 INFO Epoch:37 val_res:0.434667 +2025-04-19 09:32:06,652 INFO Epoch:38 train_loss:0.07355 +2025-04-19 09:32:19,408 INFO Epoch:38 val_res:0.435778 +2025-04-19 09:32:34,956 INFO Epoch:39 train_loss:0.08037 +2025-04-19 09:32:47,038 INFO Epoch:39 val_res:0.428444 +2025-04-19 09:33:01,607 INFO Epoch:40 train_loss:0.09066 +2025-04-19 09:33:15,171 INFO Epoch:40 val_res:0.425778 +2025-04-19 09:33:29,045 INFO Epoch:41 train_loss:0.10963 +2025-04-19 09:33:42,275 INFO Epoch:41 val_res:0.429333 +2025-04-19 09:33:56,891 INFO Epoch:42 train_loss:0.09352 +2025-04-19 09:34:09,052 INFO Epoch:42 val_res:0.429556 +2025-04-19 09:34:23,914 INFO Epoch:43 train_loss:0.08500 +2025-04-19 09:34:36,757 INFO Epoch:43 val_res:0.429556 +2025-04-19 09:34:50,345 INFO Epoch:44 train_loss:0.06489 +2025-04-19 09:35:04,123 INFO Epoch:44 val_res:0.427333 +2025-04-19 09:35:17,855 INFO Epoch:45 train_loss:0.05364 +2025-04-19 09:35:30,959 INFO Epoch:45 val_res:0.426667 +2025-04-19 09:35:45,806 INFO Epoch:46 train_loss:0.06254 +2025-04-19 09:35:58,854 INFO Epoch:46 val_res:0.426667 +2025-04-19 09:36:12,369 INFO Epoch:47 train_loss:0.05990 +2025-04-19 09:36:26,775 INFO Epoch:47 val_res:0.419778 +2025-04-19 09:36:39,742 INFO Epoch:48 train_loss:0.05185 +2025-04-19 09:36:53,643 INFO Epoch:48 val_res:0.427111 +2025-04-19 09:37:08,403 INFO Epoch:49 train_loss:0.06340 +2025-04-19 09:37:21,726 INFO Epoch:49 val_res:0.423333 +2025-04-19 09:37:36,594 INFO Epoch:50 train_loss:0.06872 +2025-04-19 09:37:51,371 INFO Epoch:50 val_res:0.423556 +2025-04-19 09:38:05,042 INFO Epoch:51 train_loss:0.05488 +2025-04-19 09:38:18,701 INFO Epoch:51 val_res:0.420889 +2025-04-19 09:38:32,741 INFO Epoch:52 train_loss:0.05377 +2025-04-19 09:38:45,500 INFO Epoch:52 val_res:0.411778 +2025-04-19 09:39:00,510 INFO Epoch:53 train_loss:0.10721 +2025-04-19 09:39:13,457 INFO Epoch:53 val_res:0.419111 +2025-04-19 09:39:27,843 INFO Epoch:54 train_loss:0.08013 +2025-04-19 09:39:41,432 INFO Epoch:54 val_res:0.417778 +2025-04-19 09:39:55,292 INFO Epoch:55 train_loss:0.08938 +2025-04-19 09:40:08,239 INFO Epoch:55 val_res:0.414222 +2025-04-19 09:40:23,152 INFO Epoch:56 train_loss:0.06026 +2025-04-19 09:40:35,493 INFO Epoch:56 val_res:0.415111 +2025-04-19 09:40:50,356 INFO Epoch:57 train_loss:0.05258 +2025-04-19 09:41:03,696 INFO Epoch:57 val_res:0.415556 +2025-04-19 09:41:17,737 INFO Epoch:58 train_loss:0.06645 +2025-04-19 09:41:31,226 INFO Epoch:58 val_res:0.411111 +2025-04-19 09:41:45,175 INFO Epoch:59 train_loss:0.07315 +2025-04-19 09:41:58,034 INFO Epoch:59 val_res:0.407333 +2025-04-19 09:42:12,597 INFO Epoch:60 train_loss:0.06681 +2025-04-19 09:42:25,978 INFO Epoch:60 val_res:0.412222 +2025-04-19 09:42:39,867 INFO Epoch:61 train_loss:0.05950 +2025-04-19 09:42:53,647 INFO Epoch:61 val_res:0.412000 +2025-04-19 09:43:07,238 INFO Epoch:62 train_loss:0.04791 +2025-04-19 09:43:21,133 INFO Epoch:62 val_res:0.410444 +2025-04-19 09:43:35,035 INFO Epoch:63 train_loss:0.04821 +2025-04-19 09:43:47,950 INFO Epoch:63 val_res:0.412222 +2025-04-19 09:44:01,900 INFO Epoch:64 train_loss:0.03979 +2025-04-19 09:44:15,490 INFO Epoch:64 val_res:0.410667 +2025-04-19 09:44:29,604 INFO Epoch:65 train_loss:0.04829 +2025-04-19 09:44:43,044 INFO Epoch:65 val_res:0.404667 +2025-04-19 09:44:57,444 INFO Epoch:66 train_loss:0.05726 +2025-04-19 09:45:10,519 INFO Epoch:66 val_res:0.407111 +2025-04-19 09:45:24,471 INFO Epoch:67 train_loss:0.07385 +2025-04-19 09:45:37,728 INFO Epoch:67 val_res:0.408667 +2025-04-19 09:45:51,796 INFO Epoch:68 train_loss:0.06118 +2025-04-19 09:46:04,484 INFO Epoch:68 val_res:0.399778 +2025-04-19 09:46:18,945 INFO Epoch:69 train_loss:0.06209 +2025-04-19 09:46:31,556 INFO Epoch:69 val_res:0.401111 +2025-04-19 09:46:45,796 INFO Epoch:70 train_loss:0.05575 +2025-04-19 09:46:59,143 INFO Epoch:70 val_res:0.405111 +2025-04-19 09:47:13,567 INFO Epoch:71 train_loss:0.05264 +2025-04-19 09:47:26,744 INFO Epoch:71 val_res:0.400889 +2025-04-19 09:47:41,566 INFO Epoch:72 train_loss:0.05304 +2025-04-19 09:47:54,248 INFO Epoch:72 val_res:0.400222 +2025-04-19 09:48:08,961 INFO Epoch:73 train_loss:0.06092 +2025-04-19 09:48:22,322 INFO Epoch:73 val_res:0.400667 +2025-04-19 09:48:36,157 INFO Epoch:74 train_loss:0.06376 +2025-04-19 09:48:49,735 INFO Epoch:74 val_res:0.396889 +2025-04-19 09:49:03,707 INFO Epoch:75 train_loss:0.04486 +2025-04-19 09:49:16,682 INFO Epoch:75 val_res:0.400444 +2025-04-19 09:49:31,362 INFO Epoch:76 train_loss:0.09151 +2025-04-19 09:49:44,235 INFO Epoch:76 val_res:0.396444 +2025-04-19 09:49:58,034 INFO Epoch:77 train_loss:0.09638 +2025-04-19 09:50:11,702 INFO Epoch:77 val_res:0.394000 +2025-04-19 09:50:25,186 INFO Epoch:78 train_loss:0.10233 +2025-04-19 09:50:38,322 INFO Epoch:78 val_res:0.392222 +2025-04-19 09:50:53,146 INFO Epoch:79 train_loss:0.07719 +2025-04-19 09:51:05,908 INFO Epoch:79 val_res:0.394444 +2025-04-19 09:51:20,043 INFO Epoch:80 train_loss:0.06619 +2025-04-19 09:51:33,956 INFO Epoch:80 val_res:0.394222 +2025-04-19 09:51:47,408 INFO Epoch:81 train_loss:0.04281 +2025-04-19 09:52:01,456 INFO Epoch:81 val_res:0.392889 +2025-04-19 09:52:15,402 INFO Epoch:82 train_loss:0.03483 +2025-04-19 09:52:28,803 INFO Epoch:82 val_res:0.391556 +2025-04-19 09:52:43,784 INFO Epoch:83 train_loss:0.03026 +2025-04-19 09:52:56,799 INFO Epoch:83 val_res:0.391778 +2025-04-19 09:53:10,778 INFO Epoch:84 train_loss:0.03869 +2025-04-19 09:53:24,638 INFO Epoch:84 val_res:0.389333 +2025-04-19 09:53:38,090 INFO Epoch:85 train_loss:0.04605 +2025-04-19 09:53:51,372 INFO Epoch:85 val_res:0.391333 +2025-04-19 09:54:06,294 INFO Epoch:86 train_loss:0.06305 +2025-04-19 09:54:18,919 INFO Epoch:86 val_res:0.390222 +2025-04-19 09:54:33,735 INFO Epoch:87 train_loss:0.13833 +2025-04-19 09:54:47,206 INFO Epoch:87 val_res:0.384222 +2025-04-19 09:55:00,875 INFO Epoch:88 train_loss:0.18746 +2025-04-19 09:55:14,567 INFO Epoch:88 val_res:0.381111 +2025-04-19 09:55:28,722 INFO Epoch:89 train_loss:0.07333 +2025-04-19 09:55:41,195 INFO Epoch:89 val_res:0.390444 +2025-04-19 09:55:56,359 INFO Epoch:90 train_loss:0.04268 +2025-04-19 09:56:09,219 INFO Epoch:90 val_res:0.386667 +2025-04-19 09:56:23,474 INFO Epoch:91 train_loss:0.03904 +2025-04-19 09:56:37,339 INFO Epoch:91 val_res:0.385333 +2025-04-19 09:56:51,017 INFO Epoch:92 train_loss:0.03725 +2025-04-19 09:57:04,472 INFO Epoch:92 val_res:0.383111 +2025-04-19 09:57:18,825 INFO Epoch:93 train_loss:0.02916 +2025-04-19 09:57:31,314 INFO Epoch:93 val_res:0.385111 +2025-04-19 09:57:45,841 INFO Epoch:94 train_loss:0.02918 +2025-04-19 09:57:59,388 INFO Epoch:94 val_res:0.385778 +2025-04-19 09:58:13,032 INFO Epoch:95 train_loss:0.03664 +2025-04-19 09:58:26,466 INFO Epoch:95 val_res:0.382889 +2025-04-19 09:58:40,697 INFO Epoch:96 train_loss:0.04634 +2025-04-19 09:58:53,703 INFO Epoch:96 val_res:0.381111 +2025-04-19 09:59:07,345 INFO Epoch:97 train_loss:0.04398 +2025-04-19 09:59:21,239 INFO Epoch:97 val_res:0.384667 +2025-04-19 09:59:34,707 INFO Epoch:98 train_loss:0.06345 +2025-04-19 09:59:48,356 INFO Epoch:98 val_res:0.379111 +2025-04-19 10:00:02,979 INFO Epoch:99 train_loss:0.06732 +2025-04-19 10:00:15,916 INFO Epoch:99 val_res:0.382444 +2025-04-19 10:00:16,910 INFO ===================================== +2025-04-19 10:00:16,911 INFO Start testing... +2025-04-19 10:00:16,911 INFO ===================================== +2025-04-19 10:00:49,532 INFO Incremental step 8 Testing res: 0.445333 +2025-04-19 10:00:49,537 INFO forgetting: 0.185750 +2025-04-19 10:00:49,539 INFO Incremental step: 9 +2025-04-19 10:02:59,585 INFO Epoch:0 train_loss:2.12362 +2025-04-19 10:03:17,518 INFO Epoch:0 val_res:0.396000 +2025-04-19 10:03:17,519 INFO Saving best model at Epoch 0 +2025-04-19 10:03:38,081 INFO Epoch:1 train_loss:0.44479 +2025-04-19 10:03:53,541 INFO Epoch:1 val_res:0.406600 +2025-04-19 10:03:53,541 INFO Saving best model at Epoch 1 +2025-04-19 10:04:12,298 INFO Epoch:2 train_loss:0.27040 +2025-04-19 10:04:28,063 INFO Epoch:2 val_res:0.405800 +2025-04-19 10:04:45,059 INFO Epoch:3 train_loss:0.21931 +2025-04-19 10:05:00,571 INFO Epoch:3 val_res:0.408200 +2025-04-19 10:05:00,577 INFO Saving best model at Epoch 3 +2025-04-19 10:05:18,639 INFO Epoch:4 train_loss:0.19481 +2025-04-19 10:05:34,117 INFO Epoch:4 val_res:0.409200 +2025-04-19 10:05:34,117 INFO Saving best model at Epoch 4 +2025-04-19 10:05:53,307 INFO Epoch:5 train_loss:0.17068 +2025-04-19 10:06:08,938 INFO Epoch:5 val_res:0.409400 +2025-04-19 10:06:08,938 INFO Saving best model at Epoch 5 +2025-04-19 10:06:28,334 INFO Epoch:6 train_loss:0.15475 +2025-04-19 10:06:42,500 INFO Epoch:6 val_res:0.408800 +2025-04-19 10:07:00,611 INFO Epoch:7 train_loss:0.14585 +2025-04-19 10:07:15,416 INFO Epoch:7 val_res:0.413800 +2025-04-19 10:07:15,417 INFO Saving best model at Epoch 7 +2025-04-19 10:07:35,899 INFO Epoch:8 train_loss:0.13436 +2025-04-19 10:07:52,235 INFO Epoch:8 val_res:0.412400 +2025-04-19 10:08:09,018 INFO Epoch:9 train_loss:0.19418 +2025-04-19 10:08:25,224 INFO Epoch:9 val_res:0.414800 +2025-04-19 10:08:25,224 INFO Saving best model at Epoch 9 +2025-04-19 10:08:43,932 INFO Epoch:10 train_loss:0.13410 +2025-04-19 10:08:59,145 INFO Epoch:10 val_res:0.416600 +2025-04-19 10:08:59,146 INFO Saving best model at Epoch 10 +2025-04-19 10:09:19,204 INFO Epoch:11 train_loss:0.11112 +2025-04-19 10:09:34,263 INFO Epoch:11 val_res:0.420600 +2025-04-19 10:09:34,264 INFO Saving best model at Epoch 11 +2025-04-19 10:09:54,455 INFO Epoch:12 train_loss:0.10462 +2025-04-19 10:10:09,615 INFO Epoch:12 val_res:0.421800 +2025-04-19 10:10:09,615 INFO Saving best model at Epoch 12 +2025-04-19 10:10:29,385 INFO Epoch:13 train_loss:0.10096 +2025-04-19 10:10:43,726 INFO Epoch:13 val_res:0.424400 +2025-04-19 10:10:43,726 INFO Saving best model at Epoch 13 +2025-04-19 10:11:02,999 INFO Epoch:14 train_loss:0.10661 +2025-04-19 10:11:17,533 INFO Epoch:14 val_res:0.425200 +2025-04-19 10:11:17,534 INFO Saving best model at Epoch 14 +2025-04-19 10:11:36,810 INFO Epoch:15 train_loss:0.10174 +2025-04-19 10:11:52,305 INFO Epoch:15 val_res:0.423800 +2025-04-19 10:12:10,160 INFO Epoch:16 train_loss:0.09630 +2025-04-19 10:12:25,363 INFO Epoch:16 val_res:0.427200 +2025-04-19 10:12:25,363 INFO Saving best model at Epoch 16 +2025-04-19 10:12:44,316 INFO Epoch:17 train_loss:0.13551 +2025-04-19 10:12:59,105 INFO Epoch:17 val_res:0.424600 +2025-04-19 10:13:16,264 INFO Epoch:18 train_loss:0.13404 +2025-04-19 10:13:31,182 INFO Epoch:18 val_res:0.432800 +2025-04-19 10:13:31,182 INFO Saving best model at Epoch 18 +2025-04-19 10:13:48,640 INFO Epoch:19 train_loss:0.09677 +2025-04-19 10:14:03,767 INFO Epoch:19 val_res:0.430000 +2025-04-19 10:14:19,977 INFO Epoch:20 train_loss:0.07999 +2025-04-19 10:14:34,414 INFO Epoch:20 val_res:0.431800 +2025-04-19 10:14:51,607 INFO Epoch:21 train_loss:0.07369 +2025-04-19 10:15:06,190 INFO Epoch:21 val_res:0.432400 +2025-04-19 10:15:22,332 INFO Epoch:22 train_loss:0.08230 +2025-04-19 10:15:37,409 INFO Epoch:22 val_res:0.434400 +2025-04-19 10:15:37,410 INFO Saving best model at Epoch 22 +2025-04-19 10:15:55,028 INFO Epoch:23 train_loss:0.08280 +2025-04-19 10:16:08,894 INFO Epoch:23 val_res:0.437200 +2025-04-19 10:16:08,894 INFO Saving best model at Epoch 23 +2025-04-19 10:16:28,012 INFO Epoch:24 train_loss:0.08249 +2025-04-19 10:16:40,905 INFO Epoch:24 val_res:0.436200 +2025-04-19 10:16:58,316 INFO Epoch:25 train_loss:0.07700 +2025-04-19 10:17:13,267 INFO Epoch:25 val_res:0.436800 +2025-04-19 10:17:29,476 INFO Epoch:26 train_loss:0.06204 +2025-04-19 10:17:45,473 INFO Epoch:26 val_res:0.437000 +2025-04-19 10:18:01,185 INFO Epoch:27 train_loss:0.06105 +2025-04-19 10:18:15,343 INFO Epoch:27 val_res:0.437400 +2025-04-19 10:18:15,343 INFO Saving best model at Epoch 27 +2025-04-19 10:18:33,494 INFO Epoch:28 train_loss:0.05271 +2025-04-19 10:18:47,501 INFO Epoch:28 val_res:0.434400 +2025-04-19 10:19:04,194 INFO Epoch:29 train_loss:0.14950 +2025-04-19 10:19:18,376 INFO Epoch:29 val_res:0.434600 +2025-04-19 10:19:35,503 INFO Epoch:30 train_loss:0.13532 +2025-04-19 10:19:49,861 INFO Epoch:30 val_res:0.433000 +2025-04-19 10:20:06,748 INFO Epoch:31 train_loss:0.07363 +2025-04-19 10:20:20,758 INFO Epoch:31 val_res:0.434400 +2025-04-19 10:20:37,096 INFO Epoch:32 train_loss:0.06168 +2025-04-19 10:20:51,767 INFO Epoch:32 val_res:0.433600 +2025-04-19 10:21:08,038 INFO Epoch:33 train_loss:0.04734 +2025-04-19 10:21:23,100 INFO Epoch:33 val_res:0.430200 +2025-04-19 10:21:39,385 INFO Epoch:34 train_loss:0.04887 +2025-04-19 10:21:54,620 INFO Epoch:34 val_res:0.431400 +2025-04-19 10:22:10,172 INFO Epoch:35 train_loss:0.05202 +2025-04-19 10:22:24,978 INFO Epoch:35 val_res:0.427200 +2025-04-19 10:22:41,855 INFO Epoch:36 train_loss:0.06844 +2025-04-19 10:22:55,174 INFO Epoch:36 val_res:0.427600 +2025-04-19 10:23:12,889 INFO Epoch:37 train_loss:0.04804 +2025-04-19 10:23:27,353 INFO Epoch:37 val_res:0.426000 +2025-04-19 10:23:43,872 INFO Epoch:38 train_loss:0.06246 +2025-04-19 10:23:59,114 INFO Epoch:38 val_res:0.422400 +2025-04-19 10:24:15,817 INFO Epoch:39 train_loss:0.05378 +2025-04-19 10:24:30,015 INFO Epoch:39 val_res:0.422800 +2025-04-19 10:24:47,307 INFO Epoch:40 train_loss:0.06088 +2025-04-19 10:25:01,801 INFO Epoch:40 val_res:0.417200 +2025-04-19 10:25:18,642 INFO Epoch:41 train_loss:0.06032 +2025-04-19 10:25:34,195 INFO Epoch:41 val_res:0.420600 +2025-04-19 10:25:50,485 INFO Epoch:42 train_loss:0.05425 +2025-04-19 10:26:06,018 INFO Epoch:42 val_res:0.415000 +2025-04-19 10:26:22,410 INFO Epoch:43 train_loss:0.05271 +2025-04-19 10:26:36,881 INFO Epoch:43 val_res:0.416800 +2025-04-19 10:26:53,601 INFO Epoch:44 train_loss:0.05166 +2025-04-19 10:27:08,126 INFO Epoch:44 val_res:0.414800 +2025-04-19 10:27:25,110 INFO Epoch:45 train_loss:0.07036 +2025-04-19 10:27:38,835 INFO Epoch:45 val_res:0.414600 +2025-04-19 10:27:55,962 INFO Epoch:46 train_loss:0.06996 +2025-04-19 10:28:10,394 INFO Epoch:46 val_res:0.410200 +2025-04-19 10:28:28,794 INFO Epoch:47 train_loss:0.10488 +2025-04-19 10:28:43,296 INFO Epoch:47 val_res:0.406800 +2025-04-19 10:29:00,116 INFO Epoch:48 train_loss:0.09075 +2025-04-19 10:29:14,193 INFO Epoch:48 val_res:0.403000 +2025-04-19 10:29:31,867 INFO Epoch:49 train_loss:0.06024 +2025-04-19 10:29:46,036 INFO Epoch:49 val_res:0.403800 +2025-04-19 10:30:02,708 INFO Epoch:50 train_loss:0.04851 +2025-04-19 10:30:18,114 INFO Epoch:50 val_res:0.403800 +2025-04-19 10:30:33,625 INFO Epoch:51 train_loss:0.05046 +2025-04-19 10:30:49,433 INFO Epoch:51 val_res:0.395200 +2025-04-19 10:31:05,508 INFO Epoch:52 train_loss:0.04426 +2025-04-19 10:31:19,736 INFO Epoch:52 val_res:0.399200 +2025-04-19 10:31:37,351 INFO Epoch:53 train_loss:0.03611 +2025-04-19 10:31:50,959 INFO Epoch:53 val_res:0.398200 +2025-04-19 10:32:07,581 INFO Epoch:54 train_loss:0.05367 +2025-04-19 10:32:22,553 INFO Epoch:54 val_res:0.393800 +2025-04-19 10:32:39,134 INFO Epoch:55 train_loss:0.04436 +2025-04-19 10:32:53,218 INFO Epoch:55 val_res:0.392200 +2025-04-19 10:33:10,652 INFO Epoch:56 train_loss:0.07039 +2025-04-19 10:33:24,555 INFO Epoch:56 val_res:0.391800 +2025-04-19 10:33:42,026 INFO Epoch:57 train_loss:0.06844 +2025-04-19 10:33:56,218 INFO Epoch:57 val_res:0.381000 +2025-04-19 10:34:12,620 INFO Epoch:58 train_loss:0.10312 +2025-04-19 10:34:27,510 INFO Epoch:58 val_res:0.390200 +2025-04-19 10:34:43,848 INFO Epoch:59 train_loss:0.05689 +2025-04-19 10:34:58,765 INFO Epoch:59 val_res:0.384000 +2025-04-19 10:35:14,987 INFO Epoch:60 train_loss:0.04831 +2025-04-19 10:35:29,497 INFO Epoch:60 val_res:0.386200 +2025-04-19 10:35:46,328 INFO Epoch:61 train_loss:0.04886 +2025-04-19 10:36:01,050 INFO Epoch:61 val_res:0.384000 +2025-04-19 10:36:17,549 INFO Epoch:62 train_loss:0.03536 +2025-04-19 10:36:32,192 INFO Epoch:62 val_res:0.382000 +2025-04-19 10:36:48,912 INFO Epoch:63 train_loss:0.03076 +2025-04-19 10:37:03,551 INFO Epoch:63 val_res:0.377200 +2025-04-19 10:37:20,343 INFO Epoch:64 train_loss:0.04208 +2025-04-19 10:37:34,256 INFO Epoch:64 val_res:0.379800 +2025-04-19 10:37:51,668 INFO Epoch:65 train_loss:0.04705 +2025-04-19 10:38:05,828 INFO Epoch:65 val_res:0.380000 +2025-04-19 10:38:22,823 INFO Epoch:66 train_loss:0.06546 +2025-04-19 10:38:37,385 INFO Epoch:66 val_res:0.369200 +2025-04-19 10:38:54,016 INFO Epoch:67 train_loss:0.12288 +2025-04-19 10:39:09,538 INFO Epoch:67 val_res:0.375000 +2025-04-19 10:39:24,908 INFO Epoch:68 train_loss:0.07715 +2025-04-19 10:39:39,773 INFO Epoch:68 val_res:0.370200 +2025-04-19 10:39:56,846 INFO Epoch:69 train_loss:0.05512 +2025-04-19 10:40:10,921 INFO Epoch:69 val_res:0.371600 +2025-04-19 10:40:27,926 INFO Epoch:70 train_loss:0.03601 +2025-04-19 10:40:42,745 INFO Epoch:70 val_res:0.366200 +2025-04-19 10:40:59,592 INFO Epoch:71 train_loss:0.03975 +2025-04-19 10:41:15,339 INFO Epoch:71 val_res:0.370000 +2025-04-19 10:41:31,857 INFO Epoch:72 train_loss:0.06967 +2025-04-19 10:41:46,565 INFO Epoch:72 val_res:0.371600 +2025-04-19 10:42:04,280 INFO Epoch:73 train_loss:0.10255 +2025-04-19 10:42:18,548 INFO Epoch:73 val_res:0.362200 +2025-04-19 10:42:36,264 INFO Epoch:74 train_loss:0.07418 +2025-04-19 10:42:50,412 INFO Epoch:74 val_res:0.359600 +2025-04-19 10:43:07,093 INFO Epoch:75 train_loss:0.06104 +2025-04-19 10:43:22,521 INFO Epoch:75 val_res:0.363400 +2025-04-19 10:43:39,378 INFO Epoch:76 train_loss:0.04405 +2025-04-19 10:43:54,199 INFO Epoch:76 val_res:0.364400 +2025-04-19 10:44:11,481 INFO Epoch:77 train_loss:0.03544 +2025-04-19 10:44:26,157 INFO Epoch:77 val_res:0.360200 +2025-04-19 10:44:43,247 INFO Epoch:78 train_loss:0.04059 +2025-04-19 10:44:57,954 INFO Epoch:78 val_res:0.359200 +2025-04-19 10:45:14,564 INFO Epoch:79 train_loss:0.04397 +2025-04-19 10:45:29,292 INFO Epoch:79 val_res:0.361400 +2025-04-19 10:45:45,918 INFO Epoch:80 train_loss:0.04942 +2025-04-19 10:46:00,796 INFO Epoch:80 val_res:0.358600 +2025-04-19 10:46:17,316 INFO Epoch:81 train_loss:0.04556 +2025-04-19 10:46:31,971 INFO Epoch:81 val_res:0.359800 +2025-04-19 10:46:48,750 INFO Epoch:82 train_loss:0.05745 +2025-04-19 10:47:02,986 INFO Epoch:82 val_res:0.351800 +2025-04-19 10:47:19,998 INFO Epoch:83 train_loss:0.04715 +2025-04-19 10:47:33,918 INFO Epoch:83 val_res:0.360200 +2025-04-19 10:47:51,180 INFO Epoch:84 train_loss:0.04001 +2025-04-19 10:48:05,768 INFO Epoch:84 val_res:0.353600 +2025-04-19 10:48:22,531 INFO Epoch:85 train_loss:0.05435 +2025-04-19 10:48:37,364 INFO Epoch:85 val_res:0.354400 +2025-04-19 10:48:54,303 INFO Epoch:86 train_loss:0.05904 +2025-04-19 10:49:08,880 INFO Epoch:86 val_res:0.351200 +2025-04-19 10:49:26,199 INFO Epoch:87 train_loss:0.06127 +2025-04-19 10:49:40,588 INFO Epoch:87 val_res:0.350600 +2025-04-19 10:49:58,888 INFO Epoch:88 train_loss:0.05418 +2025-04-19 10:50:12,788 INFO Epoch:88 val_res:0.349200 +2025-04-19 10:50:29,394 INFO Epoch:89 train_loss:0.07920 +2025-04-19 10:50:44,665 INFO Epoch:89 val_res:0.346000 +2025-04-19 10:51:00,457 INFO Epoch:90 train_loss:0.04953 +2025-04-19 10:51:15,340 INFO Epoch:90 val_res:0.350200 +2025-04-19 10:51:31,965 INFO Epoch:91 train_loss:0.08000 +2025-04-19 10:51:45,997 INFO Epoch:91 val_res:0.349600 +2025-04-19 10:52:03,095 INFO Epoch:92 train_loss:0.07007 +2025-04-19 10:52:18,059 INFO Epoch:92 val_res:0.347000 +2025-04-19 10:52:34,034 INFO Epoch:93 train_loss:0.03414 +2025-04-19 10:52:49,889 INFO Epoch:93 val_res:0.347400 +2025-04-19 10:53:06,063 INFO Epoch:94 train_loss:0.03306 +2025-04-19 10:53:21,287 INFO Epoch:94 val_res:0.343000 +2025-04-19 10:53:38,421 INFO Epoch:95 train_loss:0.04052 +2025-04-19 10:53:52,596 INFO Epoch:95 val_res:0.341000 +2025-04-19 10:54:10,354 INFO Epoch:96 train_loss:0.04574 +2025-04-19 10:54:24,451 INFO Epoch:96 val_res:0.340000 +2025-04-19 10:54:41,599 INFO Epoch:97 train_loss:0.03195 +2025-04-19 10:54:56,658 INFO Epoch:97 val_res:0.341800 +2025-04-19 10:55:13,520 INFO Epoch:98 train_loss:0.05262 +2025-04-19 10:55:28,285 INFO Epoch:98 val_res:0.341000 +2025-04-19 10:55:45,473 INFO Epoch:99 train_loss:0.06791 +2025-04-19 10:55:59,780 INFO Epoch:99 val_res:0.338600 +2025-04-19 10:56:00,605 INFO ===================================== +2025-04-19 10:56:00,606 INFO Start testing... +2025-04-19 10:56:00,606 INFO ===================================== +2025-04-19 10:56:24,812 INFO Incremental step 9 Testing res: 0.425400 +2025-04-19 10:56:24,817 INFO forgetting: 0.201556 +2025-04-19 10:56:24,818 INFO Average Accuracy: 0.590822 +2025-04-19 10:56:24,819 INFO Average Forgetting: 0.182061 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..121de621c814be9e63d5cc8914431a720def79b0 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..41d0311b09ab80b4e56208047ec6571006f0608c Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..5c6f52561f6dd7aea64d1876a78f466e732a7738 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..46f2e6f91af5fb07a578c470fafb35f03f0436b3 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..a22b5f9075c8cc44065712317a8beadf7f29e363 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_5.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..7abd40f4b90307c7258e3e63eec16cb2eab3f5f1 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_5.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_6.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..ba952a044a4a6d1afcc94a8e138cebc9cba9b8de Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_6.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_7.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..91ccf1cb30c1135ac53aaef35d341b00320ff256 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_7.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_8.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..c524330996871c3da074634afed8a438ebca5528 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_8.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_9.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..0d7581f0a5b9725eb1b0c27596feacf96ca756fb Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_9.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..4b6a471af95785951a68340446480d85e9348901 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..2d0fa5dbbaa5d170775a5b8a338b0d6e5ee77126 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..bb2f44cf38cc698317c44934f743554f89298585 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..fa96c536c1bf609f88b3b4713ecdc323f5003555 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..60552717e05b583fe387679e1f28320292254b7a Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_5.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..8da4ff2dd6dcd6668e13a25642cee46aa5120788 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_5.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_6.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..366b0e693e41cc4d108be4a77187c1940e211625 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_6.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_7.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..2ce23a3017bdb6b247e434661024b2b4a1e7cc9b Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_7.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_8.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..de1a0514e4f9a4cec7f8c4b08c407788c1449dd5 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_8.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_9.png b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..b762c2aee6b4e135f86cf3995c4df83d00e42f45 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_9.png differ diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a840d866b40b411265bc77acfe59fe1cd786b35c --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73f97c33dfa65edf3d7deda983ec691c5942112ef2079ffc9891464f5eb506c9 +size 114142801 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..7ce91fe055773edda30b82573171ce8528ea2603 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e388b60bafdac76692975caf63f46d27837d9481e956e24bced6571ce6a122c9 +size 114235153 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..05b5170f4393f58e7b619c05715bf7dfe4faa69a --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ea19bf1368b6e98fec3f8e0b05f444aea7f5b08bd3ac15f86778d3a3dd7af40 +size 114327313 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..2172d0b7fdcd75c953b821cba053d8bc869b29ef --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce8b8a986e2e03730d2c452268ff8f5ac453f64e4e5cd2d51b4919378f4326c +size 114419665 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..7f85891fccf3fe7f80857ebfd35119eb742380a8 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70bdc2d22a2d14c96979c24e13c03d29028b6d0e6159e5aa6e6152d44f24d67b +size 114512017 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_5_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_5_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a2a256bb405e4ad436e8a157d81829032a91c999 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_5_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38c0c63323336aedd1ccba889203700aea6944f6ac73c7d498398f98ea821e24 +size 114604177 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_6_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_6_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b77ce525f7ff1f8e993a6d1cc89c9d08914ba492 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_6_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c4e4888720397d173bacec371d71c8458ae3669aeb8c23992f69f084506eab6 +size 114696529 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_7_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_7_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..47425f9b8634799f67ae48121928b28bfb49b3b6 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_7_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:789ac5c4d4008f2f89158c50ddcfb1c05a5f33c7d3c66030eda72172247f3d69 +size 114788881 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_8_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_8_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9527709fea4aabd6f2263f2e25657bd6ef19a657 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_8_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c078f01a49d830f5c9738472a053a863f58a61eac41b0fd7c69ee99eb1dedd98 +size 114881041 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_9_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_9_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a5642282b7ef8dc19b965790c7b06ced8219626d --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_9_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80c8b17c1ab3ac5c87a845054383e7327ec0c25b2723a1ba694ef8043330bec6 +size 114973393 diff --git a/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/train.log b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..075f07c0e3321d86580e29f69dbc9fe598dd67a1 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/train.log @@ -0,0 +1,2211 @@ +2025-04-19 03:52:32,950 INFO Namespace(class_num_per_step=10, dataset='VGGSound_100', e_prompt=False, infer_batch_size=128, inverse=True, inverse_ends=100, inverse_starts=0, lr=0.001, lr_decay=False, max_epoches=100, milestones=[100], modality='audio-visual', num_classes=100, num_workers=4, prompt_dim=768, seed=0, train_batch_size=256, transfer=False, warm=False, weight_decay=0.0001) +2025-04-19 03:52:32,951 INFO Training start time: 2025-04-19 03:52:32.951451 +2025-04-19 03:52:33,748 INFO Incremental step: 0 +2025-04-19 03:53:08,316 INFO Epoch:0 train_loss:4.69850 +2025-04-19 03:53:11,945 INFO Epoch:0 val_res:0.638000 +2025-04-19 03:53:11,945 INFO Saving best model at Epoch 0 +2025-04-19 03:53:31,894 INFO Epoch:1 train_loss:2.58967 +2025-04-19 03:53:34,325 INFO Epoch:1 val_res:0.736000 +2025-04-19 03:53:34,325 INFO Saving best model at Epoch 1 +2025-04-19 03:53:53,370 INFO Epoch:2 train_loss:1.83897 +2025-04-19 03:53:55,663 INFO Epoch:2 val_res:0.772000 +2025-04-19 03:53:55,663 INFO Saving best model at Epoch 2 +2025-04-19 03:54:11,329 INFO Epoch:3 train_loss:1.48839 +2025-04-19 03:54:13,934 INFO Epoch:3 val_res:0.810000 +2025-04-19 03:54:13,935 INFO Saving best model at Epoch 3 +2025-04-19 03:54:31,946 INFO Epoch:4 train_loss:1.28018 +2025-04-19 03:54:34,948 INFO Epoch:4 val_res:0.796000 +2025-04-19 03:54:52,042 INFO Epoch:5 train_loss:1.10023 +2025-04-19 03:54:55,009 INFO Epoch:5 val_res:0.832000 +2025-04-19 03:54:55,010 INFO Saving best model at Epoch 5 +2025-04-19 03:55:11,303 INFO Epoch:6 train_loss:0.97515 +2025-04-19 03:55:13,598 INFO Epoch:6 val_res:0.806000 +2025-04-19 03:55:28,754 INFO Epoch:7 train_loss:0.90431 +2025-04-19 03:55:31,112 INFO Epoch:7 val_res:0.838000 +2025-04-19 03:55:31,112 INFO Saving best model at Epoch 7 +2025-04-19 03:55:48,792 INFO Epoch:8 train_loss:0.81770 +2025-04-19 03:55:51,106 INFO Epoch:8 val_res:0.882000 +2025-04-19 03:55:51,106 INFO Saving best model at Epoch 8 +2025-04-19 03:56:09,877 INFO Epoch:9 train_loss:0.75651 +2025-04-19 03:56:12,344 INFO Epoch:9 val_res:0.854000 +2025-04-19 03:56:27,601 INFO Epoch:10 train_loss:0.73253 +2025-04-19 03:56:30,433 INFO Epoch:10 val_res:0.874000 +2025-04-19 03:56:46,053 INFO Epoch:11 train_loss:0.68636 +2025-04-19 03:56:48,814 INFO Epoch:11 val_res:0.866000 +2025-04-19 03:57:06,039 INFO Epoch:12 train_loss:0.62404 +2025-04-19 03:57:09,078 INFO Epoch:12 val_res:0.884000 +2025-04-19 03:57:09,079 INFO Saving best model at Epoch 12 +2025-04-19 03:57:28,623 INFO Epoch:13 train_loss:0.60010 +2025-04-19 03:57:31,435 INFO Epoch:13 val_res:0.886000 +2025-04-19 03:57:31,435 INFO Saving best model at Epoch 13 +2025-04-19 03:57:47,590 INFO Epoch:14 train_loss:0.58130 +2025-04-19 03:57:49,911 INFO Epoch:14 val_res:0.884000 +2025-04-19 03:58:04,664 INFO Epoch:15 train_loss:0.60677 +2025-04-19 03:58:07,043 INFO Epoch:15 val_res:0.890000 +2025-04-19 03:58:07,043 INFO Saving best model at Epoch 15 +2025-04-19 03:58:25,159 INFO Epoch:16 train_loss:0.54145 +2025-04-19 03:58:27,915 INFO Epoch:16 val_res:0.892000 +2025-04-19 03:58:27,916 INFO Saving best model at Epoch 16 +2025-04-19 03:58:47,708 INFO Epoch:17 train_loss:0.51491 +2025-04-19 03:58:50,414 INFO Epoch:17 val_res:0.862000 +2025-04-19 03:59:07,049 INFO Epoch:18 train_loss:0.49799 +2025-04-19 03:59:09,755 INFO Epoch:18 val_res:0.876000 +2025-04-19 03:59:27,369 INFO Epoch:19 train_loss:0.49946 +2025-04-19 03:59:30,257 INFO Epoch:19 val_res:0.886000 +2025-04-19 03:59:47,846 INFO Epoch:20 train_loss:0.50830 +2025-04-19 03:59:50,608 INFO Epoch:20 val_res:0.866000 +2025-04-19 04:00:07,989 INFO Epoch:21 train_loss:0.49284 +2025-04-19 04:00:10,630 INFO Epoch:21 val_res:0.876000 +2025-04-19 04:00:24,303 INFO Epoch:22 train_loss:0.44909 +2025-04-19 04:00:26,830 INFO Epoch:22 val_res:0.892000 +2025-04-19 04:00:40,892 INFO Epoch:23 train_loss:0.44394 +2025-04-19 04:00:43,329 INFO Epoch:23 val_res:0.896000 +2025-04-19 04:00:43,330 INFO Saving best model at Epoch 23 +2025-04-19 04:00:58,937 INFO Epoch:24 train_loss:0.44805 +2025-04-19 04:01:01,302 INFO Epoch:24 val_res:0.884000 +2025-04-19 04:01:14,817 INFO Epoch:25 train_loss:0.45124 +2025-04-19 04:01:17,302 INFO Epoch:25 val_res:0.882000 +2025-04-19 04:01:31,346 INFO Epoch:26 train_loss:0.43462 +2025-04-19 04:01:33,695 INFO Epoch:26 val_res:0.880000 +2025-04-19 04:01:47,398 INFO Epoch:27 train_loss:0.41681 +2025-04-19 04:01:49,765 INFO Epoch:27 val_res:0.892000 +2025-04-19 04:02:03,644 INFO Epoch:28 train_loss:0.40709 +2025-04-19 04:02:05,928 INFO Epoch:28 val_res:0.888000 +2025-04-19 04:02:20,019 INFO Epoch:29 train_loss:0.39074 +2025-04-19 04:02:22,544 INFO Epoch:29 val_res:0.900000 +2025-04-19 04:02:22,544 INFO Saving best model at Epoch 29 +2025-04-19 04:02:38,317 INFO Epoch:30 train_loss:0.41238 +2025-04-19 04:02:40,711 INFO Epoch:30 val_res:0.900000 +2025-04-19 04:02:54,327 INFO Epoch:31 train_loss:0.38307 +2025-04-19 04:02:56,701 INFO Epoch:31 val_res:0.892000 +2025-04-19 04:03:10,742 INFO Epoch:32 train_loss:0.39658 +2025-04-19 04:03:13,081 INFO Epoch:32 val_res:0.898000 +2025-04-19 04:03:27,178 INFO Epoch:33 train_loss:0.39254 +2025-04-19 04:03:29,493 INFO Epoch:33 val_res:0.902000 +2025-04-19 04:03:29,494 INFO Saving best model at Epoch 33 +2025-04-19 04:03:47,010 INFO Epoch:34 train_loss:0.42492 +2025-04-19 04:03:49,677 INFO Epoch:34 val_res:0.916000 +2025-04-19 04:03:49,677 INFO Saving best model at Epoch 34 +2025-04-19 04:04:08,116 INFO Epoch:35 train_loss:0.41371 +2025-04-19 04:04:10,520 INFO Epoch:35 val_res:0.904000 +2025-04-19 04:04:24,068 INFO Epoch:36 train_loss:0.37637 +2025-04-19 04:04:26,546 INFO Epoch:36 val_res:0.886000 +2025-04-19 04:04:39,797 INFO Epoch:37 train_loss:0.36211 +2025-04-19 04:04:42,214 INFO Epoch:37 val_res:0.904000 +2025-04-19 04:04:55,953 INFO Epoch:38 train_loss:0.34272 +2025-04-19 04:04:58,594 INFO Epoch:38 val_res:0.886000 +2025-04-19 04:05:11,936 INFO Epoch:39 train_loss:0.34971 +2025-04-19 04:05:14,244 INFO Epoch:39 val_res:0.896000 +2025-04-19 04:05:27,680 INFO Epoch:40 train_loss:0.36951 +2025-04-19 04:05:29,977 INFO Epoch:40 val_res:0.882000 +2025-04-19 04:05:43,487 INFO Epoch:41 train_loss:0.34171 +2025-04-19 04:05:45,691 INFO Epoch:41 val_res:0.896000 +2025-04-19 04:05:59,162 INFO Epoch:42 train_loss:0.35856 +2025-04-19 04:06:01,574 INFO Epoch:42 val_res:0.892000 +2025-04-19 04:06:14,891 INFO Epoch:43 train_loss:0.34844 +2025-04-19 04:06:17,253 INFO Epoch:43 val_res:0.890000 +2025-04-19 04:06:30,775 INFO Epoch:44 train_loss:0.35791 +2025-04-19 04:06:33,053 INFO Epoch:44 val_res:0.884000 +2025-04-19 04:06:46,484 INFO Epoch:45 train_loss:0.34948 +2025-04-19 04:06:48,646 INFO Epoch:45 val_res:0.902000 +2025-04-19 04:07:02,112 INFO Epoch:46 train_loss:0.32567 +2025-04-19 04:07:04,305 INFO Epoch:46 val_res:0.890000 +2025-04-19 04:07:17,642 INFO Epoch:47 train_loss:0.35134 +2025-04-19 04:07:20,005 INFO Epoch:47 val_res:0.882000 +2025-04-19 04:07:33,534 INFO Epoch:48 train_loss:0.36675 +2025-04-19 04:07:35,863 INFO Epoch:48 val_res:0.894000 +2025-04-19 04:07:49,185 INFO Epoch:49 train_loss:0.32038 +2025-04-19 04:07:51,410 INFO Epoch:49 val_res:0.900000 +2025-04-19 04:08:04,699 INFO Epoch:50 train_loss:0.31806 +2025-04-19 04:08:06,884 INFO Epoch:50 val_res:0.900000 +2025-04-19 04:08:20,514 INFO Epoch:51 train_loss:0.32308 +2025-04-19 04:08:22,710 INFO Epoch:51 val_res:0.874000 +2025-04-19 04:08:36,146 INFO Epoch:52 train_loss:0.35599 +2025-04-19 04:08:38,396 INFO Epoch:52 val_res:0.860000 +2025-04-19 04:08:51,818 INFO Epoch:53 train_loss:0.33375 +2025-04-19 04:08:54,100 INFO Epoch:53 val_res:0.878000 +2025-04-19 04:09:07,358 INFO Epoch:54 train_loss:0.31814 +2025-04-19 04:09:09,553 INFO Epoch:54 val_res:0.862000 +2025-04-19 04:09:22,815 INFO Epoch:55 train_loss:0.28390 +2025-04-19 04:09:25,200 INFO Epoch:55 val_res:0.902000 +2025-04-19 04:09:38,464 INFO Epoch:56 train_loss:0.28009 +2025-04-19 04:09:40,871 INFO Epoch:56 val_res:0.898000 +2025-04-19 04:09:53,887 INFO Epoch:57 train_loss:0.33647 +2025-04-19 04:09:56,297 INFO Epoch:57 val_res:0.892000 +2025-04-19 04:10:09,333 INFO Epoch:58 train_loss:0.30808 +2025-04-19 04:10:11,568 INFO Epoch:58 val_res:0.890000 +2025-04-19 04:10:25,327 INFO Epoch:59 train_loss:0.34711 +2025-04-19 04:10:28,031 INFO Epoch:59 val_res:0.896000 +2025-04-19 04:10:42,649 INFO Epoch:60 train_loss:0.28023 +2025-04-19 04:10:45,524 INFO Epoch:60 val_res:0.896000 +2025-04-19 04:10:59,460 INFO Epoch:61 train_loss:0.26435 +2025-04-19 04:11:02,121 INFO Epoch:61 val_res:0.894000 +2025-04-19 04:11:16,406 INFO Epoch:62 train_loss:0.26862 +2025-04-19 04:11:18,811 INFO Epoch:62 val_res:0.904000 +2025-04-19 04:11:33,287 INFO Epoch:63 train_loss:0.26218 +2025-04-19 04:11:35,788 INFO Epoch:63 val_res:0.896000 +2025-04-19 04:11:51,930 INFO Epoch:64 train_loss:0.26562 +2025-04-19 04:11:54,333 INFO Epoch:64 val_res:0.888000 +2025-04-19 04:12:08,832 INFO Epoch:65 train_loss:0.28224 +2025-04-19 04:12:11,078 INFO Epoch:65 val_res:0.894000 +2025-04-19 04:12:24,405 INFO Epoch:66 train_loss:0.26929 +2025-04-19 04:12:26,663 INFO Epoch:66 val_res:0.890000 +2025-04-19 04:12:40,068 INFO Epoch:67 train_loss:0.27133 +2025-04-19 04:12:42,352 INFO Epoch:67 val_res:0.896000 +2025-04-19 04:12:55,738 INFO Epoch:68 train_loss:0.26373 +2025-04-19 04:12:57,992 INFO Epoch:68 val_res:0.888000 +2025-04-19 04:13:11,648 INFO Epoch:69 train_loss:0.28752 +2025-04-19 04:13:13,952 INFO Epoch:69 val_res:0.884000 +2025-04-19 04:13:27,331 INFO Epoch:70 train_loss:0.32106 +2025-04-19 04:13:29,634 INFO Epoch:70 val_res:0.902000 +2025-04-19 04:13:42,887 INFO Epoch:71 train_loss:0.27119 +2025-04-19 04:13:45,150 INFO Epoch:71 val_res:0.884000 +2025-04-19 04:13:59,796 INFO Epoch:72 train_loss:0.32411 +2025-04-19 04:14:02,186 INFO Epoch:72 val_res:0.890000 +2025-04-19 04:14:15,504 INFO Epoch:73 train_loss:0.28986 +2025-04-19 04:14:17,803 INFO Epoch:73 val_res:0.904000 +2025-04-19 04:14:31,215 INFO Epoch:74 train_loss:0.27798 +2025-04-19 04:14:33,497 INFO Epoch:74 val_res:0.892000 +2025-04-19 04:14:46,793 INFO Epoch:75 train_loss:0.28302 +2025-04-19 04:14:49,072 INFO Epoch:75 val_res:0.902000 +2025-04-19 04:15:02,313 INFO Epoch:76 train_loss:0.27505 +2025-04-19 04:15:04,602 INFO Epoch:76 val_res:0.890000 +2025-04-19 04:15:17,760 INFO Epoch:77 train_loss:0.25999 +2025-04-19 04:15:20,024 INFO Epoch:77 val_res:0.898000 +2025-04-19 04:15:33,069 INFO Epoch:78 train_loss:0.24845 +2025-04-19 04:15:35,348 INFO Epoch:78 val_res:0.896000 +2025-04-19 04:15:48,306 INFO Epoch:79 train_loss:0.23075 +2025-04-19 04:15:50,484 INFO Epoch:79 val_res:0.904000 +2025-04-19 04:16:03,765 INFO Epoch:80 train_loss:0.26098 +2025-04-19 04:16:06,132 INFO Epoch:80 val_res:0.908000 +2025-04-19 04:16:19,377 INFO Epoch:81 train_loss:0.29212 +2025-04-19 04:16:21,546 INFO Epoch:81 val_res:0.896000 +2025-04-19 04:16:34,887 INFO Epoch:82 train_loss:0.26345 +2025-04-19 04:16:37,160 INFO Epoch:82 val_res:0.894000 +2025-04-19 04:16:50,612 INFO Epoch:83 train_loss:0.26174 +2025-04-19 04:16:52,821 INFO Epoch:83 val_res:0.900000 +2025-04-19 04:17:06,579 INFO Epoch:84 train_loss:0.27028 +2025-04-19 04:17:08,889 INFO Epoch:84 val_res:0.896000 +2025-04-19 04:17:22,303 INFO Epoch:85 train_loss:0.25445 +2025-04-19 04:17:24,701 INFO Epoch:85 val_res:0.896000 +2025-04-19 04:17:38,287 INFO Epoch:86 train_loss:0.25605 +2025-04-19 04:17:40,522 INFO Epoch:86 val_res:0.898000 +2025-04-19 04:17:53,740 INFO Epoch:87 train_loss:0.24083 +2025-04-19 04:17:56,041 INFO Epoch:87 val_res:0.890000 +2025-04-19 04:18:09,471 INFO Epoch:88 train_loss:0.26304 +2025-04-19 04:18:11,807 INFO Epoch:88 val_res:0.890000 +2025-04-19 04:18:25,294 INFO Epoch:89 train_loss:0.25797 +2025-04-19 04:18:27,666 INFO Epoch:89 val_res:0.892000 +2025-04-19 04:18:40,966 INFO Epoch:90 train_loss:0.25487 +2025-04-19 04:18:43,252 INFO Epoch:90 val_res:0.908000 +2025-04-19 04:18:56,547 INFO Epoch:91 train_loss:0.22334 +2025-04-19 04:18:58,905 INFO Epoch:91 val_res:0.896000 +2025-04-19 04:19:11,730 INFO Epoch:92 train_loss:0.27843 +2025-04-19 04:19:13,896 INFO Epoch:92 val_res:0.874000 +2025-04-19 04:19:26,767 INFO Epoch:93 train_loss:0.31198 +2025-04-19 04:19:29,098 INFO Epoch:93 val_res:0.884000 +2025-04-19 04:19:42,449 INFO Epoch:94 train_loss:0.25994 +2025-04-19 04:19:44,713 INFO Epoch:94 val_res:0.902000 +2025-04-19 04:19:57,513 INFO Epoch:95 train_loss:0.23770 +2025-04-19 04:19:59,629 INFO Epoch:95 val_res:0.876000 +2025-04-19 04:20:12,612 INFO Epoch:96 train_loss:0.23043 +2025-04-19 04:20:14,876 INFO Epoch:96 val_res:0.874000 +2025-04-19 04:20:28,952 INFO Epoch:97 train_loss:0.26289 +2025-04-19 04:20:31,475 INFO Epoch:97 val_res:0.900000 +2025-04-19 04:20:46,203 INFO Epoch:98 train_loss:0.23072 +2025-04-19 04:20:48,429 INFO Epoch:98 val_res:0.872000 +2025-04-19 04:21:02,106 INFO Epoch:99 train_loss:0.23622 +2025-04-19 04:21:04,817 INFO Epoch:99 val_res:0.900000 +2025-04-19 04:21:05,553 INFO ===================================== +2025-04-19 04:21:05,554 INFO Start testing... +2025-04-19 04:21:05,554 INFO ===================================== +2025-04-19 04:21:14,143 INFO Incremental step 0 Testing res: 0.904000 +2025-04-19 04:21:14,146 INFO Incremental step: 1 +2025-04-19 04:21:31,094 INFO Epoch:0 train_loss:4.75484 +2025-04-19 04:21:35,490 INFO Epoch:0 val_res:0.503000 +2025-04-19 04:21:35,490 INFO Saving best model at Epoch 0 +2025-04-19 04:21:52,764 INFO Epoch:1 train_loss:2.50748 +2025-04-19 04:21:56,401 INFO Epoch:1 val_res:0.558000 +2025-04-19 04:21:56,402 INFO Saving best model at Epoch 1 +2025-04-19 04:22:15,001 INFO Epoch:2 train_loss:1.91673 +2025-04-19 04:22:18,861 INFO Epoch:2 val_res:0.597000 +2025-04-19 04:22:18,861 INFO Saving best model at Epoch 2 +2025-04-19 04:22:36,199 INFO Epoch:3 train_loss:1.62248 +2025-04-19 04:22:40,449 INFO Epoch:3 val_res:0.627000 +2025-04-19 04:22:40,449 INFO Saving best model at Epoch 3 +2025-04-19 04:22:56,988 INFO Epoch:4 train_loss:1.47619 +2025-04-19 04:23:01,087 INFO Epoch:4 val_res:0.647000 +2025-04-19 04:23:01,088 INFO Saving best model at Epoch 4 +2025-04-19 04:23:17,857 INFO Epoch:5 train_loss:1.34200 +2025-04-19 04:23:22,029 INFO Epoch:5 val_res:0.668000 +2025-04-19 04:23:22,030 INFO Saving best model at Epoch 5 +2025-04-19 04:23:38,691 INFO Epoch:6 train_loss:1.23659 +2025-04-19 04:23:42,956 INFO Epoch:6 val_res:0.683000 +2025-04-19 04:23:42,956 INFO Saving best model at Epoch 6 +2025-04-19 04:23:59,508 INFO Epoch:7 train_loss:1.15993 +2025-04-19 04:24:03,637 INFO Epoch:7 val_res:0.714000 +2025-04-19 04:24:03,638 INFO Saving best model at Epoch 7 +2025-04-19 04:24:22,592 INFO Epoch:8 train_loss:1.06049 +2025-04-19 04:24:26,752 INFO Epoch:8 val_res:0.722000 +2025-04-19 04:24:26,753 INFO Saving best model at Epoch 8 +2025-04-19 04:24:43,671 INFO Epoch:9 train_loss:1.01072 +2025-04-19 04:24:47,825 INFO Epoch:9 val_res:0.729000 +2025-04-19 04:24:47,826 INFO Saving best model at Epoch 9 +2025-04-19 04:25:04,376 INFO Epoch:10 train_loss:0.93520 +2025-04-19 04:25:08,544 INFO Epoch:10 val_res:0.740000 +2025-04-19 04:25:08,544 INFO Saving best model at Epoch 10 +2025-04-19 04:25:24,749 INFO Epoch:11 train_loss:0.88238 +2025-04-19 04:25:29,098 INFO Epoch:11 val_res:0.748000 +2025-04-19 04:25:29,098 INFO Saving best model at Epoch 11 +2025-04-19 04:25:45,882 INFO Epoch:12 train_loss:0.82639 +2025-04-19 04:25:50,214 INFO Epoch:12 val_res:0.769000 +2025-04-19 04:25:50,215 INFO Saving best model at Epoch 12 +2025-04-19 04:26:06,343 INFO Epoch:13 train_loss:0.79116 +2025-04-19 04:26:10,769 INFO Epoch:13 val_res:0.764000 +2025-04-19 04:26:26,173 INFO Epoch:14 train_loss:0.76813 +2025-04-19 04:26:30,275 INFO Epoch:14 val_res:0.785000 +2025-04-19 04:26:30,275 INFO Saving best model at Epoch 14 +2025-04-19 04:26:48,221 INFO Epoch:15 train_loss:0.75937 +2025-04-19 04:26:52,329 INFO Epoch:15 val_res:0.787000 +2025-04-19 04:26:52,330 INFO Saving best model at Epoch 15 +2025-04-19 04:27:10,128 INFO Epoch:16 train_loss:0.68996 +2025-04-19 04:27:14,226 INFO Epoch:16 val_res:0.790000 +2025-04-19 04:27:14,226 INFO Saving best model at Epoch 16 +2025-04-19 04:27:30,505 INFO Epoch:17 train_loss:0.66181 +2025-04-19 04:27:34,553 INFO Epoch:17 val_res:0.799000 +2025-04-19 04:27:34,553 INFO Saving best model at Epoch 17 +2025-04-19 04:27:50,686 INFO Epoch:18 train_loss:0.64180 +2025-04-19 04:27:54,883 INFO Epoch:18 val_res:0.812000 +2025-04-19 04:27:54,883 INFO Saving best model at Epoch 18 +2025-04-19 04:28:11,503 INFO Epoch:19 train_loss:0.61293 +2025-04-19 04:28:15,546 INFO Epoch:19 val_res:0.804000 +2025-04-19 04:28:30,356 INFO Epoch:20 train_loss:0.57706 +2025-04-19 04:28:34,594 INFO Epoch:20 val_res:0.813000 +2025-04-19 04:28:34,594 INFO Saving best model at Epoch 20 +2025-04-19 04:28:51,311 INFO Epoch:21 train_loss:0.55890 +2025-04-19 04:28:55,128 INFO Epoch:21 val_res:0.808000 +2025-04-19 04:29:09,775 INFO Epoch:22 train_loss:0.54499 +2025-04-19 04:29:13,959 INFO Epoch:22 val_res:0.828000 +2025-04-19 04:29:13,960 INFO Saving best model at Epoch 22 +2025-04-19 04:29:30,374 INFO Epoch:23 train_loss:0.51740 +2025-04-19 04:29:34,296 INFO Epoch:23 val_res:0.810000 +2025-04-19 04:29:49,404 INFO Epoch:24 train_loss:0.53489 +2025-04-19 04:29:54,007 INFO Epoch:24 val_res:0.807000 +2025-04-19 04:30:08,882 INFO Epoch:25 train_loss:0.57480 +2025-04-19 04:30:12,578 INFO Epoch:25 val_res:0.812000 +2025-04-19 04:30:27,528 INFO Epoch:26 train_loss:0.52214 +2025-04-19 04:30:31,785 INFO Epoch:26 val_res:0.821000 +2025-04-19 04:30:47,248 INFO Epoch:27 train_loss:0.50916 +2025-04-19 04:30:51,176 INFO Epoch:27 val_res:0.809000 +2025-04-19 04:31:06,548 INFO Epoch:28 train_loss:0.49020 +2025-04-19 04:31:10,854 INFO Epoch:28 val_res:0.818000 +2025-04-19 04:31:24,928 INFO Epoch:29 train_loss:0.47139 +2025-04-19 04:31:28,999 INFO Epoch:29 val_res:0.816000 +2025-04-19 04:31:44,401 INFO Epoch:30 train_loss:0.46968 +2025-04-19 04:31:48,761 INFO Epoch:30 val_res:0.813000 +2025-04-19 04:32:03,038 INFO Epoch:31 train_loss:0.44364 +2025-04-19 04:32:07,048 INFO Epoch:31 val_res:0.823000 +2025-04-19 04:32:21,875 INFO Epoch:32 train_loss:0.43413 +2025-04-19 04:32:26,297 INFO Epoch:32 val_res:0.802000 +2025-04-19 04:32:40,751 INFO Epoch:33 train_loss:0.45539 +2025-04-19 04:32:45,023 INFO Epoch:33 val_res:0.791000 +2025-04-19 04:33:00,099 INFO Epoch:34 train_loss:0.43067 +2025-04-19 04:33:04,534 INFO Epoch:34 val_res:0.813000 +2025-04-19 04:33:18,467 INFO Epoch:35 train_loss:0.39957 +2025-04-19 04:33:22,589 INFO Epoch:35 val_res:0.814000 +2025-04-19 04:33:38,007 INFO Epoch:36 train_loss:0.40182 +2025-04-19 04:33:42,212 INFO Epoch:36 val_res:0.811000 +2025-04-19 04:33:56,229 INFO Epoch:37 train_loss:0.39643 +2025-04-19 04:34:00,275 INFO Epoch:37 val_res:0.813000 +2025-04-19 04:34:15,576 INFO Epoch:38 train_loss:0.39580 +2025-04-19 04:34:19,877 INFO Epoch:38 val_res:0.806000 +2025-04-19 04:34:33,911 INFO Epoch:39 train_loss:0.38944 +2025-04-19 04:34:38,008 INFO Epoch:39 val_res:0.812000 +2025-04-19 04:34:52,992 INFO Epoch:40 train_loss:0.41341 +2025-04-19 04:34:57,120 INFO Epoch:40 val_res:0.802000 +2025-04-19 04:35:11,210 INFO Epoch:41 train_loss:0.40201 +2025-04-19 04:35:15,296 INFO Epoch:41 val_res:0.803000 +2025-04-19 04:35:30,590 INFO Epoch:42 train_loss:0.38794 +2025-04-19 04:35:34,749 INFO Epoch:42 val_res:0.812000 +2025-04-19 04:35:49,343 INFO Epoch:43 train_loss:0.39833 +2025-04-19 04:35:53,524 INFO Epoch:43 val_res:0.812000 +2025-04-19 04:36:09,318 INFO Epoch:44 train_loss:0.41565 +2025-04-19 04:36:13,482 INFO Epoch:44 val_res:0.805000 +2025-04-19 04:36:27,452 INFO Epoch:45 train_loss:0.43505 +2025-04-19 04:36:31,703 INFO Epoch:45 val_res:0.800000 +2025-04-19 04:36:47,218 INFO Epoch:46 train_loss:0.38230 +2025-04-19 04:36:51,345 INFO Epoch:46 val_res:0.811000 +2025-04-19 04:37:05,959 INFO Epoch:47 train_loss:0.37664 +2025-04-19 04:37:10,302 INFO Epoch:47 val_res:0.808000 +2025-04-19 04:37:24,655 INFO Epoch:48 train_loss:0.36582 +2025-04-19 04:37:28,676 INFO Epoch:48 val_res:0.804000 +2025-04-19 04:37:43,474 INFO Epoch:49 train_loss:0.36572 +2025-04-19 04:37:47,892 INFO Epoch:49 val_res:0.805000 +2025-04-19 04:38:02,686 INFO Epoch:50 train_loss:0.36756 +2025-04-19 04:38:07,017 INFO Epoch:50 val_res:0.788000 +2025-04-19 04:38:21,838 INFO Epoch:51 train_loss:0.40350 +2025-04-19 04:38:25,827 INFO Epoch:51 val_res:0.815000 +2025-04-19 04:38:40,659 INFO Epoch:52 train_loss:0.35273 +2025-04-19 04:38:44,651 INFO Epoch:52 val_res:0.799000 +2025-04-19 04:38:59,034 INFO Epoch:53 train_loss:0.36698 +2025-04-19 04:39:03,145 INFO Epoch:53 val_res:0.793000 +2025-04-19 04:39:18,219 INFO Epoch:54 train_loss:0.38045 +2025-04-19 04:39:22,372 INFO Epoch:54 val_res:0.807000 +2025-04-19 04:39:37,646 INFO Epoch:55 train_loss:0.37035 +2025-04-19 04:39:41,697 INFO Epoch:55 val_res:0.801000 +2025-04-19 04:39:56,344 INFO Epoch:56 train_loss:0.35960 +2025-04-19 04:40:00,577 INFO Epoch:56 val_res:0.812000 +2025-04-19 04:40:15,640 INFO Epoch:57 train_loss:0.33429 +2025-04-19 04:40:20,114 INFO Epoch:57 val_res:0.804000 +2025-04-19 04:40:35,420 INFO Epoch:58 train_loss:0.33219 +2025-04-19 04:40:39,682 INFO Epoch:58 val_res:0.809000 +2025-04-19 04:40:54,180 INFO Epoch:59 train_loss:0.30403 +2025-04-19 04:40:58,483 INFO Epoch:59 val_res:0.803000 +2025-04-19 04:41:14,171 INFO Epoch:60 train_loss:0.30849 +2025-04-19 04:41:18,262 INFO Epoch:60 val_res:0.808000 +2025-04-19 04:41:32,264 INFO Epoch:61 train_loss:0.31799 +2025-04-19 04:41:36,446 INFO Epoch:61 val_res:0.799000 +2025-04-19 04:41:51,822 INFO Epoch:62 train_loss:0.32798 +2025-04-19 04:41:55,923 INFO Epoch:62 val_res:0.795000 +2025-04-19 04:42:09,396 INFO Epoch:63 train_loss:0.30887 +2025-04-19 04:42:13,367 INFO Epoch:63 val_res:0.799000 +2025-04-19 04:42:28,895 INFO Epoch:64 train_loss:0.30638 +2025-04-19 04:42:33,112 INFO Epoch:64 val_res:0.802000 +2025-04-19 04:42:47,587 INFO Epoch:65 train_loss:0.31024 +2025-04-19 04:42:51,960 INFO Epoch:65 val_res:0.801000 +2025-04-19 04:43:06,583 INFO Epoch:66 train_loss:0.34062 +2025-04-19 04:43:10,565 INFO Epoch:66 val_res:0.801000 +2025-04-19 04:43:25,129 INFO Epoch:67 train_loss:0.32809 +2025-04-19 04:43:29,347 INFO Epoch:67 val_res:0.798000 +2025-04-19 04:43:44,650 INFO Epoch:68 train_loss:0.32942 +2025-04-19 04:43:48,893 INFO Epoch:68 val_res:0.795000 +2025-04-19 04:44:03,420 INFO Epoch:69 train_loss:0.34161 +2025-04-19 04:44:07,654 INFO Epoch:69 val_res:0.804000 +2025-04-19 04:44:22,721 INFO Epoch:70 train_loss:0.30938 +2025-04-19 04:44:26,756 INFO Epoch:70 val_res:0.798000 +2025-04-19 04:44:42,779 INFO Epoch:71 train_loss:0.29846 +2025-04-19 04:44:47,015 INFO Epoch:71 val_res:0.796000 +2025-04-19 04:45:01,277 INFO Epoch:72 train_loss:0.33570 +2025-04-19 04:45:05,256 INFO Epoch:72 val_res:0.800000 +2025-04-19 04:45:20,537 INFO Epoch:73 train_loss:0.29813 +2025-04-19 04:45:24,773 INFO Epoch:73 val_res:0.803000 +2025-04-19 04:45:39,278 INFO Epoch:74 train_loss:0.31694 +2025-04-19 04:45:43,597 INFO Epoch:74 val_res:0.802000 +2025-04-19 04:45:58,460 INFO Epoch:75 train_loss:0.30437 +2025-04-19 04:46:02,522 INFO Epoch:75 val_res:0.790000 +2025-04-19 04:46:17,231 INFO Epoch:76 train_loss:0.30003 +2025-04-19 04:46:21,112 INFO Epoch:76 val_res:0.795000 +2025-04-19 04:46:36,400 INFO Epoch:77 train_loss:0.32608 +2025-04-19 04:46:40,445 INFO Epoch:77 val_res:0.806000 +2025-04-19 04:46:55,130 INFO Epoch:78 train_loss:0.29748 +2025-04-19 04:46:59,157 INFO Epoch:78 val_res:0.802000 +2025-04-19 04:47:13,352 INFO Epoch:79 train_loss:0.27556 +2025-04-19 04:47:17,365 INFO Epoch:79 val_res:0.797000 +2025-04-19 04:47:32,195 INFO Epoch:80 train_loss:0.27158 +2025-04-19 04:47:36,350 INFO Epoch:80 val_res:0.801000 +2025-04-19 04:47:50,649 INFO Epoch:81 train_loss:0.25976 +2025-04-19 04:47:54,975 INFO Epoch:81 val_res:0.795000 +2025-04-19 04:48:10,053 INFO Epoch:82 train_loss:0.28349 +2025-04-19 04:48:14,360 INFO Epoch:82 val_res:0.811000 +2025-04-19 04:48:28,891 INFO Epoch:83 train_loss:0.29580 +2025-04-19 04:48:32,614 INFO Epoch:83 val_res:0.798000 +2025-04-19 04:48:48,137 INFO Epoch:84 train_loss:0.30697 +2025-04-19 04:48:52,338 INFO Epoch:84 val_res:0.790000 +2025-04-19 04:49:07,575 INFO Epoch:85 train_loss:0.29903 +2025-04-19 04:49:11,559 INFO Epoch:85 val_res:0.806000 +2025-04-19 04:49:26,351 INFO Epoch:86 train_loss:0.25763 +2025-04-19 04:49:30,361 INFO Epoch:86 val_res:0.798000 +2025-04-19 04:49:45,771 INFO Epoch:87 train_loss:0.25242 +2025-04-19 04:49:49,921 INFO Epoch:87 val_res:0.798000 +2025-04-19 04:50:04,550 INFO Epoch:88 train_loss:0.24686 +2025-04-19 04:50:08,932 INFO Epoch:88 val_res:0.798000 +2025-04-19 04:50:24,242 INFO Epoch:89 train_loss:0.25246 +2025-04-19 04:50:28,388 INFO Epoch:89 val_res:0.799000 +2025-04-19 04:50:43,095 INFO Epoch:90 train_loss:0.24460 +2025-04-19 04:50:47,305 INFO Epoch:90 val_res:0.800000 +2025-04-19 04:51:02,804 INFO Epoch:91 train_loss:0.26355 +2025-04-19 04:51:06,752 INFO Epoch:91 val_res:0.802000 +2025-04-19 04:51:22,013 INFO Epoch:92 train_loss:0.28777 +2025-04-19 04:51:26,297 INFO Epoch:92 val_res:0.794000 +2025-04-19 04:51:41,725 INFO Epoch:93 train_loss:0.34415 +2025-04-19 04:51:46,000 INFO Epoch:93 val_res:0.787000 +2025-04-19 04:52:00,810 INFO Epoch:94 train_loss:0.30958 +2025-04-19 04:52:04,929 INFO Epoch:94 val_res:0.788000 +2025-04-19 04:52:19,851 INFO Epoch:95 train_loss:0.35997 +2025-04-19 04:52:24,228 INFO Epoch:95 val_res:0.786000 +2025-04-19 04:52:39,759 INFO Epoch:96 train_loss:0.27668 +2025-04-19 04:52:44,193 INFO Epoch:96 val_res:0.799000 +2025-04-19 04:52:58,760 INFO Epoch:97 train_loss:0.24826 +2025-04-19 04:53:03,177 INFO Epoch:97 val_res:0.790000 +2025-04-19 04:53:19,059 INFO Epoch:98 train_loss:0.24529 +2025-04-19 04:53:23,058 INFO Epoch:98 val_res:0.791000 +2025-04-19 04:53:38,293 INFO Epoch:99 train_loss:0.24235 +2025-04-19 04:53:42,377 INFO Epoch:99 val_res:0.789000 +2025-04-19 04:53:43,032 INFO ===================================== +2025-04-19 04:53:43,033 INFO Start testing... +2025-04-19 04:53:43,033 INFO ===================================== +2025-04-19 04:53:48,125 INFO Incremental step 1 Testing res: 0.802000 +2025-04-19 04:53:48,126 INFO forgetting: 0.076000 +2025-04-19 04:53:48,128 INFO Incremental step: 2 +2025-04-19 04:54:06,434 INFO Epoch:0 train_loss:5.13915 +2025-04-19 04:54:12,778 INFO Epoch:0 val_res:0.532667 +2025-04-19 04:54:12,779 INFO Saving best model at Epoch 0 +2025-04-19 04:54:34,643 INFO Epoch:1 train_loss:2.22273 +2025-04-19 04:54:40,268 INFO Epoch:1 val_res:0.580667 +2025-04-19 04:54:40,268 INFO Saving best model at Epoch 1 +2025-04-19 04:54:59,954 INFO Epoch:2 train_loss:1.64713 +2025-04-19 04:55:05,491 INFO Epoch:2 val_res:0.607333 +2025-04-19 04:55:05,491 INFO Saving best model at Epoch 2 +2025-04-19 04:55:24,379 INFO Epoch:3 train_loss:1.39588 +2025-04-19 04:55:30,561 INFO Epoch:3 val_res:0.622667 +2025-04-19 04:55:30,562 INFO Saving best model at Epoch 3 +2025-04-19 04:55:49,426 INFO Epoch:4 train_loss:1.23835 +2025-04-19 04:55:54,934 INFO Epoch:4 val_res:0.636667 +2025-04-19 04:55:54,934 INFO Saving best model at Epoch 4 +2025-04-19 04:56:13,520 INFO Epoch:5 train_loss:1.12092 +2025-04-19 04:56:19,124 INFO Epoch:5 val_res:0.652667 +2025-04-19 04:56:19,124 INFO Saving best model at Epoch 5 +2025-04-19 04:56:37,876 INFO Epoch:6 train_loss:1.02111 +2025-04-19 04:56:43,694 INFO Epoch:6 val_res:0.659333 +2025-04-19 04:56:43,694 INFO Saving best model at Epoch 6 +2025-04-19 04:57:01,867 INFO Epoch:7 train_loss:0.94095 +2025-04-19 04:57:07,576 INFO Epoch:7 val_res:0.672000 +2025-04-19 04:57:07,576 INFO Saving best model at Epoch 7 +2025-04-19 04:57:26,388 INFO Epoch:8 train_loss:0.85581 +2025-04-19 04:57:31,917 INFO Epoch:8 val_res:0.675333 +2025-04-19 04:57:31,918 INFO Saving best model at Epoch 8 +2025-04-19 04:57:50,982 INFO Epoch:9 train_loss:0.79306 +2025-04-19 04:57:56,388 INFO Epoch:9 val_res:0.692667 +2025-04-19 04:57:56,388 INFO Saving best model at Epoch 9 +2025-04-19 04:58:14,761 INFO Epoch:10 train_loss:0.74315 +2025-04-19 04:58:20,484 INFO Epoch:10 val_res:0.700000 +2025-04-19 04:58:20,484 INFO Saving best model at Epoch 10 +2025-04-19 04:58:38,889 INFO Epoch:11 train_loss:0.68974 +2025-04-19 04:58:44,269 INFO Epoch:11 val_res:0.713333 +2025-04-19 04:58:44,269 INFO Saving best model at Epoch 11 +2025-04-19 04:59:03,378 INFO Epoch:12 train_loss:0.63055 +2025-04-19 04:59:08,636 INFO Epoch:12 val_res:0.714667 +2025-04-19 04:59:08,636 INFO Saving best model at Epoch 12 +2025-04-19 04:59:27,168 INFO Epoch:13 train_loss:0.59209 +2025-04-19 04:59:33,028 INFO Epoch:13 val_res:0.723333 +2025-04-19 04:59:33,028 INFO Saving best model at Epoch 13 +2025-04-19 04:59:51,260 INFO Epoch:14 train_loss:0.57183 +2025-04-19 04:59:56,620 INFO Epoch:14 val_res:0.714667 +2025-04-19 05:00:13,604 INFO Epoch:15 train_loss:0.55231 +2025-04-19 05:00:19,077 INFO Epoch:15 val_res:0.726000 +2025-04-19 05:00:19,077 INFO Saving best model at Epoch 15 +2025-04-19 05:00:36,374 INFO Epoch:16 train_loss:0.50146 +2025-04-19 05:00:41,726 INFO Epoch:16 val_res:0.736000 +2025-04-19 05:00:41,726 INFO Saving best model at Epoch 16 +2025-04-19 05:01:00,087 INFO Epoch:17 train_loss:0.46827 +2025-04-19 05:01:05,405 INFO Epoch:17 val_res:0.737333 +2025-04-19 05:01:05,405 INFO Saving best model at Epoch 17 +2025-04-19 05:01:24,204 INFO Epoch:18 train_loss:0.42403 +2025-04-19 05:01:29,656 INFO Epoch:18 val_res:0.739333 +2025-04-19 05:01:29,656 INFO Saving best model at Epoch 18 +2025-04-19 05:01:47,402 INFO Epoch:19 train_loss:0.41450 +2025-04-19 05:01:52,692 INFO Epoch:19 val_res:0.742000 +2025-04-19 05:01:52,692 INFO Saving best model at Epoch 19 +2025-04-19 05:02:11,046 INFO Epoch:20 train_loss:0.39345 +2025-04-19 05:02:16,328 INFO Epoch:20 val_res:0.726667 +2025-04-19 05:02:32,807 INFO Epoch:21 train_loss:0.36968 +2025-04-19 05:02:38,521 INFO Epoch:21 val_res:0.739333 +2025-04-19 05:02:54,451 INFO Epoch:22 train_loss:0.35369 +2025-04-19 05:02:59,844 INFO Epoch:22 val_res:0.734667 +2025-04-19 05:03:16,224 INFO Epoch:23 train_loss:0.33404 +2025-04-19 05:03:21,838 INFO Epoch:23 val_res:0.732667 +2025-04-19 05:03:37,974 INFO Epoch:24 train_loss:0.33561 +2025-04-19 05:03:43,622 INFO Epoch:24 val_res:0.732000 +2025-04-19 05:04:00,532 INFO Epoch:25 train_loss:0.31609 +2025-04-19 05:04:05,832 INFO Epoch:25 val_res:0.725333 +2025-04-19 05:04:22,681 INFO Epoch:26 train_loss:0.30440 +2025-04-19 05:04:28,282 INFO Epoch:26 val_res:0.730000 +2025-04-19 05:04:44,577 INFO Epoch:27 train_loss:0.29399 +2025-04-19 05:04:50,024 INFO Epoch:27 val_res:0.725333 +2025-04-19 05:05:06,706 INFO Epoch:28 train_loss:0.29246 +2025-04-19 05:05:12,321 INFO Epoch:28 val_res:0.722000 +2025-04-19 05:05:28,983 INFO Epoch:29 train_loss:0.29167 +2025-04-19 05:05:34,518 INFO Epoch:29 val_res:0.729333 +2025-04-19 05:05:51,321 INFO Epoch:30 train_loss:0.27382 +2025-04-19 05:05:56,503 INFO Epoch:30 val_res:0.723333 +2025-04-19 05:06:13,428 INFO Epoch:31 train_loss:0.27516 +2025-04-19 05:06:19,032 INFO Epoch:31 val_res:0.706667 +2025-04-19 05:06:34,828 INFO Epoch:32 train_loss:0.27058 +2025-04-19 05:06:40,176 INFO Epoch:32 val_res:0.722667 +2025-04-19 05:06:56,454 INFO Epoch:33 train_loss:0.27905 +2025-04-19 05:07:01,698 INFO Epoch:33 val_res:0.702667 +2025-04-19 05:07:17,305 INFO Epoch:34 train_loss:0.28098 +2025-04-19 05:07:22,814 INFO Epoch:34 val_res:0.716667 +2025-04-19 05:07:38,414 INFO Epoch:35 train_loss:0.24607 +2025-04-19 05:07:43,533 INFO Epoch:35 val_res:0.710667 +2025-04-19 05:08:00,009 INFO Epoch:36 train_loss:0.24289 +2025-04-19 05:08:05,164 INFO Epoch:36 val_res:0.704667 +2025-04-19 05:08:20,859 INFO Epoch:37 train_loss:0.22895 +2025-04-19 05:08:26,089 INFO Epoch:37 val_res:0.708667 +2025-04-19 05:08:41,762 INFO Epoch:38 train_loss:0.22841 +2025-04-19 05:08:46,694 INFO Epoch:38 val_res:0.708000 +2025-04-19 05:09:02,430 INFO Epoch:39 train_loss:0.21615 +2025-04-19 05:09:07,972 INFO Epoch:39 val_res:0.708667 +2025-04-19 05:09:23,572 INFO Epoch:40 train_loss:0.20056 +2025-04-19 05:09:28,872 INFO Epoch:40 val_res:0.701333 +2025-04-19 05:09:45,379 INFO Epoch:41 train_loss:0.22108 +2025-04-19 05:09:50,767 INFO Epoch:41 val_res:0.706667 +2025-04-19 05:10:06,358 INFO Epoch:42 train_loss:0.24981 +2025-04-19 05:10:12,051 INFO Epoch:42 val_res:0.710667 +2025-04-19 05:10:27,769 INFO Epoch:43 train_loss:0.27447 +2025-04-19 05:10:32,865 INFO Epoch:43 val_res:0.720667 +2025-04-19 05:10:49,425 INFO Epoch:44 train_loss:0.22325 +2025-04-19 05:10:54,708 INFO Epoch:44 val_res:0.697333 +2025-04-19 05:11:10,142 INFO Epoch:45 train_loss:0.22047 +2025-04-19 05:11:15,338 INFO Epoch:45 val_res:0.697333 +2025-04-19 05:11:31,272 INFO Epoch:46 train_loss:0.21709 +2025-04-19 05:11:36,192 INFO Epoch:46 val_res:0.688000 +2025-04-19 05:11:52,478 INFO Epoch:47 train_loss:0.22917 +2025-04-19 05:11:58,000 INFO Epoch:47 val_res:0.693333 +2025-04-19 05:12:13,514 INFO Epoch:48 train_loss:0.23055 +2025-04-19 05:12:18,834 INFO Epoch:48 val_res:0.696667 +2025-04-19 05:12:34,888 INFO Epoch:49 train_loss:0.22521 +2025-04-19 05:12:40,133 INFO Epoch:49 val_res:0.697333 +2025-04-19 05:12:55,604 INFO Epoch:50 train_loss:0.19785 +2025-04-19 05:13:01,075 INFO Epoch:50 val_res:0.702667 +2025-04-19 05:13:16,633 INFO Epoch:51 train_loss:0.20194 +2025-04-19 05:13:21,739 INFO Epoch:51 val_res:0.682667 +2025-04-19 05:13:38,000 INFO Epoch:52 train_loss:0.21216 +2025-04-19 05:13:43,287 INFO Epoch:52 val_res:0.699333 +2025-04-19 05:13:58,436 INFO Epoch:53 train_loss:0.20676 +2025-04-19 05:14:03,784 INFO Epoch:53 val_res:0.686000 +2025-04-19 05:14:20,163 INFO Epoch:54 train_loss:0.20120 +2025-04-19 05:14:25,182 INFO Epoch:54 val_res:0.685333 +2025-04-19 05:14:40,605 INFO Epoch:55 train_loss:0.17463 +2025-04-19 05:14:46,082 INFO Epoch:55 val_res:0.696667 +2025-04-19 05:15:01,399 INFO Epoch:56 train_loss:0.17729 +2025-04-19 05:15:06,393 INFO Epoch:56 val_res:0.692000 +2025-04-19 05:15:22,056 INFO Epoch:57 train_loss:0.16674 +2025-04-19 05:15:27,330 INFO Epoch:57 val_res:0.694000 +2025-04-19 05:15:42,483 INFO Epoch:58 train_loss:0.17424 +2025-04-19 05:15:47,740 INFO Epoch:58 val_res:0.681333 +2025-04-19 05:16:03,893 INFO Epoch:59 train_loss:0.19831 +2025-04-19 05:16:08,845 INFO Epoch:59 val_res:0.688667 +2025-04-19 05:16:24,538 INFO Epoch:60 train_loss:0.19172 +2025-04-19 05:16:30,182 INFO Epoch:60 val_res:0.687333 +2025-04-19 05:16:45,536 INFO Epoch:61 train_loss:0.16311 +2025-04-19 05:16:50,724 INFO Epoch:61 val_res:0.668667 +2025-04-19 05:17:07,234 INFO Epoch:62 train_loss:0.17096 +2025-04-19 05:17:12,079 INFO Epoch:62 val_res:0.677333 +2025-04-19 05:17:27,340 INFO Epoch:63 train_loss:0.16663 +2025-04-19 05:17:32,539 INFO Epoch:63 val_res:0.688000 +2025-04-19 05:17:48,884 INFO Epoch:64 train_loss:0.18150 +2025-04-19 05:17:53,947 INFO Epoch:64 val_res:0.682000 +2025-04-19 05:18:09,920 INFO Epoch:65 train_loss:0.19007 +2025-04-19 05:18:15,523 INFO Epoch:65 val_res:0.676667 +2025-04-19 05:18:30,264 INFO Epoch:66 train_loss:0.17958 +2025-04-19 05:18:35,523 INFO Epoch:66 val_res:0.680667 +2025-04-19 05:18:51,205 INFO Epoch:67 train_loss:0.15743 +2025-04-19 05:18:56,229 INFO Epoch:67 val_res:0.669333 +2025-04-19 05:19:11,606 INFO Epoch:68 train_loss:0.16605 +2025-04-19 05:19:17,096 INFO Epoch:68 val_res:0.673333 +2025-04-19 05:19:32,438 INFO Epoch:69 train_loss:0.17610 +2025-04-19 05:19:37,558 INFO Epoch:69 val_res:0.673333 +2025-04-19 05:19:53,793 INFO Epoch:70 train_loss:0.14153 +2025-04-19 05:19:59,135 INFO Epoch:70 val_res:0.677333 +2025-04-19 05:20:14,412 INFO Epoch:71 train_loss:0.14522 +2025-04-19 05:20:19,560 INFO Epoch:71 val_res:0.670000 +2025-04-19 05:20:35,446 INFO Epoch:72 train_loss:0.14235 +2025-04-19 05:20:40,661 INFO Epoch:72 val_res:0.678000 +2025-04-19 05:20:55,989 INFO Epoch:73 train_loss:0.13815 +2025-04-19 05:21:01,162 INFO Epoch:73 val_res:0.670667 +2025-04-19 05:21:16,521 INFO Epoch:74 train_loss:0.16668 +2025-04-19 05:21:21,738 INFO Epoch:74 val_res:0.668667 +2025-04-19 05:21:37,250 INFO Epoch:75 train_loss:0.15728 +2025-04-19 05:21:42,320 INFO Epoch:75 val_res:0.663333 +2025-04-19 05:21:57,418 INFO Epoch:76 train_loss:0.14836 +2025-04-19 05:22:02,429 INFO Epoch:76 val_res:0.675333 +2025-04-19 05:22:17,491 INFO Epoch:77 train_loss:0.13519 +2025-04-19 05:22:22,374 INFO Epoch:77 val_res:0.678667 +2025-04-19 05:22:37,519 INFO Epoch:78 train_loss:0.12401 +2025-04-19 05:22:42,720 INFO Epoch:78 val_res:0.667333 +2025-04-19 05:22:58,633 INFO Epoch:79 train_loss:0.14744 +2025-04-19 05:23:03,855 INFO Epoch:79 val_res:0.669333 +2025-04-19 05:23:18,951 INFO Epoch:80 train_loss:0.16386 +2025-04-19 05:23:24,160 INFO Epoch:80 val_res:0.674667 +2025-04-19 05:23:39,874 INFO Epoch:81 train_loss:0.14641 +2025-04-19 05:23:44,884 INFO Epoch:81 val_res:0.667333 +2025-04-19 05:24:00,174 INFO Epoch:82 train_loss:0.14447 +2025-04-19 05:24:05,537 INFO Epoch:82 val_res:0.650667 +2025-04-19 05:24:20,957 INFO Epoch:83 train_loss:0.15770 +2025-04-19 05:24:25,707 INFO Epoch:83 val_res:0.680667 +2025-04-19 05:24:40,991 INFO Epoch:84 train_loss:0.16378 +2025-04-19 05:24:46,238 INFO Epoch:84 val_res:0.664667 +2025-04-19 05:25:02,285 INFO Epoch:85 train_loss:0.14958 +2025-04-19 05:25:07,216 INFO Epoch:85 val_res:0.663333 +2025-04-19 05:25:22,451 INFO Epoch:86 train_loss:0.13241 +2025-04-19 05:25:28,007 INFO Epoch:86 val_res:0.663333 +2025-04-19 05:25:43,432 INFO Epoch:87 train_loss:0.11765 +2025-04-19 05:25:48,498 INFO Epoch:87 val_res:0.654000 +2025-04-19 05:26:03,767 INFO Epoch:88 train_loss:0.11662 +2025-04-19 05:26:09,462 INFO Epoch:88 val_res:0.664000 +2025-04-19 05:26:25,050 INFO Epoch:89 train_loss:0.11348 +2025-04-19 05:26:30,106 INFO Epoch:89 val_res:0.656000 +2025-04-19 05:26:45,771 INFO Epoch:90 train_loss:0.11400 +2025-04-19 05:26:51,105 INFO Epoch:90 val_res:0.673333 +2025-04-19 05:27:06,102 INFO Epoch:91 train_loss:0.15786 +2025-04-19 05:27:10,937 INFO Epoch:91 val_res:0.664667 +2025-04-19 05:27:26,986 INFO Epoch:92 train_loss:0.15957 +2025-04-19 05:27:32,592 INFO Epoch:92 val_res:0.652667 +2025-04-19 05:27:48,139 INFO Epoch:93 train_loss:0.21597 +2025-04-19 05:27:53,315 INFO Epoch:93 val_res:0.656667 +2025-04-19 05:28:09,885 INFO Epoch:94 train_loss:0.16335 +2025-04-19 05:28:15,409 INFO Epoch:94 val_res:0.650667 +2025-04-19 05:28:30,565 INFO Epoch:95 train_loss:0.12677 +2025-04-19 05:28:35,703 INFO Epoch:95 val_res:0.662000 +2025-04-19 05:28:52,232 INFO Epoch:96 train_loss:0.10333 +2025-04-19 05:28:57,758 INFO Epoch:96 val_res:0.654000 +2025-04-19 05:29:12,795 INFO Epoch:97 train_loss:0.12193 +2025-04-19 05:29:18,027 INFO Epoch:97 val_res:0.654000 +2025-04-19 05:29:34,267 INFO Epoch:98 train_loss:0.12862 +2025-04-19 05:29:39,689 INFO Epoch:98 val_res:0.651333 +2025-04-19 05:29:54,530 INFO Epoch:99 train_loss:0.11858 +2025-04-19 05:29:59,902 INFO Epoch:99 val_res:0.666667 +2025-04-19 05:30:00,575 INFO ===================================== +2025-04-19 05:30:00,576 INFO Start testing... +2025-04-19 05:30:00,577 INFO ===================================== +2025-04-19 05:30:06,925 INFO Incremental step 2 Testing res: 0.724000 +2025-04-19 05:30:06,927 INFO forgetting: 0.122000 +2025-04-19 05:30:06,930 INFO Incremental step: 3 +2025-04-19 05:30:24,970 INFO Epoch:0 train_loss:5.16559 +2025-04-19 05:30:32,196 INFO Epoch:0 val_res:0.552500 +2025-04-19 05:30:32,197 INFO Saving best model at Epoch 0 +2025-04-19 05:30:51,433 INFO Epoch:1 train_loss:2.46036 +2025-04-19 05:30:58,305 INFO Epoch:1 val_res:0.557500 +2025-04-19 05:30:58,306 INFO Saving best model at Epoch 1 +2025-04-19 05:31:15,909 INFO Epoch:2 train_loss:1.99069 +2025-04-19 05:31:22,683 INFO Epoch:2 val_res:0.566000 +2025-04-19 05:31:22,683 INFO Saving best model at Epoch 2 +2025-04-19 05:31:40,559 INFO Epoch:3 train_loss:1.76423 +2025-04-19 05:31:47,194 INFO Epoch:3 val_res:0.567500 +2025-04-19 05:31:47,194 INFO Saving best model at Epoch 3 +2025-04-19 05:32:05,070 INFO Epoch:4 train_loss:1.62565 +2025-04-19 05:32:12,011 INFO Epoch:4 val_res:0.579000 +2025-04-19 05:32:12,011 INFO Saving best model at Epoch 4 +2025-04-19 05:32:28,604 INFO Epoch:5 train_loss:1.52306 +2025-04-19 05:32:35,212 INFO Epoch:5 val_res:0.582500 +2025-04-19 05:32:35,212 INFO Saving best model at Epoch 5 +2025-04-19 05:32:53,214 INFO Epoch:6 train_loss:1.42401 +2025-04-19 05:32:59,932 INFO Epoch:6 val_res:0.594000 +2025-04-19 05:32:59,933 INFO Saving best model at Epoch 6 +2025-04-19 05:33:17,472 INFO Epoch:7 train_loss:1.34986 +2025-04-19 05:33:24,222 INFO Epoch:7 val_res:0.599500 +2025-04-19 05:33:24,222 INFO Saving best model at Epoch 7 +2025-04-19 05:33:42,165 INFO Epoch:8 train_loss:1.30081 +2025-04-19 05:33:48,623 INFO Epoch:8 val_res:0.609000 +2025-04-19 05:33:48,623 INFO Saving best model at Epoch 8 +2025-04-19 05:34:07,302 INFO Epoch:9 train_loss:1.20780 +2025-04-19 05:34:14,133 INFO Epoch:9 val_res:0.611500 +2025-04-19 05:34:14,133 INFO Saving best model at Epoch 9 +2025-04-19 05:34:31,102 INFO Epoch:10 train_loss:1.13853 +2025-04-19 05:34:37,716 INFO Epoch:10 val_res:0.620000 +2025-04-19 05:34:37,716 INFO Saving best model at Epoch 10 +2025-04-19 05:34:55,613 INFO Epoch:11 train_loss:1.09459 +2025-04-19 05:35:02,570 INFO Epoch:11 val_res:0.631000 +2025-04-19 05:35:02,570 INFO Saving best model at Epoch 11 +2025-04-19 05:35:19,127 INFO Epoch:12 train_loss:1.02097 +2025-04-19 05:35:25,911 INFO Epoch:12 val_res:0.639000 +2025-04-19 05:35:25,912 INFO Saving best model at Epoch 12 +2025-04-19 05:35:43,324 INFO Epoch:13 train_loss:0.96038 +2025-04-19 05:35:49,883 INFO Epoch:13 val_res:0.645000 +2025-04-19 05:35:49,883 INFO Saving best model at Epoch 13 +2025-04-19 05:36:07,186 INFO Epoch:14 train_loss:0.91157 +2025-04-19 05:36:14,011 INFO Epoch:14 val_res:0.651000 +2025-04-19 05:36:14,012 INFO Saving best model at Epoch 14 +2025-04-19 05:36:31,266 INFO Epoch:15 train_loss:0.86995 +2025-04-19 05:36:37,784 INFO Epoch:15 val_res:0.641000 +2025-04-19 05:36:53,222 INFO Epoch:16 train_loss:0.84663 +2025-04-19 05:36:59,776 INFO Epoch:16 val_res:0.644500 +2025-04-19 05:37:15,227 INFO Epoch:17 train_loss:0.82847 +2025-04-19 05:37:21,864 INFO Epoch:17 val_res:0.652500 +2025-04-19 05:37:21,870 INFO Saving best model at Epoch 17 +2025-04-19 05:37:39,029 INFO Epoch:18 train_loss:0.77253 +2025-04-19 05:37:45,770 INFO Epoch:18 val_res:0.660000 +2025-04-19 05:37:45,770 INFO Saving best model at Epoch 18 +2025-04-19 05:38:03,171 INFO Epoch:19 train_loss:0.73992 +2025-04-19 05:38:09,876 INFO Epoch:19 val_res:0.654500 +2025-04-19 05:38:26,097 INFO Epoch:20 train_loss:0.70106 +2025-04-19 05:38:32,526 INFO Epoch:20 val_res:0.659000 +2025-04-19 05:38:48,563 INFO Epoch:21 train_loss:0.66195 +2025-04-19 05:38:55,166 INFO Epoch:21 val_res:0.649500 +2025-04-19 05:39:11,181 INFO Epoch:22 train_loss:0.62695 +2025-04-19 05:39:17,894 INFO Epoch:22 val_res:0.656000 +2025-04-19 05:39:33,272 INFO Epoch:23 train_loss:0.60525 +2025-04-19 05:39:40,132 INFO Epoch:23 val_res:0.656000 +2025-04-19 05:39:56,328 INFO Epoch:24 train_loss:0.57901 +2025-04-19 05:40:03,210 INFO Epoch:24 val_res:0.645000 +2025-04-19 05:40:18,504 INFO Epoch:25 train_loss:0.56983 +2025-04-19 05:40:25,493 INFO Epoch:25 val_res:0.646000 +2025-04-19 05:40:41,459 INFO Epoch:26 train_loss:0.55420 +2025-04-19 05:40:48,016 INFO Epoch:26 val_res:0.649000 +2025-04-19 05:41:03,117 INFO Epoch:27 train_loss:0.56123 +2025-04-19 05:41:09,947 INFO Epoch:27 val_res:0.640500 +2025-04-19 05:41:25,145 INFO Epoch:28 train_loss:0.52484 +2025-04-19 05:41:31,810 INFO Epoch:28 val_res:0.630000 +2025-04-19 05:41:47,722 INFO Epoch:29 train_loss:0.50214 +2025-04-19 05:41:54,649 INFO Epoch:29 val_res:0.630500 +2025-04-19 05:42:09,859 INFO Epoch:30 train_loss:0.49407 +2025-04-19 05:42:16,490 INFO Epoch:30 val_res:0.632500 +2025-04-19 05:42:32,285 INFO Epoch:31 train_loss:0.47199 +2025-04-19 05:42:38,934 INFO Epoch:31 val_res:0.638000 +2025-04-19 05:42:54,444 INFO Epoch:32 train_loss:0.48861 +2025-04-19 05:43:01,381 INFO Epoch:32 val_res:0.619500 +2025-04-19 05:43:17,356 INFO Epoch:33 train_loss:0.48357 +2025-04-19 05:43:23,949 INFO Epoch:33 val_res:0.626500 +2025-04-19 05:43:40,363 INFO Epoch:34 train_loss:0.46518 +2025-04-19 05:43:47,315 INFO Epoch:34 val_res:0.630500 +2025-04-19 05:44:02,879 INFO Epoch:35 train_loss:0.45736 +2025-04-19 05:44:09,441 INFO Epoch:35 val_res:0.618500 +2025-04-19 05:44:25,642 INFO Epoch:36 train_loss:0.46033 +2025-04-19 05:44:32,299 INFO Epoch:36 val_res:0.615000 +2025-04-19 05:44:47,729 INFO Epoch:37 train_loss:0.46770 +2025-04-19 05:44:54,587 INFO Epoch:37 val_res:0.614000 +2025-04-19 05:45:10,584 INFO Epoch:38 train_loss:0.44837 +2025-04-19 05:45:16,993 INFO Epoch:38 val_res:0.613500 +2025-04-19 05:45:32,825 INFO Epoch:39 train_loss:0.43201 +2025-04-19 05:45:39,794 INFO Epoch:39 val_res:0.617000 +2025-04-19 05:45:55,361 INFO Epoch:40 train_loss:0.45465 +2025-04-19 05:46:02,116 INFO Epoch:40 val_res:0.610000 +2025-04-19 05:46:17,966 INFO Epoch:41 train_loss:0.49473 +2025-04-19 05:46:24,760 INFO Epoch:41 val_res:0.610500 +2025-04-19 05:46:39,610 INFO Epoch:42 train_loss:0.43926 +2025-04-19 05:46:46,698 INFO Epoch:42 val_res:0.610500 +2025-04-19 05:47:02,669 INFO Epoch:43 train_loss:0.42263 +2025-04-19 05:47:09,176 INFO Epoch:43 val_res:0.604000 +2025-04-19 05:47:24,610 INFO Epoch:44 train_loss:0.41784 +2025-04-19 05:47:31,739 INFO Epoch:44 val_res:0.607500 +2025-04-19 05:47:48,162 INFO Epoch:45 train_loss:0.41005 +2025-04-19 05:47:54,663 INFO Epoch:45 val_res:0.599500 +2025-04-19 05:48:11,051 INFO Epoch:46 train_loss:0.41815 +2025-04-19 05:48:18,160 INFO Epoch:46 val_res:0.601500 +2025-04-19 05:48:33,258 INFO Epoch:47 train_loss:0.39736 +2025-04-19 05:48:39,956 INFO Epoch:47 val_res:0.588500 +2025-04-19 05:48:56,021 INFO Epoch:48 train_loss:0.39744 +2025-04-19 05:49:02,322 INFO Epoch:48 val_res:0.593000 +2025-04-19 05:49:18,027 INFO Epoch:49 train_loss:0.40333 +2025-04-19 05:49:24,969 INFO Epoch:49 val_res:0.594000 +2025-04-19 05:49:40,795 INFO Epoch:50 train_loss:0.41507 +2025-04-19 05:49:47,012 INFO Epoch:50 val_res:0.585500 +2025-04-19 05:50:03,241 INFO Epoch:51 train_loss:0.39743 +2025-04-19 05:50:10,216 INFO Epoch:51 val_res:0.589500 +2025-04-19 05:50:25,408 INFO Epoch:52 train_loss:0.38836 +2025-04-19 05:50:32,071 INFO Epoch:52 val_res:0.582500 +2025-04-19 05:50:48,688 INFO Epoch:53 train_loss:0.39808 +2025-04-19 05:50:55,195 INFO Epoch:53 val_res:0.590500 +2025-04-19 05:51:10,846 INFO Epoch:54 train_loss:0.37278 +2025-04-19 05:51:17,681 INFO Epoch:54 val_res:0.585000 +2025-04-19 05:51:33,172 INFO Epoch:55 train_loss:0.35431 +2025-04-19 05:51:39,519 INFO Epoch:55 val_res:0.583500 +2025-04-19 05:51:55,365 INFO Epoch:56 train_loss:0.34606 +2025-04-19 05:52:02,169 INFO Epoch:56 val_res:0.589000 +2025-04-19 05:52:18,039 INFO Epoch:57 train_loss:0.40322 +2025-04-19 05:52:24,632 INFO Epoch:57 val_res:0.584000 +2025-04-19 05:52:41,150 INFO Epoch:58 train_loss:0.37905 +2025-04-19 05:52:48,092 INFO Epoch:58 val_res:0.581000 +2025-04-19 05:53:03,384 INFO Epoch:59 train_loss:0.36259 +2025-04-19 05:53:10,423 INFO Epoch:59 val_res:0.584000 +2025-04-19 05:53:26,334 INFO Epoch:60 train_loss:0.35283 +2025-04-19 05:53:33,148 INFO Epoch:60 val_res:0.578000 +2025-04-19 05:53:48,810 INFO Epoch:61 train_loss:0.35896 +2025-04-19 05:53:55,713 INFO Epoch:61 val_res:0.570000 +2025-04-19 05:54:11,318 INFO Epoch:62 train_loss:0.36369 +2025-04-19 05:54:18,171 INFO Epoch:62 val_res:0.575500 +2025-04-19 05:54:34,373 INFO Epoch:63 train_loss:0.36263 +2025-04-19 05:54:40,980 INFO Epoch:63 val_res:0.571000 +2025-04-19 05:54:57,014 INFO Epoch:64 train_loss:0.39156 +2025-04-19 05:55:03,695 INFO Epoch:64 val_res:0.573000 +2025-04-19 05:55:19,526 INFO Epoch:65 train_loss:0.37205 +2025-04-19 05:55:26,188 INFO Epoch:65 val_res:0.574000 +2025-04-19 05:55:41,992 INFO Epoch:66 train_loss:0.38013 +2025-04-19 05:55:48,738 INFO Epoch:66 val_res:0.571000 +2025-04-19 05:56:04,622 INFO Epoch:67 train_loss:0.42555 +2025-04-19 05:56:11,321 INFO Epoch:67 val_res:0.572500 +2025-04-19 05:56:27,268 INFO Epoch:68 train_loss:0.37754 +2025-04-19 05:56:33,864 INFO Epoch:68 val_res:0.568500 +2025-04-19 05:56:50,232 INFO Epoch:69 train_loss:0.36450 +2025-04-19 05:56:56,856 INFO Epoch:69 val_res:0.572500 +2025-04-19 05:57:12,511 INFO Epoch:70 train_loss:0.37799 +2025-04-19 05:57:19,273 INFO Epoch:70 val_res:0.563500 +2025-04-19 05:57:34,799 INFO Epoch:71 train_loss:0.36183 +2025-04-19 05:57:41,324 INFO Epoch:71 val_res:0.571000 +2025-04-19 05:57:57,652 INFO Epoch:72 train_loss:0.34753 +2025-04-19 05:58:04,426 INFO Epoch:72 val_res:0.585000 +2025-04-19 05:58:20,123 INFO Epoch:73 train_loss:0.35528 +2025-04-19 05:58:26,487 INFO Epoch:73 val_res:0.561000 +2025-04-19 05:58:41,869 INFO Epoch:74 train_loss:0.38125 +2025-04-19 05:58:48,133 INFO Epoch:74 val_res:0.561000 +2025-04-19 05:59:03,228 INFO Epoch:75 train_loss:0.36479 +2025-04-19 05:59:09,489 INFO Epoch:75 val_res:0.572000 +2025-04-19 05:59:24,538 INFO Epoch:76 train_loss:0.32127 +2025-04-19 05:59:30,906 INFO Epoch:76 val_res:0.567000 +2025-04-19 05:59:46,639 INFO Epoch:77 train_loss:0.32505 +2025-04-19 05:59:53,375 INFO Epoch:77 val_res:0.565500 +2025-04-19 06:00:09,929 INFO Epoch:78 train_loss:0.35437 +2025-04-19 06:00:16,313 INFO Epoch:78 val_res:0.554500 +2025-04-19 06:00:32,889 INFO Epoch:79 train_loss:0.32714 +2025-04-19 06:00:40,111 INFO Epoch:79 val_res:0.565500 +2025-04-19 06:00:55,802 INFO Epoch:80 train_loss:0.32293 +2025-04-19 06:01:02,594 INFO Epoch:80 val_res:0.559000 +2025-04-19 06:01:19,134 INFO Epoch:81 train_loss:0.32005 +2025-04-19 06:01:25,962 INFO Epoch:81 val_res:0.562500 +2025-04-19 06:01:41,440 INFO Epoch:82 train_loss:0.30425 +2025-04-19 06:01:48,476 INFO Epoch:82 val_res:0.558500 +2025-04-19 06:02:05,027 INFO Epoch:83 train_loss:0.29291 +2025-04-19 06:02:11,454 INFO Epoch:83 val_res:0.561500 +2025-04-19 06:02:27,449 INFO Epoch:84 train_loss:0.31122 +2025-04-19 06:02:34,670 INFO Epoch:84 val_res:0.557500 +2025-04-19 06:02:51,631 INFO Epoch:85 train_loss:0.32153 +2025-04-19 06:02:58,536 INFO Epoch:85 val_res:0.555500 +2025-04-19 06:03:15,131 INFO Epoch:86 train_loss:0.31651 +2025-04-19 06:03:22,254 INFO Epoch:86 val_res:0.546500 +2025-04-19 06:03:37,707 INFO Epoch:87 train_loss:0.31708 +2025-04-19 06:03:44,598 INFO Epoch:87 val_res:0.551500 +2025-04-19 06:04:00,744 INFO Epoch:88 train_loss:0.30356 +2025-04-19 06:04:07,852 INFO Epoch:88 val_res:0.552500 +2025-04-19 06:04:22,944 INFO Epoch:89 train_loss:0.31657 +2025-04-19 06:04:30,187 INFO Epoch:89 val_res:0.546500 +2025-04-19 06:04:46,614 INFO Epoch:90 train_loss:0.31550 +2025-04-19 06:04:53,136 INFO Epoch:90 val_res:0.553000 +2025-04-19 06:05:09,276 INFO Epoch:91 train_loss:0.30518 +2025-04-19 06:05:16,398 INFO Epoch:91 val_res:0.559000 +2025-04-19 06:05:32,532 INFO Epoch:92 train_loss:0.31036 +2025-04-19 06:05:39,570 INFO Epoch:92 val_res:0.548000 +2025-04-19 06:05:57,080 INFO Epoch:93 train_loss:0.28967 +2025-04-19 06:06:04,137 INFO Epoch:93 val_res:0.552500 +2025-04-19 06:06:21,065 INFO Epoch:94 train_loss:0.27653 +2025-04-19 06:06:28,224 INFO Epoch:94 val_res:0.550500 +2025-04-19 06:06:45,486 INFO Epoch:95 train_loss:0.29096 +2025-04-19 06:06:52,328 INFO Epoch:95 val_res:0.551500 +2025-04-19 06:07:08,519 INFO Epoch:96 train_loss:0.31245 +2025-04-19 06:07:15,763 INFO Epoch:96 val_res:0.546000 +2025-04-19 06:07:32,507 INFO Epoch:97 train_loss:0.32768 +2025-04-19 06:07:39,371 INFO Epoch:97 val_res:0.560000 +2025-04-19 06:07:56,138 INFO Epoch:98 train_loss:0.30011 +2025-04-19 06:08:03,052 INFO Epoch:98 val_res:0.551500 +2025-04-19 06:08:19,025 INFO Epoch:99 train_loss:0.30908 +2025-04-19 06:08:26,576 INFO Epoch:99 val_res:0.543000 +2025-04-19 06:08:27,239 INFO ===================================== +2025-04-19 06:08:27,239 INFO Start testing... +2025-04-19 06:08:27,240 INFO ===================================== +2025-04-19 06:08:35,234 INFO Incremental step 3 Testing res: 0.648500 +2025-04-19 06:08:35,237 INFO forgetting: 0.123333 +2025-04-19 06:08:35,240 INFO Incremental step: 4 +2025-04-19 06:08:51,933 INFO Epoch:0 train_loss:6.08454 +2025-04-19 06:09:00,896 INFO Epoch:0 val_res:0.520000 +2025-04-19 06:09:00,902 INFO Saving best model at Epoch 0 +2025-04-19 06:09:19,045 INFO Epoch:1 train_loss:2.81571 +2025-04-19 06:09:27,278 INFO Epoch:1 val_res:0.530800 +2025-04-19 06:09:27,278 INFO Saving best model at Epoch 1 +2025-04-19 06:09:46,427 INFO Epoch:2 train_loss:2.14399 +2025-04-19 06:09:55,051 INFO Epoch:2 val_res:0.534800 +2025-04-19 06:09:55,057 INFO Saving best model at Epoch 2 +2025-04-19 06:10:12,593 INFO Epoch:3 train_loss:1.86524 +2025-04-19 06:10:21,072 INFO Epoch:3 val_res:0.537200 +2025-04-19 06:10:21,073 INFO Saving best model at Epoch 3 +2025-04-19 06:10:39,234 INFO Epoch:4 train_loss:1.69448 +2025-04-19 06:10:47,233 INFO Epoch:4 val_res:0.541600 +2025-04-19 06:10:47,234 INFO Saving best model at Epoch 4 +2025-04-19 06:11:05,016 INFO Epoch:5 train_loss:1.58081 +2025-04-19 06:11:13,606 INFO Epoch:5 val_res:0.551200 +2025-04-19 06:11:13,606 INFO Saving best model at Epoch 5 +2025-04-19 06:11:30,932 INFO Epoch:6 train_loss:1.47780 +2025-04-19 06:11:39,526 INFO Epoch:6 val_res:0.557200 +2025-04-19 06:11:39,526 INFO Saving best model at Epoch 6 +2025-04-19 06:11:56,421 INFO Epoch:7 train_loss:1.39252 +2025-04-19 06:12:04,516 INFO Epoch:7 val_res:0.562000 +2025-04-19 06:12:04,516 INFO Saving best model at Epoch 7 +2025-04-19 06:12:22,016 INFO Epoch:8 train_loss:1.30738 +2025-04-19 06:12:30,438 INFO Epoch:8 val_res:0.566400 +2025-04-19 06:12:30,438 INFO Saving best model at Epoch 8 +2025-04-19 06:12:48,130 INFO Epoch:9 train_loss:1.24658 +2025-04-19 06:12:56,554 INFO Epoch:9 val_res:0.570400 +2025-04-19 06:12:56,554 INFO Saving best model at Epoch 9 +2025-04-19 06:13:15,339 INFO Epoch:10 train_loss:1.17202 +2025-04-19 06:13:23,488 INFO Epoch:10 val_res:0.568800 +2025-04-19 06:13:39,893 INFO Epoch:11 train_loss:1.13253 +2025-04-19 06:13:48,213 INFO Epoch:11 val_res:0.571600 +2025-04-19 06:13:48,213 INFO Saving best model at Epoch 11 +2025-04-19 06:14:06,054 INFO Epoch:12 train_loss:1.08075 +2025-04-19 06:14:14,427 INFO Epoch:12 val_res:0.577200 +2025-04-19 06:14:14,427 INFO Saving best model at Epoch 12 +2025-04-19 06:14:31,687 INFO Epoch:13 train_loss:1.04097 +2025-04-19 06:14:40,340 INFO Epoch:13 val_res:0.581600 +2025-04-19 06:14:40,340 INFO Saving best model at Epoch 13 +2025-04-19 06:14:57,938 INFO Epoch:14 train_loss:0.99492 +2025-04-19 06:15:06,286 INFO Epoch:14 val_res:0.583600 +2025-04-19 06:15:06,286 INFO Saving best model at Epoch 14 +2025-04-19 06:15:23,665 INFO Epoch:15 train_loss:0.94632 +2025-04-19 06:15:32,227 INFO Epoch:15 val_res:0.587200 +2025-04-19 06:15:32,227 INFO Saving best model at Epoch 15 +2025-04-19 06:15:49,686 INFO Epoch:16 train_loss:0.92393 +2025-04-19 06:15:58,124 INFO Epoch:16 val_res:0.591200 +2025-04-19 06:15:58,124 INFO Saving best model at Epoch 16 +2025-04-19 06:16:16,226 INFO Epoch:17 train_loss:0.88283 +2025-04-19 06:16:24,364 INFO Epoch:17 val_res:0.582000 +2025-04-19 06:16:41,011 INFO Epoch:18 train_loss:0.85665 +2025-04-19 06:16:49,326 INFO Epoch:18 val_res:0.584400 +2025-04-19 06:17:04,459 INFO Epoch:19 train_loss:0.83431 +2025-04-19 06:17:13,111 INFO Epoch:19 val_res:0.585200 +2025-04-19 06:17:29,046 INFO Epoch:20 train_loss:0.81184 +2025-04-19 06:17:37,288 INFO Epoch:20 val_res:0.583200 +2025-04-19 06:17:52,964 INFO Epoch:21 train_loss:0.77271 +2025-04-19 06:18:01,449 INFO Epoch:21 val_res:0.583600 +2025-04-19 06:18:16,681 INFO Epoch:22 train_loss:0.75868 +2025-04-19 06:18:25,129 INFO Epoch:22 val_res:0.580000 +2025-04-19 06:18:40,752 INFO Epoch:23 train_loss:0.74178 +2025-04-19 06:18:49,480 INFO Epoch:23 val_res:0.582000 +2025-04-19 06:19:04,886 INFO Epoch:24 train_loss:0.71734 +2025-04-19 06:19:13,883 INFO Epoch:24 val_res:0.572000 +2025-04-19 06:19:29,800 INFO Epoch:25 train_loss:0.70019 +2025-04-19 06:19:37,821 INFO Epoch:25 val_res:0.579200 +2025-04-19 06:19:54,092 INFO Epoch:26 train_loss:0.66301 +2025-04-19 06:20:02,482 INFO Epoch:26 val_res:0.569600 +2025-04-19 06:20:17,744 INFO Epoch:27 train_loss:0.64376 +2025-04-19 06:20:26,382 INFO Epoch:27 val_res:0.567600 +2025-04-19 06:20:41,908 INFO Epoch:28 train_loss:0.63844 +2025-04-19 06:20:49,963 INFO Epoch:28 val_res:0.573200 +2025-04-19 06:21:05,683 INFO Epoch:29 train_loss:0.61284 +2025-04-19 06:21:14,532 INFO Epoch:29 val_res:0.574400 +2025-04-19 06:21:30,233 INFO Epoch:30 train_loss:0.61647 +2025-04-19 06:21:38,401 INFO Epoch:30 val_res:0.557600 +2025-04-19 06:21:55,024 INFO Epoch:31 train_loss:0.62488 +2025-04-19 06:22:03,113 INFO Epoch:31 val_res:0.564800 +2025-04-19 06:22:18,246 INFO Epoch:32 train_loss:0.56745 +2025-04-19 06:22:26,830 INFO Epoch:32 val_res:0.558400 +2025-04-19 06:22:43,097 INFO Epoch:33 train_loss:0.57004 +2025-04-19 06:22:51,185 INFO Epoch:33 val_res:0.556400 +2025-04-19 06:23:07,656 INFO Epoch:34 train_loss:0.58274 +2025-04-19 06:23:16,119 INFO Epoch:34 val_res:0.558000 +2025-04-19 06:23:32,205 INFO Epoch:35 train_loss:0.54964 +2025-04-19 06:23:41,046 INFO Epoch:35 val_res:0.560000 +2025-04-19 06:23:57,061 INFO Epoch:36 train_loss:0.54960 +2025-04-19 06:24:05,767 INFO Epoch:36 val_res:0.558400 +2025-04-19 06:24:20,851 INFO Epoch:37 train_loss:0.54985 +2025-04-19 06:24:29,663 INFO Epoch:37 val_res:0.551200 +2025-04-19 06:24:44,474 INFO Epoch:38 train_loss:0.56619 +2025-04-19 06:24:53,229 INFO Epoch:38 val_res:0.549200 +2025-04-19 06:25:09,002 INFO Epoch:39 train_loss:0.53302 +2025-04-19 06:25:17,378 INFO Epoch:39 val_res:0.536800 +2025-04-19 06:25:32,663 INFO Epoch:40 train_loss:0.54347 +2025-04-19 06:25:41,139 INFO Epoch:40 val_res:0.540400 +2025-04-19 06:25:57,210 INFO Epoch:41 train_loss:0.52788 +2025-04-19 06:26:05,386 INFO Epoch:41 val_res:0.542400 +2025-04-19 06:26:21,051 INFO Epoch:42 train_loss:0.50665 +2025-04-19 06:26:29,913 INFO Epoch:42 val_res:0.546000 +2025-04-19 06:26:45,407 INFO Epoch:43 train_loss:0.48941 +2025-04-19 06:26:53,230 INFO Epoch:43 val_res:0.539600 +2025-04-19 06:27:08,780 INFO Epoch:44 train_loss:0.47584 +2025-04-19 06:27:17,180 INFO Epoch:44 val_res:0.540800 +2025-04-19 06:27:33,362 INFO Epoch:45 train_loss:0.49061 +2025-04-19 06:27:41,210 INFO Epoch:45 val_res:0.538800 +2025-04-19 06:27:56,751 INFO Epoch:46 train_loss:0.48496 +2025-04-19 06:28:04,973 INFO Epoch:46 val_res:0.539200 +2025-04-19 06:28:20,583 INFO Epoch:47 train_loss:0.48032 +2025-04-19 06:28:28,621 INFO Epoch:47 val_res:0.538400 +2025-04-19 06:28:44,561 INFO Epoch:48 train_loss:0.48529 +2025-04-19 06:28:53,108 INFO Epoch:48 val_res:0.538800 +2025-04-19 06:29:09,086 INFO Epoch:49 train_loss:0.47157 +2025-04-19 06:29:17,078 INFO Epoch:49 val_res:0.539600 +2025-04-19 06:29:33,565 INFO Epoch:50 train_loss:0.49330 +2025-04-19 06:29:42,087 INFO Epoch:50 val_res:0.536000 +2025-04-19 06:29:57,158 INFO Epoch:51 train_loss:0.47175 +2025-04-19 06:30:05,314 INFO Epoch:51 val_res:0.529600 +2025-04-19 06:30:21,208 INFO Epoch:52 train_loss:0.47450 +2025-04-19 06:30:29,750 INFO Epoch:52 val_res:0.520000 +2025-04-19 06:30:44,669 INFO Epoch:53 train_loss:0.44807 +2025-04-19 06:30:53,457 INFO Epoch:53 val_res:0.530400 +2025-04-19 06:31:09,757 INFO Epoch:54 train_loss:0.43633 +2025-04-19 06:31:18,307 INFO Epoch:54 val_res:0.531600 +2025-04-19 06:31:34,377 INFO Epoch:55 train_loss:0.42418 +2025-04-19 06:31:43,471 INFO Epoch:55 val_res:0.520800 +2025-04-19 06:31:59,408 INFO Epoch:56 train_loss:0.42650 +2025-04-19 06:32:07,160 INFO Epoch:56 val_res:0.524800 +2025-04-19 06:32:22,828 INFO Epoch:57 train_loss:0.42597 +2025-04-19 06:32:31,403 INFO Epoch:57 val_res:0.527600 +2025-04-19 06:32:47,614 INFO Epoch:58 train_loss:0.42069 +2025-04-19 06:32:55,566 INFO Epoch:58 val_res:0.519600 +2025-04-19 06:33:11,722 INFO Epoch:59 train_loss:0.42775 +2025-04-19 06:33:20,253 INFO Epoch:59 val_res:0.526400 +2025-04-19 06:33:35,401 INFO Epoch:60 train_loss:0.44617 +2025-04-19 06:33:43,543 INFO Epoch:60 val_res:0.518800 +2025-04-19 06:34:00,059 INFO Epoch:61 train_loss:0.42089 +2025-04-19 06:34:08,449 INFO Epoch:61 val_res:0.528000 +2025-04-19 06:34:24,203 INFO Epoch:62 train_loss:0.44307 +2025-04-19 06:34:32,723 INFO Epoch:62 val_res:0.522000 +2025-04-19 06:34:49,115 INFO Epoch:63 train_loss:0.41940 +2025-04-19 06:34:57,246 INFO Epoch:63 val_res:0.518000 +2025-04-19 06:35:13,656 INFO Epoch:64 train_loss:0.39525 +2025-04-19 06:35:22,299 INFO Epoch:64 val_res:0.531200 +2025-04-19 06:35:38,056 INFO Epoch:65 train_loss:0.42112 +2025-04-19 06:35:46,452 INFO Epoch:65 val_res:0.513200 +2025-04-19 06:36:02,169 INFO Epoch:66 train_loss:0.42250 +2025-04-19 06:36:10,956 INFO Epoch:66 val_res:0.516000 +2025-04-19 06:36:26,692 INFO Epoch:67 train_loss:0.38777 +2025-04-19 06:36:35,544 INFO Epoch:67 val_res:0.515200 +2025-04-19 06:36:50,763 INFO Epoch:68 train_loss:0.37862 +2025-04-19 06:36:59,099 INFO Epoch:68 val_res:0.519600 +2025-04-19 06:37:14,731 INFO Epoch:69 train_loss:0.42030 +2025-04-19 06:37:23,071 INFO Epoch:69 val_res:0.520400 +2025-04-19 06:37:38,861 INFO Epoch:70 train_loss:0.41812 +2025-04-19 06:37:47,180 INFO Epoch:70 val_res:0.517600 +2025-04-19 06:38:02,499 INFO Epoch:71 train_loss:0.44363 +2025-04-19 06:38:10,214 INFO Epoch:71 val_res:0.516400 +2025-04-19 06:38:24,517 INFO Epoch:72 train_loss:0.43600 +2025-04-19 06:38:32,612 INFO Epoch:72 val_res:0.512000 +2025-04-19 06:38:46,815 INFO Epoch:73 train_loss:0.40454 +2025-04-19 06:38:54,097 INFO Epoch:73 val_res:0.517600 +2025-04-19 06:39:08,884 INFO Epoch:74 train_loss:0.42913 +2025-04-19 06:39:16,905 INFO Epoch:74 val_res:0.515200 +2025-04-19 06:39:31,202 INFO Epoch:75 train_loss:0.43155 +2025-04-19 06:39:40,102 INFO Epoch:75 val_res:0.513600 +2025-04-19 06:39:55,284 INFO Epoch:76 train_loss:0.40390 +2025-04-19 06:40:04,221 INFO Epoch:76 val_res:0.512800 +2025-04-19 06:40:20,369 INFO Epoch:77 train_loss:0.37608 +2025-04-19 06:40:29,279 INFO Epoch:77 val_res:0.502400 +2025-04-19 06:40:46,790 INFO Epoch:78 train_loss:0.39784 +2025-04-19 06:40:56,110 INFO Epoch:78 val_res:0.504400 +2025-04-19 06:41:13,298 INFO Epoch:79 train_loss:0.41897 +2025-04-19 06:41:23,538 INFO Epoch:79 val_res:0.502400 +2025-04-19 06:41:41,062 INFO Epoch:80 train_loss:0.39532 +2025-04-19 06:41:50,787 INFO Epoch:80 val_res:0.510800 +2025-04-19 06:42:07,862 INFO Epoch:81 train_loss:0.39662 +2025-04-19 06:42:17,979 INFO Epoch:81 val_res:0.505600 +2025-04-19 06:42:34,514 INFO Epoch:82 train_loss:0.35744 +2025-04-19 06:42:44,427 INFO Epoch:82 val_res:0.498400 +2025-04-19 06:43:02,449 INFO Epoch:83 train_loss:0.37070 +2025-04-19 06:43:12,354 INFO Epoch:83 val_res:0.502800 +2025-04-19 06:43:29,100 INFO Epoch:84 train_loss:0.37912 +2025-04-19 06:43:39,534 INFO Epoch:84 val_res:0.498800 +2025-04-19 06:43:56,862 INFO Epoch:85 train_loss:0.35631 +2025-04-19 06:44:06,208 INFO Epoch:85 val_res:0.508800 +2025-04-19 06:44:24,306 INFO Epoch:86 train_loss:0.33159 +2025-04-19 06:44:35,177 INFO Epoch:86 val_res:0.508000 +2025-04-19 06:44:52,273 INFO Epoch:87 train_loss:0.34102 +2025-04-19 06:45:02,034 INFO Epoch:87 val_res:0.506400 +2025-04-19 06:45:20,461 INFO Epoch:88 train_loss:0.32428 +2025-04-19 06:45:30,717 INFO Epoch:88 val_res:0.496400 +2025-04-19 06:45:47,833 INFO Epoch:89 train_loss:0.34193 +2025-04-19 06:45:58,381 INFO Epoch:89 val_res:0.498800 +2025-04-19 06:46:15,868 INFO Epoch:90 train_loss:0.33266 +2025-04-19 06:46:25,706 INFO Epoch:90 val_res:0.488800 +2025-04-19 06:46:43,399 INFO Epoch:91 train_loss:0.34666 +2025-04-19 06:46:53,964 INFO Epoch:91 val_res:0.498000 +2025-04-19 06:47:11,582 INFO Epoch:92 train_loss:0.37018 +2025-04-19 06:47:21,149 INFO Epoch:92 val_res:0.498400 +2025-04-19 06:47:39,520 INFO Epoch:93 train_loss:0.34260 +2025-04-19 06:47:49,766 INFO Epoch:93 val_res:0.502800 +2025-04-19 06:48:07,131 INFO Epoch:94 train_loss:0.36284 +2025-04-19 06:48:17,645 INFO Epoch:94 val_res:0.504800 +2025-04-19 06:48:36,262 INFO Epoch:95 train_loss:0.34825 +2025-04-19 06:48:46,144 INFO Epoch:95 val_res:0.495600 +2025-04-19 06:49:03,402 INFO Epoch:96 train_loss:0.36211 +2025-04-19 06:49:13,993 INFO Epoch:96 val_res:0.492400 +2025-04-19 06:49:31,814 INFO Epoch:97 train_loss:0.36533 +2025-04-19 06:49:41,449 INFO Epoch:97 val_res:0.493600 +2025-04-19 06:50:00,303 INFO Epoch:98 train_loss:0.34999 +2025-04-19 06:50:10,165 INFO Epoch:98 val_res:0.500000 +2025-04-19 06:50:28,125 INFO Epoch:99 train_loss:0.35826 +2025-04-19 06:50:37,940 INFO Epoch:99 val_res:0.487200 +2025-04-19 06:50:38,699 INFO ===================================== +2025-04-19 06:50:38,700 INFO Start testing... +2025-04-19 06:50:38,700 INFO ===================================== +2025-04-19 06:50:47,848 INFO Incremental step 4 Testing res: 0.587600 +2025-04-19 06:50:47,852 INFO forgetting: 0.133000 +2025-04-19 06:50:47,856 INFO Incremental step: 5 +2025-04-19 06:51:04,954 INFO Epoch:0 train_loss:6.69203 +2025-04-19 06:51:15,382 INFO Epoch:0 val_res:0.476000 +2025-04-19 06:51:15,383 INFO Saving best model at Epoch 0 +2025-04-19 06:51:33,886 INFO Epoch:1 train_loss:2.56735 +2025-04-19 06:51:43,942 INFO Epoch:1 val_res:0.486333 +2025-04-19 06:51:43,942 INFO Saving best model at Epoch 1 +2025-04-19 06:52:01,091 INFO Epoch:2 train_loss:1.81263 +2025-04-19 06:52:11,973 INFO Epoch:2 val_res:0.490667 +2025-04-19 06:52:11,973 INFO Saving best model at Epoch 2 +2025-04-19 06:52:29,261 INFO Epoch:3 train_loss:1.53572 +2025-04-19 06:52:39,465 INFO Epoch:3 val_res:0.490667 +2025-04-19 06:52:55,181 INFO Epoch:4 train_loss:1.39690 +2025-04-19 06:53:05,914 INFO Epoch:4 val_res:0.495667 +2025-04-19 06:53:05,915 INFO Saving best model at Epoch 4 +2025-04-19 06:53:23,481 INFO Epoch:5 train_loss:1.29591 +2025-04-19 06:53:34,586 INFO Epoch:5 val_res:0.498333 +2025-04-19 06:53:34,586 INFO Saving best model at Epoch 5 +2025-04-19 06:53:52,643 INFO Epoch:6 train_loss:1.21446 +2025-04-19 06:54:03,849 INFO Epoch:6 val_res:0.505000 +2025-04-19 06:54:03,849 INFO Saving best model at Epoch 6 +2025-04-19 06:54:20,638 INFO Epoch:7 train_loss:1.14632 +2025-04-19 06:54:32,337 INFO Epoch:7 val_res:0.507667 +2025-04-19 06:54:32,337 INFO Saving best model at Epoch 7 +2025-04-19 06:54:49,692 INFO Epoch:8 train_loss:1.09187 +2025-04-19 06:55:00,778 INFO Epoch:8 val_res:0.514667 +2025-04-19 06:55:00,778 INFO Saving best model at Epoch 8 +2025-04-19 06:55:17,802 INFO Epoch:9 train_loss:1.04481 +2025-04-19 06:55:28,764 INFO Epoch:9 val_res:0.519667 +2025-04-19 06:55:28,764 INFO Saving best model at Epoch 9 +2025-04-19 06:55:45,838 INFO Epoch:10 train_loss:1.00058 +2025-04-19 06:55:56,515 INFO Epoch:10 val_res:0.521667 +2025-04-19 06:55:56,516 INFO Saving best model at Epoch 10 +2025-04-19 06:56:13,785 INFO Epoch:11 train_loss:0.94715 +2025-04-19 06:56:24,967 INFO Epoch:11 val_res:0.525000 +2025-04-19 06:56:24,967 INFO Saving best model at Epoch 11 +2025-04-19 06:56:43,146 INFO Epoch:12 train_loss:0.90877 +2025-04-19 06:56:54,012 INFO Epoch:12 val_res:0.527000 +2025-04-19 06:56:54,013 INFO Saving best model at Epoch 12 +2025-04-19 06:57:13,662 INFO Epoch:13 train_loss:0.87309 +2025-04-19 06:57:24,863 INFO Epoch:13 val_res:0.527333 +2025-04-19 06:57:24,864 INFO Saving best model at Epoch 13 +2025-04-19 06:57:41,839 INFO Epoch:14 train_loss:0.83092 +2025-04-19 06:57:53,206 INFO Epoch:14 val_res:0.529000 +2025-04-19 06:57:53,207 INFO Saving best model at Epoch 14 +2025-04-19 06:58:11,219 INFO Epoch:15 train_loss:0.81038 +2025-04-19 06:58:21,961 INFO Epoch:15 val_res:0.526333 +2025-04-19 06:58:38,200 INFO Epoch:16 train_loss:0.78376 +2025-04-19 06:58:49,232 INFO Epoch:16 val_res:0.530333 +2025-04-19 06:58:49,233 INFO Saving best model at Epoch 16 +2025-04-19 06:59:07,385 INFO Epoch:17 train_loss:0.73829 +2025-04-19 06:59:18,292 INFO Epoch:17 val_res:0.530667 +2025-04-19 06:59:18,293 INFO Saving best model at Epoch 17 +2025-04-19 06:59:36,047 INFO Epoch:18 train_loss:0.70472 +2025-04-19 06:59:46,838 INFO Epoch:18 val_res:0.526333 +2025-04-19 07:00:04,105 INFO Epoch:19 train_loss:0.70488 +2025-04-19 07:00:14,564 INFO Epoch:19 val_res:0.527667 +2025-04-19 07:00:30,298 INFO Epoch:20 train_loss:0.68384 +2025-04-19 07:00:41,127 INFO Epoch:20 val_res:0.527667 +2025-04-19 07:00:57,238 INFO Epoch:21 train_loss:0.64337 +2025-04-19 07:01:07,954 INFO Epoch:21 val_res:0.528667 +2025-04-19 07:01:24,418 INFO Epoch:22 train_loss:0.62019 +2025-04-19 07:01:35,601 INFO Epoch:22 val_res:0.518000 +2025-04-19 07:01:51,684 INFO Epoch:23 train_loss:0.63722 +2025-04-19 07:02:03,184 INFO Epoch:23 val_res:0.521000 +2025-04-19 07:02:19,545 INFO Epoch:24 train_loss:0.59705 +2025-04-19 07:02:31,084 INFO Epoch:24 val_res:0.518667 +2025-04-19 07:02:47,660 INFO Epoch:25 train_loss:0.55359 +2025-04-19 07:02:59,169 INFO Epoch:25 val_res:0.510333 +2025-04-19 07:03:15,176 INFO Epoch:26 train_loss:0.54250 +2025-04-19 07:03:26,269 INFO Epoch:26 val_res:0.514667 +2025-04-19 07:03:42,812 INFO Epoch:27 train_loss:0.53525 +2025-04-19 07:03:53,647 INFO Epoch:27 val_res:0.502000 +2025-04-19 07:04:09,172 INFO Epoch:28 train_loss:0.51817 +2025-04-19 07:04:20,821 INFO Epoch:28 val_res:0.508667 +2025-04-19 07:04:36,697 INFO Epoch:29 train_loss:0.50646 +2025-04-19 07:04:47,847 INFO Epoch:29 val_res:0.495000 +2025-04-19 07:05:04,383 INFO Epoch:30 train_loss:0.49923 +2025-04-19 07:05:15,367 INFO Epoch:30 val_res:0.502000 +2025-04-19 07:05:31,529 INFO Epoch:31 train_loss:0.50197 +2025-04-19 07:05:43,026 INFO Epoch:31 val_res:0.498667 +2025-04-19 07:05:59,366 INFO Epoch:32 train_loss:0.46288 +2025-04-19 07:06:10,151 INFO Epoch:32 val_res:0.492000 +2025-04-19 07:06:26,492 INFO Epoch:33 train_loss:0.46728 +2025-04-19 07:06:37,186 INFO Epoch:33 val_res:0.496667 +2025-04-19 07:06:53,954 INFO Epoch:34 train_loss:0.45158 +2025-04-19 07:07:04,741 INFO Epoch:34 val_res:0.492000 +2025-04-19 07:07:21,615 INFO Epoch:35 train_loss:0.45207 +2025-04-19 07:07:32,907 INFO Epoch:35 val_res:0.487667 +2025-04-19 07:07:48,713 INFO Epoch:36 train_loss:0.44019 +2025-04-19 07:08:00,650 INFO Epoch:36 val_res:0.483000 +2025-04-19 07:08:16,279 INFO Epoch:37 train_loss:0.45374 +2025-04-19 07:08:27,660 INFO Epoch:37 val_res:0.490000 +2025-04-19 07:08:44,526 INFO Epoch:38 train_loss:0.42796 +2025-04-19 07:08:56,352 INFO Epoch:38 val_res:0.484000 +2025-04-19 07:09:12,309 INFO Epoch:39 train_loss:0.40490 +2025-04-19 07:09:24,179 INFO Epoch:39 val_res:0.484667 +2025-04-19 07:09:41,157 INFO Epoch:40 train_loss:0.39828 +2025-04-19 07:09:52,192 INFO Epoch:40 val_res:0.479667 +2025-04-19 07:10:08,918 INFO Epoch:41 train_loss:0.40667 +2025-04-19 07:10:20,995 INFO Epoch:41 val_res:0.483000 +2025-04-19 07:10:36,875 INFO Epoch:42 train_loss:0.39374 +2025-04-19 07:10:48,235 INFO Epoch:42 val_res:0.473667 +2025-04-19 07:11:05,582 INFO Epoch:43 train_loss:0.37594 +2025-04-19 07:11:17,320 INFO Epoch:43 val_res:0.473667 +2025-04-19 07:11:33,776 INFO Epoch:44 train_loss:0.36934 +2025-04-19 07:11:45,272 INFO Epoch:44 val_res:0.476667 +2025-04-19 07:12:02,451 INFO Epoch:45 train_loss:0.43996 +2025-04-19 07:12:13,063 INFO Epoch:45 val_res:0.463667 +2025-04-19 07:12:30,200 INFO Epoch:46 train_loss:0.46934 +2025-04-19 07:12:41,690 INFO Epoch:46 val_res:0.467000 +2025-04-19 07:12:58,085 INFO Epoch:47 train_loss:0.36988 +2025-04-19 07:13:09,564 INFO Epoch:47 val_res:0.467000 +2025-04-19 07:13:26,374 INFO Epoch:48 train_loss:0.36592 +2025-04-19 07:13:38,396 INFO Epoch:48 val_res:0.469667 +2025-04-19 07:13:54,075 INFO Epoch:49 train_loss:0.38520 +2025-04-19 07:14:05,979 INFO Epoch:49 val_res:0.462667 +2025-04-19 07:14:21,797 INFO Epoch:50 train_loss:0.35937 +2025-04-19 07:14:32,918 INFO Epoch:50 val_res:0.463000 +2025-04-19 07:14:50,236 INFO Epoch:51 train_loss:0.34877 +2025-04-19 07:15:01,223 INFO Epoch:51 val_res:0.462667 +2025-04-19 07:15:17,422 INFO Epoch:52 train_loss:0.33137 +2025-04-19 07:15:28,792 INFO Epoch:52 val_res:0.460000 +2025-04-19 07:15:44,842 INFO Epoch:53 train_loss:0.33191 +2025-04-19 07:15:55,466 INFO Epoch:53 val_res:0.459000 +2025-04-19 07:16:11,934 INFO Epoch:54 train_loss:0.32662 +2025-04-19 07:16:23,161 INFO Epoch:54 val_res:0.453333 +2025-04-19 07:16:38,481 INFO Epoch:55 train_loss:0.34569 +2025-04-19 07:16:49,739 INFO Epoch:55 val_res:0.454333 +2025-04-19 07:17:06,571 INFO Epoch:56 train_loss:0.31769 +2025-04-19 07:17:17,455 INFO Epoch:56 val_res:0.455000 +2025-04-19 07:17:34,126 INFO Epoch:57 train_loss:0.31182 +2025-04-19 07:17:45,424 INFO Epoch:57 val_res:0.455000 +2025-04-19 07:18:01,479 INFO Epoch:58 train_loss:0.33348 +2025-04-19 07:18:12,281 INFO Epoch:58 val_res:0.455000 +2025-04-19 07:18:29,039 INFO Epoch:59 train_loss:0.34913 +2025-04-19 07:18:40,055 INFO Epoch:59 val_res:0.449000 +2025-04-19 07:18:56,517 INFO Epoch:60 train_loss:0.35419 +2025-04-19 07:19:08,265 INFO Epoch:60 val_res:0.455333 +2025-04-19 07:19:24,442 INFO Epoch:61 train_loss:0.33239 +2025-04-19 07:19:35,786 INFO Epoch:61 val_res:0.448333 +2025-04-19 07:19:52,227 INFO Epoch:62 train_loss:0.35265 +2025-04-19 07:20:04,266 INFO Epoch:62 val_res:0.451000 +2025-04-19 07:20:20,235 INFO Epoch:63 train_loss:0.33030 +2025-04-19 07:20:31,628 INFO Epoch:63 val_res:0.450667 +2025-04-19 07:20:48,896 INFO Epoch:64 train_loss:0.31819 +2025-04-19 07:21:00,025 INFO Epoch:64 val_res:0.444000 +2025-04-19 07:21:16,959 INFO Epoch:65 train_loss:0.31001 +2025-04-19 07:21:28,298 INFO Epoch:65 val_res:0.443333 +2025-04-19 07:21:44,466 INFO Epoch:66 train_loss:0.31883 +2025-04-19 07:21:55,762 INFO Epoch:66 val_res:0.452667 +2025-04-19 07:22:10,699 INFO Epoch:67 train_loss:0.29912 +2025-04-19 07:22:19,878 INFO Epoch:67 val_res:0.448667 +2025-04-19 07:22:34,691 INFO Epoch:68 train_loss:0.29182 +2025-04-19 07:22:43,697 INFO Epoch:68 val_res:0.440667 +2025-04-19 07:22:58,341 INFO Epoch:69 train_loss:0.29231 +2025-04-19 07:23:09,181 INFO Epoch:69 val_res:0.448000 +2025-04-19 07:23:23,747 INFO Epoch:70 train_loss:0.30840 +2025-04-19 07:23:32,990 INFO Epoch:70 val_res:0.444667 +2025-04-19 07:23:47,926 INFO Epoch:71 train_loss:0.28453 +2025-04-19 07:23:57,574 INFO Epoch:71 val_res:0.442667 +2025-04-19 07:24:11,397 INFO Epoch:72 train_loss:0.28730 +2025-04-19 07:24:20,716 INFO Epoch:72 val_res:0.446333 +2025-04-19 07:24:35,216 INFO Epoch:73 train_loss:0.28057 +2025-04-19 07:24:44,753 INFO Epoch:73 val_res:0.444000 +2025-04-19 07:24:58,925 INFO Epoch:74 train_loss:0.27589 +2025-04-19 07:25:09,051 INFO Epoch:74 val_res:0.439667 +2025-04-19 07:25:24,002 INFO Epoch:75 train_loss:0.30916 +2025-04-19 07:25:33,424 INFO Epoch:75 val_res:0.442333 +2025-04-19 07:25:50,224 INFO Epoch:76 train_loss:0.27696 +2025-04-19 07:26:00,518 INFO Epoch:76 val_res:0.442667 +2025-04-19 07:26:17,111 INFO Epoch:77 train_loss:0.28698 +2025-04-19 07:26:28,380 INFO Epoch:77 val_res:0.436667 +2025-04-19 07:26:45,885 INFO Epoch:78 train_loss:0.31382 +2025-04-19 07:26:58,003 INFO Epoch:78 val_res:0.438000 +2025-04-19 07:27:15,196 INFO Epoch:79 train_loss:0.30692 +2025-04-19 07:27:27,408 INFO Epoch:79 val_res:0.441000 +2025-04-19 07:27:44,656 INFO Epoch:80 train_loss:0.28766 +2025-04-19 07:27:56,672 INFO Epoch:80 val_res:0.440000 +2025-04-19 07:28:14,611 INFO Epoch:81 train_loss:0.28690 +2025-04-19 07:28:27,101 INFO Epoch:81 val_res:0.436667 +2025-04-19 07:28:43,985 INFO Epoch:82 train_loss:0.30742 +2025-04-19 07:28:56,925 INFO Epoch:82 val_res:0.441333 +2025-04-19 07:29:15,310 INFO Epoch:83 train_loss:0.26891 +2025-04-19 07:29:27,455 INFO Epoch:83 val_res:0.436000 +2025-04-19 07:29:46,086 INFO Epoch:84 train_loss:0.24114 +2025-04-19 07:29:58,464 INFO Epoch:84 val_res:0.437000 +2025-04-19 07:30:16,266 INFO Epoch:85 train_loss:0.22873 +2025-04-19 07:30:28,985 INFO Epoch:85 val_res:0.438667 +2025-04-19 07:30:47,181 INFO Epoch:86 train_loss:0.22881 +2025-04-19 07:30:59,016 INFO Epoch:86 val_res:0.435333 +2025-04-19 07:31:17,732 INFO Epoch:87 train_loss:0.24759 +2025-04-19 07:31:30,344 INFO Epoch:87 val_res:0.441000 +2025-04-19 07:31:48,215 INFO Epoch:88 train_loss:0.24562 +2025-04-19 07:32:00,900 INFO Epoch:88 val_res:0.438000 +2025-04-19 07:32:19,302 INFO Epoch:89 train_loss:0.24489 +2025-04-19 07:32:31,999 INFO Epoch:89 val_res:0.437333 +2025-04-19 07:32:50,131 INFO Epoch:90 train_loss:0.31254 +2025-04-19 07:33:03,358 INFO Epoch:90 val_res:0.431333 +2025-04-19 07:33:20,756 INFO Epoch:91 train_loss:0.27550 +2025-04-19 07:33:33,375 INFO Epoch:91 val_res:0.438000 +2025-04-19 07:33:51,349 INFO Epoch:92 train_loss:0.27899 +2025-04-19 07:34:02,957 INFO Epoch:92 val_res:0.432000 +2025-04-19 07:34:19,754 INFO Epoch:93 train_loss:0.25441 +2025-04-19 07:34:31,908 INFO Epoch:93 val_res:0.430000 +2025-04-19 07:34:49,068 INFO Epoch:94 train_loss:0.25104 +2025-04-19 07:35:00,659 INFO Epoch:94 val_res:0.434333 +2025-04-19 07:35:18,034 INFO Epoch:95 train_loss:0.24792 +2025-04-19 07:35:29,718 INFO Epoch:95 val_res:0.433667 +2025-04-19 07:35:45,994 INFO Epoch:96 train_loss:0.24488 +2025-04-19 07:35:58,161 INFO Epoch:96 val_res:0.435333 +2025-04-19 07:36:15,486 INFO Epoch:97 train_loss:0.30367 +2025-04-19 07:36:27,426 INFO Epoch:97 val_res:0.428667 +2025-04-19 07:36:44,041 INFO Epoch:98 train_loss:0.26957 +2025-04-19 07:36:55,920 INFO Epoch:98 val_res:0.433000 +2025-04-19 07:37:12,951 INFO Epoch:99 train_loss:0.27282 +2025-04-19 07:37:25,329 INFO Epoch:99 val_res:0.435667 +2025-04-19 07:37:26,002 INFO ===================================== +2025-04-19 07:37:26,003 INFO Start testing... +2025-04-19 07:37:26,003 INFO ===================================== +2025-04-19 07:37:37,467 INFO Incremental step 5 Testing res: 0.536000 +2025-04-19 07:37:37,470 INFO forgetting: 0.156400 +2025-04-19 07:37:37,472 INFO Incremental step: 6 +2025-04-19 07:37:55,983 INFO Epoch:0 train_loss:5.57393 +2025-04-19 07:38:09,775 INFO Epoch:0 val_res:0.454000 +2025-04-19 07:38:09,776 INFO Saving best model at Epoch 0 +2025-04-19 07:38:29,719 INFO Epoch:1 train_loss:1.88929 +2025-04-19 07:38:42,608 INFO Epoch:1 val_res:0.460571 +2025-04-19 07:38:42,609 INFO Saving best model at Epoch 1 +2025-04-19 07:39:03,170 INFO Epoch:2 train_loss:1.30915 +2025-04-19 07:39:16,749 INFO Epoch:2 val_res:0.466286 +2025-04-19 07:39:16,750 INFO Saving best model at Epoch 2 +2025-04-19 07:39:35,537 INFO Epoch:3 train_loss:1.11421 +2025-04-19 07:39:50,034 INFO Epoch:3 val_res:0.466286 +2025-04-19 07:40:08,133 INFO Epoch:4 train_loss:1.00719 +2025-04-19 07:40:22,332 INFO Epoch:4 val_res:0.474571 +2025-04-19 07:40:22,332 INFO Saving best model at Epoch 4 +2025-04-19 07:40:42,341 INFO Epoch:5 train_loss:0.94009 +2025-04-19 07:40:55,843 INFO Epoch:5 val_res:0.479714 +2025-04-19 07:40:55,844 INFO Saving best model at Epoch 5 +2025-04-19 07:41:15,988 INFO Epoch:6 train_loss:0.88074 +2025-04-19 07:41:29,372 INFO Epoch:6 val_res:0.483429 +2025-04-19 07:41:29,373 INFO Saving best model at Epoch 6 +2025-04-19 07:41:49,001 INFO Epoch:7 train_loss:0.83627 +2025-04-19 07:42:02,324 INFO Epoch:7 val_res:0.492286 +2025-04-19 07:42:02,331 INFO Saving best model at Epoch 7 +2025-04-19 07:42:22,596 INFO Epoch:8 train_loss:0.79173 +2025-04-19 07:42:36,457 INFO Epoch:8 val_res:0.494857 +2025-04-19 07:42:36,457 INFO Saving best model at Epoch 8 +2025-04-19 07:42:56,376 INFO Epoch:9 train_loss:0.76892 +2025-04-19 07:43:10,519 INFO Epoch:9 val_res:0.498000 +2025-04-19 07:43:10,519 INFO Saving best model at Epoch 9 +2025-04-19 07:43:30,062 INFO Epoch:10 train_loss:0.73036 +2025-04-19 07:43:44,691 INFO Epoch:10 val_res:0.502857 +2025-04-19 07:43:44,692 INFO Saving best model at Epoch 10 +2025-04-19 07:44:04,857 INFO Epoch:11 train_loss:0.71818 +2025-04-19 07:44:19,043 INFO Epoch:11 val_res:0.508286 +2025-04-19 07:44:19,043 INFO Saving best model at Epoch 11 +2025-04-19 07:44:39,189 INFO Epoch:12 train_loss:0.70807 +2025-04-19 07:44:52,986 INFO Epoch:12 val_res:0.503429 +2025-04-19 07:45:10,715 INFO Epoch:13 train_loss:0.69833 +2025-04-19 07:45:24,524 INFO Epoch:13 val_res:0.507143 +2025-04-19 07:45:40,156 INFO Epoch:14 train_loss:0.65129 +2025-04-19 07:45:51,655 INFO Epoch:14 val_res:0.506000 +2025-04-19 07:46:07,172 INFO Epoch:15 train_loss:0.63660 +2025-04-19 07:46:19,283 INFO Epoch:15 val_res:0.508286 +2025-04-19 07:46:34,571 INFO Epoch:16 train_loss:0.58992 +2025-04-19 07:46:45,937 INFO Epoch:16 val_res:0.509143 +2025-04-19 07:46:45,937 INFO Saving best model at Epoch 16 +2025-04-19 07:47:03,206 INFO Epoch:17 train_loss:0.57973 +2025-04-19 07:47:14,562 INFO Epoch:17 val_res:0.508571 +2025-04-19 07:47:28,793 INFO Epoch:18 train_loss:0.54084 +2025-04-19 07:47:40,424 INFO Epoch:18 val_res:0.510000 +2025-04-19 07:47:40,424 INFO Saving best model at Epoch 18 +2025-04-19 07:47:57,090 INFO Epoch:19 train_loss:0.54749 +2025-04-19 07:48:08,055 INFO Epoch:19 val_res:0.505143 +2025-04-19 07:48:23,739 INFO Epoch:20 train_loss:0.54356 +2025-04-19 07:48:35,364 INFO Epoch:20 val_res:0.508000 +2025-04-19 07:48:49,893 INFO Epoch:21 train_loss:0.50713 +2025-04-19 07:49:01,472 INFO Epoch:21 val_res:0.505714 +2025-04-19 07:49:16,871 INFO Epoch:22 train_loss:0.50264 +2025-04-19 07:49:27,933 INFO Epoch:22 val_res:0.504571 +2025-04-19 07:49:42,941 INFO Epoch:23 train_loss:0.47708 +2025-04-19 07:49:54,430 INFO Epoch:23 val_res:0.499143 +2025-04-19 07:50:09,130 INFO Epoch:24 train_loss:0.46463 +2025-04-19 07:50:20,393 INFO Epoch:24 val_res:0.501143 +2025-04-19 07:50:35,658 INFO Epoch:25 train_loss:0.46374 +2025-04-19 07:50:47,216 INFO Epoch:25 val_res:0.492571 +2025-04-19 07:51:01,945 INFO Epoch:26 train_loss:0.46749 +2025-04-19 07:51:13,753 INFO Epoch:26 val_res:0.492286 +2025-04-19 07:51:28,660 INFO Epoch:27 train_loss:0.43887 +2025-04-19 07:51:40,325 INFO Epoch:27 val_res:0.496286 +2025-04-19 07:51:55,303 INFO Epoch:28 train_loss:0.41277 +2025-04-19 07:52:06,734 INFO Epoch:28 val_res:0.492000 +2025-04-19 07:52:21,168 INFO Epoch:29 train_loss:0.41532 +2025-04-19 07:52:32,740 INFO Epoch:29 val_res:0.489714 +2025-04-19 07:52:47,589 INFO Epoch:30 train_loss:0.40114 +2025-04-19 07:52:59,216 INFO Epoch:30 val_res:0.485143 +2025-04-19 07:53:14,172 INFO Epoch:31 train_loss:0.39408 +2025-04-19 07:53:25,740 INFO Epoch:31 val_res:0.486571 +2025-04-19 07:53:40,156 INFO Epoch:32 train_loss:0.41663 +2025-04-19 07:53:51,752 INFO Epoch:32 val_res:0.484286 +2025-04-19 07:54:06,537 INFO Epoch:33 train_loss:0.39441 +2025-04-19 07:54:18,033 INFO Epoch:33 val_res:0.481143 +2025-04-19 07:54:32,956 INFO Epoch:34 train_loss:0.36953 +2025-04-19 07:54:44,373 INFO Epoch:34 val_res:0.482286 +2025-04-19 07:54:59,060 INFO Epoch:35 train_loss:0.33996 +2025-04-19 07:55:10,619 INFO Epoch:35 val_res:0.483429 +2025-04-19 07:55:25,382 INFO Epoch:36 train_loss:0.34824 +2025-04-19 07:55:36,470 INFO Epoch:36 val_res:0.478857 +2025-04-19 07:55:51,650 INFO Epoch:37 train_loss:0.35601 +2025-04-19 07:56:03,085 INFO Epoch:37 val_res:0.479429 +2025-04-19 07:56:17,821 INFO Epoch:38 train_loss:0.37515 +2025-04-19 07:56:30,194 INFO Epoch:38 val_res:0.472286 +2025-04-19 07:56:45,486 INFO Epoch:39 train_loss:0.37851 +2025-04-19 07:56:56,504 INFO Epoch:39 val_res:0.469429 +2025-04-19 07:57:11,669 INFO Epoch:40 train_loss:0.37977 +2025-04-19 07:57:23,341 INFO Epoch:40 val_res:0.471143 +2025-04-19 07:57:38,045 INFO Epoch:41 train_loss:0.34212 +2025-04-19 07:57:49,131 INFO Epoch:41 val_res:0.463429 +2025-04-19 07:58:04,929 INFO Epoch:42 train_loss:0.30730 +2025-04-19 07:58:16,036 INFO Epoch:42 val_res:0.463429 +2025-04-19 07:58:30,398 INFO Epoch:43 train_loss:0.32424 +2025-04-19 07:58:42,026 INFO Epoch:43 val_res:0.463143 +2025-04-19 07:58:57,314 INFO Epoch:44 train_loss:0.35343 +2025-04-19 07:59:08,412 INFO Epoch:44 val_res:0.453429 +2025-04-19 07:59:23,543 INFO Epoch:45 train_loss:0.32501 +2025-04-19 07:59:35,430 INFO Epoch:45 val_res:0.452000 +2025-04-19 07:59:49,973 INFO Epoch:46 train_loss:0.30478 +2025-04-19 08:00:01,608 INFO Epoch:46 val_res:0.451429 +2025-04-19 08:00:16,719 INFO Epoch:47 train_loss:0.33040 +2025-04-19 08:00:27,901 INFO Epoch:47 val_res:0.452857 +2025-04-19 08:00:42,653 INFO Epoch:48 train_loss:0.30033 +2025-04-19 08:00:54,692 INFO Epoch:48 val_res:0.447714 +2025-04-19 08:01:08,994 INFO Epoch:49 train_loss:0.28459 +2025-04-19 08:01:20,021 INFO Epoch:49 val_res:0.446857 +2025-04-19 08:01:35,468 INFO Epoch:50 train_loss:0.28473 +2025-04-19 08:01:46,195 INFO Epoch:50 val_res:0.442286 +2025-04-19 08:02:00,833 INFO Epoch:51 train_loss:0.30414 +2025-04-19 08:02:12,502 INFO Epoch:51 val_res:0.438571 +2025-04-19 08:02:27,238 INFO Epoch:52 train_loss:0.33736 +2025-04-19 08:02:38,249 INFO Epoch:52 val_res:0.443714 +2025-04-19 08:02:53,826 INFO Epoch:53 train_loss:0.30657 +2025-04-19 08:03:05,387 INFO Epoch:53 val_res:0.445429 +2025-04-19 08:03:20,155 INFO Epoch:54 train_loss:0.29695 +2025-04-19 08:03:31,599 INFO Epoch:54 val_res:0.447429 +2025-04-19 08:03:47,100 INFO Epoch:55 train_loss:0.31012 +2025-04-19 08:03:58,643 INFO Epoch:55 val_res:0.434857 +2025-04-19 08:04:13,181 INFO Epoch:56 train_loss:0.32681 +2025-04-19 08:04:24,951 INFO Epoch:56 val_res:0.433714 +2025-04-19 08:04:39,799 INFO Epoch:57 train_loss:0.29993 +2025-04-19 08:04:51,409 INFO Epoch:57 val_res:0.439429 +2025-04-19 08:05:06,813 INFO Epoch:58 train_loss:0.26276 +2025-04-19 08:05:17,858 INFO Epoch:58 val_res:0.435429 +2025-04-19 08:05:32,547 INFO Epoch:59 train_loss:0.28183 +2025-04-19 08:05:44,686 INFO Epoch:59 val_res:0.432286 +2025-04-19 08:05:59,498 INFO Epoch:60 train_loss:0.30488 +2025-04-19 08:06:10,722 INFO Epoch:60 val_res:0.434571 +2025-04-19 08:06:26,192 INFO Epoch:61 train_loss:0.28345 +2025-04-19 08:06:37,912 INFO Epoch:61 val_res:0.427714 +2025-04-19 08:06:52,251 INFO Epoch:62 train_loss:0.28862 +2025-04-19 08:07:03,748 INFO Epoch:62 val_res:0.429429 +2025-04-19 08:07:19,132 INFO Epoch:63 train_loss:0.26948 +2025-04-19 08:07:30,048 INFO Epoch:63 val_res:0.432571 +2025-04-19 08:07:44,996 INFO Epoch:64 train_loss:0.26884 +2025-04-19 08:07:56,499 INFO Epoch:64 val_res:0.425429 +2025-04-19 08:08:10,951 INFO Epoch:65 train_loss:0.31579 +2025-04-19 08:08:22,322 INFO Epoch:65 val_res:0.429714 +2025-04-19 08:08:37,331 INFO Epoch:66 train_loss:0.26687 +2025-04-19 08:08:48,430 INFO Epoch:66 val_res:0.421714 +2025-04-19 08:09:03,093 INFO Epoch:67 train_loss:0.24734 +2025-04-19 08:09:14,817 INFO Epoch:67 val_res:0.423143 +2025-04-19 08:09:29,536 INFO Epoch:68 train_loss:0.25515 +2025-04-19 08:09:40,829 INFO Epoch:68 val_res:0.429143 +2025-04-19 08:09:56,676 INFO Epoch:69 train_loss:0.27678 +2025-04-19 08:10:07,847 INFO Epoch:69 val_res:0.425143 +2025-04-19 08:10:22,659 INFO Epoch:70 train_loss:0.27455 +2025-04-19 08:10:34,003 INFO Epoch:70 val_res:0.420000 +2025-04-19 08:10:49,126 INFO Epoch:71 train_loss:0.25634 +2025-04-19 08:10:59,986 INFO Epoch:71 val_res:0.421429 +2025-04-19 08:11:14,318 INFO Epoch:72 train_loss:0.26907 +2025-04-19 08:11:25,015 INFO Epoch:72 val_res:0.417429 +2025-04-19 08:11:39,056 INFO Epoch:73 train_loss:0.27695 +2025-04-19 08:11:49,522 INFO Epoch:73 val_res:0.411143 +2025-04-19 08:12:03,980 INFO Epoch:74 train_loss:0.26180 +2025-04-19 08:12:14,372 INFO Epoch:74 val_res:0.420857 +2025-04-19 08:12:28,280 INFO Epoch:75 train_loss:0.26787 +2025-04-19 08:12:38,786 INFO Epoch:75 val_res:0.417143 +2025-04-19 08:12:52,252 INFO Epoch:76 train_loss:0.25145 +2025-04-19 08:13:02,327 INFO Epoch:76 val_res:0.414286 +2025-04-19 08:13:16,783 INFO Epoch:77 train_loss:0.29138 +2025-04-19 08:13:27,063 INFO Epoch:77 val_res:0.412571 +2025-04-19 08:14:39,777 INFO Epoch:78 train_loss:0.28784 +2025-04-19 08:14:50,114 INFO Epoch:78 val_res:0.410571 +2025-04-19 08:15:05,045 INFO Epoch:79 train_loss:0.24222 +2025-04-19 08:15:15,435 INFO Epoch:79 val_res:0.418857 +2025-04-19 08:15:31,088 INFO Epoch:80 train_loss:0.21550 +2025-04-19 08:15:43,526 INFO Epoch:80 val_res:0.410571 +2025-04-19 08:15:58,278 INFO Epoch:81 train_loss:0.22969 +2025-04-19 08:16:10,399 INFO Epoch:81 val_res:0.417143 +2025-04-19 08:16:27,834 INFO Epoch:82 train_loss:0.22546 +2025-04-19 08:16:39,970 INFO Epoch:82 val_res:0.412286 +2025-04-19 08:16:57,397 INFO Epoch:83 train_loss:0.21364 +2025-04-19 08:17:10,185 INFO Epoch:83 val_res:0.405143 +2025-04-19 08:17:27,910 INFO Epoch:84 train_loss:0.21743 +2025-04-19 08:17:40,773 INFO Epoch:84 val_res:0.411143 +2025-04-19 08:17:58,157 INFO Epoch:85 train_loss:0.22674 +2025-04-19 08:18:09,892 INFO Epoch:85 val_res:0.408571 +2025-04-19 08:18:27,193 INFO Epoch:86 train_loss:0.23254 +2025-04-19 08:18:40,258 INFO Epoch:86 val_res:0.406571 +2025-04-19 08:18:56,778 INFO Epoch:87 train_loss:0.22071 +2025-04-19 08:19:10,314 INFO Epoch:87 val_res:0.408571 +2025-04-19 08:19:27,380 INFO Epoch:88 train_loss:0.24680 +2025-04-19 08:19:39,426 INFO Epoch:88 val_res:0.401714 +2025-04-19 08:19:57,079 INFO Epoch:89 train_loss:0.28095 +2025-04-19 08:20:09,493 INFO Epoch:89 val_res:0.408857 +2025-04-19 08:20:26,388 INFO Epoch:90 train_loss:0.24885 +2025-04-19 08:20:38,796 INFO Epoch:90 val_res:0.405714 +2025-04-19 08:20:56,529 INFO Epoch:91 train_loss:0.22084 +2025-04-19 08:21:08,612 INFO Epoch:91 val_res:0.406000 +2025-04-19 08:21:25,398 INFO Epoch:92 train_loss:0.23725 +2025-04-19 08:21:38,626 INFO Epoch:92 val_res:0.404857 +2025-04-19 08:21:55,099 INFO Epoch:93 train_loss:0.25071 +2025-04-19 08:22:08,996 INFO Epoch:93 val_res:0.402571 +2025-04-19 08:22:26,115 INFO Epoch:94 train_loss:0.20953 +2025-04-19 08:22:39,528 INFO Epoch:94 val_res:0.402857 +2025-04-19 08:22:57,073 INFO Epoch:95 train_loss:0.24374 +2025-04-19 08:23:09,780 INFO Epoch:95 val_res:0.404571 +2025-04-19 08:23:27,095 INFO Epoch:96 train_loss:0.22957 +2025-04-19 08:23:40,263 INFO Epoch:96 val_res:0.400571 +2025-04-19 08:23:57,888 INFO Epoch:97 train_loss:0.21415 +2025-04-19 08:24:09,891 INFO Epoch:97 val_res:0.400286 +2025-04-19 08:24:27,555 INFO Epoch:98 train_loss:0.23792 +2025-04-19 08:24:40,272 INFO Epoch:98 val_res:0.403143 +2025-04-19 08:24:57,122 INFO Epoch:99 train_loss:0.20769 +2025-04-19 08:25:09,953 INFO Epoch:99 val_res:0.399143 +2025-04-19 08:25:10,648 INFO ===================================== +2025-04-19 08:25:10,649 INFO Start testing... +2025-04-19 08:25:10,649 INFO ===================================== +2025-04-19 08:25:25,091 INFO Incremental step 6 Testing res: 0.508286 +2025-04-19 08:25:25,095 INFO forgetting: 0.171333 +2025-04-19 08:25:25,097 INFO Incremental step: 7 +2025-04-19 08:25:46,943 INFO Epoch:0 train_loss:6.18006 +2025-04-19 08:26:00,851 INFO Epoch:0 val_res:0.431250 +2025-04-19 08:26:00,852 INFO Saving best model at Epoch 0 +2025-04-19 08:26:23,218 INFO Epoch:1 train_loss:2.50012 +2025-04-19 08:26:36,735 INFO Epoch:1 val_res:0.444250 +2025-04-19 08:26:36,736 INFO Saving best model at Epoch 1 +2025-04-19 08:27:00,190 INFO Epoch:2 train_loss:1.96188 +2025-04-19 08:27:14,651 INFO Epoch:2 val_res:0.449250 +2025-04-19 08:27:14,652 INFO Saving best model at Epoch 2 +2025-04-19 08:27:36,998 INFO Epoch:3 train_loss:1.75653 +2025-04-19 08:27:50,925 INFO Epoch:3 val_res:0.448750 +2025-04-19 08:28:12,143 INFO Epoch:4 train_loss:1.62458 +2025-04-19 08:28:26,230 INFO Epoch:4 val_res:0.454500 +2025-04-19 08:28:26,231 INFO Saving best model at Epoch 4 +2025-04-19 08:28:48,871 INFO Epoch:5 train_loss:1.52942 +2025-04-19 08:29:02,970 INFO Epoch:5 val_res:0.457250 +2025-04-19 08:29:02,977 INFO Saving best model at Epoch 5 +2025-04-19 08:29:26,213 INFO Epoch:6 train_loss:1.43695 +2025-04-19 08:29:40,110 INFO Epoch:6 val_res:0.461000 +2025-04-19 08:29:40,111 INFO Saving best model at Epoch 6 +2025-04-19 08:30:04,369 INFO Epoch:7 train_loss:1.37840 +2025-04-19 08:30:18,454 INFO Epoch:7 val_res:0.469250 +2025-04-19 08:30:18,455 INFO Saving best model at Epoch 7 +2025-04-19 08:30:42,692 INFO Epoch:8 train_loss:1.32484 +2025-04-19 08:30:56,229 INFO Epoch:8 val_res:0.477250 +2025-04-19 08:30:56,230 INFO Saving best model at Epoch 8 +2025-04-19 08:31:18,788 INFO Epoch:9 train_loss:1.24340 +2025-04-19 08:31:33,700 INFO Epoch:9 val_res:0.477250 +2025-04-19 08:31:55,025 INFO Epoch:10 train_loss:1.17764 +2025-04-19 08:32:09,453 INFO Epoch:10 val_res:0.476750 +2025-04-19 08:32:30,309 INFO Epoch:11 train_loss:1.13953 +2025-04-19 08:32:44,621 INFO Epoch:11 val_res:0.483750 +2025-04-19 08:32:44,621 INFO Saving best model at Epoch 11 +2025-04-19 08:33:07,940 INFO Epoch:12 train_loss:1.08569 +2025-04-19 08:33:22,416 INFO Epoch:12 val_res:0.486500 +2025-04-19 08:33:22,416 INFO Saving best model at Epoch 12 +2025-04-19 08:33:46,231 INFO Epoch:13 train_loss:1.05364 +2025-04-19 08:34:00,373 INFO Epoch:13 val_res:0.494500 +2025-04-19 08:34:00,374 INFO Saving best model at Epoch 13 +2025-04-19 08:34:24,386 INFO Epoch:14 train_loss:1.01109 +2025-04-19 08:34:38,070 INFO Epoch:14 val_res:0.487500 +2025-04-19 08:35:00,070 INFO Epoch:15 train_loss:0.94817 +2025-04-19 08:35:14,576 INFO Epoch:15 val_res:0.492750 +2025-04-19 08:35:35,538 INFO Epoch:16 train_loss:0.91204 +2025-04-19 08:35:50,213 INFO Epoch:16 val_res:0.488500 +2025-04-19 08:36:12,356 INFO Epoch:17 train_loss:0.90800 +2025-04-19 08:36:26,432 INFO Epoch:17 val_res:0.492250 +2025-04-19 08:36:48,920 INFO Epoch:18 train_loss:0.88579 +2025-04-19 08:37:03,131 INFO Epoch:18 val_res:0.489250 +2025-04-19 08:37:26,035 INFO Epoch:19 train_loss:0.86188 +2025-04-19 08:37:40,624 INFO Epoch:19 val_res:0.488750 +2025-04-19 08:38:01,906 INFO Epoch:20 train_loss:0.81064 +2025-04-19 08:38:16,489 INFO Epoch:20 val_res:0.488000 +2025-04-19 08:38:37,137 INFO Epoch:21 train_loss:0.79601 +2025-04-19 08:38:51,828 INFO Epoch:21 val_res:0.483750 +2025-04-19 08:39:12,831 INFO Epoch:22 train_loss:0.78892 +2025-04-19 08:39:26,905 INFO Epoch:22 val_res:0.483500 +2025-04-19 08:39:48,559 INFO Epoch:23 train_loss:0.73803 +2025-04-19 08:40:01,903 INFO Epoch:23 val_res:0.484500 +2025-04-19 08:40:23,736 INFO Epoch:24 train_loss:0.73021 +2025-04-19 08:40:37,758 INFO Epoch:24 val_res:0.481750 +2025-04-19 08:40:59,043 INFO Epoch:25 train_loss:0.73186 +2025-04-19 08:41:12,483 INFO Epoch:25 val_res:0.482500 +2025-04-19 08:41:33,891 INFO Epoch:26 train_loss:0.71762 +2025-04-19 08:41:47,650 INFO Epoch:26 val_res:0.477500 +2025-04-19 08:42:08,381 INFO Epoch:27 train_loss:0.68879 +2025-04-19 08:42:22,223 INFO Epoch:27 val_res:0.475000 +2025-04-19 08:42:44,059 INFO Epoch:28 train_loss:0.67238 +2025-04-19 08:42:57,471 INFO Epoch:28 val_res:0.472000 +2025-04-19 08:43:20,112 INFO Epoch:29 train_loss:0.67915 +2025-04-19 08:43:33,511 INFO Epoch:29 val_res:0.469500 +2025-04-19 08:43:55,954 INFO Epoch:30 train_loss:0.65959 +2025-04-19 08:44:09,890 INFO Epoch:30 val_res:0.462750 +2025-04-19 08:44:30,581 INFO Epoch:31 train_loss:0.67178 +2025-04-19 08:44:44,716 INFO Epoch:31 val_res:0.471750 +2025-04-19 08:45:06,250 INFO Epoch:32 train_loss:0.65001 +2025-04-19 08:45:20,256 INFO Epoch:32 val_res:0.467250 +2025-04-19 08:45:42,466 INFO Epoch:33 train_loss:0.63547 +2025-04-19 08:45:57,281 INFO Epoch:33 val_res:0.468000 +2025-04-19 08:46:19,016 INFO Epoch:34 train_loss:0.62317 +2025-04-19 08:46:33,351 INFO Epoch:34 val_res:0.463250 +2025-04-19 08:46:54,325 INFO Epoch:35 train_loss:0.60611 +2025-04-19 08:47:09,007 INFO Epoch:35 val_res:0.466250 +2025-04-19 08:47:30,113 INFO Epoch:36 train_loss:0.61357 +2025-04-19 08:47:44,748 INFO Epoch:36 val_res:0.460000 +2025-04-19 08:48:05,568 INFO Epoch:37 train_loss:0.63800 +2025-04-19 08:48:19,883 INFO Epoch:37 val_res:0.452500 +2025-04-19 08:48:41,862 INFO Epoch:38 train_loss:0.63657 +2025-04-19 08:48:56,029 INFO Epoch:38 val_res:0.453000 +2025-04-19 08:49:19,000 INFO Epoch:39 train_loss:0.58642 +2025-04-19 08:49:33,187 INFO Epoch:39 val_res:0.452250 +2025-04-19 08:49:55,816 INFO Epoch:40 train_loss:0.57588 +2025-04-19 08:50:10,092 INFO Epoch:40 val_res:0.453500 +2025-04-19 08:50:31,819 INFO Epoch:41 train_loss:0.56576 +2025-04-19 08:50:46,587 INFO Epoch:41 val_res:0.454750 +2025-04-19 08:51:08,276 INFO Epoch:42 train_loss:0.58305 +2025-04-19 08:51:22,646 INFO Epoch:42 val_res:0.450000 +2025-04-19 08:51:44,792 INFO Epoch:43 train_loss:0.58523 +2025-04-19 08:51:59,048 INFO Epoch:43 val_res:0.453000 +2025-04-19 08:52:22,252 INFO Epoch:44 train_loss:0.63355 +2025-04-19 08:52:36,256 INFO Epoch:44 val_res:0.439750 +2025-04-19 08:52:59,580 INFO Epoch:45 train_loss:0.56672 +2025-04-19 08:53:14,149 INFO Epoch:45 val_res:0.445000 +2025-04-19 08:53:35,981 INFO Epoch:46 train_loss:0.55048 +2025-04-19 08:53:51,111 INFO Epoch:46 val_res:0.440000 +2025-04-19 08:54:12,630 INFO Epoch:47 train_loss:0.51141 +2025-04-19 08:54:28,240 INFO Epoch:47 val_res:0.440750 +2025-04-19 08:54:52,636 INFO Epoch:48 train_loss:0.53579 +2025-04-19 08:55:06,982 INFO Epoch:48 val_res:0.443500 +2025-04-19 08:55:30,584 INFO Epoch:49 train_loss:0.52852 +2025-04-19 08:55:45,070 INFO Epoch:49 val_res:0.431750 +2025-04-19 08:56:07,603 INFO Epoch:50 train_loss:0.52706 +2025-04-19 08:56:21,658 INFO Epoch:50 val_res:0.442750 +2025-04-19 08:56:43,210 INFO Epoch:51 train_loss:0.51639 +2025-04-19 08:56:57,003 INFO Epoch:51 val_res:0.441500 +2025-04-19 08:57:18,127 INFO Epoch:52 train_loss:0.54527 +2025-04-19 08:57:33,091 INFO Epoch:52 val_res:0.433750 +2025-04-19 08:57:55,834 INFO Epoch:53 train_loss:0.55896 +2025-04-19 08:58:09,920 INFO Epoch:53 val_res:0.429750 +2025-04-19 08:58:32,559 INFO Epoch:54 train_loss:0.54671 +2025-04-19 08:58:46,579 INFO Epoch:54 val_res:0.433500 +2025-04-19 08:59:08,878 INFO Epoch:55 train_loss:0.56783 +2025-04-19 08:59:23,339 INFO Epoch:55 val_res:0.435500 +2025-04-19 08:59:45,924 INFO Epoch:56 train_loss:0.51644 +2025-04-19 08:59:59,681 INFO Epoch:56 val_res:0.425250 +2025-04-19 09:00:21,709 INFO Epoch:57 train_loss:0.52962 +2025-04-19 09:00:36,376 INFO Epoch:57 val_res:0.430500 +2025-04-19 09:00:57,338 INFO Epoch:58 train_loss:0.49647 +2025-04-19 09:01:12,764 INFO Epoch:58 val_res:0.429750 +2025-04-19 09:01:33,666 INFO Epoch:59 train_loss:0.51897 +2025-04-19 09:01:48,202 INFO Epoch:59 val_res:0.424750 +2025-04-19 09:02:10,240 INFO Epoch:60 train_loss:0.47890 +2025-04-19 09:02:24,172 INFO Epoch:60 val_res:0.428500 +2025-04-19 09:02:46,734 INFO Epoch:61 train_loss:0.48394 +2025-04-19 09:03:00,549 INFO Epoch:61 val_res:0.421000 +2025-04-19 09:03:22,452 INFO Epoch:62 train_loss:0.52026 +2025-04-19 09:03:37,073 INFO Epoch:62 val_res:0.419500 +2025-04-19 09:03:59,122 INFO Epoch:63 train_loss:0.50192 +2025-04-19 09:04:13,329 INFO Epoch:63 val_res:0.418250 +2025-04-19 09:04:33,204 INFO Epoch:64 train_loss:0.52073 +2025-04-19 09:04:46,615 INFO Epoch:64 val_res:0.420500 +2025-04-19 09:05:05,762 INFO Epoch:65 train_loss:0.49885 +2025-04-19 09:05:18,722 INFO Epoch:65 val_res:0.421000 +2025-04-19 09:05:38,320 INFO Epoch:66 train_loss:0.47889 +2025-04-19 09:05:50,677 INFO Epoch:66 val_res:0.417000 +2025-04-19 09:06:10,188 INFO Epoch:67 train_loss:0.48450 +2025-04-19 09:06:23,022 INFO Epoch:67 val_res:0.420500 +2025-04-19 09:06:41,935 INFO Epoch:68 train_loss:0.48145 +2025-04-19 09:06:55,402 INFO Epoch:68 val_res:0.420250 +2025-04-19 09:07:14,067 INFO Epoch:69 train_loss:0.50309 +2025-04-19 09:07:26,722 INFO Epoch:69 val_res:0.409250 +2025-04-19 09:07:46,178 INFO Epoch:70 train_loss:0.54224 +2025-04-19 09:07:58,366 INFO Epoch:70 val_res:0.413750 +2025-04-19 09:08:17,477 INFO Epoch:71 train_loss:0.47008 +2025-04-19 09:08:29,826 INFO Epoch:71 val_res:0.418250 +2025-04-19 09:08:48,443 INFO Epoch:72 train_loss:0.43372 +2025-04-19 09:09:01,763 INFO Epoch:72 val_res:0.411750 +2025-04-19 09:09:19,897 INFO Epoch:73 train_loss:0.44913 +2025-04-19 09:09:32,782 INFO Epoch:73 val_res:0.416750 +2025-04-19 09:09:51,409 INFO Epoch:74 train_loss:0.44648 +2025-04-19 09:10:03,681 INFO Epoch:74 val_res:0.414000 +2025-04-19 09:10:23,164 INFO Epoch:75 train_loss:0.51725 +2025-04-19 09:10:35,360 INFO Epoch:75 val_res:0.414250 +2025-04-19 09:10:53,807 INFO Epoch:76 train_loss:0.47601 +2025-04-19 09:11:05,726 INFO Epoch:76 val_res:0.404750 +2025-04-19 09:11:23,623 INFO Epoch:77 train_loss:0.48055 +2025-04-19 09:11:35,965 INFO Epoch:77 val_res:0.411750 +2025-04-19 09:11:53,658 INFO Epoch:78 train_loss:0.46485 +2025-04-19 09:12:05,096 INFO Epoch:78 val_res:0.414750 +2025-04-19 09:12:22,890 INFO Epoch:79 train_loss:0.44330 +2025-04-19 09:12:34,260 INFO Epoch:79 val_res:0.414000 +2025-04-19 09:12:52,207 INFO Epoch:80 train_loss:0.47205 +2025-04-19 09:13:03,682 INFO Epoch:80 val_res:0.404500 +2025-04-19 09:13:21,247 INFO Epoch:81 train_loss:0.45435 +2025-04-19 09:13:33,112 INFO Epoch:81 val_res:0.406500 +2025-04-19 09:13:50,143 INFO Epoch:82 train_loss:0.42887 +2025-04-19 09:14:02,555 INFO Epoch:82 val_res:0.407000 +2025-04-19 09:14:21,717 INFO Epoch:83 train_loss:0.44399 +2025-04-19 09:14:34,640 INFO Epoch:83 val_res:0.405250 +2025-04-19 09:14:53,949 INFO Epoch:84 train_loss:0.44927 +2025-04-19 09:15:06,706 INFO Epoch:84 val_res:0.404750 +2025-04-19 09:15:24,991 INFO Epoch:85 train_loss:0.43326 +2025-04-19 09:15:37,850 INFO Epoch:85 val_res:0.405000 +2025-04-19 09:15:56,684 INFO Epoch:86 train_loss:0.42768 +2025-04-19 09:16:09,707 INFO Epoch:86 val_res:0.402000 +2025-04-19 09:16:27,653 INFO Epoch:87 train_loss:0.46691 +2025-04-19 09:16:40,825 INFO Epoch:87 val_res:0.400750 +2025-04-19 09:16:59,103 INFO Epoch:88 train_loss:0.43773 +2025-04-19 09:17:11,393 INFO Epoch:88 val_res:0.399000 +2025-04-19 09:17:30,026 INFO Epoch:89 train_loss:0.41915 +2025-04-19 09:17:42,350 INFO Epoch:89 val_res:0.398250 +2025-04-19 09:18:01,509 INFO Epoch:90 train_loss:0.42265 +2025-04-19 09:18:14,065 INFO Epoch:90 val_res:0.398250 +2025-04-19 09:18:32,554 INFO Epoch:91 train_loss:0.48409 +2025-04-19 09:18:45,458 INFO Epoch:91 val_res:0.400250 +2025-04-19 09:19:03,659 INFO Epoch:92 train_loss:0.45735 +2025-04-19 09:19:16,143 INFO Epoch:92 val_res:0.392750 +2025-04-19 09:19:35,411 INFO Epoch:93 train_loss:0.47701 +2025-04-19 09:19:47,438 INFO Epoch:93 val_res:0.392250 +2025-04-19 09:20:06,702 INFO Epoch:94 train_loss:0.47430 +2025-04-19 09:20:19,526 INFO Epoch:94 val_res:0.389750 +2025-04-19 09:20:37,581 INFO Epoch:95 train_loss:0.44582 +2025-04-19 09:20:50,316 INFO Epoch:95 val_res:0.390000 +2025-04-19 09:21:08,742 INFO Epoch:96 train_loss:0.46670 +2025-04-19 09:21:20,776 INFO Epoch:96 val_res:0.392250 +2025-04-19 09:21:40,231 INFO Epoch:97 train_loss:0.43270 +2025-04-19 09:21:52,378 INFO Epoch:97 val_res:0.398000 +2025-04-19 09:22:11,411 INFO Epoch:98 train_loss:0.41896 +2025-04-19 09:22:24,168 INFO Epoch:98 val_res:0.399250 +2025-04-19 09:22:42,829 INFO Epoch:99 train_loss:0.42496 +2025-04-19 09:22:55,557 INFO Epoch:99 val_res:0.398500 +2025-04-19 09:22:56,247 INFO ===================================== +2025-04-19 09:22:56,248 INFO Start testing... +2025-04-19 09:22:56,248 INFO ===================================== +2025-04-19 09:23:12,787 INFO Incremental step 7 Testing res: 0.488750 +2025-04-19 09:23:12,792 INFO forgetting: 0.164286 +2025-04-19 09:23:12,797 INFO Incremental step: 8 +2025-04-19 09:23:30,961 INFO Epoch:0 train_loss:6.13177 +2025-04-19 09:23:46,419 INFO Epoch:0 val_res:0.419778 +2025-04-19 09:23:46,420 INFO Saving best model at Epoch 0 +2025-04-19 09:24:04,426 INFO Epoch:1 train_loss:1.96999 +2025-04-19 09:24:18,920 INFO Epoch:1 val_res:0.437333 +2025-04-19 09:24:18,920 INFO Saving best model at Epoch 1 +2025-04-19 09:24:37,147 INFO Epoch:2 train_loss:1.35273 +2025-04-19 09:24:51,459 INFO Epoch:2 val_res:0.442667 +2025-04-19 09:24:51,460 INFO Saving best model at Epoch 2 +2025-04-19 09:25:08,749 INFO Epoch:3 train_loss:1.14663 +2025-04-19 09:25:23,002 INFO Epoch:3 val_res:0.446444 +2025-04-19 09:25:23,002 INFO Saving best model at Epoch 3 +2025-04-19 09:25:40,263 INFO Epoch:4 train_loss:1.05250 +2025-04-19 09:25:54,772 INFO Epoch:4 val_res:0.446444 +2025-04-19 09:26:10,313 INFO Epoch:5 train_loss:0.98173 +2025-04-19 09:26:24,660 INFO Epoch:5 val_res:0.452000 +2025-04-19 09:26:24,660 INFO Saving best model at Epoch 5 +2025-04-19 09:26:42,071 INFO Epoch:6 train_loss:0.92244 +2025-04-19 09:26:56,668 INFO Epoch:6 val_res:0.455778 +2025-04-19 09:26:56,668 INFO Saving best model at Epoch 6 +2025-04-19 09:27:14,291 INFO Epoch:7 train_loss:0.86967 +2025-04-19 09:27:28,530 INFO Epoch:7 val_res:0.457556 +2025-04-19 09:27:28,530 INFO Saving best model at Epoch 7 +2025-04-19 09:27:45,816 INFO Epoch:8 train_loss:0.83392 +2025-04-19 09:28:00,073 INFO Epoch:8 val_res:0.461111 +2025-04-19 09:28:00,074 INFO Saving best model at Epoch 8 +2025-04-19 09:28:17,589 INFO Epoch:9 train_loss:0.80145 +2025-04-19 09:28:31,923 INFO Epoch:9 val_res:0.456889 +2025-04-19 09:28:47,835 INFO Epoch:10 train_loss:0.77009 +2025-04-19 09:29:01,451 INFO Epoch:10 val_res:0.463111 +2025-04-19 09:29:01,451 INFO Saving best model at Epoch 10 +2025-04-19 09:29:18,504 INFO Epoch:11 train_loss:0.73967 +2025-04-19 09:29:32,811 INFO Epoch:11 val_res:0.462444 +2025-04-19 09:29:47,667 INFO Epoch:12 train_loss:0.71349 +2025-04-19 09:30:02,625 INFO Epoch:12 val_res:0.461333 +2025-04-19 09:30:17,283 INFO Epoch:13 train_loss:0.68780 +2025-04-19 09:30:32,104 INFO Epoch:13 val_res:0.456667 +2025-04-19 09:30:46,808 INFO Epoch:14 train_loss:0.67616 +2025-04-19 09:31:00,738 INFO Epoch:14 val_res:0.456444 +2025-04-19 09:31:15,925 INFO Epoch:15 train_loss:0.64639 +2025-04-19 09:31:29,951 INFO Epoch:15 val_res:0.460444 +2025-04-19 09:31:45,316 INFO Epoch:16 train_loss:0.62032 +2025-04-19 09:32:00,129 INFO Epoch:16 val_res:0.458444 +2025-04-19 09:32:14,955 INFO Epoch:17 train_loss:0.60558 +2025-04-19 09:32:29,185 INFO Epoch:17 val_res:0.450889 +2025-04-19 09:32:44,257 INFO Epoch:18 train_loss:0.58961 +2025-04-19 09:32:57,998 INFO Epoch:18 val_res:0.450444 +2025-04-19 09:33:13,896 INFO Epoch:19 train_loss:0.57507 +2025-04-19 09:33:28,166 INFO Epoch:19 val_res:0.445556 +2025-04-19 09:33:43,701 INFO Epoch:20 train_loss:0.56480 +2025-04-19 09:33:57,618 INFO Epoch:20 val_res:0.446444 +2025-04-19 09:34:12,405 INFO Epoch:21 train_loss:0.53667 +2025-04-19 09:34:26,708 INFO Epoch:21 val_res:0.441778 +2025-04-19 09:34:41,690 INFO Epoch:22 train_loss:0.53608 +2025-04-19 09:34:55,471 INFO Epoch:22 val_res:0.445111 +2025-04-19 09:35:11,129 INFO Epoch:23 train_loss:0.51370 +2025-04-19 09:35:24,677 INFO Epoch:23 val_res:0.434222 +2025-04-19 09:35:40,072 INFO Epoch:24 train_loss:0.51001 +2025-04-19 09:35:54,508 INFO Epoch:24 val_res:0.433333 +2025-04-19 09:36:09,381 INFO Epoch:25 train_loss:0.49007 +2025-04-19 09:36:24,274 INFO Epoch:25 val_res:0.434222 +2025-04-19 09:36:38,735 INFO Epoch:26 train_loss:0.46409 +2025-04-19 09:36:53,787 INFO Epoch:26 val_res:0.436222 +2025-04-19 09:37:09,130 INFO Epoch:27 train_loss:0.45331 +2025-04-19 09:37:23,748 INFO Epoch:27 val_res:0.434667 +2025-04-19 09:37:39,561 INFO Epoch:28 train_loss:0.44257 +2025-04-19 09:37:54,836 INFO Epoch:28 val_res:0.428222 +2025-04-19 09:38:09,593 INFO Epoch:29 train_loss:0.44411 +2025-04-19 09:38:24,462 INFO Epoch:29 val_res:0.426667 +2025-04-19 09:38:39,286 INFO Epoch:30 train_loss:0.43514 +2025-04-19 09:38:53,712 INFO Epoch:30 val_res:0.428000 +2025-04-19 09:39:09,164 INFO Epoch:31 train_loss:0.42723 +2025-04-19 09:39:23,077 INFO Epoch:31 val_res:0.426222 +2025-04-19 09:39:38,766 INFO Epoch:32 train_loss:0.44105 +2025-04-19 09:39:52,550 INFO Epoch:32 val_res:0.414000 +2025-04-19 09:40:08,232 INFO Epoch:33 train_loss:0.44975 +2025-04-19 09:40:22,636 INFO Epoch:33 val_res:0.411333 +2025-04-19 09:40:37,495 INFO Epoch:34 train_loss:0.41483 +2025-04-19 09:40:51,622 INFO Epoch:34 val_res:0.412444 +2025-04-19 09:41:06,746 INFO Epoch:35 train_loss:0.40827 +2025-04-19 09:41:20,593 INFO Epoch:35 val_res:0.411556 +2025-04-19 09:41:35,974 INFO Epoch:36 train_loss:0.39105 +2025-04-19 09:41:50,015 INFO Epoch:36 val_res:0.403778 +2025-04-19 09:42:05,788 INFO Epoch:37 train_loss:0.39702 +2025-04-19 09:42:19,434 INFO Epoch:37 val_res:0.404444 +2025-04-19 09:42:34,513 INFO Epoch:38 train_loss:0.40661 +2025-04-19 09:42:48,803 INFO Epoch:38 val_res:0.400000 +2025-04-19 09:43:03,973 INFO Epoch:39 train_loss:0.38721 +2025-04-19 09:43:17,776 INFO Epoch:39 val_res:0.399556 +2025-04-19 09:43:32,938 INFO Epoch:40 train_loss:0.39020 +2025-04-19 09:43:46,728 INFO Epoch:40 val_res:0.394667 +2025-04-19 09:44:01,912 INFO Epoch:41 train_loss:0.38843 +2025-04-19 09:44:16,124 INFO Epoch:41 val_res:0.394444 +2025-04-19 09:44:31,045 INFO Epoch:42 train_loss:0.39713 +2025-04-19 09:44:45,008 INFO Epoch:42 val_res:0.392444 +2025-04-19 09:45:00,090 INFO Epoch:43 train_loss:0.40060 +2025-04-19 09:45:14,416 INFO Epoch:43 val_res:0.390000 +2025-04-19 09:45:29,306 INFO Epoch:44 train_loss:0.36959 +2025-04-19 09:45:43,556 INFO Epoch:44 val_res:0.390222 +2025-04-19 09:45:58,573 INFO Epoch:45 train_loss:0.36830 +2025-04-19 09:46:12,637 INFO Epoch:45 val_res:0.384000 +2025-04-19 09:46:27,954 INFO Epoch:46 train_loss:0.36261 +2025-04-19 09:46:41,651 INFO Epoch:46 val_res:0.382444 +2025-04-19 09:46:56,949 INFO Epoch:47 train_loss:0.37900 +2025-04-19 09:47:10,625 INFO Epoch:47 val_res:0.387556 +2025-04-19 09:47:25,974 INFO Epoch:48 train_loss:0.34915 +2025-04-19 09:47:40,202 INFO Epoch:48 val_res:0.384000 +2025-04-19 09:47:55,271 INFO Epoch:49 train_loss:0.33782 +2025-04-19 09:48:09,029 INFO Epoch:49 val_res:0.378889 +2025-04-19 09:48:24,542 INFO Epoch:50 train_loss:0.37124 +2025-04-19 09:48:37,961 INFO Epoch:50 val_res:0.378222 +2025-04-19 09:48:53,776 INFO Epoch:51 train_loss:0.38515 +2025-04-19 09:49:07,484 INFO Epoch:51 val_res:0.383111 +2025-04-19 09:49:22,796 INFO Epoch:52 train_loss:0.36269 +2025-04-19 09:49:37,090 INFO Epoch:52 val_res:0.376000 +2025-04-19 09:49:51,766 INFO Epoch:53 train_loss:0.34326 +2025-04-19 09:50:06,045 INFO Epoch:53 val_res:0.376444 +2025-04-19 09:50:21,079 INFO Epoch:54 train_loss:0.31959 +2025-04-19 09:50:34,809 INFO Epoch:54 val_res:0.377333 +2025-04-19 09:50:50,429 INFO Epoch:55 train_loss:0.32527 +2025-04-19 09:51:04,083 INFO Epoch:55 val_res:0.375778 +2025-04-19 09:51:19,229 INFO Epoch:56 train_loss:0.33001 +2025-04-19 09:51:33,715 INFO Epoch:56 val_res:0.378222 +2025-04-19 09:51:47,988 INFO Epoch:57 train_loss:0.38703 +2025-04-19 09:52:02,532 INFO Epoch:57 val_res:0.372000 +2025-04-19 09:52:17,350 INFO Epoch:58 train_loss:0.37164 +2025-04-19 09:52:31,387 INFO Epoch:58 val_res:0.373778 +2025-04-19 09:52:46,873 INFO Epoch:59 train_loss:0.32905 +2025-04-19 09:53:00,423 INFO Epoch:59 val_res:0.371556 +2025-04-19 09:53:15,505 INFO Epoch:60 train_loss:0.30037 +2025-04-19 09:53:29,761 INFO Epoch:60 val_res:0.370444 +2025-04-19 09:53:44,420 INFO Epoch:61 train_loss:0.31198 +2025-04-19 09:53:58,955 INFO Epoch:61 val_res:0.369556 +2025-04-19 09:54:14,186 INFO Epoch:62 train_loss:0.29674 +2025-04-19 09:54:28,125 INFO Epoch:62 val_res:0.367111 +2025-04-19 09:54:44,065 INFO Epoch:63 train_loss:0.30599 +2025-04-19 09:54:57,392 INFO Epoch:63 val_res:0.367778 +2025-04-19 09:55:13,137 INFO Epoch:64 train_loss:0.32167 +2025-04-19 09:55:26,994 INFO Epoch:64 val_res:0.365778 +2025-04-19 09:55:42,206 INFO Epoch:65 train_loss:0.31428 +2025-04-19 09:55:56,612 INFO Epoch:65 val_res:0.366889 +2025-04-19 09:56:11,570 INFO Epoch:66 train_loss:0.33761 +2025-04-19 09:56:25,320 INFO Epoch:66 val_res:0.360000 +2025-04-19 09:56:41,034 INFO Epoch:67 train_loss:0.35195 +2025-04-19 09:56:54,557 INFO Epoch:67 val_res:0.364000 +2025-04-19 09:57:10,604 INFO Epoch:68 train_loss:0.31239 +2025-04-19 09:57:24,380 INFO Epoch:68 val_res:0.358667 +2025-04-19 09:57:39,865 INFO Epoch:69 train_loss:0.30301 +2025-04-19 09:57:54,224 INFO Epoch:69 val_res:0.360222 +2025-04-19 09:58:08,864 INFO Epoch:70 train_loss:0.27252 +2025-04-19 09:58:22,775 INFO Epoch:70 val_res:0.360889 +2025-04-19 09:58:38,265 INFO Epoch:71 train_loss:0.28400 +2025-04-19 09:58:51,797 INFO Epoch:71 val_res:0.360444 +2025-04-19 09:59:06,713 INFO Epoch:72 train_loss:0.31667 +2025-04-19 09:59:21,295 INFO Epoch:72 val_res:0.355556 +2025-04-19 09:59:35,830 INFO Epoch:73 train_loss:0.29883 +2025-04-19 09:59:50,016 INFO Epoch:73 val_res:0.358889 +2025-04-19 10:00:05,372 INFO Epoch:74 train_loss:0.30722 +2025-04-19 10:00:19,041 INFO Epoch:74 val_res:0.360444 +2025-04-19 10:00:34,573 INFO Epoch:75 train_loss:0.32805 +2025-04-19 10:00:47,828 INFO Epoch:75 val_res:0.355556 +2025-04-19 10:01:01,994 INFO Epoch:76 train_loss:0.29487 +2025-04-19 10:01:15,056 INFO Epoch:76 val_res:0.353333 +2025-04-19 10:01:29,479 INFO Epoch:77 train_loss:0.27182 +2025-04-19 10:01:42,485 INFO Epoch:77 val_res:0.354000 +2025-04-19 10:01:56,574 INFO Epoch:78 train_loss:0.27520 +2025-04-19 10:02:09,594 INFO Epoch:78 val_res:0.352000 +2025-04-19 10:02:23,224 INFO Epoch:79 train_loss:0.29231 +2025-04-19 10:02:35,962 INFO Epoch:79 val_res:0.354222 +2025-04-19 10:02:50,315 INFO Epoch:80 train_loss:0.26712 +2025-04-19 10:03:03,177 INFO Epoch:80 val_res:0.350000 +2025-04-19 10:03:18,170 INFO Epoch:81 train_loss:0.25072 +2025-04-19 10:03:32,311 INFO Epoch:81 val_res:0.352667 +2025-04-19 10:03:47,933 INFO Epoch:82 train_loss:0.27322 +2025-04-19 10:04:01,598 INFO Epoch:82 val_res:0.346000 +2025-04-19 10:04:16,700 INFO Epoch:83 train_loss:0.27682 +2025-04-19 10:04:30,794 INFO Epoch:83 val_res:0.347333 +2025-04-19 10:04:45,701 INFO Epoch:84 train_loss:0.27670 +2025-04-19 10:04:59,886 INFO Epoch:84 val_res:0.346889 +2025-04-19 10:05:14,842 INFO Epoch:85 train_loss:0.30090 +2025-04-19 10:05:28,801 INFO Epoch:85 val_res:0.346444 +2025-04-19 10:05:43,998 INFO Epoch:86 train_loss:0.31214 +2025-04-19 10:05:57,903 INFO Epoch:86 val_res:0.342000 +2025-04-19 10:06:13,542 INFO Epoch:87 train_loss:0.30923 +2025-04-19 10:06:27,143 INFO Epoch:87 val_res:0.342667 +2025-04-19 10:06:42,975 INFO Epoch:88 train_loss:0.29871 +2025-04-19 10:06:57,614 INFO Epoch:88 val_res:0.342000 +2025-04-19 10:07:12,838 INFO Epoch:89 train_loss:0.25563 +2025-04-19 10:07:26,044 INFO Epoch:89 val_res:0.344444 +2025-04-19 10:07:41,966 INFO Epoch:90 train_loss:0.26667 +2025-04-19 10:07:56,495 INFO Epoch:90 val_res:0.337111 +2025-04-19 10:08:11,530 INFO Epoch:91 train_loss:0.26193 +2025-04-19 10:08:26,596 INFO Epoch:91 val_res:0.340222 +2025-04-19 10:08:42,022 INFO Epoch:92 train_loss:0.24802 +2025-04-19 10:08:56,025 INFO Epoch:92 val_res:0.341556 +2025-04-19 10:09:12,256 INFO Epoch:93 train_loss:0.23322 +2025-04-19 10:09:26,580 INFO Epoch:93 val_res:0.337556 +2025-04-19 10:09:41,912 INFO Epoch:94 train_loss:0.30590 +2025-04-19 10:09:56,274 INFO Epoch:94 val_res:0.332222 +2025-04-19 10:10:12,039 INFO Epoch:95 train_loss:0.27671 +2025-04-19 10:10:25,767 INFO Epoch:95 val_res:0.334444 +2025-04-19 10:10:41,983 INFO Epoch:96 train_loss:0.25403 +2025-04-19 10:10:56,200 INFO Epoch:96 val_res:0.337778 +2025-04-19 10:11:11,557 INFO Epoch:97 train_loss:0.22404 +2025-04-19 10:11:25,960 INFO Epoch:97 val_res:0.335778 +2025-04-19 10:11:42,370 INFO Epoch:98 train_loss:0.22728 +2025-04-19 10:11:56,671 INFO Epoch:98 val_res:0.336444 +2025-04-19 10:12:12,851 INFO Epoch:99 train_loss:0.22539 +2025-04-19 10:12:27,456 INFO Epoch:99 val_res:0.335778 +2025-04-19 10:12:28,157 INFO ===================================== +2025-04-19 10:12:28,158 INFO Start testing... +2025-04-19 10:12:28,159 INFO ===================================== +2025-04-19 10:12:43,593 INFO Incremental step 8 Testing res: 0.461111 +2025-04-19 10:12:43,597 INFO forgetting: 0.155250 +2025-04-19 10:12:43,599 INFO Incremental step: 9 +2025-04-19 10:13:04,234 INFO Epoch:0 train_loss:4.69629 +2025-04-19 10:13:21,426 INFO Epoch:0 val_res:0.409000 +2025-04-19 10:13:21,428 INFO Saving best model at Epoch 0 +2025-04-19 10:13:42,313 INFO Epoch:1 train_loss:1.35953 +2025-04-19 10:13:58,266 INFO Epoch:1 val_res:0.414800 +2025-04-19 10:13:58,266 INFO Saving best model at Epoch 1 +2025-04-19 10:14:20,565 INFO Epoch:2 train_loss:0.98767 +2025-04-19 10:14:36,354 INFO Epoch:2 val_res:0.420400 +2025-04-19 10:14:36,355 INFO Saving best model at Epoch 2 +2025-04-19 10:14:57,388 INFO Epoch:3 train_loss:0.85943 +2025-04-19 10:15:13,111 INFO Epoch:3 val_res:0.424400 +2025-04-19 10:15:13,111 INFO Saving best model at Epoch 3 +2025-04-19 10:15:33,962 INFO Epoch:4 train_loss:0.79049 +2025-04-19 10:15:49,311 INFO Epoch:4 val_res:0.426200 +2025-04-19 10:15:49,311 INFO Saving best model at Epoch 4 +2025-04-19 10:16:10,159 INFO Epoch:5 train_loss:0.72706 +2025-04-19 10:16:26,570 INFO Epoch:5 val_res:0.433200 +2025-04-19 10:16:26,571 INFO Saving best model at Epoch 5 +2025-04-19 10:16:48,258 INFO Epoch:6 train_loss:0.68089 +2025-04-19 10:17:04,862 INFO Epoch:6 val_res:0.438800 +2025-04-19 10:17:04,863 INFO Saving best model at Epoch 6 +2025-04-19 10:17:25,701 INFO Epoch:7 train_loss:0.64766 +2025-04-19 10:17:42,875 INFO Epoch:7 val_res:0.442000 +2025-04-19 10:17:42,876 INFO Saving best model at Epoch 7 +2025-04-19 10:18:04,183 INFO Epoch:8 train_loss:0.60812 +2025-04-19 10:18:19,918 INFO Epoch:8 val_res:0.444800 +2025-04-19 10:18:19,919 INFO Saving best model at Epoch 8 +2025-04-19 10:18:41,912 INFO Epoch:9 train_loss:0.59230 +2025-04-19 10:18:57,993 INFO Epoch:9 val_res:0.448600 +2025-04-19 10:18:57,994 INFO Saving best model at Epoch 9 +2025-04-19 10:19:18,998 INFO Epoch:10 train_loss:0.57618 +2025-04-19 10:19:34,506 INFO Epoch:10 val_res:0.447200 +2025-04-19 10:19:54,396 INFO Epoch:11 train_loss:0.57023 +2025-04-19 10:20:10,230 INFO Epoch:11 val_res:0.449800 +2025-04-19 10:20:10,231 INFO Saving best model at Epoch 11 +2025-04-19 10:20:31,033 INFO Epoch:12 train_loss:0.54306 +2025-04-19 10:20:46,493 INFO Epoch:12 val_res:0.449400 +2025-04-19 10:21:06,203 INFO Epoch:13 train_loss:0.50482 +2025-04-19 10:21:22,098 INFO Epoch:13 val_res:0.453400 +2025-04-19 10:21:22,099 INFO Saving best model at Epoch 13 +2025-04-19 10:21:43,178 INFO Epoch:14 train_loss:0.49718 +2025-04-19 10:21:59,119 INFO Epoch:14 val_res:0.449400 +2025-04-19 10:22:17,791 INFO Epoch:15 train_loss:0.45930 +2025-04-19 10:22:34,078 INFO Epoch:15 val_res:0.447600 +2025-04-19 10:22:54,565 INFO Epoch:16 train_loss:0.45519 +2025-04-19 10:23:10,909 INFO Epoch:16 val_res:0.447200 +2025-04-19 10:23:30,361 INFO Epoch:17 train_loss:0.46325 +2025-04-19 10:23:45,896 INFO Epoch:17 val_res:0.439600 +2025-04-19 10:24:05,304 INFO Epoch:18 train_loss:0.45337 +2025-04-19 10:24:20,585 INFO Epoch:18 val_res:0.446200 +2025-04-19 10:24:39,761 INFO Epoch:19 train_loss:0.44534 +2025-04-19 10:24:55,690 INFO Epoch:19 val_res:0.438800 +2025-04-19 10:25:14,559 INFO Epoch:20 train_loss:0.40686 +2025-04-19 10:25:31,114 INFO Epoch:20 val_res:0.439800 +2025-04-19 10:25:49,901 INFO Epoch:21 train_loss:0.43103 +2025-04-19 10:26:06,737 INFO Epoch:21 val_res:0.432000 +2025-04-19 10:26:26,471 INFO Epoch:22 train_loss:0.41208 +2025-04-19 10:26:42,628 INFO Epoch:22 val_res:0.430200 +2025-04-19 10:27:01,965 INFO Epoch:23 train_loss:0.40148 +2025-04-19 10:27:17,770 INFO Epoch:23 val_res:0.425000 +2025-04-19 10:27:37,667 INFO Epoch:24 train_loss:0.41547 +2025-04-19 10:27:53,389 INFO Epoch:24 val_res:0.420600 +2025-04-19 10:28:12,780 INFO Epoch:25 train_loss:0.37567 +2025-04-19 10:28:28,194 INFO Epoch:25 val_res:0.420000 +2025-04-19 10:28:47,869 INFO Epoch:26 train_loss:0.35850 +2025-04-19 10:29:03,041 INFO Epoch:26 val_res:0.421800 +2025-04-19 10:29:22,337 INFO Epoch:27 train_loss:0.35205 +2025-04-19 10:29:38,954 INFO Epoch:27 val_res:0.413400 +2025-04-19 10:29:58,627 INFO Epoch:28 train_loss:0.33658 +2025-04-19 10:30:15,504 INFO Epoch:28 val_res:0.410800 +2025-04-19 10:30:34,437 INFO Epoch:29 train_loss:0.34084 +2025-04-19 10:30:51,323 INFO Epoch:29 val_res:0.410600 +2025-04-19 10:31:10,195 INFO Epoch:30 train_loss:0.35030 +2025-04-19 10:31:26,048 INFO Epoch:30 val_res:0.404600 +2025-04-19 10:31:46,182 INFO Epoch:31 train_loss:0.33699 +2025-04-19 10:32:02,099 INFO Epoch:31 val_res:0.407400 +2025-04-19 10:32:21,688 INFO Epoch:32 train_loss:0.35361 +2025-04-19 10:32:37,278 INFO Epoch:32 val_res:0.397000 +2025-04-19 10:32:56,158 INFO Epoch:33 train_loss:0.33313 +2025-04-19 10:33:11,453 INFO Epoch:33 val_res:0.394200 +2025-04-19 10:33:30,308 INFO Epoch:34 train_loss:0.33594 +2025-04-19 10:33:45,996 INFO Epoch:34 val_res:0.391200 +2025-04-19 10:34:04,821 INFO Epoch:35 train_loss:0.30963 +2025-04-19 10:34:20,927 INFO Epoch:35 val_res:0.392400 +2025-04-19 10:34:39,842 INFO Epoch:36 train_loss:0.30668 +2025-04-19 10:34:55,778 INFO Epoch:36 val_res:0.384400 +2025-04-19 10:35:15,122 INFO Epoch:37 train_loss:0.31500 +2025-04-19 10:35:30,793 INFO Epoch:37 val_res:0.381000 +2025-04-19 10:35:49,924 INFO Epoch:38 train_loss:0.32986 +2025-04-19 10:36:05,821 INFO Epoch:38 val_res:0.380200 +2025-04-19 10:36:24,790 INFO Epoch:39 train_loss:0.32276 +2025-04-19 10:36:40,804 INFO Epoch:39 val_res:0.379200 +2025-04-19 10:37:00,137 INFO Epoch:40 train_loss:0.41066 +2025-04-19 10:37:16,502 INFO Epoch:40 val_res:0.372800 +2025-04-19 10:37:36,062 INFO Epoch:41 train_loss:0.31388 +2025-04-19 10:37:51,893 INFO Epoch:41 val_res:0.375800 +2025-04-19 10:38:10,865 INFO Epoch:42 train_loss:0.29295 +2025-04-19 10:38:26,952 INFO Epoch:42 val_res:0.370800 +2025-04-19 10:38:46,096 INFO Epoch:43 train_loss:0.29515 +2025-04-19 10:39:02,839 INFO Epoch:43 val_res:0.366200 +2025-04-19 10:39:21,837 INFO Epoch:44 train_loss:0.30553 +2025-04-19 10:39:37,622 INFO Epoch:44 val_res:0.368400 +2025-04-19 10:39:56,840 INFO Epoch:45 train_loss:0.29447 +2025-04-19 10:40:11,984 INFO Epoch:45 val_res:0.363000 +2025-04-19 10:40:30,921 INFO Epoch:46 train_loss:0.27758 +2025-04-19 10:40:46,850 INFO Epoch:46 val_res:0.360600 +2025-04-19 10:41:06,442 INFO Epoch:47 train_loss:0.27053 +2025-04-19 10:41:23,004 INFO Epoch:47 val_res:0.361200 +2025-04-19 10:41:41,407 INFO Epoch:48 train_loss:0.29209 +2025-04-19 10:41:57,697 INFO Epoch:48 val_res:0.355800 +2025-04-19 10:42:16,732 INFO Epoch:49 train_loss:0.28058 +2025-04-19 10:42:32,533 INFO Epoch:49 val_res:0.356200 +2025-04-19 10:42:50,931 INFO Epoch:50 train_loss:0.26971 +2025-04-19 10:43:06,505 INFO Epoch:50 val_res:0.363600 +2025-04-19 10:43:26,106 INFO Epoch:51 train_loss:0.26001 +2025-04-19 10:43:41,561 INFO Epoch:51 val_res:0.349800 +2025-04-19 10:44:01,499 INFO Epoch:52 train_loss:0.27234 +2025-04-19 10:44:17,261 INFO Epoch:52 val_res:0.355200 +2025-04-19 10:44:35,408 INFO Epoch:53 train_loss:0.32056 +2025-04-19 10:44:51,064 INFO Epoch:53 val_res:0.349600 +2025-04-19 10:45:09,388 INFO Epoch:54 train_loss:0.30033 +2025-04-19 10:45:25,306 INFO Epoch:54 val_res:0.351400 +2025-04-19 10:45:43,589 INFO Epoch:55 train_loss:0.25450 +2025-04-19 10:45:59,454 INFO Epoch:55 val_res:0.348000 +2025-04-19 10:46:17,536 INFO Epoch:56 train_loss:0.26282 +2025-04-19 10:46:33,368 INFO Epoch:56 val_res:0.342800 +2025-04-19 10:46:52,381 INFO Epoch:57 train_loss:0.29472 +2025-04-19 10:47:08,537 INFO Epoch:57 val_res:0.344400 +2025-04-19 10:47:26,497 INFO Epoch:58 train_loss:0.24883 +2025-04-19 10:47:41,890 INFO Epoch:58 val_res:0.346800 +2025-04-19 10:48:00,759 INFO Epoch:59 train_loss:0.25431 +2025-04-19 10:48:16,464 INFO Epoch:59 val_res:0.337200 +2025-04-19 10:48:35,420 INFO Epoch:60 train_loss:0.25293 +2025-04-19 10:48:50,498 INFO Epoch:60 val_res:0.340000 +2025-04-19 10:49:09,236 INFO Epoch:61 train_loss:0.24938 +2025-04-19 10:49:24,921 INFO Epoch:61 val_res:0.336400 +2025-04-19 10:49:43,697 INFO Epoch:62 train_loss:0.24087 +2025-04-19 10:49:59,718 INFO Epoch:62 val_res:0.334800 +2025-04-19 10:50:18,536 INFO Epoch:63 train_loss:0.26590 +2025-04-19 10:50:34,305 INFO Epoch:63 val_res:0.336600 +2025-04-19 10:50:52,740 INFO Epoch:64 train_loss:0.26487 +2025-04-19 10:51:08,328 INFO Epoch:64 val_res:0.340000 +2025-04-19 10:51:27,547 INFO Epoch:65 train_loss:0.24315 +2025-04-19 10:51:42,755 INFO Epoch:65 val_res:0.337600 +2025-04-19 10:52:01,291 INFO Epoch:66 train_loss:0.23474 +2025-04-19 10:52:17,217 INFO Epoch:66 val_res:0.337400 +2025-04-19 10:52:35,511 INFO Epoch:67 train_loss:0.23357 +2025-04-19 10:52:52,175 INFO Epoch:67 val_res:0.336800 +2025-04-19 10:53:10,491 INFO Epoch:68 train_loss:0.22911 +2025-04-19 10:53:27,362 INFO Epoch:68 val_res:0.335200 +2025-04-19 10:53:45,871 INFO Epoch:69 train_loss:0.22772 +2025-04-19 10:54:01,773 INFO Epoch:69 val_res:0.334800 +2025-04-19 10:54:20,744 INFO Epoch:70 train_loss:0.22792 +2025-04-19 10:54:36,512 INFO Epoch:70 val_res:0.335800 +2025-04-19 10:54:55,914 INFO Epoch:71 train_loss:0.21811 +2025-04-19 10:55:11,238 INFO Epoch:71 val_res:0.324000 +2025-04-19 10:55:30,160 INFO Epoch:72 train_loss:0.24543 +2025-04-19 10:55:46,272 INFO Epoch:72 val_res:0.329800 +2025-04-19 10:56:05,360 INFO Epoch:73 train_loss:0.22696 +2025-04-19 10:56:20,812 INFO Epoch:73 val_res:0.329200 +2025-04-19 10:56:38,818 INFO Epoch:74 train_loss:0.23320 +2025-04-19 10:56:53,662 INFO Epoch:74 val_res:0.327200 +2025-04-19 10:57:13,087 INFO Epoch:75 train_loss:0.24287 +2025-04-19 10:57:28,853 INFO Epoch:75 val_res:0.326200 +2025-04-19 10:57:46,287 INFO Epoch:76 train_loss:0.21605 +2025-04-19 10:58:01,165 INFO Epoch:76 val_res:0.330000 +2025-04-19 10:58:18,441 INFO Epoch:77 train_loss:0.26638 +2025-04-19 10:58:32,784 INFO Epoch:77 val_res:0.327000 +2025-04-19 10:58:50,258 INFO Epoch:78 train_loss:0.25347 +2025-04-19 10:59:04,531 INFO Epoch:78 val_res:0.317600 +2025-04-19 10:59:22,340 INFO Epoch:79 train_loss:0.23218 +2025-04-19 10:59:37,231 INFO Epoch:79 val_res:0.325800 +2025-04-19 10:59:54,400 INFO Epoch:80 train_loss:0.22814 +2025-04-19 11:00:08,702 INFO Epoch:80 val_res:0.324800 +2025-04-19 11:00:25,840 INFO Epoch:81 train_loss:0.25792 +2025-04-19 11:00:39,386 INFO Epoch:81 val_res:0.322600 +2025-04-19 11:00:56,323 INFO Epoch:82 train_loss:0.22396 +2025-04-19 11:01:10,849 INFO Epoch:82 val_res:0.320600 +2025-04-19 11:01:26,824 INFO Epoch:83 train_loss:0.23598 +2025-04-19 11:01:41,884 INFO Epoch:83 val_res:0.324000 +2025-04-19 11:01:58,475 INFO Epoch:84 train_loss:0.21843 +2025-04-19 11:02:12,668 INFO Epoch:84 val_res:0.319600 +2025-04-19 11:02:29,427 INFO Epoch:85 train_loss:0.23866 +2025-04-19 11:02:43,389 INFO Epoch:85 val_res:0.322200 +2025-04-19 11:02:59,883 INFO Epoch:86 train_loss:0.22565 +2025-04-19 11:03:14,245 INFO Epoch:86 val_res:0.321200 +2025-04-19 11:03:30,331 INFO Epoch:87 train_loss:0.22079 +2025-04-19 11:03:44,976 INFO Epoch:87 val_res:0.314600 +2025-04-19 11:04:01,023 INFO Epoch:88 train_loss:0.19507 +2025-04-19 11:04:15,583 INFO Epoch:88 val_res:0.315600 +2025-04-19 11:04:32,395 INFO Epoch:89 train_loss:0.19031 +2025-04-19 11:04:46,767 INFO Epoch:89 val_res:0.314800 +2025-04-19 11:05:03,475 INFO Epoch:90 train_loss:0.19463 +2025-04-19 11:05:17,811 INFO Epoch:90 val_res:0.314000 +2025-04-19 11:05:34,421 INFO Epoch:91 train_loss:0.19954 +2025-04-19 11:05:48,792 INFO Epoch:91 val_res:0.318200 +2025-04-19 11:06:05,943 INFO Epoch:92 train_loss:0.17521 +2025-04-19 11:06:20,293 INFO Epoch:92 val_res:0.312000 +2025-04-19 11:06:37,068 INFO Epoch:93 train_loss:0.18484 +2025-04-19 11:06:51,406 INFO Epoch:93 val_res:0.311000 +2025-04-19 11:07:08,207 INFO Epoch:94 train_loss:0.18767 +2025-04-19 11:07:23,006 INFO Epoch:94 val_res:0.307800 +2025-04-19 11:07:41,565 INFO Epoch:95 train_loss:0.17575 +2025-04-19 11:07:56,263 INFO Epoch:95 val_res:0.310000 +2025-04-19 11:08:15,544 INFO Epoch:96 train_loss:0.19795 +2025-04-19 11:08:30,029 INFO Epoch:96 val_res:0.317200 +2025-04-19 11:08:47,140 INFO Epoch:97 train_loss:0.23277 +2025-04-19 11:09:01,319 INFO Epoch:97 val_res:0.310400 +2025-04-19 11:09:17,609 INFO Epoch:98 train_loss:0.23285 +2025-04-19 11:09:32,432 INFO Epoch:98 val_res:0.308600 +2025-04-19 11:09:49,282 INFO Epoch:99 train_loss:0.20130 +2025-04-19 11:10:03,508 INFO Epoch:99 val_res:0.308600 +2025-04-19 11:10:04,228 INFO ===================================== +2025-04-19 11:10:04,229 INFO Start testing... +2025-04-19 11:10:04,229 INFO ===================================== +2025-04-19 11:10:19,391 INFO Incremental step 9 Testing res: 0.447400 +2025-04-19 11:10:19,396 INFO forgetting: 0.166000 +2025-04-19 11:10:19,397 INFO Average Accuracy: 0.610765 +2025-04-19 11:10:19,397 INFO Average Forgetting: 0.140845 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..e80be51e59d4fde4a88960179509b8e8d1c916b6 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..a00ab41718984784eb867f771a6eba79366f2176 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..d754ee92b61993957c0c6b6a2ec73fa7bf6e7b81 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..5c916938a7bb7cfcaadb316835f60c383142bc90 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..db7a7c0bcde4763e63fd24237dafcd079a4695ec Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..d5dbf85d59655b5f668278954db8bc50c831cb5c Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..aeee596a1737e6687a080425db3eb270f73f7c82 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..1ff2311551546cad5fe6aca8fd9c90f7f25ed42b Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..a9debd14fcf225467fb7ef9ee9e3eabce39e5d9f Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..b0717f3ecfa3d2b0794ea0212533bb00668ca8af Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..5fc645296919a865c1bef86552bea3e8831d33cd --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99aff3163abd8f2b1642bac9be89046b9e272169689d01ce3d4430f6d1452e83 +size 114105937 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..771f44a0f549e7c8053d2cef84628796be4a10ad --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e819b5a74dbf7cebd39efccb45324fc30b0461a015d664c49a6964e9e7a84ad0 +size 114161233 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..0f65fd85538e955926e36c1fc4ccdf2cd2f5d59f --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a3bc126ff1213b27f48a271894f28009fdbedc231274c3671c8b8b467446e9 +size 114216721 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..d4a7c036420153e452b79478dd1915b9914c4401 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:361090c51648d411dc4c7f7164830ad8e830a91315be354d898c70f1b57336b8 +size 114272017 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..15694d1eed37dd2245b49d821f948ae7ab19ed1f --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d881fee2b2df8e0725b6b906b8a91311aaaff9338e16ad41556703cb4ce59e4 +size 114327313 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/train.log b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..daa7dc69fe42c7c685b890d140570c717a905ba8 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_False-seed_0/train.log @@ -0,0 +1,1131 @@ +2025-04-18 01:59:24,049 INFO Namespace(class_num_per_step=6, dataset='ksounds', e_prompt=False, infer_batch_size=128, inverse=False, inverse_ends=100, inverse_starts=0, lr=0.01, lr_decay=False, max_epoches=100, milestones=[100], modality='audio-visual', num_classes=30, num_workers=4, prompt_dim=768, seed=0, train_batch_size=256, transfer=False, warm=False, weight_decay=0.0001) +2025-04-18 01:59:24,050 INFO Training start time: 2025-04-18 01:59:24.050290 +2025-04-18 01:59:25,503 INFO Incremental step: 0 +2025-04-18 02:02:51,097 INFO Epoch:0 train_loss:1.64542 +2025-04-18 02:03:15,307 INFO Epoch:0 val_res:0.416446 +2025-04-18 02:03:15,307 INFO Saving best model at Epoch 0 +2025-04-18 02:03:36,735 INFO Epoch:1 train_loss:1.32154 +2025-04-18 02:03:39,029 INFO Epoch:1 val_res:0.541114 +2025-04-18 02:03:39,029 INFO Saving best model at Epoch 1 +2025-04-18 02:03:53,291 INFO Epoch:2 train_loss:1.13255 +2025-04-18 02:03:55,434 INFO Epoch:2 val_res:0.652520 +2025-04-18 02:03:55,434 INFO Saving best model at Epoch 2 +2025-04-18 02:04:10,324 INFO Epoch:3 train_loss:0.96427 +2025-04-18 02:04:12,458 INFO Epoch:3 val_res:0.676393 +2025-04-18 02:04:12,459 INFO Saving best model at Epoch 3 +2025-04-18 02:04:27,129 INFO Epoch:4 train_loss:0.83648 +2025-04-18 02:04:29,744 INFO Epoch:4 val_res:0.700265 +2025-04-18 02:04:29,744 INFO Saving best model at Epoch 4 +2025-04-18 02:04:46,397 INFO Epoch:5 train_loss:0.75054 +2025-04-18 02:04:49,040 INFO Epoch:5 val_res:0.734748 +2025-04-18 02:04:49,040 INFO Saving best model at Epoch 5 +2025-04-18 02:05:04,474 INFO Epoch:6 train_loss:0.69696 +2025-04-18 02:05:06,776 INFO Epoch:6 val_res:0.745358 +2025-04-18 02:05:06,776 INFO Saving best model at Epoch 6 +2025-04-18 02:05:21,089 INFO Epoch:7 train_loss:0.64903 +2025-04-18 02:05:23,488 INFO Epoch:7 val_res:0.785146 +2025-04-18 02:05:23,488 INFO Saving best model at Epoch 7 +2025-04-18 02:05:38,466 INFO Epoch:8 train_loss:0.59788 +2025-04-18 02:05:40,797 INFO Epoch:8 val_res:0.793103 +2025-04-18 02:05:40,797 INFO Saving best model at Epoch 8 +2025-04-18 02:05:59,312 INFO Epoch:9 train_loss:0.54790 +2025-04-18 02:06:02,116 INFO Epoch:9 val_res:0.790451 +2025-04-18 02:06:23,984 INFO Epoch:10 train_loss:0.51499 +2025-04-18 02:06:26,534 INFO Epoch:10 val_res:0.806366 +2025-04-18 02:06:26,535 INFO Saving best model at Epoch 10 +2025-04-18 02:07:03,326 INFO Epoch:11 train_loss:0.49086 +2025-04-18 02:07:05,750 INFO Epoch:11 val_res:0.819629 +2025-04-18 02:07:05,751 INFO Saving best model at Epoch 11 +2025-04-18 02:07:23,377 INFO Epoch:12 train_loss:0.47041 +2025-04-18 02:07:25,829 INFO Epoch:12 val_res:0.819629 +2025-04-18 02:07:42,268 INFO Epoch:13 train_loss:0.45523 +2025-04-18 02:07:44,636 INFO Epoch:13 val_res:0.785146 +2025-04-18 02:07:58,955 INFO Epoch:14 train_loss:0.44889 +2025-04-18 02:08:01,564 INFO Epoch:14 val_res:0.809019 +2025-04-18 02:08:16,336 INFO Epoch:15 train_loss:0.42421 +2025-04-18 02:08:18,756 INFO Epoch:15 val_res:0.870027 +2025-04-18 02:08:18,757 INFO Saving best model at Epoch 15 +2025-04-18 02:08:36,272 INFO Epoch:16 train_loss:0.38365 +2025-04-18 02:08:38,686 INFO Epoch:16 val_res:0.848806 +2025-04-18 02:08:53,219 INFO Epoch:17 train_loss:0.37910 +2025-04-18 02:08:55,577 INFO Epoch:17 val_res:0.864721 +2025-04-18 02:09:12,804 INFO Epoch:18 train_loss:0.39714 +2025-04-18 02:09:15,440 INFO Epoch:18 val_res:0.870027 +2025-04-18 02:09:31,785 INFO Epoch:19 train_loss:0.38865 +2025-04-18 02:09:34,877 INFO Epoch:19 val_res:0.875332 +2025-04-18 02:09:34,877 INFO Saving best model at Epoch 19 +2025-04-18 02:09:52,841 INFO Epoch:20 train_loss:0.34805 +2025-04-18 02:09:55,414 INFO Epoch:20 val_res:0.862069 +2025-04-18 02:10:09,843 INFO Epoch:21 train_loss:0.35138 +2025-04-18 02:10:12,822 INFO Epoch:21 val_res:0.859416 +2025-04-18 02:10:27,274 INFO Epoch:22 train_loss:0.31694 +2025-04-18 02:10:29,786 INFO Epoch:22 val_res:0.883289 +2025-04-18 02:10:29,786 INFO Saving best model at Epoch 22 +2025-04-18 02:10:45,554 INFO Epoch:23 train_loss:0.30517 +2025-04-18 02:10:48,103 INFO Epoch:23 val_res:0.870027 +2025-04-18 02:11:04,492 INFO Epoch:24 train_loss:0.31528 +2025-04-18 02:11:08,140 INFO Epoch:24 val_res:0.877984 +2025-04-18 02:11:21,584 INFO Epoch:25 train_loss:0.32537 +2025-04-18 02:11:24,134 INFO Epoch:25 val_res:0.867374 +2025-04-18 02:11:36,751 INFO Epoch:26 train_loss:0.30163 +2025-04-18 02:11:39,155 INFO Epoch:26 val_res:0.885942 +2025-04-18 02:11:39,156 INFO Saving best model at Epoch 26 +2025-04-18 02:11:57,021 INFO Epoch:27 train_loss:0.29313 +2025-04-18 02:11:59,632 INFO Epoch:27 val_res:0.888594 +2025-04-18 02:11:59,632 INFO Saving best model at Epoch 27 +2025-04-18 02:12:16,138 INFO Epoch:28 train_loss:0.29709 +2025-04-18 02:12:18,759 INFO Epoch:28 val_res:0.851459 +2025-04-18 02:12:34,917 INFO Epoch:29 train_loss:0.29179 +2025-04-18 02:12:37,240 INFO Epoch:29 val_res:0.854111 +2025-04-18 02:12:50,085 INFO Epoch:30 train_loss:0.30165 +2025-04-18 02:12:52,441 INFO Epoch:30 val_res:0.888594 +2025-04-18 02:13:06,229 INFO Epoch:31 train_loss:0.27148 +2025-04-18 02:13:09,394 INFO Epoch:31 val_res:0.891247 +2025-04-18 02:13:09,394 INFO Saving best model at Epoch 31 +2025-04-18 02:13:29,878 INFO Epoch:32 train_loss:0.26907 +2025-04-18 02:13:32,547 INFO Epoch:32 val_res:0.877984 +2025-04-18 02:13:45,584 INFO Epoch:33 train_loss:0.26320 +2025-04-18 02:13:47,993 INFO Epoch:33 val_res:0.883289 +2025-04-18 02:14:01,158 INFO Epoch:34 train_loss:0.25309 +2025-04-18 02:14:04,579 INFO Epoch:34 val_res:0.901857 +2025-04-18 02:14:04,580 INFO Saving best model at Epoch 34 +2025-04-18 02:14:21,147 INFO Epoch:35 train_loss:0.26539 +2025-04-18 02:14:23,662 INFO Epoch:35 val_res:0.891247 +2025-04-18 02:14:37,276 INFO Epoch:36 train_loss:0.25618 +2025-04-18 02:14:39,568 INFO Epoch:36 val_res:0.893899 +2025-04-18 02:14:54,088 INFO Epoch:37 train_loss:0.24903 +2025-04-18 02:14:56,416 INFO Epoch:37 val_res:0.885942 +2025-04-18 02:15:08,475 INFO Epoch:38 train_loss:0.27117 +2025-04-18 02:15:10,721 INFO Epoch:38 val_res:0.907162 +2025-04-18 02:15:10,721 INFO Saving best model at Epoch 38 +2025-04-18 02:15:27,119 INFO Epoch:39 train_loss:0.24389 +2025-04-18 02:15:29,861 INFO Epoch:39 val_res:0.896552 +2025-04-18 02:15:43,483 INFO Epoch:40 train_loss:0.24607 +2025-04-18 02:15:45,749 INFO Epoch:40 val_res:0.872679 +2025-04-18 02:15:57,822 INFO Epoch:41 train_loss:0.24973 +2025-04-18 02:16:00,029 INFO Epoch:41 val_res:0.888594 +2025-04-18 02:16:14,702 INFO Epoch:42 train_loss:0.25650 +2025-04-18 02:16:17,156 INFO Epoch:42 val_res:0.883289 +2025-04-18 02:16:29,433 INFO Epoch:43 train_loss:0.23776 +2025-04-18 02:16:31,886 INFO Epoch:43 val_res:0.893899 +2025-04-18 02:16:43,663 INFO Epoch:44 train_loss:0.26604 +2025-04-18 02:16:45,980 INFO Epoch:44 val_res:0.896552 +2025-04-18 02:17:02,641 INFO Epoch:45 train_loss:0.22747 +2025-04-18 02:17:05,227 INFO Epoch:45 val_res:0.893899 +2025-04-18 02:17:17,617 INFO Epoch:46 train_loss:0.21294 +2025-04-18 02:17:19,994 INFO Epoch:46 val_res:0.912467 +2025-04-18 02:17:19,995 INFO Saving best model at Epoch 46 +2025-04-18 02:17:36,368 INFO Epoch:47 train_loss:0.21633 +2025-04-18 02:17:39,784 INFO Epoch:47 val_res:0.907162 +2025-04-18 02:17:54,147 INFO Epoch:48 train_loss:0.22107 +2025-04-18 02:17:56,682 INFO Epoch:48 val_res:0.907162 +2025-04-18 02:18:09,453 INFO Epoch:49 train_loss:0.21137 +2025-04-18 02:18:12,004 INFO Epoch:49 val_res:0.859416 +2025-04-18 02:18:27,361 INFO Epoch:50 train_loss:0.21941 +2025-04-18 02:18:29,752 INFO Epoch:50 val_res:0.912467 +2025-04-18 02:18:44,032 INFO Epoch:51 train_loss:0.20540 +2025-04-18 02:18:46,720 INFO Epoch:51 val_res:0.885942 +2025-04-18 02:19:03,998 INFO Epoch:52 train_loss:0.22734 +2025-04-18 02:19:07,245 INFO Epoch:52 val_res:0.896552 +2025-04-18 02:19:27,940 INFO Epoch:53 train_loss:0.22323 +2025-04-18 02:19:31,062 INFO Epoch:53 val_res:0.917772 +2025-04-18 02:19:31,062 INFO Saving best model at Epoch 53 +2025-04-18 02:19:56,179 INFO Epoch:54 train_loss:0.20772 +2025-04-18 02:19:59,557 INFO Epoch:54 val_res:0.901857 +2025-04-18 02:20:17,386 INFO Epoch:55 train_loss:0.20005 +2025-04-18 02:20:19,962 INFO Epoch:55 val_res:0.904509 +2025-04-18 02:20:35,083 INFO Epoch:56 train_loss:0.19445 +2025-04-18 02:20:37,247 INFO Epoch:56 val_res:0.872679 +2025-04-18 02:20:51,534 INFO Epoch:57 train_loss:0.21444 +2025-04-18 02:20:54,281 INFO Epoch:57 val_res:0.915119 +2025-04-18 02:21:08,559 INFO Epoch:58 train_loss:0.19691 +2025-04-18 02:21:11,646 INFO Epoch:58 val_res:0.891247 +2025-04-18 02:21:29,370 INFO Epoch:59 train_loss:0.19408 +2025-04-18 02:21:31,829 INFO Epoch:59 val_res:0.883289 +2025-04-18 02:21:48,292 INFO Epoch:60 train_loss:0.20830 +2025-04-18 02:21:50,827 INFO Epoch:60 val_res:0.915119 +2025-04-18 02:22:06,183 INFO Epoch:61 train_loss:0.21103 +2025-04-18 02:22:08,941 INFO Epoch:61 val_res:0.904509 +2025-04-18 02:22:22,651 INFO Epoch:62 train_loss:0.18774 +2025-04-18 02:22:25,076 INFO Epoch:62 val_res:0.912467 +2025-04-18 02:22:38,766 INFO Epoch:63 train_loss:0.17338 +2025-04-18 02:22:41,374 INFO Epoch:63 val_res:0.915119 +2025-04-18 02:22:55,628 INFO Epoch:64 train_loss:0.17824 +2025-04-18 02:22:58,264 INFO Epoch:64 val_res:0.904509 +2025-04-18 02:23:12,237 INFO Epoch:65 train_loss:0.18851 +2025-04-18 02:23:14,960 INFO Epoch:65 val_res:0.928382 +2025-04-18 02:23:14,960 INFO Saving best model at Epoch 65 +2025-04-18 02:23:30,020 INFO Epoch:66 train_loss:0.19319 +2025-04-18 02:23:32,677 INFO Epoch:66 val_res:0.912467 +2025-04-18 02:23:47,542 INFO Epoch:67 train_loss:0.21070 +2025-04-18 02:23:50,135 INFO Epoch:67 val_res:0.867374 +2025-04-18 02:24:03,822 INFO Epoch:68 train_loss:0.20050 +2025-04-18 02:24:06,213 INFO Epoch:68 val_res:0.909814 +2025-04-18 02:24:20,005 INFO Epoch:69 train_loss:0.18067 +2025-04-18 02:24:22,510 INFO Epoch:69 val_res:0.931035 +2025-04-18 02:24:22,510 INFO Saving best model at Epoch 69 +2025-04-18 02:24:38,059 INFO Epoch:70 train_loss:0.16850 +2025-04-18 02:24:40,437 INFO Epoch:70 val_res:0.891247 +2025-04-18 02:24:54,752 INFO Epoch:71 train_loss:0.16374 +2025-04-18 02:24:57,055 INFO Epoch:71 val_res:0.917772 +2025-04-18 02:25:11,537 INFO Epoch:72 train_loss:0.15190 +2025-04-18 02:25:14,249 INFO Epoch:72 val_res:0.907162 +2025-04-18 02:25:29,848 INFO Epoch:73 train_loss:0.15096 +2025-04-18 02:25:32,532 INFO Epoch:73 val_res:0.917772 +2025-04-18 02:25:45,855 INFO Epoch:74 train_loss:0.14460 +2025-04-18 02:25:48,306 INFO Epoch:74 val_res:0.920424 +2025-04-18 02:26:02,864 INFO Epoch:75 train_loss:0.14374 +2025-04-18 02:26:05,196 INFO Epoch:75 val_res:0.907162 +2025-04-18 02:26:18,608 INFO Epoch:76 train_loss:0.16272 +2025-04-18 02:26:21,002 INFO Epoch:76 val_res:0.928382 +2025-04-18 02:26:35,575 INFO Epoch:77 train_loss:0.15476 +2025-04-18 02:26:38,566 INFO Epoch:77 val_res:0.896552 +2025-04-18 02:26:52,960 INFO Epoch:78 train_loss:0.16294 +2025-04-18 02:26:55,565 INFO Epoch:78 val_res:0.893899 +2025-04-18 02:27:07,657 INFO Epoch:79 train_loss:0.15431 +2025-04-18 02:27:10,080 INFO Epoch:79 val_res:0.925729 +2025-04-18 02:27:22,611 INFO Epoch:80 train_loss:0.14898 +2025-04-18 02:27:25,064 INFO Epoch:80 val_res:0.920424 +2025-04-18 02:27:38,250 INFO Epoch:81 train_loss:0.14896 +2025-04-18 02:27:40,634 INFO Epoch:81 val_res:0.917772 +2025-04-18 02:27:56,231 INFO Epoch:82 train_loss:0.16762 +2025-04-18 02:27:58,718 INFO Epoch:82 val_res:0.896552 +2025-04-18 02:28:12,625 INFO Epoch:83 train_loss:0.14607 +2025-04-18 02:28:14,971 INFO Epoch:83 val_res:0.915119 +2025-04-18 02:28:28,743 INFO Epoch:84 train_loss:0.13220 +2025-04-18 02:28:31,242 INFO Epoch:84 val_res:0.923077 +2025-04-18 02:28:43,871 INFO Epoch:85 train_loss:0.15274 +2025-04-18 02:28:46,109 INFO Epoch:85 val_res:0.928382 +2025-04-18 02:28:58,633 INFO Epoch:86 train_loss:0.14612 +2025-04-18 02:29:01,050 INFO Epoch:86 val_res:0.907162 +2025-04-18 02:29:15,351 INFO Epoch:87 train_loss:0.12956 +2025-04-18 02:29:17,881 INFO Epoch:87 val_res:0.920424 +2025-04-18 02:29:30,908 INFO Epoch:88 train_loss:0.12641 +2025-04-18 02:29:33,354 INFO Epoch:88 val_res:0.933687 +2025-04-18 02:29:33,355 INFO Saving best model at Epoch 88 +2025-04-18 02:29:48,874 INFO Epoch:89 train_loss:0.14569 +2025-04-18 02:29:51,272 INFO Epoch:89 val_res:0.872679 +2025-04-18 02:30:05,871 INFO Epoch:90 train_loss:0.17245 +2025-04-18 02:30:08,312 INFO Epoch:90 val_res:0.917772 +2025-04-18 02:30:21,514 INFO Epoch:91 train_loss:0.16496 +2025-04-18 02:30:23,672 INFO Epoch:91 val_res:0.907162 +2025-04-18 02:30:35,528 INFO Epoch:92 train_loss:0.13284 +2025-04-18 02:30:37,803 INFO Epoch:92 val_res:0.901857 +2025-04-18 02:30:49,834 INFO Epoch:93 train_loss:0.14794 +2025-04-18 02:30:52,026 INFO Epoch:93 val_res:0.909814 +2025-04-18 02:31:04,787 INFO Epoch:94 train_loss:0.13333 +2025-04-18 02:31:07,376 INFO Epoch:94 val_res:0.933687 +2025-04-18 02:31:20,834 INFO Epoch:95 train_loss:0.12561 +2025-04-18 02:31:23,345 INFO Epoch:95 val_res:0.923077 +2025-04-18 02:31:37,591 INFO Epoch:96 train_loss:0.12251 +2025-04-18 02:31:39,879 INFO Epoch:96 val_res:0.912467 +2025-04-18 02:31:53,589 INFO Epoch:97 train_loss:0.14077 +2025-04-18 02:31:55,903 INFO Epoch:97 val_res:0.917772 +2025-04-18 02:32:09,268 INFO Epoch:98 train_loss:0.13342 +2025-04-18 02:32:11,680 INFO Epoch:98 val_res:0.904509 +2025-04-18 02:32:25,589 INFO Epoch:99 train_loss:0.12991 +2025-04-18 02:32:28,107 INFO Epoch:99 val_res:0.923077 +2025-04-18 02:32:28,945 INFO ===================================== +2025-04-18 02:32:28,946 INFO Start testing... +2025-04-18 02:32:28,946 INFO ===================================== +2025-04-18 02:32:32,886 INFO Incremental step 0 Testing res: 0.905914 +2025-04-18 02:32:32,889 INFO Incremental step: 1 +2025-04-18 02:35:07,130 INFO Epoch:0 train_loss:2.15652 +2025-04-18 02:35:26,211 INFO Epoch:0 val_res:0.425974 +2025-04-18 02:35:26,211 INFO Saving best model at Epoch 0 +2025-04-18 02:35:46,403 INFO Epoch:1 train_loss:3.02634 +2025-04-18 02:35:50,219 INFO Epoch:1 val_res:0.406494 +2025-04-18 02:36:04,011 INFO Epoch:2 train_loss:1.52774 +2025-04-18 02:36:07,781 INFO Epoch:2 val_res:0.423377 +2025-04-18 02:36:23,292 INFO Epoch:3 train_loss:1.54036 +2025-04-18 02:36:28,508 INFO Epoch:3 val_res:0.385714 +2025-04-18 02:36:45,032 INFO Epoch:4 train_loss:1.65054 +2025-04-18 02:36:49,449 INFO Epoch:4 val_res:0.438961 +2025-04-18 02:36:49,449 INFO Saving best model at Epoch 4 +2025-04-18 02:37:06,850 INFO Epoch:5 train_loss:1.21225 +2025-04-18 02:37:11,256 INFO Epoch:5 val_res:0.428571 +2025-04-18 02:37:27,396 INFO Epoch:6 train_loss:1.23457 +2025-04-18 02:37:31,816 INFO Epoch:6 val_res:0.436364 +2025-04-18 02:37:47,457 INFO Epoch:7 train_loss:1.46169 +2025-04-18 02:37:51,665 INFO Epoch:7 val_res:0.442857 +2025-04-18 02:37:51,666 INFO Saving best model at Epoch 7 +2025-04-18 02:38:07,144 INFO Epoch:8 train_loss:1.19260 +2025-04-18 02:38:10,594 INFO Epoch:8 val_res:0.461039 +2025-04-18 02:38:10,595 INFO Saving best model at Epoch 8 +2025-04-18 02:38:25,564 INFO Epoch:9 train_loss:0.92824 +2025-04-18 02:38:29,014 INFO Epoch:9 val_res:0.468831 +2025-04-18 02:38:29,015 INFO Saving best model at Epoch 9 +2025-04-18 02:38:43,525 INFO Epoch:10 train_loss:0.77690 +2025-04-18 02:38:47,021 INFO Epoch:10 val_res:0.480519 +2025-04-18 02:38:47,021 INFO Saving best model at Epoch 10 +2025-04-18 02:39:03,290 INFO Epoch:11 train_loss:0.74117 +2025-04-18 02:39:06,779 INFO Epoch:11 val_res:0.507792 +2025-04-18 02:39:06,779 INFO Saving best model at Epoch 11 +2025-04-18 02:39:21,403 INFO Epoch:12 train_loss:0.72200 +2025-04-18 02:39:24,736 INFO Epoch:12 val_res:0.481818 +2025-04-18 02:39:39,561 INFO Epoch:13 train_loss:0.70755 +2025-04-18 02:39:42,932 INFO Epoch:13 val_res:0.501299 +2025-04-18 02:39:56,409 INFO Epoch:14 train_loss:0.78020 +2025-04-18 02:39:59,779 INFO Epoch:14 val_res:0.512987 +2025-04-18 02:39:59,779 INFO Saving best model at Epoch 14 +2025-04-18 02:40:16,549 INFO Epoch:15 train_loss:0.72635 +2025-04-18 02:40:20,932 INFO Epoch:15 val_res:0.515584 +2025-04-18 02:40:20,933 INFO Saving best model at Epoch 15 +2025-04-18 02:40:36,996 INFO Epoch:16 train_loss:0.69970 +2025-04-18 02:40:40,557 INFO Epoch:16 val_res:0.518182 +2025-04-18 02:40:40,557 INFO Saving best model at Epoch 16 +2025-04-18 02:40:57,147 INFO Epoch:17 train_loss:0.67688 +2025-04-18 02:41:01,164 INFO Epoch:17 val_res:0.531169 +2025-04-18 02:41:01,164 INFO Saving best model at Epoch 17 +2025-04-18 02:41:16,627 INFO Epoch:18 train_loss:0.64622 +2025-04-18 02:41:20,627 INFO Epoch:18 val_res:0.527273 +2025-04-18 02:41:34,133 INFO Epoch:19 train_loss:0.69554 +2025-04-18 02:41:38,229 INFO Epoch:19 val_res:0.511688 +2025-04-18 02:41:51,286 INFO Epoch:20 train_loss:0.66944 +2025-04-18 02:41:54,646 INFO Epoch:20 val_res:0.518182 +2025-04-18 02:42:07,767 INFO Epoch:21 train_loss:0.66249 +2025-04-18 02:42:11,422 INFO Epoch:21 val_res:0.523377 +2025-04-18 02:42:25,566 INFO Epoch:22 train_loss:0.59467 +2025-04-18 02:42:29,319 INFO Epoch:22 val_res:0.524675 +2025-04-18 02:42:43,111 INFO Epoch:23 train_loss:0.61504 +2025-04-18 02:42:46,630 INFO Epoch:23 val_res:0.559740 +2025-04-18 02:42:46,630 INFO Saving best model at Epoch 23 +2025-04-18 02:43:03,684 INFO Epoch:24 train_loss:0.59750 +2025-04-18 02:43:07,324 INFO Epoch:24 val_res:0.518182 +2025-04-18 02:43:21,697 INFO Epoch:25 train_loss:0.60976 +2025-04-18 02:43:25,481 INFO Epoch:25 val_res:0.553247 +2025-04-18 02:43:40,326 INFO Epoch:26 train_loss:0.59851 +2025-04-18 02:43:43,737 INFO Epoch:26 val_res:0.551948 +2025-04-18 02:43:56,831 INFO Epoch:27 train_loss:0.60376 +2025-04-18 02:44:00,265 INFO Epoch:27 val_res:0.548052 +2025-04-18 02:44:13,320 INFO Epoch:28 train_loss:0.57603 +2025-04-18 02:44:17,960 INFO Epoch:28 val_res:0.561039 +2025-04-18 02:44:17,961 INFO Saving best model at Epoch 28 +2025-04-18 02:44:32,632 INFO Epoch:29 train_loss:0.54320 +2025-04-18 02:44:36,409 INFO Epoch:29 val_res:0.570130 +2025-04-18 02:44:36,410 INFO Saving best model at Epoch 29 +2025-04-18 02:44:52,677 INFO Epoch:30 train_loss:0.57905 +2025-04-18 02:44:57,351 INFO Epoch:30 val_res:0.589610 +2025-04-18 02:44:57,352 INFO Saving best model at Epoch 30 +2025-04-18 02:45:12,475 INFO Epoch:31 train_loss:0.61319 +2025-04-18 02:45:15,804 INFO Epoch:31 val_res:0.577922 +2025-04-18 02:45:28,565 INFO Epoch:32 train_loss:0.57361 +2025-04-18 02:45:32,707 INFO Epoch:32 val_res:0.579221 +2025-04-18 02:45:46,523 INFO Epoch:33 train_loss:0.54287 +2025-04-18 02:45:50,609 INFO Epoch:33 val_res:0.562338 +2025-04-18 02:46:06,088 INFO Epoch:34 train_loss:0.54880 +2025-04-18 02:46:10,027 INFO Epoch:34 val_res:0.579221 +2025-04-18 02:46:24,626 INFO Epoch:35 train_loss:0.53745 +2025-04-18 02:46:28,411 INFO Epoch:35 val_res:0.574026 +2025-04-18 02:46:44,102 INFO Epoch:36 train_loss:0.54481 +2025-04-18 02:46:47,707 INFO Epoch:36 val_res:0.575325 +2025-04-18 02:47:03,625 INFO Epoch:37 train_loss:0.48876 +2025-04-18 02:47:07,217 INFO Epoch:37 val_res:0.602597 +2025-04-18 02:47:07,217 INFO Saving best model at Epoch 37 +2025-04-18 02:47:23,852 INFO Epoch:38 train_loss:0.51117 +2025-04-18 02:47:28,184 INFO Epoch:38 val_res:0.579221 +2025-04-18 02:47:43,917 INFO Epoch:39 train_loss:0.58087 +2025-04-18 02:47:47,728 INFO Epoch:39 val_res:0.576623 +2025-04-18 02:48:02,033 INFO Epoch:40 train_loss:0.58672 +2025-04-18 02:48:06,173 INFO Epoch:40 val_res:0.587013 +2025-04-18 02:48:20,844 INFO Epoch:41 train_loss:0.52372 +2025-04-18 02:48:24,507 INFO Epoch:41 val_res:0.587013 +2025-04-18 02:48:39,608 INFO Epoch:42 train_loss:0.57897 +2025-04-18 02:48:44,580 INFO Epoch:42 val_res:0.588312 +2025-04-18 02:49:00,228 INFO Epoch:43 train_loss:0.60716 +2025-04-18 02:49:03,941 INFO Epoch:43 val_res:0.579221 +2025-04-18 02:49:18,138 INFO Epoch:44 train_loss:0.56262 +2025-04-18 02:49:22,737 INFO Epoch:44 val_res:0.624675 +2025-04-18 02:49:22,738 INFO Saving best model at Epoch 44 +2025-04-18 02:49:39,298 INFO Epoch:45 train_loss:0.51284 +2025-04-18 02:49:42,890 INFO Epoch:45 val_res:0.590909 +2025-04-18 02:49:58,198 INFO Epoch:46 train_loss:0.48660 +2025-04-18 02:50:02,556 INFO Epoch:46 val_res:0.575325 +2025-04-18 02:50:16,742 INFO Epoch:47 train_loss:0.48995 +2025-04-18 02:50:20,457 INFO Epoch:47 val_res:0.601299 +2025-04-18 02:50:35,102 INFO Epoch:48 train_loss:0.47423 +2025-04-18 02:50:39,838 INFO Epoch:48 val_res:0.611688 +2025-04-18 02:50:54,265 INFO Epoch:49 train_loss:0.46393 +2025-04-18 02:50:57,956 INFO Epoch:49 val_res:0.598701 +2025-04-18 02:51:11,566 INFO Epoch:50 train_loss:0.50766 +2025-04-18 02:51:15,698 INFO Epoch:50 val_res:0.625974 +2025-04-18 02:51:15,698 INFO Saving best model at Epoch 50 +2025-04-18 02:51:34,414 INFO Epoch:51 train_loss:0.48850 +2025-04-18 02:51:38,337 INFO Epoch:51 val_res:0.614286 +2025-04-18 02:51:53,367 INFO Epoch:52 train_loss:0.45197 +2025-04-18 02:51:58,221 INFO Epoch:52 val_res:0.612987 +2025-04-18 02:52:13,300 INFO Epoch:53 train_loss:0.49581 +2025-04-18 02:52:16,856 INFO Epoch:53 val_res:0.594805 +2025-04-18 02:52:31,518 INFO Epoch:54 train_loss:0.45955 +2025-04-18 02:52:36,684 INFO Epoch:54 val_res:0.612987 +2025-04-18 02:52:54,374 INFO Epoch:55 train_loss:0.43677 +2025-04-18 02:52:58,450 INFO Epoch:55 val_res:0.597403 +2025-04-18 02:53:12,401 INFO Epoch:56 train_loss:0.43536 +2025-04-18 02:53:16,145 INFO Epoch:56 val_res:0.625974 +2025-04-18 02:53:32,842 INFO Epoch:57 train_loss:0.42788 +2025-04-18 02:53:37,405 INFO Epoch:57 val_res:0.611688 +2025-04-18 02:53:52,902 INFO Epoch:58 train_loss:0.44340 +2025-04-18 02:53:56,344 INFO Epoch:58 val_res:0.633766 +2025-04-18 02:53:56,344 INFO Saving best model at Epoch 58 +2025-04-18 02:54:17,105 INFO Epoch:59 train_loss:0.44168 +2025-04-18 02:54:21,279 INFO Epoch:59 val_res:0.629870 +2025-04-18 02:54:36,212 INFO Epoch:60 train_loss:0.45654 +2025-04-18 02:54:40,276 INFO Epoch:60 val_res:0.610390 +2025-04-18 02:54:53,828 INFO Epoch:61 train_loss:0.48033 +2025-04-18 02:54:57,456 INFO Epoch:61 val_res:0.623377 +2025-04-18 02:55:10,362 INFO Epoch:62 train_loss:0.46457 +2025-04-18 02:55:13,881 INFO Epoch:62 val_res:0.597403 +2025-04-18 02:55:28,413 INFO Epoch:63 train_loss:0.41696 +2025-04-18 02:55:31,822 INFO Epoch:63 val_res:0.610390 +2025-04-18 02:55:44,683 INFO Epoch:64 train_loss:0.49895 +2025-04-18 02:55:48,195 INFO Epoch:64 val_res:0.597403 +2025-04-18 02:56:02,330 INFO Epoch:65 train_loss:0.44816 +2025-04-18 02:56:06,385 INFO Epoch:65 val_res:0.624675 +2025-04-18 02:56:20,015 INFO Epoch:66 train_loss:0.44757 +2025-04-18 02:56:23,456 INFO Epoch:66 val_res:0.622078 +2025-04-18 02:56:36,219 INFO Epoch:67 train_loss:0.43293 +2025-04-18 02:56:39,740 INFO Epoch:67 val_res:0.611688 +2025-04-18 02:56:54,777 INFO Epoch:68 train_loss:0.41738 +2025-04-18 02:56:58,233 INFO Epoch:68 val_res:0.649351 +2025-04-18 02:56:58,233 INFO Saving best model at Epoch 68 +2025-04-18 02:57:12,390 INFO Epoch:69 train_loss:0.42792 +2025-04-18 02:57:16,226 INFO Epoch:69 val_res:0.653247 +2025-04-18 02:57:16,226 INFO Saving best model at Epoch 69 +2025-04-18 02:57:34,453 INFO Epoch:70 train_loss:0.43794 +2025-04-18 02:57:38,207 INFO Epoch:70 val_res:0.637662 +2025-04-18 02:57:51,926 INFO Epoch:71 train_loss:0.42924 +2025-04-18 02:57:55,716 INFO Epoch:71 val_res:0.628571 +2025-04-18 02:58:09,422 INFO Epoch:72 train_loss:0.44045 +2025-04-18 02:58:14,098 INFO Epoch:72 val_res:0.615584 +2025-04-18 02:58:26,980 INFO Epoch:73 train_loss:0.44152 +2025-04-18 02:58:30,884 INFO Epoch:73 val_res:0.624675 +2025-04-18 02:58:43,855 INFO Epoch:74 train_loss:0.41389 +2025-04-18 02:58:47,658 INFO Epoch:74 val_res:0.614286 +2025-04-18 02:59:03,673 INFO Epoch:75 train_loss:0.43854 +2025-04-18 02:59:07,283 INFO Epoch:75 val_res:0.631169 +2025-04-18 02:59:21,438 INFO Epoch:76 train_loss:0.40229 +2025-04-18 02:59:25,352 INFO Epoch:76 val_res:0.625974 +2025-04-18 02:59:39,653 INFO Epoch:77 train_loss:0.41670 +2025-04-18 02:59:44,367 INFO Epoch:77 val_res:0.632468 +2025-04-18 03:00:00,354 INFO Epoch:78 train_loss:0.43612 +2025-04-18 03:00:04,335 INFO Epoch:78 val_res:0.641558 +2025-04-18 03:00:17,435 INFO Epoch:79 train_loss:0.43946 +2025-04-18 03:00:22,268 INFO Epoch:79 val_res:0.594805 +2025-04-18 03:00:35,827 INFO Epoch:80 train_loss:0.42539 +2025-04-18 03:00:39,411 INFO Epoch:80 val_res:0.607792 +2025-04-18 03:00:52,130 INFO Epoch:81 train_loss:0.48063 +2025-04-18 03:00:55,845 INFO Epoch:81 val_res:0.637662 +2025-04-18 03:01:11,517 INFO Epoch:82 train_loss:0.40790 +2025-04-18 03:01:15,386 INFO Epoch:82 val_res:0.674026 +2025-04-18 03:01:15,386 INFO Saving best model at Epoch 82 +2025-04-18 03:01:31,870 INFO Epoch:83 train_loss:0.38312 +2025-04-18 03:01:35,364 INFO Epoch:83 val_res:0.631169 +2025-04-18 03:01:48,493 INFO Epoch:84 train_loss:0.38044 +2025-04-18 03:01:53,116 INFO Epoch:84 val_res:0.635065 +2025-04-18 03:02:06,600 INFO Epoch:85 train_loss:0.41286 +2025-04-18 03:02:10,283 INFO Epoch:85 val_res:0.635065 +2025-04-18 03:02:23,447 INFO Epoch:86 train_loss:0.40543 +2025-04-18 03:02:27,133 INFO Epoch:86 val_res:0.668831 +2025-04-18 03:02:42,118 INFO Epoch:87 train_loss:0.36322 +2025-04-18 03:02:45,518 INFO Epoch:87 val_res:0.663636 +2025-04-18 03:02:58,333 INFO Epoch:88 train_loss:0.36127 +2025-04-18 03:03:01,803 INFO Epoch:88 val_res:0.642857 +2025-04-18 03:03:15,883 INFO Epoch:89 train_loss:0.38919 +2025-04-18 03:03:20,028 INFO Epoch:89 val_res:0.661039 +2025-04-18 03:03:36,004 INFO Epoch:90 train_loss:0.42134 +2025-04-18 03:03:39,889 INFO Epoch:90 val_res:0.625974 +2025-04-18 03:03:52,992 INFO Epoch:91 train_loss:0.42428 +2025-04-18 03:03:56,592 INFO Epoch:91 val_res:0.664935 +2025-04-18 03:04:12,489 INFO Epoch:92 train_loss:0.45381 +2025-04-18 03:04:16,698 INFO Epoch:92 val_res:0.625974 +2025-04-18 03:04:30,020 INFO Epoch:93 train_loss:0.46741 +2025-04-18 03:04:34,037 INFO Epoch:93 val_res:0.666234 +2025-04-18 03:04:48,799 INFO Epoch:94 train_loss:0.43747 +2025-04-18 03:04:53,409 INFO Epoch:94 val_res:0.568831 +2025-04-18 03:05:11,110 INFO Epoch:95 train_loss:0.40666 +2025-04-18 03:05:15,322 INFO Epoch:95 val_res:0.688312 +2025-04-18 03:05:15,322 INFO Saving best model at Epoch 95 +2025-04-18 03:05:31,756 INFO Epoch:96 train_loss:0.39896 +2025-04-18 03:05:35,814 INFO Epoch:96 val_res:0.637662 +2025-04-18 03:05:57,678 INFO Epoch:97 train_loss:0.37154 +2025-04-18 03:06:03,017 INFO Epoch:97 val_res:0.614286 +2025-04-18 03:06:20,226 INFO Epoch:98 train_loss:0.34646 +2025-04-18 03:06:24,561 INFO Epoch:98 val_res:0.637662 +2025-04-18 03:06:41,544 INFO Epoch:99 train_loss:0.35604 +2025-04-18 03:06:45,757 INFO Epoch:99 val_res:0.651948 +2025-04-18 03:06:46,798 INFO ===================================== +2025-04-18 03:06:46,799 INFO Start testing... +2025-04-18 03:06:46,799 INFO ===================================== +2025-04-18 03:06:52,240 INFO Incremental step 1 Testing res: 0.662338 +2025-04-18 03:06:52,241 INFO forgetting: 0.115591 +2025-04-18 03:06:52,242 INFO Incremental step: 2 +2025-04-18 03:09:06,310 INFO Epoch:0 train_loss:1.64329 +2025-04-18 03:09:30,430 INFO Epoch:0 val_res:0.448785 +2025-04-18 03:09:30,431 INFO Saving best model at Epoch 0 +2025-04-18 03:09:49,613 INFO Epoch:1 train_loss:1.69747 +2025-04-18 03:09:54,279 INFO Epoch:1 val_res:0.430556 +2025-04-18 03:10:08,321 INFO Epoch:2 train_loss:1.52241 +2025-04-18 03:10:13,220 INFO Epoch:2 val_res:0.461806 +2025-04-18 03:10:13,220 INFO Saving best model at Epoch 2 +2025-04-18 03:10:28,217 INFO Epoch:3 train_loss:1.28536 +2025-04-18 03:10:33,064 INFO Epoch:3 val_res:0.464410 +2025-04-18 03:10:33,065 INFO Saving best model at Epoch 3 +2025-04-18 03:10:47,468 INFO Epoch:4 train_loss:1.76632 +2025-04-18 03:10:52,595 INFO Epoch:4 val_res:0.448785 +2025-04-18 03:11:06,118 INFO Epoch:5 train_loss:1.69773 +2025-04-18 03:11:10,743 INFO Epoch:5 val_res:0.460938 +2025-04-18 03:11:23,757 INFO Epoch:6 train_loss:1.31381 +2025-04-18 03:11:28,490 INFO Epoch:6 val_res:0.465278 +2025-04-18 03:11:28,491 INFO Saving best model at Epoch 6 +2025-04-18 03:11:42,850 INFO Epoch:7 train_loss:1.04496 +2025-04-18 03:11:47,346 INFO Epoch:7 val_res:0.482639 +2025-04-18 03:11:47,346 INFO Saving best model at Epoch 7 +2025-04-18 03:12:01,921 INFO Epoch:8 train_loss:0.93456 +2025-04-18 03:12:06,753 INFO Epoch:8 val_res:0.478299 +2025-04-18 03:12:19,622 INFO Epoch:9 train_loss:0.94341 +2025-04-18 03:12:24,498 INFO Epoch:9 val_res:0.477431 +2025-04-18 03:12:37,299 INFO Epoch:10 train_loss:0.89129 +2025-04-18 03:12:41,944 INFO Epoch:10 val_res:0.480903 +2025-04-18 03:12:55,060 INFO Epoch:11 train_loss:0.99718 +2025-04-18 03:13:00,053 INFO Epoch:11 val_res:0.440104 +2025-04-18 03:13:12,726 INFO Epoch:12 train_loss:1.26157 +2025-04-18 03:13:17,685 INFO Epoch:12 val_res:0.493924 +2025-04-18 03:13:17,685 INFO Saving best model at Epoch 12 +2025-04-18 03:13:34,241 INFO Epoch:13 train_loss:1.20996 +2025-04-18 03:13:38,955 INFO Epoch:13 val_res:0.453993 +2025-04-18 03:13:52,032 INFO Epoch:14 train_loss:1.20691 +2025-04-18 03:13:56,946 INFO Epoch:14 val_res:0.471354 +2025-04-18 03:14:10,066 INFO Epoch:15 train_loss:1.15195 +2025-04-18 03:14:14,706 INFO Epoch:15 val_res:0.473090 +2025-04-18 03:14:27,264 INFO Epoch:16 train_loss:0.91875 +2025-04-18 03:14:32,158 INFO Epoch:16 val_res:0.489583 +2025-04-18 03:14:45,254 INFO Epoch:17 train_loss:0.84482 +2025-04-18 03:14:50,120 INFO Epoch:17 val_res:0.495660 +2025-04-18 03:14:50,121 INFO Saving best model at Epoch 17 +2025-04-18 03:15:10,663 INFO Epoch:18 train_loss:0.77570 +2025-04-18 03:15:15,407 INFO Epoch:18 val_res:0.492188 +2025-04-18 03:15:28,449 INFO Epoch:19 train_loss:0.72816 +2025-04-18 03:15:33,127 INFO Epoch:19 val_res:0.495660 +2025-04-18 03:15:46,458 INFO Epoch:20 train_loss:0.75237 +2025-04-18 03:15:51,186 INFO Epoch:20 val_res:0.480035 +2025-04-18 03:16:03,936 INFO Epoch:21 train_loss:0.74774 +2025-04-18 03:16:08,398 INFO Epoch:21 val_res:0.498264 +2025-04-18 03:16:08,399 INFO Saving best model at Epoch 21 +2025-04-18 03:16:25,042 INFO Epoch:22 train_loss:0.78967 +2025-04-18 03:16:29,992 INFO Epoch:22 val_res:0.504340 +2025-04-18 03:16:29,992 INFO Saving best model at Epoch 22 +2025-04-18 03:16:44,945 INFO Epoch:23 train_loss:0.72669 +2025-04-18 03:16:49,455 INFO Epoch:23 val_res:0.490451 +2025-04-18 03:17:03,313 INFO Epoch:24 train_loss:0.72614 +2025-04-18 03:17:08,265 INFO Epoch:24 val_res:0.484375 +2025-04-18 03:17:21,563 INFO Epoch:25 train_loss:0.71868 +2025-04-18 03:17:26,360 INFO Epoch:25 val_res:0.506076 +2025-04-18 03:17:26,360 INFO Saving best model at Epoch 25 +2025-04-18 03:17:41,187 INFO Epoch:26 train_loss:0.86335 +2025-04-18 03:17:45,993 INFO Epoch:26 val_res:0.518229 +2025-04-18 03:17:45,994 INFO Saving best model at Epoch 26 +2025-04-18 03:18:01,079 INFO Epoch:27 train_loss:0.99241 +2025-04-18 03:18:05,756 INFO Epoch:27 val_res:0.497396 +2025-04-18 03:18:19,384 INFO Epoch:28 train_loss:0.87312 +2025-04-18 03:18:24,022 INFO Epoch:28 val_res:0.486111 +2025-04-18 03:18:36,667 INFO Epoch:29 train_loss:0.74375 +2025-04-18 03:18:41,579 INFO Epoch:29 val_res:0.518229 +2025-04-18 03:18:54,555 INFO Epoch:30 train_loss:0.69185 +2025-04-18 03:18:59,125 INFO Epoch:30 val_res:0.511285 +2025-04-18 03:19:12,654 INFO Epoch:31 train_loss:0.65014 +2025-04-18 03:19:17,458 INFO Epoch:31 val_res:0.514757 +2025-04-18 03:19:30,417 INFO Epoch:32 train_loss:0.67500 +2025-04-18 03:19:35,254 INFO Epoch:32 val_res:0.505208 +2025-04-18 03:19:48,346 INFO Epoch:33 train_loss:0.64775 +2025-04-18 03:19:52,912 INFO Epoch:33 val_res:0.503472 +2025-04-18 03:20:06,493 INFO Epoch:34 train_loss:0.64820 +2025-04-18 03:20:11,189 INFO Epoch:34 val_res:0.506944 +2025-04-18 03:20:23,934 INFO Epoch:35 train_loss:0.64431 +2025-04-18 03:20:28,746 INFO Epoch:35 val_res:0.507812 +2025-04-18 03:20:42,433 INFO Epoch:36 train_loss:0.63892 +2025-04-18 03:20:47,179 INFO Epoch:36 val_res:0.526910 +2025-04-18 03:20:47,179 INFO Saving best model at Epoch 36 +2025-04-18 03:21:01,130 INFO Epoch:37 train_loss:0.61530 +2025-04-18 03:21:06,052 INFO Epoch:37 val_res:0.500868 +2025-04-18 03:21:19,211 INFO Epoch:38 train_loss:0.60712 +2025-04-18 03:21:23,754 INFO Epoch:38 val_res:0.512153 +2025-04-18 03:21:36,777 INFO Epoch:39 train_loss:0.62366 +2025-04-18 03:21:41,879 INFO Epoch:39 val_res:0.509549 +2025-04-18 03:21:54,850 INFO Epoch:40 train_loss:0.58147 +2025-04-18 03:21:59,464 INFO Epoch:40 val_res:0.509549 +2025-04-18 03:22:13,160 INFO Epoch:41 train_loss:0.60885 +2025-04-18 03:22:17,972 INFO Epoch:41 val_res:0.496528 +2025-04-18 03:22:31,057 INFO Epoch:42 train_loss:0.62512 +2025-04-18 03:22:35,753 INFO Epoch:42 val_res:0.511285 +2025-04-18 03:22:48,672 INFO Epoch:43 train_loss:0.58427 +2025-04-18 03:22:53,383 INFO Epoch:43 val_res:0.520833 +2025-04-18 03:23:06,632 INFO Epoch:44 train_loss:0.57473 +2025-04-18 03:23:11,240 INFO Epoch:44 val_res:0.518229 +2025-04-18 03:23:23,924 INFO Epoch:45 train_loss:0.55703 +2025-04-18 03:23:28,585 INFO Epoch:45 val_res:0.528646 +2025-04-18 03:23:28,585 INFO Saving best model at Epoch 45 +2025-04-18 03:23:43,633 INFO Epoch:46 train_loss:0.61083 +2025-04-18 03:23:48,083 INFO Epoch:46 val_res:0.514757 +2025-04-18 03:24:00,805 INFO Epoch:47 train_loss:0.58944 +2025-04-18 03:24:05,562 INFO Epoch:47 val_res:0.536458 +2025-04-18 03:24:05,562 INFO Saving best model at Epoch 47 +2025-04-18 03:24:20,223 INFO Epoch:48 train_loss:0.57667 +2025-04-18 03:24:24,607 INFO Epoch:48 val_res:0.533854 +2025-04-18 03:24:38,191 INFO Epoch:49 train_loss:0.54370 +2025-04-18 03:24:42,975 INFO Epoch:49 val_res:0.517361 +2025-04-18 03:24:56,035 INFO Epoch:50 train_loss:0.55999 +2025-04-18 03:25:00,552 INFO Epoch:50 val_res:0.507812 +2025-04-18 03:25:13,840 INFO Epoch:51 train_loss:0.67936 +2025-04-18 03:25:18,508 INFO Epoch:51 val_res:0.506076 +2025-04-18 03:25:31,591 INFO Epoch:52 train_loss:0.58898 +2025-04-18 03:25:36,432 INFO Epoch:52 val_res:0.536458 +2025-04-18 03:25:49,978 INFO Epoch:53 train_loss:0.58318 +2025-04-18 03:25:54,864 INFO Epoch:53 val_res:0.506944 +2025-04-18 03:26:08,941 INFO Epoch:54 train_loss:0.61099 +2025-04-18 03:26:13,706 INFO Epoch:54 val_res:0.511285 +2025-04-18 03:26:26,574 INFO Epoch:55 train_loss:0.57279 +2025-04-18 03:26:31,276 INFO Epoch:55 val_res:0.523438 +2025-04-18 03:26:44,704 INFO Epoch:56 train_loss:0.56135 +2025-04-18 03:26:49,310 INFO Epoch:56 val_res:0.528646 +2025-04-18 03:27:02,351 INFO Epoch:57 train_loss:0.55959 +2025-04-18 03:27:07,411 INFO Epoch:57 val_res:0.512153 +2025-04-18 03:27:20,894 INFO Epoch:58 train_loss:0.53621 +2025-04-18 03:27:25,749 INFO Epoch:58 val_res:0.524306 +2025-04-18 03:27:38,839 INFO Epoch:59 train_loss:0.51983 +2025-04-18 03:27:43,996 INFO Epoch:59 val_res:0.534722 +2025-04-18 03:27:56,637 INFO Epoch:60 train_loss:0.49673 +2025-04-18 03:28:01,410 INFO Epoch:60 val_res:0.528646 +2025-04-18 03:28:14,384 INFO Epoch:61 train_loss:0.49453 +2025-04-18 03:28:19,380 INFO Epoch:61 val_res:0.523438 +2025-04-18 03:28:32,324 INFO Epoch:62 train_loss:0.48406 +2025-04-18 03:28:37,231 INFO Epoch:62 val_res:0.513021 +2025-04-18 03:28:50,507 INFO Epoch:63 train_loss:0.51462 +2025-04-18 03:28:55,243 INFO Epoch:63 val_res:0.543403 +2025-04-18 03:28:55,244 INFO Saving best model at Epoch 63 +2025-04-18 03:29:10,413 INFO Epoch:64 train_loss:0.55251 +2025-04-18 03:29:15,193 INFO Epoch:64 val_res:0.529514 +2025-04-18 03:29:28,230 INFO Epoch:65 train_loss:0.52052 +2025-04-18 03:29:32,926 INFO Epoch:65 val_res:0.545139 +2025-04-18 03:29:32,926 INFO Saving best model at Epoch 65 +2025-04-18 03:29:48,155 INFO Epoch:66 train_loss:0.55559 +2025-04-18 03:29:52,628 INFO Epoch:66 val_res:0.535590 +2025-04-18 03:30:05,994 INFO Epoch:67 train_loss:0.55116 +2025-04-18 03:30:11,176 INFO Epoch:67 val_res:0.526910 +2025-04-18 03:30:24,204 INFO Epoch:68 train_loss:0.57908 +2025-04-18 03:30:28,797 INFO Epoch:68 val_res:0.539062 +2025-04-18 03:30:42,846 INFO Epoch:69 train_loss:0.50001 +2025-04-18 03:30:47,538 INFO Epoch:69 val_res:0.524306 +2025-04-18 03:31:01,006 INFO Epoch:70 train_loss:0.47168 +2025-04-18 03:31:05,742 INFO Epoch:70 val_res:0.526042 +2025-04-18 03:31:19,794 INFO Epoch:71 train_loss:0.46431 +2025-04-18 03:31:24,308 INFO Epoch:71 val_res:0.532118 +2025-04-18 03:31:38,232 INFO Epoch:72 train_loss:0.46319 +2025-04-18 03:31:43,142 INFO Epoch:72 val_res:0.531250 +2025-04-18 03:31:57,253 INFO Epoch:73 train_loss:0.50458 +2025-04-18 03:32:02,246 INFO Epoch:73 val_res:0.538194 +2025-04-18 03:32:15,499 INFO Epoch:74 train_loss:0.62895 +2025-04-18 03:32:20,080 INFO Epoch:74 val_res:0.529514 +2025-04-18 03:32:33,504 INFO Epoch:75 train_loss:0.56234 +2025-04-18 03:32:38,429 INFO Epoch:75 val_res:0.541667 +2025-04-18 03:32:51,630 INFO Epoch:76 train_loss:0.47755 +2025-04-18 03:32:56,375 INFO Epoch:76 val_res:0.547743 +2025-04-18 03:32:56,375 INFO Saving best model at Epoch 76 +2025-04-18 03:33:12,495 INFO Epoch:77 train_loss:0.45281 +2025-04-18 03:33:17,215 INFO Epoch:77 val_res:0.523438 +2025-04-18 03:33:30,187 INFO Epoch:78 train_loss:0.47067 +2025-04-18 03:33:34,927 INFO Epoch:78 val_res:0.534722 +2025-04-18 03:33:49,062 INFO Epoch:79 train_loss:0.42897 +2025-04-18 03:33:53,720 INFO Epoch:79 val_res:0.547743 +2025-04-18 03:34:06,897 INFO Epoch:80 train_loss:0.46141 +2025-04-18 03:34:11,590 INFO Epoch:80 val_res:0.516493 +2025-04-18 03:34:25,749 INFO Epoch:81 train_loss:0.44248 +2025-04-18 03:34:30,405 INFO Epoch:81 val_res:0.548611 +2025-04-18 03:34:30,405 INFO Saving best model at Epoch 81 +2025-04-18 03:34:45,109 INFO Epoch:82 train_loss:0.45417 +2025-04-18 03:34:49,949 INFO Epoch:82 val_res:0.550347 +2025-04-18 03:34:49,950 INFO Saving best model at Epoch 82 +2025-04-18 03:35:05,089 INFO Epoch:83 train_loss:0.53859 +2025-04-18 03:35:09,887 INFO Epoch:83 val_res:0.522569 +2025-04-18 03:35:22,799 INFO Epoch:84 train_loss:0.64510 +2025-04-18 03:35:27,732 INFO Epoch:84 val_res:0.553819 +2025-04-18 03:35:27,732 INFO Saving best model at Epoch 84 +2025-04-18 03:35:42,882 INFO Epoch:85 train_loss:0.47211 +2025-04-18 03:35:47,567 INFO Epoch:85 val_res:0.535590 +2025-04-18 03:36:01,455 INFO Epoch:86 train_loss:0.45296 +2025-04-18 03:36:06,612 INFO Epoch:86 val_res:0.543403 +2025-04-18 03:36:19,525 INFO Epoch:87 train_loss:0.46870 +2025-04-18 03:36:24,261 INFO Epoch:87 val_res:0.538194 +2025-04-18 03:36:37,356 INFO Epoch:88 train_loss:0.43140 +2025-04-18 03:36:42,184 INFO Epoch:88 val_res:0.539931 +2025-04-18 03:36:55,347 INFO Epoch:89 train_loss:0.41487 +2025-04-18 03:37:00,107 INFO Epoch:89 val_res:0.535590 +2025-04-18 03:37:13,772 INFO Epoch:90 train_loss:0.44326 +2025-04-18 03:37:18,827 INFO Epoch:90 val_res:0.542535 +2025-04-18 03:37:32,405 INFO Epoch:91 train_loss:0.42328 +2025-04-18 03:37:37,075 INFO Epoch:91 val_res:0.540799 +2025-04-18 03:37:50,662 INFO Epoch:92 train_loss:0.38532 +2025-04-18 03:37:55,418 INFO Epoch:92 val_res:0.530382 +2025-04-18 03:38:08,596 INFO Epoch:93 train_loss:0.43202 +2025-04-18 03:38:13,266 INFO Epoch:93 val_res:0.541667 +2025-04-18 03:38:26,074 INFO Epoch:94 train_loss:0.61100 +2025-04-18 03:38:30,656 INFO Epoch:94 val_res:0.525174 +2025-04-18 03:38:44,102 INFO Epoch:95 train_loss:0.58720 +2025-04-18 03:38:48,809 INFO Epoch:95 val_res:0.544271 +2025-04-18 03:39:02,156 INFO Epoch:96 train_loss:0.44505 +2025-04-18 03:39:06,744 INFO Epoch:96 val_res:0.541667 +2025-04-18 03:39:19,070 INFO Epoch:97 train_loss:0.49280 +2025-04-18 03:39:24,038 INFO Epoch:97 val_res:0.538194 +2025-04-18 03:39:36,823 INFO Epoch:98 train_loss:0.45392 +2025-04-18 03:39:41,359 INFO Epoch:98 val_res:0.544271 +2025-04-18 03:39:53,959 INFO Epoch:99 train_loss:0.39806 +2025-04-18 03:39:58,484 INFO Epoch:99 val_res:0.546875 +2025-04-18 03:39:59,334 INFO ===================================== +2025-04-18 03:39:59,335 INFO Start testing... +2025-04-18 03:39:59,335 INFO ===================================== +2025-04-18 03:40:04,794 INFO Incremental step 2 Testing res: 0.547660 +2025-04-18 03:40:04,795 INFO forgetting: 0.139488 +2025-04-18 03:40:04,808 INFO Incremental step: 3 +2025-04-18 03:44:30,625 INFO Epoch:0 train_loss:3.60548 +2025-04-18 03:45:09,861 INFO Epoch:0 val_res:0.304799 +2025-04-18 03:45:09,867 INFO Saving best model at Epoch 0 +2025-04-18 03:45:41,595 INFO Epoch:1 train_loss:2.25320 +2025-04-18 03:45:47,293 INFO Epoch:1 val_res:0.397536 +2025-04-18 03:45:47,294 INFO Saving best model at Epoch 1 +2025-04-18 03:46:05,173 INFO Epoch:2 train_loss:1.37771 +2025-04-18 03:46:10,859 INFO Epoch:2 val_res:0.415694 +2025-04-18 03:46:10,860 INFO Saving best model at Epoch 2 +2025-04-18 03:46:27,895 INFO Epoch:3 train_loss:1.36891 +2025-04-18 03:46:33,410 INFO Epoch:3 val_res:0.412451 +2025-04-18 03:46:47,839 INFO Epoch:4 train_loss:1.36929 +2025-04-18 03:46:53,489 INFO Epoch:4 val_res:0.395590 +2025-04-18 03:47:07,907 INFO Epoch:5 train_loss:1.21877 +2025-04-18 03:47:13,512 INFO Epoch:5 val_res:0.392996 +2025-04-18 03:47:30,857 INFO Epoch:6 train_loss:1.10564 +2025-04-18 03:47:37,440 INFO Epoch:6 val_res:0.422179 +2025-04-18 03:47:37,444 INFO Saving best model at Epoch 6 +2025-04-18 03:47:57,608 INFO Epoch:7 train_loss:0.98801 +2025-04-18 03:48:04,314 INFO Epoch:7 val_res:0.395590 +2025-04-18 03:48:21,891 INFO Epoch:8 train_loss:0.92684 +2025-04-18 03:48:28,037 INFO Epoch:8 val_res:0.421530 +2025-04-18 03:48:44,074 INFO Epoch:9 train_loss:1.08302 +2025-04-18 03:48:50,087 INFO Epoch:9 val_res:0.387808 +2025-04-18 03:49:05,825 INFO Epoch:10 train_loss:0.82211 +2025-04-18 03:49:11,842 INFO Epoch:10 val_res:0.425422 +2025-04-18 03:49:11,848 INFO Saving best model at Epoch 10 +2025-04-18 03:49:32,325 INFO Epoch:11 train_loss:0.78547 +2025-04-18 03:49:38,222 INFO Epoch:11 val_res:0.418936 +2025-04-18 03:49:53,580 INFO Epoch:12 train_loss:1.06035 +2025-04-18 03:49:59,501 INFO Epoch:12 val_res:0.415045 +2025-04-18 03:50:16,640 INFO Epoch:13 train_loss:0.95418 +2025-04-18 03:50:23,287 INFO Epoch:13 val_res:0.453307 +2025-04-18 03:50:23,291 INFO Saving best model at Epoch 13 +2025-04-18 03:50:42,295 INFO Epoch:14 train_loss:1.03498 +2025-04-18 03:50:48,720 INFO Epoch:14 val_res:0.407263 +2025-04-18 03:51:07,645 INFO Epoch:15 train_loss:1.01192 +2025-04-18 03:51:15,784 INFO Epoch:15 val_res:0.450713 +2025-04-18 03:51:34,556 INFO Epoch:16 train_loss:0.93959 +2025-04-18 03:51:42,023 INFO Epoch:16 val_res:0.457847 +2025-04-18 03:51:42,024 INFO Saving best model at Epoch 16 +2025-04-18 03:52:01,609 INFO Epoch:17 train_loss:0.74965 +2025-04-18 03:52:09,026 INFO Epoch:17 val_res:0.467575 +2025-04-18 03:52:09,027 INFO Saving best model at Epoch 17 +2025-04-18 03:52:30,147 INFO Epoch:18 train_loss:0.60707 +2025-04-18 03:52:36,530 INFO Epoch:18 val_res:0.461738 +2025-04-18 03:52:53,374 INFO Epoch:19 train_loss:0.60050 +2025-04-18 03:53:00,212 INFO Epoch:19 val_res:0.451362 +2025-04-18 03:53:17,871 INFO Epoch:20 train_loss:0.57034 +2025-04-18 03:53:24,012 INFO Epoch:20 val_res:0.463035 +2025-04-18 03:53:42,911 INFO Epoch:21 train_loss:0.54818 +2025-04-18 03:53:49,552 INFO Epoch:21 val_res:0.460441 +2025-04-18 03:54:06,945 INFO Epoch:22 train_loss:0.55143 +2025-04-18 03:54:13,400 INFO Epoch:22 val_res:0.457847 +2025-04-18 03:54:31,511 INFO Epoch:23 train_loss:0.52489 +2025-04-18 03:54:38,580 INFO Epoch:23 val_res:0.464332 +2025-04-18 03:54:58,629 INFO Epoch:24 train_loss:0.50816 +2025-04-18 03:55:05,064 INFO Epoch:24 val_res:0.468223 +2025-04-18 03:55:05,064 INFO Saving best model at Epoch 24 +2025-04-18 03:55:24,358 INFO Epoch:25 train_loss:0.50374 +2025-04-18 03:55:31,832 INFO Epoch:25 val_res:0.470169 +2025-04-18 03:55:31,840 INFO Saving best model at Epoch 25 +2025-04-18 03:55:51,442 INFO Epoch:26 train_loss:0.50698 +2025-04-18 03:55:57,691 INFO Epoch:26 val_res:0.468223 +2025-04-18 03:56:16,944 INFO Epoch:27 train_loss:0.50070 +2025-04-18 03:56:24,055 INFO Epoch:27 val_res:0.481193 +2025-04-18 03:56:24,055 INFO Saving best model at Epoch 27 +2025-04-18 03:56:47,128 INFO Epoch:28 train_loss:0.50891 +2025-04-18 03:56:53,412 INFO Epoch:28 val_res:0.471466 +2025-04-18 03:57:10,142 INFO Epoch:29 train_loss:0.48525 +2025-04-18 03:57:16,710 INFO Epoch:29 val_res:0.471466 +2025-04-18 03:57:34,976 INFO Epoch:30 train_loss:0.51432 +2025-04-18 03:57:42,222 INFO Epoch:30 val_res:0.463684 +2025-04-18 03:57:59,607 INFO Epoch:31 train_loss:0.52393 +2025-04-18 03:58:08,114 INFO Epoch:31 val_res:0.488975 +2025-04-18 03:58:08,125 INFO Saving best model at Epoch 31 +2025-04-18 03:58:30,384 INFO Epoch:32 train_loss:0.48848 +2025-04-18 03:58:37,226 INFO Epoch:32 val_res:0.481193 +2025-04-18 03:58:55,418 INFO Epoch:33 train_loss:0.50134 +2025-04-18 03:59:02,066 INFO Epoch:33 val_res:0.461089 +2025-04-18 03:59:21,520 INFO Epoch:34 train_loss:0.56547 +2025-04-18 03:59:28,190 INFO Epoch:34 val_res:0.476654 +2025-04-18 03:59:46,746 INFO Epoch:35 train_loss:0.49103 +2025-04-18 03:59:53,198 INFO Epoch:35 val_res:0.487030 +2025-04-18 04:00:11,855 INFO Epoch:36 train_loss:0.52265 +2025-04-18 04:00:18,218 INFO Epoch:36 val_res:0.483139 +2025-04-18 04:00:37,134 INFO Epoch:37 train_loss:0.52235 +2025-04-18 04:00:44,464 INFO Epoch:37 val_res:0.488975 +2025-04-18 04:01:05,732 INFO Epoch:38 train_loss:0.50874 +2025-04-18 04:01:12,330 INFO Epoch:38 val_res:0.501297 +2025-04-18 04:01:12,331 INFO Saving best model at Epoch 38 +2025-04-18 04:01:32,072 INFO Epoch:39 train_loss:0.51542 +2025-04-18 04:01:39,495 INFO Epoch:39 val_res:0.497406 +2025-04-18 04:01:57,172 INFO Epoch:40 train_loss:0.49273 +2025-04-18 04:02:03,538 INFO Epoch:40 val_res:0.460441 +2025-04-18 04:02:22,450 INFO Epoch:41 train_loss:0.53293 +2025-04-18 04:02:30,411 INFO Epoch:41 val_res:0.495460 +2025-04-18 04:02:51,325 INFO Epoch:42 train_loss:0.45896 +2025-04-18 04:02:58,097 INFO Epoch:42 val_res:0.492218 +2025-04-18 04:03:14,412 INFO Epoch:43 train_loss:0.46026 +2025-04-18 04:03:21,438 INFO Epoch:43 val_res:0.488975 +2025-04-18 04:03:37,694 INFO Epoch:44 train_loss:0.47642 +2025-04-18 04:03:45,211 INFO Epoch:44 val_res:0.472114 +2025-04-18 04:04:02,279 INFO Epoch:45 train_loss:0.47633 +2025-04-18 04:04:08,835 INFO Epoch:45 val_res:0.490921 +2025-04-18 04:04:28,532 INFO Epoch:46 train_loss:0.42355 +2025-04-18 04:04:35,476 INFO Epoch:46 val_res:0.485733 +2025-04-18 04:04:53,443 INFO Epoch:47 train_loss:0.44771 +2025-04-18 04:04:59,985 INFO Epoch:47 val_res:0.483787 +2025-04-18 04:05:19,936 INFO Epoch:48 train_loss:0.43281 +2025-04-18 04:05:26,812 INFO Epoch:48 val_res:0.485084 +2025-04-18 04:05:46,501 INFO Epoch:49 train_loss:0.41169 +2025-04-18 04:05:54,584 INFO Epoch:49 val_res:0.474060 +2025-04-18 04:06:11,993 INFO Epoch:50 train_loss:0.45955 +2025-04-18 04:06:18,809 INFO Epoch:50 val_res:0.483139 +2025-04-18 04:06:39,160 INFO Epoch:51 train_loss:0.44839 +2025-04-18 04:06:46,310 INFO Epoch:51 val_res:0.483139 +2025-04-18 04:07:03,233 INFO Epoch:52 train_loss:0.41410 +2025-04-18 04:07:11,104 INFO Epoch:52 val_res:0.494163 +2025-04-18 04:07:28,768 INFO Epoch:53 train_loss:0.46516 +2025-04-18 04:07:35,841 INFO Epoch:53 val_res:0.477302 +2025-04-18 04:07:53,533 INFO Epoch:54 train_loss:0.43110 +2025-04-18 04:08:00,262 INFO Epoch:54 val_res:0.484436 +2025-04-18 04:08:18,803 INFO Epoch:55 train_loss:0.44608 +2025-04-18 04:08:27,078 INFO Epoch:55 val_res:0.490921 +2025-04-18 04:08:44,389 INFO Epoch:56 train_loss:0.49280 +2025-04-18 04:08:51,772 INFO Epoch:56 val_res:0.470169 +2025-04-18 04:09:13,260 INFO Epoch:57 train_loss:0.43428 +2025-04-18 04:09:21,682 INFO Epoch:57 val_res:0.488327 +2025-04-18 04:09:39,232 INFO Epoch:58 train_loss:0.37087 +2025-04-18 04:09:46,104 INFO Epoch:58 val_res:0.496109 +2025-04-18 04:10:04,579 INFO Epoch:59 train_loss:0.37030 +2025-04-18 04:10:11,952 INFO Epoch:59 val_res:0.491569 +2025-04-18 04:10:30,039 INFO Epoch:60 train_loss:0.36632 +2025-04-18 04:10:37,479 INFO Epoch:60 val_res:0.497406 +2025-04-18 04:10:56,923 INFO Epoch:61 train_loss:0.43087 +2025-04-18 04:11:03,822 INFO Epoch:61 val_res:0.485084 +2025-04-18 04:11:23,193 INFO Epoch:62 train_loss:0.46960 +2025-04-18 04:11:32,243 INFO Epoch:62 val_res:0.500648 +2025-04-18 04:11:50,370 INFO Epoch:63 train_loss:0.42785 +2025-04-18 04:11:56,868 INFO Epoch:63 val_res:0.490272 +2025-04-18 04:12:16,050 INFO Epoch:64 train_loss:0.39879 +2025-04-18 04:12:22,936 INFO Epoch:64 val_res:0.477951 +2025-04-18 04:12:40,575 INFO Epoch:65 train_loss:0.48830 +2025-04-18 04:12:48,259 INFO Epoch:65 val_res:0.484436 +2025-04-18 04:13:06,910 INFO Epoch:66 train_loss:0.57643 +2025-04-18 04:13:14,473 INFO Epoch:66 val_res:0.463684 +2025-04-18 04:13:33,059 INFO Epoch:67 train_loss:0.48158 +2025-04-18 04:13:40,176 INFO Epoch:67 val_res:0.488327 +2025-04-18 04:13:58,091 INFO Epoch:68 train_loss:0.37638 +2025-04-18 04:14:06,283 INFO Epoch:68 val_res:0.483139 +2025-04-18 04:14:24,294 INFO Epoch:69 train_loss:0.41934 +2025-04-18 04:14:31,775 INFO Epoch:69 val_res:0.494812 +2025-04-18 04:14:50,597 INFO Epoch:70 train_loss:0.35014 +2025-04-18 04:14:57,738 INFO Epoch:70 val_res:0.503243 +2025-04-18 04:14:57,744 INFO Saving best model at Epoch 70 +2025-04-18 04:15:17,778 INFO Epoch:71 train_loss:0.33925 +2025-04-18 04:15:26,316 INFO Epoch:71 val_res:0.496757 +2025-04-18 04:15:44,405 INFO Epoch:72 train_loss:0.34354 +2025-04-18 04:15:51,506 INFO Epoch:72 val_res:0.506485 +2025-04-18 04:15:51,514 INFO Saving best model at Epoch 72 +2025-04-18 04:16:13,952 INFO Epoch:73 train_loss:0.37590 +2025-04-18 04:16:21,108 INFO Epoch:73 val_res:0.483787 +2025-04-18 04:16:40,368 INFO Epoch:74 train_loss:0.37933 +2025-04-18 04:16:47,398 INFO Epoch:74 val_res:0.508431 +2025-04-18 04:16:47,413 INFO Saving best model at Epoch 74 +2025-04-18 04:17:06,647 INFO Epoch:75 train_loss:0.36692 +2025-04-18 04:17:15,004 INFO Epoch:75 val_res:0.500648 +2025-04-18 04:17:32,315 INFO Epoch:76 train_loss:0.35630 +2025-04-18 04:17:39,112 INFO Epoch:76 val_res:0.497406 +2025-04-18 04:17:58,636 INFO Epoch:77 train_loss:0.34377 +2025-04-18 04:18:05,493 INFO Epoch:77 val_res:0.504540 +2025-04-18 04:18:23,355 INFO Epoch:78 train_loss:0.33301 +2025-04-18 04:18:30,584 INFO Epoch:78 val_res:0.492866 +2025-04-18 04:18:49,926 INFO Epoch:79 train_loss:0.32172 +2025-04-18 04:18:56,918 INFO Epoch:79 val_res:0.491569 +2025-04-18 04:19:14,798 INFO Epoch:80 train_loss:0.32979 +2025-04-18 04:19:21,702 INFO Epoch:80 val_res:0.507134 +2025-04-18 04:19:41,221 INFO Epoch:81 train_loss:0.32716 +2025-04-18 04:19:48,055 INFO Epoch:81 val_res:0.503891 +2025-04-18 04:20:05,531 INFO Epoch:82 train_loss:0.35183 +2025-04-18 04:20:13,180 INFO Epoch:82 val_res:0.501297 +2025-04-18 04:20:30,815 INFO Epoch:83 train_loss:0.35184 +2025-04-18 04:20:37,654 INFO Epoch:83 val_res:0.500000 +2025-04-18 04:20:57,555 INFO Epoch:84 train_loss:0.35317 +2025-04-18 04:21:04,479 INFO Epoch:84 val_res:0.497406 +2025-04-18 04:21:22,276 INFO Epoch:85 train_loss:0.35994 +2025-04-18 04:21:29,706 INFO Epoch:85 val_res:0.504540 +2025-04-18 04:21:47,576 INFO Epoch:86 train_loss:0.38552 +2025-04-18 04:21:54,702 INFO Epoch:86 val_res:0.499352 +2025-04-18 04:22:13,033 INFO Epoch:87 train_loss:0.53699 +2025-04-18 04:22:20,133 INFO Epoch:87 val_res:0.462387 +2025-04-18 04:22:37,880 INFO Epoch:88 train_loss:0.55785 +2025-04-18 04:22:46,062 INFO Epoch:88 val_res:0.484436 +2025-04-18 04:23:05,436 INFO Epoch:89 train_loss:0.42392 +2025-04-18 04:23:12,719 INFO Epoch:89 val_res:0.483787 +2025-04-18 04:23:32,027 INFO Epoch:90 train_loss:0.34207 +2025-04-18 04:23:39,899 INFO Epoch:90 val_res:0.496757 +2025-04-18 04:23:56,703 INFO Epoch:91 train_loss:0.34249 +2025-04-18 04:24:03,603 INFO Epoch:91 val_res:0.487678 +2025-04-18 04:24:21,509 INFO Epoch:92 train_loss:0.34272 +2025-04-18 04:24:27,860 INFO Epoch:92 val_res:0.491569 +2025-04-18 04:24:45,408 INFO Epoch:93 train_loss:0.31228 +2025-04-18 04:24:53,870 INFO Epoch:93 val_res:0.498703 +2025-04-18 04:25:15,834 INFO Epoch:94 train_loss:0.36972 +2025-04-18 04:25:23,456 INFO Epoch:94 val_res:0.472763 +2025-04-18 04:25:43,097 INFO Epoch:95 train_loss:0.35235 +2025-04-18 04:25:50,360 INFO Epoch:95 val_res:0.474708 +2025-04-18 04:26:06,952 INFO Epoch:96 train_loss:0.31900 +2025-04-18 04:26:13,947 INFO Epoch:96 val_res:0.478599 +2025-04-18 04:26:32,913 INFO Epoch:97 train_loss:0.32065 +2025-04-18 04:26:40,196 INFO Epoch:97 val_res:0.483139 +2025-04-18 04:26:58,442 INFO Epoch:98 train_loss:0.29287 +2025-04-18 04:27:06,428 INFO Epoch:98 val_res:0.492218 +2025-04-18 04:27:23,504 INFO Epoch:99 train_loss:0.33267 +2025-04-18 04:27:30,715 INFO Epoch:99 val_res:0.501297 +2025-04-18 04:27:31,505 INFO ===================================== +2025-04-18 04:27:31,512 INFO Start testing... +2025-04-18 04:27:31,513 INFO ===================================== +2025-04-18 04:28:25,620 INFO Incremental step 3 Testing res: 0.488026 +2025-04-18 04:28:25,625 INFO forgetting: 0.182588 +2025-04-18 04:28:25,655 INFO Incremental step: 4 +2025-04-18 04:34:58,789 INFO Epoch:0 train_loss:2.51286 +2025-04-18 04:35:43,899 INFO Epoch:0 val_res:0.368259 +2025-04-18 04:35:43,901 INFO Saving best model at Epoch 0 +2025-04-18 04:36:33,590 INFO Epoch:1 train_loss:2.02957 +2025-04-18 04:36:43,467 INFO Epoch:1 val_res:0.393939 +2025-04-18 04:36:43,467 INFO Saving best model at Epoch 1 +2025-04-18 04:37:08,384 INFO Epoch:2 train_loss:1.44932 +2025-04-18 04:37:18,692 INFO Epoch:2 val_res:0.379558 +2025-04-18 04:37:39,783 INFO Epoch:3 train_loss:1.93665 +2025-04-18 04:37:48,903 INFO Epoch:3 val_res:0.400103 +2025-04-18 04:37:48,907 INFO Saving best model at Epoch 3 +2025-04-18 04:38:10,033 INFO Epoch:4 train_loss:1.54085 +2025-04-18 04:38:20,924 INFO Epoch:4 val_res:0.376477 +2025-04-18 04:38:41,095 INFO Epoch:5 train_loss:1.62357 +2025-04-18 04:38:49,371 INFO Epoch:5 val_res:0.382126 +2025-04-18 04:39:06,191 INFO Epoch:6 train_loss:1.51443 +2025-04-18 04:39:14,583 INFO Epoch:6 val_res:0.394967 +2025-04-18 04:39:32,157 INFO Epoch:7 train_loss:1.23399 +2025-04-18 04:39:39,990 INFO Epoch:7 val_res:0.386235 +2025-04-18 04:39:59,051 INFO Epoch:8 train_loss:1.45765 +2025-04-18 04:40:08,606 INFO Epoch:8 val_res:0.366204 +2025-04-18 04:40:29,230 INFO Epoch:9 train_loss:1.37843 +2025-04-18 04:40:39,024 INFO Epoch:9 val_res:0.381613 +2025-04-18 04:40:59,029 INFO Epoch:10 train_loss:1.29182 +2025-04-18 04:41:07,873 INFO Epoch:10 val_res:0.390344 +2025-04-18 04:41:28,517 INFO Epoch:11 train_loss:1.19969 +2025-04-18 04:41:39,684 INFO Epoch:11 val_res:0.383667 +2025-04-18 04:42:00,338 INFO Epoch:12 train_loss:0.95858 +2025-04-18 04:42:07,926 INFO Epoch:12 val_res:0.389317 +2025-04-18 04:42:25,305 INFO Epoch:13 train_loss:0.82883 +2025-04-18 04:42:34,009 INFO Epoch:13 val_res:0.394453 +2025-04-18 04:42:50,408 INFO Epoch:14 train_loss:0.87252 +2025-04-18 04:42:58,206 INFO Epoch:14 val_res:0.400616 +2025-04-18 04:42:58,222 INFO Saving best model at Epoch 14 +2025-04-18 04:43:19,213 INFO Epoch:15 train_loss:0.82271 +2025-04-18 04:43:28,495 INFO Epoch:15 val_res:0.398562 +2025-04-18 04:43:45,105 INFO Epoch:16 train_loss:0.80265 +2025-04-18 04:43:52,852 INFO Epoch:16 val_res:0.396507 +2025-04-18 04:44:10,903 INFO Epoch:17 train_loss:0.80328 +2025-04-18 04:44:19,216 INFO Epoch:17 val_res:0.398562 +2025-04-18 04:44:34,935 INFO Epoch:18 train_loss:0.76427 +2025-04-18 04:44:42,716 INFO Epoch:18 val_res:0.399076 +2025-04-18 04:44:59,624 INFO Epoch:19 train_loss:0.78457 +2025-04-18 04:45:07,437 INFO Epoch:19 val_res:0.394967 +2025-04-18 04:45:24,394 INFO Epoch:20 train_loss:0.82121 +2025-04-18 04:45:33,987 INFO Epoch:20 val_res:0.394453 +2025-04-18 04:45:52,791 INFO Epoch:21 train_loss:0.85504 +2025-04-18 04:46:03,084 INFO Epoch:21 val_res:0.399076 +2025-04-18 04:46:19,954 INFO Epoch:22 train_loss:0.77213 +2025-04-18 04:46:28,895 INFO Epoch:22 val_res:0.402157 +2025-04-18 04:46:28,895 INFO Saving best model at Epoch 22 +2025-04-18 04:46:46,066 INFO Epoch:23 train_loss:0.74567 +2025-04-18 04:46:53,881 INFO Epoch:23 val_res:0.407293 +2025-04-18 04:46:53,888 INFO Saving best model at Epoch 23 +2025-04-18 04:47:12,028 INFO Epoch:24 train_loss:0.82128 +2025-04-18 04:47:20,344 INFO Epoch:24 val_res:0.393939 +2025-04-18 04:47:35,919 INFO Epoch:25 train_loss:0.74903 +2025-04-18 04:47:44,878 INFO Epoch:25 val_res:0.409861 +2025-04-18 04:47:44,888 INFO Saving best model at Epoch 25 +2025-04-18 04:48:02,059 INFO Epoch:26 train_loss:0.75667 +2025-04-18 04:48:10,016 INFO Epoch:26 val_res:0.411402 +2025-04-18 04:48:10,020 INFO Saving best model at Epoch 26 +2025-04-18 04:48:28,464 INFO Epoch:27 train_loss:0.72924 +2025-04-18 04:48:37,432 INFO Epoch:27 val_res:0.393939 +2025-04-18 04:48:53,583 INFO Epoch:28 train_loss:0.71928 +2025-04-18 04:49:02,044 INFO Epoch:28 val_res:0.401644 +2025-04-18 04:49:21,540 INFO Epoch:29 train_loss:0.72192 +2025-04-18 04:49:31,712 INFO Epoch:29 val_res:0.409348 +2025-04-18 04:49:50,153 INFO Epoch:30 train_loss:0.69161 +2025-04-18 04:49:59,481 INFO Epoch:30 val_res:0.410375 +2025-04-18 04:50:15,841 INFO Epoch:31 train_loss:0.99907 +2025-04-18 04:50:24,890 INFO Epoch:31 val_res:0.404212 +2025-04-18 04:50:42,044 INFO Epoch:32 train_loss:1.06732 +2025-04-18 04:50:50,560 INFO Epoch:32 val_res:0.415511 +2025-04-18 04:50:50,562 INFO Saving best model at Epoch 32 +2025-04-18 04:51:12,728 INFO Epoch:33 train_loss:0.94927 +2025-04-18 04:51:22,980 INFO Epoch:33 val_res:0.419620 +2025-04-18 04:51:22,985 INFO Saving best model at Epoch 33 +2025-04-18 04:51:41,572 INFO Epoch:34 train_loss:0.79630 +2025-04-18 04:51:49,214 INFO Epoch:34 val_res:0.406780 +2025-04-18 04:52:07,272 INFO Epoch:35 train_loss:0.67919 +2025-04-18 04:52:17,075 INFO Epoch:35 val_res:0.401644 +2025-04-18 04:52:37,856 INFO Epoch:36 train_loss:0.70758 +2025-04-18 04:52:49,248 INFO Epoch:36 val_res:0.424242 +2025-04-18 04:52:49,252 INFO Saving best model at Epoch 36 +2025-04-18 04:53:07,452 INFO Epoch:37 train_loss:0.76674 +2025-04-18 04:53:14,939 INFO Epoch:37 val_res:0.393426 +2025-04-18 04:53:33,285 INFO Epoch:38 train_loss:0.98404 +2025-04-18 04:53:42,719 INFO Epoch:38 val_res:0.389830 +2025-04-18 04:53:58,593 INFO Epoch:39 train_loss:0.94222 +2025-04-18 04:54:08,004 INFO Epoch:39 val_res:0.419106 +2025-04-18 04:54:26,618 INFO Epoch:40 train_loss:0.94651 +2025-04-18 04:54:34,788 INFO Epoch:40 val_res:0.379558 +2025-04-18 04:54:51,258 INFO Epoch:41 train_loss:0.82844 +2025-04-18 04:55:00,139 INFO Epoch:41 val_res:0.414997 +2025-04-18 04:55:19,323 INFO Epoch:42 train_loss:0.65558 +2025-04-18 04:55:28,212 INFO Epoch:42 val_res:0.413457 +2025-04-18 04:55:45,221 INFO Epoch:43 train_loss:0.59818 +2025-04-18 04:55:55,288 INFO Epoch:43 val_res:0.414997 +2025-04-18 04:56:14,938 INFO Epoch:44 train_loss:0.61930 +2025-04-18 04:56:25,704 INFO Epoch:44 val_res:0.409348 +2025-04-18 04:56:42,696 INFO Epoch:45 train_loss:0.65579 +2025-04-18 04:56:53,676 INFO Epoch:45 val_res:0.405239 +2025-04-18 04:57:10,213 INFO Epoch:46 train_loss:0.63536 +2025-04-18 04:57:19,024 INFO Epoch:46 val_res:0.404212 +2025-04-18 04:57:36,378 INFO Epoch:47 train_loss:0.70116 +2025-04-18 04:57:45,346 INFO Epoch:47 val_res:0.404212 +2025-04-18 04:58:01,111 INFO Epoch:48 train_loss:0.66912 +2025-04-18 04:58:11,798 INFO Epoch:48 val_res:0.417052 +2025-04-18 04:58:31,004 INFO Epoch:49 train_loss:0.63405 +2025-04-18 04:58:39,751 INFO Epoch:49 val_res:0.411402 +2025-04-18 04:58:56,903 INFO Epoch:50 train_loss:0.61329 +2025-04-18 04:59:07,416 INFO Epoch:50 val_res:0.413457 +2025-04-18 04:59:23,246 INFO Epoch:51 train_loss:0.65006 +2025-04-18 04:59:31,144 INFO Epoch:51 val_res:0.406780 +2025-04-18 04:59:49,701 INFO Epoch:52 train_loss:0.69112 +2025-04-18 04:59:58,820 INFO Epoch:52 val_res:0.399589 +2025-04-18 05:00:15,492 INFO Epoch:53 train_loss:0.71149 +2025-04-18 05:00:24,880 INFO Epoch:53 val_res:0.409861 +2025-04-18 05:00:43,285 INFO Epoch:54 train_loss:0.60381 +2025-04-18 05:00:53,055 INFO Epoch:54 val_res:0.412429 +2025-04-18 05:01:10,999 INFO Epoch:55 train_loss:0.55666 +2025-04-18 05:01:21,190 INFO Epoch:55 val_res:0.422702 +2025-04-18 05:01:42,092 INFO Epoch:56 train_loss:0.56631 +2025-04-18 05:01:49,816 INFO Epoch:56 val_res:0.416025 +2025-04-18 05:02:06,772 INFO Epoch:57 train_loss:0.55169 +2025-04-18 05:02:15,532 INFO Epoch:57 val_res:0.415511 +2025-04-18 05:02:35,767 INFO Epoch:58 train_loss:0.56471 +2025-04-18 05:02:44,330 INFO Epoch:58 val_res:0.424242 +2025-04-18 05:03:03,481 INFO Epoch:59 train_loss:0.60880 +2025-04-18 05:03:12,482 INFO Epoch:59 val_res:0.417565 +2025-04-18 05:03:31,450 INFO Epoch:60 train_loss:0.56771 +2025-04-18 05:03:39,882 INFO Epoch:60 val_res:0.419106 +2025-04-18 05:03:58,951 INFO Epoch:61 train_loss:0.63028 +2025-04-18 05:04:07,478 INFO Epoch:61 val_res:0.419106 +2025-04-18 05:04:28,223 INFO Epoch:62 train_loss:0.60784 +2025-04-18 05:04:37,896 INFO Epoch:62 val_res:0.419620 +2025-04-18 05:04:57,272 INFO Epoch:63 train_loss:0.54393 +2025-04-18 05:05:05,576 INFO Epoch:63 val_res:0.414484 +2025-04-18 05:05:22,852 INFO Epoch:64 train_loss:0.56644 +2025-04-18 05:05:31,652 INFO Epoch:64 val_res:0.430919 +2025-04-18 05:05:31,667 INFO Saving best model at Epoch 64 +2025-04-18 05:05:55,758 INFO Epoch:65 train_loss:0.57826 +2025-04-18 05:06:05,132 INFO Epoch:65 val_res:0.420647 +2025-04-18 05:06:22,699 INFO Epoch:66 train_loss:0.63242 +2025-04-18 05:06:33,843 INFO Epoch:66 val_res:0.419620 +2025-04-18 05:06:52,004 INFO Epoch:67 train_loss:0.59661 +2025-04-18 05:07:06,989 INFO Epoch:67 val_res:0.428865 +2025-04-18 05:07:28,888 INFO Epoch:68 train_loss:0.68459 +2025-04-18 05:07:38,168 INFO Epoch:68 val_res:0.413457 +2025-04-18 05:07:59,329 INFO Epoch:69 train_loss:0.59552 +2025-04-18 05:08:08,242 INFO Epoch:69 val_res:0.409348 +2025-04-18 05:08:34,232 INFO Epoch:70 train_loss:0.57174 +2025-04-18 05:08:43,681 INFO Epoch:70 val_res:0.419620 +2025-04-18 05:09:05,572 INFO Epoch:71 train_loss:0.55822 +2025-04-18 05:09:14,170 INFO Epoch:71 val_res:0.430406 +2025-04-18 05:09:35,727 INFO Epoch:72 train_loss:0.73385 +2025-04-18 05:09:44,632 INFO Epoch:72 val_res:0.401130 +2025-04-18 05:10:03,182 INFO Epoch:73 train_loss:0.60661 +2025-04-18 05:10:12,424 INFO Epoch:73 val_res:0.417052 +2025-04-18 05:10:31,781 INFO Epoch:74 train_loss:0.56273 +2025-04-18 05:10:40,963 INFO Epoch:74 val_res:0.411916 +2025-04-18 05:10:59,628 INFO Epoch:75 train_loss:0.54482 +2025-04-18 05:11:08,232 INFO Epoch:75 val_res:0.415511 +2025-04-18 05:11:25,186 INFO Epoch:76 train_loss:0.51125 +2025-04-18 05:11:33,800 INFO Epoch:76 val_res:0.411402 +2025-04-18 05:11:52,922 INFO Epoch:77 train_loss:0.57422 +2025-04-18 05:12:01,900 INFO Epoch:77 val_res:0.409348 +2025-04-18 05:12:19,511 INFO Epoch:78 train_loss:0.60001 +2025-04-18 05:12:28,126 INFO Epoch:78 val_res:0.416025 +2025-04-18 05:12:46,702 INFO Epoch:79 train_loss:0.50114 +2025-04-18 05:12:56,800 INFO Epoch:79 val_res:0.425783 +2025-04-18 05:13:15,212 INFO Epoch:80 train_loss:0.58572 +2025-04-18 05:13:24,071 INFO Epoch:80 val_res:0.419106 +2025-04-18 05:13:44,636 INFO Epoch:81 train_loss:0.55898 +2025-04-18 05:13:54,290 INFO Epoch:81 val_res:0.430406 +2025-04-18 05:14:13,557 INFO Epoch:82 train_loss:0.49970 +2025-04-18 05:14:22,617 INFO Epoch:82 val_res:0.432460 +2025-04-18 05:14:22,623 INFO Saving best model at Epoch 82 +2025-04-18 05:14:44,244 INFO Epoch:83 train_loss:0.55623 +2025-04-18 05:14:53,170 INFO Epoch:83 val_res:0.403698 +2025-04-18 05:15:11,949 INFO Epoch:84 train_loss:0.61318 +2025-04-18 05:15:20,896 INFO Epoch:84 val_res:0.386749 +2025-04-18 05:15:39,236 INFO Epoch:85 train_loss:0.60328 +2025-04-18 05:15:48,475 INFO Epoch:85 val_res:0.413457 +2025-04-18 05:16:07,525 INFO Epoch:86 train_loss:0.56810 +2025-04-18 05:16:16,264 INFO Epoch:86 val_res:0.428865 +2025-04-18 05:16:36,533 INFO Epoch:87 train_loss:0.57496 +2025-04-18 05:16:45,351 INFO Epoch:87 val_res:0.435542 +2025-04-18 05:16:45,351 INFO Saving best model at Epoch 87 +2025-04-18 05:17:06,736 INFO Epoch:88 train_loss:0.55082 +2025-04-18 05:17:15,628 INFO Epoch:88 val_res:0.425783 +2025-04-18 05:17:35,017 INFO Epoch:89 train_loss:0.48082 +2025-04-18 05:17:44,265 INFO Epoch:89 val_res:0.423729 +2025-04-18 05:18:02,884 INFO Epoch:90 train_loss:0.52122 +2025-04-18 05:18:11,692 INFO Epoch:90 val_res:0.439137 +2025-04-18 05:18:11,699 INFO Saving best model at Epoch 90 +2025-04-18 05:18:32,399 INFO Epoch:91 train_loss:0.53842 +2025-04-18 05:18:40,816 INFO Epoch:91 val_res:0.431433 +2025-04-18 05:19:00,392 INFO Epoch:92 train_loss:0.51377 +2025-04-18 05:19:09,643 INFO Epoch:92 val_res:0.438624 +2025-04-18 05:19:29,086 INFO Epoch:93 train_loss:0.53166 +2025-04-18 05:19:37,456 INFO Epoch:93 val_res:0.418593 +2025-04-18 05:19:56,044 INFO Epoch:94 train_loss:0.50574 +2025-04-18 05:20:07,832 INFO Epoch:94 val_res:0.414997 +2025-04-18 05:20:29,840 INFO Epoch:95 train_loss:0.53866 +2025-04-18 05:20:38,521 INFO Epoch:95 val_res:0.411402 +2025-04-18 05:20:56,263 INFO Epoch:96 train_loss:0.61310 +2025-04-18 05:21:05,508 INFO Epoch:96 val_res:0.426297 +2025-04-18 05:21:24,668 INFO Epoch:97 train_loss:0.76715 +2025-04-18 05:21:35,204 INFO Epoch:97 val_res:0.429892 +2025-04-18 05:21:54,858 INFO Epoch:98 train_loss:0.78634 +2025-04-18 05:22:05,509 INFO Epoch:98 val_res:0.409861 +2025-04-18 05:22:23,064 INFO Epoch:99 train_loss:0.65800 +2025-04-18 05:22:32,488 INFO Epoch:99 val_res:0.419620 +2025-04-18 05:22:33,428 INFO ===================================== +2025-04-18 05:22:33,440 INFO Start testing... +2025-04-18 05:22:33,442 INFO ===================================== +2025-04-18 05:24:03,230 INFO Incremental step 4 Testing res: 0.421348 +2025-04-18 05:24:03,238 INFO forgetting: 0.177228 +2025-04-18 05:24:03,247 INFO Average Accuracy: 0.607474 +2025-04-18 05:24:03,248 INFO Average Forgetting: 0.153724 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..732e9f324e3d71883060289be37f0d7f0d44911d Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..36d2c7c61fcdd6057e97362907f09d2709a2bd8d Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..c71f607812644e368906237fdd602db76c17ae3d Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..c140c2f2d6277980a71ace3d566b424423b31097 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..a0d9ae858bdf4b32aed13b8289c1aea83da93050 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..8901e55c8ad85a230aae14d3e03dfd4b70e9ee83 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..ad8d48f32398bec93c1b1f1dbea0ef4760603a9d Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..927c0d1bfbfc42d16f67dee87198ad60509da859 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..52007cceaefff8244028eeafdb55d5c5fd3d9a60 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..b9850df49c6c1d0db465694b962b2766ea8c0b82 Binary files /dev/null and b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..4bc93570b39202b4f129c2b74ce4bf88ecfb5d7b --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f5285c7e0b948a2c09f4cdac6f0c24b74dc736406faf8fcbdb89a264564440 +size 114105937 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..d87463fdf09312b32c4635a5f01a16abc91d1bf9 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e25f163ba13acd9f81c50dd7f21b1cbd0932f6d8e01ec3af655a2b96b4aae83e +size 114161233 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..407a1643a32f171bce994dc9af22df9e55e00050 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0b72c33fe2abe1d6b63d45aaa138232bd18e66361a074f8114586d305a4508 +size 114216721 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..dfcf42ddbcb14cad223f7a330b75b70d63cda713 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daca93272f17042dec89e6c578994ebc2d450f4700e41e1f4c871447f3be582e +size 114272017 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f3ea962417eeb9d677506cb265035d562dc33b05 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02265ea5c1f4dcdf798b3e28a8a265b9a1e69b772003eaeee49b9e2fbc3895f +size 114327313 diff --git a/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/train.log b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..e83d03752c9383ed8c2f342de36d36f41d5fe3b3 --- /dev/null +++ b/Audio Visual Continual Learning/LwF/save/ksounds/audio-visual/use-inverse_True-seed_0/train.log @@ -0,0 +1,1113 @@ +2025-04-18 01:59:24,014 INFO Namespace(class_num_per_step=6, dataset='ksounds', e_prompt=False, infer_batch_size=128, inverse=True, inverse_ends=100, inverse_starts=0, lr=0.01, lr_decay=False, max_epoches=100, milestones=[100], modality='audio-visual', num_classes=30, num_workers=4, prompt_dim=768, seed=0, train_batch_size=256, transfer=False, warm=False, weight_decay=0.0001) +2025-04-18 01:59:24,015 INFO Training start time: 2025-04-18 01:59:24.015925 +2025-04-18 01:59:25,502 INFO Incremental step: 0 +2025-04-18 02:02:51,352 INFO Epoch:0 train_loss:5.02258 +2025-04-18 02:03:15,574 INFO Epoch:0 val_res:0.458886 +2025-04-18 02:03:15,575 INFO Saving best model at Epoch 0 +2025-04-18 02:03:38,577 INFO Epoch:1 train_loss:4.33353 +2025-04-18 02:03:40,768 INFO Epoch:1 val_res:0.482759 +2025-04-18 02:03:40,769 INFO Saving best model at Epoch 1 +2025-04-18 02:03:55,792 INFO Epoch:2 train_loss:3.80189 +2025-04-18 02:03:57,903 INFO Epoch:2 val_res:0.644562 +2025-04-18 02:03:57,903 INFO Saving best model at Epoch 2 +2025-04-18 02:04:11,481 INFO Epoch:3 train_loss:3.34353 +2025-04-18 02:04:13,598 INFO Epoch:3 val_res:0.657825 +2025-04-18 02:04:13,598 INFO Saving best model at Epoch 3 +2025-04-18 02:04:31,509 INFO Epoch:4 train_loss:3.02479 +2025-04-18 02:04:34,174 INFO Epoch:4 val_res:0.734748 +2025-04-18 02:04:34,174 INFO Saving best model at Epoch 4 +2025-04-18 02:04:52,872 INFO Epoch:5 train_loss:2.74463 +2025-04-18 02:04:55,358 INFO Epoch:5 val_res:0.777188 +2025-04-18 02:04:55,358 INFO Saving best model at Epoch 5 +2025-04-18 02:05:09,909 INFO Epoch:6 train_loss:2.59444 +2025-04-18 02:05:12,214 INFO Epoch:6 val_res:0.798409 +2025-04-18 02:05:12,215 INFO Saving best model at Epoch 6 +2025-04-18 02:05:26,584 INFO Epoch:7 train_loss:2.41393 +2025-04-18 02:05:28,874 INFO Epoch:7 val_res:0.798409 +2025-04-18 02:05:44,926 INFO Epoch:8 train_loss:2.31799 +2025-04-18 02:05:47,385 INFO Epoch:8 val_res:0.798409 +2025-04-18 02:06:01,707 INFO Epoch:9 train_loss:2.27807 +2025-04-18 02:06:04,482 INFO Epoch:9 val_res:0.838196 +2025-04-18 02:06:04,482 INFO Saving best model at Epoch 9 +2025-04-18 02:06:23,958 INFO Epoch:10 train_loss:2.11887 +2025-04-18 02:06:26,449 INFO Epoch:10 val_res:0.856764 +2025-04-18 02:06:26,449 INFO Saving best model at Epoch 10 +2025-04-18 02:07:02,764 INFO Epoch:11 train_loss:1.99086 +2025-04-18 02:07:05,101 INFO Epoch:11 val_res:0.851459 +2025-04-18 02:07:22,306 INFO Epoch:12 train_loss:1.97089 +2025-04-18 02:07:25,437 INFO Epoch:12 val_res:0.835544 +2025-04-18 02:07:41,752 INFO Epoch:13 train_loss:1.89986 +2025-04-18 02:07:44,716 INFO Epoch:13 val_res:0.832891 +2025-04-18 02:08:00,713 INFO Epoch:14 train_loss:1.85421 +2025-04-18 02:08:02,984 INFO Epoch:14 val_res:0.862069 +2025-04-18 02:08:02,984 INFO Saving best model at Epoch 14 +2025-04-18 02:08:20,336 INFO Epoch:15 train_loss:1.81859 +2025-04-18 02:08:22,859 INFO Epoch:15 val_res:0.885942 +2025-04-18 02:08:22,859 INFO Saving best model at Epoch 15 +2025-04-18 02:08:41,699 INFO Epoch:16 train_loss:1.72604 +2025-04-18 02:08:43,928 INFO Epoch:16 val_res:0.793103 +2025-04-18 02:08:58,223 INFO Epoch:17 train_loss:1.77581 +2025-04-18 02:09:00,891 INFO Epoch:17 val_res:0.888594 +2025-04-18 02:09:00,892 INFO Saving best model at Epoch 17 +2025-04-18 02:09:17,264 INFO Epoch:18 train_loss:1.76941 +2025-04-18 02:09:19,383 INFO Epoch:18 val_res:0.893899 +2025-04-18 02:09:19,383 INFO Saving best model at Epoch 18 +2025-04-18 02:09:33,715 INFO Epoch:19 train_loss:1.69287 +2025-04-18 02:09:36,013 INFO Epoch:19 val_res:0.891247 +2025-04-18 02:09:48,045 INFO Epoch:20 train_loss:1.65879 +2025-04-18 02:09:50,205 INFO Epoch:20 val_res:0.888594 +2025-04-18 02:10:03,022 INFO Epoch:21 train_loss:1.68004 +2025-04-18 02:10:05,568 INFO Epoch:21 val_res:0.862069 +2025-04-18 02:10:20,023 INFO Epoch:22 train_loss:1.59439 +2025-04-18 02:10:22,186 INFO Epoch:22 val_res:0.912467 +2025-04-18 02:10:22,186 INFO Saving best model at Epoch 22 +2025-04-18 02:10:37,369 INFO Epoch:23 train_loss:1.53803 +2025-04-18 02:10:39,991 INFO Epoch:23 val_res:0.862069 +2025-04-18 02:10:53,462 INFO Epoch:24 train_loss:1.57634 +2025-04-18 02:10:55,999 INFO Epoch:24 val_res:0.893899 +2025-04-18 02:11:10,828 INFO Epoch:25 train_loss:1.57581 +2025-04-18 02:11:13,419 INFO Epoch:25 val_res:0.872679 +2025-04-18 02:11:27,095 INFO Epoch:26 train_loss:1.61244 +2025-04-18 02:11:29,245 INFO Epoch:26 val_res:0.867374 +2025-04-18 02:11:44,055 INFO Epoch:27 train_loss:1.58077 +2025-04-18 02:11:46,667 INFO Epoch:27 val_res:0.896552 +2025-04-18 02:12:03,098 INFO Epoch:28 train_loss:1.48160 +2025-04-18 02:12:05,912 INFO Epoch:28 val_res:0.920424 +2025-04-18 02:12:05,913 INFO Saving best model at Epoch 28 +2025-04-18 02:12:22,242 INFO Epoch:29 train_loss:1.46783 +2025-04-18 02:12:24,510 INFO Epoch:29 val_res:0.917772 +2025-04-18 02:12:37,416 INFO Epoch:30 train_loss:1.52086 +2025-04-18 02:12:40,620 INFO Epoch:30 val_res:0.901857 +2025-04-18 02:12:55,044 INFO Epoch:31 train_loss:1.53524 +2025-04-18 02:12:57,989 INFO Epoch:31 val_res:0.891247 +2025-04-18 02:13:14,044 INFO Epoch:32 train_loss:1.48146 +2025-04-18 02:13:16,356 INFO Epoch:32 val_res:0.893899 +2025-04-18 02:13:32,972 INFO Epoch:33 train_loss:1.44960 +2025-04-18 02:13:35,734 INFO Epoch:33 val_res:0.907162 +2025-04-18 02:13:53,314 INFO Epoch:34 train_loss:1.39090 +2025-04-18 02:13:56,077 INFO Epoch:34 val_res:0.901857 +2025-04-18 02:14:10,684 INFO Epoch:35 train_loss:1.50553 +2025-04-18 02:14:13,016 INFO Epoch:35 val_res:0.904509 +2025-04-18 02:14:26,945 INFO Epoch:36 train_loss:1.48877 +2025-04-18 02:14:29,306 INFO Epoch:36 val_res:0.891247 +2025-04-18 02:14:43,571 INFO Epoch:37 train_loss:1.44699 +2025-04-18 02:14:45,710 INFO Epoch:37 val_res:0.891247 +2025-04-18 02:14:57,819 INFO Epoch:38 train_loss:1.38603 +2025-04-18 02:14:59,882 INFO Epoch:38 val_res:0.896552 +2025-04-18 02:15:11,799 INFO Epoch:39 train_loss:1.43540 +2025-04-18 02:15:14,073 INFO Epoch:39 val_res:0.901857 +2025-04-18 02:15:29,506 INFO Epoch:40 train_loss:1.39841 +2025-04-18 02:15:31,985 INFO Epoch:40 val_res:0.925729 +2025-04-18 02:15:31,986 INFO Saving best model at Epoch 40 +2025-04-18 02:15:46,026 INFO Epoch:41 train_loss:1.41488 +2025-04-18 02:15:48,647 INFO Epoch:41 val_res:0.909814 +2025-04-18 02:16:01,655 INFO Epoch:42 train_loss:1.40223 +2025-04-18 02:16:04,256 INFO Epoch:42 val_res:0.907162 +2025-04-18 02:16:16,768 INFO Epoch:43 train_loss:1.37889 +2025-04-18 02:16:19,325 INFO Epoch:43 val_res:0.901857 +2025-04-18 02:16:31,872 INFO Epoch:44 train_loss:1.36736 +2025-04-18 02:16:34,547 INFO Epoch:44 val_res:0.904509 +2025-04-18 02:16:47,036 INFO Epoch:45 train_loss:1.32639 +2025-04-18 02:16:49,178 INFO Epoch:45 val_res:0.888594 +2025-04-18 02:17:01,285 INFO Epoch:46 train_loss:1.34647 +2025-04-18 02:17:03,809 INFO Epoch:46 val_res:0.907162 +2025-04-18 02:17:16,156 INFO Epoch:47 train_loss:1.32179 +2025-04-18 02:17:18,597 INFO Epoch:47 val_res:0.901857 +2025-04-18 02:17:33,673 INFO Epoch:48 train_loss:1.27824 +2025-04-18 02:17:36,163 INFO Epoch:48 val_res:0.920424 +2025-04-18 02:17:50,213 INFO Epoch:49 train_loss:1.28805 +2025-04-18 02:17:52,381 INFO Epoch:49 val_res:0.859416 +2025-04-18 02:18:05,408 INFO Epoch:50 train_loss:1.32093 +2025-04-18 02:18:07,706 INFO Epoch:50 val_res:0.904509 +2025-04-18 02:18:21,278 INFO Epoch:51 train_loss:1.24315 +2025-04-18 02:18:23,770 INFO Epoch:51 val_res:0.877984 +2025-04-18 02:18:37,994 INFO Epoch:52 train_loss:1.27458 +2025-04-18 02:18:40,301 INFO Epoch:52 val_res:0.923077 +2025-04-18 02:18:55,680 INFO Epoch:53 train_loss:1.30089 +2025-04-18 02:18:58,351 INFO Epoch:53 val_res:0.917772 +2025-04-18 02:19:13,292 INFO Epoch:54 train_loss:1.21562 +2025-04-18 02:19:15,710 INFO Epoch:54 val_res:0.923077 +2025-04-18 02:19:31,050 INFO Epoch:55 train_loss:1.24139 +2025-04-18 02:19:33,753 INFO Epoch:55 val_res:0.920424 +2025-04-18 02:19:49,140 INFO Epoch:56 train_loss:1.24108 +2025-04-18 02:19:51,485 INFO Epoch:56 val_res:0.891247 +2025-04-18 02:20:06,375 INFO Epoch:57 train_loss:1.20281 +2025-04-18 02:20:08,484 INFO Epoch:57 val_res:0.928382 +2025-04-18 02:20:08,484 INFO Saving best model at Epoch 57 +2025-04-18 02:20:22,953 INFO Epoch:58 train_loss:1.15713 +2025-04-18 02:20:25,204 INFO Epoch:58 val_res:0.936339 +2025-04-18 02:20:25,204 INFO Saving best model at Epoch 58 +2025-04-18 02:20:39,254 INFO Epoch:59 train_loss:1.17164 +2025-04-18 02:20:41,643 INFO Epoch:59 val_res:0.870027 +2025-04-18 02:20:57,026 INFO Epoch:60 train_loss:1.21613 +2025-04-18 02:20:59,229 INFO Epoch:60 val_res:0.917772 +2025-04-18 02:21:14,419 INFO Epoch:61 train_loss:1.19740 +2025-04-18 02:21:17,292 INFO Epoch:61 val_res:0.915119 +2025-04-18 02:21:33,881 INFO Epoch:62 train_loss:1.19675 +2025-04-18 02:21:36,756 INFO Epoch:62 val_res:0.883289 +2025-04-18 02:21:52,539 INFO Epoch:63 train_loss:1.15519 +2025-04-18 02:21:55,222 INFO Epoch:63 val_res:0.915119 +2025-04-18 02:22:11,414 INFO Epoch:64 train_loss:1.16206 +2025-04-18 02:22:13,579 INFO Epoch:64 val_res:0.928382 +2025-04-18 02:22:27,981 INFO Epoch:65 train_loss:1.15571 +2025-04-18 02:22:30,190 INFO Epoch:65 val_res:0.920424 +2025-04-18 02:22:43,838 INFO Epoch:66 train_loss:1.15391 +2025-04-18 02:22:46,446 INFO Epoch:66 val_res:0.896552 +2025-04-18 02:23:04,436 INFO Epoch:67 train_loss:1.16972 +2025-04-18 02:23:07,023 INFO Epoch:67 val_res:0.909814 +2025-04-18 02:23:21,731 INFO Epoch:68 train_loss:1.14851 +2025-04-18 02:23:23,862 INFO Epoch:68 val_res:0.920424 +2025-04-18 02:23:39,114 INFO Epoch:69 train_loss:1.15129 +2025-04-18 02:23:41,116 INFO Epoch:69 val_res:0.915119 +2025-04-18 02:23:56,792 INFO Epoch:70 train_loss:1.18546 +2025-04-18 02:23:58,989 INFO Epoch:70 val_res:0.904509 +2025-04-18 02:24:11,921 INFO Epoch:71 train_loss:1.14700 +2025-04-18 02:24:14,530 INFO Epoch:71 val_res:0.936339 +2025-04-18 02:24:31,139 INFO Epoch:72 train_loss:1.11511 +2025-04-18 02:24:33,436 INFO Epoch:72 val_res:0.909814 +2025-04-18 02:24:49,587 INFO Epoch:73 train_loss:1.13772 +2025-04-18 02:24:52,268 INFO Epoch:73 val_res:0.920424 +2025-04-18 02:25:09,012 INFO Epoch:74 train_loss:1.17029 +2025-04-18 02:25:11,694 INFO Epoch:74 val_res:0.925729 +2025-04-18 02:25:26,563 INFO Epoch:75 train_loss:1.06031 +2025-04-18 02:25:29,432 INFO Epoch:75 val_res:0.925729 +2025-04-18 02:25:44,796 INFO Epoch:76 train_loss:1.09343 +2025-04-18 02:25:47,838 INFO Epoch:76 val_res:0.923077 +2025-04-18 02:26:02,820 INFO Epoch:77 train_loss:1.14783 +2025-04-18 02:26:05,360 INFO Epoch:77 val_res:0.917772 +2025-04-18 02:26:20,375 INFO Epoch:78 train_loss:1.08606 +2025-04-18 02:26:22,998 INFO Epoch:78 val_res:0.923077 +2025-04-18 02:26:37,286 INFO Epoch:79 train_loss:1.04683 +2025-04-18 02:26:39,738 INFO Epoch:79 val_res:0.936339 +2025-04-18 02:26:53,747 INFO Epoch:80 train_loss:1.04500 +2025-04-18 02:26:56,054 INFO Epoch:80 val_res:0.938992 +2025-04-18 02:26:56,054 INFO Saving best model at Epoch 80 +2025-04-18 02:27:11,313 INFO Epoch:81 train_loss:1.12369 +2025-04-18 02:27:13,915 INFO Epoch:81 val_res:0.870027 +2025-04-18 02:27:27,744 INFO Epoch:82 train_loss:1.22020 +2025-04-18 02:27:30,466 INFO Epoch:82 val_res:0.856764 +2025-04-18 02:27:44,792 INFO Epoch:83 train_loss:1.13490 +2025-04-18 02:27:47,100 INFO Epoch:83 val_res:0.904509 +2025-04-18 02:28:01,030 INFO Epoch:84 train_loss:1.10272 +2025-04-18 02:28:03,368 INFO Epoch:84 val_res:0.917772 +2025-04-18 02:28:16,273 INFO Epoch:85 train_loss:1.13858 +2025-04-18 02:28:18,836 INFO Epoch:85 val_res:0.917772 +2025-04-18 02:28:31,396 INFO Epoch:86 train_loss:1.05898 +2025-04-18 02:28:34,021 INFO Epoch:86 val_res:0.915119 +2025-04-18 02:28:48,779 INFO Epoch:87 train_loss:1.04149 +2025-04-18 02:28:51,438 INFO Epoch:87 val_res:0.917772 +2025-04-18 02:29:05,655 INFO Epoch:88 train_loss:1.07066 +2025-04-18 02:29:08,069 INFO Epoch:88 val_res:0.925729 +2025-04-18 02:29:21,939 INFO Epoch:89 train_loss:1.05228 +2025-04-18 02:29:24,280 INFO Epoch:89 val_res:0.880637 +2025-04-18 02:29:39,670 INFO Epoch:90 train_loss:1.14692 +2025-04-18 02:29:42,255 INFO Epoch:90 val_res:0.891247 +2025-04-18 02:29:56,479 INFO Epoch:91 train_loss:1.15520 +2025-04-18 02:29:58,911 INFO Epoch:91 val_res:0.909814 +2025-04-18 02:30:12,494 INFO Epoch:92 train_loss:1.07946 +2025-04-18 02:30:14,831 INFO Epoch:92 val_res:0.917772 +2025-04-18 02:30:28,718 INFO Epoch:93 train_loss:1.05366 +2025-04-18 02:30:30,986 INFO Epoch:93 val_res:0.920424 +2025-04-18 02:30:42,939 INFO Epoch:94 train_loss:1.02265 +2025-04-18 02:30:45,102 INFO Epoch:94 val_res:0.928382 +2025-04-18 02:30:57,411 INFO Epoch:95 train_loss:1.02216 +2025-04-18 02:30:59,972 INFO Epoch:95 val_res:0.912467 +2025-04-18 02:31:15,423 INFO Epoch:96 train_loss:1.02484 +2025-04-18 02:31:17,957 INFO Epoch:96 val_res:0.925729 +2025-04-18 02:31:31,832 INFO Epoch:97 train_loss:1.04404 +2025-04-18 02:31:34,237 INFO Epoch:97 val_res:0.909814 +2025-04-18 02:31:48,013 INFO Epoch:98 train_loss:1.00680 +2025-04-18 02:31:50,200 INFO Epoch:98 val_res:0.909814 +2025-04-18 02:32:04,758 INFO Epoch:99 train_loss:1.03177 +2025-04-18 02:32:07,275 INFO Epoch:99 val_res:0.917772 +2025-04-18 02:32:08,022 INFO ===================================== +2025-04-18 02:32:08,023 INFO Start testing... +2025-04-18 02:32:08,023 INFO ===================================== +2025-04-18 02:32:26,606 INFO Incremental step 0 Testing res: 0.919355 +2025-04-18 02:32:26,610 INFO Incremental step: 1 +2025-04-18 02:35:06,967 INFO Epoch:0 train_loss:5.53913 +2025-04-18 02:35:26,472 INFO Epoch:0 val_res:0.448052 +2025-04-18 02:35:26,472 INFO Saving best model at Epoch 0 +2025-04-18 02:35:46,480 INFO Epoch:1 train_loss:4.88627 +2025-04-18 02:35:50,642 INFO Epoch:1 val_res:0.437662 +2025-04-18 02:36:07,253 INFO Epoch:2 train_loss:4.02806 +2025-04-18 02:36:11,865 INFO Epoch:2 val_res:0.431169 +2025-04-18 02:36:27,304 INFO Epoch:3 train_loss:3.90619 +2025-04-18 02:36:31,316 INFO Epoch:3 val_res:0.437662 +2025-04-18 02:36:47,423 INFO Epoch:4 train_loss:3.55260 +2025-04-18 02:36:51,550 INFO Epoch:4 val_res:0.461039 +2025-04-18 02:36:51,551 INFO Saving best model at Epoch 4 +2025-04-18 02:37:06,464 INFO Epoch:5 train_loss:3.30138 +2025-04-18 02:37:10,039 INFO Epoch:5 val_res:0.470130 +2025-04-18 02:37:10,040 INFO Saving best model at Epoch 5 +2025-04-18 02:37:24,303 INFO Epoch:6 train_loss:3.20013 +2025-04-18 02:37:27,878 INFO Epoch:6 val_res:0.471429 +2025-04-18 02:37:27,879 INFO Saving best model at Epoch 6 +2025-04-18 02:37:42,208 INFO Epoch:7 train_loss:3.24954 +2025-04-18 02:37:45,386 INFO Epoch:7 val_res:0.494805 +2025-04-18 02:37:45,387 INFO Saving best model at Epoch 7 +2025-04-18 02:38:00,568 INFO Epoch:8 train_loss:3.18941 +2025-04-18 02:38:03,923 INFO Epoch:8 val_res:0.467532 +2025-04-18 02:38:15,717 INFO Epoch:9 train_loss:3.09665 +2025-04-18 02:38:19,030 INFO Epoch:9 val_res:0.490909 +2025-04-18 02:38:30,951 INFO Epoch:10 train_loss:2.94399 +2025-04-18 02:38:34,144 INFO Epoch:10 val_res:0.475325 +2025-04-18 02:38:45,700 INFO Epoch:11 train_loss:2.80480 +2025-04-18 02:38:48,704 INFO Epoch:11 val_res:0.501299 +2025-04-18 02:38:48,705 INFO Saving best model at Epoch 11 +2025-04-18 02:39:05,024 INFO Epoch:12 train_loss:2.80243 +2025-04-18 02:39:08,810 INFO Epoch:12 val_res:0.489610 +2025-04-18 02:39:21,256 INFO Epoch:13 train_loss:2.78607 +2025-04-18 02:39:25,022 INFO Epoch:13 val_res:0.493506 +2025-04-18 02:39:37,358 INFO Epoch:14 train_loss:2.89015 +2025-04-18 02:39:41,411 INFO Epoch:14 val_res:0.503896 +2025-04-18 02:39:41,412 INFO Saving best model at Epoch 14 +2025-04-18 02:39:56,807 INFO Epoch:15 train_loss:2.82578 +2025-04-18 02:40:00,866 INFO Epoch:15 val_res:0.503896 +2025-04-18 02:40:15,128 INFO Epoch:16 train_loss:2.75799 +2025-04-18 02:40:18,786 INFO Epoch:16 val_res:0.512987 +2025-04-18 02:40:18,786 INFO Saving best model at Epoch 16 +2025-04-18 02:40:35,179 INFO Epoch:17 train_loss:2.58773 +2025-04-18 02:40:39,394 INFO Epoch:17 val_res:0.525974 +2025-04-18 02:40:39,395 INFO Saving best model at Epoch 17 +2025-04-18 02:40:55,113 INFO Epoch:18 train_loss:2.45227 +2025-04-18 02:40:59,023 INFO Epoch:18 val_res:0.544156 +2025-04-18 02:40:59,023 INFO Saving best model at Epoch 18 +2025-04-18 02:41:13,867 INFO Epoch:19 train_loss:2.54584 +2025-04-18 02:41:17,702 INFO Epoch:19 val_res:0.502597 +2025-04-18 02:41:32,227 INFO Epoch:20 train_loss:2.70553 +2025-04-18 02:41:36,537 INFO Epoch:20 val_res:0.483117 +2025-04-18 02:41:50,424 INFO Epoch:21 train_loss:2.63379 +2025-04-18 02:41:54,473 INFO Epoch:21 val_res:0.532468 +2025-04-18 02:42:09,030 INFO Epoch:22 train_loss:2.54191 +2025-04-18 02:42:13,309 INFO Epoch:22 val_res:0.536364 +2025-04-18 02:42:26,709 INFO Epoch:23 train_loss:2.61541 +2025-04-18 02:42:30,386 INFO Epoch:23 val_res:0.558442 +2025-04-18 02:42:30,387 INFO Saving best model at Epoch 23 +2025-04-18 02:42:45,236 INFO Epoch:24 train_loss:2.46372 +2025-04-18 02:42:49,367 INFO Epoch:24 val_res:0.550649 +2025-04-18 02:43:02,727 INFO Epoch:25 train_loss:2.47048 +2025-04-18 02:43:06,504 INFO Epoch:25 val_res:0.570130 +2025-04-18 02:43:06,505 INFO Saving best model at Epoch 25 +2025-04-18 02:43:20,426 INFO Epoch:26 train_loss:2.37552 +2025-04-18 02:43:24,299 INFO Epoch:26 val_res:0.592208 +2025-04-18 02:43:24,300 INFO Saving best model at Epoch 26 +2025-04-18 02:43:40,594 INFO Epoch:27 train_loss:2.45169 +2025-04-18 02:43:44,731 INFO Epoch:27 val_res:0.575325 +2025-04-18 02:43:56,013 INFO Epoch:28 train_loss:2.34557 +2025-04-18 02:43:59,472 INFO Epoch:28 val_res:0.577922 +2025-04-18 02:44:11,163 INFO Epoch:29 train_loss:2.24950 +2025-04-18 02:44:14,543 INFO Epoch:29 val_res:0.532468 +2025-04-18 02:44:28,643 INFO Epoch:30 train_loss:2.25353 +2025-04-18 02:44:32,698 INFO Epoch:30 val_res:0.564935 +2025-04-18 02:44:46,032 INFO Epoch:31 train_loss:2.27932 +2025-04-18 02:44:49,698 INFO Epoch:31 val_res:0.489610 +2025-04-18 02:45:02,675 INFO Epoch:32 train_loss:2.51921 +2025-04-18 02:45:06,156 INFO Epoch:32 val_res:0.557143 +2025-04-18 02:45:20,198 INFO Epoch:33 train_loss:2.41411 +2025-04-18 02:45:24,173 INFO Epoch:33 val_res:0.603896 +2025-04-18 02:45:24,174 INFO Saving best model at Epoch 33 +2025-04-18 02:45:40,144 INFO Epoch:34 train_loss:2.35738 +2025-04-18 02:45:44,112 INFO Epoch:34 val_res:0.581818 +2025-04-18 02:45:57,572 INFO Epoch:35 train_loss:2.19484 +2025-04-18 02:46:01,682 INFO Epoch:35 val_res:0.618182 +2025-04-18 02:46:01,683 INFO Saving best model at Epoch 35 +2025-04-18 02:46:17,153 INFO Epoch:36 train_loss:2.10821 +2025-04-18 02:46:21,091 INFO Epoch:36 val_res:0.603896 +2025-04-18 02:46:34,920 INFO Epoch:37 train_loss:2.04903 +2025-04-18 02:46:39,457 INFO Epoch:37 val_res:0.594805 +2025-04-18 02:46:53,411 INFO Epoch:38 train_loss:1.96350 +2025-04-18 02:46:57,108 INFO Epoch:38 val_res:0.600000 +2025-04-18 02:47:10,686 INFO Epoch:39 train_loss:2.05439 +2025-04-18 02:47:14,560 INFO Epoch:39 val_res:0.561039 +2025-04-18 02:47:28,882 INFO Epoch:40 train_loss:2.32551 +2025-04-18 02:47:32,741 INFO Epoch:40 val_res:0.570130 +2025-04-18 02:47:46,849 INFO Epoch:41 train_loss:2.22711 +2025-04-18 02:47:51,089 INFO Epoch:41 val_res:0.618182 +2025-04-18 02:48:06,094 INFO Epoch:42 train_loss:2.27466 +2025-04-18 02:48:09,898 INFO Epoch:42 val_res:0.585714 +2025-04-18 02:48:25,063 INFO Epoch:43 train_loss:2.00223 +2025-04-18 02:48:29,437 INFO Epoch:43 val_res:0.612987 +2025-04-18 02:48:44,496 INFO Epoch:44 train_loss:1.98662 +2025-04-18 02:48:48,423 INFO Epoch:44 val_res:0.622078 +2025-04-18 02:48:48,423 INFO Saving best model at Epoch 44 +2025-04-18 02:49:06,450 INFO Epoch:45 train_loss:1.93399 +2025-04-18 02:49:10,601 INFO Epoch:45 val_res:0.624675 +2025-04-18 02:49:10,602 INFO Saving best model at Epoch 45 +2025-04-18 02:49:27,082 INFO Epoch:46 train_loss:2.02834 +2025-04-18 02:49:31,176 INFO Epoch:46 val_res:0.587013 +2025-04-18 02:49:45,638 INFO Epoch:47 train_loss:2.10878 +2025-04-18 02:49:49,663 INFO Epoch:47 val_res:0.602597 +2025-04-18 02:50:05,658 INFO Epoch:48 train_loss:1.96414 +2025-04-18 02:50:09,486 INFO Epoch:48 val_res:0.612987 +2025-04-18 02:50:25,770 INFO Epoch:49 train_loss:1.86885 +2025-04-18 02:50:29,929 INFO Epoch:49 val_res:0.628571 +2025-04-18 02:50:29,929 INFO Saving best model at Epoch 49 +2025-04-18 02:50:45,688 INFO Epoch:50 train_loss:1.88406 +2025-04-18 02:50:49,712 INFO Epoch:50 val_res:0.627273 +2025-04-18 02:51:04,502 INFO Epoch:51 train_loss:1.91752 +2025-04-18 02:51:08,945 INFO Epoch:51 val_res:0.644156 +2025-04-18 02:51:08,945 INFO Saving best model at Epoch 51 +2025-04-18 02:51:28,077 INFO Epoch:52 train_loss:1.86741 +2025-04-18 02:51:32,491 INFO Epoch:52 val_res:0.601299 +2025-04-18 02:51:48,576 INFO Epoch:53 train_loss:1.97202 +2025-04-18 02:51:53,144 INFO Epoch:53 val_res:0.598701 +2025-04-18 02:52:10,964 INFO Epoch:54 train_loss:1.92447 +2025-04-18 02:52:15,683 INFO Epoch:54 val_res:0.614286 +2025-04-18 02:52:32,559 INFO Epoch:55 train_loss:1.73598 +2025-04-18 02:52:36,967 INFO Epoch:55 val_res:0.601299 +2025-04-18 02:52:51,677 INFO Epoch:56 train_loss:1.75879 +2025-04-18 02:52:55,871 INFO Epoch:56 val_res:0.633766 +2025-04-18 02:53:12,315 INFO Epoch:57 train_loss:1.91926 +2025-04-18 02:53:16,609 INFO Epoch:57 val_res:0.632468 +2025-04-18 02:53:30,891 INFO Epoch:58 train_loss:1.89611 +2025-04-18 02:53:35,295 INFO Epoch:58 val_res:0.642857 +2025-04-18 02:53:49,862 INFO Epoch:59 train_loss:1.87480 +2025-04-18 02:53:53,550 INFO Epoch:59 val_res:0.649351 +2025-04-18 02:53:53,550 INFO Saving best model at Epoch 59 +2025-04-18 02:54:08,188 INFO Epoch:60 train_loss:1.91497 +2025-04-18 02:54:11,868 INFO Epoch:60 val_res:0.627273 +2025-04-18 02:54:24,835 INFO Epoch:61 train_loss:1.85770 +2025-04-18 02:54:28,464 INFO Epoch:61 val_res:0.612987 +2025-04-18 02:54:41,823 INFO Epoch:62 train_loss:1.77873 +2025-04-18 02:54:45,639 INFO Epoch:62 val_res:0.638961 +2025-04-18 02:54:58,040 INFO Epoch:63 train_loss:1.69049 +2025-04-18 02:55:01,609 INFO Epoch:63 val_res:0.612987 +2025-04-18 02:55:17,558 INFO Epoch:64 train_loss:1.84401 +2025-04-18 02:55:21,821 INFO Epoch:64 val_res:0.583117 +2025-04-18 02:55:35,854 INFO Epoch:65 train_loss:1.77937 +2025-04-18 02:55:39,299 INFO Epoch:65 val_res:0.657143 +2025-04-18 02:55:39,300 INFO Saving best model at Epoch 65 +2025-04-18 02:55:53,938 INFO Epoch:66 train_loss:2.03615 +2025-04-18 02:55:57,406 INFO Epoch:66 val_res:0.674026 +2025-04-18 02:55:57,406 INFO Saving best model at Epoch 66 +2025-04-18 02:56:11,395 INFO Epoch:67 train_loss:1.81799 +2025-04-18 02:56:15,127 INFO Epoch:67 val_res:0.620779 +2025-04-18 02:56:27,738 INFO Epoch:68 train_loss:1.81274 +2025-04-18 02:56:31,241 INFO Epoch:68 val_res:0.648052 +2025-04-18 02:56:44,557 INFO Epoch:69 train_loss:1.77292 +2025-04-18 02:56:48,074 INFO Epoch:69 val_res:0.670130 +2025-04-18 02:57:00,520 INFO Epoch:70 train_loss:1.76301 +2025-04-18 02:57:04,028 INFO Epoch:70 val_res:0.661039 +2025-04-18 02:57:17,016 INFO Epoch:71 train_loss:1.72507 +2025-04-18 02:57:20,491 INFO Epoch:71 val_res:0.641558 +2025-04-18 02:57:33,275 INFO Epoch:72 train_loss:1.64362 +2025-04-18 02:57:36,875 INFO Epoch:72 val_res:0.646753 +2025-04-18 02:57:48,871 INFO Epoch:73 train_loss:1.70829 +2025-04-18 02:57:53,336 INFO Epoch:73 val_res:0.597403 +2025-04-18 02:58:06,329 INFO Epoch:74 train_loss:1.90508 +2025-04-18 02:58:09,914 INFO Epoch:74 val_res:0.628571 +2025-04-18 02:58:23,445 INFO Epoch:75 train_loss:1.68264 +2025-04-18 02:58:27,074 INFO Epoch:75 val_res:0.650649 +2025-04-18 02:58:43,180 INFO Epoch:76 train_loss:1.61551 +2025-04-18 02:58:47,352 INFO Epoch:76 val_res:0.637662 +2025-04-18 02:59:00,614 INFO Epoch:77 train_loss:1.67164 +2025-04-18 02:59:04,942 INFO Epoch:77 val_res:0.623377 +2025-04-18 02:59:18,270 INFO Epoch:78 train_loss:1.59349 +2025-04-18 02:59:22,592 INFO Epoch:78 val_res:0.668831 +2025-04-18 02:59:37,484 INFO Epoch:79 train_loss:1.59657 +2025-04-18 02:59:41,593 INFO Epoch:79 val_res:0.624675 +2025-04-18 02:59:55,821 INFO Epoch:80 train_loss:1.63482 +2025-04-18 02:59:59,848 INFO Epoch:80 val_res:0.609091 +2025-04-18 03:00:13,490 INFO Epoch:81 train_loss:1.76570 +2025-04-18 03:00:17,118 INFO Epoch:81 val_res:0.674026 +2025-04-18 03:00:31,008 INFO Epoch:82 train_loss:1.67491 +2025-04-18 03:00:34,780 INFO Epoch:82 val_res:0.683117 +2025-04-18 03:00:34,780 INFO Saving best model at Epoch 82 +2025-04-18 03:00:50,381 INFO Epoch:83 train_loss:1.60623 +2025-04-18 03:00:54,050 INFO Epoch:83 val_res:0.658442 +2025-04-18 03:01:07,104 INFO Epoch:84 train_loss:1.63209 +2025-04-18 03:01:10,563 INFO Epoch:84 val_res:0.645455 +2025-04-18 03:01:24,553 INFO Epoch:85 train_loss:1.55326 +2025-04-18 03:01:29,056 INFO Epoch:85 val_res:0.623377 +2025-04-18 03:01:44,138 INFO Epoch:86 train_loss:1.56699 +2025-04-18 03:01:47,574 INFO Epoch:86 val_res:0.667532 +2025-04-18 03:02:00,193 INFO Epoch:87 train_loss:1.54062 +2025-04-18 03:02:03,821 INFO Epoch:87 val_res:0.662338 +2025-04-18 03:02:16,586 INFO Epoch:88 train_loss:1.47618 +2025-04-18 03:02:20,242 INFO Epoch:88 val_res:0.618182 +2025-04-18 03:02:33,139 INFO Epoch:89 train_loss:1.56413 +2025-04-18 03:02:36,752 INFO Epoch:89 val_res:0.655844 +2025-04-18 03:02:49,119 INFO Epoch:90 train_loss:1.75321 +2025-04-18 03:02:52,590 INFO Epoch:90 val_res:0.627273 +2025-04-18 03:03:04,714 INFO Epoch:91 train_loss:1.79774 +2025-04-18 03:03:08,185 INFO Epoch:91 val_res:0.628571 +2025-04-18 03:03:20,329 INFO Epoch:92 train_loss:1.77802 +2025-04-18 03:03:23,878 INFO Epoch:92 val_res:0.577922 +2025-04-18 03:03:36,809 INFO Epoch:93 train_loss:1.79143 +2025-04-18 03:03:40,520 INFO Epoch:93 val_res:0.672727 +2025-04-18 03:03:52,829 INFO Epoch:94 train_loss:1.65102 +2025-04-18 03:03:56,342 INFO Epoch:94 val_res:0.635065 +2025-04-18 03:04:10,780 INFO Epoch:95 train_loss:1.55601 +2025-04-18 03:04:15,680 INFO Epoch:95 val_res:0.657143 +2025-04-18 03:04:29,950 INFO Epoch:96 train_loss:1.56289 +2025-04-18 03:04:33,969 INFO Epoch:96 val_res:0.683117 +2025-04-18 03:04:48,337 INFO Epoch:97 train_loss:1.54237 +2025-04-18 03:04:52,207 INFO Epoch:97 val_res:0.633766 +2025-04-18 03:05:06,655 INFO Epoch:98 train_loss:1.51858 +2025-04-18 03:05:11,513 INFO Epoch:98 val_res:0.681818 +2025-04-18 03:05:28,398 INFO Epoch:99 train_loss:1.58213 +2025-04-18 03:05:33,342 INFO Epoch:99 val_res:0.640260 +2025-04-18 03:05:34,580 INFO ===================================== +2025-04-18 03:05:34,581 INFO Start testing... +2025-04-18 03:05:34,581 INFO ===================================== +2025-04-18 03:06:01,070 INFO Incremental step 1 Testing res: 0.644156 +2025-04-18 03:06:01,074 INFO forgetting: 0.212366 +2025-04-18 03:06:01,081 INFO Incremental step: 2 +2025-04-18 03:09:05,639 INFO Epoch:0 train_loss:4.96995 +2025-04-18 03:09:30,439 INFO Epoch:0 val_res:0.427083 +2025-04-18 03:09:30,439 INFO Saving best model at Epoch 0 +2025-04-18 03:09:49,480 INFO Epoch:1 train_loss:4.06657 +2025-04-18 03:09:54,020 INFO Epoch:1 val_res:0.447917 +2025-04-18 03:09:54,020 INFO Saving best model at Epoch 1 +2025-04-18 03:10:10,890 INFO Epoch:2 train_loss:3.71180 +2025-04-18 03:10:15,591 INFO Epoch:2 val_res:0.448785 +2025-04-18 03:10:15,591 INFO Saving best model at Epoch 2 +2025-04-18 03:10:29,896 INFO Epoch:3 train_loss:3.48056 +2025-04-18 03:10:34,452 INFO Epoch:3 val_res:0.460069 +2025-04-18 03:10:34,452 INFO Saving best model at Epoch 3 +2025-04-18 03:10:49,201 INFO Epoch:4 train_loss:3.56286 +2025-04-18 03:10:54,176 INFO Epoch:4 val_res:0.417535 +2025-04-18 03:11:06,995 INFO Epoch:5 train_loss:3.28981 +2025-04-18 03:11:11,638 INFO Epoch:5 val_res:0.499132 +2025-04-18 03:11:11,639 INFO Saving best model at Epoch 5 +2025-04-18 03:11:27,425 INFO Epoch:6 train_loss:3.11354 +2025-04-18 03:11:32,111 INFO Epoch:6 val_res:0.495660 +2025-04-18 03:11:44,808 INFO Epoch:7 train_loss:3.07153 +2025-04-18 03:11:49,317 INFO Epoch:7 val_res:0.468750 +2025-04-18 03:12:02,236 INFO Epoch:8 train_loss:3.07140 +2025-04-18 03:12:07,234 INFO Epoch:8 val_res:0.417535 +2025-04-18 03:12:19,892 INFO Epoch:9 train_loss:3.17976 +2025-04-18 03:12:24,587 INFO Epoch:9 val_res:0.417535 +2025-04-18 03:12:37,076 INFO Epoch:10 train_loss:2.94433 +2025-04-18 03:12:41,736 INFO Epoch:10 val_res:0.472222 +2025-04-18 03:12:54,010 INFO Epoch:11 train_loss:2.95157 +2025-04-18 03:12:59,224 INFO Epoch:11 val_res:0.462674 +2025-04-18 03:13:11,511 INFO Epoch:12 train_loss:3.03112 +2025-04-18 03:13:16,265 INFO Epoch:12 val_res:0.485243 +2025-04-18 03:13:29,461 INFO Epoch:13 train_loss:3.05083 +2025-04-18 03:13:34,158 INFO Epoch:13 val_res:0.480903 +2025-04-18 03:13:46,474 INFO Epoch:14 train_loss:3.09356 +2025-04-18 03:13:51,064 INFO Epoch:14 val_res:0.489583 +2025-04-18 03:14:04,257 INFO Epoch:15 train_loss:2.93862 +2025-04-18 03:14:08,753 INFO Epoch:15 val_res:0.478299 +2025-04-18 03:14:21,531 INFO Epoch:16 train_loss:2.87149 +2025-04-18 03:14:26,222 INFO Epoch:16 val_res:0.493924 +2025-04-18 03:14:39,556 INFO Epoch:17 train_loss:2.83967 +2025-04-18 03:14:44,039 INFO Epoch:17 val_res:0.457465 +2025-04-18 03:14:56,504 INFO Epoch:18 train_loss:2.86236 +2025-04-18 03:15:01,194 INFO Epoch:18 val_res:0.496528 +2025-04-18 03:15:14,072 INFO Epoch:19 train_loss:2.80559 +2025-04-18 03:15:18,657 INFO Epoch:19 val_res:0.499132 +2025-04-18 03:15:31,075 INFO Epoch:20 train_loss:2.88780 +2025-04-18 03:15:35,918 INFO Epoch:20 val_res:0.500868 +2025-04-18 03:15:35,918 INFO Saving best model at Epoch 20 +2025-04-18 03:15:50,186 INFO Epoch:21 train_loss:2.76811 +2025-04-18 03:15:55,263 INFO Epoch:21 val_res:0.511285 +2025-04-18 03:15:55,264 INFO Saving best model at Epoch 21 +2025-04-18 03:16:10,701 INFO Epoch:22 train_loss:2.75986 +2025-04-18 03:16:15,556 INFO Epoch:22 val_res:0.517361 +2025-04-18 03:16:15,556 INFO Saving best model at Epoch 22 +2025-04-18 03:16:31,078 INFO Epoch:23 train_loss:2.74898 +2025-04-18 03:16:35,524 INFO Epoch:23 val_res:0.546875 +2025-04-18 03:16:35,525 INFO Saving best model at Epoch 23 +2025-04-18 03:16:49,486 INFO Epoch:24 train_loss:2.85496 +2025-04-18 03:16:54,216 INFO Epoch:24 val_res:0.501736 +2025-04-18 03:17:07,564 INFO Epoch:25 train_loss:2.69480 +2025-04-18 03:17:12,472 INFO Epoch:25 val_res:0.481771 +2025-04-18 03:17:25,387 INFO Epoch:26 train_loss:2.70750 +2025-04-18 03:17:29,998 INFO Epoch:26 val_res:0.490451 +2025-04-18 03:17:42,665 INFO Epoch:27 train_loss:2.63654 +2025-04-18 03:17:47,284 INFO Epoch:27 val_res:0.526910 +2025-04-18 03:18:00,212 INFO Epoch:28 train_loss:2.68555 +2025-04-18 03:18:04,758 INFO Epoch:28 val_res:0.489583 +2025-04-18 03:18:17,776 INFO Epoch:29 train_loss:2.62133 +2025-04-18 03:18:22,684 INFO Epoch:29 val_res:0.484375 +2025-04-18 03:18:35,339 INFO Epoch:30 train_loss:2.60482 +2025-04-18 03:18:40,321 INFO Epoch:30 val_res:0.526910 +2025-04-18 03:18:53,412 INFO Epoch:31 train_loss:2.56399 +2025-04-18 03:18:58,153 INFO Epoch:31 val_res:0.489583 +2025-04-18 03:19:11,929 INFO Epoch:32 train_loss:2.58316 +2025-04-18 03:19:16,937 INFO Epoch:32 val_res:0.524306 +2025-04-18 03:19:30,103 INFO Epoch:33 train_loss:2.45461 +2025-04-18 03:19:34,734 INFO Epoch:33 val_res:0.522569 +2025-04-18 03:19:47,759 INFO Epoch:34 train_loss:2.58634 +2025-04-18 03:19:52,504 INFO Epoch:34 val_res:0.521701 +2025-04-18 03:20:05,452 INFO Epoch:35 train_loss:2.61650 +2025-04-18 03:20:10,244 INFO Epoch:35 val_res:0.507812 +2025-04-18 03:20:23,154 INFO Epoch:36 train_loss:2.59125 +2025-04-18 03:20:27,855 INFO Epoch:36 val_res:0.485243 +2025-04-18 03:20:41,047 INFO Epoch:37 train_loss:2.42959 +2025-04-18 03:20:45,693 INFO Epoch:37 val_res:0.490451 +2025-04-18 03:20:57,941 INFO Epoch:38 train_loss:2.45236 +2025-04-18 03:21:02,728 INFO Epoch:38 val_res:0.483507 +2025-04-18 03:21:16,349 INFO Epoch:39 train_loss:2.33544 +2025-04-18 03:21:20,826 INFO Epoch:39 val_res:0.488715 +2025-04-18 03:21:33,309 INFO Epoch:40 train_loss:2.44588 +2025-04-18 03:21:38,198 INFO Epoch:40 val_res:0.504340 +2025-04-18 03:21:50,977 INFO Epoch:41 train_loss:2.34930 +2025-04-18 03:21:55,433 INFO Epoch:41 val_res:0.512153 +2025-04-18 03:22:08,621 INFO Epoch:42 train_loss:2.33581 +2025-04-18 03:22:13,631 INFO Epoch:42 val_res:0.498264 +2025-04-18 03:22:26,120 INFO Epoch:43 train_loss:2.19633 +2025-04-18 03:22:30,566 INFO Epoch:43 val_res:0.509549 +2025-04-18 03:22:43,610 INFO Epoch:44 train_loss:2.23487 +2025-04-18 03:22:48,093 INFO Epoch:44 val_res:0.513889 +2025-04-18 03:23:00,429 INFO Epoch:45 train_loss:2.41424 +2025-04-18 03:23:05,081 INFO Epoch:45 val_res:0.500868 +2025-04-18 03:23:17,757 INFO Epoch:46 train_loss:2.36027 +2025-04-18 03:23:22,519 INFO Epoch:46 val_res:0.512153 +2025-04-18 03:23:35,899 INFO Epoch:47 train_loss:2.38000 +2025-04-18 03:23:40,723 INFO Epoch:47 val_res:0.524306 +2025-04-18 03:23:53,190 INFO Epoch:48 train_loss:2.34870 +2025-04-18 03:23:57,703 INFO Epoch:48 val_res:0.518229 +2025-04-18 03:24:10,884 INFO Epoch:49 train_loss:2.22926 +2025-04-18 03:24:15,640 INFO Epoch:49 val_res:0.513889 +2025-04-18 03:24:27,674 INFO Epoch:50 train_loss:2.28817 +2025-04-18 03:24:32,402 INFO Epoch:50 val_res:0.493056 +2025-04-18 03:24:45,229 INFO Epoch:51 train_loss:2.35341 +2025-04-18 03:24:49,873 INFO Epoch:51 val_res:0.505208 +2025-04-18 03:25:01,966 INFO Epoch:52 train_loss:2.32851 +2025-04-18 03:25:06,660 INFO Epoch:52 val_res:0.492188 +2025-04-18 03:25:19,424 INFO Epoch:53 train_loss:2.30545 +2025-04-18 03:25:23,959 INFO Epoch:53 val_res:0.519965 +2025-04-18 03:25:36,253 INFO Epoch:54 train_loss:2.18258 +2025-04-18 03:25:41,334 INFO Epoch:54 val_res:0.513021 +2025-04-18 03:25:53,552 INFO Epoch:55 train_loss:2.20589 +2025-04-18 03:25:58,028 INFO Epoch:55 val_res:0.488715 +2025-04-18 03:26:11,218 INFO Epoch:56 train_loss:2.13539 +2025-04-18 03:26:15,753 INFO Epoch:56 val_res:0.513889 +2025-04-18 03:26:28,216 INFO Epoch:57 train_loss:2.07760 +2025-04-18 03:26:33,008 INFO Epoch:57 val_res:0.527778 +2025-04-18 03:26:46,058 INFO Epoch:58 train_loss:2.01405 +2025-04-18 03:26:50,756 INFO Epoch:58 val_res:0.529514 +2025-04-18 03:27:02,956 INFO Epoch:59 train_loss:2.16924 +2025-04-18 03:27:08,006 INFO Epoch:59 val_res:0.490451 +2025-04-18 03:27:21,251 INFO Epoch:60 train_loss:2.25333 +2025-04-18 03:27:25,797 INFO Epoch:60 val_res:0.518229 +2025-04-18 03:27:38,622 INFO Epoch:61 train_loss:2.14143 +2025-04-18 03:27:43,571 INFO Epoch:61 val_res:0.504340 +2025-04-18 03:27:56,126 INFO Epoch:62 train_loss:1.99620 +2025-04-18 03:28:00,616 INFO Epoch:62 val_res:0.523438 +2025-04-18 03:28:13,744 INFO Epoch:63 train_loss:1.98880 +2025-04-18 03:28:18,523 INFO Epoch:63 val_res:0.533854 +2025-04-18 03:28:31,083 INFO Epoch:64 train_loss:2.13075 +2025-04-18 03:28:35,656 INFO Epoch:64 val_res:0.495660 +2025-04-18 03:28:48,594 INFO Epoch:65 train_loss:2.05928 +2025-04-18 03:28:53,131 INFO Epoch:65 val_res:0.532118 +2025-04-18 03:29:05,774 INFO Epoch:66 train_loss:2.05575 +2025-04-18 03:29:10,262 INFO Epoch:66 val_res:0.546007 +2025-04-18 03:29:23,027 INFO Epoch:67 train_loss:2.13635 +2025-04-18 03:29:27,438 INFO Epoch:67 val_res:0.536458 +2025-04-18 03:29:40,185 INFO Epoch:68 train_loss:2.12554 +2025-04-18 03:29:44,903 INFO Epoch:68 val_res:0.540799 +2025-04-18 03:29:57,348 INFO Epoch:69 train_loss:2.09187 +2025-04-18 03:30:01,866 INFO Epoch:69 val_res:0.518229 +2025-04-18 03:30:15,357 INFO Epoch:70 train_loss:2.04652 +2025-04-18 03:30:20,011 INFO Epoch:70 val_res:0.527778 +2025-04-18 03:30:32,517 INFO Epoch:71 train_loss:2.05501 +2025-04-18 03:30:37,062 INFO Epoch:71 val_res:0.498264 +2025-04-18 03:30:50,102 INFO Epoch:72 train_loss:2.03315 +2025-04-18 03:30:54,800 INFO Epoch:72 val_res:0.513889 +2025-04-18 03:31:07,215 INFO Epoch:73 train_loss:2.13464 +2025-04-18 03:31:11,848 INFO Epoch:73 val_res:0.521701 +2025-04-18 03:31:25,063 INFO Epoch:74 train_loss:2.07220 +2025-04-18 03:31:29,867 INFO Epoch:74 val_res:0.497396 +2025-04-18 03:31:42,802 INFO Epoch:75 train_loss:1.95388 +2025-04-18 03:31:47,633 INFO Epoch:75 val_res:0.542535 +2025-04-18 03:32:00,482 INFO Epoch:76 train_loss:1.93157 +2025-04-18 03:32:05,349 INFO Epoch:76 val_res:0.556424 +2025-04-18 03:32:05,349 INFO Saving best model at Epoch 76 +2025-04-18 03:32:19,796 INFO Epoch:77 train_loss:1.95880 +2025-04-18 03:32:24,463 INFO Epoch:77 val_res:0.519097 +2025-04-18 03:32:37,747 INFO Epoch:78 train_loss:2.01738 +2025-04-18 03:32:42,557 INFO Epoch:78 val_res:0.558160 +2025-04-18 03:32:42,557 INFO Saving best model at Epoch 78 +2025-04-18 03:32:56,837 INFO Epoch:79 train_loss:1.96179 +2025-04-18 03:33:01,363 INFO Epoch:79 val_res:0.559028 +2025-04-18 03:33:01,364 INFO Saving best model at Epoch 79 +2025-04-18 03:33:19,546 INFO Epoch:80 train_loss:2.06678 +2025-04-18 03:33:24,229 INFO Epoch:80 val_res:0.546875 +2025-04-18 03:33:37,115 INFO Epoch:81 train_loss:1.98562 +2025-04-18 03:33:41,681 INFO Epoch:81 val_res:0.535590 +2025-04-18 03:33:54,958 INFO Epoch:82 train_loss:1.90017 +2025-04-18 03:33:59,544 INFO Epoch:82 val_res:0.550347 +2025-04-18 03:34:12,010 INFO Epoch:83 train_loss:1.91822 +2025-04-18 03:34:16,958 INFO Epoch:83 val_res:0.545139 +2025-04-18 03:34:30,500 INFO Epoch:84 train_loss:1.99093 +2025-04-18 03:34:35,156 INFO Epoch:84 val_res:0.546875 +2025-04-18 03:34:47,228 INFO Epoch:85 train_loss:1.94352 +2025-04-18 03:34:51,893 INFO Epoch:85 val_res:0.546875 +2025-04-18 03:35:05,136 INFO Epoch:86 train_loss:1.81971 +2025-04-18 03:35:09,909 INFO Epoch:86 val_res:0.542535 +2025-04-18 03:35:22,189 INFO Epoch:87 train_loss:1.88623 +2025-04-18 03:35:27,033 INFO Epoch:87 val_res:0.547743 +2025-04-18 03:35:40,274 INFO Epoch:88 train_loss:1.93162 +2025-04-18 03:35:44,892 INFO Epoch:88 val_res:0.538194 +2025-04-18 03:35:57,813 INFO Epoch:89 train_loss:2.01107 +2025-04-18 03:36:02,411 INFO Epoch:89 val_res:0.516493 +2025-04-18 03:36:15,018 INFO Epoch:90 train_loss:1.84677 +2025-04-18 03:36:19,419 INFO Epoch:90 val_res:0.552083 +2025-04-18 03:36:32,182 INFO Epoch:91 train_loss:1.80886 +2025-04-18 03:36:36,682 INFO Epoch:91 val_res:0.541667 +2025-04-18 03:36:49,465 INFO Epoch:92 train_loss:1.75232 +2025-04-18 03:36:54,070 INFO Epoch:92 val_res:0.535590 +2025-04-18 03:37:07,004 INFO Epoch:93 train_loss:1.79453 +2025-04-18 03:37:11,652 INFO Epoch:93 val_res:0.554688 +2025-04-18 03:37:24,591 INFO Epoch:94 train_loss:1.93094 +2025-04-18 03:37:29,382 INFO Epoch:94 val_res:0.547743 +2025-04-18 03:37:41,945 INFO Epoch:95 train_loss:1.87732 +2025-04-18 03:37:46,807 INFO Epoch:95 val_res:0.555556 +2025-04-18 03:38:00,106 INFO Epoch:96 train_loss:1.83550 +2025-04-18 03:38:04,701 INFO Epoch:96 val_res:0.550347 +2025-04-18 03:38:18,183 INFO Epoch:97 train_loss:1.89954 +2025-04-18 03:38:22,816 INFO Epoch:97 val_res:0.521701 +2025-04-18 03:38:35,160 INFO Epoch:98 train_loss:1.80016 +2025-04-18 03:38:39,538 INFO Epoch:98 val_res:0.556424 +2025-04-18 03:38:52,165 INFO Epoch:99 train_loss:1.72590 +2025-04-18 03:38:56,930 INFO Epoch:99 val_res:0.543403 +2025-04-18 03:38:57,729 INFO ===================================== +2025-04-18 03:38:57,730 INFO Start testing... +2025-04-18 03:38:57,730 INFO ===================================== +2025-04-18 03:39:21,327 INFO Incremental step 2 Testing res: 0.559792 +2025-04-18 03:39:21,329 INFO forgetting: 0.171131 +2025-04-18 03:39:21,332 INFO Incremental step: 3 +2025-04-18 03:44:31,026 INFO Epoch:0 train_loss:5.03080 +2025-04-18 03:45:09,658 INFO Epoch:0 val_res:0.404669 +2025-04-18 03:45:09,659 INFO Saving best model at Epoch 0 +2025-04-18 03:45:41,516 INFO Epoch:1 train_loss:4.94983 +2025-04-18 03:45:47,543 INFO Epoch:1 val_res:0.375486 +2025-04-18 03:46:02,208 INFO Epoch:2 train_loss:3.81857 +2025-04-18 03:46:07,566 INFO Epoch:2 val_res:0.397536 +2025-04-18 03:46:22,273 INFO Epoch:3 train_loss:3.49164 +2025-04-18 03:46:27,760 INFO Epoch:3 val_res:0.406615 +2025-04-18 03:46:27,760 INFO Saving best model at Epoch 3 +2025-04-18 03:46:43,621 INFO Epoch:4 train_loss:3.32523 +2025-04-18 03:46:49,013 INFO Epoch:4 val_res:0.423476 +2025-04-18 03:46:49,019 INFO Saving best model at Epoch 4 +2025-04-18 03:47:05,040 INFO Epoch:5 train_loss:3.04210 +2025-04-18 03:47:10,585 INFO Epoch:5 val_res:0.421530 +2025-04-18 03:47:27,426 INFO Epoch:6 train_loss:3.03344 +2025-04-18 03:47:35,328 INFO Epoch:6 val_res:0.434501 +2025-04-18 03:47:35,344 INFO Saving best model at Epoch 6 +2025-04-18 03:47:56,838 INFO Epoch:7 train_loss:2.90999 +2025-04-18 03:48:03,860 INFO Epoch:7 val_res:0.434501 +2025-04-18 03:48:22,459 INFO Epoch:8 train_loss:2.74356 +2025-04-18 03:48:29,615 INFO Epoch:8 val_res:0.448119 +2025-04-18 03:48:29,615 INFO Saving best model at Epoch 8 +2025-04-18 03:48:50,574 INFO Epoch:9 train_loss:2.66565 +2025-04-18 03:48:57,226 INFO Epoch:9 val_res:0.436446 +2025-04-18 03:49:15,924 INFO Epoch:10 train_loss:2.69649 +2025-04-18 03:49:23,028 INFO Epoch:10 val_res:0.440986 +2025-04-18 03:49:41,775 INFO Epoch:11 train_loss:2.49899 +2025-04-18 03:49:47,852 INFO Epoch:11 val_res:0.433204 +2025-04-18 03:50:05,013 INFO Epoch:12 train_loss:2.68536 +2025-04-18 03:50:11,863 INFO Epoch:12 val_res:0.415694 +2025-04-18 03:50:30,438 INFO Epoch:13 train_loss:2.67242 +2025-04-18 03:50:36,944 INFO Epoch:13 val_res:0.437095 +2025-04-18 03:50:54,499 INFO Epoch:14 train_loss:2.73180 +2025-04-18 03:51:00,812 INFO Epoch:14 val_res:0.444877 +2025-04-18 03:51:20,045 INFO Epoch:15 train_loss:2.36799 +2025-04-18 03:51:26,870 INFO Epoch:15 val_res:0.455901 +2025-04-18 03:51:26,872 INFO Saving best model at Epoch 15 +2025-04-18 03:51:48,990 INFO Epoch:16 train_loss:2.47794 +2025-04-18 03:51:56,072 INFO Epoch:16 val_res:0.459144 +2025-04-18 03:51:56,073 INFO Saving best model at Epoch 16 +2025-04-18 03:52:18,311 INFO Epoch:17 train_loss:2.55069 +2025-04-18 03:52:25,766 INFO Epoch:17 val_res:0.443580 +2025-04-18 03:52:45,934 INFO Epoch:18 train_loss:2.45450 +2025-04-18 03:52:53,236 INFO Epoch:18 val_res:0.450713 +2025-04-18 03:53:13,562 INFO Epoch:19 train_loss:2.37086 +2025-04-18 03:53:21,253 INFO Epoch:19 val_res:0.464332 +2025-04-18 03:53:21,254 INFO Saving best model at Epoch 19 +2025-04-18 03:53:43,433 INFO Epoch:20 train_loss:2.33948 +2025-04-18 03:53:51,618 INFO Epoch:20 val_res:0.463684 +2025-04-18 03:54:12,196 INFO Epoch:21 train_loss:2.31338 +2025-04-18 03:54:20,508 INFO Epoch:21 val_res:0.469520 +2025-04-18 03:54:20,509 INFO Saving best model at Epoch 21 +2025-04-18 03:54:46,412 INFO Epoch:22 train_loss:2.27009 +2025-04-18 03:54:54,108 INFO Epoch:22 val_res:0.472763 +2025-04-18 03:54:54,112 INFO Saving best model at Epoch 22 +2025-04-18 03:55:14,367 INFO Epoch:23 train_loss:2.25560 +2025-04-18 03:55:21,367 INFO Epoch:23 val_res:0.464332 +2025-04-18 03:55:41,528 INFO Epoch:24 train_loss:2.50011 +2025-04-18 03:55:48,820 INFO Epoch:24 val_res:0.434501 +2025-04-18 03:56:10,204 INFO Epoch:25 train_loss:2.57612 +2025-04-18 03:56:18,553 INFO Epoch:25 val_res:0.466278 +2025-04-18 03:56:37,706 INFO Epoch:26 train_loss:2.45922 +2025-04-18 03:56:44,466 INFO Epoch:26 val_res:0.432555 +2025-04-18 03:57:03,181 INFO Epoch:27 train_loss:2.38076 +2025-04-18 03:57:10,526 INFO Epoch:27 val_res:0.449416 +2025-04-18 03:57:28,833 INFO Epoch:28 train_loss:2.32906 +2025-04-18 03:57:36,192 INFO Epoch:28 val_res:0.452659 +2025-04-18 03:57:55,317 INFO Epoch:29 train_loss:2.26063 +2025-04-18 03:58:03,281 INFO Epoch:29 val_res:0.455901 +2025-04-18 03:58:23,286 INFO Epoch:30 train_loss:2.25925 +2025-04-18 03:58:30,399 INFO Epoch:30 val_res:0.454604 +2025-04-18 03:58:49,636 INFO Epoch:31 train_loss:2.20652 +2025-04-18 03:58:57,160 INFO Epoch:31 val_res:0.457198 +2025-04-18 03:59:16,260 INFO Epoch:32 train_loss:2.21872 +2025-04-18 03:59:23,991 INFO Epoch:32 val_res:0.486381 +2025-04-18 03:59:23,992 INFO Saving best model at Epoch 32 +2025-04-18 03:59:50,082 INFO Epoch:33 train_loss:2.24020 +2025-04-18 03:59:58,346 INFO Epoch:33 val_res:0.469520 +2025-04-18 04:00:16,398 INFO Epoch:34 train_loss:2.30348 +2025-04-18 04:00:24,272 INFO Epoch:34 val_res:0.456550 +2025-04-18 04:00:44,184 INFO Epoch:35 train_loss:2.28717 +2025-04-18 04:00:52,504 INFO Epoch:35 val_res:0.467575 +2025-04-18 04:01:11,394 INFO Epoch:36 train_loss:2.26100 +2025-04-18 04:01:17,802 INFO Epoch:36 val_res:0.480545 +2025-04-18 04:01:37,235 INFO Epoch:37 train_loss:2.14066 +2025-04-18 04:01:45,016 INFO Epoch:37 val_res:0.492866 +2025-04-18 04:01:45,024 INFO Saving best model at Epoch 37 +2025-04-18 04:02:08,111 INFO Epoch:38 train_loss:2.13003 +2025-04-18 04:02:15,532 INFO Epoch:38 val_res:0.472114 +2025-04-18 04:02:35,108 INFO Epoch:39 train_loss:2.06511 +2025-04-18 04:02:42,254 INFO Epoch:39 val_res:0.489624 +2025-04-18 04:03:00,991 INFO Epoch:40 train_loss:2.07710 +2025-04-18 04:03:07,697 INFO Epoch:40 val_res:0.486381 +2025-04-18 04:03:27,131 INFO Epoch:41 train_loss:2.04018 +2025-04-18 04:03:34,492 INFO Epoch:41 val_res:0.478599 +2025-04-18 04:03:54,156 INFO Epoch:42 train_loss:2.00817 +2025-04-18 04:04:01,879 INFO Epoch:42 val_res:0.488327 +2025-04-18 04:04:20,489 INFO Epoch:43 train_loss:2.04963 +2025-04-18 04:04:26,974 INFO Epoch:43 val_res:0.483787 +2025-04-18 04:04:44,927 INFO Epoch:44 train_loss:2.01169 +2025-04-18 04:04:51,996 INFO Epoch:44 val_res:0.488327 +2025-04-18 04:05:11,737 INFO Epoch:45 train_loss:2.07342 +2025-04-18 04:05:19,043 INFO Epoch:45 val_res:0.500648 +2025-04-18 04:05:19,052 INFO Saving best model at Epoch 45 +2025-04-18 04:05:40,178 INFO Epoch:46 train_loss:2.00102 +2025-04-18 04:05:47,224 INFO Epoch:46 val_res:0.483139 +2025-04-18 04:06:05,677 INFO Epoch:47 train_loss:2.01091 +2025-04-18 04:06:12,320 INFO Epoch:47 val_res:0.477951 +2025-04-18 04:06:31,201 INFO Epoch:48 train_loss:1.93526 +2025-04-18 04:06:38,672 INFO Epoch:48 val_res:0.489624 +2025-04-18 04:06:57,403 INFO Epoch:49 train_loss:2.00898 +2025-04-18 04:07:03,993 INFO Epoch:49 val_res:0.477951 +2025-04-18 04:07:24,502 INFO Epoch:50 train_loss:1.90443 +2025-04-18 04:07:32,819 INFO Epoch:50 val_res:0.464981 +2025-04-18 04:07:50,915 INFO Epoch:51 train_loss:1.83963 +2025-04-18 04:07:58,456 INFO Epoch:51 val_res:0.496109 +2025-04-18 04:08:18,726 INFO Epoch:52 train_loss:1.88469 +2025-04-18 04:08:25,868 INFO Epoch:52 val_res:0.483787 +2025-04-18 04:08:45,248 INFO Epoch:53 train_loss:1.84642 +2025-04-18 04:08:53,146 INFO Epoch:53 val_res:0.481193 +2025-04-18 04:09:11,918 INFO Epoch:54 train_loss:1.77469 +2025-04-18 04:09:19,524 INFO Epoch:54 val_res:0.498703 +2025-04-18 04:09:38,068 INFO Epoch:55 train_loss:1.81621 +2025-04-18 04:09:46,059 INFO Epoch:55 val_res:0.494163 +2025-04-18 04:10:04,332 INFO Epoch:56 train_loss:1.91409 +2025-04-18 04:10:10,948 INFO Epoch:56 val_res:0.489624 +2025-04-18 04:10:29,418 INFO Epoch:57 train_loss:1.75780 +2025-04-18 04:10:37,974 INFO Epoch:57 val_res:0.477951 +2025-04-18 04:10:57,058 INFO Epoch:58 train_loss:1.75062 +2025-04-18 04:11:04,997 INFO Epoch:58 val_res:0.494812 +2025-04-18 04:11:25,175 INFO Epoch:59 train_loss:1.91447 +2025-04-18 04:11:32,889 INFO Epoch:59 val_res:0.476005 +2025-04-18 04:11:51,572 INFO Epoch:60 train_loss:1.90509 +2025-04-18 04:11:59,021 INFO Epoch:60 val_res:0.492218 +2025-04-18 04:12:18,819 INFO Epoch:61 train_loss:1.92681 +2025-04-18 04:12:27,091 INFO Epoch:61 val_res:0.500000 +2025-04-18 04:12:48,940 INFO Epoch:62 train_loss:1.89096 +2025-04-18 04:12:57,420 INFO Epoch:62 val_res:0.487030 +2025-04-18 04:13:18,652 INFO Epoch:63 train_loss:1.90720 +2025-04-18 04:13:25,940 INFO Epoch:63 val_res:0.483139 +2025-04-18 04:13:46,551 INFO Epoch:64 train_loss:1.94274 +2025-04-18 04:13:54,640 INFO Epoch:64 val_res:0.462387 +2025-04-18 04:14:13,615 INFO Epoch:65 train_loss:2.02245 +2025-04-18 04:14:20,560 INFO Epoch:65 val_res:0.484436 +2025-04-18 04:14:41,693 INFO Epoch:66 train_loss:1.87896 +2025-04-18 04:14:49,442 INFO Epoch:66 val_res:0.505837 +2025-04-18 04:14:49,448 INFO Saving best model at Epoch 66 +2025-04-18 04:15:11,276 INFO Epoch:67 train_loss:1.82781 +2025-04-18 04:15:20,347 INFO Epoch:67 val_res:0.488975 +2025-04-18 04:15:40,657 INFO Epoch:68 train_loss:1.78980 +2025-04-18 04:15:48,232 INFO Epoch:68 val_res:0.464981 +2025-04-18 04:16:08,429 INFO Epoch:69 train_loss:1.84186 +2025-04-18 04:16:17,756 INFO Epoch:69 val_res:0.490921 +2025-04-18 04:16:38,239 INFO Epoch:70 train_loss:1.84536 +2025-04-18 04:16:46,445 INFO Epoch:70 val_res:0.501945 +2025-04-18 04:17:06,144 INFO Epoch:71 train_loss:1.84044 +2025-04-18 04:17:14,170 INFO Epoch:71 val_res:0.502594 +2025-04-18 04:17:34,341 INFO Epoch:72 train_loss:1.79975 +2025-04-18 04:17:41,634 INFO Epoch:72 val_res:0.479896 +2025-04-18 04:18:03,775 INFO Epoch:73 train_loss:1.84640 +2025-04-18 04:18:12,870 INFO Epoch:73 val_res:0.496109 +2025-04-18 04:18:32,035 INFO Epoch:74 train_loss:1.73023 +2025-04-18 04:18:39,566 INFO Epoch:74 val_res:0.492218 +2025-04-18 04:19:00,639 INFO Epoch:75 train_loss:1.74187 +2025-04-18 04:19:08,275 INFO Epoch:75 val_res:0.491569 +2025-04-18 04:19:28,843 INFO Epoch:76 train_loss:1.81337 +2025-04-18 04:19:36,862 INFO Epoch:76 val_res:0.498054 +2025-04-18 04:19:55,021 INFO Epoch:77 train_loss:1.63197 +2025-04-18 04:20:02,352 INFO Epoch:77 val_res:0.494812 +2025-04-18 04:20:21,476 INFO Epoch:78 train_loss:1.65776 +2025-04-18 04:20:29,420 INFO Epoch:78 val_res:0.485733 +2025-04-18 04:20:48,313 INFO Epoch:79 train_loss:1.56947 +2025-04-18 04:20:56,382 INFO Epoch:79 val_res:0.483787 +2025-04-18 04:21:17,390 INFO Epoch:80 train_loss:1.70049 +2025-04-18 04:21:24,864 INFO Epoch:80 val_res:0.497406 +2025-04-18 04:21:46,292 INFO Epoch:81 train_loss:1.74974 +2025-04-18 04:21:54,726 INFO Epoch:81 val_res:0.491569 +2025-04-18 04:22:14,044 INFO Epoch:82 train_loss:1.75600 +2025-04-18 04:22:23,104 INFO Epoch:82 val_res:0.499352 +2025-04-18 04:22:42,443 INFO Epoch:83 train_loss:1.81775 +2025-04-18 04:22:50,785 INFO Epoch:83 val_res:0.501945 +2025-04-18 04:23:12,140 INFO Epoch:84 train_loss:1.77331 +2025-04-18 04:23:20,972 INFO Epoch:84 val_res:0.483139 +2025-04-18 04:23:41,017 INFO Epoch:85 train_loss:1.68308 +2025-04-18 04:23:48,019 INFO Epoch:85 val_res:0.501297 +2025-04-18 04:24:06,481 INFO Epoch:86 train_loss:1.75167 +2025-04-18 04:24:13,816 INFO Epoch:86 val_res:0.474708 +2025-04-18 04:24:34,022 INFO Epoch:87 train_loss:1.74876 +2025-04-18 04:24:41,184 INFO Epoch:87 val_res:0.501945 +2025-04-18 04:25:03,285 INFO Epoch:88 train_loss:1.58547 +2025-04-18 04:25:10,812 INFO Epoch:88 val_res:0.503243 +2025-04-18 04:25:30,886 INFO Epoch:89 train_loss:1.60013 +2025-04-18 04:25:38,850 INFO Epoch:89 val_res:0.485084 +2025-04-18 04:25:59,269 INFO Epoch:90 train_loss:1.61297 +2025-04-18 04:26:07,243 INFO Epoch:90 val_res:0.494163 +2025-04-18 04:26:28,391 INFO Epoch:91 train_loss:1.55392 +2025-04-18 04:26:37,187 INFO Epoch:91 val_res:0.494163 +2025-04-18 04:26:57,929 INFO Epoch:92 train_loss:1.57498 +2025-04-18 04:27:06,054 INFO Epoch:92 val_res:0.468872 +2025-04-18 04:27:25,302 INFO Epoch:93 train_loss:1.55930 +2025-04-18 04:27:34,092 INFO Epoch:93 val_res:0.490921 +2025-04-18 04:27:54,269 INFO Epoch:94 train_loss:1.65742 +2025-04-18 04:28:02,344 INFO Epoch:94 val_res:0.487678 +2025-04-18 04:28:19,620 INFO Epoch:95 train_loss:1.60539 +2025-04-18 04:28:26,478 INFO Epoch:95 val_res:0.500000 +2025-04-18 04:28:44,306 INFO Epoch:96 train_loss:1.45960 +2025-04-18 04:28:51,286 INFO Epoch:96 val_res:0.479896 +2025-04-18 04:29:09,061 INFO Epoch:97 train_loss:1.80824 +2025-04-18 04:29:15,532 INFO Epoch:97 val_res:0.481193 +2025-04-18 04:29:34,627 INFO Epoch:98 train_loss:1.62806 +2025-04-18 04:29:41,946 INFO Epoch:98 val_res:0.496757 +2025-04-18 04:30:00,228 INFO Epoch:99 train_loss:1.56962 +2025-04-18 04:30:07,132 INFO Epoch:99 val_res:0.490921 +2025-04-18 04:30:08,149 INFO ===================================== +2025-04-18 04:30:08,167 INFO Start testing... +2025-04-18 04:30:08,177 INFO ===================================== +2025-04-18 04:30:23,940 INFO Incremental step 3 Testing res: 0.501618 +2025-04-18 04:30:23,943 INFO forgetting: 0.205615 +2025-04-18 04:30:23,946 INFO Incremental step: 4 +2025-04-18 04:34:59,860 INFO Epoch:0 train_loss:6.77222 +2025-04-18 04:35:44,024 INFO Epoch:0 val_res:0.375449 +2025-04-18 04:35:44,032 INFO Saving best model at Epoch 0 +2025-04-18 04:36:35,261 INFO Epoch:1 train_loss:4.81306 +2025-04-18 04:36:46,647 INFO Epoch:1 val_res:0.396507 +2025-04-18 04:36:46,648 INFO Saving best model at Epoch 1 +2025-04-18 04:37:11,817 INFO Epoch:2 train_loss:4.68019 +2025-04-18 04:37:22,326 INFO Epoch:2 val_res:0.391885 +2025-04-18 04:37:45,103 INFO Epoch:3 train_loss:4.03734 +2025-04-18 04:37:55,560 INFO Epoch:3 val_res:0.371341 +2025-04-18 04:38:15,752 INFO Epoch:4 train_loss:4.00788 +2025-04-18 04:38:27,008 INFO Epoch:4 val_res:0.384694 +2025-04-18 04:38:47,310 INFO Epoch:5 train_loss:3.77157 +2025-04-18 04:38:59,027 INFO Epoch:5 val_res:0.387262 +2025-04-18 04:39:18,653 INFO Epoch:6 train_loss:3.57360 +2025-04-18 04:39:27,696 INFO Epoch:6 val_res:0.375963 +2025-04-18 04:39:46,734 INFO Epoch:7 train_loss:3.43401 +2025-04-18 04:39:55,551 INFO Epoch:7 val_res:0.402671 +2025-04-18 04:39:55,552 INFO Saving best model at Epoch 7 +2025-04-18 04:40:16,590 INFO Epoch:8 train_loss:3.31836 +2025-04-18 04:40:25,670 INFO Epoch:8 val_res:0.385722 +2025-04-18 04:40:45,796 INFO Epoch:9 train_loss:3.09305 +2025-04-18 04:40:55,211 INFO Epoch:9 val_res:0.404725 +2025-04-18 04:40:55,221 INFO Saving best model at Epoch 9 +2025-04-18 04:41:16,594 INFO Epoch:10 train_loss:3.31356 +2025-04-18 04:41:28,010 INFO Epoch:10 val_res:0.384694 +2025-04-18 04:41:49,119 INFO Epoch:11 train_loss:3.12953 +2025-04-18 04:41:59,279 INFO Epoch:11 val_res:0.404212 +2025-04-18 04:42:20,487 INFO Epoch:12 train_loss:3.43004 +2025-04-18 04:42:31,149 INFO Epoch:12 val_res:0.400103 +2025-04-18 04:42:51,336 INFO Epoch:13 train_loss:3.32663 +2025-04-18 04:43:01,366 INFO Epoch:13 val_res:0.385722 +2025-04-18 04:43:21,680 INFO Epoch:14 train_loss:3.14463 +2025-04-18 04:43:31,076 INFO Epoch:14 val_res:0.380586 +2025-04-18 04:43:48,740 INFO Epoch:15 train_loss:3.08894 +2025-04-18 04:43:59,599 INFO Epoch:15 val_res:0.403184 +2025-04-18 04:44:18,967 INFO Epoch:16 train_loss:3.00455 +2025-04-18 04:44:28,498 INFO Epoch:16 val_res:0.383667 +2025-04-18 04:44:49,066 INFO Epoch:17 train_loss:3.07767 +2025-04-18 04:44:57,932 INFO Epoch:17 val_res:0.387776 +2025-04-18 04:45:16,867 INFO Epoch:18 train_loss:2.94262 +2025-04-18 04:45:25,989 INFO Epoch:18 val_res:0.400616 +2025-04-18 04:45:44,890 INFO Epoch:19 train_loss:2.96202 +2025-04-18 04:45:54,209 INFO Epoch:19 val_res:0.408320 +2025-04-18 04:45:54,215 INFO Saving best model at Epoch 19 +2025-04-18 04:46:16,124 INFO Epoch:20 train_loss:3.17552 +2025-04-18 04:46:27,168 INFO Epoch:20 val_res:0.400616 +2025-04-18 04:46:42,788 INFO Epoch:21 train_loss:3.12812 +2025-04-18 04:46:51,001 INFO Epoch:21 val_res:0.396507 +2025-04-18 04:47:08,743 INFO Epoch:22 train_loss:2.96042 +2025-04-18 04:47:17,378 INFO Epoch:22 val_res:0.397535 +2025-04-18 04:47:32,980 INFO Epoch:23 train_loss:2.94452 +2025-04-18 04:47:41,610 INFO Epoch:23 val_res:0.405239 +2025-04-18 04:48:00,469 INFO Epoch:24 train_loss:2.78377 +2025-04-18 04:48:08,828 INFO Epoch:24 val_res:0.407293 +2025-04-18 04:48:26,287 INFO Epoch:25 train_loss:2.87032 +2025-04-18 04:48:36,468 INFO Epoch:25 val_res:0.413970 +2025-04-18 04:48:36,468 INFO Saving best model at Epoch 25 +2025-04-18 04:48:57,453 INFO Epoch:26 train_loss:2.68088 +2025-04-18 04:49:05,796 INFO Epoch:26 val_res:0.403184 +2025-04-18 04:49:23,018 INFO Epoch:27 train_loss:2.65845 +2025-04-18 04:49:31,304 INFO Epoch:27 val_res:0.410375 +2025-04-18 04:49:47,379 INFO Epoch:28 train_loss:2.63474 +2025-04-18 04:49:56,128 INFO Epoch:28 val_res:0.410889 +2025-04-18 04:50:12,092 INFO Epoch:29 train_loss:2.67825 +2025-04-18 04:50:20,144 INFO Epoch:29 val_res:0.401130 +2025-04-18 04:50:36,683 INFO Epoch:30 train_loss:2.60470 +2025-04-18 04:50:45,566 INFO Epoch:30 val_res:0.408834 +2025-04-18 04:51:01,413 INFO Epoch:31 train_loss:2.69129 +2025-04-18 04:51:09,974 INFO Epoch:31 val_res:0.401130 +2025-04-18 04:51:29,136 INFO Epoch:32 train_loss:2.82683 +2025-04-18 04:51:37,114 INFO Epoch:32 val_res:0.414484 +2025-04-18 04:51:37,120 INFO Saving best model at Epoch 32 +2025-04-18 04:51:54,918 INFO Epoch:33 train_loss:2.86506 +2025-04-18 04:52:04,859 INFO Epoch:33 val_res:0.404212 +2025-04-18 04:52:26,777 INFO Epoch:34 train_loss:2.74163 +2025-04-18 04:52:38,172 INFO Epoch:34 val_res:0.420647 +2025-04-18 04:52:38,179 INFO Saving best model at Epoch 34 +2025-04-18 04:52:59,494 INFO Epoch:35 train_loss:2.67223 +2025-04-18 04:53:07,572 INFO Epoch:35 val_res:0.400616 +2025-04-18 04:53:24,266 INFO Epoch:36 train_loss:2.60874 +2025-04-18 04:53:33,261 INFO Epoch:36 val_res:0.404725 +2025-04-18 04:53:50,333 INFO Epoch:37 train_loss:2.71512 +2025-04-18 04:53:58,488 INFO Epoch:37 val_res:0.402157 +2025-04-18 04:54:15,546 INFO Epoch:38 train_loss:2.88160 +2025-04-18 04:54:25,104 INFO Epoch:38 val_res:0.429892 +2025-04-18 04:54:25,108 INFO Saving best model at Epoch 38 +2025-04-18 04:54:46,075 INFO Epoch:39 train_loss:2.71603 +2025-04-18 04:54:56,518 INFO Epoch:39 val_res:0.409348 +2025-04-18 04:55:14,872 INFO Epoch:40 train_loss:2.60273 +2025-04-18 04:55:25,364 INFO Epoch:40 val_res:0.403698 +2025-04-18 04:55:44,148 INFO Epoch:41 train_loss:2.51851 +2025-04-18 04:55:54,560 INFO Epoch:41 val_res:0.438624 +2025-04-18 04:55:54,565 INFO Saving best model at Epoch 41 +2025-04-18 04:56:14,299 INFO Epoch:42 train_loss:2.62705 +2025-04-18 04:56:23,276 INFO Epoch:42 val_res:0.408834 +2025-04-18 04:56:41,315 INFO Epoch:43 train_loss:2.62954 +2025-04-18 04:56:51,655 INFO Epoch:43 val_res:0.390858 +2025-04-18 04:57:08,004 INFO Epoch:44 train_loss:2.49033 +2025-04-18 04:57:17,814 INFO Epoch:44 val_res:0.427324 +2025-04-18 04:57:36,274 INFO Epoch:45 train_loss:2.51404 +2025-04-18 04:57:45,420 INFO Epoch:45 val_res:0.425270 +2025-04-18 04:58:01,625 INFO Epoch:46 train_loss:2.40689 +2025-04-18 04:58:10,573 INFO Epoch:46 val_res:0.424756 +2025-04-18 04:58:29,815 INFO Epoch:47 train_loss:2.45745 +2025-04-18 04:58:38,931 INFO Epoch:47 val_res:0.426810 +2025-04-18 04:58:56,994 INFO Epoch:48 train_loss:2.58995 +2025-04-18 04:59:06,932 INFO Epoch:48 val_res:0.407293 +2025-04-18 04:59:27,968 INFO Epoch:49 train_loss:2.62560 +2025-04-18 04:59:37,836 INFO Epoch:49 val_res:0.412943 +2025-04-18 05:00:00,442 INFO Epoch:50 train_loss:2.63621 +2025-04-18 05:00:08,932 INFO Epoch:50 val_res:0.410375 +2025-04-18 05:00:27,987 INFO Epoch:51 train_loss:2.66534 +2025-04-18 05:00:37,352 INFO Epoch:51 val_res:0.411402 +2025-04-18 05:00:57,399 INFO Epoch:52 train_loss:2.49866 +2025-04-18 05:01:06,189 INFO Epoch:52 val_res:0.411402 +2025-04-18 05:01:23,692 INFO Epoch:53 train_loss:2.43331 +2025-04-18 05:01:33,024 INFO Epoch:53 val_res:0.397021 +2025-04-18 05:01:53,698 INFO Epoch:54 train_loss:2.36466 +2025-04-18 05:02:02,764 INFO Epoch:54 val_res:0.413970 +2025-04-18 05:02:22,673 INFO Epoch:55 train_loss:2.33361 +2025-04-18 05:02:32,524 INFO Epoch:55 val_res:0.411402 +2025-04-18 05:02:52,106 INFO Epoch:56 train_loss:2.36286 +2025-04-18 05:03:03,446 INFO Epoch:56 val_res:0.418079 +2025-04-18 05:03:20,289 INFO Epoch:57 train_loss:2.26998 +2025-04-18 05:03:28,140 INFO Epoch:57 val_res:0.426297 +2025-04-18 05:03:47,525 INFO Epoch:58 train_loss:2.35902 +2025-04-18 05:03:55,531 INFO Epoch:58 val_res:0.424242 +2025-04-18 05:04:12,346 INFO Epoch:59 train_loss:2.56319 +2025-04-18 05:04:23,018 INFO Epoch:59 val_res:0.412943 +2025-04-18 05:04:43,142 INFO Epoch:60 train_loss:2.53493 +2025-04-18 05:04:51,478 INFO Epoch:60 val_res:0.402671 +2025-04-18 05:05:14,225 INFO Epoch:61 train_loss:2.49370 +2025-04-18 05:05:22,835 INFO Epoch:61 val_res:0.406266 +2025-04-18 05:05:41,640 INFO Epoch:62 train_loss:2.44980 +2025-04-18 05:05:51,351 INFO Epoch:62 val_res:0.424756 +2025-04-18 05:06:12,816 INFO Epoch:63 train_loss:2.38222 +2025-04-18 05:06:21,420 INFO Epoch:63 val_res:0.417052 +2025-04-18 05:06:41,330 INFO Epoch:64 train_loss:2.46935 +2025-04-18 05:06:49,776 INFO Epoch:64 val_res:0.418079 +2025-04-18 05:07:13,298 INFO Epoch:65 train_loss:2.33205 +2025-04-18 05:07:29,468 INFO Epoch:65 val_res:0.404212 +2025-04-18 05:07:52,929 INFO Epoch:66 train_loss:2.35207 +2025-04-18 05:08:03,101 INFO Epoch:66 val_res:0.416025 +2025-04-18 05:08:24,801 INFO Epoch:67 train_loss:2.39347 +2025-04-18 05:08:40,296 INFO Epoch:67 val_res:0.436055 +2025-04-18 05:09:02,605 INFO Epoch:68 train_loss:2.44075 +2025-04-18 05:09:13,702 INFO Epoch:68 val_res:0.422188 +2025-04-18 05:09:33,863 INFO Epoch:69 train_loss:2.36669 +2025-04-18 05:09:45,183 INFO Epoch:69 val_res:0.421674 +2025-04-18 05:10:04,789 INFO Epoch:70 train_loss:2.34141 +2025-04-18 05:10:14,454 INFO Epoch:70 val_res:0.415511 +2025-04-18 05:10:33,043 INFO Epoch:71 train_loss:2.34009 +2025-04-18 05:10:43,704 INFO Epoch:71 val_res:0.417052 +2025-04-18 05:11:05,346 INFO Epoch:72 train_loss:2.26649 +2025-04-18 05:11:15,124 INFO Epoch:72 val_res:0.426297 +2025-04-18 05:11:34,104 INFO Epoch:73 train_loss:2.29592 +2025-04-18 05:11:43,419 INFO Epoch:73 val_res:0.422188 +2025-04-18 05:12:06,642 INFO Epoch:74 train_loss:2.25035 +2025-04-18 05:12:17,335 INFO Epoch:74 val_res:0.437596 +2025-04-18 05:12:37,031 INFO Epoch:75 train_loss:2.28868 +2025-04-18 05:12:47,048 INFO Epoch:75 val_res:0.398562 +2025-04-18 05:13:06,356 INFO Epoch:76 train_loss:2.27483 +2025-04-18 05:13:17,456 INFO Epoch:76 val_res:0.420134 +2025-04-18 05:13:38,062 INFO Epoch:77 train_loss:2.36949 +2025-04-18 05:13:50,576 INFO Epoch:77 val_res:0.434001 +2025-04-18 05:14:12,578 INFO Epoch:78 train_loss:2.36949 +2025-04-18 05:14:23,552 INFO Epoch:78 val_res:0.402157 +2025-04-18 05:14:42,379 INFO Epoch:79 train_loss:2.30580 +2025-04-18 05:14:53,595 INFO Epoch:79 val_res:0.411916 +2025-04-18 05:15:11,744 INFO Epoch:80 train_loss:2.29424 +2025-04-18 05:15:24,524 INFO Epoch:80 val_res:0.421674 +2025-04-18 05:15:49,761 INFO Epoch:81 train_loss:2.23230 +2025-04-18 05:16:02,360 INFO Epoch:81 val_res:0.426297 +2025-04-18 05:16:23,155 INFO Epoch:82 train_loss:2.04883 +2025-04-18 05:16:33,960 INFO Epoch:82 val_res:0.420647 +2025-04-18 05:16:58,153 INFO Epoch:83 train_loss:2.13817 +2025-04-18 05:17:07,213 INFO Epoch:83 val_res:0.434515 +2025-04-18 05:17:27,130 INFO Epoch:84 train_loss:2.35567 +2025-04-18 05:17:37,038 INFO Epoch:84 val_res:0.428865 +2025-04-18 05:17:58,631 INFO Epoch:85 train_loss:2.16207 +2025-04-18 05:18:10,387 INFO Epoch:85 val_res:0.439137 +2025-04-18 05:18:10,387 INFO Saving best model at Epoch 85 +2025-04-18 05:18:31,911 INFO Epoch:86 train_loss:2.26461 +2025-04-18 05:18:43,996 INFO Epoch:86 val_res:0.426297 +2025-04-18 05:19:05,900 INFO Epoch:87 train_loss:2.20173 +2025-04-18 05:19:17,052 INFO Epoch:87 val_res:0.419106 +2025-04-18 05:19:37,606 INFO Epoch:88 train_loss:2.18346 +2025-04-18 05:19:49,615 INFO Epoch:88 val_res:0.424756 +2025-04-18 05:20:11,359 INFO Epoch:89 train_loss:2.04187 +2025-04-18 05:20:22,488 INFO Epoch:89 val_res:0.433487 +2025-04-18 05:20:44,382 INFO Epoch:90 train_loss:2.09798 +2025-04-18 05:20:54,840 INFO Epoch:90 val_res:0.421161 +2025-04-18 05:21:17,889 INFO Epoch:91 train_loss:2.14491 +2025-04-18 05:21:29,427 INFO Epoch:91 val_res:0.441705 +2025-04-18 05:21:29,432 INFO Saving best model at Epoch 91 +2025-04-18 05:21:53,376 INFO Epoch:92 train_loss:2.23545 +2025-04-18 05:22:04,901 INFO Epoch:92 val_res:0.422188 +2025-04-18 05:22:26,968 INFO Epoch:93 train_loss:2.17577 +2025-04-18 05:22:37,916 INFO Epoch:93 val_res:0.436055 +2025-04-18 05:22:57,370 INFO Epoch:94 train_loss:1.98924 +2025-04-18 05:23:06,027 INFO Epoch:94 val_res:0.432460 +2025-04-18 05:23:25,427 INFO Epoch:95 train_loss:2.06426 +2025-04-18 05:23:35,169 INFO Epoch:95 val_res:0.438624 +2025-04-18 05:23:54,051 INFO Epoch:96 train_loss:2.24327 +2025-04-18 05:24:02,561 INFO Epoch:96 val_res:0.430919 +2025-04-18 05:24:22,621 INFO Epoch:97 train_loss:2.16206 +2025-04-18 05:24:32,120 INFO Epoch:97 val_res:0.434001 +2025-04-18 05:24:51,434 INFO Epoch:98 train_loss:2.16592 +2025-04-18 05:25:00,780 INFO Epoch:98 val_res:0.432460 +2025-04-18 05:25:19,361 INFO Epoch:99 train_loss:2.22054 +2025-04-18 05:25:29,062 INFO Epoch:99 val_res:0.418593 +2025-04-18 05:25:29,915 INFO ===================================== +2025-04-18 05:25:29,927 INFO Start testing... +2025-04-18 05:25:29,934 INFO ===================================== +2025-04-18 05:25:41,202 INFO Incremental step 4 Testing res: 0.433095 +2025-04-18 05:25:41,207 INFO forgetting: 0.211952 +2025-04-18 05:25:41,210 INFO Average Accuracy: 0.613174 +2025-04-18 05:25:41,210 INFO Average Forgetting: 0.200266 diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..c8c5f586074ac51c745df3db9eec81c7a37c2891 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..af309a66370f62b9922955d0193d44add07ca04b Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..86128e44918b78171683e1e09a838b12e2455bf6 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..c94344b366c41292489e23323b00e223f6466d3d Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..13217bf07674f1a4f56404c2ba9cb5e9e4362343 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..1ed2990b16bd68c12765155a9e389589caaa0c8f Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..7b3a10ac3766be148705bb2c37e7a6fd18fece44 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..2f2b026744dd7332be9f5d5a8468dac6873fa86e Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9a52bab91e81f270100b17d2db7543838f380438 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10afc071b962fb706f4b8ba399af96af3bad8594f3b52e2ead1aeafd5cdaaf4d +size 114115153 diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..5e6497d90554b340e3567133c55a04127b4b69a5 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d9a235053f33231c08c4ee7213e96f2b66e60dc2078b207d0d2ae529211d0e +size 114179729 diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..84093767d66507a3f3da2f663460e12ae2119ec4 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9fa2fbb14c16d045aa7bcebc8af9c5a0859885b28a95086735579c9866e2501 +size 114244433 diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f824d183f77cf16dd6f2d4db1bdf9054c5b92128 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa445aae2d8fd0746b8fcb723641365fab53865da9c7c6671891a6c835fbb8c8 +size 114308945 diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/train.log b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..56bad481b1a5d877b69dfacc88e57171a472b0ab --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_False-seed_0/train.log @@ -0,0 +1,897 @@ +2025-04-18 06:26:03,175 INFO Namespace(class_num_per_step=7, dataset='AVE', e_prompt=False, exemplar_batch_size=128, fixed_fc=False, infer_batch_size=128, inverse=False, inverse_ends=100, inverse_starts=0, lr=0.01, lr_decay=False, max_epoches=100, memory_size=340, milestones=[100], modality='audio-visual', num_classes=28, num_workers=1, prompt_dim=768, seed=0, train_batch_size=256, weight_decay=0.0001) +2025-04-18 06:26:03,177 INFO Training start time: 2025-04-18 06:26:03.177691 +2025-04-18 06:32:11,392 INFO ***************New Step*************************** +2025-04-18 06:32:11,393 INFO Incremental step: 0 +2025-04-18 06:33:37,129 INFO Epoch:0 train_loss:1.94366 +2025-04-18 06:35:05,379 INFO Epoch:0 val_res:0.323810 +2025-04-18 06:35:05,380 INFO Saving best model at Epoch 0 +2025-04-18 06:35:16,257 INFO Epoch:1 train_loss:1.81413 +2025-04-18 06:35:17,430 INFO Epoch:1 val_res:0.342857 +2025-04-18 06:35:17,430 INFO Saving best model at Epoch 1 +2025-04-18 06:35:26,964 INFO Epoch:2 train_loss:1.65088 +2025-04-18 06:35:27,947 INFO Epoch:2 val_res:0.466667 +2025-04-18 06:35:27,947 INFO Saving best model at Epoch 2 +2025-04-18 06:35:36,681 INFO Epoch:3 train_loss:1.51719 +2025-04-18 06:35:37,834 INFO Epoch:3 val_res:0.485714 +2025-04-18 06:35:37,834 INFO Saving best model at Epoch 3 +2025-04-18 06:35:45,329 INFO Epoch:4 train_loss:1.36562 +2025-04-18 06:35:46,269 INFO Epoch:4 val_res:0.485714 +2025-04-18 06:35:52,240 INFO Epoch:5 train_loss:1.27456 +2025-04-18 06:35:53,258 INFO Epoch:5 val_res:0.590476 +2025-04-18 06:35:53,258 INFO Saving best model at Epoch 5 +2025-04-18 06:36:02,138 INFO Epoch:6 train_loss:1.18017 +2025-04-18 06:36:03,047 INFO Epoch:6 val_res:0.609524 +2025-04-18 06:36:03,048 INFO Saving best model at Epoch 6 +2025-04-18 06:36:12,434 INFO Epoch:7 train_loss:1.11857 +2025-04-18 06:36:13,480 INFO Epoch:7 val_res:0.561905 +2025-04-18 06:36:20,439 INFO Epoch:8 train_loss:1.05565 +2025-04-18 06:36:21,520 INFO Epoch:8 val_res:0.628571 +2025-04-18 06:36:21,520 INFO Saving best model at Epoch 8 +2025-04-18 06:36:32,981 INFO Epoch:9 train_loss:1.01613 +2025-04-18 06:36:34,119 INFO Epoch:9 val_res:0.609524 +2025-04-18 06:36:40,044 INFO Epoch:10 train_loss:0.94676 +2025-04-18 06:36:41,154 INFO Epoch:10 val_res:0.628571 +2025-04-18 06:36:47,251 INFO Epoch:11 train_loss:0.91281 +2025-04-18 06:36:48,316 INFO Epoch:11 val_res:0.609524 +2025-04-18 06:36:55,362 INFO Epoch:12 train_loss:0.87752 +2025-04-18 06:36:56,436 INFO Epoch:12 val_res:0.676190 +2025-04-18 06:36:56,436 INFO Saving best model at Epoch 12 +2025-04-18 06:37:04,162 INFO Epoch:13 train_loss:0.86002 +2025-04-18 06:37:05,139 INFO Epoch:13 val_res:0.647619 +2025-04-18 06:37:11,082 INFO Epoch:14 train_loss:0.83440 +2025-04-18 06:37:12,113 INFO Epoch:14 val_res:0.685714 +2025-04-18 06:37:12,114 INFO Saving best model at Epoch 14 +2025-04-18 06:37:19,947 INFO Epoch:15 train_loss:0.83222 +2025-04-18 06:37:20,960 INFO Epoch:15 val_res:0.695238 +2025-04-18 06:37:20,961 INFO Saving best model at Epoch 15 +2025-04-18 06:37:28,670 INFO Epoch:16 train_loss:0.78499 +2025-04-18 06:37:29,726 INFO Epoch:16 val_res:0.666667 +2025-04-18 06:37:36,440 INFO Epoch:17 train_loss:0.78663 +2025-04-18 06:37:37,512 INFO Epoch:17 val_res:0.714286 +2025-04-18 06:37:37,513 INFO Saving best model at Epoch 17 +2025-04-18 06:37:46,901 INFO Epoch:18 train_loss:0.76294 +2025-04-18 06:37:48,105 INFO Epoch:18 val_res:0.676190 +2025-04-18 06:37:54,449 INFO Epoch:19 train_loss:0.73460 +2025-04-18 06:37:55,688 INFO Epoch:19 val_res:0.695238 +2025-04-18 06:38:01,728 INFO Epoch:20 train_loss:0.70919 +2025-04-18 06:38:02,831 INFO Epoch:20 val_res:0.704762 +2025-04-18 06:38:09,075 INFO Epoch:21 train_loss:0.69607 +2025-04-18 06:38:10,123 INFO Epoch:21 val_res:0.733333 +2025-04-18 06:38:10,123 INFO Saving best model at Epoch 21 +2025-04-18 06:38:18,821 INFO Epoch:22 train_loss:0.71024 +2025-04-18 06:38:19,882 INFO Epoch:22 val_res:0.695238 +2025-04-18 06:38:25,750 INFO Epoch:23 train_loss:0.70429 +2025-04-18 06:38:26,929 INFO Epoch:23 val_res:0.676190 +2025-04-18 06:38:32,848 INFO Epoch:24 train_loss:0.69884 +2025-04-18 06:38:33,985 INFO Epoch:24 val_res:0.714286 +2025-04-18 06:38:39,771 INFO Epoch:25 train_loss:0.69681 +2025-04-18 06:38:40,874 INFO Epoch:25 val_res:0.685714 +2025-04-18 06:38:46,928 INFO Epoch:26 train_loss:0.68626 +2025-04-18 06:38:48,042 INFO Epoch:26 val_res:0.657143 +2025-04-18 06:38:54,463 INFO Epoch:27 train_loss:0.67970 +2025-04-18 06:38:55,525 INFO Epoch:27 val_res:0.638095 +2025-04-18 06:39:01,285 INFO Epoch:28 train_loss:0.67111 +2025-04-18 06:39:02,346 INFO Epoch:28 val_res:0.714286 +2025-04-18 06:39:08,451 INFO Epoch:29 train_loss:0.65985 +2025-04-18 06:39:09,438 INFO Epoch:29 val_res:0.704762 +2025-04-18 06:39:15,072 INFO Epoch:30 train_loss:0.65739 +2025-04-18 06:39:16,128 INFO Epoch:30 val_res:0.742857 +2025-04-18 06:39:16,128 INFO Saving best model at Epoch 30 +2025-04-18 06:39:24,479 INFO Epoch:31 train_loss:0.63277 +2025-04-18 06:39:25,510 INFO Epoch:31 val_res:0.723810 +2025-04-18 06:39:32,125 INFO Epoch:32 train_loss:0.60224 +2025-04-18 06:39:33,105 INFO Epoch:32 val_res:0.723810 +2025-04-18 06:39:38,996 INFO Epoch:33 train_loss:0.62836 +2025-04-18 06:39:39,967 INFO Epoch:33 val_res:0.742857 +2025-04-18 06:39:45,884 INFO Epoch:34 train_loss:0.62094 +2025-04-18 06:39:46,914 INFO Epoch:34 val_res:0.742857 +2025-04-18 06:39:53,024 INFO Epoch:35 train_loss:0.59332 +2025-04-18 06:39:54,057 INFO Epoch:35 val_res:0.752381 +2025-04-18 06:39:54,057 INFO Saving best model at Epoch 35 +2025-04-18 06:40:01,319 INFO Epoch:36 train_loss:0.56057 +2025-04-18 06:40:02,266 INFO Epoch:36 val_res:0.733333 +2025-04-18 06:40:08,261 INFO Epoch:37 train_loss:0.58499 +2025-04-18 06:40:09,256 INFO Epoch:37 val_res:0.733333 +2025-04-18 06:40:15,044 INFO Epoch:38 train_loss:0.57286 +2025-04-18 06:40:16,001 INFO Epoch:38 val_res:0.723810 +2025-04-18 06:40:21,857 INFO Epoch:39 train_loss:0.57325 +2025-04-18 06:40:22,909 INFO Epoch:39 val_res:0.723810 +2025-04-18 06:40:29,522 INFO Epoch:40 train_loss:0.55130 +2025-04-18 06:40:30,503 INFO Epoch:40 val_res:0.742857 +2025-04-18 06:40:36,434 INFO Epoch:41 train_loss:0.54877 +2025-04-18 06:40:37,512 INFO Epoch:41 val_res:0.752381 +2025-04-18 06:40:43,700 INFO Epoch:42 train_loss:0.54469 +2025-04-18 06:40:44,678 INFO Epoch:42 val_res:0.733333 +2025-04-18 06:40:50,815 INFO Epoch:43 train_loss:0.54767 +2025-04-18 06:40:51,804 INFO Epoch:43 val_res:0.733333 +2025-04-18 06:40:57,440 INFO Epoch:44 train_loss:0.54451 +2025-04-18 06:40:58,462 INFO Epoch:44 val_res:0.704762 +2025-04-18 06:41:04,142 INFO Epoch:45 train_loss:0.54941 +2025-04-18 06:41:05,133 INFO Epoch:45 val_res:0.704762 +2025-04-18 06:41:11,142 INFO Epoch:46 train_loss:0.52713 +2025-04-18 06:41:12,100 INFO Epoch:46 val_res:0.704762 +2025-04-18 06:41:18,218 INFO Epoch:47 train_loss:0.54137 +2025-04-18 06:41:19,121 INFO Epoch:47 val_res:0.733333 +2025-04-18 06:41:25,401 INFO Epoch:48 train_loss:0.51933 +2025-04-18 06:41:26,418 INFO Epoch:48 val_res:0.723810 +2025-04-18 06:41:32,124 INFO Epoch:49 train_loss:0.48752 +2025-04-18 06:41:33,123 INFO Epoch:49 val_res:0.761905 +2025-04-18 06:41:33,124 INFO Saving best model at Epoch 49 +2025-04-18 06:41:42,165 INFO Epoch:50 train_loss:0.49321 +2025-04-18 06:41:43,233 INFO Epoch:50 val_res:0.752381 +2025-04-18 06:41:48,949 INFO Epoch:51 train_loss:0.50473 +2025-04-18 06:41:49,901 INFO Epoch:51 val_res:0.723810 +2025-04-18 06:41:55,977 INFO Epoch:52 train_loss:0.49361 +2025-04-18 06:41:56,952 INFO Epoch:52 val_res:0.771429 +2025-04-18 06:41:56,952 INFO Saving best model at Epoch 52 +2025-04-18 06:42:06,785 INFO Epoch:53 train_loss:0.49045 +2025-04-18 06:42:07,893 INFO Epoch:53 val_res:0.752381 +2025-04-18 06:42:13,983 INFO Epoch:54 train_loss:0.48797 +2025-04-18 06:42:14,925 INFO Epoch:54 val_res:0.733333 +2025-04-18 06:42:20,473 INFO Epoch:55 train_loss:0.49981 +2025-04-18 06:42:21,430 INFO Epoch:55 val_res:0.723810 +2025-04-18 06:42:27,275 INFO Epoch:56 train_loss:0.50274 +2025-04-18 06:42:28,347 INFO Epoch:56 val_res:0.761905 +2025-04-18 06:42:34,370 INFO Epoch:57 train_loss:0.53160 +2025-04-18 06:42:35,322 INFO Epoch:57 val_res:0.666667 +2025-04-18 06:42:41,693 INFO Epoch:58 train_loss:0.51971 +2025-04-18 06:42:42,827 INFO Epoch:58 val_res:0.714286 +2025-04-18 06:42:48,857 INFO Epoch:59 train_loss:0.50277 +2025-04-18 06:42:49,765 INFO Epoch:59 val_res:0.685714 +2025-04-18 06:42:55,440 INFO Epoch:60 train_loss:0.51143 +2025-04-18 06:42:56,396 INFO Epoch:60 val_res:0.714286 +2025-04-18 06:43:01,886 INFO Epoch:61 train_loss:0.51438 +2025-04-18 06:43:02,823 INFO Epoch:61 val_res:0.723810 +2025-04-18 06:43:09,116 INFO Epoch:62 train_loss:0.50994 +2025-04-18 06:43:10,027 INFO Epoch:62 val_res:0.733333 +2025-04-18 06:43:16,302 INFO Epoch:63 train_loss:0.46063 +2025-04-18 06:43:17,289 INFO Epoch:63 val_res:0.752381 +2025-04-18 06:43:23,446 INFO Epoch:64 train_loss:0.46125 +2025-04-18 06:43:24,397 INFO Epoch:64 val_res:0.780952 +2025-04-18 06:43:24,397 INFO Saving best model at Epoch 64 +2025-04-18 06:43:31,738 INFO Epoch:65 train_loss:0.44128 +2025-04-18 06:43:32,685 INFO Epoch:65 val_res:0.742857 +2025-04-18 06:43:38,300 INFO Epoch:66 train_loss:0.46251 +2025-04-18 06:43:39,287 INFO Epoch:66 val_res:0.780952 +2025-04-18 06:43:45,212 INFO Epoch:67 train_loss:0.44230 +2025-04-18 06:43:46,190 INFO Epoch:67 val_res:0.790476 +2025-04-18 06:43:46,190 INFO Saving best model at Epoch 67 +2025-04-18 06:43:54,173 INFO Epoch:68 train_loss:0.42733 +2025-04-18 06:43:55,201 INFO Epoch:68 val_res:0.771429 +2025-04-18 06:44:01,910 INFO Epoch:69 train_loss:0.41541 +2025-04-18 06:44:03,025 INFO Epoch:69 val_res:0.790476 +2025-04-18 06:44:09,137 INFO Epoch:70 train_loss:0.40962 +2025-04-18 06:44:10,092 INFO Epoch:70 val_res:0.752381 +2025-04-18 06:44:15,491 INFO Epoch:71 train_loss:0.42097 +2025-04-18 06:44:16,503 INFO Epoch:71 val_res:0.761905 +2025-04-18 06:44:22,119 INFO Epoch:72 train_loss:0.43746 +2025-04-18 06:44:23,106 INFO Epoch:72 val_res:0.771429 +2025-04-18 06:44:29,148 INFO Epoch:73 train_loss:0.41530 +2025-04-18 06:44:30,123 INFO Epoch:73 val_res:0.780952 +2025-04-18 06:44:36,518 INFO Epoch:74 train_loss:0.41933 +2025-04-18 06:44:37,676 INFO Epoch:74 val_res:0.771429 +2025-04-18 06:44:43,937 INFO Epoch:75 train_loss:0.43234 +2025-04-18 06:44:45,198 INFO Epoch:75 val_res:0.780952 +2025-04-18 06:44:50,989 INFO Epoch:76 train_loss:0.41679 +2025-04-18 06:44:52,008 INFO Epoch:76 val_res:0.771429 +2025-04-18 06:44:58,420 INFO Epoch:77 train_loss:0.40569 +2025-04-18 06:44:59,594 INFO Epoch:77 val_res:0.800000 +2025-04-18 06:44:59,595 INFO Saving best model at Epoch 77 +2025-04-18 06:45:07,827 INFO Epoch:78 train_loss:0.40633 +2025-04-18 06:45:08,877 INFO Epoch:78 val_res:0.752381 +2025-04-18 06:45:15,098 INFO Epoch:79 train_loss:0.39803 +2025-04-18 06:45:16,219 INFO Epoch:79 val_res:0.780952 +2025-04-18 06:45:22,344 INFO Epoch:80 train_loss:0.39496 +2025-04-18 06:45:23,442 INFO Epoch:80 val_res:0.752381 +2025-04-18 06:45:30,015 INFO Epoch:81 train_loss:0.37422 +2025-04-18 06:45:30,979 INFO Epoch:81 val_res:0.752381 +2025-04-18 06:45:36,836 INFO Epoch:82 train_loss:0.39512 +2025-04-18 06:45:37,942 INFO Epoch:82 val_res:0.752381 +2025-04-18 06:45:43,714 INFO Epoch:83 train_loss:0.38352 +2025-04-18 06:45:44,741 INFO Epoch:83 val_res:0.780952 +2025-04-18 06:45:50,521 INFO Epoch:84 train_loss:0.39437 +2025-04-18 06:45:51,702 INFO Epoch:84 val_res:0.780952 +2025-04-18 06:45:58,178 INFO Epoch:85 train_loss:0.40136 +2025-04-18 06:45:59,143 INFO Epoch:85 val_res:0.723810 +2025-04-18 06:46:05,203 INFO Epoch:86 train_loss:0.38368 +2025-04-18 06:46:06,271 INFO Epoch:86 val_res:0.771429 +2025-04-18 06:46:12,097 INFO Epoch:87 train_loss:0.37420 +2025-04-18 06:46:13,149 INFO Epoch:87 val_res:0.790476 +2025-04-18 06:46:19,060 INFO Epoch:88 train_loss:0.36540 +2025-04-18 06:46:20,015 INFO Epoch:88 val_res:0.800000 +2025-04-18 06:46:25,502 INFO Epoch:89 train_loss:0.36395 +2025-04-18 06:46:26,515 INFO Epoch:89 val_res:0.771429 +2025-04-18 06:46:32,747 INFO Epoch:90 train_loss:0.36680 +2025-04-18 06:46:33,761 INFO Epoch:90 val_res:0.809524 +2025-04-18 06:46:33,762 INFO Saving best model at Epoch 90 +2025-04-18 06:46:43,224 INFO Epoch:91 train_loss:0.35851 +2025-04-18 06:46:44,144 INFO Epoch:91 val_res:0.761905 +2025-04-18 06:46:50,284 INFO Epoch:92 train_loss:0.36404 +2025-04-18 06:46:51,332 INFO Epoch:92 val_res:0.752381 +2025-04-18 06:46:57,448 INFO Epoch:93 train_loss:0.37612 +2025-04-18 06:46:58,357 INFO Epoch:93 val_res:0.809524 +2025-04-18 06:47:04,530 INFO Epoch:94 train_loss:0.34500 +2025-04-18 06:47:05,631 INFO Epoch:94 val_res:0.809524 +2025-04-18 06:47:11,773 INFO Epoch:95 train_loss:0.33947 +2025-04-18 06:47:12,832 INFO Epoch:95 val_res:0.780952 +2025-04-18 06:47:19,328 INFO Epoch:96 train_loss:0.33773 +2025-04-18 06:47:20,293 INFO Epoch:96 val_res:0.790476 +2025-04-18 06:47:27,048 INFO Epoch:97 train_loss:0.35440 +2025-04-18 06:47:28,154 INFO Epoch:97 val_res:0.790476 +2025-04-18 06:47:34,454 INFO Epoch:98 train_loss:0.37487 +2025-04-18 06:47:35,381 INFO Epoch:98 val_res:0.771429 +2025-04-18 06:47:41,016 INFO Epoch:99 train_loss:0.38234 +2025-04-18 06:47:41,958 INFO Epoch:99 val_res:0.800000 +2025-04-18 06:47:51,624 INFO ===================================== +2025-04-18 06:47:51,625 INFO Start testing... +2025-04-18 06:47:51,625 INFO ===================================== +2025-04-18 06:47:58,638 INFO Incremental step 0 Testing res: 0.750000 +2025-04-18 06:47:58,640 INFO ***************New Step*************************** +2025-04-18 06:47:58,640 INFO Incremental step: 1 +2025-04-18 06:47:58,897 INFO actual size of exemplar set: 336 +2025-04-18 06:52:12,679 INFO Epoch:0 train_loss:1.38113 +2025-04-18 06:54:01,786 INFO Epoch:0 val_res:0.394366 +2025-04-18 06:54:01,787 INFO Saving best model at Epoch 0 +2025-04-18 06:54:26,212 INFO Epoch:1 train_loss:1.24362 +2025-04-18 06:54:27,660 INFO Epoch:1 val_res:0.403756 +2025-04-18 06:54:27,660 INFO Saving best model at Epoch 1 +2025-04-18 06:54:46,329 INFO Epoch:2 train_loss:1.12464 +2025-04-18 06:54:48,161 INFO Epoch:2 val_res:0.399061 +2025-04-18 06:55:05,130 INFO Epoch:3 train_loss:1.05411 +2025-04-18 06:55:06,917 INFO Epoch:3 val_res:0.399061 +2025-04-18 06:55:23,937 INFO Epoch:4 train_loss:0.94821 +2025-04-18 06:55:25,517 INFO Epoch:4 val_res:0.399061 +2025-04-18 06:55:42,989 INFO Epoch:5 train_loss:0.92111 +2025-04-18 06:55:44,668 INFO Epoch:5 val_res:0.384977 +2025-04-18 06:56:01,536 INFO Epoch:6 train_loss:0.89499 +2025-04-18 06:56:03,445 INFO Epoch:6 val_res:0.413146 +2025-04-18 06:56:03,446 INFO Saving best model at Epoch 6 +2025-04-18 06:56:26,789 INFO Epoch:7 train_loss:0.84069 +2025-04-18 06:56:28,338 INFO Epoch:7 val_res:0.417840 +2025-04-18 06:56:28,338 INFO Saving best model at Epoch 7 +2025-04-18 06:56:48,919 INFO Epoch:8 train_loss:0.80719 +2025-04-18 06:56:50,754 INFO Epoch:8 val_res:0.431925 +2025-04-18 06:56:50,754 INFO Saving best model at Epoch 8 +2025-04-18 06:57:11,924 INFO Epoch:9 train_loss:0.78478 +2025-04-18 06:57:14,070 INFO Epoch:9 val_res:0.427230 +2025-04-18 06:57:30,394 INFO Epoch:10 train_loss:0.77145 +2025-04-18 06:57:32,284 INFO Epoch:10 val_res:0.399061 +2025-04-18 06:57:49,451 INFO Epoch:11 train_loss:0.75674 +2025-04-18 06:57:51,383 INFO Epoch:11 val_res:0.413146 +2025-04-18 06:58:08,682 INFO Epoch:12 train_loss:0.72450 +2025-04-18 06:58:10,155 INFO Epoch:12 val_res:0.422535 +2025-04-18 06:58:26,150 INFO Epoch:13 train_loss:0.74728 +2025-04-18 06:58:27,585 INFO Epoch:13 val_res:0.436620 +2025-04-18 06:58:27,585 INFO Saving best model at Epoch 13 +2025-04-18 06:58:46,082 INFO Epoch:14 train_loss:0.74472 +2025-04-18 06:58:47,613 INFO Epoch:14 val_res:0.422535 +2025-04-18 06:59:02,748 INFO Epoch:15 train_loss:0.71059 +2025-04-18 06:59:04,227 INFO Epoch:15 val_res:0.422535 +2025-04-18 06:59:20,156 INFO Epoch:16 train_loss:0.71293 +2025-04-18 06:59:21,650 INFO Epoch:16 val_res:0.431925 +2025-04-18 06:59:36,482 INFO Epoch:17 train_loss:0.69713 +2025-04-18 06:59:37,951 INFO Epoch:17 val_res:0.413146 +2025-04-18 06:59:53,211 INFO Epoch:18 train_loss:0.70764 +2025-04-18 06:59:54,805 INFO Epoch:18 val_res:0.422535 +2025-04-18 07:00:11,552 INFO Epoch:19 train_loss:0.67853 +2025-04-18 07:00:13,452 INFO Epoch:19 val_res:0.441315 +2025-04-18 07:00:13,453 INFO Saving best model at Epoch 19 +2025-04-18 07:00:32,929 INFO Epoch:20 train_loss:0.67452 +2025-04-18 07:00:34,602 INFO Epoch:20 val_res:0.427230 +2025-04-18 07:00:51,786 INFO Epoch:21 train_loss:0.68211 +2025-04-18 07:00:53,356 INFO Epoch:21 val_res:0.436620 +2025-04-18 07:01:11,131 INFO Epoch:22 train_loss:0.64594 +2025-04-18 07:01:12,742 INFO Epoch:22 val_res:0.464789 +2025-04-18 07:01:12,742 INFO Saving best model at Epoch 22 +2025-04-18 07:01:34,278 INFO Epoch:23 train_loss:0.60204 +2025-04-18 07:01:35,944 INFO Epoch:23 val_res:0.488263 +2025-04-18 07:01:35,944 INFO Saving best model at Epoch 23 +2025-04-18 07:01:56,259 INFO Epoch:24 train_loss:0.58735 +2025-04-18 07:01:58,169 INFO Epoch:24 val_res:0.478873 +2025-04-18 07:02:16,825 INFO Epoch:25 train_loss:0.58137 +2025-04-18 07:02:18,966 INFO Epoch:25 val_res:0.516432 +2025-04-18 07:02:18,967 INFO Saving best model at Epoch 25 +2025-04-18 07:02:42,308 INFO Epoch:26 train_loss:0.58683 +2025-04-18 07:02:43,805 INFO Epoch:26 val_res:0.497653 +2025-04-18 07:02:59,477 INFO Epoch:27 train_loss:0.57070 +2025-04-18 07:03:01,119 INFO Epoch:27 val_res:0.516432 +2025-04-18 07:03:17,223 INFO Epoch:28 train_loss:0.56747 +2025-04-18 07:03:18,857 INFO Epoch:28 val_res:0.530516 +2025-04-18 07:03:18,857 INFO Saving best model at Epoch 28 +2025-04-18 07:03:38,883 INFO Epoch:29 train_loss:0.55522 +2025-04-18 07:03:40,573 INFO Epoch:29 val_res:0.521127 +2025-04-18 07:03:56,474 INFO Epoch:30 train_loss:0.54022 +2025-04-18 07:03:58,055 INFO Epoch:30 val_res:0.521127 +2025-04-18 07:04:16,459 INFO Epoch:31 train_loss:0.55332 +2025-04-18 07:04:18,693 INFO Epoch:31 val_res:0.525822 +2025-04-18 07:04:35,787 INFO Epoch:32 train_loss:0.54325 +2025-04-18 07:04:37,539 INFO Epoch:32 val_res:0.544601 +2025-04-18 07:04:37,539 INFO Saving best model at Epoch 32 +2025-04-18 07:05:00,286 INFO Epoch:33 train_loss:0.51823 +2025-04-18 07:05:02,213 INFO Epoch:33 val_res:0.553991 +2025-04-18 07:05:02,213 INFO Saving best model at Epoch 33 +2025-04-18 07:05:21,311 INFO Epoch:34 train_loss:0.53409 +2025-04-18 07:05:23,238 INFO Epoch:34 val_res:0.553991 +2025-04-18 07:05:39,938 INFO Epoch:35 train_loss:0.51948 +2025-04-18 07:05:41,756 INFO Epoch:35 val_res:0.572770 +2025-04-18 07:05:41,756 INFO Saving best model at Epoch 35 +2025-04-18 07:06:01,038 INFO Epoch:36 train_loss:0.51920 +2025-04-18 07:06:02,810 INFO Epoch:36 val_res:0.553991 +2025-04-18 07:06:20,500 INFO Epoch:37 train_loss:0.50308 +2025-04-18 07:06:22,310 INFO Epoch:37 val_res:0.553991 +2025-04-18 07:06:38,811 INFO Epoch:38 train_loss:0.51450 +2025-04-18 07:06:40,768 INFO Epoch:38 val_res:0.549296 +2025-04-18 07:06:59,061 INFO Epoch:39 train_loss:0.50047 +2025-04-18 07:07:00,750 INFO Epoch:39 val_res:0.553991 +2025-04-18 07:07:18,713 INFO Epoch:40 train_loss:0.48787 +2025-04-18 07:07:20,255 INFO Epoch:40 val_res:0.558685 +2025-04-18 07:07:37,679 INFO Epoch:41 train_loss:0.50049 +2025-04-18 07:07:39,371 INFO Epoch:41 val_res:0.572770 +2025-04-18 07:07:56,914 INFO Epoch:42 train_loss:0.47938 +2025-04-18 07:07:59,060 INFO Epoch:42 val_res:0.568075 +2025-04-18 07:08:16,606 INFO Epoch:43 train_loss:0.47065 +2025-04-18 07:08:18,497 INFO Epoch:43 val_res:0.572770 +2025-04-18 07:08:37,915 INFO Epoch:44 train_loss:0.47691 +2025-04-18 07:08:39,560 INFO Epoch:44 val_res:0.572770 +2025-04-18 07:08:55,502 INFO Epoch:45 train_loss:0.46529 +2025-04-18 07:08:57,441 INFO Epoch:45 val_res:0.596244 +2025-04-18 07:08:57,457 INFO Saving best model at Epoch 45 +2025-04-18 07:09:16,446 INFO Epoch:46 train_loss:0.46418 +2025-04-18 07:09:18,166 INFO Epoch:46 val_res:0.591549 +2025-04-18 07:09:34,293 INFO Epoch:47 train_loss:0.45248 +2025-04-18 07:09:36,161 INFO Epoch:47 val_res:0.582160 +2025-04-18 07:09:53,469 INFO Epoch:48 train_loss:0.46945 +2025-04-18 07:09:55,450 INFO Epoch:48 val_res:0.596244 +2025-04-18 07:10:13,398 INFO Epoch:49 train_loss:0.45613 +2025-04-18 07:10:15,064 INFO Epoch:49 val_res:0.586854 +2025-04-18 07:10:32,100 INFO Epoch:50 train_loss:0.46354 +2025-04-18 07:10:33,761 INFO Epoch:50 val_res:0.577465 +2025-04-18 07:10:50,533 INFO Epoch:51 train_loss:0.45309 +2025-04-18 07:10:52,176 INFO Epoch:51 val_res:0.577465 +2025-04-18 07:11:08,608 INFO Epoch:52 train_loss:0.46753 +2025-04-18 07:11:10,325 INFO Epoch:52 val_res:0.582160 +2025-04-18 07:11:26,747 INFO Epoch:53 train_loss:0.44419 +2025-04-18 07:11:28,983 INFO Epoch:53 val_res:0.600939 +2025-04-18 07:11:28,984 INFO Saving best model at Epoch 53 +2025-04-18 07:11:48,884 INFO Epoch:54 train_loss:0.44051 +2025-04-18 07:11:51,179 INFO Epoch:54 val_res:0.596244 +2025-04-18 07:12:07,951 INFO Epoch:55 train_loss:0.44253 +2025-04-18 07:12:09,435 INFO Epoch:55 val_res:0.596244 +2025-04-18 07:12:26,780 INFO Epoch:56 train_loss:0.44252 +2025-04-18 07:12:28,431 INFO Epoch:56 val_res:0.615023 +2025-04-18 07:12:28,431 INFO Saving best model at Epoch 56 +2025-04-18 07:12:47,063 INFO Epoch:57 train_loss:0.43491 +2025-04-18 07:12:49,260 INFO Epoch:57 val_res:0.596244 +2025-04-18 07:13:06,963 INFO Epoch:58 train_loss:0.44990 +2025-04-18 07:13:08,905 INFO Epoch:58 val_res:0.591549 +2025-04-18 07:13:28,095 INFO Epoch:59 train_loss:0.43323 +2025-04-18 07:13:29,709 INFO Epoch:59 val_res:0.624413 +2025-04-18 07:13:29,709 INFO Saving best model at Epoch 59 +2025-04-18 07:13:47,672 INFO Epoch:60 train_loss:0.44600 +2025-04-18 07:13:49,276 INFO Epoch:60 val_res:0.605634 +2025-04-18 07:14:06,845 INFO Epoch:61 train_loss:0.42876 +2025-04-18 07:14:08,685 INFO Epoch:61 val_res:0.596244 +2025-04-18 07:14:25,169 INFO Epoch:62 train_loss:0.42280 +2025-04-18 07:14:26,941 INFO Epoch:62 val_res:0.596244 +2025-04-18 07:14:45,360 INFO Epoch:63 train_loss:0.42460 +2025-04-18 07:14:47,313 INFO Epoch:63 val_res:0.605634 +2025-04-18 07:15:05,404 INFO Epoch:64 train_loss:0.43256 +2025-04-18 07:15:07,698 INFO Epoch:64 val_res:0.600939 +2025-04-18 07:15:26,205 INFO Epoch:65 train_loss:0.39816 +2025-04-18 07:15:27,798 INFO Epoch:65 val_res:0.582160 +2025-04-18 07:15:46,248 INFO Epoch:66 train_loss:0.40557 +2025-04-18 07:15:48,010 INFO Epoch:66 val_res:0.582160 +2025-04-18 07:16:08,440 INFO Epoch:67 train_loss:0.41042 +2025-04-18 07:16:10,467 INFO Epoch:67 val_res:0.596244 +2025-04-18 07:16:28,606 INFO Epoch:68 train_loss:0.40973 +2025-04-18 07:16:30,669 INFO Epoch:68 val_res:0.615023 +2025-04-18 07:16:47,164 INFO Epoch:69 train_loss:0.39598 +2025-04-18 07:16:49,297 INFO Epoch:69 val_res:0.596244 +2025-04-18 07:17:07,669 INFO Epoch:70 train_loss:0.40923 +2025-04-18 07:17:09,505 INFO Epoch:70 val_res:0.605634 +2025-04-18 07:17:26,764 INFO Epoch:71 train_loss:0.39386 +2025-04-18 07:17:28,335 INFO Epoch:71 val_res:0.619718 +2025-04-18 07:17:44,461 INFO Epoch:72 train_loss:0.40311 +2025-04-18 07:17:46,200 INFO Epoch:72 val_res:0.596244 +2025-04-18 07:18:04,177 INFO Epoch:73 train_loss:0.38875 +2025-04-18 07:18:06,040 INFO Epoch:73 val_res:0.615023 +2025-04-18 07:18:25,367 INFO Epoch:74 train_loss:0.38929 +2025-04-18 07:18:27,163 INFO Epoch:74 val_res:0.624413 +2025-04-18 07:18:43,670 INFO Epoch:75 train_loss:0.40017 +2025-04-18 07:18:45,348 INFO Epoch:75 val_res:0.629108 +2025-04-18 07:18:45,348 INFO Saving best model at Epoch 75 +2025-04-18 07:19:04,909 INFO Epoch:76 train_loss:0.38656 +2025-04-18 07:19:06,663 INFO Epoch:76 val_res:0.633803 +2025-04-18 07:19:06,663 INFO Saving best model at Epoch 76 +2025-04-18 07:19:26,597 INFO Epoch:77 train_loss:0.39515 +2025-04-18 07:19:28,276 INFO Epoch:77 val_res:0.624413 +2025-04-18 07:19:48,454 INFO Epoch:78 train_loss:0.39866 +2025-04-18 07:19:50,106 INFO Epoch:78 val_res:0.629108 +2025-04-18 07:20:06,898 INFO Epoch:79 train_loss:0.38391 +2025-04-18 07:20:08,668 INFO Epoch:79 val_res:0.615023 +2025-04-18 07:20:29,245 INFO Epoch:80 train_loss:0.38551 +2025-04-18 07:20:31,037 INFO Epoch:80 val_res:0.596244 +2025-04-18 07:20:48,008 INFO Epoch:81 train_loss:0.38125 +2025-04-18 07:20:49,859 INFO Epoch:81 val_res:0.615023 +2025-04-18 07:21:08,536 INFO Epoch:82 train_loss:0.39135 +2025-04-18 07:21:10,472 INFO Epoch:82 val_res:0.615023 +2025-04-18 07:21:31,596 INFO Epoch:83 train_loss:0.37437 +2025-04-18 07:21:33,165 INFO Epoch:83 val_res:0.615023 +2025-04-18 07:21:49,538 INFO Epoch:84 train_loss:0.37385 +2025-04-18 07:21:51,289 INFO Epoch:84 val_res:0.596244 +2025-04-18 07:22:10,871 INFO Epoch:85 train_loss:0.36761 +2025-04-18 07:22:12,934 INFO Epoch:85 val_res:0.596244 +2025-04-18 07:22:30,671 INFO Epoch:86 train_loss:0.37585 +2025-04-18 07:22:32,465 INFO Epoch:86 val_res:0.600939 +2025-04-18 07:22:51,162 INFO Epoch:87 train_loss:0.36322 +2025-04-18 07:22:53,520 INFO Epoch:87 val_res:0.600939 +2025-04-18 07:23:12,254 INFO Epoch:88 train_loss:0.35774 +2025-04-18 07:23:13,903 INFO Epoch:88 val_res:0.643192 +2025-04-18 07:23:13,903 INFO Saving best model at Epoch 88 +2025-04-18 07:23:37,082 INFO Epoch:89 train_loss:0.36359 +2025-04-18 07:23:38,882 INFO Epoch:89 val_res:0.629108 +2025-04-18 07:23:58,580 INFO Epoch:90 train_loss:0.36851 +2025-04-18 07:24:00,350 INFO Epoch:90 val_res:0.624413 +2025-04-18 07:24:17,201 INFO Epoch:91 train_loss:0.36252 +2025-04-18 07:24:18,735 INFO Epoch:91 val_res:0.624413 +2025-04-18 07:24:37,372 INFO Epoch:92 train_loss:0.36028 +2025-04-18 07:24:39,645 INFO Epoch:92 val_res:0.638498 +2025-04-18 07:24:56,110 INFO Epoch:93 train_loss:0.36185 +2025-04-18 07:24:57,708 INFO Epoch:93 val_res:0.624413 +2025-04-18 07:25:16,815 INFO Epoch:94 train_loss:0.35664 +2025-04-18 07:25:18,826 INFO Epoch:94 val_res:0.629108 +2025-04-18 07:25:35,876 INFO Epoch:95 train_loss:0.35605 +2025-04-18 07:25:37,692 INFO Epoch:95 val_res:0.629108 +2025-04-18 07:25:55,427 INFO Epoch:96 train_loss:0.34906 +2025-04-18 07:25:57,066 INFO Epoch:96 val_res:0.610329 +2025-04-18 07:26:15,025 INFO Epoch:97 train_loss:0.35561 +2025-04-18 07:26:16,718 INFO Epoch:97 val_res:0.624413 +2025-04-18 07:26:35,559 INFO Epoch:98 train_loss:0.35115 +2025-04-18 07:26:37,060 INFO Epoch:98 val_res:0.629108 +2025-04-18 07:26:55,877 INFO Epoch:99 train_loss:0.34887 +2025-04-18 07:26:57,775 INFO Epoch:99 val_res:0.615023 +2025-04-18 07:27:07,681 INFO ===================================== +2025-04-18 07:27:07,681 INFO Start testing... +2025-04-18 07:27:07,705 INFO ===================================== +2025-04-18 07:27:16,466 INFO Incremental step 1 Testing res: 0.585714 +2025-04-18 07:27:16,468 INFO forgetting: 0.153846 +2025-04-18 07:27:16,474 INFO ***************New Step*************************** +2025-04-18 07:27:16,475 INFO Incremental step: 2 +2025-04-18 07:27:16,753 INFO actual size of exemplar set: 336 +2025-04-18 07:29:29,152 INFO Epoch:0 train_loss:1.59319 +2025-04-18 07:29:51,683 INFO Epoch:0 val_res:0.445513 +2025-04-18 07:29:51,683 INFO Saving best model at Epoch 0 +2025-04-18 07:30:11,012 INFO Epoch:1 train_loss:1.58209 +2025-04-18 07:30:13,567 INFO Epoch:1 val_res:0.413462 +2025-04-18 07:30:30,416 INFO Epoch:2 train_loss:1.47892 +2025-04-18 07:30:32,574 INFO Epoch:2 val_res:0.394231 +2025-04-18 07:30:50,684 INFO Epoch:3 train_loss:1.32665 +2025-04-18 07:30:53,145 INFO Epoch:3 val_res:0.442308 +2025-04-18 07:31:09,685 INFO Epoch:4 train_loss:1.28888 +2025-04-18 07:31:12,014 INFO Epoch:4 val_res:0.426282 +2025-04-18 07:31:28,137 INFO Epoch:5 train_loss:1.21704 +2025-04-18 07:31:30,593 INFO Epoch:5 val_res:0.435897 +2025-04-18 07:31:47,138 INFO Epoch:6 train_loss:1.40098 +2025-04-18 07:31:49,434 INFO Epoch:6 val_res:0.451923 +2025-04-18 07:31:49,435 INFO Saving best model at Epoch 6 +2025-04-18 07:32:08,331 INFO Epoch:7 train_loss:1.57828 +2025-04-18 07:32:10,833 INFO Epoch:7 val_res:0.413462 +2025-04-18 07:32:27,873 INFO Epoch:8 train_loss:1.56822 +2025-04-18 07:32:30,415 INFO Epoch:8 val_res:0.455128 +2025-04-18 07:32:30,415 INFO Saving best model at Epoch 8 +2025-04-18 07:32:52,871 INFO Epoch:9 train_loss:1.29063 +2025-04-18 07:32:55,025 INFO Epoch:9 val_res:0.448718 +2025-04-18 07:33:12,464 INFO Epoch:10 train_loss:1.17836 +2025-04-18 07:33:14,588 INFO Epoch:10 val_res:0.455128 +2025-04-18 07:33:32,592 INFO Epoch:11 train_loss:1.54633 +2025-04-18 07:33:35,023 INFO Epoch:11 val_res:0.432692 +2025-04-18 07:33:52,015 INFO Epoch:12 train_loss:1.40001 +2025-04-18 07:33:54,128 INFO Epoch:12 val_res:0.413462 +2025-04-18 07:34:10,273 INFO Epoch:13 train_loss:1.27584 +2025-04-18 07:34:12,497 INFO Epoch:13 val_res:0.490385 +2025-04-18 07:34:12,497 INFO Saving best model at Epoch 13 +2025-04-18 07:34:32,171 INFO Epoch:14 train_loss:1.32890 +2025-04-18 07:34:34,530 INFO Epoch:14 val_res:0.451923 +2025-04-18 07:34:50,220 INFO Epoch:15 train_loss:1.23613 +2025-04-18 07:34:52,601 INFO Epoch:15 val_res:0.426282 +2025-04-18 07:35:09,891 INFO Epoch:16 train_loss:1.28173 +2025-04-18 07:35:12,144 INFO Epoch:16 val_res:0.445513 +2025-04-18 07:35:27,494 INFO Epoch:17 train_loss:1.05773 +2025-04-18 07:35:29,740 INFO Epoch:17 val_res:0.464744 +2025-04-18 07:35:45,776 INFO Epoch:18 train_loss:0.96888 +2025-04-18 07:35:47,991 INFO Epoch:18 val_res:0.477564 +2025-04-18 07:36:03,668 INFO Epoch:19 train_loss:0.98700 +2025-04-18 07:36:05,885 INFO Epoch:19 val_res:0.451923 +2025-04-18 07:36:22,056 INFO Epoch:20 train_loss:0.98102 +2025-04-18 07:36:24,407 INFO Epoch:20 val_res:0.448718 +2025-04-18 07:36:39,664 INFO Epoch:21 train_loss:0.87905 +2025-04-18 07:36:41,885 INFO Epoch:21 val_res:0.464744 +2025-04-18 07:36:58,976 INFO Epoch:22 train_loss:0.89891 +2025-04-18 07:37:00,890 INFO Epoch:22 val_res:0.451923 +2025-04-18 07:37:15,781 INFO Epoch:23 train_loss:0.90453 +2025-04-18 07:37:17,868 INFO Epoch:23 val_res:0.471154 +2025-04-18 07:37:33,871 INFO Epoch:24 train_loss:0.86150 +2025-04-18 07:37:35,857 INFO Epoch:24 val_res:0.451923 +2025-04-18 07:37:52,059 INFO Epoch:25 train_loss:0.91196 +2025-04-18 07:37:54,175 INFO Epoch:25 val_res:0.461538 +2025-04-18 07:38:12,005 INFO Epoch:26 train_loss:0.82793 +2025-04-18 07:38:14,080 INFO Epoch:26 val_res:0.467949 +2025-04-18 07:38:30,669 INFO Epoch:27 train_loss:0.80648 +2025-04-18 07:38:32,918 INFO Epoch:27 val_res:0.467949 +2025-04-18 07:38:48,582 INFO Epoch:28 train_loss:0.83188 +2025-04-18 07:38:50,605 INFO Epoch:28 val_res:0.474359 +2025-04-18 07:39:06,930 INFO Epoch:29 train_loss:0.77685 +2025-04-18 07:39:09,033 INFO Epoch:29 val_res:0.455128 +2025-04-18 07:39:27,298 INFO Epoch:30 train_loss:0.70780 +2025-04-18 07:39:29,547 INFO Epoch:30 val_res:0.464744 +2025-04-18 07:39:46,780 INFO Epoch:31 train_loss:0.70932 +2025-04-18 07:39:48,996 INFO Epoch:31 val_res:0.467949 +2025-04-18 07:40:07,896 INFO Epoch:32 train_loss:0.77971 +2025-04-18 07:40:10,455 INFO Epoch:32 val_res:0.477564 +2025-04-18 07:40:27,581 INFO Epoch:33 train_loss:0.71137 +2025-04-18 07:40:29,757 INFO Epoch:33 val_res:0.464744 +2025-04-18 07:40:47,529 INFO Epoch:34 train_loss:0.71767 +2025-04-18 07:40:49,807 INFO Epoch:34 val_res:0.474359 +2025-04-18 07:41:07,041 INFO Epoch:35 train_loss:0.77772 +2025-04-18 07:41:09,452 INFO Epoch:35 val_res:0.467949 +2025-04-18 07:41:26,437 INFO Epoch:36 train_loss:0.75883 +2025-04-18 07:41:28,736 INFO Epoch:36 val_res:0.448718 +2025-04-18 07:41:47,079 INFO Epoch:37 train_loss:0.71635 +2025-04-18 07:41:49,451 INFO Epoch:37 val_res:0.458333 +2025-04-18 07:42:06,708 INFO Epoch:38 train_loss:0.72512 +2025-04-18 07:42:08,995 INFO Epoch:38 val_res:0.467949 +2025-04-18 07:42:27,722 INFO Epoch:39 train_loss:0.75583 +2025-04-18 07:42:30,130 INFO Epoch:39 val_res:0.448718 +2025-04-18 07:42:47,057 INFO Epoch:40 train_loss:0.75066 +2025-04-18 07:42:49,275 INFO Epoch:40 val_res:0.464744 +2025-04-18 07:43:06,132 INFO Epoch:41 train_loss:0.69578 +2025-04-18 07:43:08,360 INFO Epoch:41 val_res:0.461538 +2025-04-18 07:43:25,395 INFO Epoch:42 train_loss:0.72144 +2025-04-18 07:43:27,919 INFO Epoch:42 val_res:0.496795 +2025-04-18 07:43:27,919 INFO Saving best model at Epoch 42 +2025-04-18 07:43:47,208 INFO Epoch:43 train_loss:0.66601 +2025-04-18 07:43:49,633 INFO Epoch:43 val_res:0.512821 +2025-04-18 07:43:49,633 INFO Saving best model at Epoch 43 +2025-04-18 07:44:12,392 INFO Epoch:44 train_loss:0.66123 +2025-04-18 07:44:15,627 INFO Epoch:44 val_res:0.496795 +2025-04-18 07:44:31,895 INFO Epoch:45 train_loss:0.65235 +2025-04-18 07:44:34,312 INFO Epoch:45 val_res:0.490385 +2025-04-18 07:44:51,643 INFO Epoch:46 train_loss:0.62009 +2025-04-18 07:44:54,331 INFO Epoch:46 val_res:0.480769 +2025-04-18 07:45:11,298 INFO Epoch:47 train_loss:0.61660 +2025-04-18 07:45:13,827 INFO Epoch:47 val_res:0.464744 +2025-04-18 07:45:31,580 INFO Epoch:48 train_loss:0.60257 +2025-04-18 07:45:33,700 INFO Epoch:48 val_res:0.477564 +2025-04-18 07:45:49,413 INFO Epoch:49 train_loss:0.58603 +2025-04-18 07:45:51,576 INFO Epoch:49 val_res:0.467949 +2025-04-18 07:46:09,699 INFO Epoch:50 train_loss:0.58257 +2025-04-18 07:46:12,176 INFO Epoch:50 val_res:0.477564 +2025-04-18 07:46:29,388 INFO Epoch:51 train_loss:0.56587 +2025-04-18 07:46:32,054 INFO Epoch:51 val_res:0.480769 +2025-04-18 07:46:49,033 INFO Epoch:52 train_loss:0.57830 +2025-04-18 07:46:51,198 INFO Epoch:52 val_res:0.493590 +2025-04-18 07:47:06,449 INFO Epoch:53 train_loss:0.56884 +2025-04-18 07:47:09,109 INFO Epoch:53 val_res:0.506410 +2025-04-18 07:47:25,402 INFO Epoch:54 train_loss:0.55090 +2025-04-18 07:47:27,598 INFO Epoch:54 val_res:0.496795 +2025-04-18 07:47:43,879 INFO Epoch:55 train_loss:0.54325 +2025-04-18 07:47:46,421 INFO Epoch:55 val_res:0.490385 +2025-04-18 07:48:03,196 INFO Epoch:56 train_loss:0.53375 +2025-04-18 07:48:05,665 INFO Epoch:56 val_res:0.493590 +2025-04-18 07:48:22,390 INFO Epoch:57 train_loss:0.54363 +2025-04-18 07:48:24,686 INFO Epoch:57 val_res:0.490385 +2025-04-18 07:48:41,034 INFO Epoch:58 train_loss:0.53637 +2025-04-18 07:48:43,162 INFO Epoch:58 val_res:0.496795 +2025-04-18 07:48:59,470 INFO Epoch:59 train_loss:0.52063 +2025-04-18 07:49:01,658 INFO Epoch:59 val_res:0.483974 +2025-04-18 07:49:17,926 INFO Epoch:60 train_loss:0.52801 +2025-04-18 07:49:20,298 INFO Epoch:60 val_res:0.483974 +2025-04-18 07:49:37,174 INFO Epoch:61 train_loss:0.52854 +2025-04-18 07:49:39,206 INFO Epoch:61 val_res:0.483974 +2025-04-18 07:49:54,928 INFO Epoch:62 train_loss:0.51022 +2025-04-18 07:49:57,235 INFO Epoch:62 val_res:0.471154 +2025-04-18 07:50:13,628 INFO Epoch:63 train_loss:0.51862 +2025-04-18 07:50:15,803 INFO Epoch:63 val_res:0.480769 +2025-04-18 07:50:31,565 INFO Epoch:64 train_loss:0.52043 +2025-04-18 07:50:33,823 INFO Epoch:64 val_res:0.493590 +2025-04-18 07:50:50,266 INFO Epoch:65 train_loss:0.51851 +2025-04-18 07:50:52,312 INFO Epoch:65 val_res:0.474359 +2025-04-18 07:51:07,811 INFO Epoch:66 train_loss:0.52352 +2025-04-18 07:51:10,036 INFO Epoch:66 val_res:0.487179 +2025-04-18 07:51:26,705 INFO Epoch:67 train_loss:0.49499 +2025-04-18 07:51:28,845 INFO Epoch:67 val_res:0.471154 +2025-04-18 07:51:45,171 INFO Epoch:68 train_loss:0.51341 +2025-04-18 07:51:47,281 INFO Epoch:68 val_res:0.483974 +2025-04-18 07:52:03,999 INFO Epoch:69 train_loss:0.51701 +2025-04-18 07:52:06,103 INFO Epoch:69 val_res:0.490385 +2025-04-18 07:52:21,604 INFO Epoch:70 train_loss:0.48475 +2025-04-18 07:52:23,774 INFO Epoch:70 val_res:0.477564 +2025-04-18 07:52:40,636 INFO Epoch:71 train_loss:0.48811 +2025-04-18 07:52:42,980 INFO Epoch:71 val_res:0.496795 +2025-04-18 07:52:59,630 INFO Epoch:72 train_loss:0.50169 +2025-04-18 07:53:01,890 INFO Epoch:72 val_res:0.480769 +2025-04-18 07:53:18,306 INFO Epoch:73 train_loss:0.49788 +2025-04-18 07:53:20,715 INFO Epoch:73 val_res:0.490385 +2025-04-18 07:53:36,841 INFO Epoch:74 train_loss:0.48196 +2025-04-18 07:53:38,946 INFO Epoch:74 val_res:0.477564 +2025-04-18 07:53:55,016 INFO Epoch:75 train_loss:0.49417 +2025-04-18 07:53:57,005 INFO Epoch:75 val_res:0.480769 +2025-04-18 07:54:12,355 INFO Epoch:76 train_loss:0.49392 +2025-04-18 07:54:14,333 INFO Epoch:76 val_res:0.480769 +2025-04-18 07:54:30,571 INFO Epoch:77 train_loss:0.49448 +2025-04-18 07:54:32,937 INFO Epoch:77 val_res:0.483974 +2025-04-18 07:54:48,304 INFO Epoch:78 train_loss:0.48961 +2025-04-18 07:54:50,507 INFO Epoch:78 val_res:0.480769 +2025-04-18 07:55:06,753 INFO Epoch:79 train_loss:0.48198 +2025-04-18 07:55:08,883 INFO Epoch:79 val_res:0.483974 +2025-04-18 07:55:25,441 INFO Epoch:80 train_loss:0.49580 +2025-04-18 07:55:27,866 INFO Epoch:80 val_res:0.480769 +2025-04-18 07:55:45,312 INFO Epoch:81 train_loss:0.45237 +2025-04-18 07:55:47,496 INFO Epoch:81 val_res:0.467949 +2025-04-18 07:56:03,476 INFO Epoch:82 train_loss:0.46050 +2025-04-18 07:56:05,740 INFO Epoch:82 val_res:0.474359 +2025-04-18 07:56:22,830 INFO Epoch:83 train_loss:0.45237 +2025-04-18 07:56:25,177 INFO Epoch:83 val_res:0.477564 +2025-04-18 07:56:41,164 INFO Epoch:84 train_loss:0.44592 +2025-04-18 07:56:43,572 INFO Epoch:84 val_res:0.487179 +2025-04-18 07:56:59,686 INFO Epoch:85 train_loss:0.46289 +2025-04-18 07:57:01,891 INFO Epoch:85 val_res:0.490385 +2025-04-18 07:57:17,900 INFO Epoch:86 train_loss:0.44926 +2025-04-18 07:57:20,217 INFO Epoch:86 val_res:0.493590 +2025-04-18 07:57:36,863 INFO Epoch:87 train_loss:0.45215 +2025-04-18 07:57:39,170 INFO Epoch:87 val_res:0.493590 +2025-04-18 07:57:55,193 INFO Epoch:88 train_loss:0.43262 +2025-04-18 07:57:57,013 INFO Epoch:88 val_res:0.483974 +2025-04-18 07:58:12,983 INFO Epoch:89 train_loss:0.45467 +2025-04-18 07:58:15,365 INFO Epoch:89 val_res:0.490385 +2025-04-18 07:58:31,248 INFO Epoch:90 train_loss:0.44161 +2025-04-18 07:58:33,281 INFO Epoch:90 val_res:0.487179 +2025-04-18 07:58:48,632 INFO Epoch:91 train_loss:0.43576 +2025-04-18 07:58:51,164 INFO Epoch:91 val_res:0.506410 +2025-04-18 07:59:07,039 INFO Epoch:92 train_loss:0.43925 +2025-04-18 07:59:08,982 INFO Epoch:92 val_res:0.503205 +2025-04-18 07:59:24,020 INFO Epoch:93 train_loss:0.45573 +2025-04-18 07:59:26,305 INFO Epoch:93 val_res:0.496795 +2025-04-18 07:59:42,786 INFO Epoch:94 train_loss:0.44575 +2025-04-18 07:59:45,050 INFO Epoch:94 val_res:0.490385 +2025-04-18 08:00:00,437 INFO Epoch:95 train_loss:0.43487 +2025-04-18 08:00:02,521 INFO Epoch:95 val_res:0.496795 +2025-04-18 08:00:17,599 INFO Epoch:96 train_loss:0.43659 +2025-04-18 08:00:19,889 INFO Epoch:96 val_res:0.506410 +2025-04-18 08:00:35,939 INFO Epoch:97 train_loss:0.43242 +2025-04-18 08:00:37,836 INFO Epoch:97 val_res:0.487179 +2025-04-18 08:00:54,392 INFO Epoch:98 train_loss:0.44557 +2025-04-18 08:00:56,505 INFO Epoch:98 val_res:0.480769 +2025-04-18 08:01:11,870 INFO Epoch:99 train_loss:0.42204 +2025-04-18 08:01:14,072 INFO Epoch:99 val_res:0.503205 +2025-04-18 08:01:23,908 INFO ===================================== +2025-04-18 08:01:23,909 INFO Start testing... +2025-04-18 08:01:23,909 INFO ===================================== +2025-04-18 08:01:32,036 INFO Incremental step 2 Testing res: 0.450794 +2025-04-18 08:01:32,038 INFO forgetting: 0.077377 +2025-04-18 08:01:32,040 INFO ***************New Step*************************** +2025-04-18 08:01:32,040 INFO Incremental step: 3 +2025-04-18 08:01:32,216 INFO actual size of exemplar set: 336 +2025-04-18 08:02:26,445 INFO Epoch:0 train_loss:1.78637 +2025-04-18 08:02:58,576 INFO Epoch:0 val_res:0.401535 +2025-04-18 08:02:58,577 INFO Saving best model at Epoch 0 +2025-04-18 08:03:17,156 INFO Epoch:1 train_loss:1.59204 +2025-04-18 08:03:20,160 INFO Epoch:1 val_res:0.409207 +2025-04-18 08:03:20,160 INFO Saving best model at Epoch 1 +2025-04-18 08:03:35,908 INFO Epoch:2 train_loss:1.43678 +2025-04-18 08:03:38,894 INFO Epoch:2 val_res:0.421995 +2025-04-18 08:03:38,895 INFO Saving best model at Epoch 2 +2025-04-18 08:03:54,137 INFO Epoch:3 train_loss:1.30864 +2025-04-18 08:03:56,835 INFO Epoch:3 val_res:0.414322 +2025-04-18 08:04:10,987 INFO Epoch:4 train_loss:1.20041 +2025-04-18 08:04:14,092 INFO Epoch:4 val_res:0.414322 +2025-04-18 08:04:28,137 INFO Epoch:5 train_loss:1.12145 +2025-04-18 08:04:30,756 INFO Epoch:5 val_res:0.409207 +2025-04-18 08:04:45,076 INFO Epoch:6 train_loss:1.04311 +2025-04-18 08:04:48,028 INFO Epoch:6 val_res:0.427110 +2025-04-18 08:04:48,029 INFO Saving best model at Epoch 6 +2025-04-18 08:05:04,127 INFO Epoch:7 train_loss:1.01098 +2025-04-18 08:05:07,048 INFO Epoch:7 val_res:0.437340 +2025-04-18 08:05:07,048 INFO Saving best model at Epoch 7 +2025-04-18 08:05:22,324 INFO Epoch:8 train_loss:1.01307 +2025-04-18 08:05:25,017 INFO Epoch:8 val_res:0.447570 +2025-04-18 08:05:25,018 INFO Saving best model at Epoch 8 +2025-04-18 08:05:42,719 INFO Epoch:9 train_loss:0.91986 +2025-04-18 08:05:45,422 INFO Epoch:9 val_res:0.434783 +2025-04-18 08:06:00,522 INFO Epoch:10 train_loss:0.92047 +2025-04-18 08:06:03,270 INFO Epoch:10 val_res:0.445013 +2025-04-18 08:06:16,840 INFO Epoch:11 train_loss:0.91110 +2025-04-18 08:06:19,427 INFO Epoch:11 val_res:0.450128 +2025-04-18 08:06:19,427 INFO Saving best model at Epoch 11 +2025-04-18 08:06:34,872 INFO Epoch:12 train_loss:0.85056 +2025-04-18 08:06:37,482 INFO Epoch:12 val_res:0.465473 +2025-04-18 08:06:37,483 INFO Saving best model at Epoch 12 +2025-04-18 08:06:53,417 INFO Epoch:13 train_loss:0.83879 +2025-04-18 08:06:56,090 INFO Epoch:13 val_res:0.468031 +2025-04-18 08:06:56,090 INFO Saving best model at Epoch 13 +2025-04-18 08:07:10,676 INFO Epoch:14 train_loss:0.83996 +2025-04-18 08:07:13,341 INFO Epoch:14 val_res:0.468031 +2025-04-18 08:07:26,779 INFO Epoch:15 train_loss:0.79533 +2025-04-18 08:07:29,616 INFO Epoch:15 val_res:0.475703 +2025-04-18 08:07:29,617 INFO Saving best model at Epoch 15 +2025-04-18 08:07:44,700 INFO Epoch:16 train_loss:0.80357 +2025-04-18 08:07:47,316 INFO Epoch:16 val_res:0.480818 +2025-04-18 08:07:47,316 INFO Saving best model at Epoch 16 +2025-04-18 08:08:02,125 INFO Epoch:17 train_loss:0.76756 +2025-04-18 08:08:04,730 INFO Epoch:17 val_res:0.475703 +2025-04-18 08:08:18,823 INFO Epoch:18 train_loss:0.76822 +2025-04-18 08:08:21,701 INFO Epoch:18 val_res:0.496164 +2025-04-18 08:08:21,701 INFO Saving best model at Epoch 18 +2025-04-18 08:08:36,222 INFO Epoch:19 train_loss:0.77287 +2025-04-18 08:08:38,821 INFO Epoch:19 val_res:0.496164 +2025-04-18 08:08:52,491 INFO Epoch:20 train_loss:0.73451 +2025-04-18 08:08:55,113 INFO Epoch:20 val_res:0.503836 +2025-04-18 08:08:55,114 INFO Saving best model at Epoch 20 +2025-04-18 08:09:10,532 INFO Epoch:21 train_loss:0.78340 +2025-04-18 08:09:13,199 INFO Epoch:21 val_res:0.488491 +2025-04-18 08:09:26,773 INFO Epoch:22 train_loss:0.74725 +2025-04-18 08:09:29,550 INFO Epoch:22 val_res:0.519182 +2025-04-18 08:09:29,551 INFO Saving best model at Epoch 22 +2025-04-18 08:09:43,642 INFO Epoch:23 train_loss:0.74008 +2025-04-18 08:09:46,403 INFO Epoch:23 val_res:0.478261 +2025-04-18 08:10:00,049 INFO Epoch:24 train_loss:0.74608 +2025-04-18 08:10:02,777 INFO Epoch:24 val_res:0.498721 +2025-04-18 08:10:15,637 INFO Epoch:25 train_loss:0.70464 +2025-04-18 08:10:18,218 INFO Epoch:25 val_res:0.514067 +2025-04-18 08:10:31,634 INFO Epoch:26 train_loss:0.74603 +2025-04-18 08:10:34,595 INFO Epoch:26 val_res:0.514067 +2025-04-18 08:10:48,247 INFO Epoch:27 train_loss:0.71740 +2025-04-18 08:10:50,588 INFO Epoch:27 val_res:0.493606 +2025-04-18 08:11:04,181 INFO Epoch:28 train_loss:0.72790 +2025-04-18 08:11:07,273 INFO Epoch:28 val_res:0.501279 +2025-04-18 08:11:20,710 INFO Epoch:29 train_loss:0.70547 +2025-04-18 08:11:23,223 INFO Epoch:29 val_res:0.501279 +2025-04-18 08:11:36,781 INFO Epoch:30 train_loss:0.69073 +2025-04-18 08:11:39,660 INFO Epoch:30 val_res:0.480818 +2025-04-18 08:11:52,988 INFO Epoch:31 train_loss:0.70216 +2025-04-18 08:11:55,600 INFO Epoch:31 val_res:0.496164 +2025-04-18 08:12:08,658 INFO Epoch:32 train_loss:0.68505 +2025-04-18 08:12:11,590 INFO Epoch:32 val_res:0.503836 +2025-04-18 08:12:25,567 INFO Epoch:33 train_loss:0.67251 +2025-04-18 08:12:28,204 INFO Epoch:33 val_res:0.508951 +2025-04-18 08:12:41,492 INFO Epoch:34 train_loss:0.67604 +2025-04-18 08:12:44,362 INFO Epoch:34 val_res:0.485934 +2025-04-18 08:12:58,515 INFO Epoch:35 train_loss:0.68230 +2025-04-18 08:13:01,036 INFO Epoch:35 val_res:0.514067 +2025-04-18 08:13:14,778 INFO Epoch:36 train_loss:0.70393 +2025-04-18 08:13:17,741 INFO Epoch:36 val_res:0.514067 +2025-04-18 08:13:32,371 INFO Epoch:37 train_loss:0.68776 +2025-04-18 08:13:35,224 INFO Epoch:37 val_res:0.493606 +2025-04-18 08:13:50,276 INFO Epoch:38 train_loss:0.70845 +2025-04-18 08:13:53,114 INFO Epoch:38 val_res:0.498721 +2025-04-18 08:14:07,684 INFO Epoch:39 train_loss:0.66038 +2025-04-18 08:14:10,338 INFO Epoch:39 val_res:0.508951 +2025-04-18 08:14:25,619 INFO Epoch:40 train_loss:0.65268 +2025-04-18 08:14:28,333 INFO Epoch:40 val_res:0.496164 +2025-04-18 08:14:42,884 INFO Epoch:41 train_loss:0.66346 +2025-04-18 08:14:45,838 INFO Epoch:41 val_res:0.485934 +2025-04-18 08:14:59,665 INFO Epoch:42 train_loss:0.64380 +2025-04-18 08:15:02,464 INFO Epoch:42 val_res:0.526854 +2025-04-18 08:15:02,464 INFO Saving best model at Epoch 42 +2025-04-18 08:15:19,258 INFO Epoch:43 train_loss:0.63500 +2025-04-18 08:15:22,248 INFO Epoch:43 val_res:0.498721 +2025-04-18 08:15:37,330 INFO Epoch:44 train_loss:0.63734 +2025-04-18 08:15:40,374 INFO Epoch:44 val_res:0.506394 +2025-04-18 08:15:56,824 INFO Epoch:45 train_loss:0.65285 +2025-04-18 08:15:59,964 INFO Epoch:45 val_res:0.498721 +2025-04-18 08:16:13,442 INFO Epoch:46 train_loss:0.63544 +2025-04-18 08:16:15,967 INFO Epoch:46 val_res:0.511509 +2025-04-18 08:16:30,098 INFO Epoch:47 train_loss:0.63170 +2025-04-18 08:16:32,839 INFO Epoch:47 val_res:0.488491 +2025-04-18 08:16:46,999 INFO Epoch:48 train_loss:0.63182 +2025-04-18 08:16:49,586 INFO Epoch:48 val_res:0.503836 +2025-04-18 08:17:03,236 INFO Epoch:49 train_loss:0.65202 +2025-04-18 08:17:05,743 INFO Epoch:49 val_res:0.511509 +2025-04-18 08:17:20,544 INFO Epoch:50 train_loss:0.60841 +2025-04-18 08:17:23,671 INFO Epoch:50 val_res:0.496164 +2025-04-18 08:17:37,615 INFO Epoch:51 train_loss:0.63105 +2025-04-18 08:17:40,375 INFO Epoch:51 val_res:0.511509 +2025-04-18 08:17:54,793 INFO Epoch:52 train_loss:0.66499 +2025-04-18 08:17:57,525 INFO Epoch:52 val_res:0.508951 +2025-04-18 08:18:15,352 INFO Epoch:53 train_loss:0.63549 +2025-04-18 08:18:18,592 INFO Epoch:53 val_res:0.516624 +2025-04-18 08:18:34,463 INFO Epoch:54 train_loss:0.64462 +2025-04-18 08:18:37,271 INFO Epoch:54 val_res:0.498721 +2025-04-18 08:18:53,830 INFO Epoch:55 train_loss:0.61859 +2025-04-18 08:18:57,109 INFO Epoch:55 val_res:0.526854 +2025-04-18 08:19:14,108 INFO Epoch:56 train_loss:0.62390 +2025-04-18 08:19:17,022 INFO Epoch:56 val_res:0.506394 +2025-04-18 08:19:33,210 INFO Epoch:57 train_loss:0.60846 +2025-04-18 08:19:36,374 INFO Epoch:57 val_res:0.506394 +2025-04-18 08:19:54,569 INFO Epoch:58 train_loss:0.61380 +2025-04-18 08:19:57,772 INFO Epoch:58 val_res:0.514067 +2025-04-18 08:20:14,884 INFO Epoch:59 train_loss:0.60285 +2025-04-18 08:20:17,616 INFO Epoch:59 val_res:0.524297 +2025-04-18 08:20:32,464 INFO Epoch:60 train_loss:0.62970 +2025-04-18 08:20:35,579 INFO Epoch:60 val_res:0.524297 +2025-04-18 08:20:53,561 INFO Epoch:61 train_loss:0.59842 +2025-04-18 08:20:56,426 INFO Epoch:61 val_res:0.511509 +2025-04-18 08:21:10,622 INFO Epoch:62 train_loss:0.61126 +2025-04-18 08:21:13,319 INFO Epoch:62 val_res:0.519182 +2025-04-18 08:21:29,889 INFO Epoch:63 train_loss:0.58545 +2025-04-18 08:21:32,892 INFO Epoch:63 val_res:0.519182 +2025-04-18 08:21:49,959 INFO Epoch:64 train_loss:0.60150 +2025-04-18 08:21:52,735 INFO Epoch:64 val_res:0.514067 +2025-04-18 08:22:08,065 INFO Epoch:65 train_loss:0.62500 +2025-04-18 08:22:10,926 INFO Epoch:65 val_res:0.526854 +2025-04-18 08:22:27,605 INFO Epoch:66 train_loss:0.60557 +2025-04-18 08:22:30,404 INFO Epoch:66 val_res:0.506394 +2025-04-18 08:22:44,501 INFO Epoch:67 train_loss:0.58303 +2025-04-18 08:22:47,460 INFO Epoch:67 val_res:0.516624 +2025-04-18 08:23:03,149 INFO Epoch:68 train_loss:0.58296 +2025-04-18 08:23:06,070 INFO Epoch:68 val_res:0.508951 +2025-04-18 08:23:22,607 INFO Epoch:69 train_loss:0.58578 +2025-04-18 08:23:25,482 INFO Epoch:69 val_res:0.524297 +2025-04-18 08:23:40,801 INFO Epoch:70 train_loss:0.59091 +2025-04-18 08:23:43,435 INFO Epoch:70 val_res:0.506394 +2025-04-18 08:23:59,770 INFO Epoch:71 train_loss:0.58818 +2025-04-18 08:24:02,490 INFO Epoch:71 val_res:0.531969 +2025-04-18 08:24:02,490 INFO Saving best model at Epoch 71 +2025-04-18 08:24:18,582 INFO Epoch:72 train_loss:0.58344 +2025-04-18 08:24:21,209 INFO Epoch:72 val_res:0.511509 +2025-04-18 08:24:37,698 INFO Epoch:73 train_loss:0.56355 +2025-04-18 08:24:40,824 INFO Epoch:73 val_res:0.529412 +2025-04-18 08:24:56,446 INFO Epoch:74 train_loss:0.57158 +2025-04-18 08:24:59,132 INFO Epoch:74 val_res:0.519182 +2025-04-18 08:25:15,059 INFO Epoch:75 train_loss:0.57605 +2025-04-18 08:25:18,198 INFO Epoch:75 val_res:0.514067 +2025-04-18 08:25:33,542 INFO Epoch:76 train_loss:0.56480 +2025-04-18 08:25:36,635 INFO Epoch:76 val_res:0.521739 +2025-04-18 08:25:52,087 INFO Epoch:77 train_loss:0.55143 +2025-04-18 08:25:54,829 INFO Epoch:77 val_res:0.519182 +2025-04-18 08:26:10,662 INFO Epoch:78 train_loss:0.56560 +2025-04-18 08:26:13,868 INFO Epoch:78 val_res:0.531969 +2025-04-18 08:26:28,745 INFO Epoch:79 train_loss:0.54949 +2025-04-18 08:26:31,668 INFO Epoch:79 val_res:0.519182 +2025-04-18 08:26:47,464 INFO Epoch:80 train_loss:0.56337 +2025-04-18 08:26:50,649 INFO Epoch:80 val_res:0.521739 +2025-04-18 08:27:06,587 INFO Epoch:81 train_loss:0.55109 +2025-04-18 08:27:09,305 INFO Epoch:81 val_res:0.521739 +2025-04-18 08:27:24,834 INFO Epoch:82 train_loss:0.57013 +2025-04-18 08:27:27,624 INFO Epoch:82 val_res:0.531969 +2025-04-18 08:27:42,234 INFO Epoch:83 train_loss:0.56150 +2025-04-18 08:27:45,195 INFO Epoch:83 val_res:0.511509 +2025-04-18 08:28:00,944 INFO Epoch:84 train_loss:0.54303 +2025-04-18 08:28:03,654 INFO Epoch:84 val_res:0.514067 +2025-04-18 08:28:18,967 INFO Epoch:85 train_loss:0.54034 +2025-04-18 08:28:21,864 INFO Epoch:85 val_res:0.524297 +2025-04-18 08:28:37,797 INFO Epoch:86 train_loss:0.56096 +2025-04-18 08:28:40,341 INFO Epoch:86 val_res:0.521739 +2025-04-18 08:28:53,730 INFO Epoch:87 train_loss:0.54372 +2025-04-18 08:28:56,734 INFO Epoch:87 val_res:0.516624 +2025-04-18 08:29:13,534 INFO Epoch:88 train_loss:0.53670 +2025-04-18 08:29:16,473 INFO Epoch:88 val_res:0.526854 +2025-04-18 08:29:30,573 INFO Epoch:89 train_loss:0.53926 +2025-04-18 08:29:33,606 INFO Epoch:89 val_res:0.514067 +2025-04-18 08:29:49,877 INFO Epoch:90 train_loss:0.53220 +2025-04-18 08:29:52,899 INFO Epoch:90 val_res:0.516624 +2025-04-18 08:30:06,457 INFO Epoch:91 train_loss:0.52416 +2025-04-18 08:30:09,342 INFO Epoch:91 val_res:0.511509 +2025-04-18 08:30:25,577 INFO Epoch:92 train_loss:0.53354 +2025-04-18 08:30:29,093 INFO Epoch:92 val_res:0.506394 +2025-04-18 08:30:45,106 INFO Epoch:93 train_loss:0.55411 +2025-04-18 08:30:47,842 INFO Epoch:93 val_res:0.521739 +2025-04-18 08:31:02,091 INFO Epoch:94 train_loss:0.52723 +2025-04-18 08:31:04,789 INFO Epoch:94 val_res:0.511509 +2025-04-18 08:31:21,107 INFO Epoch:95 train_loss:0.54783 +2025-04-18 08:31:24,245 INFO Epoch:95 val_res:0.519182 +2025-04-18 08:31:39,146 INFO Epoch:96 train_loss:0.52598 +2025-04-18 08:31:42,069 INFO Epoch:96 val_res:0.511509 +2025-04-18 08:31:58,524 INFO Epoch:97 train_loss:0.52640 +2025-04-18 08:32:01,402 INFO Epoch:97 val_res:0.506394 +2025-04-18 08:32:14,644 INFO Epoch:98 train_loss:0.51728 +2025-04-18 08:32:17,260 INFO Epoch:98 val_res:0.526854 +2025-04-18 08:32:33,454 INFO Epoch:99 train_loss:0.53639 +2025-04-18 08:32:37,105 INFO Epoch:99 val_res:0.501279 +2025-04-18 08:32:46,972 INFO ===================================== +2025-04-18 08:32:46,973 INFO Start testing... +2025-04-18 08:32:46,973 INFO ===================================== +2025-04-18 08:32:55,897 INFO Incremental step 3 Testing res: 0.474619 +2025-04-18 08:32:55,900 INFO forgetting: 0.035688 +2025-04-18 08:32:55,903 INFO Average Accuracy: 0.564690 +2025-04-18 08:32:55,903 INFO Average Forgetting: 0.088970 diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..71e62b2ad093488033379cde1c93dbf487171275 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..58613b7cce83cc07f83818489d6923846875e98c Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..8ba1c0db49f85255b693d63cf1155d410c44d531 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..91b1827df81fd98cd388ef7060fabd2f786d76b0 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..cf2fd04ba236947a25235c703548bd3d3dfc98f8 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..003a489f807b0ad57893863e0f025d3c3d90a764 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..31c94ea5a33526b138acaf751326b977ff5295d6 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..f3e81f0151ec0d5b8f0a920e794f45a4d4089448 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c35649b94536abcd909c823ff68c1daaf4e398f3 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa165367a63577d7f1ee1c66cdfc8148b8c350429c47004cc0e84542cd1f465 +size 114115153 diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c04439e836c4f9ec2ea73159a7a5d7c0691759e9 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee85f89abc13685f483f66310b2296c2f9a71a023e418b432ca615c74929b2b +size 114179729 diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..7aa8aa7fdc10505b70e6c459942b9ca8ac5d7697 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfb5e1609bd186c84ec1420a8af87fc0d63a5c9da295fba8ca73aef762fb5fe1 +size 114244433 diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..3cd965208c0adab98108c4d6e757e4c5bb36ab31 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eae352a87017e2427fdd0287e5699c05b1ff3fae73fd609d78d5bc3a35efd185 +size 114308945 diff --git a/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/train.log b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..816edd1fce65f8997e624af6988aac322cbb11e3 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/AVE/audio-visual/use-inverse_True-seed_0/train.log @@ -0,0 +1,895 @@ +2025-04-18 06:26:03,220 INFO Namespace(class_num_per_step=7, dataset='AVE', e_prompt=False, exemplar_batch_size=128, fixed_fc=False, infer_batch_size=128, inverse=True, inverse_ends=100, inverse_starts=0, lr=0.01, lr_decay=False, max_epoches=100, memory_size=340, milestones=[100], modality='audio-visual', num_classes=28, num_workers=1, prompt_dim=768, seed=0, train_batch_size=256, weight_decay=0.0001) +2025-04-18 06:26:03,222 INFO Training start time: 2025-04-18 06:26:03.222044 +2025-04-18 06:32:11,395 INFO ***************New Step*************************** +2025-04-18 06:32:11,396 INFO Incremental step: 0 +2025-04-18 06:33:35,986 INFO Epoch:0 train_loss:5.79097 +2025-04-18 06:35:05,413 INFO Epoch:0 val_res:0.304762 +2025-04-18 06:35:05,413 INFO Saving best model at Epoch 0 +2025-04-18 06:35:14,803 INFO Epoch:1 train_loss:5.47550 +2025-04-18 06:35:15,751 INFO Epoch:1 val_res:0.371429 +2025-04-18 06:35:15,751 INFO Saving best model at Epoch 1 +2025-04-18 06:35:25,107 INFO Epoch:2 train_loss:5.16405 +2025-04-18 06:35:26,063 INFO Epoch:2 val_res:0.438095 +2025-04-18 06:35:26,063 INFO Saving best model at Epoch 2 +2025-04-18 06:35:35,342 INFO Epoch:3 train_loss:4.85723 +2025-04-18 06:35:36,345 INFO Epoch:3 val_res:0.523810 +2025-04-18 06:35:36,345 INFO Saving best model at Epoch 3 +2025-04-18 06:35:44,240 INFO Epoch:4 train_loss:4.49728 +2025-04-18 06:35:45,147 INFO Epoch:4 val_res:0.457143 +2025-04-18 06:35:51,711 INFO Epoch:5 train_loss:4.23763 +2025-04-18 06:35:52,893 INFO Epoch:5 val_res:0.571429 +2025-04-18 06:35:52,894 INFO Saving best model at Epoch 5 +2025-04-18 06:36:01,933 INFO Epoch:6 train_loss:3.98139 +2025-04-18 06:36:02,904 INFO Epoch:6 val_res:0.542857 +2025-04-18 06:36:08,777 INFO Epoch:7 train_loss:3.81053 +2025-04-18 06:36:09,886 INFO Epoch:7 val_res:0.542857 +2025-04-18 06:36:15,575 INFO Epoch:8 train_loss:3.62186 +2025-04-18 06:36:16,674 INFO Epoch:8 val_res:0.600000 +2025-04-18 06:36:16,674 INFO Saving best model at Epoch 8 +2025-04-18 06:36:24,470 INFO Epoch:9 train_loss:3.48063 +2025-04-18 06:36:25,466 INFO Epoch:9 val_res:0.704762 +2025-04-18 06:36:25,466 INFO Saving best model at Epoch 9 +2025-04-18 06:36:35,554 INFO Epoch:10 train_loss:3.30581 +2025-04-18 06:36:36,565 INFO Epoch:10 val_res:0.723810 +2025-04-18 06:36:36,565 INFO Saving best model at Epoch 10 +2025-04-18 06:36:44,190 INFO Epoch:11 train_loss:3.24480 +2025-04-18 06:36:45,191 INFO Epoch:11 val_res:0.666667 +2025-04-18 06:36:51,196 INFO Epoch:12 train_loss:3.10125 +2025-04-18 06:36:52,241 INFO Epoch:12 val_res:0.657143 +2025-04-18 06:36:58,252 INFO Epoch:13 train_loss:3.04735 +2025-04-18 06:36:59,335 INFO Epoch:13 val_res:0.695238 +2025-04-18 06:37:05,073 INFO Epoch:14 train_loss:2.95337 +2025-04-18 06:37:06,243 INFO Epoch:14 val_res:0.638095 +2025-04-18 06:37:12,395 INFO Epoch:15 train_loss:2.92027 +2025-04-18 06:37:13,498 INFO Epoch:15 val_res:0.657143 +2025-04-18 06:37:19,733 INFO Epoch:16 train_loss:2.84665 +2025-04-18 06:37:20,780 INFO Epoch:16 val_res:0.676190 +2025-04-18 06:37:26,516 INFO Epoch:17 train_loss:2.80102 +2025-04-18 06:37:27,495 INFO Epoch:17 val_res:0.723810 +2025-04-18 06:37:33,033 INFO Epoch:18 train_loss:2.73080 +2025-04-18 06:37:33,967 INFO Epoch:18 val_res:0.714286 +2025-04-18 06:37:39,337 INFO Epoch:19 train_loss:2.67189 +2025-04-18 06:37:40,314 INFO Epoch:19 val_res:0.714286 +2025-04-18 06:37:46,062 INFO Epoch:20 train_loss:2.62056 +2025-04-18 06:37:47,181 INFO Epoch:20 val_res:0.723810 +2025-04-18 06:37:53,222 INFO Epoch:21 train_loss:2.58886 +2025-04-18 06:37:54,396 INFO Epoch:21 val_res:0.704762 +2025-04-18 06:38:00,071 INFO Epoch:22 train_loss:2.58273 +2025-04-18 06:38:01,070 INFO Epoch:22 val_res:0.666667 +2025-04-18 06:38:07,492 INFO Epoch:23 train_loss:2.54518 +2025-04-18 06:38:08,740 INFO Epoch:23 val_res:0.628571 +2025-04-18 06:38:14,295 INFO Epoch:24 train_loss:2.59948 +2025-04-18 06:38:15,372 INFO Epoch:24 val_res:0.685714 +2025-04-18 06:38:21,035 INFO Epoch:25 train_loss:2.58085 +2025-04-18 06:38:22,070 INFO Epoch:25 val_res:0.695238 +2025-04-18 06:38:27,741 INFO Epoch:26 train_loss:2.44645 +2025-04-18 06:38:28,908 INFO Epoch:26 val_res:0.685714 +2025-04-18 06:38:34,573 INFO Epoch:27 train_loss:2.39247 +2025-04-18 06:38:35,677 INFO Epoch:27 val_res:0.695238 +2025-04-18 06:38:41,494 INFO Epoch:28 train_loss:2.37079 +2025-04-18 06:38:42,634 INFO Epoch:28 val_res:0.714286 +2025-04-18 06:38:48,696 INFO Epoch:29 train_loss:2.35517 +2025-04-18 06:38:49,925 INFO Epoch:29 val_res:0.666667 +2025-04-18 06:38:55,869 INFO Epoch:30 train_loss:2.29290 +2025-04-18 06:38:57,053 INFO Epoch:30 val_res:0.695238 +2025-04-18 06:39:02,796 INFO Epoch:31 train_loss:2.28190 +2025-04-18 06:39:03,877 INFO Epoch:31 val_res:0.714286 +2025-04-18 06:39:09,506 INFO Epoch:32 train_loss:2.20210 +2025-04-18 06:39:10,647 INFO Epoch:32 val_res:0.723810 +2025-04-18 06:39:16,676 INFO Epoch:33 train_loss:2.19707 +2025-04-18 06:39:17,626 INFO Epoch:33 val_res:0.714286 +2025-04-18 06:39:23,580 INFO Epoch:34 train_loss:2.19700 +2025-04-18 06:39:24,565 INFO Epoch:34 val_res:0.704762 +2025-04-18 06:39:30,625 INFO Epoch:35 train_loss:2.17686 +2025-04-18 06:39:31,685 INFO Epoch:35 val_res:0.752381 +2025-04-18 06:39:31,685 INFO Saving best model at Epoch 35 +2025-04-18 06:39:38,868 INFO Epoch:36 train_loss:2.13532 +2025-04-18 06:39:39,874 INFO Epoch:36 val_res:0.742857 +2025-04-18 06:39:45,425 INFO Epoch:37 train_loss:2.16024 +2025-04-18 06:39:46,435 INFO Epoch:37 val_res:0.733333 +2025-04-18 06:39:52,178 INFO Epoch:38 train_loss:2.09642 +2025-04-18 06:39:53,281 INFO Epoch:38 val_res:0.733333 +2025-04-18 06:39:58,758 INFO Epoch:39 train_loss:2.11613 +2025-04-18 06:39:59,880 INFO Epoch:39 val_res:0.752381 +2025-04-18 06:40:05,362 INFO Epoch:40 train_loss:2.14881 +2025-04-18 06:40:06,346 INFO Epoch:40 val_res:0.761905 +2025-04-18 06:40:06,347 INFO Saving best model at Epoch 40 +2025-04-18 06:40:13,200 INFO Epoch:41 train_loss:2.08009 +2025-04-18 06:40:14,099 INFO Epoch:41 val_res:0.685714 +2025-04-18 06:40:19,617 INFO Epoch:42 train_loss:2.13785 +2025-04-18 06:40:20,630 INFO Epoch:42 val_res:0.752381 +2025-04-18 06:40:26,222 INFO Epoch:43 train_loss:2.07551 +2025-04-18 06:40:27,095 INFO Epoch:43 val_res:0.704762 +2025-04-18 06:40:32,761 INFO Epoch:44 train_loss:2.02686 +2025-04-18 06:40:33,802 INFO Epoch:44 val_res:0.742857 +2025-04-18 06:40:39,545 INFO Epoch:45 train_loss:2.06909 +2025-04-18 06:40:40,607 INFO Epoch:45 val_res:0.704762 +2025-04-18 06:40:45,845 INFO Epoch:46 train_loss:1.99788 +2025-04-18 06:40:46,767 INFO Epoch:46 val_res:0.714286 +2025-04-18 06:40:51,952 INFO Epoch:47 train_loss:2.08221 +2025-04-18 06:40:52,929 INFO Epoch:47 val_res:0.676190 +2025-04-18 06:40:58,332 INFO Epoch:48 train_loss:2.05656 +2025-04-18 06:40:59,317 INFO Epoch:48 val_res:0.723810 +2025-04-18 06:41:04,709 INFO Epoch:49 train_loss:1.95162 +2025-04-18 06:41:05,808 INFO Epoch:49 val_res:0.714286 +2025-04-18 06:41:11,332 INFO Epoch:50 train_loss:1.96530 +2025-04-18 06:41:12,320 INFO Epoch:50 val_res:0.771429 +2025-04-18 06:41:12,320 INFO Saving best model at Epoch 50 +2025-04-18 06:41:19,752 INFO Epoch:51 train_loss:2.01556 +2025-04-18 06:41:20,806 INFO Epoch:51 val_res:0.676190 +2025-04-18 06:41:26,494 INFO Epoch:52 train_loss:1.95965 +2025-04-18 06:41:27,657 INFO Epoch:52 val_res:0.761905 +2025-04-18 06:41:33,651 INFO Epoch:53 train_loss:1.91746 +2025-04-18 06:41:34,759 INFO Epoch:53 val_res:0.771429 +2025-04-18 06:41:40,702 INFO Epoch:54 train_loss:1.92062 +2025-04-18 06:41:41,690 INFO Epoch:54 val_res:0.780952 +2025-04-18 06:41:41,691 INFO Saving best model at Epoch 54 +2025-04-18 06:41:49,014 INFO Epoch:55 train_loss:1.89036 +2025-04-18 06:41:49,949 INFO Epoch:55 val_res:0.685714 +2025-04-18 06:41:55,641 INFO Epoch:56 train_loss:1.87514 +2025-04-18 06:41:56,830 INFO Epoch:56 val_res:0.733333 +2025-04-18 06:42:02,654 INFO Epoch:57 train_loss:1.84230 +2025-04-18 06:42:03,716 INFO Epoch:57 val_res:0.628571 +2025-04-18 06:42:09,320 INFO Epoch:58 train_loss:1.97380 +2025-04-18 06:42:10,423 INFO Epoch:58 val_res:0.685714 +2025-04-18 06:42:16,457 INFO Epoch:59 train_loss:1.88954 +2025-04-18 06:42:17,438 INFO Epoch:59 val_res:0.733333 +2025-04-18 06:42:23,323 INFO Epoch:60 train_loss:1.93899 +2025-04-18 06:42:24,365 INFO Epoch:60 val_res:0.704762 +2025-04-18 06:42:29,977 INFO Epoch:61 train_loss:1.96417 +2025-04-18 06:42:30,892 INFO Epoch:61 val_res:0.685714 +2025-04-18 06:42:36,262 INFO Epoch:62 train_loss:2.01533 +2025-04-18 06:42:37,224 INFO Epoch:62 val_res:0.695238 +2025-04-18 06:42:42,691 INFO Epoch:63 train_loss:2.03210 +2025-04-18 06:42:43,753 INFO Epoch:63 val_res:0.704762 +2025-04-18 06:42:48,965 INFO Epoch:64 train_loss:1.96892 +2025-04-18 06:42:49,866 INFO Epoch:64 val_res:0.761905 +2025-04-18 06:42:55,364 INFO Epoch:65 train_loss:1.89257 +2025-04-18 06:42:56,322 INFO Epoch:65 val_res:0.742857 +2025-04-18 06:43:01,931 INFO Epoch:66 train_loss:1.98213 +2025-04-18 06:43:03,247 INFO Epoch:66 val_res:0.695238 +2025-04-18 06:43:09,107 INFO Epoch:67 train_loss:2.02356 +2025-04-18 06:43:10,148 INFO Epoch:67 val_res:0.676190 +2025-04-18 06:43:16,086 INFO Epoch:68 train_loss:1.99283 +2025-04-18 06:43:17,136 INFO Epoch:68 val_res:0.723810 +2025-04-18 06:43:22,748 INFO Epoch:69 train_loss:1.92011 +2025-04-18 06:43:23,819 INFO Epoch:69 val_res:0.733333 +2025-04-18 06:43:29,215 INFO Epoch:70 train_loss:1.91187 +2025-04-18 06:43:30,204 INFO Epoch:70 val_res:0.742857 +2025-04-18 06:43:35,828 INFO Epoch:71 train_loss:1.87435 +2025-04-18 06:43:36,798 INFO Epoch:71 val_res:0.695238 +2025-04-18 06:43:42,159 INFO Epoch:72 train_loss:1.83637 +2025-04-18 06:43:43,209 INFO Epoch:72 val_res:0.714286 +2025-04-18 06:43:49,241 INFO Epoch:73 train_loss:1.94095 +2025-04-18 06:43:50,320 INFO Epoch:73 val_res:0.771429 +2025-04-18 06:43:56,426 INFO Epoch:74 train_loss:1.78313 +2025-04-18 06:43:57,479 INFO Epoch:74 val_res:0.704762 +2025-04-18 06:44:03,377 INFO Epoch:75 train_loss:1.76183 +2025-04-18 06:44:04,626 INFO Epoch:75 val_res:0.771429 +2025-04-18 06:44:10,273 INFO Epoch:76 train_loss:1.70017 +2025-04-18 06:44:11,348 INFO Epoch:76 val_res:0.771429 +2025-04-18 06:44:16,878 INFO Epoch:77 train_loss:1.65427 +2025-04-18 06:44:18,009 INFO Epoch:77 val_res:0.761905 +2025-04-18 06:44:23,863 INFO Epoch:78 train_loss:1.66926 +2025-04-18 06:44:24,818 INFO Epoch:78 val_res:0.714286 +2025-04-18 06:44:30,197 INFO Epoch:79 train_loss:1.64148 +2025-04-18 06:44:31,262 INFO Epoch:79 val_res:0.771429 +2025-04-18 06:44:36,726 INFO Epoch:80 train_loss:1.65630 +2025-04-18 06:44:37,736 INFO Epoch:80 val_res:0.742857 +2025-04-18 06:44:43,329 INFO Epoch:81 train_loss:1.59167 +2025-04-18 06:44:44,405 INFO Epoch:81 val_res:0.771429 +2025-04-18 06:44:50,070 INFO Epoch:82 train_loss:1.62388 +2025-04-18 06:44:51,125 INFO Epoch:82 val_res:0.752381 +2025-04-18 06:44:57,038 INFO Epoch:83 train_loss:1.62871 +2025-04-18 06:44:58,147 INFO Epoch:83 val_res:0.800000 +2025-04-18 06:44:58,147 INFO Saving best model at Epoch 83 +2025-04-18 06:45:05,966 INFO Epoch:84 train_loss:1.60769 +2025-04-18 06:45:07,019 INFO Epoch:84 val_res:0.800000 +2025-04-18 06:45:12,644 INFO Epoch:85 train_loss:1.67427 +2025-04-18 06:45:13,710 INFO Epoch:85 val_res:0.704762 +2025-04-18 06:45:19,267 INFO Epoch:86 train_loss:1.61333 +2025-04-18 06:45:20,270 INFO Epoch:86 val_res:0.809524 +2025-04-18 06:45:20,270 INFO Saving best model at Epoch 86 +2025-04-18 06:45:30,093 INFO Epoch:87 train_loss:1.56818 +2025-04-18 06:45:31,058 INFO Epoch:87 val_res:0.800000 +2025-04-18 06:45:36,542 INFO Epoch:88 train_loss:1.63791 +2025-04-18 06:45:37,898 INFO Epoch:88 val_res:0.742857 +2025-04-18 06:45:43,696 INFO Epoch:89 train_loss:1.58068 +2025-04-18 06:45:44,729 INFO Epoch:89 val_res:0.723810 +2025-04-18 06:45:50,406 INFO Epoch:90 train_loss:1.56957 +2025-04-18 06:45:51,501 INFO Epoch:90 val_res:0.761905 +2025-04-18 06:45:56,877 INFO Epoch:91 train_loss:1.55027 +2025-04-18 06:45:57,927 INFO Epoch:91 val_res:0.752381 +2025-04-18 06:46:03,941 INFO Epoch:92 train_loss:1.53301 +2025-04-18 06:46:05,057 INFO Epoch:92 val_res:0.723810 +2025-04-18 06:46:10,926 INFO Epoch:93 train_loss:1.52874 +2025-04-18 06:46:11,976 INFO Epoch:93 val_res:0.819048 +2025-04-18 06:46:11,977 INFO Saving best model at Epoch 93 +2025-04-18 06:46:19,032 INFO Epoch:94 train_loss:1.49914 +2025-04-18 06:46:19,983 INFO Epoch:94 val_res:0.790476 +2025-04-18 06:46:25,392 INFO Epoch:95 train_loss:1.49462 +2025-04-18 06:46:26,477 INFO Epoch:95 val_res:0.809524 +2025-04-18 06:46:32,203 INFO Epoch:96 train_loss:1.44943 +2025-04-18 06:46:33,256 INFO Epoch:96 val_res:0.771429 +2025-04-18 06:46:39,060 INFO Epoch:97 train_loss:1.51112 +2025-04-18 06:46:40,099 INFO Epoch:97 val_res:0.742857 +2025-04-18 06:46:45,948 INFO Epoch:98 train_loss:1.56470 +2025-04-18 06:46:47,022 INFO Epoch:98 val_res:0.714286 +2025-04-18 06:46:53,032 INFO Epoch:99 train_loss:1.60568 +2025-04-18 06:46:54,210 INFO Epoch:99 val_res:0.800000 +2025-04-18 06:47:03,928 INFO ===================================== +2025-04-18 06:47:03,928 INFO Start testing... +2025-04-18 06:47:03,928 INFO ===================================== +2025-04-18 06:47:10,889 INFO Incremental step 0 Testing res: 0.788462 +2025-04-18 06:47:10,893 INFO ***************New Step*************************** +2025-04-18 06:47:10,894 INFO Incremental step: 1 +2025-04-18 06:47:11,075 INFO actual size of exemplar set: 336 +2025-04-18 06:52:13,563 INFO Epoch:0 train_loss:4.40066 +2025-04-18 06:55:44,913 INFO Epoch:0 val_res:0.389671 +2025-04-18 06:55:44,913 INFO Saving best model at Epoch 0 +2025-04-18 06:56:04,463 INFO Epoch:1 train_loss:4.19362 +2025-04-18 06:56:06,130 INFO Epoch:1 val_res:0.384977 +2025-04-18 06:56:24,052 INFO Epoch:2 train_loss:4.09072 +2025-04-18 06:56:25,480 INFO Epoch:2 val_res:0.370892 +2025-04-18 06:56:41,951 INFO Epoch:3 train_loss:4.25959 +2025-04-18 06:56:43,811 INFO Epoch:3 val_res:0.384977 +2025-04-18 06:57:00,871 INFO Epoch:4 train_loss:3.76134 +2025-04-18 06:57:02,674 INFO Epoch:4 val_res:0.370892 +2025-04-18 06:57:19,188 INFO Epoch:5 train_loss:3.50982 +2025-04-18 06:57:20,848 INFO Epoch:5 val_res:0.399061 +2025-04-18 06:57:20,848 INFO Saving best model at Epoch 5 +2025-04-18 06:57:43,243 INFO Epoch:6 train_loss:3.52827 +2025-04-18 06:57:44,969 INFO Epoch:6 val_res:0.399061 +2025-04-18 06:58:00,807 INFO Epoch:7 train_loss:3.46515 +2025-04-18 06:58:02,624 INFO Epoch:7 val_res:0.389671 +2025-04-18 06:58:18,620 INFO Epoch:8 train_loss:3.33335 +2025-04-18 06:58:20,227 INFO Epoch:8 val_res:0.417840 +2025-04-18 06:58:20,227 INFO Saving best model at Epoch 8 +2025-04-18 06:58:41,034 INFO Epoch:9 train_loss:3.14425 +2025-04-18 06:58:42,630 INFO Epoch:9 val_res:0.342723 +2025-04-18 06:58:57,933 INFO Epoch:10 train_loss:3.50546 +2025-04-18 06:58:59,480 INFO Epoch:10 val_res:0.375587 +2025-04-18 06:59:14,590 INFO Epoch:11 train_loss:3.02232 +2025-04-18 06:59:16,146 INFO Epoch:11 val_res:0.384977 +2025-04-18 06:59:31,662 INFO Epoch:12 train_loss:3.10086 +2025-04-18 06:59:33,173 INFO Epoch:12 val_res:0.399061 +2025-04-18 06:59:47,753 INFO Epoch:13 train_loss:3.10809 +2025-04-18 06:59:49,402 INFO Epoch:13 val_res:0.403756 +2025-04-18 07:00:05,114 INFO Epoch:14 train_loss:3.01241 +2025-04-18 07:00:06,797 INFO Epoch:14 val_res:0.370892 +2025-04-18 07:00:24,459 INFO Epoch:15 train_loss:3.30800 +2025-04-18 07:00:26,009 INFO Epoch:15 val_res:0.399061 +2025-04-18 07:00:42,448 INFO Epoch:16 train_loss:3.41439 +2025-04-18 07:00:43,969 INFO Epoch:16 val_res:0.399061 +2025-04-18 07:00:59,861 INFO Epoch:17 train_loss:3.32842 +2025-04-18 07:01:01,848 INFO Epoch:17 val_res:0.380282 +2025-04-18 07:01:18,619 INFO Epoch:18 train_loss:3.25898 +2025-04-18 07:01:20,105 INFO Epoch:18 val_res:0.384977 +2025-04-18 07:01:36,227 INFO Epoch:19 train_loss:2.90881 +2025-04-18 07:01:37,865 INFO Epoch:19 val_res:0.413146 +2025-04-18 07:01:55,315 INFO Epoch:20 train_loss:3.00341 +2025-04-18 07:01:57,200 INFO Epoch:20 val_res:0.394366 +2025-04-18 07:02:16,121 INFO Epoch:21 train_loss:3.15990 +2025-04-18 07:02:17,943 INFO Epoch:21 val_res:0.422535 +2025-04-18 07:02:17,943 INFO Saving best model at Epoch 21 +2025-04-18 07:02:41,357 INFO Epoch:22 train_loss:3.00403 +2025-04-18 07:02:43,089 INFO Epoch:22 val_res:0.380282 +2025-04-18 07:02:58,661 INFO Epoch:23 train_loss:2.92314 +2025-04-18 07:03:00,547 INFO Epoch:23 val_res:0.436620 +2025-04-18 07:03:00,547 INFO Saving best model at Epoch 23 +2025-04-18 07:03:20,302 INFO Epoch:24 train_loss:2.88619 +2025-04-18 07:03:21,858 INFO Epoch:24 val_res:0.403756 +2025-04-18 07:03:37,850 INFO Epoch:25 train_loss:2.73613 +2025-04-18 07:03:39,623 INFO Epoch:25 val_res:0.427230 +2025-04-18 07:03:55,814 INFO Epoch:26 train_loss:2.64562 +2025-04-18 07:03:57,370 INFO Epoch:26 val_res:0.450704 +2025-04-18 07:03:57,370 INFO Saving best model at Epoch 26 +2025-04-18 07:04:17,106 INFO Epoch:27 train_loss:2.72112 +2025-04-18 07:04:18,913 INFO Epoch:27 val_res:0.413146 +2025-04-18 07:04:35,827 INFO Epoch:28 train_loss:2.70154 +2025-04-18 07:04:37,635 INFO Epoch:28 val_res:0.417840 +2025-04-18 07:04:53,869 INFO Epoch:29 train_loss:2.61764 +2025-04-18 07:04:55,319 INFO Epoch:29 val_res:0.417840 +2025-04-18 07:05:12,088 INFO Epoch:30 train_loss:2.54523 +2025-04-18 07:05:13,874 INFO Epoch:30 val_res:0.488263 +2025-04-18 07:05:13,874 INFO Saving best model at Epoch 30 +2025-04-18 07:05:32,163 INFO Epoch:31 train_loss:2.56366 +2025-04-18 07:05:33,710 INFO Epoch:31 val_res:0.460094 +2025-04-18 07:05:49,326 INFO Epoch:32 train_loss:2.55760 +2025-04-18 07:05:50,943 INFO Epoch:32 val_res:0.464789 +2025-04-18 07:06:07,729 INFO Epoch:33 train_loss:2.41298 +2025-04-18 07:06:09,333 INFO Epoch:33 val_res:0.455399 +2025-04-18 07:06:26,400 INFO Epoch:34 train_loss:2.39807 +2025-04-18 07:06:28,014 INFO Epoch:34 val_res:0.478873 +2025-04-18 07:06:45,267 INFO Epoch:35 train_loss:2.34724 +2025-04-18 07:06:46,992 INFO Epoch:35 val_res:0.474178 +2025-04-18 07:07:04,828 INFO Epoch:36 train_loss:2.38280 +2025-04-18 07:07:06,774 INFO Epoch:36 val_res:0.488263 +2025-04-18 07:07:23,635 INFO Epoch:37 train_loss:2.25810 +2025-04-18 07:07:25,311 INFO Epoch:37 val_res:0.478873 +2025-04-18 07:07:42,504 INFO Epoch:38 train_loss:2.23221 +2025-04-18 07:07:44,286 INFO Epoch:38 val_res:0.492958 +2025-04-18 07:07:44,287 INFO Saving best model at Epoch 38 +2025-04-18 07:08:05,179 INFO Epoch:39 train_loss:2.14604 +2025-04-18 07:08:07,094 INFO Epoch:39 val_res:0.535211 +2025-04-18 07:08:07,094 INFO Saving best model at Epoch 39 +2025-04-18 07:08:28,858 INFO Epoch:40 train_loss:2.17803 +2025-04-18 07:08:30,972 INFO Epoch:40 val_res:0.488263 +2025-04-18 07:08:46,653 INFO Epoch:41 train_loss:2.18735 +2025-04-18 07:08:48,128 INFO Epoch:41 val_res:0.474178 +2025-04-18 07:09:04,471 INFO Epoch:42 train_loss:2.13589 +2025-04-18 07:09:06,110 INFO Epoch:42 val_res:0.516432 +2025-04-18 07:09:23,001 INFO Epoch:43 train_loss:2.12973 +2025-04-18 07:09:24,455 INFO Epoch:43 val_res:0.511737 +2025-04-18 07:09:41,643 INFO Epoch:44 train_loss:2.11055 +2025-04-18 07:09:43,411 INFO Epoch:44 val_res:0.525822 +2025-04-18 07:10:00,114 INFO Epoch:45 train_loss:2.02880 +2025-04-18 07:10:02,083 INFO Epoch:45 val_res:0.539906 +2025-04-18 07:10:02,083 INFO Saving best model at Epoch 45 +2025-04-18 07:10:20,253 INFO Epoch:46 train_loss:2.08061 +2025-04-18 07:10:21,845 INFO Epoch:46 val_res:0.497653 +2025-04-18 07:10:38,651 INFO Epoch:47 train_loss:2.03253 +2025-04-18 07:10:40,211 INFO Epoch:47 val_res:0.502347 +2025-04-18 07:10:56,830 INFO Epoch:48 train_loss:2.23159 +2025-04-18 07:10:58,323 INFO Epoch:48 val_res:0.530516 +2025-04-18 07:11:14,437 INFO Epoch:49 train_loss:2.07742 +2025-04-18 07:11:15,898 INFO Epoch:49 val_res:0.544601 +2025-04-18 07:11:15,898 INFO Saving best model at Epoch 49 +2025-04-18 07:11:36,185 INFO Epoch:50 train_loss:2.19838 +2025-04-18 07:11:38,186 INFO Epoch:50 val_res:0.549296 +2025-04-18 07:11:38,186 INFO Saving best model at Epoch 50 +2025-04-18 07:11:58,469 INFO Epoch:51 train_loss:2.09481 +2025-04-18 07:12:00,186 INFO Epoch:51 val_res:0.497653 +2025-04-18 07:12:15,672 INFO Epoch:52 train_loss:2.11997 +2025-04-18 07:12:17,495 INFO Epoch:52 val_res:0.525822 +2025-04-18 07:12:33,486 INFO Epoch:53 train_loss:2.03149 +2025-04-18 07:12:35,226 INFO Epoch:53 val_res:0.535211 +2025-04-18 07:12:52,778 INFO Epoch:54 train_loss:1.99096 +2025-04-18 07:12:54,433 INFO Epoch:54 val_res:0.535211 +2025-04-18 07:13:11,030 INFO Epoch:55 train_loss:1.95130 +2025-04-18 07:13:12,662 INFO Epoch:55 val_res:0.563380 +2025-04-18 07:13:12,662 INFO Saving best model at Epoch 55 +2025-04-18 07:13:31,424 INFO Epoch:56 train_loss:2.02177 +2025-04-18 07:13:33,146 INFO Epoch:56 val_res:0.572770 +2025-04-18 07:13:33,147 INFO Saving best model at Epoch 56 +2025-04-18 07:13:50,887 INFO Epoch:57 train_loss:2.05684 +2025-04-18 07:13:52,495 INFO Epoch:57 val_res:0.572770 +2025-04-18 07:14:09,312 INFO Epoch:58 train_loss:2.00396 +2025-04-18 07:14:10,946 INFO Epoch:58 val_res:0.563380 +2025-04-18 07:14:27,082 INFO Epoch:59 train_loss:1.96297 +2025-04-18 07:14:28,970 INFO Epoch:59 val_res:0.549296 +2025-04-18 07:14:46,763 INFO Epoch:60 train_loss:1.95981 +2025-04-18 07:14:48,830 INFO Epoch:60 val_res:0.539906 +2025-04-18 07:15:06,661 INFO Epoch:61 train_loss:1.91127 +2025-04-18 07:15:08,714 INFO Epoch:61 val_res:0.558685 +2025-04-18 07:15:25,997 INFO Epoch:62 train_loss:1.87544 +2025-04-18 07:15:27,780 INFO Epoch:62 val_res:0.586854 +2025-04-18 07:15:27,780 INFO Saving best model at Epoch 62 +2025-04-18 07:15:47,812 INFO Epoch:63 train_loss:1.83246 +2025-04-18 07:15:49,503 INFO Epoch:63 val_res:0.563380 +2025-04-18 07:16:09,681 INFO Epoch:64 train_loss:1.88808 +2025-04-18 07:16:11,341 INFO Epoch:64 val_res:0.591549 +2025-04-18 07:16:11,341 INFO Saving best model at Epoch 64 +2025-04-18 07:16:32,120 INFO Epoch:65 train_loss:1.88595 +2025-04-18 07:16:33,920 INFO Epoch:65 val_res:0.582160 +2025-04-18 07:16:50,778 INFO Epoch:66 train_loss:1.86070 +2025-04-18 07:16:52,613 INFO Epoch:66 val_res:0.596244 +2025-04-18 07:16:52,613 INFO Saving best model at Epoch 66 +2025-04-18 07:17:14,116 INFO Epoch:67 train_loss:1.83170 +2025-04-18 07:17:16,299 INFO Epoch:67 val_res:0.600939 +2025-04-18 07:17:16,300 INFO Saving best model at Epoch 67 +2025-04-18 07:17:34,753 INFO Epoch:68 train_loss:1.80864 +2025-04-18 07:17:36,379 INFO Epoch:68 val_res:0.605634 +2025-04-18 07:17:36,380 INFO Saving best model at Epoch 68 +2025-04-18 07:17:55,494 INFO Epoch:69 train_loss:1.79433 +2025-04-18 07:17:57,402 INFO Epoch:69 val_res:0.572770 +2025-04-18 07:18:15,412 INFO Epoch:70 train_loss:1.90354 +2025-04-18 07:18:17,369 INFO Epoch:70 val_res:0.568075 +2025-04-18 07:18:35,268 INFO Epoch:71 train_loss:1.83096 +2025-04-18 07:18:37,238 INFO Epoch:71 val_res:0.586854 +2025-04-18 07:18:53,824 INFO Epoch:72 train_loss:1.74035 +2025-04-18 07:18:55,554 INFO Epoch:72 val_res:0.615023 +2025-04-18 07:18:55,555 INFO Saving best model at Epoch 72 +2025-04-18 07:19:14,610 INFO Epoch:73 train_loss:1.70988 +2025-04-18 07:19:16,294 INFO Epoch:73 val_res:0.586854 +2025-04-18 07:19:34,735 INFO Epoch:74 train_loss:1.70265 +2025-04-18 07:19:37,028 INFO Epoch:74 val_res:0.605634 +2025-04-18 07:19:53,953 INFO Epoch:75 train_loss:1.71118 +2025-04-18 07:19:55,627 INFO Epoch:75 val_res:0.600939 +2025-04-18 07:20:13,303 INFO Epoch:76 train_loss:1.70278 +2025-04-18 07:20:15,900 INFO Epoch:76 val_res:0.577465 +2025-04-18 07:20:34,722 INFO Epoch:77 train_loss:1.71585 +2025-04-18 07:20:36,459 INFO Epoch:77 val_res:0.568075 +2025-04-18 07:20:54,801 INFO Epoch:78 train_loss:1.70962 +2025-04-18 07:20:56,756 INFO Epoch:78 val_res:0.568075 +2025-04-18 07:21:14,298 INFO Epoch:79 train_loss:1.70125 +2025-04-18 07:21:16,444 INFO Epoch:79 val_res:0.572770 +2025-04-18 07:21:35,446 INFO Epoch:80 train_loss:1.69854 +2025-04-18 07:21:37,628 INFO Epoch:80 val_res:0.586854 +2025-04-18 07:21:54,771 INFO Epoch:81 train_loss:1.68190 +2025-04-18 07:21:57,007 INFO Epoch:81 val_res:0.586854 +2025-04-18 07:22:16,200 INFO Epoch:82 train_loss:1.70160 +2025-04-18 07:22:18,120 INFO Epoch:82 val_res:0.591549 +2025-04-18 07:22:33,972 INFO Epoch:83 train_loss:1.68479 +2025-04-18 07:22:35,661 INFO Epoch:83 val_res:0.586854 +2025-04-18 07:22:53,286 INFO Epoch:84 train_loss:1.67534 +2025-04-18 07:22:55,301 INFO Epoch:84 val_res:0.619718 +2025-04-18 07:22:55,302 INFO Saving best model at Epoch 84 +2025-04-18 07:23:15,312 INFO Epoch:85 train_loss:1.61739 +2025-04-18 07:23:16,900 INFO Epoch:85 val_res:0.615023 +2025-04-18 07:23:35,341 INFO Epoch:86 train_loss:1.59306 +2025-04-18 07:23:37,331 INFO Epoch:86 val_res:0.586854 +2025-04-18 07:23:57,543 INFO Epoch:87 train_loss:1.60805 +2025-04-18 07:23:59,485 INFO Epoch:87 val_res:0.596244 +2025-04-18 07:24:17,192 INFO Epoch:88 train_loss:1.60663 +2025-04-18 07:24:18,841 INFO Epoch:88 val_res:0.610329 +2025-04-18 07:24:39,278 INFO Epoch:89 train_loss:1.58472 +2025-04-18 07:24:41,291 INFO Epoch:89 val_res:0.600939 +2025-04-18 07:24:57,788 INFO Epoch:90 train_loss:1.62067 +2025-04-18 07:24:59,623 INFO Epoch:90 val_res:0.577465 +2025-04-18 07:25:19,437 INFO Epoch:91 train_loss:1.63872 +2025-04-18 07:25:21,332 INFO Epoch:91 val_res:0.605634 +2025-04-18 07:25:39,026 INFO Epoch:92 train_loss:1.58904 +2025-04-18 07:25:40,873 INFO Epoch:92 val_res:0.605634 +2025-04-18 07:25:58,727 INFO Epoch:93 train_loss:1.64571 +2025-04-18 07:26:00,342 INFO Epoch:93 val_res:0.596244 +2025-04-18 07:26:18,804 INFO Epoch:94 train_loss:1.54088 +2025-04-18 07:26:20,769 INFO Epoch:94 val_res:0.619718 +2025-04-18 07:26:38,573 INFO Epoch:95 train_loss:1.56100 +2025-04-18 07:26:40,098 INFO Epoch:95 val_res:0.605634 +2025-04-18 07:26:59,045 INFO Epoch:96 train_loss:1.49953 +2025-04-18 07:27:00,571 INFO Epoch:96 val_res:0.605634 +2025-04-18 07:27:17,657 INFO Epoch:97 train_loss:1.53055 +2025-04-18 07:27:19,249 INFO Epoch:97 val_res:0.619718 +2025-04-18 07:27:37,409 INFO Epoch:98 train_loss:1.50767 +2025-04-18 07:27:39,288 INFO Epoch:98 val_res:0.600939 +2025-04-18 07:27:57,187 INFO Epoch:99 train_loss:1.50278 +2025-04-18 07:27:58,825 INFO Epoch:99 val_res:0.610329 +2025-04-18 07:28:08,893 INFO ===================================== +2025-04-18 07:28:08,894 INFO Start testing... +2025-04-18 07:28:08,894 INFO ===================================== +2025-04-18 07:28:17,119 INFO Incremental step 1 Testing res: 0.590476 +2025-04-18 07:28:17,121 INFO forgetting: 0.057692 +2025-04-18 07:28:17,126 INFO ***************New Step*************************** +2025-04-18 07:28:17,127 INFO Incremental step: 2 +2025-04-18 07:28:17,419 INFO actual size of exemplar set: 336 +2025-04-18 07:29:27,538 INFO Epoch:0 train_loss:5.09975 +2025-04-18 07:29:49,861 INFO Epoch:0 val_res:0.435897 +2025-04-18 07:29:49,861 INFO Saving best model at Epoch 0 +2025-04-18 07:30:10,202 INFO Epoch:1 train_loss:5.59945 +2025-04-18 07:30:12,851 INFO Epoch:1 val_res:0.394231 +2025-04-18 07:30:31,435 INFO Epoch:2 train_loss:5.67658 +2025-04-18 07:30:33,861 INFO Epoch:2 val_res:0.384615 +2025-04-18 07:30:52,544 INFO Epoch:3 train_loss:4.98841 +2025-04-18 07:30:54,869 INFO Epoch:3 val_res:0.439103 +2025-04-18 07:30:54,870 INFO Saving best model at Epoch 3 +2025-04-18 07:31:12,786 INFO Epoch:4 train_loss:5.30070 +2025-04-18 07:31:14,750 INFO Epoch:4 val_res:0.442308 +2025-04-18 07:31:14,750 INFO Saving best model at Epoch 4 +2025-04-18 07:31:34,165 INFO Epoch:5 train_loss:4.28379 +2025-04-18 07:31:36,794 INFO Epoch:5 val_res:0.458333 +2025-04-18 07:31:36,794 INFO Saving best model at Epoch 5 +2025-04-18 07:31:54,704 INFO Epoch:6 train_loss:4.15397 +2025-04-18 07:31:56,774 INFO Epoch:6 val_res:0.432692 +2025-04-18 07:32:15,588 INFO Epoch:7 train_loss:3.99545 +2025-04-18 07:32:17,846 INFO Epoch:7 val_res:0.442308 +2025-04-18 07:32:34,995 INFO Epoch:8 train_loss:4.26628 +2025-04-18 07:32:37,038 INFO Epoch:8 val_res:0.471154 +2025-04-18 07:32:37,038 INFO Saving best model at Epoch 8 +2025-04-18 07:32:57,516 INFO Epoch:9 train_loss:4.81085 +2025-04-18 07:32:59,899 INFO Epoch:9 val_res:0.480769 +2025-04-18 07:32:59,899 INFO Saving best model at Epoch 9 +2025-04-18 07:33:18,861 INFO Epoch:10 train_loss:3.73495 +2025-04-18 07:33:20,976 INFO Epoch:10 val_res:0.455128 +2025-04-18 07:33:38,653 INFO Epoch:11 train_loss:4.21802 +2025-04-18 07:33:41,063 INFO Epoch:11 val_res:0.426282 +2025-04-18 07:33:57,285 INFO Epoch:12 train_loss:4.01629 +2025-04-18 07:33:59,364 INFO Epoch:12 val_res:0.451923 +2025-04-18 07:34:14,334 INFO Epoch:13 train_loss:3.72358 +2025-04-18 07:34:16,596 INFO Epoch:13 val_res:0.445513 +2025-04-18 07:34:33,976 INFO Epoch:14 train_loss:3.99060 +2025-04-18 07:34:36,003 INFO Epoch:14 val_res:0.445513 +2025-04-18 07:34:52,104 INFO Epoch:15 train_loss:3.69215 +2025-04-18 07:34:54,219 INFO Epoch:15 val_res:0.423077 +2025-04-18 07:35:11,586 INFO Epoch:16 train_loss:3.71758 +2025-04-18 07:35:13,481 INFO Epoch:16 val_res:0.464744 +2025-04-18 07:35:28,807 INFO Epoch:17 train_loss:3.47108 +2025-04-18 07:35:30,924 INFO Epoch:17 val_res:0.461538 +2025-04-18 07:35:46,734 INFO Epoch:18 train_loss:3.61685 +2025-04-18 07:35:48,835 INFO Epoch:18 val_res:0.435897 +2025-04-18 07:36:05,185 INFO Epoch:19 train_loss:3.47369 +2025-04-18 07:36:07,291 INFO Epoch:19 val_res:0.458333 +2025-04-18 07:36:24,285 INFO Epoch:20 train_loss:3.43078 +2025-04-18 07:36:26,281 INFO Epoch:20 val_res:0.451923 +2025-04-18 07:36:41,399 INFO Epoch:21 train_loss:3.44403 +2025-04-18 07:36:43,657 INFO Epoch:21 val_res:0.493590 +2025-04-18 07:36:43,657 INFO Saving best model at Epoch 21 +2025-04-18 07:37:02,769 INFO Epoch:22 train_loss:3.16251 +2025-04-18 07:37:04,835 INFO Epoch:22 val_res:0.461538 +2025-04-18 07:37:20,080 INFO Epoch:23 train_loss:3.47396 +2025-04-18 07:37:22,422 INFO Epoch:23 val_res:0.455128 +2025-04-18 07:37:38,973 INFO Epoch:24 train_loss:3.25715 +2025-04-18 07:37:41,169 INFO Epoch:24 val_res:0.474359 +2025-04-18 07:37:56,920 INFO Epoch:25 train_loss:3.11195 +2025-04-18 07:37:59,142 INFO Epoch:25 val_res:0.464744 +2025-04-18 07:38:15,711 INFO Epoch:26 train_loss:2.99499 +2025-04-18 07:38:17,850 INFO Epoch:26 val_res:0.480769 +2025-04-18 07:38:35,412 INFO Epoch:27 train_loss:2.95069 +2025-04-18 07:38:37,536 INFO Epoch:27 val_res:0.461538 +2025-04-18 07:38:53,611 INFO Epoch:28 train_loss:2.93155 +2025-04-18 07:38:55,661 INFO Epoch:28 val_res:0.451923 +2025-04-18 07:39:11,256 INFO Epoch:29 train_loss:2.88804 +2025-04-18 07:39:13,440 INFO Epoch:29 val_res:0.467949 +2025-04-18 07:39:31,394 INFO Epoch:30 train_loss:2.81486 +2025-04-18 07:39:33,725 INFO Epoch:30 val_res:0.467949 +2025-04-18 07:39:50,841 INFO Epoch:31 train_loss:2.80467 +2025-04-18 07:39:53,003 INFO Epoch:31 val_res:0.474359 +2025-04-18 07:40:11,349 INFO Epoch:32 train_loss:2.73688 +2025-04-18 07:40:13,399 INFO Epoch:32 val_res:0.496795 +2025-04-18 07:40:13,399 INFO Saving best model at Epoch 32 +2025-04-18 07:40:31,477 INFO Epoch:33 train_loss:2.72333 +2025-04-18 07:40:33,684 INFO Epoch:33 val_res:0.493590 +2025-04-18 07:40:51,719 INFO Epoch:34 train_loss:2.71972 +2025-04-18 07:40:53,808 INFO Epoch:34 val_res:0.483974 +2025-04-18 07:41:11,215 INFO Epoch:35 train_loss:2.72908 +2025-04-18 07:41:13,288 INFO Epoch:35 val_res:0.464744 +2025-04-18 07:41:32,610 INFO Epoch:36 train_loss:2.97124 +2025-04-18 07:41:34,867 INFO Epoch:36 val_res:0.442308 +2025-04-18 07:41:53,105 INFO Epoch:37 train_loss:3.17567 +2025-04-18 07:41:55,464 INFO Epoch:37 val_res:0.461538 +2025-04-18 07:42:11,389 INFO Epoch:38 train_loss:2.96397 +2025-04-18 07:42:13,875 INFO Epoch:38 val_res:0.483974 +2025-04-18 07:42:32,182 INFO Epoch:39 train_loss:2.96358 +2025-04-18 07:42:34,435 INFO Epoch:39 val_res:0.471154 +2025-04-18 07:42:51,626 INFO Epoch:40 train_loss:2.97979 +2025-04-18 07:42:54,544 INFO Epoch:40 val_res:0.474359 +2025-04-18 07:43:12,264 INFO Epoch:41 train_loss:2.80924 +2025-04-18 07:43:14,509 INFO Epoch:41 val_res:0.455128 +2025-04-18 07:43:32,259 INFO Epoch:42 train_loss:2.99076 +2025-04-18 07:43:34,504 INFO Epoch:42 val_res:0.471154 +2025-04-18 07:43:51,078 INFO Epoch:43 train_loss:2.77455 +2025-04-18 07:43:53,263 INFO Epoch:43 val_res:0.496795 +2025-04-18 07:44:12,602 INFO Epoch:44 train_loss:2.79040 +2025-04-18 07:44:15,190 INFO Epoch:44 val_res:0.467949 +2025-04-18 07:44:32,093 INFO Epoch:45 train_loss:3.18071 +2025-04-18 07:44:34,273 INFO Epoch:45 val_res:0.487179 +2025-04-18 07:44:53,818 INFO Epoch:46 train_loss:2.84775 +2025-04-18 07:44:56,029 INFO Epoch:46 val_res:0.493590 +2025-04-18 07:45:12,924 INFO Epoch:47 train_loss:2.93789 +2025-04-18 07:45:15,544 INFO Epoch:47 val_res:0.464744 +2025-04-18 07:45:33,665 INFO Epoch:48 train_loss:2.76751 +2025-04-18 07:45:36,015 INFO Epoch:48 val_res:0.512821 +2025-04-18 07:45:36,015 INFO Saving best model at Epoch 48 +2025-04-18 07:45:54,248 INFO Epoch:49 train_loss:3.28458 +2025-04-18 07:45:56,812 INFO Epoch:49 val_res:0.464744 +2025-04-18 07:46:14,543 INFO Epoch:50 train_loss:2.91083 +2025-04-18 07:46:16,581 INFO Epoch:50 val_res:0.439103 +2025-04-18 07:46:32,970 INFO Epoch:51 train_loss:2.93952 +2025-04-18 07:46:35,755 INFO Epoch:51 val_res:0.483974 +2025-04-18 07:46:51,699 INFO Epoch:52 train_loss:2.79675 +2025-04-18 07:46:53,830 INFO Epoch:52 val_res:0.487179 +2025-04-18 07:47:09,351 INFO Epoch:53 train_loss:2.86990 +2025-04-18 07:47:11,645 INFO Epoch:53 val_res:0.464744 +2025-04-18 07:47:27,445 INFO Epoch:54 train_loss:2.75545 +2025-04-18 07:47:29,915 INFO Epoch:54 val_res:0.474359 +2025-04-18 07:47:45,219 INFO Epoch:55 train_loss:2.83486 +2025-04-18 07:47:47,427 INFO Epoch:55 val_res:0.477564 +2025-04-18 07:48:02,882 INFO Epoch:56 train_loss:2.68259 +2025-04-18 07:48:05,118 INFO Epoch:56 val_res:0.506410 +2025-04-18 07:48:20,767 INFO Epoch:57 train_loss:2.74745 +2025-04-18 07:48:23,074 INFO Epoch:57 val_res:0.503205 +2025-04-18 07:48:39,244 INFO Epoch:58 train_loss:2.67138 +2025-04-18 07:48:41,563 INFO Epoch:58 val_res:0.461538 +2025-04-18 07:48:57,637 INFO Epoch:59 train_loss:2.59833 +2025-04-18 07:48:59,859 INFO Epoch:59 val_res:0.467949 +2025-04-18 07:49:15,349 INFO Epoch:60 train_loss:2.67500 +2025-04-18 07:49:17,476 INFO Epoch:60 val_res:0.506410 +2025-04-18 07:49:32,895 INFO Epoch:61 train_loss:2.56935 +2025-04-18 07:49:35,052 INFO Epoch:61 val_res:0.506410 +2025-04-18 07:49:49,984 INFO Epoch:62 train_loss:2.51135 +2025-04-18 07:49:52,210 INFO Epoch:62 val_res:0.487179 +2025-04-18 07:50:08,699 INFO Epoch:63 train_loss:2.61447 +2025-04-18 07:50:10,981 INFO Epoch:63 val_res:0.483974 +2025-04-18 07:50:25,645 INFO Epoch:64 train_loss:2.42288 +2025-04-18 07:50:27,845 INFO Epoch:64 val_res:0.512821 +2025-04-18 07:50:43,549 INFO Epoch:65 train_loss:2.34799 +2025-04-18 07:50:46,285 INFO Epoch:65 val_res:0.503205 +2025-04-18 07:51:01,088 INFO Epoch:66 train_loss:2.37056 +2025-04-18 07:51:03,355 INFO Epoch:66 val_res:0.509615 +2025-04-18 07:51:19,540 INFO Epoch:67 train_loss:2.28829 +2025-04-18 07:51:22,165 INFO Epoch:67 val_res:0.483974 +2025-04-18 07:51:36,601 INFO Epoch:68 train_loss:2.29395 +2025-04-18 07:51:38,874 INFO Epoch:68 val_res:0.509615 +2025-04-18 07:51:54,427 INFO Epoch:69 train_loss:2.29390 +2025-04-18 07:51:56,839 INFO Epoch:69 val_res:0.483974 +2025-04-18 07:52:11,307 INFO Epoch:70 train_loss:2.17135 +2025-04-18 07:52:13,376 INFO Epoch:70 val_res:0.516026 +2025-04-18 07:52:13,377 INFO Saving best model at Epoch 70 +2025-04-18 07:52:30,859 INFO Epoch:71 train_loss:2.17021 +2025-04-18 07:52:33,296 INFO Epoch:71 val_res:0.516026 +2025-04-18 07:52:47,456 INFO Epoch:72 train_loss:2.20804 +2025-04-18 07:52:49,506 INFO Epoch:72 val_res:0.516026 +2025-04-18 07:53:04,993 INFO Epoch:73 train_loss:2.17201 +2025-04-18 07:53:07,416 INFO Epoch:73 val_res:0.535256 +2025-04-18 07:53:07,417 INFO Saving best model at Epoch 73 +2025-04-18 07:53:24,411 INFO Epoch:74 train_loss:2.13881 +2025-04-18 07:53:26,717 INFO Epoch:74 val_res:0.516026 +2025-04-18 07:53:42,745 INFO Epoch:75 train_loss:2.17878 +2025-04-18 07:53:44,859 INFO Epoch:75 val_res:0.503205 +2025-04-18 07:53:59,859 INFO Epoch:76 train_loss:2.15994 +2025-04-18 07:54:01,862 INFO Epoch:76 val_res:0.500000 +2025-04-18 07:54:16,416 INFO Epoch:77 train_loss:2.15129 +2025-04-18 07:54:18,685 INFO Epoch:77 val_res:0.525641 +2025-04-18 07:54:33,321 INFO Epoch:78 train_loss:2.17376 +2025-04-18 07:54:35,361 INFO Epoch:78 val_res:0.512821 +2025-04-18 07:54:50,778 INFO Epoch:79 train_loss:2.08383 +2025-04-18 07:54:53,104 INFO Epoch:79 val_res:0.535256 +2025-04-18 07:55:08,374 INFO Epoch:80 train_loss:2.10082 +2025-04-18 07:55:10,821 INFO Epoch:80 val_res:0.522436 +2025-04-18 07:55:26,032 INFO Epoch:81 train_loss:1.99050 +2025-04-18 07:55:28,383 INFO Epoch:81 val_res:0.544872 +2025-04-18 07:55:28,383 INFO Saving best model at Epoch 81 +2025-04-18 07:55:45,517 INFO Epoch:82 train_loss:2.05343 +2025-04-18 07:55:47,816 INFO Epoch:82 val_res:0.525641 +2025-04-18 07:56:03,462 INFO Epoch:83 train_loss:1.99213 +2025-04-18 07:56:05,586 INFO Epoch:83 val_res:0.535256 +2025-04-18 07:56:21,782 INFO Epoch:84 train_loss:1.97665 +2025-04-18 07:56:23,912 INFO Epoch:84 val_res:0.522436 +2025-04-18 07:56:38,315 INFO Epoch:85 train_loss:2.03626 +2025-04-18 07:56:40,536 INFO Epoch:85 val_res:0.532051 +2025-04-18 07:56:55,104 INFO Epoch:86 train_loss:1.96468 +2025-04-18 07:56:57,368 INFO Epoch:86 val_res:0.522436 +2025-04-18 07:57:12,850 INFO Epoch:87 train_loss:2.00530 +2025-04-18 07:57:15,205 INFO Epoch:87 val_res:0.541667 +2025-04-18 07:57:30,757 INFO Epoch:88 train_loss:1.96256 +2025-04-18 07:57:32,856 INFO Epoch:88 val_res:0.522436 +2025-04-18 07:57:47,940 INFO Epoch:89 train_loss:2.07318 +2025-04-18 07:57:50,367 INFO Epoch:89 val_res:0.528846 +2025-04-18 07:58:04,502 INFO Epoch:90 train_loss:2.02819 +2025-04-18 07:58:06,690 INFO Epoch:90 val_res:0.509615 +2025-04-18 07:58:22,244 INFO Epoch:91 train_loss:2.02628 +2025-04-18 07:58:24,514 INFO Epoch:91 val_res:0.525641 +2025-04-18 07:58:40,055 INFO Epoch:92 train_loss:2.00140 +2025-04-18 07:58:42,587 INFO Epoch:92 val_res:0.516026 +2025-04-18 07:58:57,736 INFO Epoch:93 train_loss:2.23097 +2025-04-18 07:59:00,308 INFO Epoch:93 val_res:0.516026 +2025-04-18 07:59:14,361 INFO Epoch:94 train_loss:2.31448 +2025-04-18 07:59:16,505 INFO Epoch:94 val_res:0.500000 +2025-04-18 07:59:31,450 INFO Epoch:95 train_loss:2.25701 +2025-04-18 07:59:33,770 INFO Epoch:95 val_res:0.525641 +2025-04-18 07:59:49,103 INFO Epoch:96 train_loss:2.14991 +2025-04-18 07:59:51,313 INFO Epoch:96 val_res:0.522436 +2025-04-18 08:00:05,847 INFO Epoch:97 train_loss:2.13804 +2025-04-18 08:00:07,696 INFO Epoch:97 val_res:0.516026 +2025-04-18 08:00:22,010 INFO Epoch:98 train_loss:2.11401 +2025-04-18 08:00:24,220 INFO Epoch:98 val_res:0.548077 +2025-04-18 08:00:24,221 INFO Saving best model at Epoch 98 +2025-04-18 08:00:40,645 INFO Epoch:99 train_loss:2.08706 +2025-04-18 08:00:42,835 INFO Epoch:99 val_res:0.525641 +2025-04-18 08:00:52,823 INFO ===================================== +2025-04-18 08:00:52,824 INFO Start testing... +2025-04-18 08:00:52,824 INFO ===================================== +2025-04-18 08:01:00,550 INFO Incremental step 2 Testing res: 0.466667 +2025-04-18 08:01:00,551 INFO forgetting: 0.097333 +2025-04-18 08:01:00,554 INFO ***************New Step*************************** +2025-04-18 08:01:00,554 INFO Incremental step: 3 +2025-04-18 08:01:00,708 INFO actual size of exemplar set: 336 +2025-04-18 08:02:24,099 INFO Epoch:0 train_loss:5.29787 +2025-04-18 08:02:58,539 INFO Epoch:0 val_res:0.432225 +2025-04-18 08:02:58,539 INFO Saving best model at Epoch 0 +2025-04-18 08:03:16,997 INFO Epoch:1 train_loss:4.88495 +2025-04-18 08:03:19,860 INFO Epoch:1 val_res:0.442455 +2025-04-18 08:03:19,861 INFO Saving best model at Epoch 1 +2025-04-18 08:03:36,393 INFO Epoch:2 train_loss:4.39227 +2025-04-18 08:03:39,418 INFO Epoch:2 val_res:0.437340 +2025-04-18 08:03:54,126 INFO Epoch:3 train_loss:4.10318 +2025-04-18 08:03:57,545 INFO Epoch:3 val_res:0.445013 +2025-04-18 08:03:57,545 INFO Saving best model at Epoch 3 +2025-04-18 08:04:12,991 INFO Epoch:4 train_loss:3.88488 +2025-04-18 08:04:16,267 INFO Epoch:4 val_res:0.470588 +2025-04-18 08:04:16,267 INFO Saving best model at Epoch 4 +2025-04-18 08:04:31,304 INFO Epoch:5 train_loss:3.71736 +2025-04-18 08:04:34,050 INFO Epoch:5 val_res:0.460358 +2025-04-18 08:04:47,596 INFO Epoch:6 train_loss:3.57042 +2025-04-18 08:04:50,597 INFO Epoch:6 val_res:0.468031 +2025-04-18 08:05:04,948 INFO Epoch:7 train_loss:3.68960 +2025-04-18 08:05:07,801 INFO Epoch:7 val_res:0.442455 +2025-04-18 08:05:21,754 INFO Epoch:8 train_loss:3.72217 +2025-04-18 08:05:24,564 INFO Epoch:8 val_res:0.493606 +2025-04-18 08:05:24,565 INFO Saving best model at Epoch 8 +2025-04-18 08:05:41,865 INFO Epoch:9 train_loss:3.39677 +2025-04-18 08:05:44,427 INFO Epoch:9 val_res:0.457801 +2025-04-18 08:05:58,423 INFO Epoch:10 train_loss:3.32549 +2025-04-18 08:06:01,183 INFO Epoch:10 val_res:0.493606 +2025-04-18 08:06:14,738 INFO Epoch:11 train_loss:3.23090 +2025-04-18 08:06:17,343 INFO Epoch:11 val_res:0.511509 +2025-04-18 08:06:17,343 INFO Saving best model at Epoch 11 +2025-04-18 08:06:32,345 INFO Epoch:12 train_loss:2.98679 +2025-04-18 08:06:34,979 INFO Epoch:12 val_res:0.457801 +2025-04-18 08:06:49,511 INFO Epoch:13 train_loss:3.03541 +2025-04-18 08:06:52,129 INFO Epoch:13 val_res:0.506394 +2025-04-18 08:07:06,031 INFO Epoch:14 train_loss:3.01187 +2025-04-18 08:07:08,856 INFO Epoch:14 val_res:0.488491 +2025-04-18 08:07:22,300 INFO Epoch:15 train_loss:2.96789 +2025-04-18 08:07:24,854 INFO Epoch:15 val_res:0.511509 +2025-04-18 08:07:38,414 INFO Epoch:16 train_loss:3.13277 +2025-04-18 08:07:41,123 INFO Epoch:16 val_res:0.496164 +2025-04-18 08:07:54,895 INFO Epoch:17 train_loss:2.99122 +2025-04-18 08:07:57,508 INFO Epoch:17 val_res:0.496164 +2025-04-18 08:08:10,969 INFO Epoch:18 train_loss:2.86592 +2025-04-18 08:08:13,854 INFO Epoch:18 val_res:0.514067 +2025-04-18 08:08:13,854 INFO Saving best model at Epoch 18 +2025-04-18 08:08:29,923 INFO Epoch:19 train_loss:3.10954 +2025-04-18 08:08:32,532 INFO Epoch:19 val_res:0.539642 +2025-04-18 08:08:32,532 INFO Saving best model at Epoch 19 +2025-04-18 08:08:47,621 INFO Epoch:20 train_loss:2.91426 +2025-04-18 08:08:50,590 INFO Epoch:20 val_res:0.491049 +2025-04-18 08:09:04,743 INFO Epoch:21 train_loss:3.11051 +2025-04-18 08:09:07,388 INFO Epoch:21 val_res:0.514067 +2025-04-18 08:09:20,745 INFO Epoch:22 train_loss:3.14537 +2025-04-18 08:09:23,500 INFO Epoch:22 val_res:0.501279 +2025-04-18 08:09:37,609 INFO Epoch:23 train_loss:3.11955 +2025-04-18 08:09:40,200 INFO Epoch:23 val_res:0.501279 +2025-04-18 08:09:56,308 INFO Epoch:24 train_loss:3.11039 +2025-04-18 08:09:59,048 INFO Epoch:24 val_res:0.478261 +2025-04-18 08:10:13,003 INFO Epoch:25 train_loss:3.05646 +2025-04-18 08:10:15,627 INFO Epoch:25 val_res:0.514067 +2025-04-18 08:10:28,463 INFO Epoch:26 train_loss:2.98458 +2025-04-18 08:10:31,099 INFO Epoch:26 val_res:0.485934 +2025-04-18 08:10:45,072 INFO Epoch:27 train_loss:2.90029 +2025-04-18 08:10:47,594 INFO Epoch:27 val_res:0.511509 +2025-04-18 08:11:01,478 INFO Epoch:28 train_loss:2.84063 +2025-04-18 08:11:04,125 INFO Epoch:28 val_res:0.498721 +2025-04-18 08:11:18,558 INFO Epoch:29 train_loss:3.00643 +2025-04-18 08:11:20,878 INFO Epoch:29 val_res:0.496164 +2025-04-18 08:11:33,809 INFO Epoch:30 train_loss:2.90517 +2025-04-18 08:11:36,450 INFO Epoch:30 val_res:0.501279 +2025-04-18 08:11:50,630 INFO Epoch:31 train_loss:2.81908 +2025-04-18 08:11:53,108 INFO Epoch:31 val_res:0.521739 +2025-04-18 08:12:05,543 INFO Epoch:32 train_loss:2.71690 +2025-04-18 08:12:08,096 INFO Epoch:32 val_res:0.521739 +2025-04-18 08:12:22,582 INFO Epoch:33 train_loss:2.70774 +2025-04-18 08:12:25,034 INFO Epoch:33 val_res:0.506394 +2025-04-18 08:12:38,781 INFO Epoch:34 train_loss:2.84245 +2025-04-18 08:12:41,551 INFO Epoch:34 val_res:0.534527 +2025-04-18 08:12:56,101 INFO Epoch:35 train_loss:2.68016 +2025-04-18 08:12:58,544 INFO Epoch:35 val_res:0.493606 +2025-04-18 08:13:11,391 INFO Epoch:36 train_loss:2.71255 +2025-04-18 08:13:14,116 INFO Epoch:36 val_res:0.526854 +2025-04-18 08:13:28,864 INFO Epoch:37 train_loss:2.67319 +2025-04-18 08:13:32,133 INFO Epoch:37 val_res:0.485934 +2025-04-18 08:13:46,498 INFO Epoch:38 train_loss:2.61790 +2025-04-18 08:13:49,427 INFO Epoch:38 val_res:0.542199 +2025-04-18 08:13:49,427 INFO Saving best model at Epoch 38 +2025-04-18 08:14:05,443 INFO Epoch:39 train_loss:2.72267 +2025-04-18 08:14:08,456 INFO Epoch:39 val_res:0.501279 +2025-04-18 08:14:23,428 INFO Epoch:40 train_loss:2.65697 +2025-04-18 08:14:26,127 INFO Epoch:40 val_res:0.531969 +2025-04-18 08:14:40,270 INFO Epoch:41 train_loss:2.51931 +2025-04-18 08:14:43,103 INFO Epoch:41 val_res:0.514067 +2025-04-18 08:14:56,607 INFO Epoch:42 train_loss:2.53620 +2025-04-18 08:14:59,119 INFO Epoch:42 val_res:0.539642 +2025-04-18 08:15:14,038 INFO Epoch:43 train_loss:2.39060 +2025-04-18 08:15:16,945 INFO Epoch:43 val_res:0.498721 +2025-04-18 08:15:31,156 INFO Epoch:44 train_loss:2.55943 +2025-04-18 08:15:33,989 INFO Epoch:44 val_res:0.529412 +2025-04-18 08:15:49,082 INFO Epoch:45 train_loss:2.85298 +2025-04-18 08:15:51,585 INFO Epoch:45 val_res:0.526854 +2025-04-18 08:16:06,323 INFO Epoch:46 train_loss:2.70613 +2025-04-18 08:16:08,983 INFO Epoch:46 val_res:0.506394 +2025-04-18 08:16:22,546 INFO Epoch:47 train_loss:2.67831 +2025-04-18 08:16:25,467 INFO Epoch:47 val_res:0.552430 +2025-04-18 08:16:25,467 INFO Saving best model at Epoch 47 +2025-04-18 08:16:42,521 INFO Epoch:48 train_loss:2.59117 +2025-04-18 08:16:45,300 INFO Epoch:48 val_res:0.511509 +2025-04-18 08:16:59,922 INFO Epoch:49 train_loss:2.56348 +2025-04-18 08:17:02,669 INFO Epoch:49 val_res:0.542199 +2025-04-18 08:17:18,259 INFO Epoch:50 train_loss:2.41607 +2025-04-18 08:17:21,119 INFO Epoch:50 val_res:0.531969 +2025-04-18 08:17:34,992 INFO Epoch:51 train_loss:2.43834 +2025-04-18 08:17:37,469 INFO Epoch:51 val_res:0.526854 +2025-04-18 08:17:51,019 INFO Epoch:52 train_loss:2.59518 +2025-04-18 08:17:53,639 INFO Epoch:52 val_res:0.516624 +2025-04-18 08:18:08,809 INFO Epoch:53 train_loss:2.43166 +2025-04-18 08:18:12,830 INFO Epoch:53 val_res:0.526854 +2025-04-18 08:18:27,977 INFO Epoch:54 train_loss:2.49206 +2025-04-18 08:18:31,098 INFO Epoch:54 val_res:0.516624 +2025-04-18 08:18:45,568 INFO Epoch:55 train_loss:2.75120 +2025-04-18 08:18:48,153 INFO Epoch:55 val_res:0.519182 +2025-04-18 08:19:05,615 INFO Epoch:56 train_loss:2.57977 +2025-04-18 08:19:08,380 INFO Epoch:56 val_res:0.488491 +2025-04-18 08:19:22,796 INFO Epoch:57 train_loss:2.48018 +2025-04-18 08:19:25,329 INFO Epoch:57 val_res:0.531969 +2025-04-18 08:19:42,482 INFO Epoch:58 train_loss:2.49338 +2025-04-18 08:19:45,264 INFO Epoch:58 val_res:0.506394 +2025-04-18 08:20:00,957 INFO Epoch:59 train_loss:2.42886 +2025-04-18 08:20:03,565 INFO Epoch:59 val_res:0.537084 +2025-04-18 08:20:18,951 INFO Epoch:60 train_loss:2.48305 +2025-04-18 08:20:21,567 INFO Epoch:60 val_res:0.526854 +2025-04-18 08:20:36,461 INFO Epoch:61 train_loss:2.78556 +2025-04-18 08:20:39,372 INFO Epoch:61 val_res:0.567775 +2025-04-18 08:20:39,372 INFO Saving best model at Epoch 61 +2025-04-18 08:20:57,220 INFO Epoch:62 train_loss:2.81267 +2025-04-18 08:20:59,880 INFO Epoch:62 val_res:0.493606 +2025-04-18 08:21:15,174 INFO Epoch:63 train_loss:2.76093 +2025-04-18 08:21:18,208 INFO Epoch:63 val_res:0.526854 +2025-04-18 08:21:34,624 INFO Epoch:64 train_loss:2.60047 +2025-04-18 08:21:37,463 INFO Epoch:64 val_res:0.501279 +2025-04-18 08:21:52,413 INFO Epoch:65 train_loss:2.54888 +2025-04-18 08:21:54,995 INFO Epoch:65 val_res:0.539642 +2025-04-18 08:22:10,152 INFO Epoch:66 train_loss:2.47937 +2025-04-18 08:22:12,854 INFO Epoch:66 val_res:0.534527 +2025-04-18 08:22:28,950 INFO Epoch:67 train_loss:2.43166 +2025-04-18 08:22:31,866 INFO Epoch:67 val_res:0.516624 +2025-04-18 08:22:46,418 INFO Epoch:68 train_loss:2.59725 +2025-04-18 08:22:49,085 INFO Epoch:68 val_res:0.524297 +2025-04-18 08:23:05,232 INFO Epoch:69 train_loss:2.79265 +2025-04-18 08:23:07,875 INFO Epoch:69 val_res:0.511509 +2025-04-18 08:23:23,100 INFO Epoch:70 train_loss:2.47582 +2025-04-18 08:23:25,960 INFO Epoch:70 val_res:0.524297 +2025-04-18 08:23:40,817 INFO Epoch:71 train_loss:2.42396 +2025-04-18 08:23:43,534 INFO Epoch:71 val_res:0.521739 +2025-04-18 08:23:59,602 INFO Epoch:72 train_loss:2.35202 +2025-04-18 08:24:02,539 INFO Epoch:72 val_res:0.516624 +2025-04-18 08:24:17,414 INFO Epoch:73 train_loss:2.26241 +2025-04-18 08:24:20,054 INFO Epoch:73 val_res:0.557545 +2025-04-18 08:24:36,222 INFO Epoch:74 train_loss:2.19255 +2025-04-18 08:24:39,972 INFO Epoch:74 val_res:0.539642 +2025-04-18 08:24:54,740 INFO Epoch:75 train_loss:2.33739 +2025-04-18 08:24:57,508 INFO Epoch:75 val_res:0.549872 +2025-04-18 08:25:13,340 INFO Epoch:76 train_loss:2.23520 +2025-04-18 08:25:16,552 INFO Epoch:76 val_res:0.534527 +2025-04-18 08:25:31,731 INFO Epoch:77 train_loss:2.24586 +2025-04-18 08:25:34,786 INFO Epoch:77 val_res:0.516624 +2025-04-18 08:25:51,377 INFO Epoch:78 train_loss:2.33804 +2025-04-18 08:25:54,005 INFO Epoch:78 val_res:0.542199 +2025-04-18 08:26:09,820 INFO Epoch:79 train_loss:2.27378 +2025-04-18 08:26:13,552 INFO Epoch:79 val_res:0.526854 +2025-04-18 08:26:28,699 INFO Epoch:80 train_loss:2.31355 +2025-04-18 08:26:31,178 INFO Epoch:80 val_res:0.542199 +2025-04-18 08:26:47,136 INFO Epoch:81 train_loss:2.27433 +2025-04-18 08:26:50,456 INFO Epoch:81 val_res:0.537084 +2025-04-18 08:27:05,815 INFO Epoch:82 train_loss:2.24511 +2025-04-18 08:27:08,553 INFO Epoch:82 val_res:0.567775 +2025-04-18 08:27:24,793 INFO Epoch:83 train_loss:2.27327 +2025-04-18 08:27:27,471 INFO Epoch:83 val_res:0.529412 +2025-04-18 08:27:42,959 INFO Epoch:84 train_loss:2.09835 +2025-04-18 08:27:45,988 INFO Epoch:84 val_res:0.544757 +2025-04-18 08:28:01,655 INFO Epoch:85 train_loss:2.05173 +2025-04-18 08:28:04,387 INFO Epoch:85 val_res:0.544757 +2025-04-18 08:28:19,298 INFO Epoch:86 train_loss:2.08974 +2025-04-18 08:28:22,305 INFO Epoch:86 val_res:0.557545 +2025-04-18 08:28:38,295 INFO Epoch:87 train_loss:2.07785 +2025-04-18 08:28:40,968 INFO Epoch:87 val_res:0.547315 +2025-04-18 08:28:55,719 INFO Epoch:88 train_loss:2.01031 +2025-04-18 08:28:58,789 INFO Epoch:88 val_res:0.544757 +2025-04-18 08:29:15,559 INFO Epoch:89 train_loss:2.06027 +2025-04-18 08:29:18,230 INFO Epoch:89 val_res:0.547315 +2025-04-18 08:29:32,969 INFO Epoch:90 train_loss:2.03578 +2025-04-18 08:29:36,402 INFO Epoch:90 val_res:0.537084 +2025-04-18 08:29:52,192 INFO Epoch:91 train_loss:2.01789 +2025-04-18 08:29:54,867 INFO Epoch:91 val_res:0.549872 +2025-04-18 08:30:09,795 INFO Epoch:92 train_loss:2.05236 +2025-04-18 08:30:12,854 INFO Epoch:92 val_res:0.537084 +2025-04-18 08:30:28,991 INFO Epoch:93 train_loss:2.15170 +2025-04-18 08:30:31,817 INFO Epoch:93 val_res:0.542199 +2025-04-18 08:30:47,121 INFO Epoch:94 train_loss:2.01566 +2025-04-18 08:30:49,842 INFO Epoch:94 val_res:0.557545 +2025-04-18 08:31:04,406 INFO Epoch:95 train_loss:2.04136 +2025-04-18 08:31:07,123 INFO Epoch:95 val_res:0.544757 +2025-04-18 08:31:22,314 INFO Epoch:96 train_loss:2.04382 +2025-04-18 08:31:25,477 INFO Epoch:96 val_res:0.539642 +2025-04-18 08:31:40,048 INFO Epoch:97 train_loss:2.03868 +2025-04-18 08:31:42,758 INFO Epoch:97 val_res:0.557545 +2025-04-18 08:31:59,940 INFO Epoch:98 train_loss:2.03962 +2025-04-18 08:32:02,691 INFO Epoch:98 val_res:0.570332 +2025-04-18 08:32:02,691 INFO Saving best model at Epoch 98 +2025-04-18 08:32:19,440 INFO Epoch:99 train_loss:2.09648 +2025-04-18 08:32:22,221 INFO Epoch:99 val_res:0.539642 +2025-04-18 08:32:32,722 INFO ===================================== +2025-04-18 08:32:32,723 INFO Start testing... +2025-04-18 08:32:32,723 INFO ===================================== +2025-04-18 08:32:43,606 INFO Incremental step 3 Testing res: 0.515228 +2025-04-18 08:32:43,608 INFO forgetting: 0.006961 +2025-04-18 08:32:43,611 INFO Average Accuracy: 0.587392 +2025-04-18 08:32:43,612 INFO Average Forgetting: 0.053996 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..a32c1dd4a37c4e3e658f7d517fad45178c758b8b Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..029bd6f6952a44e8d58c7d19ab85c9cf1f7809e0 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..df8c9d4dfd5b8040c79939d20588cd12b0d13a99 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..edfb9edeb9a0d9157a020942753d7de0deddbc94 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..7bd833d04fa7ff1a5b2f129f04f0266136e31f96 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_5.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..889981227eb2555251e252a850df237375d1ed19 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_5.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_6.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..62b001af90ea8cca1e29f5af40a4be9427b5098b Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_6.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_7.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..720f2e982f5e193568b0a83d3b1139954c4643ce Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_7.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_8.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..f826223b051b597b3b24beda2013877db76304d7 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_8.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_9.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..04caaf7de2a6be4e86d479a484fe95909f49a53b Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_9.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..0c15b85f0a5cb7c42a2a6b726231832f229739ec Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..734f7d34ea8ad9b4f1b95a49311a72ff14345636 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..8cf298c50f19b27f22186f6c00378e9c4e5127c0 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..d2ee54b855351afdf926afd6eb4bbb2f3e16ea9f Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..8f8db2658d2cc069bc1ec45cc22f3c273b81a779 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_5.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..5dd6af5ae574eed45ce20951146ac58b237c7031 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_5.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_6.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..22cb5c87069eaca2f42a5fbc73ca4e6e32baf5c7 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_6.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_7.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..d3ba2377fc8f7e33b2917a3dfd53d22f27507cdd Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_7.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_8.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..6be9b9c7b021a3d59f91495b368a0c49c7c54b18 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_8.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_9.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..8bda88cd5d91bddc799ff37036059f4da0486da7 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_9.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..7fa8e26d88204cdc9ef51e65136bc9c9b564b9f6 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73105016071a446079c148a16c920daffee77fdbe7053102d52cf9f5b02868a7 +size 114142801 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..465b452e5f6c34b373c0bcd79c344083bc614bc5 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ec0b42bd0eb442f4ff93f0fa8d488bd0c95f854720d849c2cab4aa1f2e6922 +size 114235217 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f983f103d09350abb45dc6485f1f0139b1837da3 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cff7af3546d3b6c51a233434550d7b88d4a78635a9d738b8aa9a1ae13fbc68a5 +size 114327377 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..56f6c524165a5e70814b28285a0a95ab38d804ca --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:867d94a320adb205b8fddd44924de29ce8f2733a9f87e142585615d9c153dea7 +size 114419729 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..27a209fb629d5ecbc977ac45445d4eccb957002f --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975e795b9ccc6661d0b94c971e41fc530557175af9153d09e0e8cb3a720dd23a +size 114512081 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_5_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_5_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f24cdfbb81ea19d8d51445eb0fea3ef8680e7c3f --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_5_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb253289795173b092656ab12f7ba7c7271ddf77db8b1967a6665b6d1ae87c1d +size 114604241 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_6_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_6_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..06cf0ba693050f1295a9794ec936702a4b372da3 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_6_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840a2ae87b9c733b800035cd49b926b6d38b584a8b2085f121234181dd5a2518 +size 114696593 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_7_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_7_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..77fb6a5c80773b08e45fb98e28a13579c1992f5b --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_7_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cefe638a894a63a4ef7a55121c6d45c568ec556d8b27698f1b13a41bf15e36c +size 114788945 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_8_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_8_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a9e177dbdd5756e46efb1254bd0c2721be17796a --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_8_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcda7fc49527b9af3af6327b70083a7923abe574a5953a5ed899012314638c24 +size 114881105 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_9_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_9_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..65809b9c71a174b8b5fad20e22dc54acfd1d222d --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/step_9_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a012c8702acd344cdf99f34cc2f4f52b0b641a4a2b0ca46deb634eb226e85b +size 114973457 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/train.log b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..255ad8e930a85a66c26584a0c4138e2963f92bb7 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_False-seed_0/train.log @@ -0,0 +1,2385 @@ +2025-04-19 03:52:32,573 INFO Namespace(class_num_per_step=10, dataset='VGGSound_100', e_prompt=False, exemplar_batch_size=128, fixed_fc=False, infer_batch_size=128, inverse=False, inverse_ends=100, inverse_starts=0, lr=0.001, lr_decay=False, max_epoches=100, memory_size=1500, milestones=[100], modality='audio-visual', num_classes=100, num_workers=4, prompt_dim=768, seed=0, train_batch_size=256, weight_decay=0.0001) +2025-04-19 03:52:32,574 INFO Training start time: 2025-04-19 03:52:32.574263 +2025-04-19 03:52:33,763 INFO ***************New Step*************************** +2025-04-19 03:52:33,763 INFO Incremental step: 0 +2025-04-19 03:53:00,560 INFO Epoch:0 train_loss:1.57833 +2025-04-19 03:53:04,295 INFO Epoch:0 val_res:0.566000 +2025-04-19 03:53:04,295 INFO Saving best model at Epoch 0 +2025-04-19 03:53:26,731 INFO Epoch:1 train_loss:0.68135 +2025-04-19 03:53:29,555 INFO Epoch:1 val_res:0.718000 +2025-04-19 03:53:29,555 INFO Saving best model at Epoch 1 +2025-04-19 03:53:47,264 INFO Epoch:2 train_loss:0.43893 +2025-04-19 03:53:49,826 INFO Epoch:2 val_res:0.760000 +2025-04-19 03:53:49,827 INFO Saving best model at Epoch 2 +2025-04-19 03:54:05,889 INFO Epoch:3 train_loss:0.32675 +2025-04-19 03:54:08,280 INFO Epoch:3 val_res:0.814000 +2025-04-19 03:54:08,281 INFO Saving best model at Epoch 3 +2025-04-19 03:54:24,721 INFO Epoch:4 train_loss:0.26638 +2025-04-19 03:54:27,169 INFO Epoch:4 val_res:0.794000 +2025-04-19 03:54:42,876 INFO Epoch:5 train_loss:0.22597 +2025-04-19 03:54:45,335 INFO Epoch:5 val_res:0.816000 +2025-04-19 03:54:45,335 INFO Saving best model at Epoch 5 +2025-04-19 03:55:02,317 INFO Epoch:6 train_loss:0.18935 +2025-04-19 03:55:04,635 INFO Epoch:6 val_res:0.800000 +2025-04-19 03:55:18,758 INFO Epoch:7 train_loss:0.16873 +2025-04-19 03:55:21,061 INFO Epoch:7 val_res:0.842000 +2025-04-19 03:55:21,061 INFO Saving best model at Epoch 7 +2025-04-19 03:55:37,210 INFO Epoch:8 train_loss:0.14080 +2025-04-19 03:55:39,697 INFO Epoch:8 val_res:0.854000 +2025-04-19 03:55:39,698 INFO Saving best model at Epoch 8 +2025-04-19 03:55:55,993 INFO Epoch:9 train_loss:0.12211 +2025-04-19 03:55:58,706 INFO Epoch:9 val_res:0.850000 +2025-04-19 03:56:14,117 INFO Epoch:10 train_loss:0.11082 +2025-04-19 03:56:16,700 INFO Epoch:10 val_res:0.850000 +2025-04-19 03:56:30,748 INFO Epoch:11 train_loss:0.09948 +2025-04-19 03:56:33,360 INFO Epoch:11 val_res:0.850000 +2025-04-19 03:56:48,196 INFO Epoch:12 train_loss:0.08492 +2025-04-19 03:56:51,238 INFO Epoch:12 val_res:0.878000 +2025-04-19 03:56:51,238 INFO Saving best model at Epoch 12 +2025-04-19 03:57:08,023 INFO Epoch:13 train_loss:0.07938 +2025-04-19 03:57:10,729 INFO Epoch:13 val_res:0.872000 +2025-04-19 03:57:25,429 INFO Epoch:14 train_loss:0.06874 +2025-04-19 03:57:27,959 INFO Epoch:14 val_res:0.880000 +2025-04-19 03:57:27,959 INFO Saving best model at Epoch 14 +2025-04-19 03:57:43,848 INFO Epoch:15 train_loss:0.06896 +2025-04-19 03:57:46,197 INFO Epoch:15 val_res:0.864000 +2025-04-19 03:58:00,051 INFO Epoch:16 train_loss:0.05633 +2025-04-19 03:58:02,499 INFO Epoch:16 val_res:0.880000 +2025-04-19 03:58:16,409 INFO Epoch:17 train_loss:0.05432 +2025-04-19 03:58:18,897 INFO Epoch:17 val_res:0.880000 +2025-04-19 03:58:33,977 INFO Epoch:18 train_loss:0.05192 +2025-04-19 03:58:36,579 INFO Epoch:18 val_res:0.860000 +2025-04-19 03:58:52,047 INFO Epoch:19 train_loss:0.04799 +2025-04-19 03:58:54,365 INFO Epoch:19 val_res:0.894000 +2025-04-19 03:58:54,365 INFO Saving best model at Epoch 19 +2025-04-19 03:59:10,328 INFO Epoch:20 train_loss:0.04055 +2025-04-19 03:59:13,090 INFO Epoch:20 val_res:0.874000 +2025-04-19 03:59:28,304 INFO Epoch:21 train_loss:0.03702 +2025-04-19 03:59:30,948 INFO Epoch:21 val_res:0.878000 +2025-04-19 03:59:45,301 INFO Epoch:22 train_loss:0.03772 +2025-04-19 03:59:47,886 INFO Epoch:22 val_res:0.870000 +2025-04-19 04:00:02,481 INFO Epoch:23 train_loss:0.03025 +2025-04-19 04:00:04,928 INFO Epoch:23 val_res:0.878000 +2025-04-19 04:00:18,509 INFO Epoch:24 train_loss:0.03009 +2025-04-19 04:00:20,880 INFO Epoch:24 val_res:0.868000 +2025-04-19 04:00:35,071 INFO Epoch:25 train_loss:0.03152 +2025-04-19 04:00:37,433 INFO Epoch:25 val_res:0.874000 +2025-04-19 04:00:51,077 INFO Epoch:26 train_loss:0.02550 +2025-04-19 04:00:53,437 INFO Epoch:26 val_res:0.868000 +2025-04-19 04:01:07,471 INFO Epoch:27 train_loss:0.02292 +2025-04-19 04:01:09,780 INFO Epoch:27 val_res:0.888000 +2025-04-19 04:01:23,609 INFO Epoch:28 train_loss:0.02158 +2025-04-19 04:01:25,834 INFO Epoch:28 val_res:0.886000 +2025-04-19 04:01:39,748 INFO Epoch:29 train_loss:0.02141 +2025-04-19 04:01:41,977 INFO Epoch:29 val_res:0.886000 +2025-04-19 04:01:56,281 INFO Epoch:30 train_loss:0.02026 +2025-04-19 04:01:58,418 INFO Epoch:30 val_res:0.890000 +2025-04-19 04:02:13,210 INFO Epoch:31 train_loss:0.01820 +2025-04-19 04:02:15,601 INFO Epoch:31 val_res:0.880000 +2025-04-19 04:02:29,400 INFO Epoch:32 train_loss:0.02193 +2025-04-19 04:02:31,511 INFO Epoch:32 val_res:0.886000 +2025-04-19 04:02:45,334 INFO Epoch:33 train_loss:0.01989 +2025-04-19 04:02:47,613 INFO Epoch:33 val_res:0.882000 +2025-04-19 04:03:01,188 INFO Epoch:34 train_loss:0.01837 +2025-04-19 04:03:03,415 INFO Epoch:34 val_res:0.886000 +2025-04-19 04:03:17,570 INFO Epoch:35 train_loss:0.01960 +2025-04-19 04:03:19,713 INFO Epoch:35 val_res:0.896000 +2025-04-19 04:03:19,714 INFO Saving best model at Epoch 35 +2025-04-19 04:03:35,818 INFO Epoch:36 train_loss:0.03499 +2025-04-19 04:03:38,426 INFO Epoch:36 val_res:0.844000 +2025-04-19 04:03:54,479 INFO Epoch:37 train_loss:0.03164 +2025-04-19 04:03:56,885 INFO Epoch:37 val_res:0.888000 +2025-04-19 04:04:11,740 INFO Epoch:38 train_loss:0.02363 +2025-04-19 04:04:13,949 INFO Epoch:38 val_res:0.854000 +2025-04-19 04:04:28,489 INFO Epoch:39 train_loss:0.03960 +2025-04-19 04:04:30,715 INFO Epoch:39 val_res:0.886000 +2025-04-19 04:04:45,070 INFO Epoch:40 train_loss:0.04674 +2025-04-19 04:04:47,589 INFO Epoch:40 val_res:0.850000 +2025-04-19 04:05:02,655 INFO Epoch:41 train_loss:0.03982 +2025-04-19 04:05:04,942 INFO Epoch:41 val_res:0.878000 +2025-04-19 04:05:18,968 INFO Epoch:42 train_loss:0.04199 +2025-04-19 04:05:21,255 INFO Epoch:42 val_res:0.826000 +2025-04-19 04:05:37,937 INFO Epoch:43 train_loss:0.04512 +2025-04-19 04:05:40,325 INFO Epoch:43 val_res:0.890000 +2025-04-19 04:05:54,703 INFO Epoch:44 train_loss:0.01358 +2025-04-19 04:05:57,091 INFO Epoch:44 val_res:0.878000 +2025-04-19 04:06:10,572 INFO Epoch:45 train_loss:0.01693 +2025-04-19 04:06:12,885 INFO Epoch:45 val_res:0.872000 +2025-04-19 04:06:26,493 INFO Epoch:46 train_loss:0.01615 +2025-04-19 04:06:28,728 INFO Epoch:46 val_res:0.876000 +2025-04-19 04:06:42,141 INFO Epoch:47 train_loss:0.01003 +2025-04-19 04:06:44,481 INFO Epoch:47 val_res:0.874000 +2025-04-19 04:06:58,057 INFO Epoch:48 train_loss:0.00787 +2025-04-19 04:07:00,348 INFO Epoch:48 val_res:0.884000 +2025-04-19 04:07:13,745 INFO Epoch:49 train_loss:0.00872 +2025-04-19 04:07:16,004 INFO Epoch:49 val_res:0.886000 +2025-04-19 04:07:29,642 INFO Epoch:50 train_loss:0.00930 +2025-04-19 04:07:31,895 INFO Epoch:50 val_res:0.890000 +2025-04-19 04:07:45,505 INFO Epoch:51 train_loss:0.00960 +2025-04-19 04:07:47,706 INFO Epoch:51 val_res:0.884000 +2025-04-19 04:08:01,194 INFO Epoch:52 train_loss:0.00920 +2025-04-19 04:08:03,673 INFO Epoch:52 val_res:0.880000 +2025-04-19 04:08:17,094 INFO Epoch:53 train_loss:0.00911 +2025-04-19 04:08:19,374 INFO Epoch:53 val_res:0.878000 +2025-04-19 04:08:32,890 INFO Epoch:54 train_loss:0.01045 +2025-04-19 04:08:35,101 INFO Epoch:54 val_res:0.874000 +2025-04-19 04:08:48,708 INFO Epoch:55 train_loss:0.00858 +2025-04-19 04:08:51,037 INFO Epoch:55 val_res:0.904000 +2025-04-19 04:08:51,038 INFO Saving best model at Epoch 55 +2025-04-19 04:09:06,645 INFO Epoch:56 train_loss:0.00871 +2025-04-19 04:09:09,110 INFO Epoch:56 val_res:0.892000 +2025-04-19 04:09:22,343 INFO Epoch:57 train_loss:0.00773 +2025-04-19 04:09:24,674 INFO Epoch:57 val_res:0.882000 +2025-04-19 04:09:38,193 INFO Epoch:58 train_loss:0.00809 +2025-04-19 04:09:40,581 INFO Epoch:58 val_res:0.892000 +2025-04-19 04:09:53,621 INFO Epoch:59 train_loss:0.00792 +2025-04-19 04:09:56,021 INFO Epoch:59 val_res:0.884000 +2025-04-19 04:10:08,983 INFO Epoch:60 train_loss:0.00943 +2025-04-19 04:10:11,407 INFO Epoch:60 val_res:0.878000 +2025-04-19 04:10:24,718 INFO Epoch:61 train_loss:0.00851 +2025-04-19 04:10:27,220 INFO Epoch:61 val_res:0.892000 +2025-04-19 04:10:40,790 INFO Epoch:62 train_loss:0.00975 +2025-04-19 04:10:43,367 INFO Epoch:62 val_res:0.882000 +2025-04-19 04:10:56,743 INFO Epoch:63 train_loss:0.00975 +2025-04-19 04:10:59,475 INFO Epoch:63 val_res:0.890000 +2025-04-19 04:11:12,723 INFO Epoch:64 train_loss:0.00896 +2025-04-19 04:11:15,397 INFO Epoch:64 val_res:0.880000 +2025-04-19 04:11:28,936 INFO Epoch:65 train_loss:0.00773 +2025-04-19 04:11:31,664 INFO Epoch:65 val_res:0.886000 +2025-04-19 04:11:46,689 INFO Epoch:66 train_loss:0.00757 +2025-04-19 04:11:49,157 INFO Epoch:66 val_res:0.886000 +2025-04-19 04:12:02,394 INFO Epoch:67 train_loss:0.00688 +2025-04-19 04:12:05,209 INFO Epoch:67 val_res:0.882000 +2025-04-19 04:12:18,791 INFO Epoch:68 train_loss:0.00842 +2025-04-19 04:12:21,168 INFO Epoch:68 val_res:0.880000 +2025-04-19 04:12:33,984 INFO Epoch:69 train_loss:0.00819 +2025-04-19 04:12:36,353 INFO Epoch:69 val_res:0.896000 +2025-04-19 04:12:49,600 INFO Epoch:70 train_loss:0.00967 +2025-04-19 04:12:51,986 INFO Epoch:70 val_res:0.890000 +2025-04-19 04:13:04,855 INFO Epoch:71 train_loss:0.00807 +2025-04-19 04:13:07,246 INFO Epoch:71 val_res:0.876000 +2025-04-19 04:13:20,542 INFO Epoch:72 train_loss:0.03392 +2025-04-19 04:13:22,859 INFO Epoch:72 val_res:0.868000 +2025-04-19 04:13:36,330 INFO Epoch:73 train_loss:1.02883 +2025-04-19 04:13:38,611 INFO Epoch:73 val_res:0.726000 +2025-04-19 04:13:51,856 INFO Epoch:74 train_loss:0.36634 +2025-04-19 04:13:54,127 INFO Epoch:74 val_res:0.820000 +2025-04-19 04:14:07,880 INFO Epoch:75 train_loss:0.08752 +2025-04-19 04:14:10,136 INFO Epoch:75 val_res:0.868000 +2025-04-19 04:14:23,286 INFO Epoch:76 train_loss:0.02406 +2025-04-19 04:14:25,529 INFO Epoch:76 val_res:0.882000 +2025-04-19 04:14:38,939 INFO Epoch:77 train_loss:0.01029 +2025-04-19 04:14:41,180 INFO Epoch:77 val_res:0.882000 +2025-04-19 04:14:54,383 INFO Epoch:78 train_loss:0.00665 +2025-04-19 04:14:56,600 INFO Epoch:78 val_res:0.892000 +2025-04-19 04:15:09,911 INFO Epoch:79 train_loss:0.00641 +2025-04-19 04:15:12,099 INFO Epoch:79 val_res:0.896000 +2025-04-19 04:15:25,440 INFO Epoch:80 train_loss:0.00621 +2025-04-19 04:15:27,704 INFO Epoch:80 val_res:0.884000 +2025-04-19 04:15:40,699 INFO Epoch:81 train_loss:0.00490 +2025-04-19 04:15:42,860 INFO Epoch:81 val_res:0.878000 +2025-04-19 04:15:56,281 INFO Epoch:82 train_loss:0.00477 +2025-04-19 04:15:58,507 INFO Epoch:82 val_res:0.880000 +2025-04-19 04:16:11,509 INFO Epoch:83 train_loss:0.00474 +2025-04-19 04:16:13,821 INFO Epoch:83 val_res:0.890000 +2025-04-19 04:16:26,833 INFO Epoch:84 train_loss:0.00468 +2025-04-19 04:16:29,100 INFO Epoch:84 val_res:0.886000 +2025-04-19 04:16:41,692 INFO Epoch:85 train_loss:0.00462 +2025-04-19 04:16:44,028 INFO Epoch:85 val_res:0.880000 +2025-04-19 04:16:56,892 INFO Epoch:86 train_loss:0.00462 +2025-04-19 04:16:59,333 INFO Epoch:86 val_res:0.886000 +2025-04-19 04:17:12,277 INFO Epoch:87 train_loss:0.00464 +2025-04-19 04:17:14,671 INFO Epoch:87 val_res:0.888000 +2025-04-19 04:17:27,530 INFO Epoch:88 train_loss:0.00489 +2025-04-19 04:17:29,971 INFO Epoch:88 val_res:0.874000 +2025-04-19 04:17:43,435 INFO Epoch:89 train_loss:0.00495 +2025-04-19 04:17:45,765 INFO Epoch:89 val_res:0.874000 +2025-04-19 04:17:58,929 INFO Epoch:90 train_loss:0.00525 +2025-04-19 04:18:01,456 INFO Epoch:90 val_res:0.894000 +2025-04-19 04:18:14,617 INFO Epoch:91 train_loss:0.00546 +2025-04-19 04:18:16,951 INFO Epoch:91 val_res:0.878000 +2025-04-19 04:18:30,153 INFO Epoch:92 train_loss:0.00500 +2025-04-19 04:18:32,413 INFO Epoch:92 val_res:0.880000 +2025-04-19 04:18:45,564 INFO Epoch:93 train_loss:0.00509 +2025-04-19 04:18:47,820 INFO Epoch:93 val_res:0.888000 +2025-04-19 04:19:01,758 INFO Epoch:94 train_loss:0.00488 +2025-04-19 04:19:03,984 INFO Epoch:94 val_res:0.876000 +2025-04-19 04:19:17,579 INFO Epoch:95 train_loss:0.00512 +2025-04-19 04:19:19,843 INFO Epoch:95 val_res:0.878000 +2025-04-19 04:19:33,165 INFO Epoch:96 train_loss:0.00509 +2025-04-19 04:19:35,542 INFO Epoch:96 val_res:0.880000 +2025-04-19 04:19:48,823 INFO Epoch:97 train_loss:0.00508 +2025-04-19 04:19:51,021 INFO Epoch:97 val_res:0.872000 +2025-04-19 04:20:04,404 INFO Epoch:98 train_loss:0.00530 +2025-04-19 04:20:06,584 INFO Epoch:98 val_res:0.888000 +2025-04-19 04:20:19,964 INFO Epoch:99 train_loss:0.00515 +2025-04-19 04:20:22,293 INFO Epoch:99 val_res:0.882000 +2025-04-19 04:20:23,016 INFO ===================================== +2025-04-19 04:20:23,017 INFO Start testing... +2025-04-19 04:20:23,017 INFO ===================================== +2025-04-19 04:20:26,108 INFO Incremental step 0 Testing res: 0.912000 +2025-04-19 04:20:26,115 INFO ***************New Step*************************** +2025-04-19 04:20:26,115 INFO Incremental step: 1 +2025-04-19 04:20:26,311 INFO actual size of exemplar set: 1449 +2025-04-19 04:21:11,889 INFO Epoch:0 train_loss:1.61306 +2025-04-19 04:21:16,894 INFO Epoch:0 val_res:0.442000 +2025-04-19 04:21:16,895 INFO Saving best model at Epoch 0 +2025-04-19 04:21:53,611 INFO Epoch:1 train_loss:0.63848 +2025-04-19 04:21:57,419 INFO Epoch:1 val_res:0.473000 +2025-04-19 04:21:57,419 INFO Saving best model at Epoch 1 +2025-04-19 04:22:31,525 INFO Epoch:2 train_loss:0.39789 +2025-04-19 04:22:35,379 INFO Epoch:2 val_res:0.512000 +2025-04-19 04:22:35,379 INFO Saving best model at Epoch 2 +2025-04-19 04:23:07,856 INFO Epoch:3 train_loss:0.30858 +2025-04-19 04:23:11,736 INFO Epoch:3 val_res:0.540000 +2025-04-19 04:23:11,736 INFO Saving best model at Epoch 3 +2025-04-19 04:23:43,577 INFO Epoch:4 train_loss:0.27079 +2025-04-19 04:23:48,017 INFO Epoch:4 val_res:0.556000 +2025-04-19 04:23:48,018 INFO Saving best model at Epoch 4 +2025-04-19 04:24:20,183 INFO Epoch:5 train_loss:0.23732 +2025-04-19 04:24:24,267 INFO Epoch:5 val_res:0.573000 +2025-04-19 04:24:24,268 INFO Saving best model at Epoch 5 +2025-04-19 04:24:56,477 INFO Epoch:6 train_loss:0.21373 +2025-04-19 04:25:00,568 INFO Epoch:6 val_res:0.581000 +2025-04-19 04:25:00,568 INFO Saving best model at Epoch 6 +2025-04-19 04:25:32,209 INFO Epoch:7 train_loss:0.19452 +2025-04-19 04:25:36,372 INFO Epoch:7 val_res:0.600000 +2025-04-19 04:25:36,373 INFO Saving best model at Epoch 7 +2025-04-19 04:26:08,194 INFO Epoch:8 train_loss:0.18127 +2025-04-19 04:26:12,418 INFO Epoch:8 val_res:0.615000 +2025-04-19 04:26:12,418 INFO Saving best model at Epoch 8 +2025-04-19 04:26:45,292 INFO Epoch:9 train_loss:0.16904 +2025-04-19 04:26:49,489 INFO Epoch:9 val_res:0.626000 +2025-04-19 04:26:49,490 INFO Saving best model at Epoch 9 +2025-04-19 04:27:22,600 INFO Epoch:10 train_loss:0.15319 +2025-04-19 04:27:26,994 INFO Epoch:10 val_res:0.641000 +2025-04-19 04:27:26,995 INFO Saving best model at Epoch 10 +2025-04-19 04:28:01,399 INFO Epoch:11 train_loss:0.14190 +2025-04-19 04:28:05,757 INFO Epoch:11 val_res:0.659000 +2025-04-19 04:28:05,757 INFO Saving best model at Epoch 11 +2025-04-19 04:28:39,773 INFO Epoch:12 train_loss:0.12912 +2025-04-19 04:28:44,172 INFO Epoch:12 val_res:0.661000 +2025-04-19 04:28:44,172 INFO Saving best model at Epoch 12 +2025-04-19 04:29:18,512 INFO Epoch:13 train_loss:0.11945 +2025-04-19 04:29:22,761 INFO Epoch:13 val_res:0.679000 +2025-04-19 04:29:22,762 INFO Saving best model at Epoch 13 +2025-04-19 04:29:57,049 INFO Epoch:14 train_loss:0.10951 +2025-04-19 04:30:01,086 INFO Epoch:14 val_res:0.687000 +2025-04-19 04:30:01,087 INFO Saving best model at Epoch 14 +2025-04-19 04:30:34,325 INFO Epoch:15 train_loss:0.09962 +2025-04-19 04:30:38,115 INFO Epoch:15 val_res:0.694000 +2025-04-19 04:30:38,115 INFO Saving best model at Epoch 15 +2025-04-19 04:31:10,259 INFO Epoch:16 train_loss:0.09642 +2025-04-19 04:31:14,422 INFO Epoch:16 val_res:0.706000 +2025-04-19 04:31:14,422 INFO Saving best model at Epoch 16 +2025-04-19 04:31:47,242 INFO Epoch:17 train_loss:0.08657 +2025-04-19 04:31:51,343 INFO Epoch:17 val_res:0.716000 +2025-04-19 04:31:51,343 INFO Saving best model at Epoch 17 +2025-04-19 04:32:26,018 INFO Epoch:18 train_loss:0.08759 +2025-04-19 04:32:30,004 INFO Epoch:18 val_res:0.718000 +2025-04-19 04:32:30,004 INFO Saving best model at Epoch 18 +2025-04-19 04:33:04,777 INFO Epoch:19 train_loss:0.07872 +2025-04-19 04:33:08,828 INFO Epoch:19 val_res:0.727000 +2025-04-19 04:33:08,829 INFO Saving best model at Epoch 19 +2025-04-19 04:33:43,707 INFO Epoch:20 train_loss:0.07650 +2025-04-19 04:33:47,752 INFO Epoch:20 val_res:0.731000 +2025-04-19 04:33:47,752 INFO Saving best model at Epoch 20 +2025-04-19 04:34:21,342 INFO Epoch:21 train_loss:0.06656 +2025-04-19 04:34:25,615 INFO Epoch:21 val_res:0.747000 +2025-04-19 04:34:25,615 INFO Saving best model at Epoch 21 +2025-04-19 04:34:58,745 INFO Epoch:22 train_loss:0.05997 +2025-04-19 04:35:03,509 INFO Epoch:22 val_res:0.743000 +2025-04-19 04:35:35,303 INFO Epoch:23 train_loss:0.05807 +2025-04-19 04:35:39,689 INFO Epoch:23 val_res:0.750000 +2025-04-19 04:35:39,689 INFO Saving best model at Epoch 23 +2025-04-19 04:36:13,424 INFO Epoch:24 train_loss:0.05045 +2025-04-19 04:36:17,375 INFO Epoch:24 val_res:0.753000 +2025-04-19 04:36:17,375 INFO Saving best model at Epoch 24 +2025-04-19 04:36:49,224 INFO Epoch:25 train_loss:0.06228 +2025-04-19 04:36:53,446 INFO Epoch:25 val_res:0.769000 +2025-04-19 04:36:53,447 INFO Saving best model at Epoch 25 +2025-04-19 04:37:27,987 INFO Epoch:26 train_loss:0.06307 +2025-04-19 04:37:32,329 INFO Epoch:26 val_res:0.763000 +2025-04-19 04:38:03,106 INFO Epoch:27 train_loss:0.05659 +2025-04-19 04:38:07,340 INFO Epoch:27 val_res:0.765000 +2025-04-19 04:38:40,582 INFO Epoch:28 train_loss:0.04307 +2025-04-19 04:38:44,966 INFO Epoch:28 val_res:0.783000 +2025-04-19 04:38:44,966 INFO Saving best model at Epoch 28 +2025-04-19 04:39:17,395 INFO Epoch:29 train_loss:0.04540 +2025-04-19 04:39:21,441 INFO Epoch:29 val_res:0.780000 +2025-04-19 04:39:52,038 INFO Epoch:30 train_loss:0.04085 +2025-04-19 04:39:56,060 INFO Epoch:30 val_res:0.786000 +2025-04-19 04:39:56,060 INFO Saving best model at Epoch 30 +2025-04-19 04:40:30,161 INFO Epoch:31 train_loss:0.03575 +2025-04-19 04:40:34,494 INFO Epoch:31 val_res:0.788000 +2025-04-19 04:40:34,494 INFO Saving best model at Epoch 31 +2025-04-19 04:41:07,944 INFO Epoch:32 train_loss:0.03488 +2025-04-19 04:41:12,156 INFO Epoch:32 val_res:0.789000 +2025-04-19 04:41:12,156 INFO Saving best model at Epoch 32 +2025-04-19 04:41:45,780 INFO Epoch:33 train_loss:0.03572 +2025-04-19 04:41:49,667 INFO Epoch:33 val_res:0.791000 +2025-04-19 04:41:49,668 INFO Saving best model at Epoch 33 +2025-04-19 04:42:21,824 INFO Epoch:34 train_loss:0.04000 +2025-04-19 04:42:25,684 INFO Epoch:34 val_res:0.795000 +2025-04-19 04:42:25,684 INFO Saving best model at Epoch 34 +2025-04-19 04:42:59,480 INFO Epoch:35 train_loss:0.04629 +2025-04-19 04:43:03,635 INFO Epoch:35 val_res:0.792000 +2025-04-19 04:43:35,438 INFO Epoch:36 train_loss:0.04387 +2025-04-19 04:43:39,417 INFO Epoch:36 val_res:0.799000 +2025-04-19 04:43:39,418 INFO Saving best model at Epoch 36 +2025-04-19 04:44:11,694 INFO Epoch:37 train_loss:0.03761 +2025-04-19 04:44:15,720 INFO Epoch:37 val_res:0.802000 +2025-04-19 04:44:15,720 INFO Saving best model at Epoch 37 +2025-04-19 04:44:48,309 INFO Epoch:38 train_loss:0.03219 +2025-04-19 04:44:52,855 INFO Epoch:38 val_res:0.801000 +2025-04-19 04:45:23,883 INFO Epoch:39 train_loss:0.03413 +2025-04-19 04:45:27,899 INFO Epoch:39 val_res:0.793000 +2025-04-19 04:45:59,703 INFO Epoch:40 train_loss:0.03272 +2025-04-19 04:46:03,882 INFO Epoch:40 val_res:0.801000 +2025-04-19 04:46:34,652 INFO Epoch:41 train_loss:0.02582 +2025-04-19 04:46:39,047 INFO Epoch:41 val_res:0.808000 +2025-04-19 04:46:39,048 INFO Saving best model at Epoch 41 +2025-04-19 04:47:13,256 INFO Epoch:42 train_loss:0.02442 +2025-04-19 04:47:17,775 INFO Epoch:42 val_res:0.805000 +2025-04-19 04:47:50,319 INFO Epoch:43 train_loss:0.02360 +2025-04-19 04:47:54,276 INFO Epoch:43 val_res:0.799000 +2025-04-19 04:48:27,843 INFO Epoch:44 train_loss:0.02430 +2025-04-19 04:48:32,356 INFO Epoch:44 val_res:0.808000 +2025-04-19 04:49:04,074 INFO Epoch:45 train_loss:0.02459 +2025-04-19 04:49:08,237 INFO Epoch:45 val_res:0.800000 +2025-04-19 04:49:39,486 INFO Epoch:46 train_loss:0.02523 +2025-04-19 04:49:43,402 INFO Epoch:46 val_res:0.806000 +2025-04-19 04:50:15,759 INFO Epoch:47 train_loss:0.02290 +2025-04-19 04:50:20,128 INFO Epoch:47 val_res:0.813000 +2025-04-19 04:50:20,128 INFO Saving best model at Epoch 47 +2025-04-19 04:50:54,841 INFO Epoch:48 train_loss:0.02070 +2025-04-19 04:50:58,676 INFO Epoch:48 val_res:0.811000 +2025-04-19 04:51:30,935 INFO Epoch:49 train_loss:0.02279 +2025-04-19 04:51:34,797 INFO Epoch:49 val_res:0.805000 +2025-04-19 04:52:08,880 INFO Epoch:50 train_loss:0.02401 +2025-04-19 04:52:13,807 INFO Epoch:50 val_res:0.806000 +2025-04-19 04:52:46,232 INFO Epoch:51 train_loss:0.03619 +2025-04-19 04:52:50,766 INFO Epoch:51 val_res:0.806000 +2025-04-19 04:53:21,617 INFO Epoch:52 train_loss:0.03598 +2025-04-19 04:53:26,043 INFO Epoch:52 val_res:0.803000 +2025-04-19 04:53:59,669 INFO Epoch:53 train_loss:0.03099 +2025-04-19 04:54:04,040 INFO Epoch:53 val_res:0.811000 +2025-04-19 04:54:35,795 INFO Epoch:54 train_loss:0.02577 +2025-04-19 04:54:39,835 INFO Epoch:54 val_res:0.808000 +2025-04-19 04:55:13,637 INFO Epoch:55 train_loss:0.03215 +2025-04-19 04:55:18,013 INFO Epoch:55 val_res:0.809000 +2025-04-19 04:55:50,283 INFO Epoch:56 train_loss:0.03078 +2025-04-19 04:55:54,609 INFO Epoch:56 val_res:0.812000 +2025-04-19 04:56:26,974 INFO Epoch:57 train_loss:0.03704 +2025-04-19 04:56:31,418 INFO Epoch:57 val_res:0.804000 +2025-04-19 04:57:06,172 INFO Epoch:58 train_loss:0.04212 +2025-04-19 04:57:11,123 INFO Epoch:58 val_res:0.795000 +2025-04-19 04:57:46,425 INFO Epoch:59 train_loss:0.15724 +2025-04-19 04:57:51,492 INFO Epoch:59 val_res:0.776000 +2025-04-19 04:58:24,939 INFO Epoch:60 train_loss:0.17889 +2025-04-19 04:58:28,899 INFO Epoch:60 val_res:0.800000 +2025-04-19 04:59:03,109 INFO Epoch:61 train_loss:0.05780 +2025-04-19 04:59:07,212 INFO Epoch:61 val_res:0.815000 +2025-04-19 04:59:07,213 INFO Saving best model at Epoch 61 +2025-04-19 04:59:41,655 INFO Epoch:62 train_loss:0.02708 +2025-04-19 04:59:45,883 INFO Epoch:62 val_res:0.806000 +2025-04-19 05:00:18,417 INFO Epoch:63 train_loss:0.01875 +2025-04-19 05:00:23,865 INFO Epoch:63 val_res:0.806000 +2025-04-19 05:00:56,324 INFO Epoch:64 train_loss:0.01627 +2025-04-19 05:01:00,862 INFO Epoch:64 val_res:0.813000 +2025-04-19 05:01:33,410 INFO Epoch:65 train_loss:0.01664 +2025-04-19 05:01:37,482 INFO Epoch:65 val_res:0.808000 +2025-04-19 05:02:11,313 INFO Epoch:66 train_loss:0.01541 +2025-04-19 05:02:15,249 INFO Epoch:66 val_res:0.809000 +2025-04-19 05:02:47,787 INFO Epoch:67 train_loss:0.01483 +2025-04-19 05:02:51,726 INFO Epoch:67 val_res:0.803000 +2025-04-19 05:03:24,510 INFO Epoch:68 train_loss:0.01477 +2025-04-19 05:03:28,681 INFO Epoch:68 val_res:0.804000 +2025-04-19 05:04:01,241 INFO Epoch:69 train_loss:0.01413 +2025-04-19 05:04:05,281 INFO Epoch:69 val_res:0.802000 +2025-04-19 05:04:37,101 INFO Epoch:70 train_loss:0.01412 +2025-04-19 05:04:41,009 INFO Epoch:70 val_res:0.807000 +2025-04-19 05:05:12,326 INFO Epoch:71 train_loss:0.01504 +2025-04-19 05:05:16,214 INFO Epoch:71 val_res:0.804000 +2025-04-19 05:05:49,066 INFO Epoch:72 train_loss:0.01442 +2025-04-19 05:05:53,123 INFO Epoch:72 val_res:0.808000 +2025-04-19 05:06:25,357 INFO Epoch:73 train_loss:0.01459 +2025-04-19 05:06:29,591 INFO Epoch:73 val_res:0.807000 +2025-04-19 05:07:00,994 INFO Epoch:74 train_loss:0.01592 +2025-04-19 05:07:04,753 INFO Epoch:74 val_res:0.804000 +2025-04-19 05:07:34,695 INFO Epoch:75 train_loss:0.01528 +2025-04-19 05:07:38,459 INFO Epoch:75 val_res:0.808000 +2025-04-19 05:08:08,529 INFO Epoch:76 train_loss:0.01531 +2025-04-19 05:08:12,035 INFO Epoch:76 val_res:0.791000 +2025-04-19 05:08:42,006 INFO Epoch:77 train_loss:0.01564 +2025-04-19 05:08:45,782 INFO Epoch:77 val_res:0.811000 +2025-04-19 05:09:16,307 INFO Epoch:78 train_loss:0.01965 +2025-04-19 05:09:19,913 INFO Epoch:78 val_res:0.804000 +2025-04-19 05:09:50,082 INFO Epoch:79 train_loss:0.01948 +2025-04-19 05:09:53,602 INFO Epoch:79 val_res:0.805000 +2025-04-19 05:10:22,736 INFO Epoch:80 train_loss:0.01767 +2025-04-19 05:10:26,300 INFO Epoch:80 val_res:0.810000 +2025-04-19 05:10:55,963 INFO Epoch:81 train_loss:0.01627 +2025-04-19 05:10:59,568 INFO Epoch:81 val_res:0.809000 +2025-04-19 05:11:29,790 INFO Epoch:82 train_loss:0.01575 +2025-04-19 05:11:33,343 INFO Epoch:82 val_res:0.802000 +2025-04-19 05:12:03,629 INFO Epoch:83 train_loss:0.01567 +2025-04-19 05:12:07,250 INFO Epoch:83 val_res:0.811000 +2025-04-19 05:12:37,409 INFO Epoch:84 train_loss:0.01818 +2025-04-19 05:12:41,106 INFO Epoch:84 val_res:0.806000 +2025-04-19 05:13:11,232 INFO Epoch:85 train_loss:0.01806 +2025-04-19 05:13:14,850 INFO Epoch:85 val_res:0.803000 +2025-04-19 05:13:45,669 INFO Epoch:86 train_loss:0.02684 +2025-04-19 05:13:49,361 INFO Epoch:86 val_res:0.804000 +2025-04-19 05:14:20,252 INFO Epoch:87 train_loss:0.05388 +2025-04-19 05:14:24,007 INFO Epoch:87 val_res:0.718000 +2025-04-19 05:14:53,625 INFO Epoch:88 train_loss:0.70209 +2025-04-19 05:14:57,623 INFO Epoch:88 val_res:0.766000 +2025-04-19 05:15:27,190 INFO Epoch:89 train_loss:0.57403 +2025-04-19 05:15:31,178 INFO Epoch:89 val_res:0.711000 +2025-04-19 05:15:59,240 INFO Epoch:90 train_loss:0.21237 +2025-04-19 05:16:02,982 INFO Epoch:90 val_res:0.740000 +2025-04-19 05:16:32,986 INFO Epoch:91 train_loss:0.08692 +2025-04-19 05:16:36,727 INFO Epoch:91 val_res:0.761000 +2025-04-19 05:17:06,679 INFO Epoch:92 train_loss:0.03870 +2025-04-19 05:17:10,273 INFO Epoch:92 val_res:0.769000 +2025-04-19 05:17:41,073 INFO Epoch:93 train_loss:0.02361 +2025-04-19 05:17:44,802 INFO Epoch:93 val_res:0.776000 +2025-04-19 05:18:14,876 INFO Epoch:94 train_loss:0.01767 +2025-04-19 05:18:18,480 INFO Epoch:94 val_res:0.782000 +2025-04-19 05:18:47,650 INFO Epoch:95 train_loss:0.01650 +2025-04-19 05:18:51,261 INFO Epoch:95 val_res:0.782000 +2025-04-19 05:19:20,176 INFO Epoch:96 train_loss:0.01398 +2025-04-19 05:19:23,738 INFO Epoch:96 val_res:0.785000 +2025-04-19 05:19:53,006 INFO Epoch:97 train_loss:0.01293 +2025-04-19 05:19:56,598 INFO Epoch:97 val_res:0.783000 +2025-04-19 05:20:26,013 INFO Epoch:98 train_loss:0.01256 +2025-04-19 05:20:29,691 INFO Epoch:98 val_res:0.792000 +2025-04-19 05:20:59,123 INFO Epoch:99 train_loss:0.01214 +2025-04-19 05:21:02,892 INFO Epoch:99 val_res:0.794000 +2025-04-19 05:21:03,676 INFO ===================================== +2025-04-19 05:21:03,677 INFO Start testing... +2025-04-19 05:21:03,677 INFO ===================================== +2025-04-19 05:21:08,283 INFO Incremental step 1 Testing res: 0.792000 +2025-04-19 05:21:08,285 INFO forgetting: 0.128000 +2025-04-19 05:21:08,297 INFO ***************New Step*************************** +2025-04-19 05:21:08,297 INFO Incremental step: 2 +2025-04-19 05:21:08,465 INFO actual size of exemplar set: 1500 +2025-04-19 05:21:43,880 INFO Epoch:0 train_loss:1.93296 +2025-04-19 05:21:50,026 INFO Epoch:0 val_res:0.527333 +2025-04-19 05:21:50,027 INFO Saving best model at Epoch 0 +2025-04-19 05:22:25,159 INFO Epoch:1 train_loss:0.63175 +2025-04-19 05:22:30,516 INFO Epoch:1 val_res:0.552000 +2025-04-19 05:22:30,517 INFO Saving best model at Epoch 1 +2025-04-19 05:23:04,221 INFO Epoch:2 train_loss:0.41519 +2025-04-19 05:23:09,258 INFO Epoch:2 val_res:0.558000 +2025-04-19 05:23:09,258 INFO Saving best model at Epoch 2 +2025-04-19 05:23:42,344 INFO Epoch:3 train_loss:0.34243 +2025-04-19 05:23:47,162 INFO Epoch:3 val_res:0.566667 +2025-04-19 05:23:47,163 INFO Saving best model at Epoch 3 +2025-04-19 05:24:21,171 INFO Epoch:4 train_loss:0.29480 +2025-04-19 05:24:25,904 INFO Epoch:4 val_res:0.576000 +2025-04-19 05:24:25,905 INFO Saving best model at Epoch 4 +2025-04-19 05:24:59,888 INFO Epoch:5 train_loss:0.26574 +2025-04-19 05:25:04,851 INFO Epoch:5 val_res:0.580667 +2025-04-19 05:25:04,851 INFO Saving best model at Epoch 5 +2025-04-19 05:25:38,548 INFO Epoch:6 train_loss:0.24032 +2025-04-19 05:25:44,018 INFO Epoch:6 val_res:0.595333 +2025-04-19 05:25:44,019 INFO Saving best model at Epoch 6 +2025-04-19 05:26:18,207 INFO Epoch:7 train_loss:0.22219 +2025-04-19 05:26:23,428 INFO Epoch:7 val_res:0.602667 +2025-04-19 05:26:23,428 INFO Saving best model at Epoch 7 +2025-04-19 05:26:57,309 INFO Epoch:8 train_loss:0.20636 +2025-04-19 05:27:02,045 INFO Epoch:8 val_res:0.606000 +2025-04-19 05:27:02,046 INFO Saving best model at Epoch 8 +2025-04-19 05:27:35,635 INFO Epoch:9 train_loss:0.18960 +2025-04-19 05:27:40,437 INFO Epoch:9 val_res:0.617333 +2025-04-19 05:27:40,437 INFO Saving best model at Epoch 9 +2025-04-19 05:28:15,418 INFO Epoch:10 train_loss:0.17769 +2025-04-19 05:28:20,286 INFO Epoch:10 val_res:0.622000 +2025-04-19 05:28:20,286 INFO Saving best model at Epoch 10 +2025-04-19 05:28:55,823 INFO Epoch:11 train_loss:0.16686 +2025-04-19 05:29:00,816 INFO Epoch:11 val_res:0.624000 +2025-04-19 05:29:00,817 INFO Saving best model at Epoch 11 +2025-04-19 05:29:35,884 INFO Epoch:12 train_loss:0.15107 +2025-04-19 05:29:41,042 INFO Epoch:12 val_res:0.635333 +2025-04-19 05:29:41,043 INFO Saving best model at Epoch 12 +2025-04-19 05:30:16,921 INFO Epoch:13 train_loss:0.14188 +2025-04-19 05:30:22,084 INFO Epoch:13 val_res:0.640667 +2025-04-19 05:30:22,084 INFO Saving best model at Epoch 13 +2025-04-19 05:30:56,619 INFO Epoch:14 train_loss:0.14061 +2025-04-19 05:31:01,736 INFO Epoch:14 val_res:0.644000 +2025-04-19 05:31:01,737 INFO Saving best model at Epoch 14 +2025-04-19 05:31:35,425 INFO Epoch:15 train_loss:0.12752 +2025-04-19 05:31:40,134 INFO Epoch:15 val_res:0.654667 +2025-04-19 05:31:40,134 INFO Saving best model at Epoch 15 +2025-04-19 05:32:14,093 INFO Epoch:16 train_loss:0.11989 +2025-04-19 05:32:18,951 INFO Epoch:16 val_res:0.656000 +2025-04-19 05:32:18,951 INFO Saving best model at Epoch 16 +2025-04-19 05:32:54,189 INFO Epoch:17 train_loss:0.11247 +2025-04-19 05:32:59,132 INFO Epoch:17 val_res:0.667333 +2025-04-19 05:32:59,133 INFO Saving best model at Epoch 17 +2025-04-19 05:33:33,810 INFO Epoch:18 train_loss:0.11277 +2025-04-19 05:33:38,698 INFO Epoch:18 val_res:0.668000 +2025-04-19 05:33:38,699 INFO Saving best model at Epoch 18 +2025-04-19 05:34:13,288 INFO Epoch:19 train_loss:0.12179 +2025-04-19 05:34:18,313 INFO Epoch:19 val_res:0.676667 +2025-04-19 05:34:18,313 INFO Saving best model at Epoch 19 +2025-04-19 05:34:52,821 INFO Epoch:20 train_loss:0.12362 +2025-04-19 05:34:57,638 INFO Epoch:20 val_res:0.680000 +2025-04-19 05:34:57,639 INFO Saving best model at Epoch 20 +2025-04-19 05:35:32,674 INFO Epoch:21 train_loss:0.14114 +2025-04-19 05:35:37,614 INFO Epoch:21 val_res:0.697333 +2025-04-19 05:35:37,614 INFO Saving best model at Epoch 21 +2025-04-19 05:36:11,938 INFO Epoch:22 train_loss:0.10912 +2025-04-19 05:36:17,045 INFO Epoch:22 val_res:0.694667 +2025-04-19 05:36:49,356 INFO Epoch:23 train_loss:0.09844 +2025-04-19 05:36:54,389 INFO Epoch:23 val_res:0.696000 +2025-04-19 05:37:27,030 INFO Epoch:24 train_loss:0.11175 +2025-04-19 05:37:32,007 INFO Epoch:24 val_res:0.717333 +2025-04-19 05:37:32,008 INFO Saving best model at Epoch 24 +2025-04-19 05:38:06,067 INFO Epoch:25 train_loss:0.10783 +2025-04-19 05:38:11,054 INFO Epoch:25 val_res:0.706000 +2025-04-19 05:38:42,962 INFO Epoch:26 train_loss:0.08142 +2025-04-19 05:38:48,084 INFO Epoch:26 val_res:0.719333 +2025-04-19 05:38:48,084 INFO Saving best model at Epoch 26 +2025-04-19 05:39:22,159 INFO Epoch:27 train_loss:0.07258 +2025-04-19 05:39:27,150 INFO Epoch:27 val_res:0.721333 +2025-04-19 05:39:27,151 INFO Saving best model at Epoch 27 +2025-04-19 05:40:01,504 INFO Epoch:28 train_loss:0.06849 +2025-04-19 05:40:06,490 INFO Epoch:28 val_res:0.724667 +2025-04-19 05:40:06,491 INFO Saving best model at Epoch 28 +2025-04-19 05:40:41,208 INFO Epoch:29 train_loss:0.07818 +2025-04-19 05:40:46,352 INFO Epoch:29 val_res:0.722000 +2025-04-19 05:41:18,787 INFO Epoch:30 train_loss:0.08479 +2025-04-19 05:41:23,668 INFO Epoch:30 val_res:0.726667 +2025-04-19 05:41:23,668 INFO Saving best model at Epoch 30 +2025-04-19 05:41:58,109 INFO Epoch:31 train_loss:0.07419 +2025-04-19 05:42:02,930 INFO Epoch:31 val_res:0.730000 +2025-04-19 05:42:02,930 INFO Saving best model at Epoch 31 +2025-04-19 05:42:37,868 INFO Epoch:32 train_loss:0.09984 +2025-04-19 05:42:42,788 INFO Epoch:32 val_res:0.728667 +2025-04-19 05:43:15,178 INFO Epoch:33 train_loss:0.17702 +2025-04-19 05:43:19,998 INFO Epoch:33 val_res:0.728667 +2025-04-19 05:43:51,619 INFO Epoch:34 train_loss:0.09923 +2025-04-19 05:43:56,507 INFO Epoch:34 val_res:0.731333 +2025-04-19 05:43:56,508 INFO Saving best model at Epoch 34 +2025-04-19 05:44:30,406 INFO Epoch:35 train_loss:0.06388 +2025-04-19 05:44:35,549 INFO Epoch:35 val_res:0.742667 +2025-04-19 05:44:35,549 INFO Saving best model at Epoch 35 +2025-04-19 05:45:09,547 INFO Epoch:36 train_loss:0.05491 +2025-04-19 05:45:14,367 INFO Epoch:36 val_res:0.727333 +2025-04-19 05:45:46,181 INFO Epoch:37 train_loss:0.05256 +2025-04-19 05:45:51,116 INFO Epoch:37 val_res:0.738667 +2025-04-19 05:46:24,245 INFO Epoch:38 train_loss:0.05053 +2025-04-19 05:46:29,335 INFO Epoch:38 val_res:0.732667 +2025-04-19 05:47:02,112 INFO Epoch:39 train_loss:0.04829 +2025-04-19 05:47:07,490 INFO Epoch:39 val_res:0.741333 +2025-04-19 05:47:40,259 INFO Epoch:40 train_loss:0.04527 +2025-04-19 05:47:45,483 INFO Epoch:40 val_res:0.738667 +2025-04-19 05:48:17,759 INFO Epoch:41 train_loss:0.04853 +2025-04-19 05:48:22,700 INFO Epoch:41 val_res:0.734667 +2025-04-19 05:48:55,050 INFO Epoch:42 train_loss:0.04635 +2025-04-19 05:49:00,022 INFO Epoch:42 val_res:0.735333 +2025-04-19 05:49:31,819 INFO Epoch:43 train_loss:0.04651 +2025-04-19 05:49:36,673 INFO Epoch:43 val_res:0.740667 +2025-04-19 05:50:08,628 INFO Epoch:44 train_loss:0.04849 +2025-04-19 05:50:13,359 INFO Epoch:44 val_res:0.736000 +2025-04-19 05:50:44,448 INFO Epoch:45 train_loss:0.05886 +2025-04-19 05:50:49,026 INFO Epoch:45 val_res:0.736000 +2025-04-19 05:51:22,090 INFO Epoch:46 train_loss:0.05904 +2025-04-19 05:51:26,908 INFO Epoch:46 val_res:0.738667 +2025-04-19 05:52:00,202 INFO Epoch:47 train_loss:0.08452 +2025-04-19 05:52:05,209 INFO Epoch:47 val_res:0.742000 +2025-04-19 05:52:38,278 INFO Epoch:48 train_loss:0.07430 +2025-04-19 05:52:43,227 INFO Epoch:48 val_res:0.742667 +2025-04-19 05:53:15,595 INFO Epoch:49 train_loss:0.05962 +2025-04-19 05:53:20,422 INFO Epoch:49 val_res:0.742000 +2025-04-19 05:53:53,203 INFO Epoch:50 train_loss:0.05220 +2025-04-19 05:53:58,154 INFO Epoch:50 val_res:0.744667 +2025-04-19 05:53:58,154 INFO Saving best model at Epoch 50 +2025-04-19 05:54:31,513 INFO Epoch:51 train_loss:0.04973 +2025-04-19 05:54:36,330 INFO Epoch:51 val_res:0.733333 +2025-04-19 05:55:07,602 INFO Epoch:52 train_loss:0.05689 +2025-04-19 05:55:12,571 INFO Epoch:52 val_res:0.742000 +2025-04-19 05:55:44,035 INFO Epoch:53 train_loss:0.07528 +2025-04-19 05:55:48,933 INFO Epoch:53 val_res:0.731333 +2025-04-19 05:56:20,852 INFO Epoch:54 train_loss:0.19806 +2025-04-19 05:56:25,818 INFO Epoch:54 val_res:0.737333 +2025-04-19 05:56:57,325 INFO Epoch:55 train_loss:0.15074 +2025-04-19 05:57:02,256 INFO Epoch:55 val_res:0.731333 +2025-04-19 05:57:33,942 INFO Epoch:56 train_loss:0.12737 +2025-04-19 05:57:38,794 INFO Epoch:56 val_res:0.743333 +2025-04-19 05:58:11,502 INFO Epoch:57 train_loss:0.07477 +2025-04-19 05:58:16,822 INFO Epoch:57 val_res:0.745333 +2025-04-19 05:58:16,822 INFO Saving best model at Epoch 57 +2025-04-19 05:58:51,902 INFO Epoch:58 train_loss:0.05688 +2025-04-19 05:58:56,954 INFO Epoch:58 val_res:0.750667 +2025-04-19 05:58:56,954 INFO Saving best model at Epoch 58 +2025-04-19 05:59:31,306 INFO Epoch:59 train_loss:0.05880 +2025-04-19 05:59:36,172 INFO Epoch:59 val_res:0.738000 +2025-04-19 06:00:09,687 INFO Epoch:60 train_loss:0.04071 +2025-04-19 06:00:14,414 INFO Epoch:60 val_res:0.740000 +2025-04-19 06:00:47,526 INFO Epoch:61 train_loss:0.03701 +2025-04-19 06:00:53,021 INFO Epoch:61 val_res:0.755333 +2025-04-19 06:00:53,022 INFO Saving best model at Epoch 61 +2025-04-19 06:01:27,962 INFO Epoch:62 train_loss:0.03720 +2025-04-19 06:01:32,895 INFO Epoch:62 val_res:0.747333 +2025-04-19 06:02:05,808 INFO Epoch:63 train_loss:0.03372 +2025-04-19 06:02:10,971 INFO Epoch:63 val_res:0.740000 +2025-04-19 06:02:44,947 INFO Epoch:64 train_loss:0.03298 +2025-04-19 06:02:50,653 INFO Epoch:64 val_res:0.744000 +2025-04-19 06:03:23,914 INFO Epoch:65 train_loss:0.03123 +2025-04-19 06:03:29,519 INFO Epoch:65 val_res:0.747333 +2025-04-19 06:04:03,154 INFO Epoch:66 train_loss:0.03957 +2025-04-19 06:04:08,597 INFO Epoch:66 val_res:0.744000 +2025-04-19 06:04:41,840 INFO Epoch:67 train_loss:0.07296 +2025-04-19 06:04:46,941 INFO Epoch:67 val_res:0.753333 +2025-04-19 06:05:20,273 INFO Epoch:68 train_loss:0.08493 +2025-04-19 06:05:25,745 INFO Epoch:68 val_res:0.745333 +2025-04-19 06:06:00,551 INFO Epoch:69 train_loss:0.06776 +2025-04-19 06:06:06,022 INFO Epoch:69 val_res:0.748667 +2025-04-19 06:06:40,154 INFO Epoch:70 train_loss:0.04727 +2025-04-19 06:06:45,234 INFO Epoch:70 val_res:0.746667 +2025-04-19 06:07:19,162 INFO Epoch:71 train_loss:0.04276 +2025-04-19 06:07:24,302 INFO Epoch:71 val_res:0.755333 +2025-04-19 06:07:57,661 INFO Epoch:72 train_loss:0.03763 +2025-04-19 06:08:02,479 INFO Epoch:72 val_res:0.744667 +2025-04-19 06:08:35,960 INFO Epoch:73 train_loss:0.03734 +2025-04-19 06:08:40,725 INFO Epoch:73 val_res:0.746000 +2025-04-19 06:09:13,127 INFO Epoch:74 train_loss:0.03852 +2025-04-19 06:09:17,872 INFO Epoch:74 val_res:0.749333 +2025-04-19 06:09:50,094 INFO Epoch:75 train_loss:0.03480 +2025-04-19 06:09:54,986 INFO Epoch:75 val_res:0.751333 +2025-04-19 06:10:27,224 INFO Epoch:76 train_loss:0.03405 +2025-04-19 06:10:32,595 INFO Epoch:76 val_res:0.747333 +2025-04-19 06:11:05,835 INFO Epoch:77 train_loss:0.03002 +2025-04-19 06:11:11,198 INFO Epoch:77 val_res:0.750000 +2025-04-19 06:11:43,603 INFO Epoch:78 train_loss:0.03708 +2025-04-19 06:11:48,649 INFO Epoch:78 val_res:0.751333 +2025-04-19 06:12:22,306 INFO Epoch:79 train_loss:0.04380 +2025-04-19 06:12:27,349 INFO Epoch:79 val_res:0.746667 +2025-04-19 06:13:01,046 INFO Epoch:80 train_loss:0.05655 +2025-04-19 06:13:06,376 INFO Epoch:80 val_res:0.737333 +2025-04-19 06:13:39,257 INFO Epoch:81 train_loss:0.06678 +2025-04-19 06:13:44,345 INFO Epoch:81 val_res:0.752000 +2025-04-19 06:14:17,179 INFO Epoch:82 train_loss:0.04889 +2025-04-19 06:14:22,348 INFO Epoch:82 val_res:0.746667 +2025-04-19 06:14:54,987 INFO Epoch:83 train_loss:0.04329 +2025-04-19 06:15:00,107 INFO Epoch:83 val_res:0.741333 +2025-04-19 06:15:34,417 INFO Epoch:84 train_loss:0.03676 +2025-04-19 06:15:39,607 INFO Epoch:84 val_res:0.744000 +2025-04-19 06:16:13,148 INFO Epoch:85 train_loss:0.03653 +2025-04-19 06:16:18,261 INFO Epoch:85 val_res:0.748667 +2025-04-19 06:16:50,460 INFO Epoch:86 train_loss:0.04816 +2025-04-19 06:16:55,691 INFO Epoch:86 val_res:0.748667 +2025-04-19 06:17:28,634 INFO Epoch:87 train_loss:0.05906 +2025-04-19 06:17:33,628 INFO Epoch:87 val_res:0.749333 +2025-04-19 06:18:07,185 INFO Epoch:88 train_loss:0.04807 +2025-04-19 06:18:12,259 INFO Epoch:88 val_res:0.744667 +2025-04-19 06:18:44,950 INFO Epoch:89 train_loss:0.03959 +2025-04-19 06:18:49,977 INFO Epoch:89 val_res:0.748667 +2025-04-19 06:19:22,900 INFO Epoch:90 train_loss:0.04085 +2025-04-19 06:19:28,400 INFO Epoch:90 val_res:0.746667 +2025-04-19 06:20:00,471 INFO Epoch:91 train_loss:0.04359 +2025-04-19 06:20:05,678 INFO Epoch:91 val_res:0.746667 +2025-04-19 06:20:38,937 INFO Epoch:92 train_loss:0.03597 +2025-04-19 06:20:44,216 INFO Epoch:92 val_res:0.754667 +2025-04-19 06:21:17,452 INFO Epoch:93 train_loss:0.04374 +2025-04-19 06:21:23,044 INFO Epoch:93 val_res:0.753333 +2025-04-19 06:21:56,529 INFO Epoch:94 train_loss:0.04723 +2025-04-19 06:22:01,404 INFO Epoch:94 val_res:0.753333 +2025-04-19 06:22:34,457 INFO Epoch:95 train_loss:0.05780 +2025-04-19 06:22:39,651 INFO Epoch:95 val_res:0.748667 +2025-04-19 06:23:13,108 INFO Epoch:96 train_loss:0.04701 +2025-04-19 06:23:17,998 INFO Epoch:96 val_res:0.750000 +2025-04-19 06:23:52,287 INFO Epoch:97 train_loss:0.04873 +2025-04-19 06:23:57,294 INFO Epoch:97 val_res:0.748667 +2025-04-19 06:24:31,169 INFO Epoch:98 train_loss:0.09282 +2025-04-19 06:24:36,255 INFO Epoch:98 val_res:0.749333 +2025-04-19 06:25:09,753 INFO Epoch:99 train_loss:0.18878 +2025-04-19 06:25:14,966 INFO Epoch:99 val_res:0.753333 +2025-04-19 06:25:15,753 INFO ===================================== +2025-04-19 06:25:15,754 INFO Start testing... +2025-04-19 06:25:15,755 INFO ===================================== +2025-04-19 06:25:21,670 INFO Incremental step 2 Testing res: 0.750000 +2025-04-19 06:25:21,671 INFO forgetting: 0.109000 +2025-04-19 06:25:21,675 INFO ***************New Step*************************** +2025-04-19 06:25:21,675 INFO Incremental step: 3 +2025-04-19 06:25:21,839 INFO actual size of exemplar set: 1500 +2025-04-19 06:25:57,839 INFO Epoch:0 train_loss:2.31424 +2025-04-19 06:26:05,444 INFO Epoch:0 val_res:0.572500 +2025-04-19 06:26:05,445 INFO Saving best model at Epoch 0 +2025-04-19 06:26:41,111 INFO Epoch:1 train_loss:0.76680 +2025-04-19 06:26:47,754 INFO Epoch:1 val_res:0.578500 +2025-04-19 06:26:47,754 INFO Saving best model at Epoch 1 +2025-04-19 06:27:26,441 INFO Epoch:2 train_loss:0.52538 +2025-04-19 06:27:33,561 INFO Epoch:2 val_res:0.584500 +2025-04-19 06:27:33,562 INFO Saving best model at Epoch 2 +2025-04-19 06:28:12,061 INFO Epoch:3 train_loss:0.44997 +2025-04-19 06:28:19,442 INFO Epoch:3 val_res:0.586500 +2025-04-19 06:28:19,442 INFO Saving best model at Epoch 3 +2025-04-19 06:28:58,537 INFO Epoch:4 train_loss:0.40985 +2025-04-19 06:29:05,399 INFO Epoch:4 val_res:0.588000 +2025-04-19 06:29:05,399 INFO Saving best model at Epoch 4 +2025-04-19 06:29:41,313 INFO Epoch:5 train_loss:0.38229 +2025-04-19 06:29:48,270 INFO Epoch:5 val_res:0.590000 +2025-04-19 06:29:48,270 INFO Saving best model at Epoch 5 +2025-04-19 06:30:25,617 INFO Epoch:6 train_loss:0.35549 +2025-04-19 06:30:32,363 INFO Epoch:6 val_res:0.590500 +2025-04-19 06:30:32,363 INFO Saving best model at Epoch 6 +2025-04-19 06:31:10,573 INFO Epoch:7 train_loss:0.33480 +2025-04-19 06:31:17,511 INFO Epoch:7 val_res:0.594500 +2025-04-19 06:31:17,512 INFO Saving best model at Epoch 7 +2025-04-19 06:31:54,082 INFO Epoch:8 train_loss:0.31689 +2025-04-19 06:32:00,689 INFO Epoch:8 val_res:0.601000 +2025-04-19 06:32:00,689 INFO Saving best model at Epoch 8 +2025-04-19 06:32:35,983 INFO Epoch:9 train_loss:0.29504 +2025-04-19 06:32:42,527 INFO Epoch:9 val_res:0.598500 +2025-04-19 06:33:15,913 INFO Epoch:10 train_loss:0.28213 +2025-04-19 06:33:22,229 INFO Epoch:10 val_res:0.602000 +2025-04-19 06:33:22,230 INFO Saving best model at Epoch 10 +2025-04-19 06:33:57,487 INFO Epoch:11 train_loss:0.26341 +2025-04-19 06:34:03,834 INFO Epoch:11 val_res:0.605500 +2025-04-19 06:34:03,835 INFO Saving best model at Epoch 11 +2025-04-19 06:34:38,793 INFO Epoch:12 train_loss:0.25340 +2025-04-19 06:34:45,424 INFO Epoch:12 val_res:0.605000 +2025-04-19 06:35:18,410 INFO Epoch:13 train_loss:0.24224 +2025-04-19 06:35:25,099 INFO Epoch:13 val_res:0.614000 +2025-04-19 06:35:25,100 INFO Saving best model at Epoch 13 +2025-04-19 06:35:59,698 INFO Epoch:14 train_loss:0.22894 +2025-04-19 06:36:06,235 INFO Epoch:14 val_res:0.613000 +2025-04-19 06:36:39,166 INFO Epoch:15 train_loss:0.21814 +2025-04-19 06:36:45,848 INFO Epoch:15 val_res:0.616500 +2025-04-19 06:36:45,848 INFO Saving best model at Epoch 15 +2025-04-19 06:37:20,294 INFO Epoch:16 train_loss:0.21031 +2025-04-19 06:37:27,081 INFO Epoch:16 val_res:0.620500 +2025-04-19 06:37:27,081 INFO Saving best model at Epoch 16 +2025-04-19 06:38:01,432 INFO Epoch:17 train_loss:0.20374 +2025-04-19 06:38:08,221 INFO Epoch:17 val_res:0.625500 +2025-04-19 06:38:08,222 INFO Saving best model at Epoch 17 +2025-04-19 06:38:42,994 INFO Epoch:18 train_loss:0.19299 +2025-04-19 06:38:49,174 INFO Epoch:18 val_res:0.630000 +2025-04-19 06:38:49,174 INFO Saving best model at Epoch 18 +2025-04-19 06:39:24,160 INFO Epoch:19 train_loss:0.18691 +2025-04-19 06:39:30,505 INFO Epoch:19 val_res:0.635500 +2025-04-19 06:39:30,506 INFO Saving best model at Epoch 19 +2025-04-19 06:40:06,065 INFO Epoch:20 train_loss:0.19751 +2025-04-19 06:40:13,153 INFO Epoch:20 val_res:0.638000 +2025-04-19 06:40:13,154 INFO Saving best model at Epoch 20 +2025-04-19 06:40:50,338 INFO Epoch:21 train_loss:0.21413 +2025-04-19 06:40:57,825 INFO Epoch:21 val_res:0.645000 +2025-04-19 06:40:57,826 INFO Saving best model at Epoch 21 +2025-04-19 06:41:36,206 INFO Epoch:22 train_loss:0.18733 +2025-04-19 06:41:43,536 INFO Epoch:22 val_res:0.647500 +2025-04-19 06:41:43,536 INFO Saving best model at Epoch 22 +2025-04-19 06:42:22,127 INFO Epoch:23 train_loss:0.17526 +2025-04-19 06:42:29,831 INFO Epoch:23 val_res:0.652500 +2025-04-19 06:42:29,831 INFO Saving best model at Epoch 23 +2025-04-19 06:43:08,133 INFO Epoch:24 train_loss:0.15595 +2025-04-19 06:43:15,416 INFO Epoch:24 val_res:0.657500 +2025-04-19 06:43:15,417 INFO Saving best model at Epoch 24 +2025-04-19 06:43:54,712 INFO Epoch:25 train_loss:0.14284 +2025-04-19 06:44:02,251 INFO Epoch:25 val_res:0.659000 +2025-04-19 06:44:02,252 INFO Saving best model at Epoch 25 +2025-04-19 06:44:40,609 INFO Epoch:26 train_loss:0.14125 +2025-04-19 06:44:48,245 INFO Epoch:26 val_res:0.664500 +2025-04-19 06:44:48,246 INFO Saving best model at Epoch 26 +2025-04-19 06:45:26,166 INFO Epoch:27 train_loss:0.13264 +2025-04-19 06:45:33,363 INFO Epoch:27 val_res:0.674500 +2025-04-19 06:45:33,364 INFO Saving best model at Epoch 27 +2025-04-19 06:46:11,890 INFO Epoch:28 train_loss:0.13405 +2025-04-19 06:46:18,798 INFO Epoch:28 val_res:0.677000 +2025-04-19 06:46:18,798 INFO Saving best model at Epoch 28 +2025-04-19 06:46:57,291 INFO Epoch:29 train_loss:0.12899 +2025-04-19 06:47:05,249 INFO Epoch:29 val_res:0.678000 +2025-04-19 06:47:05,250 INFO Saving best model at Epoch 29 +2025-04-19 06:47:45,901 INFO Epoch:30 train_loss:0.12292 +2025-04-19 06:47:53,410 INFO Epoch:30 val_res:0.677000 +2025-04-19 06:48:30,230 INFO Epoch:31 train_loss:0.10622 +2025-04-19 06:48:37,110 INFO Epoch:31 val_res:0.678500 +2025-04-19 06:48:37,110 INFO Saving best model at Epoch 31 +2025-04-19 06:49:16,446 INFO Epoch:32 train_loss:0.09798 +2025-04-19 06:49:24,521 INFO Epoch:32 val_res:0.684000 +2025-04-19 06:49:24,521 INFO Saving best model at Epoch 32 +2025-04-19 06:50:03,678 INFO Epoch:33 train_loss:0.09454 +2025-04-19 06:50:10,784 INFO Epoch:33 val_res:0.690500 +2025-04-19 06:50:10,785 INFO Saving best model at Epoch 33 +2025-04-19 06:50:48,596 INFO Epoch:34 train_loss:0.10241 +2025-04-19 06:50:55,170 INFO Epoch:34 val_res:0.684500 +2025-04-19 06:51:28,857 INFO Epoch:35 train_loss:0.19809 +2025-04-19 06:51:36,168 INFO Epoch:35 val_res:0.684500 +2025-04-19 06:52:10,697 INFO Epoch:36 train_loss:0.40353 +2025-04-19 06:52:17,304 INFO Epoch:36 val_res:0.691500 +2025-04-19 06:52:17,304 INFO Saving best model at Epoch 36 +2025-04-19 06:52:54,410 INFO Epoch:37 train_loss:0.30131 +2025-04-19 06:53:01,430 INFO Epoch:37 val_res:0.675000 +2025-04-19 06:53:36,248 INFO Epoch:38 train_loss:0.14849 +2025-04-19 06:53:43,490 INFO Epoch:38 val_res:0.694000 +2025-04-19 06:53:43,491 INFO Saving best model at Epoch 38 +2025-04-19 06:54:20,324 INFO Epoch:39 train_loss:0.09159 +2025-04-19 06:54:27,984 INFO Epoch:39 val_res:0.692000 +2025-04-19 06:55:03,670 INFO Epoch:40 train_loss:0.08067 +2025-04-19 06:55:11,317 INFO Epoch:40 val_res:0.687500 +2025-04-19 06:55:45,035 INFO Epoch:41 train_loss:0.07628 +2025-04-19 06:55:52,567 INFO Epoch:41 val_res:0.692000 +2025-04-19 06:56:28,785 INFO Epoch:42 train_loss:0.06997 +2025-04-19 06:56:36,497 INFO Epoch:42 val_res:0.697000 +2025-04-19 06:56:36,497 INFO Saving best model at Epoch 42 +2025-04-19 06:57:13,528 INFO Epoch:43 train_loss:0.07028 +2025-04-19 06:57:21,155 INFO Epoch:43 val_res:0.702000 +2025-04-19 06:57:21,155 INFO Saving best model at Epoch 43 +2025-04-19 06:57:58,654 INFO Epoch:44 train_loss:0.06599 +2025-04-19 06:58:06,037 INFO Epoch:44 val_res:0.702000 +2025-04-19 06:58:41,774 INFO Epoch:45 train_loss:0.06126 +2025-04-19 06:58:49,078 INFO Epoch:45 val_res:0.691500 +2025-04-19 06:59:24,857 INFO Epoch:46 train_loss:0.06062 +2025-04-19 06:59:32,197 INFO Epoch:46 val_res:0.700000 +2025-04-19 07:00:06,913 INFO Epoch:47 train_loss:0.06313 +2025-04-19 07:00:14,258 INFO Epoch:47 val_res:0.693500 +2025-04-19 07:00:50,324 INFO Epoch:48 train_loss:0.06193 +2025-04-19 07:00:58,060 INFO Epoch:48 val_res:0.695500 +2025-04-19 07:01:33,565 INFO Epoch:49 train_loss:0.05695 +2025-04-19 07:01:40,929 INFO Epoch:49 val_res:0.691000 +2025-04-19 07:02:18,831 INFO Epoch:50 train_loss:0.05642 +2025-04-19 07:02:26,631 INFO Epoch:50 val_res:0.701000 +2025-04-19 07:03:02,285 INFO Epoch:51 train_loss:0.05772 +2025-04-19 07:03:09,678 INFO Epoch:51 val_res:0.693000 +2025-04-19 07:03:44,655 INFO Epoch:52 train_loss:0.05824 +2025-04-19 07:03:52,122 INFO Epoch:52 val_res:0.688000 +2025-04-19 07:04:28,573 INFO Epoch:53 train_loss:0.06845 +2025-04-19 07:04:35,641 INFO Epoch:53 val_res:0.697000 +2025-04-19 07:05:11,611 INFO Epoch:54 train_loss:0.05814 +2025-04-19 07:05:18,218 INFO Epoch:54 val_res:0.686500 +2025-04-19 07:05:55,378 INFO Epoch:55 train_loss:0.05816 +2025-04-19 07:06:02,523 INFO Epoch:55 val_res:0.709000 +2025-04-19 07:06:02,524 INFO Saving best model at Epoch 55 +2025-04-19 07:06:40,481 INFO Epoch:56 train_loss:0.06432 +2025-04-19 07:06:47,498 INFO Epoch:56 val_res:0.700000 +2025-04-19 07:07:23,696 INFO Epoch:57 train_loss:0.09128 +2025-04-19 07:07:31,316 INFO Epoch:57 val_res:0.695000 +2025-04-19 07:08:07,707 INFO Epoch:58 train_loss:0.08628 +2025-04-19 07:08:15,129 INFO Epoch:58 val_res:0.700000 +2025-04-19 07:08:52,672 INFO Epoch:59 train_loss:0.06364 +2025-04-19 07:09:00,099 INFO Epoch:59 val_res:0.695500 +2025-04-19 07:09:37,300 INFO Epoch:60 train_loss:0.07116 +2025-04-19 07:09:44,960 INFO Epoch:60 val_res:0.708000 +2025-04-19 07:10:22,121 INFO Epoch:61 train_loss:0.06332 +2025-04-19 07:10:29,701 INFO Epoch:61 val_res:0.695500 +2025-04-19 07:11:06,582 INFO Epoch:62 train_loss:0.08957 +2025-04-19 07:11:15,176 INFO Epoch:62 val_res:0.695500 +2025-04-19 07:11:51,311 INFO Epoch:63 train_loss:0.09110 +2025-04-19 07:11:58,811 INFO Epoch:63 val_res:0.694000 +2025-04-19 07:12:36,997 INFO Epoch:64 train_loss:0.06287 +2025-04-19 07:12:44,237 INFO Epoch:64 val_res:0.700500 +2025-04-19 07:13:21,346 INFO Epoch:65 train_loss:0.05501 +2025-04-19 07:13:28,891 INFO Epoch:65 val_res:0.702000 +2025-04-19 07:14:06,884 INFO Epoch:66 train_loss:0.04908 +2025-04-19 07:14:14,387 INFO Epoch:66 val_res:0.692000 +2025-04-19 07:14:50,895 INFO Epoch:67 train_loss:0.06008 +2025-04-19 07:14:58,674 INFO Epoch:67 val_res:0.699000 +2025-04-19 07:15:35,133 INFO Epoch:68 train_loss:0.08446 +2025-04-19 07:15:42,417 INFO Epoch:68 val_res:0.690000 +2025-04-19 07:16:18,277 INFO Epoch:69 train_loss:0.10759 +2025-04-19 07:16:24,955 INFO Epoch:69 val_res:0.706000 +2025-04-19 07:17:00,942 INFO Epoch:70 train_loss:0.09301 +2025-04-19 07:17:07,481 INFO Epoch:70 val_res:0.692500 +2025-04-19 07:17:44,126 INFO Epoch:71 train_loss:0.09511 +2025-04-19 07:17:51,410 INFO Epoch:71 val_res:0.694500 +2025-04-19 07:18:27,140 INFO Epoch:72 train_loss:0.09275 +2025-04-19 07:18:34,392 INFO Epoch:72 val_res:0.700500 +2025-04-19 07:19:10,732 INFO Epoch:73 train_loss:0.07141 +2025-04-19 07:19:18,707 INFO Epoch:73 val_res:0.689500 +2025-04-19 07:19:55,860 INFO Epoch:74 train_loss:0.05563 +2025-04-19 07:20:03,139 INFO Epoch:74 val_res:0.697000 +2025-04-19 07:20:39,687 INFO Epoch:75 train_loss:0.05145 +2025-04-19 07:20:47,064 INFO Epoch:75 val_res:0.694500 +2025-04-19 07:21:22,160 INFO Epoch:76 train_loss:0.05176 +2025-04-19 07:21:29,444 INFO Epoch:76 val_res:0.693500 +2025-04-19 07:22:05,599 INFO Epoch:77 train_loss:0.05860 +2025-04-19 07:22:11,967 INFO Epoch:77 val_res:0.695000 +2025-04-19 07:22:44,023 INFO Epoch:78 train_loss:0.07595 +2025-04-19 07:22:50,574 INFO Epoch:78 val_res:0.697500 +2025-04-19 07:23:24,354 INFO Epoch:79 train_loss:0.06542 +2025-04-19 07:23:31,166 INFO Epoch:79 val_res:0.700000 +2025-04-19 07:24:04,203 INFO Epoch:80 train_loss:0.08064 +2025-04-19 07:24:11,309 INFO Epoch:80 val_res:0.697000 +2025-04-19 07:24:44,660 INFO Epoch:81 train_loss:0.08705 +2025-04-19 07:24:51,513 INFO Epoch:81 val_res:0.689000 +2025-04-19 07:25:25,711 INFO Epoch:82 train_loss:0.09581 +2025-04-19 07:25:32,270 INFO Epoch:82 val_res:0.693500 +2025-04-19 07:26:08,460 INFO Epoch:83 train_loss:0.06476 +2025-04-19 07:26:15,957 INFO Epoch:83 val_res:0.691000 +2025-04-19 07:26:53,501 INFO Epoch:84 train_loss:0.05437 +2025-04-19 07:27:01,020 INFO Epoch:84 val_res:0.699000 +2025-04-19 07:27:38,007 INFO Epoch:85 train_loss:0.05619 +2025-04-19 07:27:45,450 INFO Epoch:85 val_res:0.695500 +2025-04-19 07:28:23,675 INFO Epoch:86 train_loss:0.04984 +2025-04-19 07:28:31,190 INFO Epoch:86 val_res:0.704500 +2025-04-19 07:29:10,816 INFO Epoch:87 train_loss:0.05581 +2025-04-19 07:29:18,053 INFO Epoch:87 val_res:0.693500 +2025-04-19 07:29:56,599 INFO Epoch:88 train_loss:0.05253 +2025-04-19 07:30:04,398 INFO Epoch:88 val_res:0.695500 +2025-04-19 07:30:42,460 INFO Epoch:89 train_loss:0.06152 +2025-04-19 07:30:50,544 INFO Epoch:89 val_res:0.694500 +2025-04-19 07:31:29,034 INFO Epoch:90 train_loss:0.07872 +2025-04-19 07:31:37,138 INFO Epoch:90 val_res:0.695500 +2025-04-19 07:32:16,467 INFO Epoch:91 train_loss:0.06652 +2025-04-19 07:32:24,121 INFO Epoch:91 val_res:0.696500 +2025-04-19 07:33:02,864 INFO Epoch:92 train_loss:0.08438 +2025-04-19 07:33:10,023 INFO Epoch:92 val_res:0.705500 +2025-04-19 07:33:49,186 INFO Epoch:93 train_loss:0.06712 +2025-04-19 07:33:57,458 INFO Epoch:93 val_res:0.690500 +2025-04-19 07:34:34,409 INFO Epoch:94 train_loss:0.05803 +2025-04-19 07:34:41,770 INFO Epoch:94 val_res:0.694000 +2025-04-19 07:35:20,022 INFO Epoch:95 train_loss:0.05938 +2025-04-19 07:35:27,776 INFO Epoch:95 val_res:0.692500 +2025-04-19 07:36:04,847 INFO Epoch:96 train_loss:0.05570 +2025-04-19 07:36:12,166 INFO Epoch:96 val_res:0.690500 +2025-04-19 07:36:49,288 INFO Epoch:97 train_loss:0.04678 +2025-04-19 07:36:57,027 INFO Epoch:97 val_res:0.693500 +2025-04-19 07:37:33,000 INFO Epoch:98 train_loss:0.04093 +2025-04-19 07:37:39,188 INFO Epoch:98 val_res:0.690500 +2025-04-19 07:38:14,864 INFO Epoch:99 train_loss:0.04245 +2025-04-19 07:38:22,539 INFO Epoch:99 val_res:0.690500 +2025-04-19 07:38:23,362 INFO ===================================== +2025-04-19 07:38:23,363 INFO Start testing... +2025-04-19 07:38:23,363 INFO ===================================== +2025-04-19 07:38:31,408 INFO Incremental step 3 Testing res: 0.704000 +2025-04-19 07:38:31,410 INFO forgetting: 0.070667 +2025-04-19 07:38:31,422 INFO ***************New Step*************************** +2025-04-19 07:38:31,423 INFO Incremental step: 4 +2025-04-19 07:38:31,602 INFO actual size of exemplar set: 1480 +2025-04-19 07:39:10,075 INFO Epoch:0 train_loss:3.30208 +2025-04-19 07:39:19,950 INFO Epoch:0 val_res:0.560400 +2025-04-19 07:39:19,952 INFO Saving best model at Epoch 0 +2025-04-19 07:39:59,768 INFO Epoch:1 train_loss:0.96480 +2025-04-19 07:40:08,486 INFO Epoch:1 val_res:0.577200 +2025-04-19 07:40:08,486 INFO Saving best model at Epoch 1 +2025-04-19 07:40:47,251 INFO Epoch:2 train_loss:0.56584 +2025-04-19 07:40:56,303 INFO Epoch:2 val_res:0.578400 +2025-04-19 07:40:56,304 INFO Saving best model at Epoch 2 +2025-04-19 07:41:34,318 INFO Epoch:3 train_loss:0.44787 +2025-04-19 07:41:43,173 INFO Epoch:3 val_res:0.579600 +2025-04-19 07:41:43,173 INFO Saving best model at Epoch 3 +2025-04-19 07:42:22,691 INFO Epoch:4 train_loss:0.39784 +2025-04-19 07:42:33,017 INFO Epoch:4 val_res:0.582800 +2025-04-19 07:42:33,017 INFO Saving best model at Epoch 4 +2025-04-19 07:43:13,097 INFO Epoch:5 train_loss:0.36404 +2025-04-19 07:43:22,960 INFO Epoch:5 val_res:0.579200 +2025-04-19 07:44:01,045 INFO Epoch:6 train_loss:0.33772 +2025-04-19 07:44:11,165 INFO Epoch:6 val_res:0.580000 +2025-04-19 07:44:49,253 INFO Epoch:7 train_loss:0.31632 +2025-04-19 07:44:58,623 INFO Epoch:7 val_res:0.585200 +2025-04-19 07:44:58,624 INFO Saving best model at Epoch 7 +2025-04-19 07:45:38,107 INFO Epoch:8 train_loss:0.29382 +2025-04-19 07:45:46,690 INFO Epoch:8 val_res:0.586400 +2025-04-19 07:45:46,691 INFO Saving best model at Epoch 8 +2025-04-19 07:46:24,949 INFO Epoch:9 train_loss:0.27389 +2025-04-19 07:46:33,394 INFO Epoch:9 val_res:0.592800 +2025-04-19 07:46:33,395 INFO Saving best model at Epoch 9 +2025-04-19 07:47:07,921 INFO Epoch:10 train_loss:0.26291 +2025-04-19 07:47:16,348 INFO Epoch:10 val_res:0.592800 +2025-04-19 07:47:48,279 INFO Epoch:11 train_loss:0.24780 +2025-04-19 07:47:55,813 INFO Epoch:11 val_res:0.594800 +2025-04-19 07:47:55,813 INFO Saving best model at Epoch 11 +2025-04-19 07:48:29,677 INFO Epoch:12 train_loss:0.24207 +2025-04-19 07:48:37,417 INFO Epoch:12 val_res:0.594400 +2025-04-19 07:49:09,916 INFO Epoch:13 train_loss:0.26710 +2025-04-19 07:49:17,608 INFO Epoch:13 val_res:0.594400 +2025-04-19 07:49:49,106 INFO Epoch:14 train_loss:0.25356 +2025-04-19 07:49:57,225 INFO Epoch:14 val_res:0.598000 +2025-04-19 07:49:57,226 INFO Saving best model at Epoch 14 +2025-04-19 07:50:31,867 INFO Epoch:15 train_loss:0.24924 +2025-04-19 07:50:39,695 INFO Epoch:15 val_res:0.596400 +2025-04-19 07:51:12,564 INFO Epoch:16 train_loss:0.25957 +2025-04-19 07:51:20,718 INFO Epoch:16 val_res:0.600400 +2025-04-19 07:51:20,718 INFO Saving best model at Epoch 16 +2025-04-19 07:51:54,662 INFO Epoch:17 train_loss:0.21281 +2025-04-19 07:52:02,767 INFO Epoch:17 val_res:0.605600 +2025-04-19 07:52:02,768 INFO Saving best model at Epoch 17 +2025-04-19 07:52:36,546 INFO Epoch:18 train_loss:0.20128 +2025-04-19 07:52:44,523 INFO Epoch:18 val_res:0.608000 +2025-04-19 07:52:44,523 INFO Saving best model at Epoch 18 +2025-04-19 07:53:18,370 INFO Epoch:19 train_loss:0.18100 +2025-04-19 07:53:26,439 INFO Epoch:19 val_res:0.608400 +2025-04-19 07:53:26,440 INFO Saving best model at Epoch 19 +2025-04-19 07:53:59,365 INFO Epoch:20 train_loss:0.17067 +2025-04-19 07:54:07,544 INFO Epoch:20 val_res:0.612000 +2025-04-19 07:54:07,545 INFO Saving best model at Epoch 20 +2025-04-19 07:54:40,829 INFO Epoch:21 train_loss:0.16132 +2025-04-19 07:54:48,899 INFO Epoch:21 val_res:0.612400 +2025-04-19 07:54:48,899 INFO Saving best model at Epoch 21 +2025-04-19 07:55:22,519 INFO Epoch:22 train_loss:0.16215 +2025-04-19 07:55:30,603 INFO Epoch:22 val_res:0.614400 +2025-04-19 07:55:30,603 INFO Saving best model at Epoch 22 +2025-04-19 07:56:04,473 INFO Epoch:23 train_loss:0.16455 +2025-04-19 07:56:12,725 INFO Epoch:23 val_res:0.618800 +2025-04-19 07:56:12,726 INFO Saving best model at Epoch 23 +2025-04-19 07:56:46,733 INFO Epoch:24 train_loss:0.17666 +2025-04-19 07:56:54,644 INFO Epoch:24 val_res:0.616400 +2025-04-19 07:57:27,410 INFO Epoch:25 train_loss:0.16754 +2025-04-19 07:57:35,021 INFO Epoch:25 val_res:0.620800 +2025-04-19 07:57:35,021 INFO Saving best model at Epoch 25 +2025-04-19 07:58:08,740 INFO Epoch:26 train_loss:0.15641 +2025-04-19 07:58:16,540 INFO Epoch:26 val_res:0.624000 +2025-04-19 07:58:16,541 INFO Saving best model at Epoch 26 +2025-04-19 07:58:51,002 INFO Epoch:27 train_loss:0.14829 +2025-04-19 07:58:59,111 INFO Epoch:27 val_res:0.626800 +2025-04-19 07:58:59,112 INFO Saving best model at Epoch 27 +2025-04-19 07:59:33,318 INFO Epoch:28 train_loss:0.14402 +2025-04-19 07:59:41,496 INFO Epoch:28 val_res:0.628000 +2025-04-19 07:59:41,497 INFO Saving best model at Epoch 28 +2025-04-19 08:00:15,702 INFO Epoch:29 train_loss:0.15816 +2025-04-19 08:00:23,348 INFO Epoch:29 val_res:0.627600 +2025-04-19 08:00:54,580 INFO Epoch:30 train_loss:0.15339 +2025-04-19 08:01:02,452 INFO Epoch:30 val_res:0.631200 +2025-04-19 08:01:02,453 INFO Saving best model at Epoch 30 +2025-04-19 08:01:36,338 INFO Epoch:31 train_loss:0.13454 +2025-04-19 08:01:43,885 INFO Epoch:31 val_res:0.632000 +2025-04-19 08:01:43,885 INFO Saving best model at Epoch 31 +2025-04-19 08:02:17,681 INFO Epoch:32 train_loss:0.13243 +2025-04-19 08:02:25,434 INFO Epoch:32 val_res:0.632400 +2025-04-19 08:02:25,434 INFO Saving best model at Epoch 32 +2025-04-19 08:02:59,511 INFO Epoch:33 train_loss:0.13184 +2025-04-19 08:03:07,284 INFO Epoch:33 val_res:0.633600 +2025-04-19 08:03:07,285 INFO Saving best model at Epoch 33 +2025-04-19 08:03:43,633 INFO Epoch:34 train_loss:0.12132 +2025-04-19 08:03:51,537 INFO Epoch:34 val_res:0.637200 +2025-04-19 08:03:51,538 INFO Saving best model at Epoch 34 +2025-04-19 08:04:27,984 INFO Epoch:35 train_loss:0.12904 +2025-04-19 08:04:35,689 INFO Epoch:35 val_res:0.635600 +2025-04-19 08:05:08,083 INFO Epoch:36 train_loss:0.13256 +2025-04-19 08:05:16,009 INFO Epoch:36 val_res:0.639200 +2025-04-19 08:05:16,010 INFO Saving best model at Epoch 36 +2025-04-19 08:05:51,199 INFO Epoch:37 train_loss:0.11371 +2025-04-19 08:05:59,144 INFO Epoch:37 val_res:0.638400 +2025-04-19 08:06:32,251 INFO Epoch:38 train_loss:0.12436 +2025-04-19 08:06:40,343 INFO Epoch:38 val_res:0.647200 +2025-04-19 08:06:40,343 INFO Saving best model at Epoch 38 +2025-04-19 08:07:13,899 INFO Epoch:39 train_loss:0.10944 +2025-04-19 08:07:21,381 INFO Epoch:39 val_res:0.640800 +2025-04-19 08:07:53,671 INFO Epoch:40 train_loss:0.11628 +2025-04-19 08:08:01,220 INFO Epoch:40 val_res:0.640400 +2025-04-19 08:08:33,043 INFO Epoch:41 train_loss:0.10954 +2025-04-19 08:08:40,561 INFO Epoch:41 val_res:0.643600 +2025-04-19 08:09:12,201 INFO Epoch:42 train_loss:0.10448 +2025-04-19 08:09:19,759 INFO Epoch:42 val_res:0.643200 +2025-04-19 08:09:51,267 INFO Epoch:43 train_loss:0.10001 +2025-04-19 08:09:58,919 INFO Epoch:43 val_res:0.646400 +2025-04-19 08:10:30,852 INFO Epoch:44 train_loss:0.11233 +2025-04-19 08:10:38,495 INFO Epoch:44 val_res:0.651600 +2025-04-19 08:10:38,496 INFO Saving best model at Epoch 44 +2025-04-19 08:11:12,836 INFO Epoch:45 train_loss:0.16007 +2025-04-19 08:11:20,856 INFO Epoch:45 val_res:0.650400 +2025-04-19 08:11:54,414 INFO Epoch:46 train_loss:0.14784 +2025-04-19 08:12:02,368 INFO Epoch:46 val_res:0.644800 +2025-04-19 08:12:33,428 INFO Epoch:47 train_loss:0.11731 +2025-04-19 08:12:41,291 INFO Epoch:47 val_res:0.654800 +2025-04-19 08:12:41,291 INFO Saving best model at Epoch 47 +2025-04-19 08:13:14,664 INFO Epoch:48 train_loss:0.11480 +2025-04-19 08:13:22,674 INFO Epoch:48 val_res:0.646800 +2025-04-19 08:14:58,890 INFO Epoch:49 train_loss:0.09597 +2025-04-19 08:15:07,182 INFO Epoch:49 val_res:0.648400 +2025-04-19 08:15:41,653 INFO Epoch:50 train_loss:0.08972 +2025-04-19 08:15:50,095 INFO Epoch:50 val_res:0.645200 +2025-04-19 08:16:24,968 INFO Epoch:51 train_loss:0.08621 +2025-04-19 08:16:33,803 INFO Epoch:51 val_res:0.651200 +2025-04-19 08:17:09,295 INFO Epoch:52 train_loss:0.07934 +2025-04-19 08:17:18,239 INFO Epoch:52 val_res:0.650400 +2025-04-19 08:17:53,180 INFO Epoch:53 train_loss:0.07864 +2025-04-19 08:18:01,890 INFO Epoch:53 val_res:0.652000 +2025-04-19 08:18:37,613 INFO Epoch:54 train_loss:0.13264 +2025-04-19 08:18:46,899 INFO Epoch:54 val_res:0.653600 +2025-04-19 08:19:22,037 INFO Epoch:55 train_loss:0.16876 +2025-04-19 08:19:30,441 INFO Epoch:55 val_res:0.652800 +2025-04-19 08:20:05,262 INFO Epoch:56 train_loss:0.12605 +2025-04-19 08:20:14,097 INFO Epoch:56 val_res:0.652000 +2025-04-19 08:20:49,372 INFO Epoch:57 train_loss:0.10146 +2025-04-19 08:20:58,089 INFO Epoch:57 val_res:0.650000 +2025-04-19 08:21:33,224 INFO Epoch:58 train_loss:0.09721 +2025-04-19 08:21:41,954 INFO Epoch:58 val_res:0.651200 +2025-04-19 08:22:16,313 INFO Epoch:59 train_loss:0.08161 +2025-04-19 08:22:25,363 INFO Epoch:59 val_res:0.657600 +2025-04-19 08:22:25,364 INFO Saving best model at Epoch 59 +2025-04-19 08:23:02,383 INFO Epoch:60 train_loss:0.08504 +2025-04-19 08:23:11,769 INFO Epoch:60 val_res:0.650000 +2025-04-19 08:23:46,092 INFO Epoch:61 train_loss:0.08136 +2025-04-19 08:23:54,907 INFO Epoch:61 val_res:0.652000 +2025-04-19 08:24:29,055 INFO Epoch:62 train_loss:0.07353 +2025-04-19 08:24:38,365 INFO Epoch:62 val_res:0.656000 +2025-04-19 08:25:11,860 INFO Epoch:63 train_loss:0.06686 +2025-04-19 08:25:20,103 INFO Epoch:63 val_res:0.655200 +2025-04-19 08:25:52,545 INFO Epoch:64 train_loss:0.07737 +2025-04-19 08:26:01,088 INFO Epoch:64 val_res:0.653600 +2025-04-19 08:26:33,470 INFO Epoch:65 train_loss:0.10354 +2025-04-19 08:26:41,211 INFO Epoch:65 val_res:0.648400 +2025-04-19 08:27:15,491 INFO Epoch:66 train_loss:0.17334 +2025-04-19 08:27:24,445 INFO Epoch:66 val_res:0.638800 +2025-04-19 08:27:57,989 INFO Epoch:67 train_loss:0.14672 +2025-04-19 08:28:06,726 INFO Epoch:67 val_res:0.655200 +2025-04-19 08:28:40,270 INFO Epoch:68 train_loss:0.09994 +2025-04-19 08:28:49,076 INFO Epoch:68 val_res:0.652000 +2025-04-19 08:29:22,620 INFO Epoch:69 train_loss:0.09549 +2025-04-19 08:29:31,029 INFO Epoch:69 val_res:0.654400 +2025-04-19 08:30:06,297 INFO Epoch:70 train_loss:0.08299 +2025-04-19 08:30:15,005 INFO Epoch:70 val_res:0.657200 +2025-04-19 08:30:49,454 INFO Epoch:71 train_loss:0.08210 +2025-04-19 08:30:57,729 INFO Epoch:71 val_res:0.648000 +2025-04-19 08:31:32,607 INFO Epoch:72 train_loss:0.12022 +2025-04-19 08:31:40,808 INFO Epoch:72 val_res:0.650800 +2025-04-19 08:32:15,915 INFO Epoch:73 train_loss:0.13202 +2025-04-19 08:32:24,933 INFO Epoch:73 val_res:0.649200 +2025-04-19 08:33:00,080 INFO Epoch:74 train_loss:0.12571 +2025-04-19 08:33:09,016 INFO Epoch:74 val_res:0.649600 +2025-04-19 08:33:43,835 INFO Epoch:75 train_loss:0.11543 +2025-04-19 08:33:52,820 INFO Epoch:75 val_res:0.650800 +2025-04-19 08:34:27,530 INFO Epoch:76 train_loss:0.11117 +2025-04-19 08:34:37,011 INFO Epoch:76 val_res:0.647200 +2025-04-19 08:35:12,896 INFO Epoch:77 train_loss:0.08003 +2025-04-19 08:35:21,951 INFO Epoch:77 val_res:0.658000 +2025-04-19 08:35:21,952 INFO Saving best model at Epoch 77 +2025-04-19 08:35:58,149 INFO Epoch:78 train_loss:0.06573 +2025-04-19 08:36:07,085 INFO Epoch:78 val_res:0.651200 +2025-04-19 08:36:41,512 INFO Epoch:79 train_loss:0.06303 +2025-04-19 08:36:50,047 INFO Epoch:79 val_res:0.648000 +2025-04-19 08:37:25,386 INFO Epoch:80 train_loss:0.07128 +2025-04-19 08:37:34,477 INFO Epoch:80 val_res:0.654000 +2025-04-19 08:38:09,200 INFO Epoch:81 train_loss:0.09239 +2025-04-19 08:38:18,133 INFO Epoch:81 val_res:0.654000 +2025-04-19 08:38:53,778 INFO Epoch:82 train_loss:0.06857 +2025-04-19 08:39:02,764 INFO Epoch:82 val_res:0.651200 +2025-04-19 08:39:37,265 INFO Epoch:83 train_loss:0.05880 +2025-04-19 08:39:46,164 INFO Epoch:83 val_res:0.650000 +2025-04-19 08:40:21,282 INFO Epoch:84 train_loss:0.06280 +2025-04-19 08:40:29,927 INFO Epoch:84 val_res:0.653200 +2025-04-19 08:41:05,300 INFO Epoch:85 train_loss:0.09696 +2025-04-19 08:41:14,009 INFO Epoch:85 val_res:0.647200 +2025-04-19 08:41:48,394 INFO Epoch:86 train_loss:0.09690 +2025-04-19 08:41:57,240 INFO Epoch:86 val_res:0.647200 +2025-04-19 08:42:32,174 INFO Epoch:87 train_loss:0.07581 +2025-04-19 08:42:40,803 INFO Epoch:87 val_res:0.652000 +2025-04-19 08:43:16,179 INFO Epoch:88 train_loss:0.07992 +2025-04-19 08:43:24,792 INFO Epoch:88 val_res:0.651600 +2025-04-19 08:43:59,724 INFO Epoch:89 train_loss:0.07322 +2025-04-19 08:44:07,940 INFO Epoch:89 val_res:0.644400 +2025-04-19 08:44:42,439 INFO Epoch:90 train_loss:0.07172 +2025-04-19 08:44:51,122 INFO Epoch:90 val_res:0.647600 +2025-04-19 08:45:26,008 INFO Epoch:91 train_loss:0.06648 +2025-04-19 08:45:35,117 INFO Epoch:91 val_res:0.653200 +2025-04-19 08:46:10,605 INFO Epoch:92 train_loss:0.07323 +2025-04-19 08:46:19,100 INFO Epoch:92 val_res:0.642400 +2025-04-19 08:46:55,296 INFO Epoch:93 train_loss:0.08561 +2025-04-19 08:47:04,337 INFO Epoch:93 val_res:0.650400 +2025-04-19 08:47:38,482 INFO Epoch:94 train_loss:0.11291 +2025-04-19 08:47:46,716 INFO Epoch:94 val_res:0.640800 +2025-04-19 08:48:21,817 INFO Epoch:95 train_loss:0.11147 +2025-04-19 08:48:30,953 INFO Epoch:95 val_res:0.646800 +2025-04-19 08:49:06,198 INFO Epoch:96 train_loss:0.08108 +2025-04-19 08:49:15,221 INFO Epoch:96 val_res:0.647600 +2025-04-19 08:49:50,605 INFO Epoch:97 train_loss:0.06202 +2025-04-19 08:49:59,075 INFO Epoch:97 val_res:0.646800 +2025-04-19 08:50:33,669 INFO Epoch:98 train_loss:0.05958 +2025-04-19 08:50:43,106 INFO Epoch:98 val_res:0.648000 +2025-04-19 08:51:17,215 INFO Epoch:99 train_loss:0.05791 +2025-04-19 08:51:26,226 INFO Epoch:99 val_res:0.644400 +2025-04-19 08:51:27,037 INFO ===================================== +2025-04-19 08:51:27,038 INFO Start testing... +2025-04-19 08:51:27,057 INFO ===================================== +2025-04-19 08:51:37,000 INFO Incremental step 4 Testing res: 0.663600 +2025-04-19 08:51:37,002 INFO forgetting: 0.084000 +2025-04-19 08:51:37,006 INFO ***************New Step*************************** +2025-04-19 08:51:37,006 INFO Incremental step: 5 +2025-04-19 08:51:37,207 INFO actual size of exemplar set: 1500 +2025-04-19 08:52:14,853 INFO Epoch:0 train_loss:3.16446 +2025-04-19 08:52:26,644 INFO Epoch:0 val_res:0.553000 +2025-04-19 08:52:26,645 INFO Saving best model at Epoch 0 +2025-04-19 08:53:04,376 INFO Epoch:1 train_loss:0.92206 +2025-04-19 08:53:15,068 INFO Epoch:1 val_res:0.561667 +2025-04-19 08:53:15,068 INFO Saving best model at Epoch 1 +2025-04-19 08:53:51,790 INFO Epoch:2 train_loss:0.54738 +2025-04-19 08:54:02,817 INFO Epoch:2 val_res:0.573333 +2025-04-19 08:54:02,818 INFO Saving best model at Epoch 2 +2025-04-19 08:54:37,887 INFO Epoch:3 train_loss:0.43602 +2025-04-19 08:54:48,634 INFO Epoch:3 val_res:0.576667 +2025-04-19 08:54:48,635 INFO Saving best model at Epoch 3 +2025-04-19 08:55:23,421 INFO Epoch:4 train_loss:0.37472 +2025-04-19 08:55:34,651 INFO Epoch:4 val_res:0.575333 +2025-04-19 08:56:07,492 INFO Epoch:5 train_loss:0.34730 +2025-04-19 08:56:17,946 INFO Epoch:5 val_res:0.575667 +2025-04-19 08:56:50,193 INFO Epoch:6 train_loss:0.31995 +2025-04-19 08:57:00,300 INFO Epoch:6 val_res:0.579333 +2025-04-19 08:57:00,301 INFO Saving best model at Epoch 6 +2025-04-19 08:57:34,677 INFO Epoch:7 train_loss:0.30113 +2025-04-19 08:57:45,821 INFO Epoch:7 val_res:0.578667 +2025-04-19 08:58:17,777 INFO Epoch:8 train_loss:0.28566 +2025-04-19 08:58:28,398 INFO Epoch:8 val_res:0.580667 +2025-04-19 08:58:28,399 INFO Saving best model at Epoch 8 +2025-04-19 08:59:03,522 INFO Epoch:9 train_loss:0.27387 +2025-04-19 08:59:14,085 INFO Epoch:9 val_res:0.580667 +2025-04-19 08:59:47,262 INFO Epoch:10 train_loss:0.27584 +2025-04-19 08:59:57,872 INFO Epoch:10 val_res:0.583333 +2025-04-19 08:59:57,873 INFO Saving best model at Epoch 10 +2025-04-19 09:00:32,795 INFO Epoch:11 train_loss:0.28196 +2025-04-19 09:00:42,456 INFO Epoch:11 val_res:0.583000 +2025-04-19 09:01:16,083 INFO Epoch:12 train_loss:0.27380 +2025-04-19 09:01:26,759 INFO Epoch:12 val_res:0.584000 +2025-04-19 09:01:26,760 INFO Saving best model at Epoch 12 +2025-04-19 09:02:00,931 INFO Epoch:13 train_loss:0.25442 +2025-04-19 09:02:11,501 INFO Epoch:13 val_res:0.585333 +2025-04-19 09:02:11,501 INFO Saving best model at Epoch 13 +2025-04-19 09:02:45,476 INFO Epoch:14 train_loss:0.23683 +2025-04-19 09:02:56,130 INFO Epoch:14 val_res:0.588667 +2025-04-19 09:02:56,131 INFO Saving best model at Epoch 14 +2025-04-19 09:03:30,493 INFO Epoch:15 train_loss:0.23087 +2025-04-19 09:03:41,030 INFO Epoch:15 val_res:0.591333 +2025-04-19 09:03:41,031 INFO Saving best model at Epoch 15 +2025-04-19 09:04:15,075 INFO Epoch:16 train_loss:0.26447 +2025-04-19 09:04:25,338 INFO Epoch:16 val_res:0.591333 +2025-04-19 09:04:56,126 INFO Epoch:17 train_loss:0.23510 +2025-04-19 09:05:05,295 INFO Epoch:17 val_res:0.590667 +2025-04-19 09:05:34,933 INFO Epoch:18 train_loss:0.21128 +2025-04-19 09:05:44,099 INFO Epoch:18 val_res:0.589333 +2025-04-19 09:06:14,622 INFO Epoch:19 train_loss:0.21511 +2025-04-19 09:06:23,933 INFO Epoch:19 val_res:0.592000 +2025-04-19 09:06:23,934 INFO Saving best model at Epoch 19 +2025-04-19 09:06:58,427 INFO Epoch:20 train_loss:0.24276 +2025-04-19 09:07:07,891 INFO Epoch:20 val_res:0.596000 +2025-04-19 09:07:07,891 INFO Saving best model at Epoch 20 +2025-04-19 09:07:39,382 INFO Epoch:21 train_loss:0.20916 +2025-04-19 09:07:48,729 INFO Epoch:21 val_res:0.599000 +2025-04-19 09:07:48,730 INFO Saving best model at Epoch 21 +2025-04-19 09:08:19,812 INFO Epoch:22 train_loss:0.19143 +2025-04-19 09:08:28,696 INFO Epoch:22 val_res:0.595333 +2025-04-19 09:08:58,568 INFO Epoch:23 train_loss:0.19333 +2025-04-19 09:09:07,108 INFO Epoch:23 val_res:0.598000 +2025-04-19 09:09:36,524 INFO Epoch:24 train_loss:0.18361 +2025-04-19 09:09:45,079 INFO Epoch:24 val_res:0.600333 +2025-04-19 09:09:45,079 INFO Saving best model at Epoch 24 +2025-04-19 09:10:15,339 INFO Epoch:25 train_loss:0.17628 +2025-04-19 09:10:23,842 INFO Epoch:25 val_res:0.602333 +2025-04-19 09:10:23,843 INFO Saving best model at Epoch 25 +2025-04-19 09:10:53,946 INFO Epoch:26 train_loss:0.21230 +2025-04-19 09:11:02,833 INFO Epoch:26 val_res:0.597000 +2025-04-19 09:11:32,065 INFO Epoch:27 train_loss:0.25684 +2025-04-19 09:11:40,702 INFO Epoch:27 val_res:0.600667 +2025-04-19 09:12:09,506 INFO Epoch:28 train_loss:0.20494 +2025-04-19 09:12:18,265 INFO Epoch:28 val_res:0.604333 +2025-04-19 09:12:18,266 INFO Saving best model at Epoch 28 +2025-04-19 09:12:48,683 INFO Epoch:29 train_loss:0.15657 +2025-04-19 09:12:57,929 INFO Epoch:29 val_res:0.610667 +2025-04-19 09:12:57,929 INFO Saving best model at Epoch 29 +2025-04-19 09:13:28,633 INFO Epoch:30 train_loss:0.13220 +2025-04-19 09:13:37,781 INFO Epoch:30 val_res:0.611333 +2025-04-19 09:13:37,782 INFO Saving best model at Epoch 30 +2025-04-19 09:14:09,468 INFO Epoch:31 train_loss:0.12460 +2025-04-19 09:14:18,534 INFO Epoch:31 val_res:0.614667 +2025-04-19 09:14:18,535 INFO Saving best model at Epoch 31 +2025-04-19 09:14:50,294 INFO Epoch:32 train_loss:0.12247 +2025-04-19 09:14:59,582 INFO Epoch:32 val_res:0.617000 +2025-04-19 09:14:59,582 INFO Saving best model at Epoch 32 +2025-04-19 09:15:30,768 INFO Epoch:33 train_loss:0.13324 +2025-04-19 09:15:39,880 INFO Epoch:33 val_res:0.614333 +2025-04-19 09:16:09,683 INFO Epoch:34 train_loss:0.12631 +2025-04-19 09:16:18,917 INFO Epoch:34 val_res:0.620333 +2025-04-19 09:16:18,918 INFO Saving best model at Epoch 34 +2025-04-19 09:16:50,970 INFO Epoch:35 train_loss:0.11484 +2025-04-19 09:17:00,217 INFO Epoch:35 val_res:0.619000 +2025-04-19 09:17:30,406 INFO Epoch:36 train_loss:0.12548 +2025-04-19 09:17:39,843 INFO Epoch:36 val_res:0.620667 +2025-04-19 09:17:39,844 INFO Saving best model at Epoch 36 +2025-04-19 09:18:11,514 INFO Epoch:37 train_loss:0.13154 +2025-04-19 09:18:20,788 INFO Epoch:37 val_res:0.608000 +2025-04-19 09:18:49,881 INFO Epoch:38 train_loss:0.37672 +2025-04-19 09:18:59,177 INFO Epoch:38 val_res:0.610000 +2025-04-19 09:19:29,577 INFO Epoch:39 train_loss:0.31633 +2025-04-19 09:19:38,817 INFO Epoch:39 val_res:0.621000 +2025-04-19 09:19:38,817 INFO Saving best model at Epoch 39 +2025-04-19 09:20:12,753 INFO Epoch:40 train_loss:0.16780 +2025-04-19 09:20:22,080 INFO Epoch:40 val_res:0.629667 +2025-04-19 09:20:22,080 INFO Saving best model at Epoch 40 +2025-04-19 09:20:54,055 INFO Epoch:41 train_loss:0.11688 +2025-04-19 09:21:03,184 INFO Epoch:41 val_res:0.630667 +2025-04-19 09:21:03,185 INFO Saving best model at Epoch 41 +2025-04-19 09:21:34,949 INFO Epoch:42 train_loss:0.10036 +2025-04-19 09:21:43,983 INFO Epoch:42 val_res:0.628333 +2025-04-19 09:22:13,889 INFO Epoch:43 train_loss:0.09375 +2025-04-19 09:22:22,582 INFO Epoch:43 val_res:0.626667 +2025-04-19 09:22:52,906 INFO Epoch:44 train_loss:0.08952 +2025-04-19 09:23:02,241 INFO Epoch:44 val_res:0.625000 +2025-04-19 09:23:32,530 INFO Epoch:45 train_loss:0.08841 +2025-04-19 09:23:42,240 INFO Epoch:45 val_res:0.626333 +2025-04-19 09:24:13,220 INFO Epoch:46 train_loss:0.08448 +2025-04-19 09:24:22,835 INFO Epoch:46 val_res:0.626667 +2025-04-19 09:24:51,993 INFO Epoch:47 train_loss:0.08830 +2025-04-19 09:25:00,573 INFO Epoch:47 val_res:0.625000 +2025-04-19 09:25:30,596 INFO Epoch:48 train_loss:0.11513 +2025-04-19 09:25:39,226 INFO Epoch:48 val_res:0.630333 +2025-04-19 09:26:08,495 INFO Epoch:49 train_loss:0.09961 +2025-04-19 09:26:18,179 INFO Epoch:49 val_res:0.631000 +2025-04-19 09:26:18,180 INFO Saving best model at Epoch 49 +2025-04-19 09:26:50,008 INFO Epoch:50 train_loss:0.08924 +2025-04-19 09:26:58,766 INFO Epoch:50 val_res:0.625000 +2025-04-19 09:27:28,617 INFO Epoch:51 train_loss:0.09504 +2025-04-19 09:27:37,430 INFO Epoch:51 val_res:0.632333 +2025-04-19 09:27:37,430 INFO Saving best model at Epoch 51 +2025-04-19 09:28:08,274 INFO Epoch:52 train_loss:0.13450 +2025-04-19 09:28:16,939 INFO Epoch:52 val_res:0.626000 +2025-04-19 09:28:46,343 INFO Epoch:53 train_loss:0.13540 +2025-04-19 09:28:54,907 INFO Epoch:53 val_res:0.632667 +2025-04-19 09:28:54,908 INFO Saving best model at Epoch 53 +2025-04-19 09:29:26,595 INFO Epoch:54 train_loss:0.10607 +2025-04-19 09:29:35,251 INFO Epoch:54 val_res:0.635000 +2025-04-19 09:29:35,251 INFO Saving best model at Epoch 54 +2025-04-19 09:30:06,235 INFO Epoch:55 train_loss:0.09970 +2025-04-19 09:30:14,975 INFO Epoch:55 val_res:0.627333 +2025-04-19 09:30:43,215 INFO Epoch:56 train_loss:0.08130 +2025-04-19 09:30:52,038 INFO Epoch:56 val_res:0.631333 +2025-04-19 09:31:21,614 INFO Epoch:57 train_loss:0.07626 +2025-04-19 09:31:30,357 INFO Epoch:57 val_res:0.630667 +2025-04-19 09:31:59,216 INFO Epoch:58 train_loss:0.08226 +2025-04-19 09:32:07,830 INFO Epoch:58 val_res:0.629667 +2025-04-19 09:32:37,021 INFO Epoch:59 train_loss:0.10585 +2025-04-19 09:32:46,270 INFO Epoch:59 val_res:0.632667 +2025-04-19 09:33:15,698 INFO Epoch:60 train_loss:0.09128 +2025-04-19 09:33:24,605 INFO Epoch:60 val_res:0.632667 +2025-04-19 09:33:53,683 INFO Epoch:61 train_loss:0.08801 +2025-04-19 09:34:02,589 INFO Epoch:61 val_res:0.631667 +2025-04-19 09:34:31,599 INFO Epoch:62 train_loss:0.10615 +2025-04-19 09:34:40,407 INFO Epoch:62 val_res:0.634667 +2025-04-19 09:35:09,261 INFO Epoch:63 train_loss:0.08581 +2025-04-19 09:35:18,100 INFO Epoch:63 val_res:0.633333 +2025-04-19 09:35:46,549 INFO Epoch:64 train_loss:0.09663 +2025-04-19 09:35:55,926 INFO Epoch:64 val_res:0.632333 +2025-04-19 09:36:24,298 INFO Epoch:65 train_loss:0.10646 +2025-04-19 09:36:32,941 INFO Epoch:65 val_res:0.634667 +2025-04-19 09:37:03,152 INFO Epoch:66 train_loss:0.10234 +2025-04-19 09:37:12,365 INFO Epoch:66 val_res:0.636000 +2025-04-19 09:37:12,365 INFO Saving best model at Epoch 66 +2025-04-19 09:37:43,433 INFO Epoch:67 train_loss:0.12939 +2025-04-19 09:37:52,448 INFO Epoch:67 val_res:0.630667 +2025-04-19 09:38:21,508 INFO Epoch:68 train_loss:0.09502 +2025-04-19 09:38:29,949 INFO Epoch:68 val_res:0.626333 +2025-04-19 09:38:58,774 INFO Epoch:69 train_loss:0.10708 +2025-04-19 09:39:07,249 INFO Epoch:69 val_res:0.628667 +2025-04-19 09:39:35,701 INFO Epoch:70 train_loss:0.08421 +2025-04-19 09:39:44,039 INFO Epoch:70 val_res:0.632000 +2025-04-19 09:40:13,473 INFO Epoch:71 train_loss:0.08093 +2025-04-19 09:40:21,890 INFO Epoch:71 val_res:0.626000 +2025-04-19 09:40:50,745 INFO Epoch:72 train_loss:0.08244 +2025-04-19 09:40:59,301 INFO Epoch:72 val_res:0.629667 +2025-04-19 09:41:28,344 INFO Epoch:73 train_loss:0.08394 +2025-04-19 09:41:37,127 INFO Epoch:73 val_res:0.634333 +2025-04-19 09:42:06,252 INFO Epoch:74 train_loss:0.07503 +2025-04-19 09:42:14,903 INFO Epoch:74 val_res:0.632667 +2025-04-19 09:42:44,067 INFO Epoch:75 train_loss:0.08310 +2025-04-19 09:42:52,754 INFO Epoch:75 val_res:0.626333 +2025-04-19 09:43:21,601 INFO Epoch:76 train_loss:0.11111 +2025-04-19 09:43:30,122 INFO Epoch:76 val_res:0.622333 +2025-04-19 09:43:58,228 INFO Epoch:77 train_loss:0.15921 +2025-04-19 09:44:06,922 INFO Epoch:77 val_res:0.627667 +2025-04-19 09:44:35,722 INFO Epoch:78 train_loss:0.15266 +2025-04-19 09:44:44,395 INFO Epoch:78 val_res:0.623667 +2025-04-19 09:45:13,527 INFO Epoch:79 train_loss:0.11566 +2025-04-19 09:45:22,238 INFO Epoch:79 val_res:0.632667 +2025-04-19 09:45:50,794 INFO Epoch:80 train_loss:0.09353 +2025-04-19 09:45:59,726 INFO Epoch:80 val_res:0.632000 +2025-04-19 09:46:29,400 INFO Epoch:81 train_loss:0.08647 +2025-04-19 09:46:38,116 INFO Epoch:81 val_res:0.626667 +2025-04-19 09:47:07,507 INFO Epoch:82 train_loss:0.07157 +2025-04-19 09:47:16,031 INFO Epoch:82 val_res:0.624333 +2025-04-19 09:47:45,742 INFO Epoch:83 train_loss:0.06345 +2025-04-19 09:47:54,324 INFO Epoch:83 val_res:0.629333 +2025-04-19 09:48:22,595 INFO Epoch:84 train_loss:0.07157 +2025-04-19 09:48:31,373 INFO Epoch:84 val_res:0.631333 +2025-04-19 09:49:00,442 INFO Epoch:85 train_loss:0.09805 +2025-04-19 09:49:08,922 INFO Epoch:85 val_res:0.626000 +2025-04-19 09:49:37,350 INFO Epoch:86 train_loss:0.07468 +2025-04-19 09:49:46,121 INFO Epoch:86 val_res:0.622667 +2025-04-19 09:50:14,562 INFO Epoch:87 train_loss:0.07859 +2025-04-19 09:50:23,719 INFO Epoch:87 val_res:0.623667 +2025-04-19 09:50:52,578 INFO Epoch:88 train_loss:0.08683 +2025-04-19 09:51:01,478 INFO Epoch:88 val_res:0.623667 +2025-04-19 09:51:30,451 INFO Epoch:89 train_loss:0.09414 +2025-04-19 09:51:39,251 INFO Epoch:89 val_res:0.623333 +2025-04-19 09:52:07,946 INFO Epoch:90 train_loss:0.13099 +2025-04-19 09:52:17,046 INFO Epoch:90 val_res:0.626667 +2025-04-19 09:52:45,780 INFO Epoch:91 train_loss:0.09939 +2025-04-19 09:52:54,734 INFO Epoch:91 val_res:0.623667 +2025-04-19 09:53:24,111 INFO Epoch:92 train_loss:0.07880 +2025-04-19 09:53:33,318 INFO Epoch:92 val_res:0.617667 +2025-04-19 09:54:02,334 INFO Epoch:93 train_loss:0.09261 +2025-04-19 09:54:11,183 INFO Epoch:93 val_res:0.629667 +2025-04-19 09:54:40,082 INFO Epoch:94 train_loss:0.08729 +2025-04-19 09:54:48,814 INFO Epoch:94 val_res:0.626333 +2025-04-19 09:55:17,541 INFO Epoch:95 train_loss:0.08557 +2025-04-19 09:55:26,478 INFO Epoch:95 val_res:0.622333 +2025-04-19 09:55:56,144 INFO Epoch:96 train_loss:0.06555 +2025-04-19 09:56:04,654 INFO Epoch:96 val_res:0.623000 +2025-04-19 09:56:32,945 INFO Epoch:97 train_loss:0.07457 +2025-04-19 09:56:41,517 INFO Epoch:97 val_res:0.623333 +2025-04-19 09:57:09,962 INFO Epoch:98 train_loss:0.09663 +2025-04-19 09:57:18,362 INFO Epoch:98 val_res:0.619667 +2025-04-19 09:57:47,702 INFO Epoch:99 train_loss:0.09105 +2025-04-19 09:57:56,062 INFO Epoch:99 val_res:0.618333 +2025-04-19 09:57:56,864 INFO ===================================== +2025-04-19 09:57:56,864 INFO Start testing... +2025-04-19 09:57:56,865 INFO ===================================== +2025-04-19 09:58:06,556 INFO Incremental step 5 Testing res: 0.625667 +2025-04-19 09:58:06,558 INFO forgetting: 0.091600 +2025-04-19 09:58:06,562 INFO ***************New Step*************************** +2025-04-19 09:58:06,562 INFO Incremental step: 6 +2025-04-19 09:58:06,735 INFO actual size of exemplar set: 1500 +2025-04-19 09:58:38,774 INFO Epoch:0 train_loss:3.33598 +2025-04-19 09:58:49,798 INFO Epoch:0 val_res:0.532000 +2025-04-19 09:58:49,800 INFO Saving best model at Epoch 0 +2025-04-19 09:59:23,228 INFO Epoch:1 train_loss:0.83530 +2025-04-19 09:59:33,640 INFO Epoch:1 val_res:0.548286 +2025-04-19 09:59:33,640 INFO Saving best model at Epoch 1 +2025-04-19 10:00:05,115 INFO Epoch:2 train_loss:0.44919 +2025-04-19 10:00:14,793 INFO Epoch:2 val_res:0.555143 +2025-04-19 10:00:14,794 INFO Saving best model at Epoch 2 +2025-04-19 10:00:46,941 INFO Epoch:3 train_loss:0.34751 +2025-04-19 10:00:56,729 INFO Epoch:3 val_res:0.556857 +2025-04-19 10:00:56,729 INFO Saving best model at Epoch 3 +2025-04-19 10:01:28,165 INFO Epoch:4 train_loss:0.30866 +2025-04-19 10:01:38,311 INFO Epoch:4 val_res:0.557143 +2025-04-19 10:01:38,312 INFO Saving best model at Epoch 4 +2025-04-19 10:02:09,574 INFO Epoch:5 train_loss:0.28800 +2025-04-19 10:02:19,658 INFO Epoch:5 val_res:0.560000 +2025-04-19 10:02:19,658 INFO Saving best model at Epoch 5 +2025-04-19 10:02:51,846 INFO Epoch:6 train_loss:0.26688 +2025-04-19 10:03:01,923 INFO Epoch:6 val_res:0.562571 +2025-04-19 10:03:01,924 INFO Saving best model at Epoch 6 +2025-04-19 10:03:33,889 INFO Epoch:7 train_loss:0.25319 +2025-04-19 10:03:44,165 INFO Epoch:7 val_res:0.567143 +2025-04-19 10:03:44,165 INFO Saving best model at Epoch 7 +2025-04-19 10:04:15,452 INFO Epoch:8 train_loss:0.23293 +2025-04-19 10:04:26,188 INFO Epoch:8 val_res:0.567714 +2025-04-19 10:04:26,188 INFO Saving best model at Epoch 8 +2025-04-19 10:04:58,445 INFO Epoch:9 train_loss:0.22483 +2025-04-19 10:05:08,591 INFO Epoch:9 val_res:0.568857 +2025-04-19 10:05:08,592 INFO Saving best model at Epoch 9 +2025-04-19 10:05:40,585 INFO Epoch:10 train_loss:0.21647 +2025-04-19 10:05:50,959 INFO Epoch:10 val_res:0.570857 +2025-04-19 10:05:50,963 INFO Saving best model at Epoch 10 +2025-04-19 10:06:22,986 INFO Epoch:11 train_loss:0.20716 +2025-04-19 10:06:33,455 INFO Epoch:11 val_res:0.575429 +2025-04-19 10:06:33,455 INFO Saving best model at Epoch 11 +2025-04-19 10:07:05,638 INFO Epoch:12 train_loss:0.19931 +2025-04-19 10:07:16,299 INFO Epoch:12 val_res:0.576286 +2025-04-19 10:07:16,299 INFO Saving best model at Epoch 12 +2025-04-19 10:07:49,330 INFO Epoch:13 train_loss:0.18718 +2025-04-19 10:08:00,000 INFO Epoch:13 val_res:0.575143 +2025-04-19 10:08:32,882 INFO Epoch:14 train_loss:0.18421 +2025-04-19 10:08:43,053 INFO Epoch:14 val_res:0.577143 +2025-04-19 10:08:43,053 INFO Saving best model at Epoch 14 +2025-04-19 10:09:14,420 INFO Epoch:15 train_loss:0.18811 +2025-04-19 10:09:24,735 INFO Epoch:15 val_res:0.577143 +2025-04-19 10:09:55,407 INFO Epoch:16 train_loss:0.20887 +2025-04-19 10:10:05,195 INFO Epoch:16 val_res:0.573143 +2025-04-19 10:10:36,087 INFO Epoch:17 train_loss:0.22746 +2025-04-19 10:10:46,446 INFO Epoch:17 val_res:0.578571 +2025-04-19 10:10:46,447 INFO Saving best model at Epoch 17 +2025-04-19 10:11:18,347 INFO Epoch:18 train_loss:0.19369 +2025-04-19 10:11:28,691 INFO Epoch:18 val_res:0.580857 +2025-04-19 10:11:28,691 INFO Saving best model at Epoch 18 +2025-04-19 10:12:01,469 INFO Epoch:19 train_loss:0.19300 +2025-04-19 10:12:12,170 INFO Epoch:19 val_res:0.582000 +2025-04-19 10:12:12,170 INFO Saving best model at Epoch 19 +2025-04-19 10:12:45,635 INFO Epoch:20 train_loss:0.19208 +2025-04-19 10:12:56,895 INFO Epoch:20 val_res:0.582571 +2025-04-19 10:12:56,895 INFO Saving best model at Epoch 20 +2025-04-19 10:13:29,515 INFO Epoch:21 train_loss:0.15831 +2025-04-19 10:13:40,761 INFO Epoch:21 val_res:0.583429 +2025-04-19 10:13:40,762 INFO Saving best model at Epoch 21 +2025-04-19 10:14:13,224 INFO Epoch:22 train_loss:0.16087 +2025-04-19 10:14:24,204 INFO Epoch:22 val_res:0.584571 +2025-04-19 10:14:24,205 INFO Saving best model at Epoch 22 +2025-04-19 10:14:56,659 INFO Epoch:23 train_loss:0.18211 +2025-04-19 10:15:07,217 INFO Epoch:23 val_res:0.582286 +2025-04-19 10:15:37,689 INFO Epoch:24 train_loss:0.22675 +2025-04-19 10:15:47,986 INFO Epoch:24 val_res:0.581714 +2025-04-19 10:16:19,591 INFO Epoch:25 train_loss:0.18868 +2025-04-19 10:16:29,262 INFO Epoch:25 val_res:0.586857 +2025-04-19 10:16:29,262 INFO Saving best model at Epoch 25 +2025-04-19 10:17:01,901 INFO Epoch:26 train_loss:0.20273 +2025-04-19 10:17:11,860 INFO Epoch:26 val_res:0.588571 +2025-04-19 10:17:11,866 INFO Saving best model at Epoch 26 +2025-04-19 10:17:44,741 INFO Epoch:27 train_loss:0.24724 +2025-04-19 10:17:55,482 INFO Epoch:27 val_res:0.586286 +2025-04-19 10:18:25,475 INFO Epoch:28 train_loss:0.20267 +2025-04-19 10:18:36,164 INFO Epoch:28 val_res:0.587143 +2025-04-19 10:19:06,731 INFO Epoch:29 train_loss:0.15414 +2025-04-19 10:19:17,452 INFO Epoch:29 val_res:0.591714 +2025-04-19 10:19:17,452 INFO Saving best model at Epoch 29 +2025-04-19 10:19:49,843 INFO Epoch:30 train_loss:0.12940 +2025-04-19 10:20:00,453 INFO Epoch:30 val_res:0.592857 +2025-04-19 10:20:00,453 INFO Saving best model at Epoch 30 +2025-04-19 10:20:32,485 INFO Epoch:31 train_loss:0.11771 +2025-04-19 10:20:42,458 INFO Epoch:31 val_res:0.594000 +2025-04-19 10:20:42,458 INFO Saving best model at Epoch 31 +2025-04-19 10:21:14,674 INFO Epoch:32 train_loss:0.12006 +2025-04-19 10:21:24,688 INFO Epoch:32 val_res:0.596571 +2025-04-19 10:21:24,689 INFO Saving best model at Epoch 32 +2025-04-19 10:21:57,782 INFO Epoch:33 train_loss:0.11689 +2025-04-19 10:22:08,509 INFO Epoch:33 val_res:0.600857 +2025-04-19 10:22:08,510 INFO Saving best model at Epoch 33 +2025-04-19 10:22:40,210 INFO Epoch:34 train_loss:0.13236 +2025-04-19 10:22:50,880 INFO Epoch:34 val_res:0.597143 +2025-04-19 10:23:21,267 INFO Epoch:35 train_loss:0.15625 +2025-04-19 10:23:31,729 INFO Epoch:35 val_res:0.600571 +2025-04-19 10:24:02,426 INFO Epoch:36 train_loss:0.21781 +2025-04-19 10:24:12,826 INFO Epoch:36 val_res:0.599429 +2025-04-19 10:24:43,035 INFO Epoch:37 train_loss:0.19451 +2025-04-19 10:24:52,880 INFO Epoch:37 val_res:0.600286 +2025-04-19 10:25:23,129 INFO Epoch:38 train_loss:0.13260 +2025-04-19 10:25:33,008 INFO Epoch:38 val_res:0.604000 +2025-04-19 10:25:33,009 INFO Saving best model at Epoch 38 +2025-04-19 10:26:04,624 INFO Epoch:39 train_loss:0.11508 +2025-04-19 10:26:14,770 INFO Epoch:39 val_res:0.610857 +2025-04-19 10:26:14,771 INFO Saving best model at Epoch 39 +2025-04-19 10:26:47,255 INFO Epoch:40 train_loss:0.10143 +2025-04-19 10:26:57,705 INFO Epoch:40 val_res:0.607714 +2025-04-19 10:27:28,022 INFO Epoch:41 train_loss:0.11451 +2025-04-19 10:27:38,642 INFO Epoch:41 val_res:0.607429 +2025-04-19 10:28:08,936 INFO Epoch:42 train_loss:0.11715 +2025-04-19 10:28:19,549 INFO Epoch:42 val_res:0.610000 +2025-04-19 10:28:49,432 INFO Epoch:43 train_loss:0.11430 +2025-04-19 10:28:59,570 INFO Epoch:43 val_res:0.613714 +2025-04-19 10:28:59,571 INFO Saving best model at Epoch 43 +2025-04-19 10:29:31,808 INFO Epoch:44 train_loss:0.11451 +2025-04-19 10:29:41,993 INFO Epoch:44 val_res:0.609429 +2025-04-19 10:30:12,549 INFO Epoch:45 train_loss:0.12895 +2025-04-19 10:30:22,725 INFO Epoch:45 val_res:0.617143 +2025-04-19 10:30:22,726 INFO Saving best model at Epoch 45 +2025-04-19 10:30:55,014 INFO Epoch:46 train_loss:0.13873 +2025-04-19 10:31:05,586 INFO Epoch:46 val_res:0.617143 +2025-04-19 10:31:35,635 INFO Epoch:47 train_loss:0.11450 +2025-04-19 10:31:46,335 INFO Epoch:47 val_res:0.618286 +2025-04-19 10:31:46,335 INFO Saving best model at Epoch 47 +2025-04-19 10:32:18,928 INFO Epoch:48 train_loss:0.12556 +2025-04-19 10:32:29,255 INFO Epoch:48 val_res:0.619429 +2025-04-19 10:32:29,255 INFO Saving best model at Epoch 48 +2025-04-19 10:33:01,312 INFO Epoch:49 train_loss:0.18410 +2025-04-19 10:33:11,127 INFO Epoch:49 val_res:0.614286 +2025-04-19 10:33:41,756 INFO Epoch:50 train_loss:0.20973 +2025-04-19 10:33:51,900 INFO Epoch:50 val_res:0.617429 +2025-04-19 10:34:22,571 INFO Epoch:51 train_loss:0.14996 +2025-04-19 10:34:32,896 INFO Epoch:51 val_res:0.620286 +2025-04-19 10:34:32,896 INFO Saving best model at Epoch 51 +2025-04-19 10:35:04,754 INFO Epoch:52 train_loss:0.10465 +2025-04-19 10:35:15,025 INFO Epoch:52 val_res:0.624286 +2025-04-19 10:35:15,025 INFO Saving best model at Epoch 52 +2025-04-19 10:35:46,828 INFO Epoch:53 train_loss:0.08736 +2025-04-19 10:35:56,913 INFO Epoch:53 val_res:0.622571 +2025-04-19 10:36:27,762 INFO Epoch:54 train_loss:0.08119 +2025-04-19 10:36:37,540 INFO Epoch:54 val_res:0.621714 +2025-04-19 10:37:08,159 INFO Epoch:55 train_loss:0.09628 +2025-04-19 10:37:17,967 INFO Epoch:55 val_res:0.622571 +2025-04-19 10:37:49,274 INFO Epoch:56 train_loss:0.10169 +2025-04-19 10:37:59,450 INFO Epoch:56 val_res:0.622571 +2025-04-19 10:38:30,766 INFO Epoch:57 train_loss:0.09148 +2025-04-19 10:38:40,916 INFO Epoch:57 val_res:0.624286 +2025-04-19 10:39:11,777 INFO Epoch:58 train_loss:0.11851 +2025-04-19 10:39:22,250 INFO Epoch:58 val_res:0.618286 +2025-04-19 10:39:53,548 INFO Epoch:59 train_loss:0.13787 +2025-04-19 10:40:04,132 INFO Epoch:59 val_res:0.622286 +2025-04-19 10:40:35,381 INFO Epoch:60 train_loss:0.11193 +2025-04-19 10:40:45,358 INFO Epoch:60 val_res:0.624286 +2025-04-19 10:41:16,225 INFO Epoch:61 train_loss:0.11304 +2025-04-19 10:41:26,449 INFO Epoch:61 val_res:0.623429 +2025-04-19 10:41:57,248 INFO Epoch:62 train_loss:0.10937 +2025-04-19 10:42:07,256 INFO Epoch:62 val_res:0.626286 +2025-04-19 10:42:07,256 INFO Saving best model at Epoch 62 +2025-04-19 10:42:39,106 INFO Epoch:63 train_loss:0.10642 +2025-04-19 10:42:48,995 INFO Epoch:63 val_res:0.628000 +2025-04-19 10:42:48,996 INFO Saving best model at Epoch 63 +2025-04-19 10:43:20,897 INFO Epoch:64 train_loss:0.12465 +2025-04-19 10:43:30,910 INFO Epoch:64 val_res:0.628000 +2025-04-19 10:44:00,742 INFO Epoch:65 train_loss:0.15229 +2025-04-19 10:44:10,368 INFO Epoch:65 val_res:0.620571 +2025-04-19 10:44:39,787 INFO Epoch:66 train_loss:0.13969 +2025-04-19 10:44:49,732 INFO Epoch:66 val_res:0.623429 +2025-04-19 10:45:20,136 INFO Epoch:67 train_loss:0.10463 +2025-04-19 10:45:30,212 INFO Epoch:67 val_res:0.627143 +2025-04-19 10:46:01,099 INFO Epoch:68 train_loss:0.10152 +2025-04-19 10:46:10,887 INFO Epoch:68 val_res:0.624571 +2025-04-19 10:46:41,424 INFO Epoch:69 train_loss:0.08673 +2025-04-19 10:46:51,243 INFO Epoch:69 val_res:0.625143 +2025-04-19 10:47:21,216 INFO Epoch:70 train_loss:0.09081 +2025-04-19 10:47:31,093 INFO Epoch:70 val_res:0.625429 +2025-04-19 10:48:01,599 INFO Epoch:71 train_loss:0.09747 +2025-04-19 10:48:12,223 INFO Epoch:71 val_res:0.624000 +2025-04-19 10:48:42,505 INFO Epoch:72 train_loss:0.11508 +2025-04-19 10:48:52,473 INFO Epoch:72 val_res:0.622286 +2025-04-19 10:49:22,946 INFO Epoch:73 train_loss:0.11016 +2025-04-19 10:49:32,928 INFO Epoch:73 val_res:0.618000 +2025-04-19 10:50:02,246 INFO Epoch:74 train_loss:0.15299 +2025-04-19 10:50:12,654 INFO Epoch:74 val_res:0.627429 +2025-04-19 10:50:43,666 INFO Epoch:75 train_loss:0.14281 +2025-04-19 10:50:54,057 INFO Epoch:75 val_res:0.621143 +2025-04-19 10:51:25,070 INFO Epoch:76 train_loss:0.12056 +2025-04-19 10:51:35,275 INFO Epoch:76 val_res:0.623143 +2025-04-19 10:52:05,495 INFO Epoch:77 train_loss:0.11411 +2025-04-19 10:52:15,273 INFO Epoch:77 val_res:0.624857 +2025-04-19 10:52:45,737 INFO Epoch:78 train_loss:0.09362 +2025-04-19 10:52:55,495 INFO Epoch:78 val_res:0.622000 +2025-04-19 10:53:26,831 INFO Epoch:79 train_loss:0.08522 +2025-04-19 10:53:36,967 INFO Epoch:79 val_res:0.621714 +2025-04-19 10:54:08,468 INFO Epoch:80 train_loss:0.08332 +2025-04-19 10:54:18,462 INFO Epoch:80 val_res:0.626571 +2025-04-19 10:54:48,331 INFO Epoch:81 train_loss:0.09160 +2025-04-19 10:54:58,071 INFO Epoch:81 val_res:0.622286 +2025-04-19 10:55:27,624 INFO Epoch:82 train_loss:0.08281 +2025-04-19 10:55:37,662 INFO Epoch:82 val_res:0.622571 +2025-04-19 10:56:08,450 INFO Epoch:83 train_loss:0.08675 +2025-04-19 10:56:19,100 INFO Epoch:83 val_res:0.619143 +2025-04-19 10:56:51,512 INFO Epoch:84 train_loss:0.08700 +2025-04-19 10:57:01,955 INFO Epoch:84 val_res:0.621714 +2025-04-19 10:57:33,992 INFO Epoch:85 train_loss:0.10705 +2025-04-19 10:57:45,118 INFO Epoch:85 val_res:0.621429 +2025-04-19 10:58:16,322 INFO Epoch:86 train_loss:0.13037 +2025-04-19 10:58:27,457 INFO Epoch:86 val_res:0.622571 +2025-04-19 10:58:58,994 INFO Epoch:87 train_loss:0.13797 +2025-04-19 10:59:09,642 INFO Epoch:87 val_res:0.624000 +2025-04-19 10:59:40,311 INFO Epoch:88 train_loss:0.10194 +2025-04-19 10:59:50,858 INFO Epoch:88 val_res:0.624286 +2025-04-19 11:00:21,273 INFO Epoch:89 train_loss:0.08197 +2025-04-19 11:00:32,086 INFO Epoch:89 val_res:0.619714 +2025-04-19 11:01:01,931 INFO Epoch:90 train_loss:0.08355 +2025-04-19 11:01:11,915 INFO Epoch:90 val_res:0.623714 +2025-04-19 11:01:41,382 INFO Epoch:91 train_loss:0.07633 +2025-04-19 11:01:50,979 INFO Epoch:91 val_res:0.620286 +2025-04-19 11:02:20,411 INFO Epoch:92 train_loss:0.08510 +2025-04-19 11:02:30,022 INFO Epoch:92 val_res:0.618857 +2025-04-19 11:03:00,162 INFO Epoch:93 train_loss:0.12145 +2025-04-19 11:03:09,771 INFO Epoch:93 val_res:0.621429 +2025-04-19 11:03:39,842 INFO Epoch:94 train_loss:0.11613 +2025-04-19 11:03:49,428 INFO Epoch:94 val_res:0.618857 +2025-04-19 11:04:18,633 INFO Epoch:95 train_loss:0.08202 +2025-04-19 11:04:28,429 INFO Epoch:95 val_res:0.624000 +2025-04-19 11:04:58,764 INFO Epoch:96 train_loss:0.07879 +2025-04-19 11:05:08,641 INFO Epoch:96 val_res:0.619143 +2025-04-19 11:05:37,969 INFO Epoch:97 train_loss:0.07824 +2025-04-19 11:05:48,031 INFO Epoch:97 val_res:0.623143 +2025-04-19 11:06:18,426 INFO Epoch:98 train_loss:0.09380 +2025-04-19 11:06:29,102 INFO Epoch:98 val_res:0.619143 +2025-04-19 11:06:58,763 INFO Epoch:99 train_loss:0.09609 +2025-04-19 11:07:08,841 INFO Epoch:99 val_res:0.621143 +2025-04-19 11:07:09,614 INFO ===================================== +2025-04-19 11:07:09,616 INFO Start testing... +2025-04-19 11:07:09,616 INFO ===================================== +2025-04-19 11:07:20,459 INFO Incremental step 6 Testing res: 0.625714 +2025-04-19 11:07:20,464 INFO forgetting: 0.064333 +2025-04-19 11:07:20,471 INFO ***************New Step*************************** +2025-04-19 11:07:20,472 INFO Incremental step: 7 +2025-04-19 11:07:20,673 INFO actual size of exemplar set: 1470 +2025-04-19 11:08:00,069 INFO Epoch:0 train_loss:3.34205 +2025-04-19 11:08:14,296 INFO Epoch:0 val_res:0.541500 +2025-04-19 11:08:14,297 INFO Saving best model at Epoch 0 +2025-04-19 11:08:54,413 INFO Epoch:1 train_loss:0.80746 +2025-04-19 11:09:05,638 INFO Epoch:1 val_res:0.550250 +2025-04-19 11:09:05,638 INFO Saving best model at Epoch 1 +2025-04-19 11:09:42,846 INFO Epoch:2 train_loss:0.52414 +2025-04-19 11:09:54,185 INFO Epoch:2 val_res:0.553500 +2025-04-19 11:09:54,185 INFO Saving best model at Epoch 2 +2025-04-19 11:10:32,462 INFO Epoch:3 train_loss:0.44536 +2025-04-19 11:10:46,147 INFO Epoch:3 val_res:0.553750 +2025-04-19 11:10:46,148 INFO Saving best model at Epoch 3 +2025-04-19 11:11:30,790 INFO Epoch:4 train_loss:0.40794 +2025-04-19 11:11:47,180 INFO Epoch:4 val_res:0.553750 +2025-04-19 11:12:28,673 INFO Epoch:5 train_loss:0.38154 +2025-04-19 11:12:42,158 INFO Epoch:5 val_res:0.553500 +2025-04-19 11:13:25,824 INFO Epoch:6 train_loss:0.35736 +2025-04-19 11:13:40,087 INFO Epoch:6 val_res:0.554250 +2025-04-19 11:13:40,088 INFO Saving best model at Epoch 6 +2025-04-19 11:14:23,639 INFO Epoch:7 train_loss:0.34071 +2025-04-19 11:14:37,905 INFO Epoch:7 val_res:0.555250 +2025-04-19 11:14:37,905 INFO Saving best model at Epoch 7 +2025-04-19 11:15:18,947 INFO Epoch:8 train_loss:0.32629 +2025-04-19 11:15:33,658 INFO Epoch:8 val_res:0.556500 +2025-04-19 11:15:33,659 INFO Saving best model at Epoch 8 +2025-04-19 11:16:13,147 INFO Epoch:9 train_loss:0.30928 +2025-04-19 11:16:27,638 INFO Epoch:9 val_res:0.557250 +2025-04-19 11:16:27,639 INFO Saving best model at Epoch 9 +2025-04-19 11:17:09,450 INFO Epoch:10 train_loss:0.29776 +2025-04-19 11:17:23,500 INFO Epoch:10 val_res:0.558250 +2025-04-19 11:17:23,501 INFO Saving best model at Epoch 10 +2025-04-19 11:18:02,987 INFO Epoch:11 train_loss:0.28779 +2025-04-19 11:18:14,477 INFO Epoch:11 val_res:0.560000 +2025-04-19 11:18:14,478 INFO Saving best model at Epoch 11 +2025-04-19 11:18:53,130 INFO Epoch:12 train_loss:0.31653 +2025-04-19 11:19:04,284 INFO Epoch:12 val_res:0.560500 +2025-04-19 11:19:04,285 INFO Saving best model at Epoch 12 +2025-04-19 11:19:42,765 INFO Epoch:13 train_loss:0.29607 +2025-04-19 11:19:54,422 INFO Epoch:13 val_res:0.560250 +2025-04-19 11:20:32,186 INFO Epoch:14 train_loss:0.25890 +2025-04-19 11:20:43,983 INFO Epoch:14 val_res:0.564750 +2025-04-19 11:20:43,983 INFO Saving best model at Epoch 14 +2025-04-19 11:21:21,848 INFO Epoch:15 train_loss:0.25800 +2025-04-19 11:21:33,392 INFO Epoch:15 val_res:0.561000 +2025-04-19 11:22:09,692 INFO Epoch:16 train_loss:0.25106 +2025-04-19 11:22:21,348 INFO Epoch:16 val_res:0.566000 +2025-04-19 11:22:21,348 INFO Saving best model at Epoch 16 +2025-04-19 11:23:00,258 INFO Epoch:17 train_loss:0.28392 +2025-04-19 11:23:11,912 INFO Epoch:17 val_res:0.566000 +2025-04-19 11:23:48,761 INFO Epoch:18 train_loss:0.26241 +2025-04-19 11:24:00,733 INFO Epoch:18 val_res:0.569750 +2025-04-19 11:24:00,734 INFO Saving best model at Epoch 18 +2025-04-19 11:24:38,575 INFO Epoch:19 train_loss:0.21786 +2025-04-19 11:24:50,097 INFO Epoch:19 val_res:0.571000 +2025-04-19 11:24:50,097 INFO Saving best model at Epoch 19 +2025-04-19 11:25:27,341 INFO Epoch:20 train_loss:0.22981 +2025-04-19 11:25:38,898 INFO Epoch:20 val_res:0.567750 +2025-04-19 11:26:14,299 INFO Epoch:21 train_loss:0.22014 +2025-04-19 11:26:25,931 INFO Epoch:21 val_res:0.572750 +2025-04-19 11:26:25,932 INFO Saving best model at Epoch 21 +2025-04-19 11:27:03,209 INFO Epoch:22 train_loss:0.21603 +2025-04-19 11:27:14,552 INFO Epoch:22 val_res:0.570250 +2025-04-19 11:27:49,334 INFO Epoch:23 train_loss:0.21967 +2025-04-19 11:28:00,951 INFO Epoch:23 val_res:0.576250 +2025-04-19 11:28:00,951 INFO Saving best model at Epoch 23 +2025-04-19 11:28:38,220 INFO Epoch:24 train_loss:0.20034 +2025-04-19 11:28:49,826 INFO Epoch:24 val_res:0.576750 +2025-04-19 11:28:49,827 INFO Saving best model at Epoch 24 +2025-04-19 11:29:26,532 INFO Epoch:25 train_loss:0.20002 +2025-04-19 11:29:38,220 INFO Epoch:25 val_res:0.577500 +2025-04-19 11:29:38,220 INFO Saving best model at Epoch 25 +2025-04-19 11:30:15,111 INFO Epoch:26 train_loss:0.19509 +2025-04-19 11:30:26,671 INFO Epoch:26 val_res:0.581250 +2025-04-19 11:30:26,672 INFO Saving best model at Epoch 26 +2025-04-19 11:31:03,364 INFO Epoch:27 train_loss:0.20693 +2025-04-19 11:31:15,088 INFO Epoch:27 val_res:0.574750 +2025-04-19 11:31:49,394 INFO Epoch:28 train_loss:0.24738 +2025-04-19 11:32:01,283 INFO Epoch:28 val_res:0.575750 +2025-04-19 11:32:36,235 INFO Epoch:29 train_loss:0.24141 +2025-04-19 11:32:47,925 INFO Epoch:29 val_res:0.580750 +2025-04-19 11:33:22,697 INFO Epoch:30 train_loss:0.19104 +2025-04-19 11:33:34,469 INFO Epoch:30 val_res:0.587500 +2025-04-19 11:33:34,469 INFO Saving best model at Epoch 30 +2025-04-19 11:34:10,943 INFO Epoch:31 train_loss:0.17622 +2025-04-19 11:34:22,655 INFO Epoch:31 val_res:0.585000 +2025-04-19 11:34:58,151 INFO Epoch:32 train_loss:0.15792 +2025-04-19 11:35:09,892 INFO Epoch:32 val_res:0.587000 +2025-04-19 11:35:44,656 INFO Epoch:33 train_loss:0.16063 +2025-04-19 11:35:56,606 INFO Epoch:33 val_res:0.588750 +2025-04-19 11:35:56,606 INFO Saving best model at Epoch 33 +2025-04-19 11:36:33,986 INFO Epoch:34 train_loss:0.16576 +2025-04-19 11:36:45,526 INFO Epoch:34 val_res:0.590000 +2025-04-19 11:36:45,526 INFO Saving best model at Epoch 34 +2025-04-19 11:37:23,126 INFO Epoch:35 train_loss:0.15685 +2025-04-19 11:37:34,701 INFO Epoch:35 val_res:0.589250 +2025-04-19 11:38:09,922 INFO Epoch:36 train_loss:0.17673 +2025-04-19 11:38:21,823 INFO Epoch:36 val_res:0.592000 +2025-04-19 11:38:21,824 INFO Saving best model at Epoch 36 +2025-04-19 11:38:58,530 INFO Epoch:37 train_loss:0.16353 +2025-04-19 11:39:10,107 INFO Epoch:37 val_res:0.591500 +2025-04-19 11:39:45,484 INFO Epoch:38 train_loss:0.16294 +2025-04-19 11:39:57,623 INFO Epoch:38 val_res:0.598000 +2025-04-19 11:39:57,624 INFO Saving best model at Epoch 38 +2025-04-19 11:40:34,839 INFO Epoch:39 train_loss:0.15320 +2025-04-19 11:40:46,538 INFO Epoch:39 val_res:0.599750 +2025-04-19 11:40:46,539 INFO Saving best model at Epoch 39 +2025-04-19 11:41:22,916 INFO Epoch:40 train_loss:0.12862 +2025-04-19 11:41:34,587 INFO Epoch:40 val_res:0.600000 +2025-04-19 11:41:34,587 INFO Saving best model at Epoch 40 +2025-04-19 11:42:11,806 INFO Epoch:41 train_loss:0.13963 +2025-04-19 11:42:23,396 INFO Epoch:41 val_res:0.596500 +2025-04-19 11:42:58,930 INFO Epoch:42 train_loss:0.18104 +2025-04-19 11:43:10,565 INFO Epoch:42 val_res:0.602000 +2025-04-19 11:43:10,566 INFO Saving best model at Epoch 42 +2025-04-19 11:43:47,951 INFO Epoch:43 train_loss:0.19197 +2025-04-19 11:43:59,693 INFO Epoch:43 val_res:0.600500 +2025-04-19 11:44:35,463 INFO Epoch:44 train_loss:0.14773 +2025-04-19 11:44:47,158 INFO Epoch:44 val_res:0.603250 +2025-04-19 11:44:47,158 INFO Saving best model at Epoch 44 +2025-04-19 11:45:24,601 INFO Epoch:45 train_loss:0.11861 +2025-04-19 11:45:36,210 INFO Epoch:45 val_res:0.604250 +2025-04-19 11:45:36,210 INFO Saving best model at Epoch 45 +2025-04-19 11:46:13,472 INFO Epoch:46 train_loss:0.11748 +2025-04-19 11:46:24,954 INFO Epoch:46 val_res:0.604500 +2025-04-19 11:46:24,954 INFO Saving best model at Epoch 46 +2025-04-19 11:47:01,803 INFO Epoch:47 train_loss:0.12853 +2025-04-19 11:47:13,334 INFO Epoch:47 val_res:0.602750 +2025-04-19 11:47:48,220 INFO Epoch:48 train_loss:0.16354 +2025-04-19 11:47:59,990 INFO Epoch:48 val_res:0.603750 +2025-04-19 11:48:35,945 INFO Epoch:49 train_loss:0.12158 +2025-04-19 11:48:47,742 INFO Epoch:49 val_res:0.606000 +2025-04-19 11:48:47,742 INFO Saving best model at Epoch 49 +2025-04-19 11:49:24,893 INFO Epoch:50 train_loss:0.12292 +2025-04-19 11:49:36,762 INFO Epoch:50 val_res:0.606250 +2025-04-19 11:49:36,762 INFO Saving best model at Epoch 50 +2025-04-19 11:50:13,818 INFO Epoch:51 train_loss:0.13726 +2025-04-19 11:50:25,553 INFO Epoch:51 val_res:0.603500 +2025-04-19 11:51:00,407 INFO Epoch:52 train_loss:0.13425 +2025-04-19 11:51:12,144 INFO Epoch:52 val_res:0.601750 +2025-04-19 11:51:48,000 INFO Epoch:53 train_loss:0.16996 +2025-04-19 11:51:59,577 INFO Epoch:53 val_res:0.605500 +2025-04-19 11:52:34,399 INFO Epoch:54 train_loss:0.13916 +2025-04-19 11:52:46,215 INFO Epoch:54 val_res:0.608500 +2025-04-19 11:52:46,216 INFO Saving best model at Epoch 54 +2025-04-19 11:53:23,333 INFO Epoch:55 train_loss:0.11845 +2025-04-19 11:53:35,076 INFO Epoch:55 val_res:0.608500 +2025-04-19 11:54:10,341 INFO Epoch:56 train_loss:0.13609 +2025-04-19 11:54:22,242 INFO Epoch:56 val_res:0.607250 +2025-04-19 11:54:57,292 INFO Epoch:57 train_loss:0.13328 +2025-04-19 11:55:09,115 INFO Epoch:57 val_res:0.610000 +2025-04-19 11:55:09,115 INFO Saving best model at Epoch 57 +2025-04-19 11:55:46,037 INFO Epoch:58 train_loss:0.12370 +2025-04-19 11:55:57,673 INFO Epoch:58 val_res:0.609500 +2025-04-19 11:56:33,094 INFO Epoch:59 train_loss:0.12267 +2025-04-19 11:56:44,792 INFO Epoch:59 val_res:0.609750 +2025-04-19 11:57:20,537 INFO Epoch:60 train_loss:0.11459 +2025-04-19 11:57:32,080 INFO Epoch:60 val_res:0.607500 +2025-04-19 11:58:07,567 INFO Epoch:61 train_loss:0.15088 +2025-04-19 11:58:18,813 INFO Epoch:61 val_res:0.609000 +2025-04-19 11:58:54,782 INFO Epoch:62 train_loss:0.14404 +2025-04-19 11:59:06,021 INFO Epoch:62 val_res:0.608500 +2025-04-19 11:59:41,910 INFO Epoch:63 train_loss:0.11853 +2025-04-19 11:59:53,107 INFO Epoch:63 val_res:0.610250 +2025-04-19 11:59:53,107 INFO Saving best model at Epoch 63 +2025-04-19 12:00:29,963 INFO Epoch:64 train_loss:0.11575 +2025-04-19 12:00:41,526 INFO Epoch:64 val_res:0.607750 +2025-04-19 12:01:16,994 INFO Epoch:65 train_loss:0.10067 +2025-04-19 12:01:28,455 INFO Epoch:65 val_res:0.612000 +2025-04-19 12:01:28,456 INFO Saving best model at Epoch 65 +2025-04-19 12:02:06,080 INFO Epoch:66 train_loss:0.10137 +2025-04-19 12:02:17,766 INFO Epoch:66 val_res:0.609000 +2025-04-19 12:02:52,601 INFO Epoch:67 train_loss:0.10746 +2025-04-19 12:03:04,396 INFO Epoch:67 val_res:0.611500 +2025-04-19 12:03:39,346 INFO Epoch:68 train_loss:0.13187 +2025-04-19 12:03:51,175 INFO Epoch:68 val_res:0.609250 +2025-04-19 12:04:26,490 INFO Epoch:69 train_loss:0.18628 +2025-04-19 12:04:38,334 INFO Epoch:69 val_res:0.607500 +2025-04-19 12:05:12,732 INFO Epoch:70 train_loss:0.20192 +2025-04-19 12:05:24,115 INFO Epoch:70 val_res:0.609500 +2025-04-19 12:05:59,061 INFO Epoch:71 train_loss:0.17294 +2025-04-19 12:06:10,666 INFO Epoch:71 val_res:0.608500 +2025-04-19 12:06:45,173 INFO Epoch:72 train_loss:0.11183 +2025-04-19 12:06:57,134 INFO Epoch:72 val_res:0.610250 +2025-04-19 12:07:32,802 INFO Epoch:73 train_loss:0.08769 +2025-04-19 12:07:44,705 INFO Epoch:73 val_res:0.607750 +2025-04-19 12:08:18,746 INFO Epoch:74 train_loss:0.07858 +2025-04-19 12:08:30,590 INFO Epoch:74 val_res:0.609750 +2025-04-19 12:09:05,096 INFO Epoch:75 train_loss:0.08413 +2025-04-19 12:09:16,896 INFO Epoch:75 val_res:0.614250 +2025-04-19 12:09:16,897 INFO Saving best model at Epoch 75 +2025-04-19 12:09:52,653 INFO Epoch:76 train_loss:0.09231 +2025-04-19 12:10:04,338 INFO Epoch:76 val_res:0.613000 +2025-04-19 12:10:38,967 INFO Epoch:77 train_loss:0.09486 +2025-04-19 12:10:50,816 INFO Epoch:77 val_res:0.610250 +2025-04-19 12:11:25,627 INFO Epoch:78 train_loss:0.12077 +2025-04-19 12:11:37,172 INFO Epoch:78 val_res:0.606000 +2025-04-19 12:12:11,880 INFO Epoch:79 train_loss:0.12153 +2025-04-19 12:12:23,629 INFO Epoch:79 val_res:0.608250 +2025-04-19 12:12:58,094 INFO Epoch:80 train_loss:0.09416 +2025-04-19 12:13:09,711 INFO Epoch:80 val_res:0.609500 +2025-04-19 12:13:44,752 INFO Epoch:81 train_loss:0.11527 +2025-04-19 12:13:56,293 INFO Epoch:81 val_res:0.605250 +2025-04-19 12:14:30,829 INFO Epoch:82 train_loss:0.13251 +2025-04-19 12:14:42,234 INFO Epoch:82 val_res:0.610000 +2025-04-19 12:15:17,416 INFO Epoch:83 train_loss:0.11710 +2025-04-19 12:15:28,980 INFO Epoch:83 val_res:0.610000 +2025-04-19 12:16:04,226 INFO Epoch:84 train_loss:0.12754 +2025-04-19 12:16:16,043 INFO Epoch:84 val_res:0.606000 +2025-04-19 12:16:51,900 INFO Epoch:85 train_loss:0.09283 +2025-04-19 12:17:03,708 INFO Epoch:85 val_res:0.606750 +2025-04-19 12:17:39,367 INFO Epoch:86 train_loss:0.09167 +2025-04-19 12:17:51,011 INFO Epoch:86 val_res:0.610000 +2025-04-19 12:18:26,244 INFO Epoch:87 train_loss:0.07505 +2025-04-19 12:18:37,979 INFO Epoch:87 val_res:0.611000 +2025-04-19 12:19:13,315 INFO Epoch:88 train_loss:0.07419 +2025-04-19 12:19:24,835 INFO Epoch:88 val_res:0.609750 +2025-04-19 12:20:00,128 INFO Epoch:89 train_loss:0.08589 +2025-04-19 12:20:11,927 INFO Epoch:89 val_res:0.607250 +2025-04-19 12:20:47,836 INFO Epoch:90 train_loss:0.15072 +2025-04-19 12:20:59,712 INFO Epoch:90 val_res:0.603750 +2025-04-19 12:21:33,799 INFO Epoch:91 train_loss:0.16666 +2025-04-19 12:21:45,378 INFO Epoch:91 val_res:0.602750 +2025-04-19 12:22:21,374 INFO Epoch:92 train_loss:0.12433 +2025-04-19 12:22:33,223 INFO Epoch:92 val_res:0.607500 +2025-04-19 12:23:08,507 INFO Epoch:93 train_loss:0.10462 +2025-04-19 12:23:20,362 INFO Epoch:93 val_res:0.606000 +2025-04-19 12:23:55,818 INFO Epoch:94 train_loss:0.11355 +2025-04-19 12:24:07,526 INFO Epoch:94 val_res:0.608250 +2025-04-19 12:24:43,347 INFO Epoch:95 train_loss:0.08358 +2025-04-19 12:24:55,078 INFO Epoch:95 val_res:0.606250 +2025-04-19 12:25:30,658 INFO Epoch:96 train_loss:0.10104 +2025-04-19 12:25:42,337 INFO Epoch:96 val_res:0.608000 +2025-04-19 12:26:16,671 INFO Epoch:97 train_loss:0.09954 +2025-04-19 12:26:28,338 INFO Epoch:97 val_res:0.606750 +2025-04-19 12:27:03,408 INFO Epoch:98 train_loss:0.10357 +2025-04-19 12:27:15,100 INFO Epoch:98 val_res:0.601250 +2025-04-19 12:27:50,933 INFO Epoch:99 train_loss:0.10837 +2025-04-19 12:28:02,987 INFO Epoch:99 val_res:0.608750 +2025-04-19 12:28:03,889 INFO ===================================== +2025-04-19 12:28:03,890 INFO Start testing... +2025-04-19 12:28:03,890 INFO ===================================== +2025-04-19 12:28:16,308 INFO Incremental step 7 Testing res: 0.606250 +2025-04-19 12:28:16,311 INFO forgetting: 0.092571 +2025-04-19 12:28:16,315 INFO ***************New Step*************************** +2025-04-19 12:28:16,316 INFO Incremental step: 8 +2025-04-19 12:28:16,511 INFO actual size of exemplar set: 1440 +2025-04-19 12:28:48,887 INFO Epoch:0 train_loss:3.21865 +2025-04-19 12:29:03,516 INFO Epoch:0 val_res:0.527333 +2025-04-19 12:29:03,517 INFO Saving best model at Epoch 0 +2025-04-19 12:29:36,129 INFO Epoch:1 train_loss:0.72751 +2025-04-19 12:29:49,544 INFO Epoch:1 val_res:0.541333 +2025-04-19 12:29:49,545 INFO Saving best model at Epoch 1 +2025-04-19 12:30:21,170 INFO Epoch:2 train_loss:0.40917 +2025-04-19 12:30:34,542 INFO Epoch:2 val_res:0.545778 +2025-04-19 12:30:34,542 INFO Saving best model at Epoch 2 +2025-04-19 12:31:06,548 INFO Epoch:3 train_loss:0.32952 +2025-04-19 12:31:19,297 INFO Epoch:3 val_res:0.544444 +2025-04-19 12:31:50,283 INFO Epoch:4 train_loss:0.29679 +2025-04-19 12:32:02,804 INFO Epoch:4 val_res:0.545778 +2025-04-19 12:32:33,322 INFO Epoch:5 train_loss:0.27518 +2025-04-19 12:32:45,824 INFO Epoch:5 val_res:0.546000 +2025-04-19 12:32:45,825 INFO Saving best model at Epoch 5 +2025-04-19 12:33:18,178 INFO Epoch:6 train_loss:0.25860 +2025-04-19 12:33:30,799 INFO Epoch:6 val_res:0.548222 +2025-04-19 12:33:30,800 INFO Saving best model at Epoch 6 +2025-04-19 12:34:03,713 INFO Epoch:7 train_loss:0.24215 +2025-04-19 12:34:16,475 INFO Epoch:7 val_res:0.549333 +2025-04-19 12:34:16,476 INFO Saving best model at Epoch 7 +2025-04-19 12:34:48,697 INFO Epoch:8 train_loss:0.23081 +2025-04-19 12:35:01,174 INFO Epoch:8 val_res:0.550444 +2025-04-19 12:35:01,175 INFO Saving best model at Epoch 8 +2025-04-19 12:35:33,425 INFO Epoch:9 train_loss:0.22375 +2025-04-19 12:35:46,216 INFO Epoch:9 val_res:0.551111 +2025-04-19 12:35:46,217 INFO Saving best model at Epoch 9 +2025-04-19 12:36:18,141 INFO Epoch:10 train_loss:0.21476 +2025-04-19 12:36:30,719 INFO Epoch:10 val_res:0.550222 +2025-04-19 12:37:00,881 INFO Epoch:11 train_loss:0.21087 +2025-04-19 12:37:13,685 INFO Epoch:11 val_res:0.554667 +2025-04-19 12:37:13,685 INFO Saving best model at Epoch 11 +2025-04-19 12:37:45,623 INFO Epoch:12 train_loss:0.20859 +2025-04-19 12:37:58,379 INFO Epoch:12 val_res:0.552889 +2025-04-19 12:38:28,542 INFO Epoch:13 train_loss:0.20599 +2025-04-19 12:38:41,105 INFO Epoch:13 val_res:0.552222 +2025-04-19 12:39:10,832 INFO Epoch:14 train_loss:0.24376 +2025-04-19 12:39:23,277 INFO Epoch:14 val_res:0.556222 +2025-04-19 12:39:23,278 INFO Saving best model at Epoch 14 +2025-04-19 12:39:54,949 INFO Epoch:15 train_loss:0.21307 +2025-04-19 12:40:07,300 INFO Epoch:15 val_res:0.557333 +2025-04-19 12:40:07,301 INFO Saving best model at Epoch 15 +2025-04-19 12:40:39,649 INFO Epoch:16 train_loss:0.21022 +2025-04-19 12:40:51,937 INFO Epoch:16 val_res:0.556222 +2025-04-19 12:41:22,207 INFO Epoch:17 train_loss:0.21159 +2025-04-19 12:41:34,833 INFO Epoch:17 val_res:0.558889 +2025-04-19 12:41:34,834 INFO Saving best model at Epoch 17 +2025-04-19 12:42:06,946 INFO Epoch:18 train_loss:0.18721 +2025-04-19 12:42:19,565 INFO Epoch:18 val_res:0.559333 +2025-04-19 12:42:19,565 INFO Saving best model at Epoch 18 +2025-04-19 12:42:51,654 INFO Epoch:19 train_loss:0.19940 +2025-04-19 12:43:04,292 INFO Epoch:19 val_res:0.558889 +2025-04-19 12:43:34,223 INFO Epoch:20 train_loss:0.24020 +2025-04-19 12:43:46,999 INFO Epoch:20 val_res:0.562000 +2025-04-19 12:43:46,999 INFO Saving best model at Epoch 20 +2025-04-19 12:44:18,612 INFO Epoch:21 train_loss:0.21442 +2025-04-19 12:44:31,425 INFO Epoch:21 val_res:0.564667 +2025-04-19 12:44:31,425 INFO Saving best model at Epoch 21 +2025-04-19 12:45:03,673 INFO Epoch:22 train_loss:0.20435 +2025-04-19 12:45:16,364 INFO Epoch:22 val_res:0.561111 +2025-04-19 12:45:46,314 INFO Epoch:23 train_loss:0.19601 +2025-04-19 12:45:58,938 INFO Epoch:23 val_res:0.567556 +2025-04-19 12:45:58,939 INFO Saving best model at Epoch 23 +2025-04-19 12:46:30,611 INFO Epoch:24 train_loss:0.16773 +2025-04-19 12:46:43,321 INFO Epoch:24 val_res:0.567778 +2025-04-19 12:46:43,321 INFO Saving best model at Epoch 24 +2025-04-19 12:47:14,350 INFO Epoch:25 train_loss:0.16188 +2025-04-19 12:47:27,019 INFO Epoch:25 val_res:0.567556 +2025-04-19 12:47:57,105 INFO Epoch:26 train_loss:0.15741 +2025-04-19 12:48:09,778 INFO Epoch:26 val_res:0.567556 +2025-04-19 12:48:39,936 INFO Epoch:27 train_loss:0.17715 +2025-04-19 12:48:52,509 INFO Epoch:27 val_res:0.564222 +2025-04-19 12:49:22,465 INFO Epoch:28 train_loss:0.19961 +2025-04-19 12:49:35,126 INFO Epoch:28 val_res:0.562000 +2025-04-19 12:50:05,221 INFO Epoch:29 train_loss:0.16479 +2025-04-19 12:50:17,970 INFO Epoch:29 val_res:0.573111 +2025-04-19 12:50:17,970 INFO Saving best model at Epoch 29 +2025-04-19 12:50:49,795 INFO Epoch:30 train_loss:0.14623 +2025-04-19 12:51:02,475 INFO Epoch:30 val_res:0.578000 +2025-04-19 12:51:02,476 INFO Saving best model at Epoch 30 +2025-04-19 12:51:34,194 INFO Epoch:31 train_loss:0.14417 +2025-04-19 12:51:46,812 INFO Epoch:31 val_res:0.574000 +2025-04-19 12:52:16,912 INFO Epoch:32 train_loss:0.19132 +2025-04-19 12:52:29,563 INFO Epoch:32 val_res:0.569556 +2025-04-19 12:52:59,650 INFO Epoch:33 train_loss:0.20611 +2025-04-19 12:53:12,181 INFO Epoch:33 val_res:0.572889 +2025-04-19 12:53:42,519 INFO Epoch:34 train_loss:0.16276 +2025-04-19 12:53:55,025 INFO Epoch:34 val_res:0.576889 +2025-04-19 12:54:25,307 INFO Epoch:35 train_loss:0.15892 +2025-04-19 12:54:37,616 INFO Epoch:35 val_res:0.574000 +2025-04-19 12:55:07,420 INFO Epoch:36 train_loss:0.17144 +2025-04-19 12:55:19,964 INFO Epoch:36 val_res:0.572667 +2025-04-19 12:55:50,126 INFO Epoch:37 train_loss:0.13361 +2025-04-19 12:56:02,763 INFO Epoch:37 val_res:0.577111 +2025-04-19 12:56:32,667 INFO Epoch:38 train_loss:0.12366 +2025-04-19 12:56:45,039 INFO Epoch:38 val_res:0.576667 +2025-04-19 12:57:14,521 INFO Epoch:39 train_loss:0.13411 +2025-04-19 12:57:27,067 INFO Epoch:39 val_res:0.577333 +2025-04-19 12:57:57,272 INFO Epoch:40 train_loss:0.13455 +2025-04-19 12:58:09,783 INFO Epoch:40 val_res:0.575333 +2025-04-19 12:58:40,277 INFO Epoch:41 train_loss:0.13943 +2025-04-19 12:58:52,713 INFO Epoch:41 val_res:0.577778 +2025-04-19 12:59:22,994 INFO Epoch:42 train_loss:0.12311 +2025-04-19 12:59:35,412 INFO Epoch:42 val_res:0.579333 +2025-04-19 12:59:35,413 INFO Saving best model at Epoch 42 +2025-04-19 13:00:06,767 INFO Epoch:43 train_loss:0.14204 +2025-04-19 13:00:19,309 INFO Epoch:43 val_res:0.576222 +2025-04-19 13:00:49,319 INFO Epoch:44 train_loss:0.22146 +2025-04-19 13:01:01,667 INFO Epoch:44 val_res:0.578667 +2025-04-19 13:01:30,827 INFO Epoch:45 train_loss:0.14909 +2025-04-19 13:01:43,469 INFO Epoch:45 val_res:0.576222 +2025-04-19 13:02:13,484 INFO Epoch:46 train_loss:0.11632 +2025-04-19 13:02:26,191 INFO Epoch:46 val_res:0.576889 +2025-04-19 13:02:55,764 INFO Epoch:47 train_loss:0.10886 +2025-04-19 13:03:08,352 INFO Epoch:47 val_res:0.579333 +2025-04-19 13:03:37,418 INFO Epoch:48 train_loss:0.14366 +2025-04-19 13:03:50,084 INFO Epoch:48 val_res:0.579556 +2025-04-19 13:03:50,084 INFO Saving best model at Epoch 48 +2025-04-19 13:04:21,473 INFO Epoch:49 train_loss:0.17897 +2025-04-19 13:04:34,077 INFO Epoch:49 val_res:0.581111 +2025-04-19 13:04:34,077 INFO Saving best model at Epoch 49 +2025-04-19 13:05:05,232 INFO Epoch:50 train_loss:0.15877 +2025-04-19 13:05:17,745 INFO Epoch:50 val_res:0.582222 +2025-04-19 13:05:17,745 INFO Saving best model at Epoch 50 +2025-04-19 13:05:48,736 INFO Epoch:51 train_loss:0.11918 +2025-04-19 13:06:01,289 INFO Epoch:51 val_res:0.578889 +2025-04-19 13:06:30,188 INFO Epoch:52 train_loss:0.11979 +2025-04-19 13:06:42,662 INFO Epoch:52 val_res:0.577778 +2025-04-19 13:07:11,256 INFO Epoch:53 train_loss:0.12375 +2025-04-19 13:07:23,844 INFO Epoch:53 val_res:0.578889 +2025-04-19 13:07:52,594 INFO Epoch:54 train_loss:0.11086 +2025-04-19 13:08:05,386 INFO Epoch:54 val_res:0.580000 +2025-04-19 13:08:34,334 INFO Epoch:55 train_loss:0.11901 +2025-04-19 13:08:47,074 INFO Epoch:55 val_res:0.576444 +2025-04-19 13:09:16,722 INFO Epoch:56 train_loss:0.11560 +2025-04-19 13:09:29,445 INFO Epoch:56 val_res:0.577111 +2025-04-19 13:09:58,174 INFO Epoch:57 train_loss:0.11018 +2025-04-19 13:10:10,806 INFO Epoch:57 val_res:0.575111 +2025-04-19 13:10:39,809 INFO Epoch:58 train_loss:0.09600 +2025-04-19 13:10:52,459 INFO Epoch:58 val_res:0.576222 +2025-04-19 13:11:21,569 INFO Epoch:59 train_loss:0.08694 +2025-04-19 13:11:34,090 INFO Epoch:59 val_res:0.578000 +2025-04-19 13:12:03,184 INFO Epoch:60 train_loss:0.11276 +2025-04-19 13:12:15,574 INFO Epoch:60 val_res:0.575111 +2025-04-19 13:12:44,611 INFO Epoch:61 train_loss:0.17303 +2025-04-19 13:12:57,085 INFO Epoch:61 val_res:0.573778 +2025-04-19 13:13:26,127 INFO Epoch:62 train_loss:0.85531 +2025-04-19 13:13:38,571 INFO Epoch:62 val_res:0.557111 +2025-04-19 13:14:07,609 INFO Epoch:63 train_loss:0.78267 +2025-04-19 13:14:20,319 INFO Epoch:63 val_res:0.567111 +2025-04-19 13:14:49,435 INFO Epoch:64 train_loss:0.29424 +2025-04-19 13:15:02,025 INFO Epoch:64 val_res:0.573556 +2025-04-19 13:15:30,873 INFO Epoch:65 train_loss:0.15254 +2025-04-19 13:15:43,419 INFO Epoch:65 val_res:0.572000 +2025-04-19 13:16:11,840 INFO Epoch:66 train_loss:0.10747 +2025-04-19 13:16:24,257 INFO Epoch:66 val_res:0.574667 +2025-04-19 13:16:52,874 INFO Epoch:67 train_loss:0.08884 +2025-04-19 13:17:04,974 INFO Epoch:67 val_res:0.572889 +2025-04-19 13:17:33,441 INFO Epoch:68 train_loss:0.07972 +2025-04-19 13:17:45,794 INFO Epoch:68 val_res:0.572000 +2025-04-19 13:18:15,022 INFO Epoch:69 train_loss:0.07343 +2025-04-19 13:18:27,240 INFO Epoch:69 val_res:0.568667 +2025-04-19 13:18:56,331 INFO Epoch:70 train_loss:0.07139 +2025-04-19 13:19:08,452 INFO Epoch:70 val_res:0.572222 +2025-04-19 13:19:37,412 INFO Epoch:71 train_loss:0.06889 +2025-04-19 13:19:49,552 INFO Epoch:71 val_res:0.568444 +2025-04-19 13:20:18,885 INFO Epoch:72 train_loss:0.06880 +2025-04-19 13:20:30,892 INFO Epoch:72 val_res:0.570667 +2025-04-19 13:20:59,475 INFO Epoch:73 train_loss:0.06978 +2025-04-19 13:21:11,609 INFO Epoch:73 val_res:0.569111 +2025-04-19 13:21:40,823 INFO Epoch:74 train_loss:0.06794 +2025-04-19 13:21:53,093 INFO Epoch:74 val_res:0.566667 +2025-04-19 13:22:22,466 INFO Epoch:75 train_loss:0.06653 +2025-04-19 13:22:34,798 INFO Epoch:75 val_res:0.566444 +2025-04-19 13:23:04,114 INFO Epoch:76 train_loss:0.06608 +2025-04-19 13:23:16,493 INFO Epoch:76 val_res:0.567778 +2025-04-19 13:23:45,713 INFO Epoch:77 train_loss:0.06379 +2025-04-19 13:23:58,140 INFO Epoch:77 val_res:0.567778 +2025-04-19 13:24:26,827 INFO Epoch:78 train_loss:0.06920 +2025-04-19 13:24:39,154 INFO Epoch:78 val_res:0.567333 +2025-04-19 13:25:08,496 INFO Epoch:79 train_loss:0.09499 +2025-04-19 13:25:20,890 INFO Epoch:79 val_res:0.564889 +2025-04-19 13:25:49,702 INFO Epoch:80 train_loss:0.13717 +2025-04-19 13:26:01,883 INFO Epoch:80 val_res:0.564222 +2025-04-19 13:26:30,354 INFO Epoch:81 train_loss:0.10948 +2025-04-19 13:26:43,000 INFO Epoch:81 val_res:0.565333 +2025-04-19 13:27:12,040 INFO Epoch:82 train_loss:0.09425 +2025-04-19 13:27:24,507 INFO Epoch:82 val_res:0.561333 +2025-04-19 13:27:52,970 INFO Epoch:83 train_loss:0.10915 +2025-04-19 13:28:05,396 INFO Epoch:83 val_res:0.563778 +2025-04-19 13:28:34,246 INFO Epoch:84 train_loss:0.13157 +2025-04-19 13:28:46,800 INFO Epoch:84 val_res:0.556889 +2025-04-19 13:29:15,500 INFO Epoch:85 train_loss:0.10448 +2025-04-19 13:29:28,020 INFO Epoch:85 val_res:0.558222 +2025-04-19 13:29:57,869 INFO Epoch:86 train_loss:0.07784 +2025-04-19 13:30:10,309 INFO Epoch:86 val_res:0.561556 +2025-04-19 13:30:39,472 INFO Epoch:87 train_loss:0.08940 +2025-04-19 13:30:52,012 INFO Epoch:87 val_res:0.561333 +2025-04-19 13:31:21,582 INFO Epoch:88 train_loss:0.08442 +2025-04-19 13:31:34,142 INFO Epoch:88 val_res:0.555556 +2025-04-19 13:32:03,498 INFO Epoch:89 train_loss:0.09437 +2025-04-19 13:32:16,371 INFO Epoch:89 val_res:0.557778 +2025-04-19 13:32:45,271 INFO Epoch:90 train_loss:0.09099 +2025-04-19 13:32:58,089 INFO Epoch:90 val_res:0.555111 +2025-04-19 13:33:27,011 INFO Epoch:91 train_loss:0.08067 +2025-04-19 13:33:39,969 INFO Epoch:91 val_res:0.560444 +2025-04-19 13:34:08,104 INFO Epoch:92 train_loss:0.16854 +2025-04-19 13:34:21,010 INFO Epoch:92 val_res:0.556889 +2025-04-19 13:34:49,147 INFO Epoch:93 train_loss:0.13365 +2025-04-19 13:35:01,897 INFO Epoch:93 val_res:0.552222 +2025-04-19 13:35:29,942 INFO Epoch:94 train_loss:0.09565 +2025-04-19 13:35:42,709 INFO Epoch:94 val_res:0.552444 +2025-04-19 13:36:11,532 INFO Epoch:95 train_loss:0.08167 +2025-04-19 13:36:24,122 INFO Epoch:95 val_res:0.549333 +2025-04-19 13:36:52,429 INFO Epoch:96 train_loss:0.07650 +2025-04-19 13:37:05,099 INFO Epoch:96 val_res:0.553556 +2025-04-19 13:37:33,467 INFO Epoch:97 train_loss:0.08561 +2025-04-19 13:37:46,524 INFO Epoch:97 val_res:0.546889 +2025-04-19 13:38:16,548 INFO Epoch:98 train_loss:0.08989 +2025-04-19 13:38:29,167 INFO Epoch:98 val_res:0.549778 +2025-04-19 13:38:58,408 INFO Epoch:99 train_loss:0.11735 +2025-04-19 13:39:11,128 INFO Epoch:99 val_res:0.543333 +2025-04-19 13:39:11,858 INFO ===================================== +2025-04-19 13:39:11,860 INFO Start testing... +2025-04-19 13:39:11,860 INFO ===================================== +2025-04-19 13:39:24,916 INFO Incremental step 8 Testing res: 0.574444 +2025-04-19 13:39:24,920 INFO forgetting: 0.103500 +2025-04-19 13:39:24,924 INFO ***************New Step*************************** +2025-04-19 13:39:24,924 INFO Incremental step: 9 +2025-04-19 13:39:25,089 INFO actual size of exemplar set: 1440 +2025-04-19 13:39:59,525 INFO Epoch:0 train_loss:3.26241 +2025-04-19 13:40:14,023 INFO Epoch:0 val_res:0.511200 +2025-04-19 13:40:14,024 INFO Saving best model at Epoch 0 +2025-04-19 13:40:50,639 INFO Epoch:1 train_loss:0.57438 +2025-04-19 13:41:04,356 INFO Epoch:1 val_res:0.529400 +2025-04-19 13:41:04,357 INFO Saving best model at Epoch 1 +2025-04-19 13:41:38,702 INFO Epoch:2 train_loss:0.31510 +2025-04-19 13:41:52,243 INFO Epoch:2 val_res:0.530600 +2025-04-19 13:41:52,244 INFO Saving best model at Epoch 2 +2025-04-19 13:42:27,219 INFO Epoch:3 train_loss:0.25728 +2025-04-19 13:42:40,974 INFO Epoch:3 val_res:0.533800 +2025-04-19 13:42:40,975 INFO Saving best model at Epoch 3 +2025-04-19 13:43:14,636 INFO Epoch:4 train_loss:0.22776 +2025-04-19 13:43:28,387 INFO Epoch:4 val_res:0.535800 +2025-04-19 13:43:28,388 INFO Saving best model at Epoch 4 +2025-04-19 13:44:02,148 INFO Epoch:5 train_loss:0.20948 +2025-04-19 13:44:16,067 INFO Epoch:5 val_res:0.535200 +2025-04-19 13:44:48,878 INFO Epoch:6 train_loss:0.19528 +2025-04-19 13:45:02,550 INFO Epoch:6 val_res:0.537800 +2025-04-19 13:45:02,550 INFO Saving best model at Epoch 6 +2025-04-19 13:45:36,294 INFO Epoch:7 train_loss:0.18571 +2025-04-19 13:45:49,763 INFO Epoch:7 val_res:0.540400 +2025-04-19 13:45:49,763 INFO Saving best model at Epoch 7 +2025-04-19 13:46:24,848 INFO Epoch:8 train_loss:0.17639 +2025-04-19 13:46:38,494 INFO Epoch:8 val_res:0.539800 +2025-04-19 13:47:12,713 INFO Epoch:9 train_loss:0.16970 +2025-04-19 13:47:26,316 INFO Epoch:9 val_res:0.539000 +2025-04-19 13:47:59,257 INFO Epoch:10 train_loss:0.16367 +2025-04-19 13:48:12,830 INFO Epoch:10 val_res:0.542400 +2025-04-19 13:48:12,831 INFO Saving best model at Epoch 10 +2025-04-19 13:48:47,874 INFO Epoch:11 train_loss:0.15527 +2025-04-19 13:49:01,445 INFO Epoch:11 val_res:0.543200 +2025-04-19 13:49:01,445 INFO Saving best model at Epoch 11 +2025-04-19 13:49:36,176 INFO Epoch:12 train_loss:0.19801 +2025-04-19 13:49:50,070 INFO Epoch:12 val_res:0.539800 +2025-04-19 13:50:22,861 INFO Epoch:13 train_loss:0.20540 +2025-04-19 13:50:36,692 INFO Epoch:13 val_res:0.542400 +2025-04-19 13:51:09,104 INFO Epoch:14 train_loss:0.16147 +2025-04-19 13:51:23,019 INFO Epoch:14 val_res:0.541800 +2025-04-19 13:51:55,421 INFO Epoch:15 train_loss:0.15563 +2025-04-19 13:52:09,235 INFO Epoch:15 val_res:0.543600 +2025-04-19 13:52:09,236 INFO Saving best model at Epoch 15 +2025-04-19 13:52:43,342 INFO Epoch:16 train_loss:0.17691 +2025-04-19 13:52:56,924 INFO Epoch:16 val_res:0.545800 +2025-04-19 13:52:56,924 INFO Saving best model at Epoch 16 +2025-04-19 13:53:31,552 INFO Epoch:17 train_loss:0.17625 +2025-04-19 13:53:45,211 INFO Epoch:17 val_res:0.544000 +2025-04-19 13:54:17,619 INFO Epoch:18 train_loss:0.15324 +2025-04-19 13:54:31,402 INFO Epoch:18 val_res:0.544000 +2025-04-19 13:55:03,522 INFO Epoch:19 train_loss:0.14808 +2025-04-19 13:55:17,088 INFO Epoch:19 val_res:0.543800 +2025-04-19 13:55:50,289 INFO Epoch:20 train_loss:0.18855 +2025-04-19 13:56:03,846 INFO Epoch:20 val_res:0.545400 +2025-04-19 13:56:35,944 INFO Epoch:21 train_loss:0.23009 +2025-04-19 13:56:49,568 INFO Epoch:21 val_res:0.544800 +2025-04-19 13:57:22,217 INFO Epoch:22 train_loss:0.25469 +2025-04-19 13:57:35,968 INFO Epoch:22 val_res:0.546600 +2025-04-19 13:57:35,974 INFO Saving best model at Epoch 22 +2025-04-19 13:58:09,424 INFO Epoch:23 train_loss:0.16561 +2025-04-19 13:58:23,126 INFO Epoch:23 val_res:0.551800 +2025-04-19 13:58:23,126 INFO Saving best model at Epoch 23 +2025-04-19 13:58:57,510 INFO Epoch:24 train_loss:0.12661 +2025-04-19 13:59:11,317 INFO Epoch:24 val_res:0.553800 +2025-04-19 13:59:11,318 INFO Saving best model at Epoch 24 +2025-04-19 13:59:44,948 INFO Epoch:25 train_loss:0.11635 +2025-04-19 13:59:58,954 INFO Epoch:25 val_res:0.553000 +2025-04-19 14:00:31,737 INFO Epoch:26 train_loss:0.11238 +2025-04-19 14:00:45,459 INFO Epoch:26 val_res:0.552200 +2025-04-19 14:01:17,647 INFO Epoch:27 train_loss:0.11735 +2025-04-19 14:01:31,497 INFO Epoch:27 val_res:0.553800 +2025-04-19 14:02:04,119 INFO Epoch:28 train_loss:0.17734 +2025-04-19 14:02:17,939 INFO Epoch:28 val_res:0.553800 +2025-04-19 14:02:50,260 INFO Epoch:29 train_loss:0.20529 +2025-04-19 14:03:04,323 INFO Epoch:29 val_res:0.556200 +2025-04-19 14:03:04,324 INFO Saving best model at Epoch 29 +2025-04-19 14:03:38,040 INFO Epoch:30 train_loss:0.14248 +2025-04-19 14:03:51,895 INFO Epoch:30 val_res:0.556600 +2025-04-19 14:03:51,895 INFO Saving best model at Epoch 30 +2025-04-19 14:04:25,454 INFO Epoch:31 train_loss:0.11738 +2025-04-19 14:04:39,324 INFO Epoch:31 val_res:0.555800 +2025-04-19 14:05:12,242 INFO Epoch:32 train_loss:0.11733 +2025-04-19 14:05:26,132 INFO Epoch:32 val_res:0.557800 +2025-04-19 14:05:26,133 INFO Saving best model at Epoch 32 +2025-04-19 14:05:59,642 INFO Epoch:33 train_loss:0.22963 +2025-04-19 14:06:13,514 INFO Epoch:33 val_res:0.558000 +2025-04-19 14:06:13,514 INFO Saving best model at Epoch 33 +2025-04-19 14:06:48,122 INFO Epoch:34 train_loss:0.21967 +2025-04-19 14:07:01,666 INFO Epoch:34 val_res:0.558400 +2025-04-19 14:07:01,667 INFO Saving best model at Epoch 34 +2025-04-19 14:07:35,095 INFO Epoch:35 train_loss:0.13877 +2025-04-19 14:07:48,805 INFO Epoch:35 val_res:0.560800 +2025-04-19 14:07:48,805 INFO Saving best model at Epoch 35 +2025-04-19 14:08:22,660 INFO Epoch:36 train_loss:0.11344 +2025-04-19 14:08:36,422 INFO Epoch:36 val_res:0.562200 +2025-04-19 14:08:36,422 INFO Saving best model at Epoch 36 +2025-04-19 14:09:10,261 INFO Epoch:37 train_loss:0.10735 +2025-04-19 14:09:24,087 INFO Epoch:37 val_res:0.560600 +2025-04-19 14:09:56,058 INFO Epoch:38 train_loss:0.10553 +2025-04-19 14:10:09,628 INFO Epoch:38 val_res:0.564400 +2025-04-19 14:10:09,629 INFO Saving best model at Epoch 38 +2025-04-19 14:10:44,066 INFO Epoch:39 train_loss:0.10838 +2025-04-19 14:10:57,606 INFO Epoch:39 val_res:0.563200 +2025-04-19 14:11:30,608 INFO Epoch:40 train_loss:0.12140 +2025-04-19 14:11:44,209 INFO Epoch:40 val_res:0.563800 +2025-04-19 14:12:16,954 INFO Epoch:41 train_loss:0.10352 +2025-04-19 14:12:30,533 INFO Epoch:41 val_res:0.566200 +2025-04-19 14:12:30,534 INFO Saving best model at Epoch 41 +2025-04-19 14:13:04,163 INFO Epoch:42 train_loss:0.10398 +2025-04-19 14:13:17,692 INFO Epoch:42 val_res:0.564400 +2025-04-19 14:13:50,907 INFO Epoch:43 train_loss:0.23249 +2025-04-19 14:14:04,356 INFO Epoch:43 val_res:0.557400 +2025-04-19 14:14:37,460 INFO Epoch:44 train_loss:0.28725 +2025-04-19 14:14:50,796 INFO Epoch:44 val_res:0.557400 +2025-04-19 14:15:23,134 INFO Epoch:45 train_loss:0.70074 +2025-04-19 14:15:36,486 INFO Epoch:45 val_res:0.560000 +2025-04-19 14:16:09,876 INFO Epoch:46 train_loss:0.23985 +2025-04-19 14:16:23,370 INFO Epoch:46 val_res:0.559600 +2025-04-19 14:16:55,331 INFO Epoch:47 train_loss:0.12535 +2025-04-19 14:17:08,877 INFO Epoch:47 val_res:0.570600 +2025-04-19 14:17:08,877 INFO Saving best model at Epoch 47 +2025-04-19 14:17:43,277 INFO Epoch:48 train_loss:0.09222 +2025-04-19 14:17:56,721 INFO Epoch:48 val_res:0.566000 +2025-04-19 14:18:29,702 INFO Epoch:49 train_loss:0.08281 +2025-04-19 14:18:43,256 INFO Epoch:49 val_res:0.566600 +2025-04-19 14:19:16,702 INFO Epoch:50 train_loss:0.07952 +2025-04-19 14:19:30,252 INFO Epoch:50 val_res:0.566000 +2025-04-19 14:20:02,691 INFO Epoch:51 train_loss:0.07638 +2025-04-19 14:20:16,177 INFO Epoch:51 val_res:0.566800 +2025-04-19 14:20:49,240 INFO Epoch:52 train_loss:0.07802 +2025-04-19 14:21:02,808 INFO Epoch:52 val_res:0.565200 +2025-04-19 14:21:35,378 INFO Epoch:53 train_loss:0.07325 +2025-04-19 14:21:48,996 INFO Epoch:53 val_res:0.569200 +2025-04-19 14:22:22,117 INFO Epoch:54 train_loss:0.07233 +2025-04-19 14:22:35,617 INFO Epoch:54 val_res:0.567200 +2025-04-19 14:23:08,397 INFO Epoch:55 train_loss:0.07598 +2025-04-19 14:23:21,955 INFO Epoch:55 val_res:0.568000 +2025-04-19 14:23:53,999 INFO Epoch:56 train_loss:0.07806 +2025-04-19 14:24:07,694 INFO Epoch:56 val_res:0.569600 +2025-04-19 14:24:39,471 INFO Epoch:57 train_loss:0.08712 +2025-04-19 14:24:52,994 INFO Epoch:57 val_res:0.567000 +2025-04-19 14:25:24,826 INFO Epoch:58 train_loss:0.10305 +2025-04-19 14:25:38,524 INFO Epoch:58 val_res:0.568200 +2025-04-19 14:26:09,909 INFO Epoch:59 train_loss:0.09704 +2025-04-19 14:26:23,682 INFO Epoch:59 val_res:0.566400 +2025-04-19 14:26:55,577 INFO Epoch:60 train_loss:0.11940 +2025-04-19 14:27:09,022 INFO Epoch:60 val_res:0.559600 +2025-04-19 14:27:40,779 INFO Epoch:61 train_loss:0.13575 +2025-04-19 14:27:54,326 INFO Epoch:61 val_res:0.565800 +2025-04-19 14:28:25,951 INFO Epoch:62 train_loss:0.13857 +2025-04-19 14:28:39,354 INFO Epoch:62 val_res:0.565600 +2025-04-19 14:29:11,426 INFO Epoch:63 train_loss:0.18488 +2025-04-19 14:29:24,686 INFO Epoch:63 val_res:0.565600 +2025-04-19 14:29:58,287 INFO Epoch:64 train_loss:0.19362 +2025-04-19 14:30:11,599 INFO Epoch:64 val_res:0.563800 +2025-04-19 14:30:43,553 INFO Epoch:65 train_loss:0.11949 +2025-04-19 14:30:56,949 INFO Epoch:65 val_res:0.565200 +2025-04-19 14:31:29,583 INFO Epoch:66 train_loss:0.09197 +2025-04-19 14:31:43,065 INFO Epoch:66 val_res:0.563800 +2025-04-19 14:32:15,385 INFO Epoch:67 train_loss:0.08650 +2025-04-19 14:32:28,795 INFO Epoch:67 val_res:0.567200 +2025-04-19 14:33:01,909 INFO Epoch:68 train_loss:0.09598 +2025-04-19 14:33:15,258 INFO Epoch:68 val_res:0.561800 +2025-04-19 14:33:47,280 INFO Epoch:69 train_loss:0.11081 +2025-04-19 14:34:00,637 INFO Epoch:69 val_res:0.561400 +2025-04-19 14:34:32,597 INFO Epoch:70 train_loss:0.15029 +2025-04-19 14:34:45,976 INFO Epoch:70 val_res:0.564400 +2025-04-19 14:35:18,216 INFO Epoch:71 train_loss:0.10291 +2025-04-19 14:35:31,750 INFO Epoch:71 val_res:0.565800 +2025-04-19 14:36:03,956 INFO Epoch:72 train_loss:0.10651 +2025-04-19 14:36:17,624 INFO Epoch:72 val_res:0.561200 +2025-04-19 14:36:51,045 INFO Epoch:73 train_loss:0.10681 +2025-04-19 14:37:04,638 INFO Epoch:73 val_res:0.562600 +2025-04-19 14:37:38,213 INFO Epoch:74 train_loss:0.08519 +2025-04-19 14:37:51,803 INFO Epoch:74 val_res:0.563200 +2025-04-19 14:38:24,039 INFO Epoch:75 train_loss:0.08236 +2025-04-19 14:38:37,526 INFO Epoch:75 val_res:0.560800 +2025-04-19 14:39:09,458 INFO Epoch:76 train_loss:0.08204 +2025-04-19 14:39:23,061 INFO Epoch:76 val_res:0.558000 +2025-04-19 14:39:54,821 INFO Epoch:77 train_loss:0.12269 +2025-04-19 14:40:08,389 INFO Epoch:77 val_res:0.562800 +2025-04-19 14:40:40,311 INFO Epoch:78 train_loss:0.13419 +2025-04-19 14:40:54,170 INFO Epoch:78 val_res:0.561200 +2025-04-19 14:41:27,212 INFO Epoch:79 train_loss:0.13170 +2025-04-19 14:41:41,032 INFO Epoch:79 val_res:0.561400 +2025-04-19 14:42:13,102 INFO Epoch:80 train_loss:0.11715 +2025-04-19 14:42:26,852 INFO Epoch:80 val_res:0.557600 +2025-04-19 14:42:57,622 INFO Epoch:81 train_loss:0.11977 +2025-04-19 14:43:11,296 INFO Epoch:81 val_res:0.557600 +2025-04-19 14:43:44,123 INFO Epoch:82 train_loss:0.09900 +2025-04-19 14:43:58,080 INFO Epoch:82 val_res:0.559800 +2025-04-19 14:44:30,340 INFO Epoch:83 train_loss:0.08743 +2025-04-19 14:44:44,185 INFO Epoch:83 val_res:0.558200 +2025-04-19 14:45:15,848 INFO Epoch:84 train_loss:0.09916 +2025-04-19 14:45:29,534 INFO Epoch:84 val_res:0.557400 +2025-04-19 14:46:00,958 INFO Epoch:85 train_loss:0.09851 +2025-04-19 14:46:14,738 INFO Epoch:85 val_res:0.558400 +2025-04-19 14:46:46,443 INFO Epoch:86 train_loss:0.10210 +2025-04-19 14:47:00,155 INFO Epoch:86 val_res:0.556800 +2025-04-19 14:47:32,048 INFO Epoch:87 train_loss:0.10577 +2025-04-19 14:47:45,572 INFO Epoch:87 val_res:0.556000 +2025-04-19 14:48:18,302 INFO Epoch:88 train_loss:0.10259 +2025-04-19 14:48:31,846 INFO Epoch:88 val_res:0.559800 +2025-04-19 14:49:03,939 INFO Epoch:89 train_loss:0.12093 +2025-04-19 14:49:17,523 INFO Epoch:89 val_res:0.552600 +2025-04-19 14:49:50,491 INFO Epoch:90 train_loss:0.15582 +2025-04-19 14:50:03,861 INFO Epoch:90 val_res:0.558600 +2025-04-19 14:50:35,983 INFO Epoch:91 train_loss:0.12942 +2025-04-19 14:50:49,379 INFO Epoch:91 val_res:0.553400 +2025-04-19 14:51:22,725 INFO Epoch:92 train_loss:0.11268 +2025-04-19 14:51:36,056 INFO Epoch:92 val_res:0.552200 +2025-04-19 14:52:09,548 INFO Epoch:93 train_loss:0.09220 +2025-04-19 14:52:22,979 INFO Epoch:93 val_res:0.553200 +2025-04-19 14:52:55,115 INFO Epoch:94 train_loss:0.07475 +2025-04-19 14:53:08,353 INFO Epoch:94 val_res:0.554800 +2025-04-19 14:53:40,029 INFO Epoch:95 train_loss:0.09959 +2025-04-19 14:53:53,407 INFO Epoch:95 val_res:0.551000 +2025-04-19 14:54:25,237 INFO Epoch:96 train_loss:0.13349 +2025-04-19 14:54:38,689 INFO Epoch:96 val_res:0.552800 +2025-04-19 14:55:11,549 INFO Epoch:97 train_loss:0.09536 +2025-04-19 14:55:25,187 INFO Epoch:97 val_res:0.557600 +2025-04-19 14:55:57,198 INFO Epoch:98 train_loss:0.13716 +2025-04-19 14:56:10,839 INFO Epoch:98 val_res:0.551600 +2025-04-19 14:56:42,780 INFO Epoch:99 train_loss:0.14961 +2025-04-19 14:56:56,120 INFO Epoch:99 val_res:0.547800 +2025-04-19 14:56:56,799 INFO ===================================== +2025-04-19 14:56:56,800 INFO Start testing... +2025-04-19 14:56:56,800 INFO ===================================== +2025-04-19 14:57:11,612 INFO Incremental step 9 Testing res: 0.561600 +2025-04-19 14:57:11,649 INFO forgetting: 0.099333 +2025-04-19 14:57:11,652 INFO Average Accuracy: 0.681528 +2025-04-19 14:57:11,653 INFO Average Forgetting: 0.093667 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..121de621c814be9e63d5cc8914431a720def79b0 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..32f3c713e218cc29784b12129462480b277cdbc2 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..d826f3f06eedecdffa24da9e7a8e53e7e9cda61b Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..8e7fc58e46c6243d89cc9ccc0534103dbe6eefca Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..a01014f0aa8b9c3e0c6424153d86e60db1043da8 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_5.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..a60262a5a60e58d8110f6290403e70bb6d5d250b Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_5.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_6.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..71179b53e5d1c2260478c460bb552d6517aeace2 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_6.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_7.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..f4ad6c487e8f90bab16f78ea78075304a0e8c199 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_7.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_8.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..1b84f20678a2805ec6cfd03af7e39230d82bda35 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_8.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_9.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..25c8ca7d874e850f4744c662b90c09f08697c4cb Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_9.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..4b6a471af95785951a68340446480d85e9348901 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..96edec803c4880db1d5d2a83670f937f02a88746 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..3b87d55fa29f3b780ef8498ef4bed56c2a1fa7a5 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..58451f1140ad7a49a504bb51a6c0cc2e9607d0f9 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..7e4f7f57efceba62e884590bc44a0283fd53e302 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_5.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..ade7cf9776774411b371d734704e531942f6964e Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_5.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_6.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..e37aff5650aa1762d0ab440796af1d3c23eb8f52 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_6.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_7.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..c0310c1a2f283887f66664cd8cd05384ed272819 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_7.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_8.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..7ce2ca71f0e9742c610fb8ff8771a3ea887bd8d0 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_8.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_9.png b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..21c67a734eca89f73756b50c94dcf4f1a88e84dc Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_9.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..6c74dcc8010aef9c4790847235278064f8d8d032 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ac205b1083de10574013800e7ba289a701261794087e1176ce3dcef8243ba7f +size 114142801 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..5ac41f253d68286007b96ec9e285b3456441191e --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:352ac2edf58af025be0ddb1fcfa834efc4c17a9ca5b117c37110a7c27e7c41f4 +size 114235217 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..e1c0f9e4df7596448ccae271affb631af9be7f63 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99ab349136adad9cfef7e37a325e831ccb2ff83187f73d6b0503a17565bad3c8 +size 114327377 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..dae9b5b992f86b6f50db0b90adb42bd6b55a2b52 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88988f8eea18860acc21702d56fdcf4c51c66e8ae7435fe9d9553323652647e2 +size 114419729 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a2a0e7f0126830ca76afe2a6fb0079cf69c8e94d --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e69c57cb52cb47ec24656cb1b42248e15c08c85ba0ef7c99c7c5193ffdb839e +size 114512081 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_5_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_5_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8263b6aafb828e0fcd798cfed94c5b40d7b47aaf --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_5_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358c91d9015d23ccd31bd0363e65e52c9aa9d3636b22475430da78a99b14eb56 +size 114604241 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_6_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_6_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..cc2ca81196fc3ed34bd0838c0aa2de39f040cdba --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_6_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b35d515e372f007dae83dffa5e7bccbf7bf629bf880f6657818a8272f964f377 +size 114696593 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_7_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_7_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f1aeba82cb41e558214f66a3bb8d5fa17e5b8adf --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_7_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e9c2fc6f58772b14f8e19ebd265e5e7edc4efc2c3e6820d36ebb7c283032218 +size 114788945 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_8_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_8_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..32f899bd1c66eb4f88eb96da16efc01fb86ce7e6 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_8_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be44c8d9b60347c83e0665e11e8a3a6e525abe90d482bb5eb68c82d28deefd28 +size 114881105 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_9_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_9_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9ab8a2a6a610800ebc3bca2d74252dccec1ead32 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/step_9_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:647812a7c5a6ac574ff7c653cfdf50d8b71d99639ce9b6b00e91d6869566d787 +size 114973457 diff --git a/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/train.log b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..f69127d4e4445509f1119093aa50e7ba39e9b6bc --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/VGGSound_100/audio-visual/use-inverse_True-seed_0/train.log @@ -0,0 +1,2342 @@ +2025-04-19 03:52:32,689 INFO Namespace(class_num_per_step=10, dataset='VGGSound_100', e_prompt=False, exemplar_batch_size=128, fixed_fc=False, infer_batch_size=128, inverse=True, inverse_ends=100, inverse_starts=0, lr=0.001, lr_decay=False, max_epoches=100, memory_size=1500, milestones=[100], modality='audio-visual', num_classes=100, num_workers=4, prompt_dim=768, seed=0, train_batch_size=256, weight_decay=0.0001) +2025-04-19 03:52:32,690 INFO Training start time: 2025-04-19 03:52:32.690292 +2025-04-19 03:52:33,791 INFO ***************New Step*************************** +2025-04-19 03:52:33,791 INFO Incremental step: 0 +2025-04-19 03:53:01,495 INFO Epoch:0 train_loss:4.69850 +2025-04-19 03:53:04,850 INFO Epoch:0 val_res:0.638000 +2025-04-19 03:53:04,850 INFO Saving best model at Epoch 0 +2025-04-19 03:53:22,942 INFO Epoch:1 train_loss:2.58967 +2025-04-19 03:53:25,485 INFO Epoch:1 val_res:0.736000 +2025-04-19 03:53:25,485 INFO Saving best model at Epoch 1 +2025-04-19 03:53:42,632 INFO Epoch:2 train_loss:1.83897 +2025-04-19 03:53:45,057 INFO Epoch:2 val_res:0.772000 +2025-04-19 03:53:45,057 INFO Saving best model at Epoch 2 +2025-04-19 03:54:01,749 INFO Epoch:3 train_loss:1.48839 +2025-04-19 03:54:04,180 INFO Epoch:3 val_res:0.810000 +2025-04-19 03:54:04,180 INFO Saving best model at Epoch 3 +2025-04-19 03:54:20,815 INFO Epoch:4 train_loss:1.28018 +2025-04-19 03:54:23,302 INFO Epoch:4 val_res:0.796000 +2025-04-19 03:54:37,739 INFO Epoch:5 train_loss:1.10023 +2025-04-19 03:54:40,152 INFO Epoch:5 val_res:0.832000 +2025-04-19 03:54:40,152 INFO Saving best model at Epoch 5 +2025-04-19 03:54:56,316 INFO Epoch:6 train_loss:0.97515 +2025-04-19 03:54:58,803 INFO Epoch:6 val_res:0.806000 +2025-04-19 03:55:14,037 INFO Epoch:7 train_loss:0.90431 +2025-04-19 03:55:16,520 INFO Epoch:7 val_res:0.838000 +2025-04-19 03:55:16,520 INFO Saving best model at Epoch 7 +2025-04-19 03:55:32,608 INFO Epoch:8 train_loss:0.81770 +2025-04-19 03:55:34,963 INFO Epoch:8 val_res:0.882000 +2025-04-19 03:55:34,963 INFO Saving best model at Epoch 8 +2025-04-19 03:55:51,650 INFO Epoch:9 train_loss:0.75651 +2025-04-19 03:55:54,086 INFO Epoch:9 val_res:0.854000 +2025-04-19 03:56:09,034 INFO Epoch:10 train_loss:0.73253 +2025-04-19 03:56:11,526 INFO Epoch:10 val_res:0.874000 +2025-04-19 03:56:26,637 INFO Epoch:11 train_loss:0.68636 +2025-04-19 03:56:29,233 INFO Epoch:11 val_res:0.866000 +2025-04-19 03:56:44,233 INFO Epoch:12 train_loss:0.62404 +2025-04-19 03:56:46,643 INFO Epoch:12 val_res:0.884000 +2025-04-19 03:56:46,643 INFO Saving best model at Epoch 12 +2025-04-19 03:57:02,950 INFO Epoch:13 train_loss:0.60010 +2025-04-19 03:57:05,374 INFO Epoch:13 val_res:0.886000 +2025-04-19 03:57:05,375 INFO Saving best model at Epoch 13 +2025-04-19 03:57:21,978 INFO Epoch:14 train_loss:0.58130 +2025-04-19 03:57:24,351 INFO Epoch:14 val_res:0.884000 +2025-04-19 03:57:39,064 INFO Epoch:15 train_loss:0.60677 +2025-04-19 03:57:41,633 INFO Epoch:15 val_res:0.890000 +2025-04-19 03:57:41,633 INFO Saving best model at Epoch 15 +2025-04-19 03:57:58,029 INFO Epoch:16 train_loss:0.54145 +2025-04-19 03:58:00,436 INFO Epoch:16 val_res:0.892000 +2025-04-19 03:58:00,437 INFO Saving best model at Epoch 16 +2025-04-19 03:58:17,370 INFO Epoch:17 train_loss:0.51491 +2025-04-19 03:58:19,835 INFO Epoch:17 val_res:0.862000 +2025-04-19 03:58:34,388 INFO Epoch:18 train_loss:0.49799 +2025-04-19 03:58:36,930 INFO Epoch:18 val_res:0.876000 +2025-04-19 03:58:52,024 INFO Epoch:19 train_loss:0.49946 +2025-04-19 03:58:54,512 INFO Epoch:19 val_res:0.886000 +2025-04-19 03:59:09,341 INFO Epoch:20 train_loss:0.50830 +2025-04-19 03:59:11,912 INFO Epoch:20 val_res:0.866000 +2025-04-19 03:59:26,308 INFO Epoch:21 train_loss:0.49284 +2025-04-19 03:59:28,852 INFO Epoch:21 val_res:0.876000 +2025-04-19 03:59:43,868 INFO Epoch:22 train_loss:0.44909 +2025-04-19 03:59:46,409 INFO Epoch:22 val_res:0.892000 +2025-04-19 04:00:01,221 INFO Epoch:23 train_loss:0.44394 +2025-04-19 04:00:03,718 INFO Epoch:23 val_res:0.896000 +2025-04-19 04:00:03,719 INFO Saving best model at Epoch 23 +2025-04-19 04:00:19,366 INFO Epoch:24 train_loss:0.44805 +2025-04-19 04:00:21,668 INFO Epoch:24 val_res:0.884000 +2025-04-19 04:00:35,576 INFO Epoch:25 train_loss:0.45124 +2025-04-19 04:00:38,047 INFO Epoch:25 val_res:0.882000 +2025-04-19 04:00:52,281 INFO Epoch:26 train_loss:0.43462 +2025-04-19 04:00:54,611 INFO Epoch:26 val_res:0.880000 +2025-04-19 04:01:08,917 INFO Epoch:27 train_loss:0.41681 +2025-04-19 04:01:11,386 INFO Epoch:27 val_res:0.892000 +2025-04-19 04:01:26,258 INFO Epoch:28 train_loss:0.40709 +2025-04-19 04:01:28,554 INFO Epoch:28 val_res:0.888000 +2025-04-19 04:01:42,816 INFO Epoch:29 train_loss:0.39074 +2025-04-19 04:01:45,044 INFO Epoch:29 val_res:0.900000 +2025-04-19 04:01:45,044 INFO Saving best model at Epoch 29 +2025-04-19 04:02:01,023 INFO Epoch:30 train_loss:0.41238 +2025-04-19 04:02:03,336 INFO Epoch:30 val_res:0.900000 +2025-04-19 04:02:17,677 INFO Epoch:31 train_loss:0.38307 +2025-04-19 04:02:20,030 INFO Epoch:31 val_res:0.892000 +2025-04-19 04:02:35,013 INFO Epoch:32 train_loss:0.39658 +2025-04-19 04:02:37,255 INFO Epoch:32 val_res:0.898000 +2025-04-19 04:02:51,853 INFO Epoch:33 train_loss:0.39254 +2025-04-19 04:02:54,224 INFO Epoch:33 val_res:0.902000 +2025-04-19 04:02:54,225 INFO Saving best model at Epoch 33 +2025-04-19 04:03:10,761 INFO Epoch:34 train_loss:0.42492 +2025-04-19 04:03:13,086 INFO Epoch:34 val_res:0.916000 +2025-04-19 04:03:13,086 INFO Saving best model at Epoch 34 +2025-04-19 04:03:29,192 INFO Epoch:35 train_loss:0.41371 +2025-04-19 04:03:31,566 INFO Epoch:35 val_res:0.904000 +2025-04-19 04:03:45,663 INFO Epoch:36 train_loss:0.37637 +2025-04-19 04:03:48,017 INFO Epoch:36 val_res:0.886000 +2025-04-19 04:04:02,294 INFO Epoch:37 train_loss:0.36211 +2025-04-19 04:04:04,773 INFO Epoch:37 val_res:0.904000 +2025-04-19 04:04:18,590 INFO Epoch:38 train_loss:0.34272 +2025-04-19 04:04:21,097 INFO Epoch:38 val_res:0.886000 +2025-04-19 04:04:35,241 INFO Epoch:39 train_loss:0.34971 +2025-04-19 04:04:37,629 INFO Epoch:39 val_res:0.896000 +2025-04-19 04:04:51,953 INFO Epoch:40 train_loss:0.36951 +2025-04-19 04:04:54,408 INFO Epoch:40 val_res:0.882000 +2025-04-19 04:05:08,598 INFO Epoch:41 train_loss:0.34171 +2025-04-19 04:05:10,995 INFO Epoch:41 val_res:0.896000 +2025-04-19 04:05:25,140 INFO Epoch:42 train_loss:0.35856 +2025-04-19 04:05:27,606 INFO Epoch:42 val_res:0.892000 +2025-04-19 04:05:41,494 INFO Epoch:43 train_loss:0.34844 +2025-04-19 04:05:43,895 INFO Epoch:43 val_res:0.890000 +2025-04-19 04:05:58,229 INFO Epoch:44 train_loss:0.35791 +2025-04-19 04:06:00,615 INFO Epoch:44 val_res:0.884000 +2025-04-19 04:06:14,768 INFO Epoch:45 train_loss:0.34948 +2025-04-19 04:06:17,178 INFO Epoch:45 val_res:0.902000 +2025-04-19 04:06:31,194 INFO Epoch:46 train_loss:0.32567 +2025-04-19 04:06:33,585 INFO Epoch:46 val_res:0.890000 +2025-04-19 04:06:47,643 INFO Epoch:47 train_loss:0.35134 +2025-04-19 04:06:50,004 INFO Epoch:47 val_res:0.882000 +2025-04-19 04:07:03,751 INFO Epoch:48 train_loss:0.36675 +2025-04-19 04:07:06,252 INFO Epoch:48 val_res:0.894000 +2025-04-19 04:07:20,292 INFO Epoch:49 train_loss:0.32038 +2025-04-19 04:07:22,896 INFO Epoch:49 val_res:0.900000 +2025-04-19 04:07:36,916 INFO Epoch:50 train_loss:0.31806 +2025-04-19 04:07:39,375 INFO Epoch:50 val_res:0.900000 +2025-04-19 04:07:53,849 INFO Epoch:51 train_loss:0.32308 +2025-04-19 04:07:56,178 INFO Epoch:51 val_res:0.874000 +2025-04-19 04:08:10,358 INFO Epoch:52 train_loss:0.35599 +2025-04-19 04:08:12,820 INFO Epoch:52 val_res:0.860000 +2025-04-19 04:08:26,560 INFO Epoch:53 train_loss:0.33375 +2025-04-19 04:08:29,004 INFO Epoch:53 val_res:0.878000 +2025-04-19 04:08:42,927 INFO Epoch:54 train_loss:0.31814 +2025-04-19 04:08:45,329 INFO Epoch:54 val_res:0.862000 +2025-04-19 04:08:59,466 INFO Epoch:55 train_loss:0.28390 +2025-04-19 04:09:01,918 INFO Epoch:55 val_res:0.902000 +2025-04-19 04:09:15,827 INFO Epoch:56 train_loss:0.28009 +2025-04-19 04:09:18,271 INFO Epoch:56 val_res:0.898000 +2025-04-19 04:09:31,923 INFO Epoch:57 train_loss:0.33647 +2025-04-19 04:09:34,384 INFO Epoch:57 val_res:0.892000 +2025-04-19 04:09:48,290 INFO Epoch:58 train_loss:0.30808 +2025-04-19 04:09:50,624 INFO Epoch:58 val_res:0.890000 +2025-04-19 04:10:04,687 INFO Epoch:59 train_loss:0.34711 +2025-04-19 04:10:07,086 INFO Epoch:59 val_res:0.896000 +2025-04-19 04:10:21,126 INFO Epoch:60 train_loss:0.28023 +2025-04-19 04:10:23,343 INFO Epoch:60 val_res:0.896000 +2025-04-19 04:10:37,299 INFO Epoch:61 train_loss:0.26435 +2025-04-19 04:10:39,579 INFO Epoch:61 val_res:0.894000 +2025-04-19 04:10:53,703 INFO Epoch:62 train_loss:0.26862 +2025-04-19 04:10:56,091 INFO Epoch:62 val_res:0.904000 +2025-04-19 04:11:10,078 INFO Epoch:63 train_loss:0.26218 +2025-04-19 04:11:12,545 INFO Epoch:63 val_res:0.896000 +2025-04-19 04:11:26,638 INFO Epoch:64 train_loss:0.26562 +2025-04-19 04:11:29,060 INFO Epoch:64 val_res:0.888000 +2025-04-19 04:11:42,996 INFO Epoch:65 train_loss:0.28224 +2025-04-19 04:11:45,321 INFO Epoch:65 val_res:0.894000 +2025-04-19 04:11:59,496 INFO Epoch:66 train_loss:0.26929 +2025-04-19 04:12:01,892 INFO Epoch:66 val_res:0.890000 +2025-04-19 04:12:15,805 INFO Epoch:67 train_loss:0.27133 +2025-04-19 04:12:18,251 INFO Epoch:67 val_res:0.896000 +2025-04-19 04:12:32,325 INFO Epoch:68 train_loss:0.26373 +2025-04-19 04:12:34,732 INFO Epoch:68 val_res:0.888000 +2025-04-19 04:12:48,885 INFO Epoch:69 train_loss:0.28752 +2025-04-19 04:12:51,451 INFO Epoch:69 val_res:0.884000 +2025-04-19 04:13:05,392 INFO Epoch:70 train_loss:0.32106 +2025-04-19 04:13:07,829 INFO Epoch:70 val_res:0.902000 +2025-04-19 04:13:21,612 INFO Epoch:71 train_loss:0.27119 +2025-04-19 04:13:24,060 INFO Epoch:71 val_res:0.884000 +2025-04-19 04:13:37,871 INFO Epoch:72 train_loss:0.32411 +2025-04-19 04:13:40,355 INFO Epoch:72 val_res:0.890000 +2025-04-19 04:13:54,259 INFO Epoch:73 train_loss:0.28986 +2025-04-19 04:13:56,736 INFO Epoch:73 val_res:0.904000 +2025-04-19 04:14:10,414 INFO Epoch:74 train_loss:0.27798 +2025-04-19 04:14:12,919 INFO Epoch:74 val_res:0.892000 +2025-04-19 04:14:26,879 INFO Epoch:75 train_loss:0.28302 +2025-04-19 04:14:29,192 INFO Epoch:75 val_res:0.902000 +2025-04-19 04:14:43,258 INFO Epoch:76 train_loss:0.27505 +2025-04-19 04:14:45,514 INFO Epoch:76 val_res:0.890000 +2025-04-19 04:14:59,826 INFO Epoch:77 train_loss:0.25999 +2025-04-19 04:15:02,087 INFO Epoch:77 val_res:0.898000 +2025-04-19 04:15:15,816 INFO Epoch:78 train_loss:0.24845 +2025-04-19 04:15:18,248 INFO Epoch:78 val_res:0.896000 +2025-04-19 04:15:32,299 INFO Epoch:79 train_loss:0.23075 +2025-04-19 04:15:34,766 INFO Epoch:79 val_res:0.904000 +2025-04-19 04:15:48,643 INFO Epoch:80 train_loss:0.26098 +2025-04-19 04:15:51,069 INFO Epoch:80 val_res:0.908000 +2025-04-19 04:16:05,015 INFO Epoch:81 train_loss:0.29212 +2025-04-19 04:16:07,544 INFO Epoch:81 val_res:0.896000 +2025-04-19 04:16:21,541 INFO Epoch:82 train_loss:0.26345 +2025-04-19 04:16:23,884 INFO Epoch:82 val_res:0.894000 +2025-04-19 04:16:37,919 INFO Epoch:83 train_loss:0.26174 +2025-04-19 04:16:40,367 INFO Epoch:83 val_res:0.900000 +2025-04-19 04:16:54,530 INFO Epoch:84 train_loss:0.27028 +2025-04-19 04:16:56,916 INFO Epoch:84 val_res:0.896000 +2025-04-19 04:17:10,998 INFO Epoch:85 train_loss:0.25445 +2025-04-19 04:17:13,449 INFO Epoch:85 val_res:0.896000 +2025-04-19 04:17:27,634 INFO Epoch:86 train_loss:0.25605 +2025-04-19 04:17:30,062 INFO Epoch:86 val_res:0.898000 +2025-04-19 04:17:44,073 INFO Epoch:87 train_loss:0.24083 +2025-04-19 04:17:46,639 INFO Epoch:87 val_res:0.890000 +2025-04-19 04:18:00,479 INFO Epoch:88 train_loss:0.26304 +2025-04-19 04:18:03,058 INFO Epoch:88 val_res:0.890000 +2025-04-19 04:18:17,047 INFO Epoch:89 train_loss:0.25797 +2025-04-19 04:18:19,533 INFO Epoch:89 val_res:0.892000 +2025-04-19 04:18:33,411 INFO Epoch:90 train_loss:0.25487 +2025-04-19 04:18:35,864 INFO Epoch:90 val_res:0.908000 +2025-04-19 04:18:49,726 INFO Epoch:91 train_loss:0.22334 +2025-04-19 04:18:52,174 INFO Epoch:91 val_res:0.896000 +2025-04-19 04:19:06,420 INFO Epoch:92 train_loss:0.27843 +2025-04-19 04:19:08,762 INFO Epoch:92 val_res:0.874000 +2025-04-19 04:19:22,955 INFO Epoch:93 train_loss:0.31198 +2025-04-19 04:19:25,404 INFO Epoch:93 val_res:0.884000 +2025-04-19 04:19:39,632 INFO Epoch:94 train_loss:0.25994 +2025-04-19 04:19:42,033 INFO Epoch:94 val_res:0.902000 +2025-04-19 04:19:56,112 INFO Epoch:95 train_loss:0.23770 +2025-04-19 04:19:58,470 INFO Epoch:95 val_res:0.876000 +2025-04-19 04:20:12,436 INFO Epoch:96 train_loss:0.23043 +2025-04-19 04:20:14,739 INFO Epoch:96 val_res:0.874000 +2025-04-19 04:20:29,262 INFO Epoch:97 train_loss:0.26289 +2025-04-19 04:20:31,632 INFO Epoch:97 val_res:0.900000 +2025-04-19 04:20:45,914 INFO Epoch:98 train_loss:0.23072 +2025-04-19 04:20:48,310 INFO Epoch:98 val_res:0.872000 +2025-04-19 04:21:03,024 INFO Epoch:99 train_loss:0.23622 +2025-04-19 04:21:05,455 INFO Epoch:99 val_res:0.900000 +2025-04-19 04:21:06,165 INFO ===================================== +2025-04-19 04:21:06,166 INFO Start testing... +2025-04-19 04:21:06,166 INFO ===================================== +2025-04-19 04:21:14,182 INFO Incremental step 0 Testing res: 0.904000 +2025-04-19 04:21:14,186 INFO ***************New Step*************************** +2025-04-19 04:21:14,186 INFO Incremental step: 1 +2025-04-19 04:21:14,343 INFO actual size of exemplar set: 1449 +2025-04-19 04:22:04,844 INFO Epoch:0 train_loss:3.84080 +2025-04-19 04:22:09,291 INFO Epoch:0 val_res:0.473000 +2025-04-19 04:22:09,291 INFO Saving best model at Epoch 0 +2025-04-19 04:22:46,499 INFO Epoch:1 train_loss:2.03189 +2025-04-19 04:22:50,786 INFO Epoch:1 val_res:0.533000 +2025-04-19 04:22:50,787 INFO Saving best model at Epoch 1 +2025-04-19 04:23:23,959 INFO Epoch:2 train_loss:1.53901 +2025-04-19 04:23:27,832 INFO Epoch:2 val_res:0.575000 +2025-04-19 04:23:27,832 INFO Saving best model at Epoch 2 +2025-04-19 04:24:00,235 INFO Epoch:3 train_loss:1.31642 +2025-04-19 04:24:04,146 INFO Epoch:3 val_res:0.608000 +2025-04-19 04:24:04,147 INFO Saving best model at Epoch 3 +2025-04-19 04:24:38,072 INFO Epoch:4 train_loss:1.20263 +2025-04-19 04:24:41,993 INFO Epoch:4 val_res:0.628000 +2025-04-19 04:24:41,993 INFO Saving best model at Epoch 4 +2025-04-19 04:25:14,453 INFO Epoch:5 train_loss:1.11334 +2025-04-19 04:25:18,436 INFO Epoch:5 val_res:0.654000 +2025-04-19 04:25:18,436 INFO Saving best model at Epoch 5 +2025-04-19 04:25:51,041 INFO Epoch:6 train_loss:1.05004 +2025-04-19 04:25:54,849 INFO Epoch:6 val_res:0.665000 +2025-04-19 04:25:54,849 INFO Saving best model at Epoch 6 +2025-04-19 04:26:26,511 INFO Epoch:7 train_loss:0.98834 +2025-04-19 04:26:30,326 INFO Epoch:7 val_res:0.687000 +2025-04-19 04:26:30,327 INFO Saving best model at Epoch 7 +2025-04-19 04:27:04,307 INFO Epoch:8 train_loss:0.94211 +2025-04-19 04:27:08,189 INFO Epoch:8 val_res:0.703000 +2025-04-19 04:27:08,190 INFO Saving best model at Epoch 8 +2025-04-19 04:27:39,954 INFO Epoch:9 train_loss:0.89206 +2025-04-19 04:27:43,915 INFO Epoch:9 val_res:0.714000 +2025-04-19 04:27:43,915 INFO Saving best model at Epoch 9 +2025-04-19 04:28:15,081 INFO Epoch:10 train_loss:0.84562 +2025-04-19 04:28:18,733 INFO Epoch:10 val_res:0.731000 +2025-04-19 04:28:18,733 INFO Saving best model at Epoch 10 +2025-04-19 04:28:50,534 INFO Epoch:11 train_loss:0.82226 +2025-04-19 04:28:54,232 INFO Epoch:11 val_res:0.739000 +2025-04-19 04:28:54,233 INFO Saving best model at Epoch 11 +2025-04-19 04:29:26,756 INFO Epoch:12 train_loss:0.78475 +2025-04-19 04:29:30,679 INFO Epoch:12 val_res:0.741000 +2025-04-19 04:29:30,679 INFO Saving best model at Epoch 12 +2025-04-19 04:30:02,815 INFO Epoch:13 train_loss:0.74206 +2025-04-19 04:30:06,991 INFO Epoch:13 val_res:0.756000 +2025-04-19 04:30:06,991 INFO Saving best model at Epoch 13 +2025-04-19 04:30:39,444 INFO Epoch:14 train_loss:0.71234 +2025-04-19 04:30:43,716 INFO Epoch:14 val_res:0.765000 +2025-04-19 04:30:43,716 INFO Saving best model at Epoch 14 +2025-04-19 04:31:15,582 INFO Epoch:15 train_loss:0.68568 +2025-04-19 04:31:19,630 INFO Epoch:15 val_res:0.772000 +2025-04-19 04:31:19,630 INFO Saving best model at Epoch 15 +2025-04-19 04:31:50,842 INFO Epoch:16 train_loss:0.67214 +2025-04-19 04:31:54,554 INFO Epoch:16 val_res:0.780000 +2025-04-19 04:31:54,554 INFO Saving best model at Epoch 16 +2025-04-19 04:32:26,495 INFO Epoch:17 train_loss:0.63067 +2025-04-19 04:32:30,306 INFO Epoch:17 val_res:0.783000 +2025-04-19 04:32:30,307 INFO Saving best model at Epoch 17 +2025-04-19 04:33:03,997 INFO Epoch:18 train_loss:0.63405 +2025-04-19 04:33:07,882 INFO Epoch:18 val_res:0.794000 +2025-04-19 04:33:07,883 INFO Saving best model at Epoch 18 +2025-04-19 04:33:40,994 INFO Epoch:19 train_loss:0.64009 +2025-04-19 04:33:44,640 INFO Epoch:19 val_res:0.795000 +2025-04-19 04:33:44,640 INFO Saving best model at Epoch 19 +2025-04-19 04:34:17,132 INFO Epoch:20 train_loss:0.60936 +2025-04-19 04:34:20,784 INFO Epoch:20 val_res:0.802000 +2025-04-19 04:34:20,784 INFO Saving best model at Epoch 20 +2025-04-19 04:34:52,625 INFO Epoch:21 train_loss:0.57533 +2025-04-19 04:34:56,276 INFO Epoch:21 val_res:0.808000 +2025-04-19 04:34:56,276 INFO Saving best model at Epoch 21 +2025-04-19 04:35:29,098 INFO Epoch:22 train_loss:0.55841 +2025-04-19 04:35:32,769 INFO Epoch:22 val_res:0.808000 +2025-04-19 04:36:04,258 INFO Epoch:23 train_loss:0.54553 +2025-04-19 04:36:08,202 INFO Epoch:23 val_res:0.805000 +2025-04-19 04:36:38,578 INFO Epoch:24 train_loss:0.53641 +2025-04-19 04:36:42,357 INFO Epoch:24 val_res:0.806000 +2025-04-19 04:37:11,895 INFO Epoch:25 train_loss:0.53548 +2025-04-19 04:37:15,632 INFO Epoch:25 val_res:0.812000 +2025-04-19 04:37:15,632 INFO Saving best model at Epoch 25 +2025-04-19 04:37:47,173 INFO Epoch:26 train_loss:0.52124 +2025-04-19 04:37:51,104 INFO Epoch:26 val_res:0.817000 +2025-04-19 04:37:51,104 INFO Saving best model at Epoch 26 +2025-04-19 04:38:22,186 INFO Epoch:27 train_loss:0.51611 +2025-04-19 04:38:25,983 INFO Epoch:27 val_res:0.825000 +2025-04-19 04:38:25,983 INFO Saving best model at Epoch 27 +2025-04-19 04:38:57,643 INFO Epoch:28 train_loss:0.50364 +2025-04-19 04:39:01,682 INFO Epoch:28 val_res:0.825000 +2025-04-19 04:39:31,522 INFO Epoch:29 train_loss:0.51054 +2025-04-19 04:39:35,533 INFO Epoch:29 val_res:0.824000 +2025-04-19 04:40:05,313 INFO Epoch:30 train_loss:0.47705 +2025-04-19 04:40:09,181 INFO Epoch:30 val_res:0.826000 +2025-04-19 04:40:09,181 INFO Saving best model at Epoch 30 +2025-04-19 04:40:41,067 INFO Epoch:31 train_loss:0.49412 +2025-04-19 04:40:44,749 INFO Epoch:31 val_res:0.835000 +2025-04-19 04:40:44,750 INFO Saving best model at Epoch 31 +2025-04-19 04:41:16,886 INFO Epoch:32 train_loss:0.48445 +2025-04-19 04:41:20,681 INFO Epoch:32 val_res:0.829000 +2025-04-19 04:41:51,457 INFO Epoch:33 train_loss:0.45700 +2025-04-19 04:41:55,643 INFO Epoch:33 val_res:0.826000 +2025-04-19 04:42:25,468 INFO Epoch:34 train_loss:0.44234 +2025-04-19 04:42:29,240 INFO Epoch:34 val_res:0.830000 +2025-04-19 04:43:00,622 INFO Epoch:35 train_loss:0.43633 +2025-04-19 04:43:04,271 INFO Epoch:35 val_res:0.817000 +2025-04-19 04:43:35,465 INFO Epoch:36 train_loss:0.46526 +2025-04-19 04:43:39,246 INFO Epoch:36 val_res:0.824000 +2025-04-19 04:44:09,629 INFO Epoch:37 train_loss:0.46742 +2025-04-19 04:44:13,240 INFO Epoch:37 val_res:0.835000 +2025-04-19 04:44:43,769 INFO Epoch:38 train_loss:0.44530 +2025-04-19 04:44:47,349 INFO Epoch:38 val_res:0.827000 +2025-04-19 04:45:17,150 INFO Epoch:39 train_loss:0.43196 +2025-04-19 04:45:20,854 INFO Epoch:39 val_res:0.823000 +2025-04-19 04:45:51,134 INFO Epoch:40 train_loss:0.44140 +2025-04-19 04:45:54,920 INFO Epoch:40 val_res:0.821000 +2025-04-19 04:46:26,190 INFO Epoch:41 train_loss:0.45897 +2025-04-19 04:46:30,072 INFO Epoch:41 val_res:0.821000 +2025-04-19 04:47:00,367 INFO Epoch:42 train_loss:0.44716 +2025-04-19 04:47:04,211 INFO Epoch:42 val_res:0.823000 +2025-04-19 04:47:35,136 INFO Epoch:43 train_loss:0.41165 +2025-04-19 04:47:38,961 INFO Epoch:43 val_res:0.823000 +2025-04-19 04:48:08,938 INFO Epoch:44 train_loss:0.42151 +2025-04-19 04:48:12,832 INFO Epoch:44 val_res:0.829000 +2025-04-19 04:48:42,814 INFO Epoch:45 train_loss:0.43767 +2025-04-19 04:48:46,604 INFO Epoch:45 val_res:0.824000 +2025-04-19 04:49:16,670 INFO Epoch:46 train_loss:0.43579 +2025-04-19 04:49:20,464 INFO Epoch:46 val_res:0.820000 +2025-04-19 04:49:50,528 INFO Epoch:47 train_loss:0.42660 +2025-04-19 04:49:54,215 INFO Epoch:47 val_res:0.827000 +2025-04-19 04:50:23,706 INFO Epoch:48 train_loss:0.40925 +2025-04-19 04:50:27,571 INFO Epoch:48 val_res:0.827000 +2025-04-19 04:50:58,726 INFO Epoch:49 train_loss:0.39670 +2025-04-19 04:51:02,994 INFO Epoch:49 val_res:0.817000 +2025-04-19 04:51:33,858 INFO Epoch:50 train_loss:0.39353 +2025-04-19 04:51:37,890 INFO Epoch:50 val_res:0.819000 +2025-04-19 04:52:08,849 INFO Epoch:51 train_loss:0.41600 +2025-04-19 04:52:12,790 INFO Epoch:51 val_res:0.821000 +2025-04-19 04:52:43,787 INFO Epoch:52 train_loss:0.41777 +2025-04-19 04:52:47,422 INFO Epoch:52 val_res:0.818000 +2025-04-19 04:53:18,903 INFO Epoch:53 train_loss:0.39360 +2025-04-19 04:53:22,744 INFO Epoch:53 val_res:0.821000 +2025-04-19 04:53:53,727 INFO Epoch:54 train_loss:0.40387 +2025-04-19 04:53:57,507 INFO Epoch:54 val_res:0.832000 +2025-04-19 04:54:27,926 INFO Epoch:55 train_loss:0.38798 +2025-04-19 04:54:31,796 INFO Epoch:55 val_res:0.830000 +2025-04-19 04:55:01,507 INFO Epoch:56 train_loss:0.38316 +2025-04-19 04:55:05,288 INFO Epoch:56 val_res:0.827000 +2025-04-19 04:55:35,637 INFO Epoch:57 train_loss:0.38975 +2025-04-19 04:55:39,475 INFO Epoch:57 val_res:0.817000 +2025-04-19 04:56:09,811 INFO Epoch:58 train_loss:0.39090 +2025-04-19 04:56:13,641 INFO Epoch:58 val_res:0.816000 +2025-04-19 04:56:44,471 INFO Epoch:59 train_loss:0.39310 +2025-04-19 04:56:48,543 INFO Epoch:59 val_res:0.822000 +2025-04-19 04:57:19,483 INFO Epoch:60 train_loss:0.39796 +2025-04-19 04:57:23,328 INFO Epoch:60 val_res:0.829000 +2025-04-19 04:57:53,243 INFO Epoch:61 train_loss:0.39015 +2025-04-19 04:57:57,157 INFO Epoch:61 val_res:0.823000 +2025-04-19 04:58:28,119 INFO Epoch:62 train_loss:0.38659 +2025-04-19 04:58:32,021 INFO Epoch:62 val_res:0.828000 +2025-04-19 04:59:03,697 INFO Epoch:63 train_loss:0.39375 +2025-04-19 04:59:07,495 INFO Epoch:63 val_res:0.821000 +2025-04-19 04:59:39,291 INFO Epoch:64 train_loss:0.37575 +2025-04-19 04:59:43,390 INFO Epoch:64 val_res:0.822000 +2025-04-19 05:00:15,277 INFO Epoch:65 train_loss:0.36354 +2025-04-19 05:00:19,269 INFO Epoch:65 val_res:0.816000 +2025-04-19 05:00:51,650 INFO Epoch:66 train_loss:0.36167 +2025-04-19 05:00:55,422 INFO Epoch:66 val_res:0.828000 +2025-04-19 05:01:27,267 INFO Epoch:67 train_loss:0.36579 +2025-04-19 05:01:31,147 INFO Epoch:67 val_res:0.823000 +2025-04-19 05:02:02,904 INFO Epoch:68 train_loss:0.39178 +2025-04-19 05:02:06,956 INFO Epoch:68 val_res:0.815000 +2025-04-19 05:02:38,683 INFO Epoch:69 train_loss:0.37367 +2025-04-19 05:02:42,704 INFO Epoch:69 val_res:0.824000 +2025-04-19 05:03:14,943 INFO Epoch:70 train_loss:0.37710 +2025-04-19 05:03:18,793 INFO Epoch:70 val_res:0.829000 +2025-04-19 05:03:51,062 INFO Epoch:71 train_loss:0.37196 +2025-04-19 05:03:55,045 INFO Epoch:71 val_res:0.825000 +2025-04-19 05:04:26,617 INFO Epoch:72 train_loss:0.34726 +2025-04-19 05:04:30,617 INFO Epoch:72 val_res:0.823000 +2025-04-19 05:05:01,996 INFO Epoch:73 train_loss:0.33769 +2025-04-19 05:05:05,977 INFO Epoch:73 val_res:0.826000 +2025-04-19 05:05:38,690 INFO Epoch:74 train_loss:0.34412 +2025-04-19 05:05:42,645 INFO Epoch:74 val_res:0.824000 +2025-04-19 05:06:14,345 INFO Epoch:75 train_loss:0.35154 +2025-04-19 05:06:18,252 INFO Epoch:75 val_res:0.822000 +2025-04-19 05:06:50,196 INFO Epoch:76 train_loss:0.34555 +2025-04-19 05:06:53,991 INFO Epoch:76 val_res:0.821000 +2025-04-19 05:07:24,173 INFO Epoch:77 train_loss:0.34237 +2025-04-19 05:07:28,021 INFO Epoch:77 val_res:0.824000 +2025-04-19 05:07:58,417 INFO Epoch:78 train_loss:0.33977 +2025-04-19 05:08:02,477 INFO Epoch:78 val_res:0.831000 +2025-04-19 05:08:32,596 INFO Epoch:79 train_loss:0.34537 +2025-04-19 05:08:36,362 INFO Epoch:79 val_res:0.822000 +2025-04-19 05:09:06,731 INFO Epoch:80 train_loss:0.34390 +2025-04-19 05:09:10,487 INFO Epoch:80 val_res:0.825000 +2025-04-19 05:09:40,344 INFO Epoch:81 train_loss:0.35026 +2025-04-19 05:09:44,023 INFO Epoch:81 val_res:0.811000 +2025-04-19 05:10:14,719 INFO Epoch:82 train_loss:0.35169 +2025-04-19 05:10:18,451 INFO Epoch:82 val_res:0.821000 +2025-04-19 05:10:48,318 INFO Epoch:83 train_loss:0.33130 +2025-04-19 05:10:52,048 INFO Epoch:83 val_res:0.821000 +2025-04-19 05:11:22,732 INFO Epoch:84 train_loss:0.33537 +2025-04-19 05:11:26,447 INFO Epoch:84 val_res:0.810000 +2025-04-19 05:11:55,934 INFO Epoch:85 train_loss:0.35115 +2025-04-19 05:11:59,767 INFO Epoch:85 val_res:0.822000 +2025-04-19 05:12:30,233 INFO Epoch:86 train_loss:0.35677 +2025-04-19 05:12:33,919 INFO Epoch:86 val_res:0.819000 +2025-04-19 05:13:04,455 INFO Epoch:87 train_loss:0.33440 +2025-04-19 05:13:08,188 INFO Epoch:87 val_res:0.816000 +2025-04-19 05:13:37,919 INFO Epoch:88 train_loss:0.32706 +2025-04-19 05:13:41,971 INFO Epoch:88 val_res:0.820000 +2025-04-19 05:14:14,865 INFO Epoch:89 train_loss:0.33326 +2025-04-19 05:14:18,550 INFO Epoch:89 val_res:0.825000 +2025-04-19 05:14:49,262 INFO Epoch:90 train_loss:0.32940 +2025-04-19 05:14:52,910 INFO Epoch:90 val_res:0.826000 +2025-04-19 05:15:23,817 INFO Epoch:91 train_loss:0.33420 +2025-04-19 05:15:27,451 INFO Epoch:91 val_res:0.823000 +2025-04-19 05:15:57,488 INFO Epoch:92 train_loss:0.33553 +2025-04-19 05:16:01,138 INFO Epoch:92 val_res:0.816000 +2025-04-19 05:16:32,251 INFO Epoch:93 train_loss:0.35299 +2025-04-19 05:16:36,094 INFO Epoch:93 val_res:0.821000 +2025-04-19 05:17:06,119 INFO Epoch:94 train_loss:0.41523 +2025-04-19 05:17:09,822 INFO Epoch:94 val_res:0.820000 +2025-04-19 05:17:41,277 INFO Epoch:95 train_loss:0.36639 +2025-04-19 05:17:45,133 INFO Epoch:95 val_res:0.812000 +2025-04-19 05:18:16,479 INFO Epoch:96 train_loss:0.36179 +2025-04-19 05:18:20,328 INFO Epoch:96 val_res:0.812000 +2025-04-19 05:18:49,769 INFO Epoch:97 train_loss:0.33524 +2025-04-19 05:18:53,637 INFO Epoch:97 val_res:0.819000 +2025-04-19 05:19:23,885 INFO Epoch:98 train_loss:0.33128 +2025-04-19 05:19:27,873 INFO Epoch:98 val_res:0.821000 +2025-04-19 05:19:57,188 INFO Epoch:99 train_loss:0.33234 +2025-04-19 05:20:01,290 INFO Epoch:99 val_res:0.819000 +2025-04-19 05:20:02,055 INFO ===================================== +2025-04-19 05:20:02,056 INFO Start testing... +2025-04-19 05:20:02,056 INFO ===================================== +2025-04-19 05:20:06,526 INFO Incremental step 1 Testing res: 0.805000 +2025-04-19 05:20:06,527 INFO forgetting: 0.080000 +2025-04-19 05:20:06,530 INFO ***************New Step*************************** +2025-04-19 05:20:06,531 INFO Incremental step: 2 +2025-04-19 05:20:06,682 INFO actual size of exemplar set: 1500 +2025-04-19 05:20:42,503 INFO Epoch:0 train_loss:4.84955 +2025-04-19 05:20:48,229 INFO Epoch:0 val_res:0.554667 +2025-04-19 05:20:48,230 INFO Saving best model at Epoch 0 +2025-04-19 05:21:24,632 INFO Epoch:1 train_loss:2.07670 +2025-04-19 05:21:29,824 INFO Epoch:1 val_res:0.593333 +2025-04-19 05:21:29,824 INFO Saving best model at Epoch 1 +2025-04-19 05:22:08,589 INFO Epoch:2 train_loss:1.58660 +2025-04-19 05:22:13,851 INFO Epoch:2 val_res:0.602667 +2025-04-19 05:22:13,855 INFO Saving best model at Epoch 2 +2025-04-19 05:22:49,944 INFO Epoch:3 train_loss:1.40494 +2025-04-19 05:22:55,089 INFO Epoch:3 val_res:0.617333 +2025-04-19 05:22:55,090 INFO Saving best model at Epoch 3 +2025-04-19 05:23:29,655 INFO Epoch:4 train_loss:1.27239 +2025-04-19 05:23:34,949 INFO Epoch:4 val_res:0.622667 +2025-04-19 05:23:34,950 INFO Saving best model at Epoch 4 +2025-04-19 05:24:09,236 INFO Epoch:5 train_loss:1.20306 +2025-04-19 05:24:14,437 INFO Epoch:5 val_res:0.636000 +2025-04-19 05:24:14,438 INFO Saving best model at Epoch 5 +2025-04-19 05:24:50,682 INFO Epoch:6 train_loss:1.12945 +2025-04-19 05:24:55,703 INFO Epoch:6 val_res:0.646667 +2025-04-19 05:24:55,703 INFO Saving best model at Epoch 6 +2025-04-19 05:25:31,749 INFO Epoch:7 train_loss:1.07614 +2025-04-19 05:25:36,675 INFO Epoch:7 val_res:0.657333 +2025-04-19 05:25:36,675 INFO Saving best model at Epoch 7 +2025-04-19 05:26:12,787 INFO Epoch:8 train_loss:1.01880 +2025-04-19 05:26:17,752 INFO Epoch:8 val_res:0.672000 +2025-04-19 05:26:17,752 INFO Saving best model at Epoch 8 +2025-04-19 05:26:53,066 INFO Epoch:9 train_loss:0.97867 +2025-04-19 05:26:57,918 INFO Epoch:9 val_res:0.682000 +2025-04-19 05:26:57,919 INFO Saving best model at Epoch 9 +2025-04-19 05:27:35,058 INFO Epoch:10 train_loss:0.93046 +2025-04-19 05:27:40,110 INFO Epoch:10 val_res:0.686000 +2025-04-19 05:27:40,111 INFO Saving best model at Epoch 10 +2025-04-19 05:28:16,598 INFO Epoch:11 train_loss:0.89817 +2025-04-19 05:28:21,481 INFO Epoch:11 val_res:0.687333 +2025-04-19 05:28:21,481 INFO Saving best model at Epoch 11 +2025-04-19 05:28:57,360 INFO Epoch:12 train_loss:0.86102 +2025-04-19 05:29:02,313 INFO Epoch:12 val_res:0.694667 +2025-04-19 05:29:02,314 INFO Saving best model at Epoch 12 +2025-04-19 05:29:37,489 INFO Epoch:13 train_loss:0.82055 +2025-04-19 05:29:42,819 INFO Epoch:13 val_res:0.712667 +2025-04-19 05:29:42,819 INFO Saving best model at Epoch 13 +2025-04-19 05:30:20,997 INFO Epoch:14 train_loss:0.78920 +2025-04-19 05:30:26,728 INFO Epoch:14 val_res:0.710000 +2025-04-19 05:31:01,048 INFO Epoch:15 train_loss:0.75285 +2025-04-19 05:31:06,705 INFO Epoch:15 val_res:0.722000 +2025-04-19 05:31:06,706 INFO Saving best model at Epoch 15 +2025-04-19 05:31:41,972 INFO Epoch:16 train_loss:0.72598 +2025-04-19 05:31:47,897 INFO Epoch:16 val_res:0.736667 +2025-04-19 05:31:47,898 INFO Saving best model at Epoch 16 +2025-04-19 05:32:23,973 INFO Epoch:17 train_loss:0.71544 +2025-04-19 05:32:28,777 INFO Epoch:17 val_res:0.742000 +2025-04-19 05:32:28,777 INFO Saving best model at Epoch 17 +2025-04-19 05:33:04,363 INFO Epoch:18 train_loss:0.69187 +2025-04-19 05:33:09,264 INFO Epoch:18 val_res:0.738000 +2025-04-19 05:33:42,825 INFO Epoch:19 train_loss:0.67771 +2025-04-19 05:33:47,747 INFO Epoch:19 val_res:0.747333 +2025-04-19 05:33:47,747 INFO Saving best model at Epoch 19 +2025-04-19 05:34:25,890 INFO Epoch:20 train_loss:0.64170 +2025-04-19 05:34:30,730 INFO Epoch:20 val_res:0.746000 +2025-04-19 05:35:04,760 INFO Epoch:21 train_loss:0.64521 +2025-04-19 05:35:09,871 INFO Epoch:21 val_res:0.751333 +2025-04-19 05:35:09,871 INFO Saving best model at Epoch 21 +2025-04-19 05:35:46,310 INFO Epoch:22 train_loss:0.63361 +2025-04-19 05:35:51,672 INFO Epoch:22 val_res:0.745333 +2025-04-19 05:36:25,737 INFO Epoch:23 train_loss:0.60803 +2025-04-19 05:36:30,817 INFO Epoch:23 val_res:0.754667 +2025-04-19 05:36:30,817 INFO Saving best model at Epoch 23 +2025-04-19 05:37:07,262 INFO Epoch:24 train_loss:0.58734 +2025-04-19 05:37:12,260 INFO Epoch:24 val_res:0.760000 +2025-04-19 05:37:12,260 INFO Saving best model at Epoch 24 +2025-04-19 05:37:47,806 INFO Epoch:25 train_loss:0.58610 +2025-04-19 05:37:52,811 INFO Epoch:25 val_res:0.749333 +2025-04-19 05:38:27,124 INFO Epoch:26 train_loss:0.57758 +2025-04-19 05:38:31,958 INFO Epoch:26 val_res:0.762000 +2025-04-19 05:38:31,958 INFO Saving best model at Epoch 26 +2025-04-19 05:39:07,093 INFO Epoch:27 train_loss:0.56204 +2025-04-19 05:39:11,999 INFO Epoch:27 val_res:0.760000 +2025-04-19 05:39:45,856 INFO Epoch:28 train_loss:0.54798 +2025-04-19 05:39:51,055 INFO Epoch:28 val_res:0.767333 +2025-04-19 05:39:51,055 INFO Saving best model at Epoch 28 +2025-04-19 05:40:28,317 INFO Epoch:29 train_loss:0.54107 +2025-04-19 05:40:33,487 INFO Epoch:29 val_res:0.758000 +2025-04-19 05:41:08,009 INFO Epoch:30 train_loss:0.53962 +2025-04-19 05:41:13,086 INFO Epoch:30 val_res:0.754667 +2025-04-19 05:41:47,180 INFO Epoch:31 train_loss:0.52333 +2025-04-19 05:41:52,256 INFO Epoch:31 val_res:0.763333 +2025-04-19 05:42:26,318 INFO Epoch:32 train_loss:0.51741 +2025-04-19 05:42:31,200 INFO Epoch:32 val_res:0.764667 +2025-04-19 05:43:04,316 INFO Epoch:33 train_loss:0.51934 +2025-04-19 05:43:09,337 INFO Epoch:33 val_res:0.766667 +2025-04-19 05:43:42,528 INFO Epoch:34 train_loss:0.50362 +2025-04-19 05:43:47,492 INFO Epoch:34 val_res:0.757333 +2025-04-19 05:44:20,800 INFO Epoch:35 train_loss:0.48905 +2025-04-19 05:44:25,694 INFO Epoch:35 val_res:0.755333 +2025-04-19 05:44:59,086 INFO Epoch:36 train_loss:0.50014 +2025-04-19 05:45:04,146 INFO Epoch:36 val_res:0.750667 +2025-04-19 05:45:37,671 INFO Epoch:37 train_loss:0.47850 +2025-04-19 05:45:42,426 INFO Epoch:37 val_res:0.766667 +2025-04-19 05:46:16,618 INFO Epoch:38 train_loss:0.48574 +2025-04-19 05:46:21,974 INFO Epoch:38 val_res:0.760667 +2025-04-19 05:46:57,175 INFO Epoch:39 train_loss:0.47040 +2025-04-19 05:47:01,979 INFO Epoch:39 val_res:0.760000 +2025-04-19 05:47:36,964 INFO Epoch:40 train_loss:0.48551 +2025-04-19 05:47:41,890 INFO Epoch:40 val_res:0.763333 +2025-04-19 05:48:15,085 INFO Epoch:41 train_loss:0.47669 +2025-04-19 05:48:19,985 INFO Epoch:41 val_res:0.750000 +2025-04-19 05:48:55,135 INFO Epoch:42 train_loss:0.46583 +2025-04-19 05:49:00,272 INFO Epoch:42 val_res:0.761333 +2025-04-19 05:49:34,052 INFO Epoch:43 train_loss:0.48532 +2025-04-19 05:49:38,991 INFO Epoch:43 val_res:0.768667 +2025-04-19 05:49:38,991 INFO Saving best model at Epoch 43 +2025-04-19 05:50:13,233 INFO Epoch:44 train_loss:0.49940 +2025-04-19 05:50:18,567 INFO Epoch:44 val_res:0.752667 +2025-04-19 05:50:51,677 INFO Epoch:45 train_loss:0.50732 +2025-04-19 05:50:56,562 INFO Epoch:45 val_res:0.747333 +2025-04-19 05:51:29,841 INFO Epoch:46 train_loss:0.45578 +2025-04-19 05:51:34,798 INFO Epoch:46 val_res:0.753333 +2025-04-19 05:52:09,265 INFO Epoch:47 train_loss:0.44194 +2025-04-19 05:52:14,154 INFO Epoch:47 val_res:0.754000 +2025-04-19 05:52:48,177 INFO Epoch:48 train_loss:0.44617 +2025-04-19 05:52:53,309 INFO Epoch:48 val_res:0.758667 +2025-04-19 05:53:28,246 INFO Epoch:49 train_loss:0.43373 +2025-04-19 05:53:33,809 INFO Epoch:49 val_res:0.761333 +2025-04-19 05:54:07,403 INFO Epoch:50 train_loss:0.44317 +2025-04-19 05:54:12,572 INFO Epoch:50 val_res:0.759333 +2025-04-19 05:54:46,182 INFO Epoch:51 train_loss:0.46167 +2025-04-19 05:54:51,405 INFO Epoch:51 val_res:0.752000 +2025-04-19 05:55:25,749 INFO Epoch:52 train_loss:0.48890 +2025-04-19 05:55:30,756 INFO Epoch:52 val_res:0.748667 +2025-04-19 05:56:04,052 INFO Epoch:53 train_loss:0.45216 +2025-04-19 05:56:08,962 INFO Epoch:53 val_res:0.762000 +2025-04-19 05:56:41,841 INFO Epoch:54 train_loss:0.42452 +2025-04-19 05:56:46,786 INFO Epoch:54 val_res:0.754667 +2025-04-19 05:57:20,443 INFO Epoch:55 train_loss:0.42329 +2025-04-19 05:57:25,540 INFO Epoch:55 val_res:0.748667 +2025-04-19 05:57:59,277 INFO Epoch:56 train_loss:0.44366 +2025-04-19 05:58:04,342 INFO Epoch:56 val_res:0.744667 +2025-04-19 05:58:40,254 INFO Epoch:57 train_loss:0.41750 +2025-04-19 05:58:45,846 INFO Epoch:57 val_res:0.757333 +2025-04-19 05:59:20,505 INFO Epoch:58 train_loss:0.42024 +2025-04-19 05:59:25,521 INFO Epoch:58 val_res:0.752000 +2025-04-19 06:00:00,160 INFO Epoch:59 train_loss:0.41088 +2025-04-19 06:00:05,657 INFO Epoch:59 val_res:0.748000 +2025-04-19 06:00:40,343 INFO Epoch:60 train_loss:0.39211 +2025-04-19 06:00:45,544 INFO Epoch:60 val_res:0.754667 +2025-04-19 06:01:20,803 INFO Epoch:61 train_loss:0.39328 +2025-04-19 06:01:25,825 INFO Epoch:61 val_res:0.757333 +2025-04-19 06:01:59,801 INFO Epoch:62 train_loss:0.40355 +2025-04-19 06:02:04,907 INFO Epoch:62 val_res:0.758667 +2025-04-19 06:02:38,972 INFO Epoch:63 train_loss:0.42316 +2025-04-19 06:02:44,042 INFO Epoch:63 val_res:0.744667 +2025-04-19 06:03:19,905 INFO Epoch:64 train_loss:0.42440 +2025-04-19 06:03:24,682 INFO Epoch:64 val_res:0.752667 +2025-04-19 06:03:59,238 INFO Epoch:65 train_loss:0.41562 +2025-04-19 06:04:04,362 INFO Epoch:65 val_res:0.756000 +2025-04-19 06:04:39,221 INFO Epoch:66 train_loss:0.39988 +2025-04-19 06:04:44,429 INFO Epoch:66 val_res:0.742000 +2025-04-19 06:05:19,491 INFO Epoch:67 train_loss:0.40117 +2025-04-19 06:05:25,174 INFO Epoch:67 val_res:0.763333 +2025-04-19 06:06:00,578 INFO Epoch:68 train_loss:0.40479 +2025-04-19 06:06:05,978 INFO Epoch:68 val_res:0.760667 +2025-04-19 06:06:41,733 INFO Epoch:69 train_loss:0.39186 +2025-04-19 06:06:46,876 INFO Epoch:69 val_res:0.756667 +2025-04-19 06:07:21,408 INFO Epoch:70 train_loss:0.37876 +2025-04-19 06:07:26,533 INFO Epoch:70 val_res:0.748667 +2025-04-19 06:08:01,231 INFO Epoch:71 train_loss:0.37873 +2025-04-19 06:08:06,834 INFO Epoch:71 val_res:0.763333 +2025-04-19 06:08:41,205 INFO Epoch:72 train_loss:0.37870 +2025-04-19 06:08:46,478 INFO Epoch:72 val_res:0.745333 +2025-04-19 06:09:21,189 INFO Epoch:73 train_loss:0.37459 +2025-04-19 06:09:26,027 INFO Epoch:73 val_res:0.751333 +2025-04-19 06:10:00,451 INFO Epoch:74 train_loss:0.38129 +2025-04-19 06:10:05,835 INFO Epoch:74 val_res:0.750000 +2025-04-19 06:10:39,848 INFO Epoch:75 train_loss:0.40528 +2025-04-19 06:10:45,106 INFO Epoch:75 val_res:0.741333 +2025-04-19 06:11:19,675 INFO Epoch:76 train_loss:0.38937 +2025-04-19 06:11:24,868 INFO Epoch:76 val_res:0.741333 +2025-04-19 06:11:58,936 INFO Epoch:77 train_loss:0.38926 +2025-04-19 06:12:04,232 INFO Epoch:77 val_res:0.751333 +2025-04-19 06:12:38,730 INFO Epoch:78 train_loss:0.37640 +2025-04-19 06:12:44,327 INFO Epoch:78 val_res:0.744667 +2025-04-19 06:13:17,905 INFO Epoch:79 train_loss:0.36152 +2025-04-19 06:13:23,175 INFO Epoch:79 val_res:0.748000 +2025-04-19 06:13:58,194 INFO Epoch:80 train_loss:0.36415 +2025-04-19 06:14:03,683 INFO Epoch:80 val_res:0.744000 +2025-04-19 06:14:38,124 INFO Epoch:81 train_loss:0.35985 +2025-04-19 06:14:43,181 INFO Epoch:81 val_res:0.754000 +2025-04-19 06:15:18,226 INFO Epoch:82 train_loss:0.37601 +2025-04-19 06:15:23,728 INFO Epoch:82 val_res:0.746000 +2025-04-19 06:15:57,814 INFO Epoch:83 train_loss:0.38362 +2025-04-19 06:16:02,906 INFO Epoch:83 val_res:0.736000 +2025-04-19 06:16:37,388 INFO Epoch:84 train_loss:0.36901 +2025-04-19 06:16:42,646 INFO Epoch:84 val_res:0.738667 +2025-04-19 06:17:16,053 INFO Epoch:85 train_loss:0.35129 +2025-04-19 06:17:21,614 INFO Epoch:85 val_res:0.756000 +2025-04-19 06:17:56,705 INFO Epoch:86 train_loss:0.35362 +2025-04-19 06:18:01,785 INFO Epoch:86 val_res:0.755333 +2025-04-19 06:18:37,152 INFO Epoch:87 train_loss:0.37098 +2025-04-19 06:18:42,164 INFO Epoch:87 val_res:0.744000 +2025-04-19 06:19:16,936 INFO Epoch:88 train_loss:0.36846 +2025-04-19 06:19:21,931 INFO Epoch:88 val_res:0.761333 +2025-04-19 06:19:56,829 INFO Epoch:89 train_loss:0.37752 +2025-04-19 06:20:01,748 INFO Epoch:89 val_res:0.740667 +2025-04-19 06:20:35,488 INFO Epoch:90 train_loss:0.36642 +2025-04-19 06:20:40,853 INFO Epoch:90 val_res:0.748000 +2025-04-19 06:21:16,054 INFO Epoch:91 train_loss:0.35609 +2025-04-19 06:21:21,618 INFO Epoch:91 val_res:0.753333 +2025-04-19 06:21:56,645 INFO Epoch:92 train_loss:0.36411 +2025-04-19 06:22:01,707 INFO Epoch:92 val_res:0.746667 +2025-04-19 06:22:36,497 INFO Epoch:93 train_loss:0.33613 +2025-04-19 06:22:41,653 INFO Epoch:93 val_res:0.742000 +2025-04-19 06:23:16,041 INFO Epoch:94 train_loss:0.34115 +2025-04-19 06:23:21,545 INFO Epoch:94 val_res:0.752000 +2025-04-19 06:23:55,287 INFO Epoch:95 train_loss:0.33104 +2025-04-19 06:24:00,661 INFO Epoch:95 val_res:0.746000 +2025-04-19 06:24:34,746 INFO Epoch:96 train_loss:0.35262 +2025-04-19 06:24:40,155 INFO Epoch:96 val_res:0.736667 +2025-04-19 06:25:14,349 INFO Epoch:97 train_loss:0.34134 +2025-04-19 06:25:19,420 INFO Epoch:97 val_res:0.741333 +2025-04-19 06:25:54,997 INFO Epoch:98 train_loss:0.34819 +2025-04-19 06:26:00,375 INFO Epoch:98 val_res:0.723333 +2025-04-19 06:26:35,174 INFO Epoch:99 train_loss:0.35019 +2025-04-19 06:26:40,517 INFO Epoch:99 val_res:0.753333 +2025-04-19 06:26:41,272 INFO ===================================== +2025-04-19 06:26:41,273 INFO Start testing... +2025-04-19 06:26:41,273 INFO ===================================== +2025-04-19 06:26:47,561 INFO Incremental step 2 Testing res: 0.760667 +2025-04-19 06:26:47,563 INFO forgetting: 0.105000 +2025-04-19 06:26:47,567 INFO ***************New Step*************************** +2025-04-19 06:26:47,568 INFO Incremental step: 3 +2025-04-19 06:26:47,699 INFO actual size of exemplar set: 1500 +2025-04-19 06:27:25,109 INFO Epoch:0 train_loss:5.43614 +2025-04-19 06:27:33,245 INFO Epoch:0 val_res:0.585500 +2025-04-19 06:27:33,247 INFO Saving best model at Epoch 0 +2025-04-19 06:28:12,897 INFO Epoch:1 train_loss:2.35157 +2025-04-19 06:28:20,133 INFO Epoch:1 val_res:0.601500 +2025-04-19 06:28:20,133 INFO Saving best model at Epoch 1 +2025-04-19 06:28:58,679 INFO Epoch:2 train_loss:1.85250 +2025-04-19 06:29:05,505 INFO Epoch:2 val_res:0.600000 +2025-04-19 06:29:41,357 INFO Epoch:3 train_loss:1.67833 +2025-04-19 06:29:48,339 INFO Epoch:3 val_res:0.604500 +2025-04-19 06:29:48,339 INFO Saving best model at Epoch 3 +2025-04-19 06:30:26,510 INFO Epoch:4 train_loss:1.57186 +2025-04-19 06:30:33,002 INFO Epoch:4 val_res:0.606000 +2025-04-19 06:30:33,003 INFO Saving best model at Epoch 4 +2025-04-19 06:31:10,861 INFO Epoch:5 train_loss:1.50072 +2025-04-19 06:31:17,878 INFO Epoch:5 val_res:0.606500 +2025-04-19 06:31:17,878 INFO Saving best model at Epoch 5 +2025-04-19 06:31:57,281 INFO Epoch:6 train_loss:1.43561 +2025-04-19 06:32:03,852 INFO Epoch:6 val_res:0.613500 +2025-04-19 06:32:03,853 INFO Saving best model at Epoch 6 +2025-04-19 06:32:40,513 INFO Epoch:7 train_loss:1.37992 +2025-04-19 06:32:47,809 INFO Epoch:7 val_res:0.619500 +2025-04-19 06:32:47,809 INFO Saving best model at Epoch 7 +2025-04-19 06:33:23,782 INFO Epoch:8 train_loss:1.31722 +2025-04-19 06:33:31,127 INFO Epoch:8 val_res:0.622500 +2025-04-19 06:33:31,127 INFO Saving best model at Epoch 8 +2025-04-19 06:34:08,226 INFO Epoch:9 train_loss:1.27940 +2025-04-19 06:34:14,960 INFO Epoch:9 val_res:0.624500 +2025-04-19 06:34:14,960 INFO Saving best model at Epoch 9 +2025-04-19 06:34:52,658 INFO Epoch:10 train_loss:1.24047 +2025-04-19 06:34:59,283 INFO Epoch:10 val_res:0.633000 +2025-04-19 06:34:59,283 INFO Saving best model at Epoch 10 +2025-04-19 06:35:35,861 INFO Epoch:11 train_loss:1.20104 +2025-04-19 06:35:42,371 INFO Epoch:11 val_res:0.636000 +2025-04-19 06:35:42,372 INFO Saving best model at Epoch 11 +2025-04-19 06:36:19,134 INFO Epoch:12 train_loss:1.16487 +2025-04-19 06:36:26,102 INFO Epoch:12 val_res:0.643000 +2025-04-19 06:36:26,102 INFO Saving best model at Epoch 12 +2025-04-19 06:37:02,986 INFO Epoch:13 train_loss:1.13165 +2025-04-19 06:37:09,718 INFO Epoch:13 val_res:0.650000 +2025-04-19 06:37:09,719 INFO Saving best model at Epoch 13 +2025-04-19 06:37:46,377 INFO Epoch:14 train_loss:1.10334 +2025-04-19 06:37:53,505 INFO Epoch:14 val_res:0.658000 +2025-04-19 06:37:53,505 INFO Saving best model at Epoch 14 +2025-04-19 06:38:31,451 INFO Epoch:15 train_loss:1.06733 +2025-04-19 06:38:37,678 INFO Epoch:15 val_res:0.659000 +2025-04-19 06:38:37,678 INFO Saving best model at Epoch 15 +2025-04-19 06:39:13,375 INFO Epoch:16 train_loss:1.04328 +2025-04-19 06:39:20,092 INFO Epoch:16 val_res:0.670000 +2025-04-19 06:39:20,092 INFO Saving best model at Epoch 16 +2025-04-19 06:39:58,375 INFO Epoch:17 train_loss:1.01231 +2025-04-19 06:40:05,494 INFO Epoch:17 val_res:0.668000 +2025-04-19 06:40:42,965 INFO Epoch:18 train_loss:1.00215 +2025-04-19 06:40:50,030 INFO Epoch:18 val_res:0.678000 +2025-04-19 06:40:50,030 INFO Saving best model at Epoch 18 +2025-04-19 06:41:28,232 INFO Epoch:19 train_loss:0.98177 +2025-04-19 06:41:35,994 INFO Epoch:19 val_res:0.671500 +2025-04-19 06:42:13,195 INFO Epoch:20 train_loss:0.96657 +2025-04-19 06:42:20,431 INFO Epoch:20 val_res:0.686500 +2025-04-19 06:42:20,431 INFO Saving best model at Epoch 20 +2025-04-19 06:42:59,380 INFO Epoch:21 train_loss:0.89423 +2025-04-19 06:43:07,015 INFO Epoch:21 val_res:0.692000 +2025-04-19 06:43:07,015 INFO Saving best model at Epoch 21 +2025-04-19 06:43:46,767 INFO Epoch:22 train_loss:0.87034 +2025-04-19 06:43:54,291 INFO Epoch:22 val_res:0.695000 +2025-04-19 06:43:54,291 INFO Saving best model at Epoch 22 +2025-04-19 06:44:35,283 INFO Epoch:23 train_loss:0.86927 +2025-04-19 06:44:42,783 INFO Epoch:23 val_res:0.696000 +2025-04-19 06:44:42,784 INFO Saving best model at Epoch 23 +2025-04-19 06:45:22,126 INFO Epoch:24 train_loss:0.83399 +2025-04-19 06:45:29,798 INFO Epoch:24 val_res:0.696000 +2025-04-19 06:46:08,614 INFO Epoch:25 train_loss:0.82179 +2025-04-19 06:46:15,668 INFO Epoch:25 val_res:0.702500 +2025-04-19 06:46:15,668 INFO Saving best model at Epoch 25 +2025-04-19 06:46:56,579 INFO Epoch:26 train_loss:0.81203 +2025-04-19 06:47:04,632 INFO Epoch:26 val_res:0.704000 +2025-04-19 06:47:04,633 INFO Saving best model at Epoch 26 +2025-04-19 06:47:46,733 INFO Epoch:27 train_loss:0.80309 +2025-04-19 06:47:54,062 INFO Epoch:27 val_res:0.706000 +2025-04-19 06:47:54,062 INFO Saving best model at Epoch 27 +2025-04-19 06:48:34,616 INFO Epoch:28 train_loss:0.78821 +2025-04-19 06:48:42,444 INFO Epoch:28 val_res:0.714000 +2025-04-19 06:48:42,445 INFO Saving best model at Epoch 28 +2025-04-19 06:49:22,465 INFO Epoch:29 train_loss:0.75475 +2025-04-19 06:49:29,756 INFO Epoch:29 val_res:0.717000 +2025-04-19 06:49:29,757 INFO Saving best model at Epoch 29 +2025-04-19 06:50:10,730 INFO Epoch:30 train_loss:0.74527 +2025-04-19 06:50:18,511 INFO Epoch:30 val_res:0.720500 +2025-04-19 06:50:18,512 INFO Saving best model at Epoch 30 +2025-04-19 06:50:56,923 INFO Epoch:31 train_loss:0.72605 +2025-04-19 06:51:03,663 INFO Epoch:31 val_res:0.719500 +2025-04-19 06:51:39,031 INFO Epoch:32 train_loss:0.71797 +2025-04-19 06:51:45,553 INFO Epoch:32 val_res:0.724500 +2025-04-19 06:51:45,554 INFO Saving best model at Epoch 32 +2025-04-19 06:52:23,122 INFO Epoch:33 train_loss:0.70253 +2025-04-19 06:52:29,850 INFO Epoch:33 val_res:0.723500 +2025-04-19 06:53:06,248 INFO Epoch:34 train_loss:0.70180 +2025-04-19 06:53:13,094 INFO Epoch:34 val_res:0.718500 +2025-04-19 06:53:50,332 INFO Epoch:35 train_loss:0.68619 +2025-04-19 06:53:57,096 INFO Epoch:35 val_res:0.721500 +2025-04-19 06:54:34,798 INFO Epoch:36 train_loss:0.67880 +2025-04-19 06:54:42,142 INFO Epoch:36 val_res:0.719000 +2025-04-19 06:55:18,918 INFO Epoch:37 train_loss:0.68090 +2025-04-19 06:55:26,420 INFO Epoch:37 val_res:0.724000 +2025-04-19 06:56:02,778 INFO Epoch:38 train_loss:0.69274 +2025-04-19 06:56:10,417 INFO Epoch:38 val_res:0.712000 +2025-04-19 06:56:46,916 INFO Epoch:39 train_loss:0.67007 +2025-04-19 06:56:54,171 INFO Epoch:39 val_res:0.727000 +2025-04-19 06:56:54,172 INFO Saving best model at Epoch 39 +2025-04-19 06:57:34,602 INFO Epoch:40 train_loss:0.66961 +2025-04-19 06:57:41,717 INFO Epoch:40 val_res:0.720500 +2025-04-19 06:58:19,167 INFO Epoch:41 train_loss:0.71932 +2025-04-19 06:58:26,461 INFO Epoch:41 val_res:0.730000 +2025-04-19 06:58:26,461 INFO Saving best model at Epoch 41 +2025-04-19 06:59:04,907 INFO Epoch:42 train_loss:0.67754 +2025-04-19 06:59:12,014 INFO Epoch:42 val_res:0.721500 +2025-04-19 06:59:48,995 INFO Epoch:43 train_loss:0.64113 +2025-04-19 06:59:56,982 INFO Epoch:43 val_res:0.727500 +2025-04-19 07:00:33,983 INFO Epoch:44 train_loss:0.62024 +2025-04-19 07:00:41,312 INFO Epoch:44 val_res:0.726500 +2025-04-19 07:01:17,400 INFO Epoch:45 train_loss:0.61674 +2025-04-19 07:01:24,735 INFO Epoch:45 val_res:0.726000 +2025-04-19 07:02:01,831 INFO Epoch:46 train_loss:0.60277 +2025-04-19 07:02:09,333 INFO Epoch:46 val_res:0.727000 +2025-04-19 07:02:46,878 INFO Epoch:47 train_loss:0.62103 +2025-04-19 07:02:54,853 INFO Epoch:47 val_res:0.721000 +2025-04-19 07:03:31,392 INFO Epoch:48 train_loss:0.59764 +2025-04-19 07:03:38,877 INFO Epoch:48 val_res:0.725000 +2025-04-19 07:04:15,101 INFO Epoch:49 train_loss:0.58936 +2025-04-19 07:04:22,640 INFO Epoch:49 val_res:0.720500 +2025-04-19 07:05:00,070 INFO Epoch:50 train_loss:0.58651 +2025-04-19 07:05:07,181 INFO Epoch:50 val_res:0.727000 +2025-04-19 07:05:44,843 INFO Epoch:51 train_loss:0.57681 +2025-04-19 07:05:52,523 INFO Epoch:51 val_res:0.723000 +2025-04-19 07:06:29,716 INFO Epoch:52 train_loss:0.62799 +2025-04-19 07:06:36,999 INFO Epoch:52 val_res:0.722500 +2025-04-19 07:07:14,238 INFO Epoch:53 train_loss:0.61043 +2025-04-19 07:07:21,378 INFO Epoch:53 val_res:0.723500 +2025-04-19 07:08:00,263 INFO Epoch:54 train_loss:0.61764 +2025-04-19 07:08:07,734 INFO Epoch:54 val_res:0.712000 +2025-04-19 07:08:46,045 INFO Epoch:55 train_loss:0.57328 +2025-04-19 07:08:53,632 INFO Epoch:55 val_res:0.726500 +2025-04-19 07:09:32,325 INFO Epoch:56 train_loss:0.58479 +2025-04-19 07:09:39,761 INFO Epoch:56 val_res:0.718500 +2025-04-19 07:10:17,784 INFO Epoch:57 train_loss:0.58201 +2025-04-19 07:10:24,798 INFO Epoch:57 val_res:0.716500 +2025-04-19 07:11:03,789 INFO Epoch:58 train_loss:0.56656 +2025-04-19 07:11:11,831 INFO Epoch:58 val_res:0.723000 +2025-04-19 07:11:49,456 INFO Epoch:59 train_loss:0.54720 +2025-04-19 07:11:57,235 INFO Epoch:59 val_res:0.723000 +2025-04-19 07:12:35,549 INFO Epoch:60 train_loss:0.56780 +2025-04-19 07:12:42,988 INFO Epoch:60 val_res:0.720500 +2025-04-19 07:13:21,380 INFO Epoch:61 train_loss:0.56514 +2025-04-19 07:13:28,948 INFO Epoch:61 val_res:0.720500 +2025-04-19 07:14:08,317 INFO Epoch:62 train_loss:0.57637 +2025-04-19 07:14:15,548 INFO Epoch:62 val_res:0.719500 +2025-04-19 07:14:52,444 INFO Epoch:63 train_loss:0.54201 +2025-04-19 07:14:59,786 INFO Epoch:63 val_res:0.722500 +2025-04-19 07:15:37,450 INFO Epoch:64 train_loss:0.54858 +2025-04-19 07:15:44,782 INFO Epoch:64 val_res:0.721000 +2025-04-19 07:16:22,504 INFO Epoch:65 train_loss:0.58264 +2025-04-19 07:16:29,804 INFO Epoch:65 val_res:0.720500 +2025-04-19 07:17:07,807 INFO Epoch:66 train_loss:0.57475 +2025-04-19 07:17:15,469 INFO Epoch:66 val_res:0.719500 +2025-04-19 07:17:52,233 INFO Epoch:67 train_loss:0.55835 +2025-04-19 07:17:59,455 INFO Epoch:67 val_res:0.713000 +2025-04-19 07:18:37,092 INFO Epoch:68 train_loss:0.57651 +2025-04-19 07:18:44,300 INFO Epoch:68 val_res:0.711500 +2025-04-19 07:19:22,810 INFO Epoch:69 train_loss:0.55355 +2025-04-19 07:19:30,020 INFO Epoch:69 val_res:0.712000 +2025-04-19 07:20:09,040 INFO Epoch:70 train_loss:0.54002 +2025-04-19 07:20:16,213 INFO Epoch:70 val_res:0.708500 +2025-04-19 07:20:54,725 INFO Epoch:71 train_loss:0.52334 +2025-04-19 07:21:01,922 INFO Epoch:71 val_res:0.718000 +2025-04-19 07:21:40,649 INFO Epoch:72 train_loss:0.51433 +2025-04-19 07:21:48,083 INFO Epoch:72 val_res:0.717000 +2025-04-19 07:22:23,310 INFO Epoch:73 train_loss:0.53784 +2025-04-19 07:22:29,844 INFO Epoch:73 val_res:0.707500 +2025-04-19 07:23:04,683 INFO Epoch:74 train_loss:0.53947 +2025-04-19 07:23:11,826 INFO Epoch:74 val_res:0.717500 +2025-04-19 07:23:46,695 INFO Epoch:75 train_loss:0.55123 +2025-04-19 07:23:53,477 INFO Epoch:75 val_res:0.715000 +2025-04-19 07:24:28,035 INFO Epoch:76 train_loss:0.53470 +2025-04-19 07:24:35,077 INFO Epoch:76 val_res:0.711500 +2025-04-19 07:25:09,261 INFO Epoch:77 train_loss:0.52961 +2025-04-19 07:25:16,559 INFO Epoch:77 val_res:0.710500 +2025-04-19 07:25:53,028 INFO Epoch:78 train_loss:0.51709 +2025-04-19 07:26:00,236 INFO Epoch:78 val_res:0.714500 +2025-04-19 07:26:41,210 INFO Epoch:79 train_loss:0.50042 +2025-04-19 07:26:48,802 INFO Epoch:79 val_res:0.705500 +2025-04-19 07:27:27,823 INFO Epoch:80 train_loss:0.53206 +2025-04-19 07:27:35,849 INFO Epoch:80 val_res:0.715000 +2025-04-19 07:28:14,811 INFO Epoch:81 train_loss:0.55189 +2025-04-19 07:28:23,105 INFO Epoch:81 val_res:0.714000 +2025-04-19 07:29:01,780 INFO Epoch:82 train_loss:0.54804 +2025-04-19 07:29:10,746 INFO Epoch:82 val_res:0.713500 +2025-04-19 07:29:50,065 INFO Epoch:83 train_loss:0.52073 +2025-04-19 07:29:58,054 INFO Epoch:83 val_res:0.708000 +2025-04-19 07:30:37,350 INFO Epoch:84 train_loss:0.49571 +2025-04-19 07:30:45,294 INFO Epoch:84 val_res:0.707500 +2025-04-19 07:31:26,034 INFO Epoch:85 train_loss:0.49243 +2025-04-19 07:31:33,574 INFO Epoch:85 val_res:0.712500 +2025-04-19 07:32:15,033 INFO Epoch:86 train_loss:0.48752 +2025-04-19 07:32:22,724 INFO Epoch:86 val_res:0.709500 +2025-04-19 07:33:03,034 INFO Epoch:87 train_loss:0.51540 +2025-04-19 07:33:10,357 INFO Epoch:87 val_res:0.709000 +2025-04-19 07:33:49,168 INFO Epoch:88 train_loss:0.48081 +2025-04-19 07:33:56,391 INFO Epoch:88 val_res:0.703000 +2025-04-19 07:34:35,222 INFO Epoch:89 train_loss:0.51396 +2025-04-19 07:34:42,412 INFO Epoch:89 val_res:0.707000 +2025-04-19 07:35:20,247 INFO Epoch:90 train_loss:0.48714 +2025-04-19 07:35:28,105 INFO Epoch:90 val_res:0.709000 +2025-04-19 07:36:05,615 INFO Epoch:91 train_loss:0.48979 +2025-04-19 07:36:12,793 INFO Epoch:91 val_res:0.708500 +2025-04-19 07:36:51,017 INFO Epoch:92 train_loss:0.50913 +2025-04-19 07:36:58,663 INFO Epoch:92 val_res:0.705500 +2025-04-19 07:37:36,422 INFO Epoch:93 train_loss:0.48640 +2025-04-19 07:37:43,257 INFO Epoch:93 val_res:0.709000 +2025-04-19 07:38:19,791 INFO Epoch:94 train_loss:0.48801 +2025-04-19 07:38:27,011 INFO Epoch:94 val_res:0.705500 +2025-04-19 07:39:06,049 INFO Epoch:95 train_loss:0.50661 +2025-04-19 07:39:13,933 INFO Epoch:95 val_res:0.706500 +2025-04-19 07:39:52,927 INFO Epoch:96 train_loss:0.50492 +2025-04-19 07:40:00,844 INFO Epoch:96 val_res:0.708000 +2025-04-19 07:40:38,443 INFO Epoch:97 train_loss:0.48048 +2025-04-19 07:40:45,968 INFO Epoch:97 val_res:0.700000 +2025-04-19 07:41:23,861 INFO Epoch:98 train_loss:0.48244 +2025-04-19 07:41:31,195 INFO Epoch:98 val_res:0.701500 +2025-04-19 07:42:09,239 INFO Epoch:99 train_loss:0.48770 +2025-04-19 07:42:16,934 INFO Epoch:99 val_res:0.707500 +2025-04-19 07:42:17,846 INFO ===================================== +2025-04-19 07:42:17,847 INFO Start testing... +2025-04-19 07:42:17,847 INFO ===================================== +2025-04-19 07:42:26,448 INFO Incremental step 3 Testing res: 0.728000 +2025-04-19 07:42:26,450 INFO forgetting: 0.074667 +2025-04-19 07:42:26,454 INFO ***************New Step*************************** +2025-04-19 07:42:26,454 INFO Incremental step: 4 +2025-04-19 07:42:26,601 INFO actual size of exemplar set: 1480 +2025-04-19 07:43:07,114 INFO Epoch:0 train_loss:7.50214 +2025-04-19 07:43:16,899 INFO Epoch:0 val_res:0.581200 +2025-04-19 07:43:16,900 INFO Saving best model at Epoch 0 +2025-04-19 07:43:59,594 INFO Epoch:1 train_loss:2.84974 +2025-04-19 07:44:09,603 INFO Epoch:1 val_res:0.588400 +2025-04-19 07:44:09,603 INFO Saving best model at Epoch 1 +2025-04-19 07:44:50,215 INFO Epoch:2 train_loss:2.10035 +2025-04-19 07:44:59,558 INFO Epoch:2 val_res:0.591200 +2025-04-19 07:44:59,558 INFO Saving best model at Epoch 2 +2025-04-19 07:45:38,158 INFO Epoch:3 train_loss:1.83190 +2025-04-19 07:45:46,973 INFO Epoch:3 val_res:0.598800 +2025-04-19 07:45:46,973 INFO Saving best model at Epoch 3 +2025-04-19 07:46:24,977 INFO Epoch:4 train_loss:1.70064 +2025-04-19 07:46:33,421 INFO Epoch:4 val_res:0.596800 +2025-04-19 07:47:07,933 INFO Epoch:5 train_loss:1.60378 +2025-04-19 07:47:16,666 INFO Epoch:5 val_res:0.602800 +2025-04-19 07:47:16,666 INFO Saving best model at Epoch 5 +2025-04-19 07:47:52,123 INFO Epoch:6 train_loss:1.53505 +2025-04-19 07:48:00,727 INFO Epoch:6 val_res:0.609600 +2025-04-19 07:48:00,727 INFO Saving best model at Epoch 6 +2025-04-19 07:48:35,899 INFO Epoch:7 train_loss:1.47239 +2025-04-19 07:48:44,304 INFO Epoch:7 val_res:0.610800 +2025-04-19 07:48:44,304 INFO Saving best model at Epoch 7 +2025-04-19 07:49:20,146 INFO Epoch:8 train_loss:1.41718 +2025-04-19 07:49:28,467 INFO Epoch:8 val_res:0.614400 +2025-04-19 07:49:28,468 INFO Saving best model at Epoch 8 +2025-04-19 07:50:03,853 INFO Epoch:9 train_loss:1.37203 +2025-04-19 07:50:11,579 INFO Epoch:9 val_res:0.617600 +2025-04-19 07:50:11,583 INFO Saving best model at Epoch 9 +2025-04-19 07:50:47,948 INFO Epoch:10 train_loss:1.33497 +2025-04-19 07:50:56,517 INFO Epoch:10 val_res:0.621600 +2025-04-19 07:50:56,518 INFO Saving best model at Epoch 10 +2025-04-19 07:51:32,471 INFO Epoch:11 train_loss:1.29142 +2025-04-19 07:51:41,183 INFO Epoch:11 val_res:0.622400 +2025-04-19 07:51:41,183 INFO Saving best model at Epoch 11 +2025-04-19 07:52:17,158 INFO Epoch:12 train_loss:1.27310 +2025-04-19 07:52:25,682 INFO Epoch:12 val_res:0.622400 +2025-04-19 07:52:59,644 INFO Epoch:13 train_loss:1.22387 +2025-04-19 07:53:08,268 INFO Epoch:13 val_res:0.630000 +2025-04-19 07:53:08,268 INFO Saving best model at Epoch 13 +2025-04-19 07:53:43,238 INFO Epoch:14 train_loss:1.19406 +2025-04-19 07:53:51,089 INFO Epoch:14 val_res:0.629600 +2025-04-19 07:54:24,722 INFO Epoch:15 train_loss:1.17097 +2025-04-19 07:54:32,903 INFO Epoch:15 val_res:0.636400 +2025-04-19 07:54:32,903 INFO Saving best model at Epoch 15 +2025-04-19 07:55:08,806 INFO Epoch:16 train_loss:1.18113 +2025-04-19 07:55:16,700 INFO Epoch:16 val_res:0.639200 +2025-04-19 07:55:16,700 INFO Saving best model at Epoch 16 +2025-04-19 07:55:53,694 INFO Epoch:17 train_loss:1.13081 +2025-04-19 07:56:02,305 INFO Epoch:17 val_res:0.642400 +2025-04-19 07:56:02,306 INFO Saving best model at Epoch 17 +2025-04-19 07:56:39,254 INFO Epoch:18 train_loss:1.11576 +2025-04-19 07:56:46,854 INFO Epoch:18 val_res:0.639600 +2025-04-19 07:57:21,355 INFO Epoch:19 train_loss:1.08648 +2025-04-19 07:57:29,020 INFO Epoch:19 val_res:0.645200 +2025-04-19 07:57:29,021 INFO Saving best model at Epoch 19 +2025-04-19 07:58:03,535 INFO Epoch:20 train_loss:1.07499 +2025-04-19 07:58:11,090 INFO Epoch:20 val_res:0.657600 +2025-04-19 07:58:11,090 INFO Saving best model at Epoch 20 +2025-04-19 07:58:46,005 INFO Epoch:21 train_loss:1.06513 +2025-04-19 07:58:53,646 INFO Epoch:21 val_res:0.650400 +2025-04-19 07:59:27,082 INFO Epoch:22 train_loss:1.04374 +2025-04-19 07:59:35,627 INFO Epoch:22 val_res:0.655200 +2025-04-19 08:00:09,221 INFO Epoch:23 train_loss:1.04817 +2025-04-19 08:00:16,819 INFO Epoch:23 val_res:0.659600 +2025-04-19 08:00:16,820 INFO Saving best model at Epoch 23 +2025-04-19 08:00:52,357 INFO Epoch:24 train_loss:1.00017 +2025-04-19 08:01:00,191 INFO Epoch:24 val_res:0.660400 +2025-04-19 08:01:00,191 INFO Saving best model at Epoch 24 +2025-04-19 08:01:34,595 INFO Epoch:25 train_loss:0.97351 +2025-04-19 08:01:42,676 INFO Epoch:25 val_res:0.663600 +2025-04-19 08:01:42,676 INFO Saving best model at Epoch 25 +2025-04-19 08:02:17,841 INFO Epoch:26 train_loss:0.94544 +2025-04-19 08:02:25,820 INFO Epoch:26 val_res:0.662400 +2025-04-19 08:02:59,701 INFO Epoch:27 train_loss:0.92593 +2025-04-19 08:03:07,777 INFO Epoch:27 val_res:0.665600 +2025-04-19 08:03:07,778 INFO Saving best model at Epoch 27 +2025-04-19 08:03:43,812 INFO Epoch:28 train_loss:0.92667 +2025-04-19 08:03:51,895 INFO Epoch:28 val_res:0.669600 +2025-04-19 08:03:51,896 INFO Saving best model at Epoch 28 +2025-04-19 08:04:28,399 INFO Epoch:29 train_loss:0.93270 +2025-04-19 08:04:36,113 INFO Epoch:29 val_res:0.668800 +2025-04-19 08:05:09,564 INFO Epoch:30 train_loss:0.90742 +2025-04-19 08:05:17,609 INFO Epoch:30 val_res:0.667600 +2025-04-19 08:05:51,262 INFO Epoch:31 train_loss:0.88485 +2025-04-19 08:05:59,268 INFO Epoch:31 val_res:0.672000 +2025-04-19 08:05:59,268 INFO Saving best model at Epoch 31 +2025-04-19 08:06:35,658 INFO Epoch:32 train_loss:0.88147 +2025-04-19 08:06:43,809 INFO Epoch:32 val_res:0.675200 +2025-04-19 08:06:43,810 INFO Saving best model at Epoch 32 +2025-04-19 08:07:18,721 INFO Epoch:33 train_loss:0.86396 +2025-04-19 08:07:26,823 INFO Epoch:33 val_res:0.676400 +2025-04-19 08:07:26,824 INFO Saving best model at Epoch 33 +2025-04-19 08:08:02,378 INFO Epoch:34 train_loss:0.84727 +2025-04-19 08:08:10,178 INFO Epoch:34 val_res:0.672800 +2025-04-19 08:08:44,359 INFO Epoch:35 train_loss:0.84427 +2025-04-19 08:08:51,884 INFO Epoch:35 val_res:0.672000 +2025-04-19 08:09:24,691 INFO Epoch:36 train_loss:0.82593 +2025-04-19 08:09:32,668 INFO Epoch:36 val_res:0.675200 +2025-04-19 08:10:05,688 INFO Epoch:37 train_loss:0.80039 +2025-04-19 08:10:13,415 INFO Epoch:37 val_res:0.673600 +2025-04-19 08:10:46,483 INFO Epoch:38 train_loss:0.80417 +2025-04-19 08:10:55,129 INFO Epoch:38 val_res:0.676000 +2025-04-19 08:11:31,019 INFO Epoch:39 train_loss:0.79868 +2025-04-19 08:11:40,253 INFO Epoch:39 val_res:0.681200 +2025-04-19 08:11:40,253 INFO Saving best model at Epoch 39 +2025-04-19 08:12:15,479 INFO Epoch:40 train_loss:0.80134 +2025-04-19 08:12:23,384 INFO Epoch:40 val_res:0.676800 +2025-04-19 08:12:56,512 INFO Epoch:41 train_loss:0.82602 +2025-04-19 08:13:04,289 INFO Epoch:41 val_res:0.677200 +2025-04-19 08:13:39,547 INFO Epoch:42 train_loss:0.80762 +2025-04-19 08:13:48,124 INFO Epoch:42 val_res:0.673200 +2025-04-19 08:15:00,508 INFO Epoch:43 train_loss:0.79354 +2025-04-19 08:15:09,846 INFO Epoch:43 val_res:0.677200 +2025-04-19 08:15:44,911 INFO Epoch:44 train_loss:0.75327 +2025-04-19 08:15:53,720 INFO Epoch:44 val_res:0.678800 +2025-04-19 08:16:29,119 INFO Epoch:45 train_loss:0.75229 +2025-04-19 08:16:38,365 INFO Epoch:45 val_res:0.677200 +2025-04-19 08:17:15,102 INFO Epoch:46 train_loss:0.77368 +2025-04-19 08:17:24,239 INFO Epoch:46 val_res:0.675600 +2025-04-19 08:18:00,970 INFO Epoch:47 train_loss:0.73633 +2025-04-19 08:18:09,995 INFO Epoch:47 val_res:0.672800 +2025-04-19 08:18:46,450 INFO Epoch:48 train_loss:0.71527 +2025-04-19 08:18:55,179 INFO Epoch:48 val_res:0.672000 +2025-04-19 08:19:32,899 INFO Epoch:49 train_loss:0.73954 +2025-04-19 08:19:41,604 INFO Epoch:49 val_res:0.674000 +2025-04-19 08:20:17,254 INFO Epoch:50 train_loss:0.74330 +2025-04-19 08:20:25,897 INFO Epoch:50 val_res:0.670800 +2025-04-19 08:21:02,470 INFO Epoch:51 train_loss:0.72911 +2025-04-19 08:21:10,754 INFO Epoch:51 val_res:0.666400 +2025-04-19 08:21:47,563 INFO Epoch:52 train_loss:0.71801 +2025-04-19 08:21:56,058 INFO Epoch:52 val_res:0.672000 +2025-04-19 08:22:33,608 INFO Epoch:53 train_loss:0.71667 +2025-04-19 08:22:42,507 INFO Epoch:53 val_res:0.676000 +2025-04-19 08:23:19,240 INFO Epoch:54 train_loss:0.74841 +2025-04-19 08:23:28,068 INFO Epoch:54 val_res:0.671600 +2025-04-19 08:24:04,806 INFO Epoch:55 train_loss:0.68784 +2025-04-19 08:24:13,417 INFO Epoch:55 val_res:0.666800 +2025-04-19 08:24:48,866 INFO Epoch:56 train_loss:0.69051 +2025-04-19 08:24:58,045 INFO Epoch:56 val_res:0.670800 +2025-04-19 08:25:33,294 INFO Epoch:57 train_loss:0.69742 +2025-04-19 08:25:41,444 INFO Epoch:57 val_res:0.673600 +2025-04-19 08:26:14,743 INFO Epoch:58 train_loss:0.69698 +2025-04-19 08:26:23,100 INFO Epoch:58 val_res:0.668800 +2025-04-19 08:26:56,845 INFO Epoch:59 train_loss:0.66724 +2025-04-19 08:27:05,716 INFO Epoch:59 val_res:0.666800 +2025-04-19 08:27:40,307 INFO Epoch:60 train_loss:0.66920 +2025-04-19 08:27:49,097 INFO Epoch:60 val_res:0.671200 +2025-04-19 08:28:25,100 INFO Epoch:61 train_loss:0.66108 +2025-04-19 08:28:33,361 INFO Epoch:61 val_res:0.665200 +2025-04-19 08:29:08,297 INFO Epoch:62 train_loss:0.71330 +2025-04-19 08:29:17,512 INFO Epoch:62 val_res:0.666400 +2025-04-19 08:29:51,961 INFO Epoch:63 train_loss:0.73513 +2025-04-19 08:30:00,888 INFO Epoch:63 val_res:0.670400 +2025-04-19 08:30:35,738 INFO Epoch:64 train_loss:0.69154 +2025-04-19 08:30:44,487 INFO Epoch:64 val_res:0.668800 +2025-04-19 08:31:20,515 INFO Epoch:65 train_loss:0.65712 +2025-04-19 08:31:29,470 INFO Epoch:65 val_res:0.663600 +2025-04-19 08:32:05,354 INFO Epoch:66 train_loss:0.65681 +2025-04-19 08:32:13,779 INFO Epoch:66 val_res:0.665600 +2025-04-19 08:32:50,585 INFO Epoch:67 train_loss:0.65490 +2025-04-19 08:32:59,395 INFO Epoch:67 val_res:0.666800 +2025-04-19 08:33:35,428 INFO Epoch:68 train_loss:0.63716 +2025-04-19 08:33:44,497 INFO Epoch:68 val_res:0.663600 +2025-04-19 08:34:20,613 INFO Epoch:69 train_loss:0.64345 +2025-04-19 08:34:29,212 INFO Epoch:69 val_res:0.668000 +2025-04-19 08:35:05,448 INFO Epoch:70 train_loss:0.63401 +2025-04-19 08:35:14,077 INFO Epoch:70 val_res:0.666400 +2025-04-19 08:35:49,708 INFO Epoch:71 train_loss:0.63407 +2025-04-19 08:35:58,439 INFO Epoch:71 val_res:0.666800 +2025-04-19 08:36:34,337 INFO Epoch:72 train_loss:0.61944 +2025-04-19 08:36:43,629 INFO Epoch:72 val_res:0.664000 +2025-04-19 08:37:19,532 INFO Epoch:73 train_loss:0.63712 +2025-04-19 08:37:27,948 INFO Epoch:73 val_res:0.668800 +2025-04-19 08:38:04,797 INFO Epoch:74 train_loss:0.66238 +2025-04-19 08:38:14,373 INFO Epoch:74 val_res:0.665600 +2025-04-19 08:38:50,026 INFO Epoch:75 train_loss:0.64795 +2025-04-19 08:38:58,741 INFO Epoch:75 val_res:0.667200 +2025-04-19 08:39:34,600 INFO Epoch:76 train_loss:0.65511 +2025-04-19 08:39:43,277 INFO Epoch:76 val_res:0.660400 +2025-04-19 08:40:19,986 INFO Epoch:77 train_loss:0.62604 +2025-04-19 08:40:28,648 INFO Epoch:77 val_res:0.664800 +2025-04-19 08:41:05,324 INFO Epoch:78 train_loss:0.62050 +2025-04-19 08:41:14,230 INFO Epoch:78 val_res:0.664000 +2025-04-19 08:41:49,923 INFO Epoch:79 train_loss:0.61498 +2025-04-19 08:41:58,894 INFO Epoch:79 val_res:0.662800 +2025-04-19 08:42:35,559 INFO Epoch:80 train_loss:0.63895 +2025-04-19 08:42:44,352 INFO Epoch:80 val_res:0.666800 +2025-04-19 08:43:19,837 INFO Epoch:81 train_loss:0.61496 +2025-04-19 08:43:28,850 INFO Epoch:81 val_res:0.666800 +2025-04-19 08:44:04,765 INFO Epoch:82 train_loss:0.62156 +2025-04-19 08:44:13,663 INFO Epoch:82 val_res:0.658800 +2025-04-19 08:44:48,502 INFO Epoch:83 train_loss:0.65778 +2025-04-19 08:44:57,414 INFO Epoch:83 val_res:0.664400 +2025-04-19 08:45:34,028 INFO Epoch:84 train_loss:0.62456 +2025-04-19 08:45:43,046 INFO Epoch:84 val_res:0.670000 +2025-04-19 08:46:19,129 INFO Epoch:85 train_loss:0.61255 +2025-04-19 08:46:28,252 INFO Epoch:85 val_res:0.668400 +2025-04-19 08:47:03,569 INFO Epoch:86 train_loss:0.61072 +2025-04-19 08:47:12,426 INFO Epoch:86 val_res:0.665200 +2025-04-19 08:47:48,713 INFO Epoch:87 train_loss:0.60899 +2025-04-19 08:47:57,209 INFO Epoch:87 val_res:0.666000 +2025-04-19 08:48:33,814 INFO Epoch:88 train_loss:0.58027 +2025-04-19 08:48:42,471 INFO Epoch:88 val_res:0.665600 +2025-04-19 08:49:18,843 INFO Epoch:89 train_loss:0.57669 +2025-04-19 08:49:27,496 INFO Epoch:89 val_res:0.670800 +2025-04-19 08:50:04,332 INFO Epoch:90 train_loss:0.56622 +2025-04-19 08:50:12,830 INFO Epoch:90 val_res:0.660400 +2025-04-19 08:50:49,831 INFO Epoch:91 train_loss:0.63048 +2025-04-19 08:50:59,113 INFO Epoch:91 val_res:0.657600 +2025-04-19 08:51:35,177 INFO Epoch:92 train_loss:0.57302 +2025-04-19 08:51:44,085 INFO Epoch:92 val_res:0.662000 +2025-04-19 08:52:21,330 INFO Epoch:93 train_loss:0.59749 +2025-04-19 08:52:30,176 INFO Epoch:93 val_res:0.666400 +2025-04-19 08:53:07,431 INFO Epoch:94 train_loss:0.59860 +2025-04-19 08:53:16,279 INFO Epoch:94 val_res:0.662800 +2025-04-19 08:53:54,050 INFO Epoch:95 train_loss:0.62862 +2025-04-19 08:54:03,661 INFO Epoch:95 val_res:0.658800 +2025-04-19 08:54:40,094 INFO Epoch:96 train_loss:0.59410 +2025-04-19 08:54:48,712 INFO Epoch:96 val_res:0.663200 +2025-04-19 08:55:26,331 INFO Epoch:97 train_loss:0.57868 +2025-04-19 08:55:35,885 INFO Epoch:97 val_res:0.662000 +2025-04-19 08:56:12,625 INFO Epoch:98 train_loss:0.56994 +2025-04-19 08:56:21,814 INFO Epoch:98 val_res:0.665200 +2025-04-19 08:56:57,232 INFO Epoch:99 train_loss:0.55193 +2025-04-19 08:57:06,180 INFO Epoch:99 val_res:0.660000 +2025-04-19 08:57:07,032 INFO ===================================== +2025-04-19 08:57:07,033 INFO Start testing... +2025-04-19 08:57:07,033 INFO ===================================== +2025-04-19 08:57:16,839 INFO Incremental step 4 Testing res: 0.691200 +2025-04-19 08:57:16,841 INFO forgetting: 0.074000 +2025-04-19 08:57:16,845 INFO ***************New Step*************************** +2025-04-19 08:57:16,845 INFO Incremental step: 5 +2025-04-19 08:57:17,023 INFO actual size of exemplar set: 1500 +2025-04-19 08:57:52,868 INFO Epoch:0 train_loss:7.64315 +2025-04-19 08:58:04,478 INFO Epoch:0 val_res:0.563000 +2025-04-19 08:58:04,479 INFO Saving best model at Epoch 0 +2025-04-19 08:58:42,377 INFO Epoch:1 train_loss:2.80866 +2025-04-19 08:58:52,915 INFO Epoch:1 val_res:0.585333 +2025-04-19 08:58:52,916 INFO Saving best model at Epoch 1 +2025-04-19 08:59:29,789 INFO Epoch:2 train_loss:1.97108 +2025-04-19 08:59:41,271 INFO Epoch:2 val_res:0.593000 +2025-04-19 08:59:41,274 INFO Saving best model at Epoch 2 +2025-04-19 09:00:16,154 INFO Epoch:3 train_loss:1.70387 +2025-04-19 09:00:26,816 INFO Epoch:3 val_res:0.594333 +2025-04-19 09:00:26,817 INFO Saving best model at Epoch 3 +2025-04-19 09:01:03,221 INFO Epoch:4 train_loss:1.54062 +2025-04-19 09:01:14,142 INFO Epoch:4 val_res:0.598000 +2025-04-19 09:01:14,142 INFO Saving best model at Epoch 4 +2025-04-19 09:01:49,544 INFO Epoch:5 train_loss:1.46268 +2025-04-19 09:02:00,481 INFO Epoch:5 val_res:0.594000 +2025-04-19 09:02:33,895 INFO Epoch:6 train_loss:1.37892 +2025-04-19 09:02:44,903 INFO Epoch:6 val_res:0.597667 +2025-04-19 09:03:19,118 INFO Epoch:7 train_loss:1.33169 +2025-04-19 09:03:29,737 INFO Epoch:7 val_res:0.600000 +2025-04-19 09:03:29,737 INFO Saving best model at Epoch 7 +2025-04-19 09:04:04,830 INFO Epoch:8 train_loss:1.29299 +2025-04-19 09:04:14,768 INFO Epoch:8 val_res:0.601333 +2025-04-19 09:04:14,768 INFO Saving best model at Epoch 8 +2025-04-19 09:04:48,544 INFO Epoch:9 train_loss:1.25094 +2025-04-19 09:04:57,560 INFO Epoch:9 val_res:0.600333 +2025-04-19 09:05:30,530 INFO Epoch:10 train_loss:1.21975 +2025-04-19 09:05:39,942 INFO Epoch:10 val_res:0.603667 +2025-04-19 09:05:39,942 INFO Saving best model at Epoch 10 +2025-04-19 09:06:14,027 INFO Epoch:11 train_loss:1.19971 +2025-04-19 09:06:24,089 INFO Epoch:11 val_res:0.605000 +2025-04-19 09:06:24,089 INFO Saving best model at Epoch 11 +2025-04-19 09:07:00,346 INFO Epoch:12 train_loss:1.16558 +2025-04-19 09:07:10,046 INFO Epoch:12 val_res:0.607667 +2025-04-19 09:07:10,046 INFO Saving best model at Epoch 12 +2025-04-19 09:07:42,994 INFO Epoch:13 train_loss:1.15366 +2025-04-19 09:07:53,043 INFO Epoch:13 val_res:0.606667 +2025-04-19 09:08:22,927 INFO Epoch:14 train_loss:1.11244 +2025-04-19 09:08:32,351 INFO Epoch:14 val_res:0.610667 +2025-04-19 09:08:32,351 INFO Saving best model at Epoch 14 +2025-04-19 09:09:03,919 INFO Epoch:15 train_loss:1.08253 +2025-04-19 09:09:12,982 INFO Epoch:15 val_res:0.610333 +2025-04-19 09:09:43,237 INFO Epoch:16 train_loss:1.07867 +2025-04-19 09:09:52,429 INFO Epoch:16 val_res:0.611667 +2025-04-19 09:09:52,430 INFO Saving best model at Epoch 16 +2025-04-19 09:10:24,188 INFO Epoch:17 train_loss:1.05943 +2025-04-19 09:10:33,544 INFO Epoch:17 val_res:0.614667 +2025-04-19 09:10:33,544 INFO Saving best model at Epoch 17 +2025-04-19 09:11:06,241 INFO Epoch:18 train_loss:1.06762 +2025-04-19 09:11:14,825 INFO Epoch:18 val_res:0.616000 +2025-04-19 09:11:14,825 INFO Saving best model at Epoch 18 +2025-04-19 09:11:46,677 INFO Epoch:19 train_loss:1.04212 +2025-04-19 09:11:55,885 INFO Epoch:19 val_res:0.620667 +2025-04-19 09:11:55,886 INFO Saving best model at Epoch 19 +2025-04-19 09:12:28,177 INFO Epoch:20 train_loss:1.04697 +2025-04-19 09:12:37,177 INFO Epoch:20 val_res:0.620000 +2025-04-19 09:13:08,232 INFO Epoch:21 train_loss:0.99879 +2025-04-19 09:13:17,511 INFO Epoch:21 val_res:0.617333 +2025-04-19 09:13:47,098 INFO Epoch:22 train_loss:0.97949 +2025-04-19 09:13:56,057 INFO Epoch:22 val_res:0.624000 +2025-04-19 09:13:56,058 INFO Saving best model at Epoch 22 +2025-04-19 09:14:29,111 INFO Epoch:23 train_loss:0.95083 +2025-04-19 09:14:38,867 INFO Epoch:23 val_res:0.624333 +2025-04-19 09:14:38,867 INFO Saving best model at Epoch 23 +2025-04-19 09:15:12,871 INFO Epoch:24 train_loss:0.95458 +2025-04-19 09:15:22,580 INFO Epoch:24 val_res:0.627000 +2025-04-19 09:15:22,580 INFO Saving best model at Epoch 24 +2025-04-19 09:15:56,147 INFO Epoch:25 train_loss:0.94309 +2025-04-19 09:16:06,277 INFO Epoch:25 val_res:0.630333 +2025-04-19 09:16:06,278 INFO Saving best model at Epoch 25 +2025-04-19 09:16:40,365 INFO Epoch:26 train_loss:0.91397 +2025-04-19 09:16:49,800 INFO Epoch:26 val_res:0.630000 +2025-04-19 09:17:22,116 INFO Epoch:27 train_loss:0.93112 +2025-04-19 09:17:30,991 INFO Epoch:27 val_res:0.629000 +2025-04-19 09:18:02,882 INFO Epoch:28 train_loss:0.92715 +2025-04-19 09:18:12,681 INFO Epoch:28 val_res:0.631000 +2025-04-19 09:18:12,682 INFO Saving best model at Epoch 28 +2025-04-19 09:18:46,372 INFO Epoch:29 train_loss:0.91271 +2025-04-19 09:18:55,903 INFO Epoch:29 val_res:0.630667 +2025-04-19 09:19:29,225 INFO Epoch:30 train_loss:0.89719 +2025-04-19 09:19:39,315 INFO Epoch:30 val_res:0.633333 +2025-04-19 09:19:39,315 INFO Saving best model at Epoch 30 +2025-04-19 09:20:14,399 INFO Epoch:31 train_loss:0.85351 +2025-04-19 09:20:24,139 INFO Epoch:31 val_res:0.640667 +2025-04-19 09:20:24,140 INFO Saving best model at Epoch 31 +2025-04-19 09:20:57,222 INFO Epoch:32 train_loss:0.82696 +2025-04-19 09:21:07,197 INFO Epoch:32 val_res:0.638000 +2025-04-19 09:21:38,724 INFO Epoch:33 train_loss:0.81798 +2025-04-19 09:21:48,785 INFO Epoch:33 val_res:0.640667 +2025-04-19 09:22:22,328 INFO Epoch:34 train_loss:0.82530 +2025-04-19 09:22:32,314 INFO Epoch:34 val_res:0.638333 +2025-04-19 09:23:04,689 INFO Epoch:35 train_loss:0.81703 +2025-04-19 09:23:14,764 INFO Epoch:35 val_res:0.638000 +2025-04-19 09:23:48,003 INFO Epoch:36 train_loss:0.78717 +2025-04-19 09:23:57,894 INFO Epoch:36 val_res:0.639000 +2025-04-19 09:24:30,722 INFO Epoch:37 train_loss:0.81394 +2025-04-19 09:24:40,048 INFO Epoch:37 val_res:0.642333 +2025-04-19 09:24:40,048 INFO Saving best model at Epoch 37 +2025-04-19 09:25:12,178 INFO Epoch:38 train_loss:0.78680 +2025-04-19 09:25:21,590 INFO Epoch:38 val_res:0.637333 +2025-04-19 09:25:52,924 INFO Epoch:39 train_loss:0.80437 +2025-04-19 09:26:02,185 INFO Epoch:39 val_res:0.642333 +2025-04-19 09:26:32,538 INFO Epoch:40 train_loss:0.79756 +2025-04-19 09:26:42,054 INFO Epoch:40 val_res:0.644333 +2025-04-19 09:26:42,054 INFO Saving best model at Epoch 40 +2025-04-19 09:27:14,372 INFO Epoch:41 train_loss:0.77322 +2025-04-19 09:27:23,909 INFO Epoch:41 val_res:0.641333 +2025-04-19 09:27:54,476 INFO Epoch:42 train_loss:0.74650 +2025-04-19 09:28:03,557 INFO Epoch:42 val_res:0.643333 +2025-04-19 09:28:33,920 INFO Epoch:43 train_loss:0.74772 +2025-04-19 09:28:43,016 INFO Epoch:43 val_res:0.640000 +2025-04-19 09:29:13,031 INFO Epoch:44 train_loss:0.75812 +2025-04-19 09:29:21,898 INFO Epoch:44 val_res:0.637000 +2025-04-19 09:29:51,496 INFO Epoch:45 train_loss:0.84717 +2025-04-19 09:30:00,553 INFO Epoch:45 val_res:0.639000 +2025-04-19 09:30:30,855 INFO Epoch:46 train_loss:0.78708 +2025-04-19 09:30:39,664 INFO Epoch:46 val_res:0.634667 +2025-04-19 09:31:09,126 INFO Epoch:47 train_loss:0.71763 +2025-04-19 09:31:17,943 INFO Epoch:47 val_res:0.635667 +2025-04-19 09:31:48,614 INFO Epoch:48 train_loss:0.70167 +2025-04-19 09:31:57,487 INFO Epoch:48 val_res:0.640000 +2025-04-19 09:32:28,136 INFO Epoch:49 train_loss:0.69399 +2025-04-19 09:32:36,960 INFO Epoch:49 val_res:0.640667 +2025-04-19 09:33:07,458 INFO Epoch:50 train_loss:0.69736 +2025-04-19 09:33:16,386 INFO Epoch:50 val_res:0.640333 +2025-04-19 09:33:47,438 INFO Epoch:51 train_loss:0.72255 +2025-04-19 09:33:56,066 INFO Epoch:51 val_res:0.637333 +2025-04-19 09:34:26,221 INFO Epoch:52 train_loss:0.74430 +2025-04-19 09:34:35,275 INFO Epoch:52 val_res:0.641000 +2025-04-19 09:35:05,219 INFO Epoch:53 train_loss:0.71242 +2025-04-19 09:35:14,481 INFO Epoch:53 val_res:0.641000 +2025-04-19 09:35:44,274 INFO Epoch:54 train_loss:0.66891 +2025-04-19 09:35:53,450 INFO Epoch:54 val_res:0.637333 +2025-04-19 09:36:24,356 INFO Epoch:55 train_loss:0.66981 +2025-04-19 09:36:33,274 INFO Epoch:55 val_res:0.640000 +2025-04-19 09:37:04,125 INFO Epoch:56 train_loss:0.65881 +2025-04-19 09:37:13,367 INFO Epoch:56 val_res:0.638333 +2025-04-19 09:37:45,689 INFO Epoch:57 train_loss:0.65274 +2025-04-19 09:37:55,809 INFO Epoch:57 val_res:0.633667 +2025-04-19 09:38:25,222 INFO Epoch:58 train_loss:0.66561 +2025-04-19 09:38:34,432 INFO Epoch:58 val_res:0.637000 +2025-04-19 09:39:05,050 INFO Epoch:59 train_loss:0.66410 +2025-04-19 09:39:14,122 INFO Epoch:59 val_res:0.637333 +2025-04-19 09:39:44,403 INFO Epoch:60 train_loss:0.66874 +2025-04-19 09:39:53,356 INFO Epoch:60 val_res:0.638667 +2025-04-19 09:40:23,184 INFO Epoch:61 train_loss:0.66826 +2025-04-19 09:40:31,915 INFO Epoch:61 val_res:0.639667 +2025-04-19 09:41:02,439 INFO Epoch:62 train_loss:0.67208 +2025-04-19 09:41:11,103 INFO Epoch:62 val_res:0.632000 +2025-04-19 09:41:41,540 INFO Epoch:63 train_loss:0.68302 +2025-04-19 09:41:50,320 INFO Epoch:63 val_res:0.637000 +2025-04-19 09:42:20,483 INFO Epoch:64 train_loss:0.66106 +2025-04-19 09:42:29,287 INFO Epoch:64 val_res:0.639667 +2025-04-19 09:42:59,427 INFO Epoch:65 train_loss:0.62850 +2025-04-19 09:43:08,311 INFO Epoch:65 val_res:0.629333 +2025-04-19 09:43:37,943 INFO Epoch:66 train_loss:0.65058 +2025-04-19 09:43:46,973 INFO Epoch:66 val_res:0.636333 +2025-04-19 09:44:17,049 INFO Epoch:67 train_loss:0.63253 +2025-04-19 09:44:26,170 INFO Epoch:67 val_res:0.634000 +2025-04-19 09:44:56,921 INFO Epoch:68 train_loss:0.63842 +2025-04-19 09:45:06,123 INFO Epoch:68 val_res:0.639667 +2025-04-19 09:45:35,933 INFO Epoch:69 train_loss:0.62010 +2025-04-19 09:45:44,908 INFO Epoch:69 val_res:0.635667 +2025-04-19 09:46:15,169 INFO Epoch:70 train_loss:0.61650 +2025-04-19 09:46:24,318 INFO Epoch:70 val_res:0.636000 +2025-04-19 09:46:54,055 INFO Epoch:71 train_loss:0.66534 +2025-04-19 09:47:03,150 INFO Epoch:71 val_res:0.635000 +2025-04-19 09:47:32,815 INFO Epoch:72 train_loss:0.64582 +2025-04-19 09:47:41,794 INFO Epoch:72 val_res:0.634333 +2025-04-19 09:48:11,347 INFO Epoch:73 train_loss:0.63275 +2025-04-19 09:48:20,383 INFO Epoch:73 val_res:0.635333 +2025-04-19 09:48:50,005 INFO Epoch:74 train_loss:0.64802 +2025-04-19 09:48:58,801 INFO Epoch:74 val_res:0.631333 +2025-04-19 09:49:28,802 INFO Epoch:75 train_loss:0.64191 +2025-04-19 09:49:37,609 INFO Epoch:75 val_res:0.635333 +2025-04-19 09:50:08,084 INFO Epoch:76 train_loss:0.62605 +2025-04-19 09:50:17,094 INFO Epoch:76 val_res:0.630667 +2025-04-19 09:50:47,024 INFO Epoch:77 train_loss:0.61009 +2025-04-19 09:50:55,844 INFO Epoch:77 val_res:0.637000 +2025-04-19 09:51:26,424 INFO Epoch:78 train_loss:0.59195 +2025-04-19 09:51:35,253 INFO Epoch:78 val_res:0.634000 +2025-04-19 09:52:05,993 INFO Epoch:79 train_loss:0.60242 +2025-04-19 09:52:15,126 INFO Epoch:79 val_res:0.631667 +2025-04-19 09:52:45,100 INFO Epoch:80 train_loss:0.61905 +2025-04-19 09:52:54,345 INFO Epoch:80 val_res:0.638333 +2025-04-19 09:53:25,008 INFO Epoch:81 train_loss:0.59294 +2025-04-19 09:53:34,049 INFO Epoch:81 val_res:0.632000 +2025-04-19 09:54:04,731 INFO Epoch:82 train_loss:0.58906 +2025-04-19 09:54:13,749 INFO Epoch:82 val_res:0.630333 +2025-04-19 09:54:43,048 INFO Epoch:83 train_loss:0.59618 +2025-04-19 09:54:52,270 INFO Epoch:83 val_res:0.632333 +2025-04-19 09:55:21,464 INFO Epoch:84 train_loss:0.74882 +2025-04-19 09:55:30,594 INFO Epoch:84 val_res:0.632667 +2025-04-19 09:56:00,111 INFO Epoch:85 train_loss:0.65286 +2025-04-19 09:56:09,026 INFO Epoch:85 val_res:0.630333 +2025-04-19 09:56:38,208 INFO Epoch:86 train_loss:0.58711 +2025-04-19 09:56:47,223 INFO Epoch:86 val_res:0.630333 +2025-04-19 09:57:16,893 INFO Epoch:87 train_loss:0.56795 +2025-04-19 09:57:25,982 INFO Epoch:87 val_res:0.629000 +2025-04-19 09:57:55,573 INFO Epoch:88 train_loss:0.57434 +2025-04-19 09:58:05,203 INFO Epoch:88 val_res:0.631000 +2025-04-19 09:58:35,385 INFO Epoch:89 train_loss:0.60616 +2025-04-19 09:58:44,477 INFO Epoch:89 val_res:0.629333 +2025-04-19 09:59:14,902 INFO Epoch:90 train_loss:0.58551 +2025-04-19 09:59:23,585 INFO Epoch:90 val_res:0.628000 +2025-04-19 09:59:54,381 INFO Epoch:91 train_loss:0.56364 +2025-04-19 10:00:03,355 INFO Epoch:91 val_res:0.627000 +2025-04-19 10:00:33,998 INFO Epoch:92 train_loss:0.57535 +2025-04-19 10:00:42,858 INFO Epoch:92 val_res:0.630667 +2025-04-19 10:01:12,185 INFO Epoch:93 train_loss:0.54884 +2025-04-19 10:01:20,984 INFO Epoch:93 val_res:0.630000 +2025-04-19 10:01:50,439 INFO Epoch:94 train_loss:0.55373 +2025-04-19 10:01:59,285 INFO Epoch:94 val_res:0.629000 +2025-04-19 10:02:30,024 INFO Epoch:95 train_loss:0.54762 +2025-04-19 10:02:39,738 INFO Epoch:95 val_res:0.629000 +2025-04-19 10:03:10,363 INFO Epoch:96 train_loss:0.58770 +2025-04-19 10:03:19,235 INFO Epoch:96 val_res:0.621667 +2025-04-19 10:03:50,665 INFO Epoch:97 train_loss:0.61290 +2025-04-19 10:04:00,267 INFO Epoch:97 val_res:0.622333 +2025-04-19 10:04:31,938 INFO Epoch:98 train_loss:0.58080 +2025-04-19 10:04:41,250 INFO Epoch:98 val_res:0.626000 +2025-04-19 10:05:13,494 INFO Epoch:99 train_loss:0.55052 +2025-04-19 10:05:22,549 INFO Epoch:99 val_res:0.619667 +2025-04-19 10:05:23,365 INFO ===================================== +2025-04-19 10:05:23,366 INFO Start testing... +2025-04-19 10:05:23,366 INFO ===================================== +2025-04-19 10:05:34,653 INFO Incremental step 5 Testing res: 0.647667 +2025-04-19 10:05:34,656 INFO forgetting: 0.075600 +2025-04-19 10:05:34,661 INFO ***************New Step*************************** +2025-04-19 10:05:34,661 INFO Incremental step: 6 +2025-04-19 10:05:34,990 INFO actual size of exemplar set: 1500 +2025-04-19 10:06:10,863 INFO Epoch:0 train_loss:6.95103 +2025-04-19 10:06:23,060 INFO Epoch:0 val_res:0.557714 +2025-04-19 10:06:23,061 INFO Saving best model at Epoch 0 +2025-04-19 10:06:58,767 INFO Epoch:1 train_loss:2.36057 +2025-04-19 10:07:10,198 INFO Epoch:1 val_res:0.561143 +2025-04-19 10:07:10,198 INFO Saving best model at Epoch 1 +2025-04-19 10:07:47,917 INFO Epoch:2 train_loss:1.63787 +2025-04-19 10:07:59,511 INFO Epoch:2 val_res:0.566000 +2025-04-19 10:07:59,512 INFO Saving best model at Epoch 2 +2025-04-19 10:08:35,870 INFO Epoch:3 train_loss:1.42476 +2025-04-19 10:08:47,106 INFO Epoch:3 val_res:0.571143 +2025-04-19 10:08:47,107 INFO Saving best model at Epoch 3 +2025-04-19 10:09:23,768 INFO Epoch:4 train_loss:1.32099 +2025-04-19 10:09:35,540 INFO Epoch:4 val_res:0.575714 +2025-04-19 10:09:35,541 INFO Saving best model at Epoch 4 +2025-04-19 10:10:11,741 INFO Epoch:5 train_loss:1.26263 +2025-04-19 10:10:23,318 INFO Epoch:5 val_res:0.578286 +2025-04-19 10:10:23,318 INFO Saving best model at Epoch 5 +2025-04-19 10:11:00,468 INFO Epoch:6 train_loss:1.20451 +2025-04-19 10:11:10,790 INFO Epoch:6 val_res:0.578857 +2025-04-19 10:11:10,791 INFO Saving best model at Epoch 6 +2025-04-19 10:11:47,061 INFO Epoch:7 train_loss:1.15899 +2025-04-19 10:11:58,647 INFO Epoch:7 val_res:0.584571 +2025-04-19 10:11:58,654 INFO Saving best model at Epoch 7 +2025-04-19 10:12:36,411 INFO Epoch:8 train_loss:1.10795 +2025-04-19 10:12:48,536 INFO Epoch:8 val_res:0.584857 +2025-04-19 10:12:48,542 INFO Saving best model at Epoch 8 +2025-04-19 10:13:25,063 INFO Epoch:9 train_loss:1.08787 +2025-04-19 10:13:36,128 INFO Epoch:9 val_res:0.587429 +2025-04-19 10:13:36,129 INFO Saving best model at Epoch 9 +2025-04-19 10:14:11,392 INFO Epoch:10 train_loss:1.06664 +2025-04-19 10:14:22,396 INFO Epoch:10 val_res:0.587143 +2025-04-19 10:14:56,184 INFO Epoch:11 train_loss:1.03760 +2025-04-19 10:15:07,138 INFO Epoch:11 val_res:0.590000 +2025-04-19 10:15:07,139 INFO Saving best model at Epoch 11 +2025-04-19 10:15:41,425 INFO Epoch:12 train_loss:1.01663 +2025-04-19 10:15:52,354 INFO Epoch:12 val_res:0.591714 +2025-04-19 10:15:52,354 INFO Saving best model at Epoch 12 +2025-04-19 10:16:27,359 INFO Epoch:13 train_loss:0.97897 +2025-04-19 10:16:38,329 INFO Epoch:13 val_res:0.596286 +2025-04-19 10:16:38,330 INFO Saving best model at Epoch 13 +2025-04-19 10:17:13,333 INFO Epoch:14 train_loss:0.97268 +2025-04-19 10:17:25,032 INFO Epoch:14 val_res:0.596000 +2025-04-19 10:17:58,824 INFO Epoch:15 train_loss:0.96738 +2025-04-19 10:18:09,614 INFO Epoch:15 val_res:0.600857 +2025-04-19 10:18:09,615 INFO Saving best model at Epoch 15 +2025-04-19 10:18:43,487 INFO Epoch:16 train_loss:1.00646 +2025-04-19 10:18:54,050 INFO Epoch:16 val_res:0.602286 +2025-04-19 10:18:54,051 INFO Saving best model at Epoch 16 +2025-04-19 10:19:28,718 INFO Epoch:17 train_loss:0.99384 +2025-04-19 10:19:39,938 INFO Epoch:17 val_res:0.604000 +2025-04-19 10:19:39,938 INFO Saving best model at Epoch 17 +2025-04-19 10:20:14,679 INFO Epoch:18 train_loss:0.91718 +2025-04-19 10:20:26,485 INFO Epoch:18 val_res:0.610571 +2025-04-19 10:20:26,486 INFO Saving best model at Epoch 18 +2025-04-19 10:21:01,497 INFO Epoch:19 train_loss:0.91461 +2025-04-19 10:21:12,693 INFO Epoch:19 val_res:0.612571 +2025-04-19 10:21:12,693 INFO Saving best model at Epoch 19 +2025-04-19 10:21:46,628 INFO Epoch:20 train_loss:0.90749 +2025-04-19 10:21:57,176 INFO Epoch:20 val_res:0.610571 +2025-04-19 10:22:30,665 INFO Epoch:21 train_loss:0.91777 +2025-04-19 10:22:42,031 INFO Epoch:21 val_res:0.616857 +2025-04-19 10:22:42,032 INFO Saving best model at Epoch 21 +2025-04-19 10:23:16,578 INFO Epoch:22 train_loss:0.95404 +2025-04-19 10:23:27,837 INFO Epoch:22 val_res:0.617714 +2025-04-19 10:23:27,838 INFO Saving best model at Epoch 22 +2025-04-19 10:24:03,336 INFO Epoch:23 train_loss:0.89700 +2025-04-19 10:24:14,415 INFO Epoch:23 val_res:0.620286 +2025-04-19 10:24:14,416 INFO Saving best model at Epoch 23 +2025-04-19 10:24:49,822 INFO Epoch:24 train_loss:0.87115 +2025-04-19 10:25:01,036 INFO Epoch:24 val_res:0.625429 +2025-04-19 10:25:01,037 INFO Saving best model at Epoch 24 +2025-04-19 10:25:36,388 INFO Epoch:25 train_loss:0.84028 +2025-04-19 10:25:47,435 INFO Epoch:25 val_res:0.623143 +2025-04-19 10:26:20,491 INFO Epoch:26 train_loss:0.85976 +2025-04-19 10:26:31,566 INFO Epoch:26 val_res:0.626857 +2025-04-19 10:26:31,567 INFO Saving best model at Epoch 26 +2025-04-19 10:27:06,523 INFO Epoch:27 train_loss:0.85894 +2025-04-19 10:27:17,274 INFO Epoch:27 val_res:0.631429 +2025-04-19 10:27:17,275 INFO Saving best model at Epoch 27 +2025-04-19 10:27:51,748 INFO Epoch:28 train_loss:0.84308 +2025-04-19 10:28:02,711 INFO Epoch:28 val_res:0.633714 +2025-04-19 10:28:02,711 INFO Saving best model at Epoch 28 +2025-04-19 10:28:37,132 INFO Epoch:29 train_loss:0.81634 +2025-04-19 10:28:47,904 INFO Epoch:29 val_res:0.632286 +2025-04-19 10:29:20,245 INFO Epoch:30 train_loss:0.90821 +2025-04-19 10:29:31,405 INFO Epoch:30 val_res:0.638000 +2025-04-19 10:29:31,405 INFO Saving best model at Epoch 30 +2025-04-19 10:30:05,811 INFO Epoch:31 train_loss:0.85158 +2025-04-19 10:30:16,689 INFO Epoch:31 val_res:0.638857 +2025-04-19 10:30:16,689 INFO Saving best model at Epoch 31 +2025-04-19 10:30:50,119 INFO Epoch:32 train_loss:0.80944 +2025-04-19 10:31:01,081 INFO Epoch:32 val_res:0.639714 +2025-04-19 10:31:01,081 INFO Saving best model at Epoch 32 +2025-04-19 10:31:36,560 INFO Epoch:33 train_loss:0.81750 +2025-04-19 10:31:47,628 INFO Epoch:33 val_res:0.640000 +2025-04-19 10:31:47,629 INFO Saving best model at Epoch 33 +2025-04-19 10:32:22,280 INFO Epoch:34 train_loss:0.78971 +2025-04-19 10:32:33,295 INFO Epoch:34 val_res:0.640571 +2025-04-19 10:32:33,295 INFO Saving best model at Epoch 34 +2025-04-19 10:33:07,983 INFO Epoch:35 train_loss:0.75475 +2025-04-19 10:33:19,294 INFO Epoch:35 val_res:0.641429 +2025-04-19 10:33:19,294 INFO Saving best model at Epoch 35 +2025-04-19 10:33:53,165 INFO Epoch:36 train_loss:0.76744 +2025-04-19 10:34:04,356 INFO Epoch:36 val_res:0.646000 +2025-04-19 10:34:04,357 INFO Saving best model at Epoch 36 +2025-04-19 10:34:38,450 INFO Epoch:37 train_loss:0.77293 +2025-04-19 10:34:49,646 INFO Epoch:37 val_res:0.645143 +2025-04-19 10:35:21,655 INFO Epoch:38 train_loss:0.76827 +2025-04-19 10:35:33,098 INFO Epoch:38 val_res:0.643429 +2025-04-19 10:36:06,567 INFO Epoch:39 train_loss:0.73937 +2025-04-19 10:36:17,415 INFO Epoch:39 val_res:0.642571 +2025-04-19 10:36:49,468 INFO Epoch:40 train_loss:0.74728 +2025-04-19 10:37:00,936 INFO Epoch:40 val_res:0.646000 +2025-04-19 10:37:33,546 INFO Epoch:41 train_loss:0.73723 +2025-04-19 10:37:44,735 INFO Epoch:41 val_res:0.642571 +2025-04-19 10:38:16,837 INFO Epoch:42 train_loss:0.77559 +2025-04-19 10:38:27,732 INFO Epoch:42 val_res:0.645714 +2025-04-19 10:38:59,839 INFO Epoch:43 train_loss:0.73153 +2025-04-19 10:39:10,734 INFO Epoch:43 val_res:0.646286 +2025-04-19 10:39:10,734 INFO Saving best model at Epoch 43 +2025-04-19 10:39:45,833 INFO Epoch:44 train_loss:0.75247 +2025-04-19 10:39:56,695 INFO Epoch:44 val_res:0.644571 +2025-04-19 10:40:28,804 INFO Epoch:45 train_loss:0.76578 +2025-04-19 10:40:39,557 INFO Epoch:45 val_res:0.647143 +2025-04-19 10:40:39,557 INFO Saving best model at Epoch 45 +2025-04-19 10:41:14,799 INFO Epoch:46 train_loss:0.69258 +2025-04-19 10:41:25,325 INFO Epoch:46 val_res:0.646857 +2025-04-19 10:41:58,079 INFO Epoch:47 train_loss:0.71689 +2025-04-19 10:42:09,027 INFO Epoch:47 val_res:0.646571 +2025-04-19 10:42:42,119 INFO Epoch:48 train_loss:0.71994 +2025-04-19 10:42:52,889 INFO Epoch:48 val_res:0.644571 +2025-04-19 10:43:25,447 INFO Epoch:49 train_loss:0.77964 +2025-04-19 10:43:36,828 INFO Epoch:49 val_res:0.641143 +2025-04-19 10:44:10,366 INFO Epoch:50 train_loss:0.74436 +2025-04-19 10:44:21,366 INFO Epoch:50 val_res:0.644286 +2025-04-19 10:44:53,804 INFO Epoch:51 train_loss:0.68446 +2025-04-19 10:45:05,025 INFO Epoch:51 val_res:0.646857 +2025-04-19 10:45:38,315 INFO Epoch:52 train_loss:0.66308 +2025-04-19 10:45:49,491 INFO Epoch:52 val_res:0.647143 +2025-04-19 10:46:21,641 INFO Epoch:53 train_loss:0.67908 +2025-04-19 10:46:32,709 INFO Epoch:53 val_res:0.648571 +2025-04-19 10:46:32,709 INFO Saving best model at Epoch 53 +2025-04-19 10:47:07,351 INFO Epoch:54 train_loss:0.70695 +2025-04-19 10:47:18,051 INFO Epoch:54 val_res:0.643143 +2025-04-19 10:47:50,828 INFO Epoch:55 train_loss:0.78230 +2025-04-19 10:48:01,661 INFO Epoch:55 val_res:0.640857 +2025-04-19 10:48:34,678 INFO Epoch:56 train_loss:0.68604 +2025-04-19 10:48:45,331 INFO Epoch:56 val_res:0.644000 +2025-04-19 10:49:17,653 INFO Epoch:57 train_loss:0.64817 +2025-04-19 10:49:28,208 INFO Epoch:57 val_res:0.640286 +2025-04-19 10:50:01,224 INFO Epoch:58 train_loss:0.64589 +2025-04-19 10:50:12,061 INFO Epoch:58 val_res:0.640571 +2025-04-19 10:50:44,925 INFO Epoch:59 train_loss:0.64297 +2025-04-19 10:50:55,841 INFO Epoch:59 val_res:0.638286 +2025-04-19 10:51:28,389 INFO Epoch:60 train_loss:0.68179 +2025-04-19 10:51:39,507 INFO Epoch:60 val_res:0.640286 +2025-04-19 10:52:11,368 INFO Epoch:61 train_loss:0.65787 +2025-04-19 10:52:22,213 INFO Epoch:61 val_res:0.636571 +2025-04-19 10:52:55,118 INFO Epoch:62 train_loss:0.64927 +2025-04-19 10:53:05,633 INFO Epoch:62 val_res:0.642000 +2025-04-19 10:53:38,426 INFO Epoch:63 train_loss:0.68565 +2025-04-19 10:53:49,239 INFO Epoch:63 val_res:0.637429 +2025-04-19 10:54:21,457 INFO Epoch:64 train_loss:0.67230 +2025-04-19 10:54:31,687 INFO Epoch:64 val_res:0.634000 +2025-04-19 10:55:05,364 INFO Epoch:65 train_loss:0.71112 +2025-04-19 10:55:15,652 INFO Epoch:65 val_res:0.638286 +2025-04-19 10:55:49,131 INFO Epoch:66 train_loss:0.68395 +2025-04-19 10:55:59,537 INFO Epoch:66 val_res:0.633714 +2025-04-19 10:56:34,954 INFO Epoch:67 train_loss:0.65604 +2025-04-19 10:56:46,640 INFO Epoch:67 val_res:0.637429 +2025-04-19 10:57:21,588 INFO Epoch:68 train_loss:0.64068 +2025-04-19 10:57:32,538 INFO Epoch:68 val_res:0.634286 +2025-04-19 10:58:08,390 INFO Epoch:69 train_loss:0.62849 +2025-04-19 10:58:19,880 INFO Epoch:69 val_res:0.636571 +2025-04-19 10:58:56,461 INFO Epoch:70 train_loss:0.62625 +2025-04-19 10:59:08,341 INFO Epoch:70 val_res:0.630857 +2025-04-19 10:59:41,879 INFO Epoch:71 train_loss:0.65403 +2025-04-19 10:59:52,891 INFO Epoch:71 val_res:0.632000 +2025-04-19 11:00:24,612 INFO Epoch:72 train_loss:0.63095 +2025-04-19 11:00:35,518 INFO Epoch:72 val_res:0.631143 +2025-04-19 11:01:06,974 INFO Epoch:73 train_loss:0.64651 +2025-04-19 11:01:17,556 INFO Epoch:73 val_res:0.632286 +2025-04-19 11:01:50,320 INFO Epoch:74 train_loss:0.67662 +2025-04-19 11:02:00,563 INFO Epoch:74 val_res:0.630000 +2025-04-19 11:02:32,213 INFO Epoch:75 train_loss:0.68224 +2025-04-19 11:02:42,135 INFO Epoch:75 val_res:0.631429 +2025-04-19 11:03:13,761 INFO Epoch:76 train_loss:0.63688 +2025-04-19 11:03:23,551 INFO Epoch:76 val_res:0.632000 +2025-04-19 11:03:55,634 INFO Epoch:77 train_loss:0.61944 +2025-04-19 11:04:05,692 INFO Epoch:77 val_res:0.629714 +2025-04-19 11:04:37,855 INFO Epoch:78 train_loss:0.58989 +2025-04-19 11:04:48,056 INFO Epoch:78 val_res:0.633714 +2025-04-19 11:05:19,698 INFO Epoch:79 train_loss:0.59592 +2025-04-19 11:05:29,747 INFO Epoch:79 val_res:0.628857 +2025-04-19 11:06:01,506 INFO Epoch:80 train_loss:0.61212 +2025-04-19 11:06:12,010 INFO Epoch:80 val_res:0.624857 +2025-04-19 11:06:43,582 INFO Epoch:81 train_loss:0.63080 +2025-04-19 11:06:53,904 INFO Epoch:81 val_res:0.625714 +2025-04-19 11:07:25,932 INFO Epoch:82 train_loss:0.59956 +2025-04-19 11:07:36,287 INFO Epoch:82 val_res:0.625143 +2025-04-19 11:08:08,374 INFO Epoch:83 train_loss:0.65268 +2025-04-19 11:08:18,788 INFO Epoch:83 val_res:0.623714 +2025-04-19 11:08:50,581 INFO Epoch:84 train_loss:0.64026 +2025-04-19 11:09:00,651 INFO Epoch:84 val_res:0.623143 +2025-04-19 11:09:32,419 INFO Epoch:85 train_loss:0.60015 +2025-04-19 11:09:42,191 INFO Epoch:85 val_res:0.629143 +2025-04-19 11:10:15,060 INFO Epoch:86 train_loss:0.61164 +2025-04-19 11:10:25,332 INFO Epoch:86 val_res:0.626286 +2025-04-19 11:10:57,009 INFO Epoch:87 train_loss:0.57842 +2025-04-19 11:11:07,625 INFO Epoch:87 val_res:0.626286 +2025-04-19 11:11:39,340 INFO Epoch:88 train_loss:0.57514 +2025-04-19 11:11:50,588 INFO Epoch:88 val_res:0.621714 +2025-04-19 11:12:22,074 INFO Epoch:89 train_loss:0.57881 +2025-04-19 11:12:33,183 INFO Epoch:89 val_res:0.622000 +2025-04-19 11:13:05,797 INFO Epoch:90 train_loss:0.59803 +2025-04-19 11:13:16,874 INFO Epoch:90 val_res:0.626000 +2025-04-19 11:13:49,918 INFO Epoch:91 train_loss:0.58188 +2025-04-19 11:14:00,941 INFO Epoch:91 val_res:0.620000 +2025-04-19 11:14:33,881 INFO Epoch:92 train_loss:0.61992 +2025-04-19 11:14:45,372 INFO Epoch:92 val_res:0.620571 +2025-04-19 11:15:18,836 INFO Epoch:93 train_loss:0.58875 +2025-04-19 11:15:29,996 INFO Epoch:93 val_res:0.623429 +2025-04-19 11:16:03,278 INFO Epoch:94 train_loss:0.61911 +2025-04-19 11:16:14,312 INFO Epoch:94 val_res:0.622857 +2025-04-19 11:16:48,137 INFO Epoch:95 train_loss:0.60368 +2025-04-19 11:16:59,010 INFO Epoch:95 val_res:0.621143 +2025-04-19 11:17:32,178 INFO Epoch:96 train_loss:0.59556 +2025-04-19 11:17:43,344 INFO Epoch:96 val_res:0.623429 +2025-04-19 11:18:14,972 INFO Epoch:97 train_loss:0.58274 +2025-04-19 11:18:25,029 INFO Epoch:97 val_res:0.623429 +2025-04-19 11:18:56,357 INFO Epoch:98 train_loss:0.59519 +2025-04-19 11:19:06,764 INFO Epoch:98 val_res:0.615714 +2025-04-19 11:19:37,640 INFO Epoch:99 train_loss:0.60038 +2025-04-19 11:19:47,794 INFO Epoch:99 val_res:0.621143 +2025-04-19 11:19:48,564 INFO ===================================== +2025-04-19 11:19:48,565 INFO Start testing... +2025-04-19 11:19:48,566 INFO ===================================== +2025-04-19 11:20:00,029 INFO Incremental step 6 Testing res: 0.647143 +2025-04-19 11:20:00,032 INFO forgetting: 0.069000 +2025-04-19 11:20:00,037 INFO ***************New Step*************************** +2025-04-19 11:20:00,037 INFO Incremental step: 7 +2025-04-19 11:20:00,280 INFO actual size of exemplar set: 1470 +2025-04-19 11:20:39,424 INFO Epoch:0 train_loss:6.66617 +2025-04-19 11:20:53,012 INFO Epoch:0 val_res:0.563750 +2025-04-19 11:20:53,013 INFO Saving best model at Epoch 0 +2025-04-19 11:21:33,362 INFO Epoch:1 train_loss:2.45249 +2025-04-19 11:21:45,798 INFO Epoch:1 val_res:0.569250 +2025-04-19 11:21:45,798 INFO Saving best model at Epoch 1 +2025-04-19 11:22:26,420 INFO Epoch:2 train_loss:1.94340 +2025-04-19 11:22:39,121 INFO Epoch:2 val_res:0.570500 +2025-04-19 11:22:39,121 INFO Saving best model at Epoch 2 +2025-04-19 11:23:18,806 INFO Epoch:3 train_loss:1.75725 +2025-04-19 11:23:31,382 INFO Epoch:3 val_res:0.569250 +2025-04-19 11:24:09,606 INFO Epoch:4 train_loss:1.66069 +2025-04-19 11:24:22,452 INFO Epoch:4 val_res:0.570250 +2025-04-19 11:25:00,884 INFO Epoch:5 train_loss:1.59811 +2025-04-19 11:25:13,452 INFO Epoch:5 val_res:0.569750 +2025-04-19 11:25:50,944 INFO Epoch:6 train_loss:1.53080 +2025-04-19 11:26:03,463 INFO Epoch:6 val_res:0.572250 +2025-04-19 11:26:03,463 INFO Saving best model at Epoch 6 +2025-04-19 11:26:42,277 INFO Epoch:7 train_loss:1.47698 +2025-04-19 11:26:55,042 INFO Epoch:7 val_res:0.575750 +2025-04-19 11:26:55,042 INFO Saving best model at Epoch 7 +2025-04-19 11:27:33,121 INFO Epoch:8 train_loss:1.44713 +2025-04-19 11:27:45,422 INFO Epoch:8 val_res:0.578750 +2025-04-19 11:27:45,422 INFO Saving best model at Epoch 8 +2025-04-19 11:28:24,019 INFO Epoch:9 train_loss:1.40277 +2025-04-19 11:28:36,924 INFO Epoch:9 val_res:0.579750 +2025-04-19 11:28:36,930 INFO Saving best model at Epoch 9 +2025-04-19 11:29:17,128 INFO Epoch:10 train_loss:1.35868 +2025-04-19 11:29:29,711 INFO Epoch:10 val_res:0.578500 +2025-04-19 11:30:07,500 INFO Epoch:11 train_loss:1.32893 +2025-04-19 11:30:19,533 INFO Epoch:11 val_res:0.583000 +2025-04-19 11:30:19,533 INFO Saving best model at Epoch 11 +2025-04-19 11:30:58,608 INFO Epoch:12 train_loss:1.30474 +2025-04-19 11:31:10,975 INFO Epoch:12 val_res:0.585750 +2025-04-19 11:31:10,976 INFO Saving best model at Epoch 12 +2025-04-19 11:31:49,115 INFO Epoch:13 train_loss:1.28415 +2025-04-19 11:32:01,320 INFO Epoch:13 val_res:0.583500 +2025-04-19 11:32:38,896 INFO Epoch:14 train_loss:1.26516 +2025-04-19 11:32:51,085 INFO Epoch:14 val_res:0.587000 +2025-04-19 11:32:51,085 INFO Saving best model at Epoch 14 +2025-04-19 11:33:29,483 INFO Epoch:15 train_loss:1.26256 +2025-04-19 11:33:41,508 INFO Epoch:15 val_res:0.590500 +2025-04-19 11:33:41,509 INFO Saving best model at Epoch 15 +2025-04-19 11:34:21,096 INFO Epoch:16 train_loss:1.26513 +2025-04-19 11:34:33,077 INFO Epoch:16 val_res:0.586500 +2025-04-19 11:35:09,947 INFO Epoch:17 train_loss:1.22300 +2025-04-19 11:35:21,779 INFO Epoch:17 val_res:0.591000 +2025-04-19 11:35:21,779 INFO Saving best model at Epoch 17 +2025-04-19 11:36:01,343 INFO Epoch:18 train_loss:1.16018 +2025-04-19 11:36:13,304 INFO Epoch:18 val_res:0.595250 +2025-04-19 11:36:13,304 INFO Saving best model at Epoch 18 +2025-04-19 11:36:52,565 INFO Epoch:19 train_loss:1.17479 +2025-04-19 11:37:04,403 INFO Epoch:19 val_res:0.593250 +2025-04-19 11:37:42,236 INFO Epoch:20 train_loss:1.15171 +2025-04-19 11:37:54,074 INFO Epoch:20 val_res:0.595750 +2025-04-19 11:37:54,074 INFO Saving best model at Epoch 20 +2025-04-19 11:38:33,374 INFO Epoch:21 train_loss:1.12171 +2025-04-19 11:38:45,295 INFO Epoch:21 val_res:0.601000 +2025-04-19 11:38:45,295 INFO Saving best model at Epoch 21 +2025-04-19 11:39:24,454 INFO Epoch:22 train_loss:1.10452 +2025-04-19 11:39:36,303 INFO Epoch:22 val_res:0.600750 +2025-04-19 11:40:13,713 INFO Epoch:23 train_loss:1.09411 +2025-04-19 11:40:25,485 INFO Epoch:23 val_res:0.602500 +2025-04-19 11:40:25,486 INFO Saving best model at Epoch 23 +2025-04-19 11:41:04,284 INFO Epoch:24 train_loss:1.05840 +2025-04-19 11:41:16,299 INFO Epoch:24 val_res:0.605250 +2025-04-19 11:41:16,300 INFO Saving best model at Epoch 24 +2025-04-19 11:41:54,515 INFO Epoch:25 train_loss:1.04367 +2025-04-19 11:42:06,185 INFO Epoch:25 val_res:0.605000 +2025-04-19 11:42:45,020 INFO Epoch:26 train_loss:1.01993 +2025-04-19 11:42:56,688 INFO Epoch:26 val_res:0.605000 +2025-04-19 11:43:34,350 INFO Epoch:27 train_loss:1.03300 +2025-04-19 11:43:45,984 INFO Epoch:27 val_res:0.614000 +2025-04-19 11:43:45,985 INFO Saving best model at Epoch 27 +2025-04-19 11:44:25,957 INFO Epoch:28 train_loss:1.05374 +2025-04-19 11:44:37,619 INFO Epoch:28 val_res:0.610750 +2025-04-19 11:45:15,293 INFO Epoch:29 train_loss:1.03173 +2025-04-19 11:45:27,027 INFO Epoch:29 val_res:0.611000 +2025-04-19 11:46:03,907 INFO Epoch:30 train_loss:0.98090 +2025-04-19 11:46:15,527 INFO Epoch:30 val_res:0.614250 +2025-04-19 11:46:15,527 INFO Saving best model at Epoch 30 +2025-04-19 11:46:55,767 INFO Epoch:31 train_loss:0.95471 +2025-04-19 11:47:07,499 INFO Epoch:31 val_res:0.617500 +2025-04-19 11:47:07,500 INFO Saving best model at Epoch 31 +2025-04-19 11:47:47,723 INFO Epoch:32 train_loss:0.99671 +2025-04-19 11:47:59,289 INFO Epoch:32 val_res:0.618250 +2025-04-19 11:47:59,289 INFO Saving best model at Epoch 32 +2025-04-19 11:48:38,379 INFO Epoch:33 train_loss:0.99126 +2025-04-19 11:48:50,116 INFO Epoch:33 val_res:0.619500 +2025-04-19 11:48:50,116 INFO Saving best model at Epoch 33 +2025-04-19 11:49:29,549 INFO Epoch:34 train_loss:0.97550 +2025-04-19 11:49:41,199 INFO Epoch:34 val_res:0.621750 +2025-04-19 11:49:41,200 INFO Saving best model at Epoch 34 +2025-04-19 11:50:20,599 INFO Epoch:35 train_loss:0.94151 +2025-04-19 11:50:32,343 INFO Epoch:35 val_res:0.621250 +2025-04-19 11:51:09,206 INFO Epoch:36 train_loss:0.93645 +2025-04-19 11:51:21,029 INFO Epoch:36 val_res:0.619500 +2025-04-19 11:51:59,084 INFO Epoch:37 train_loss:0.90569 +2025-04-19 11:52:11,049 INFO Epoch:37 val_res:0.620500 +2025-04-19 11:52:48,326 INFO Epoch:38 train_loss:0.93495 +2025-04-19 11:53:00,078 INFO Epoch:38 val_res:0.624500 +2025-04-19 11:53:00,078 INFO Saving best model at Epoch 38 +2025-04-19 11:53:39,296 INFO Epoch:39 train_loss:0.91806 +2025-04-19 11:53:50,834 INFO Epoch:39 val_res:0.623500 +2025-04-19 11:54:28,393 INFO Epoch:40 train_loss:0.86385 +2025-04-19 11:54:40,355 INFO Epoch:40 val_res:0.622500 +2025-04-19 11:55:18,737 INFO Epoch:41 train_loss:0.87074 +2025-04-19 11:55:30,434 INFO Epoch:41 val_res:0.625000 +2025-04-19 11:55:30,434 INFO Saving best model at Epoch 41 +2025-04-19 11:56:09,746 INFO Epoch:42 train_loss:0.88698 +2025-04-19 11:56:21,244 INFO Epoch:42 val_res:0.621250 +2025-04-19 11:56:59,559 INFO Epoch:43 train_loss:0.92121 +2025-04-19 11:57:11,414 INFO Epoch:43 val_res:0.621750 +2025-04-19 11:57:50,341 INFO Epoch:44 train_loss:0.87572 +2025-04-19 11:58:02,000 INFO Epoch:44 val_res:0.622500 +2025-04-19 11:58:39,580 INFO Epoch:45 train_loss:0.93335 +2025-04-19 11:58:51,313 INFO Epoch:45 val_res:0.624250 +2025-04-19 11:59:29,210 INFO Epoch:46 train_loss:0.90003 +2025-04-19 11:59:40,824 INFO Epoch:46 val_res:0.623250 +2025-04-19 12:00:17,614 INFO Epoch:47 train_loss:0.86113 +2025-04-19 12:00:29,518 INFO Epoch:47 val_res:0.625750 +2025-04-19 12:00:29,518 INFO Saving best model at Epoch 47 +2025-04-19 12:01:08,683 INFO Epoch:48 train_loss:0.84585 +2025-04-19 12:01:20,021 INFO Epoch:48 val_res:0.624500 +2025-04-19 12:01:58,544 INFO Epoch:49 train_loss:0.81786 +2025-04-19 12:02:10,361 INFO Epoch:49 val_res:0.624500 +2025-04-19 12:02:48,910 INFO Epoch:50 train_loss:0.83553 +2025-04-19 12:03:00,757 INFO Epoch:50 val_res:0.624250 +2025-04-19 12:03:39,033 INFO Epoch:51 train_loss:0.80578 +2025-04-19 12:03:50,799 INFO Epoch:51 val_res:0.619250 +2025-04-19 12:04:29,088 INFO Epoch:52 train_loss:0.82425 +2025-04-19 12:04:41,077 INFO Epoch:52 val_res:0.621750 +2025-04-19 12:05:18,816 INFO Epoch:53 train_loss:0.84101 +2025-04-19 12:05:30,296 INFO Epoch:53 val_res:0.625750 +2025-04-19 12:06:09,714 INFO Epoch:54 train_loss:0.83955 +2025-04-19 12:06:21,610 INFO Epoch:54 val_res:0.623000 +2025-04-19 12:06:59,801 INFO Epoch:55 train_loss:0.80567 +2025-04-19 12:07:11,699 INFO Epoch:55 val_res:0.620750 +2025-04-19 12:07:49,994 INFO Epoch:56 train_loss:0.82345 +2025-04-19 12:08:01,412 INFO Epoch:56 val_res:0.621750 +2025-04-19 12:08:38,266 INFO Epoch:57 train_loss:0.81885 +2025-04-19 12:08:49,728 INFO Epoch:57 val_res:0.620750 +2025-04-19 12:09:27,198 INFO Epoch:58 train_loss:0.81253 +2025-04-19 12:09:38,709 INFO Epoch:58 val_res:0.622500 +2025-04-19 12:10:16,094 INFO Epoch:59 train_loss:0.83539 +2025-04-19 12:10:27,796 INFO Epoch:59 val_res:0.616500 +2025-04-19 12:11:05,964 INFO Epoch:60 train_loss:0.84047 +2025-04-19 12:11:17,575 INFO Epoch:60 val_res:0.619250 +2025-04-19 12:11:55,358 INFO Epoch:61 train_loss:0.79068 +2025-04-19 12:12:06,908 INFO Epoch:61 val_res:0.621750 +2025-04-19 12:12:45,430 INFO Epoch:62 train_loss:0.75612 +2025-04-19 12:12:57,217 INFO Epoch:62 val_res:0.621250 +2025-04-19 12:13:35,281 INFO Epoch:63 train_loss:0.82561 +2025-04-19 12:13:47,248 INFO Epoch:63 val_res:0.619750 +2025-04-19 12:14:25,438 INFO Epoch:64 train_loss:0.84901 +2025-04-19 12:14:37,292 INFO Epoch:64 val_res:0.619000 +2025-04-19 12:15:15,079 INFO Epoch:65 train_loss:0.81911 +2025-04-19 12:15:26,801 INFO Epoch:65 val_res:0.615500 +2025-04-19 12:16:04,669 INFO Epoch:66 train_loss:0.79636 +2025-04-19 12:16:16,544 INFO Epoch:66 val_res:0.619000 +2025-04-19 12:16:54,165 INFO Epoch:67 train_loss:0.77011 +2025-04-19 12:17:06,302 INFO Epoch:67 val_res:0.618750 +2025-04-19 12:17:44,276 INFO Epoch:68 train_loss:0.75947 +2025-04-19 12:17:56,042 INFO Epoch:68 val_res:0.619250 +2025-04-19 12:18:33,098 INFO Epoch:69 train_loss:0.77250 +2025-04-19 12:18:45,126 INFO Epoch:69 val_res:0.616250 +2025-04-19 12:19:23,487 INFO Epoch:70 train_loss:0.75859 +2025-04-19 12:19:35,173 INFO Epoch:70 val_res:0.619750 +2025-04-19 12:20:12,661 INFO Epoch:71 train_loss:0.75468 +2025-04-19 12:20:24,432 INFO Epoch:71 val_res:0.615250 +2025-04-19 12:21:02,005 INFO Epoch:72 train_loss:0.75882 +2025-04-19 12:21:13,469 INFO Epoch:72 val_res:0.618250 +2025-04-19 12:21:50,327 INFO Epoch:73 train_loss:0.76291 +2025-04-19 12:22:01,895 INFO Epoch:73 val_res:0.618000 +2025-04-19 12:22:39,508 INFO Epoch:74 train_loss:0.75279 +2025-04-19 12:22:51,632 INFO Epoch:74 val_res:0.612750 +2025-04-19 12:23:28,279 INFO Epoch:75 train_loss:0.73961 +2025-04-19 12:23:40,192 INFO Epoch:75 val_res:0.613500 +2025-04-19 12:24:17,597 INFO Epoch:76 train_loss:0.75875 +2025-04-19 12:24:29,120 INFO Epoch:76 val_res:0.614000 +2025-04-19 12:25:05,698 INFO Epoch:77 train_loss:0.76283 +2025-04-19 12:25:17,246 INFO Epoch:77 val_res:0.615250 +2025-04-19 12:25:55,060 INFO Epoch:78 train_loss:0.75473 +2025-04-19 12:26:06,387 INFO Epoch:78 val_res:0.613750 +2025-04-19 12:26:43,206 INFO Epoch:79 train_loss:0.80355 +2025-04-19 12:26:54,615 INFO Epoch:79 val_res:0.614000 +2025-04-19 12:27:31,731 INFO Epoch:80 train_loss:0.73525 +2025-04-19 12:27:43,177 INFO Epoch:80 val_res:0.613500 +2025-04-19 12:28:20,106 INFO Epoch:81 train_loss:0.69569 +2025-04-19 12:28:31,726 INFO Epoch:81 val_res:0.614750 +2025-04-19 12:29:08,828 INFO Epoch:82 train_loss:0.77044 +2025-04-19 12:29:20,521 INFO Epoch:82 val_res:0.616250 +2025-04-19 12:29:58,018 INFO Epoch:83 train_loss:0.76799 +2025-04-19 12:30:09,691 INFO Epoch:83 val_res:0.618500 +2025-04-19 12:30:47,199 INFO Epoch:84 train_loss:0.72904 +2025-04-19 12:30:58,876 INFO Epoch:84 val_res:0.615000 +2025-04-19 12:31:35,421 INFO Epoch:85 train_loss:0.74398 +2025-04-19 12:31:47,542 INFO Epoch:85 val_res:0.613500 +2025-04-19 12:32:24,920 INFO Epoch:86 train_loss:0.72275 +2025-04-19 12:32:36,607 INFO Epoch:86 val_res:0.614500 +2025-04-19 12:33:13,183 INFO Epoch:87 train_loss:0.70617 +2025-04-19 12:33:24,624 INFO Epoch:87 val_res:0.615750 +2025-04-19 12:34:02,110 INFO Epoch:88 train_loss:0.70590 +2025-04-19 12:34:13,355 INFO Epoch:88 val_res:0.614500 +2025-04-19 12:34:49,900 INFO Epoch:89 train_loss:0.69243 +2025-04-19 12:35:01,165 INFO Epoch:89 val_res:0.611500 +2025-04-19 12:35:37,938 INFO Epoch:90 train_loss:0.66944 +2025-04-19 12:35:49,562 INFO Epoch:90 val_res:0.612250 +2025-04-19 12:36:26,125 INFO Epoch:91 train_loss:0.71952 +2025-04-19 12:36:37,947 INFO Epoch:91 val_res:0.611250 +2025-04-19 12:37:14,820 INFO Epoch:92 train_loss:0.75473 +2025-04-19 12:37:26,384 INFO Epoch:92 val_res:0.613000 +2025-04-19 12:38:03,154 INFO Epoch:93 train_loss:0.69874 +2025-04-19 12:38:14,929 INFO Epoch:93 val_res:0.613500 +2025-04-19 12:38:51,856 INFO Epoch:94 train_loss:0.67686 +2025-04-19 12:39:03,347 INFO Epoch:94 val_res:0.613250 +2025-04-19 12:39:39,120 INFO Epoch:95 train_loss:0.69522 +2025-04-19 12:39:50,723 INFO Epoch:95 val_res:0.609250 +2025-04-19 12:40:26,047 INFO Epoch:96 train_loss:0.68452 +2025-04-19 12:40:38,334 INFO Epoch:96 val_res:0.613500 +2025-04-19 12:41:14,486 INFO Epoch:97 train_loss:0.74696 +2025-04-19 12:41:25,997 INFO Epoch:97 val_res:0.609250 +2025-04-19 12:42:02,914 INFO Epoch:98 train_loss:0.69818 +2025-04-19 12:42:14,366 INFO Epoch:98 val_res:0.611750 +2025-04-19 12:42:51,278 INFO Epoch:99 train_loss:0.66504 +2025-04-19 12:43:02,641 INFO Epoch:99 val_res:0.609250 +2025-04-19 12:43:03,394 INFO ===================================== +2025-04-19 12:43:03,394 INFO Start testing... +2025-04-19 12:43:03,395 INFO ===================================== +2025-04-19 12:43:15,627 INFO Incremental step 7 Testing res: 0.627250 +2025-04-19 12:43:15,630 INFO forgetting: 0.092000 +2025-04-19 12:43:15,644 INFO ***************New Step*************************** +2025-04-19 12:43:15,644 INFO Incremental step: 8 +2025-04-19 12:43:15,782 INFO actual size of exemplar set: 1440 +2025-04-19 12:43:49,071 INFO Epoch:0 train_loss:7.01160 +2025-04-19 12:44:02,836 INFO Epoch:0 val_res:0.552889 +2025-04-19 12:44:02,837 INFO Saving best model at Epoch 0 +2025-04-19 12:44:37,082 INFO Epoch:1 train_loss:2.17404 +2025-04-19 12:44:50,033 INFO Epoch:1 val_res:0.556889 +2025-04-19 12:44:50,033 INFO Saving best model at Epoch 1 +2025-04-19 12:45:22,823 INFO Epoch:2 train_loss:1.54063 +2025-04-19 12:45:35,301 INFO Epoch:2 val_res:0.560000 +2025-04-19 12:45:35,302 INFO Saving best model at Epoch 2 +2025-04-19 12:46:07,129 INFO Epoch:3 train_loss:1.34581 +2025-04-19 12:46:19,797 INFO Epoch:3 val_res:0.561778 +2025-04-19 12:46:19,798 INFO Saving best model at Epoch 3 +2025-04-19 12:46:51,417 INFO Epoch:4 train_loss:1.26307 +2025-04-19 12:47:03,552 INFO Epoch:4 val_res:0.561111 +2025-04-19 12:47:34,294 INFO Epoch:5 train_loss:1.20636 +2025-04-19 12:47:46,704 INFO Epoch:5 val_res:0.560667 +2025-04-19 12:48:17,435 INFO Epoch:6 train_loss:1.15710 +2025-04-19 12:48:29,812 INFO Epoch:6 val_res:0.566444 +2025-04-19 12:48:29,812 INFO Saving best model at Epoch 6 +2025-04-19 12:49:01,976 INFO Epoch:7 train_loss:1.11193 +2025-04-19 12:49:14,661 INFO Epoch:7 val_res:0.566000 +2025-04-19 12:49:44,450 INFO Epoch:8 train_loss:1.08117 +2025-04-19 12:49:56,876 INFO Epoch:8 val_res:0.566444 +2025-04-19 12:50:27,495 INFO Epoch:9 train_loss:1.06484 +2025-04-19 12:50:40,258 INFO Epoch:9 val_res:0.572222 +2025-04-19 12:50:40,259 INFO Saving best model at Epoch 9 +2025-04-19 12:51:12,738 INFO Epoch:10 train_loss:1.03063 +2025-04-19 12:51:25,489 INFO Epoch:10 val_res:0.572222 +2025-04-19 12:51:55,838 INFO Epoch:11 train_loss:1.02524 +2025-04-19 12:52:08,522 INFO Epoch:11 val_res:0.574222 +2025-04-19 12:52:08,523 INFO Saving best model at Epoch 11 +2025-04-19 12:52:41,192 INFO Epoch:12 train_loss:1.00538 +2025-04-19 12:52:54,310 INFO Epoch:12 val_res:0.575556 +2025-04-19 12:52:54,311 INFO Saving best model at Epoch 12 +2025-04-19 12:53:25,929 INFO Epoch:13 train_loss:0.98936 +2025-04-19 12:53:38,712 INFO Epoch:13 val_res:0.577556 +2025-04-19 12:53:38,712 INFO Saving best model at Epoch 13 +2025-04-19 12:54:10,600 INFO Epoch:14 train_loss:1.10795 +2025-04-19 12:54:23,337 INFO Epoch:14 val_res:0.579778 +2025-04-19 12:54:23,337 INFO Saving best model at Epoch 14 +2025-04-19 12:54:55,279 INFO Epoch:15 train_loss:1.01374 +2025-04-19 12:55:08,113 INFO Epoch:15 val_res:0.582000 +2025-04-19 12:55:08,113 INFO Saving best model at Epoch 15 +2025-04-19 12:55:39,718 INFO Epoch:16 train_loss:0.96477 +2025-04-19 12:55:52,299 INFO Epoch:16 val_res:0.582222 +2025-04-19 12:55:52,299 INFO Saving best model at Epoch 16 +2025-04-19 12:56:24,173 INFO Epoch:17 train_loss:0.94105 +2025-04-19 12:56:36,613 INFO Epoch:17 val_res:0.585333 +2025-04-19 12:56:36,614 INFO Saving best model at Epoch 17 +2025-04-19 12:57:08,604 INFO Epoch:18 train_loss:0.92230 +2025-04-19 12:57:21,120 INFO Epoch:18 val_res:0.585556 +2025-04-19 12:57:21,121 INFO Saving best model at Epoch 18 +2025-04-19 12:57:52,971 INFO Epoch:19 train_loss:0.90757 +2025-04-19 12:58:04,768 INFO Epoch:19 val_res:0.588889 +2025-04-19 12:58:04,768 INFO Saving best model at Epoch 19 +2025-04-19 12:58:37,595 INFO Epoch:20 train_loss:0.89335 +2025-04-19 12:58:49,187 INFO Epoch:20 val_res:0.590889 +2025-04-19 12:58:49,188 INFO Saving best model at Epoch 20 +2025-04-19 12:59:22,216 INFO Epoch:21 train_loss:0.90470 +2025-04-19 12:59:33,960 INFO Epoch:21 val_res:0.592000 +2025-04-19 12:59:33,961 INFO Saving best model at Epoch 21 +2025-04-19 13:00:06,444 INFO Epoch:22 train_loss:0.89600 +2025-04-19 13:00:18,282 INFO Epoch:22 val_res:0.592000 +2025-04-19 13:00:48,813 INFO Epoch:23 train_loss:0.86979 +2025-04-19 13:01:00,726 INFO Epoch:23 val_res:0.592889 +2025-04-19 13:01:00,727 INFO Saving best model at Epoch 23 +2025-04-19 13:01:33,201 INFO Epoch:24 train_loss:0.86642 +2025-04-19 13:01:45,314 INFO Epoch:24 val_res:0.595333 +2025-04-19 13:01:45,314 INFO Saving best model at Epoch 24 +2025-04-19 13:02:17,927 INFO Epoch:25 train_loss:0.87162 +2025-04-19 13:02:29,596 INFO Epoch:25 val_res:0.596222 +2025-04-19 13:02:29,597 INFO Saving best model at Epoch 25 +2025-04-19 13:03:01,400 INFO Epoch:26 train_loss:0.88429 +2025-04-19 13:03:13,227 INFO Epoch:26 val_res:0.592889 +2025-04-19 13:03:43,821 INFO Epoch:27 train_loss:0.92664 +2025-04-19 13:03:55,442 INFO Epoch:27 val_res:0.597333 +2025-04-19 13:03:55,442 INFO Saving best model at Epoch 27 +2025-04-19 13:04:27,500 INFO Epoch:28 train_loss:0.92107 +2025-04-19 13:04:38,884 INFO Epoch:28 val_res:0.594000 +2025-04-19 13:05:09,333 INFO Epoch:29 train_loss:0.81091 +2025-04-19 13:05:21,159 INFO Epoch:29 val_res:0.597111 +2025-04-19 13:05:52,132 INFO Epoch:30 train_loss:0.78714 +2025-04-19 13:06:04,171 INFO Epoch:30 val_res:0.597556 +2025-04-19 13:06:04,172 INFO Saving best model at Epoch 30 +2025-04-19 13:06:36,269 INFO Epoch:31 train_loss:0.79340 +2025-04-19 13:06:47,917 INFO Epoch:31 val_res:0.598667 +2025-04-19 13:06:47,917 INFO Saving best model at Epoch 31 +2025-04-19 13:07:19,908 INFO Epoch:32 train_loss:0.78959 +2025-04-19 13:07:31,811 INFO Epoch:32 val_res:0.597778 +2025-04-19 13:08:02,475 INFO Epoch:33 train_loss:0.79255 +2025-04-19 13:08:14,641 INFO Epoch:33 val_res:0.599111 +2025-04-19 13:08:14,641 INFO Saving best model at Epoch 33 +2025-04-19 13:08:46,255 INFO Epoch:34 train_loss:0.78758 +2025-04-19 13:08:58,190 INFO Epoch:34 val_res:0.600444 +2025-04-19 13:08:58,196 INFO Saving best model at Epoch 34 +2025-04-19 13:09:30,666 INFO Epoch:35 train_loss:0.76860 +2025-04-19 13:09:42,573 INFO Epoch:35 val_res:0.598000 +2025-04-19 13:10:13,061 INFO Epoch:36 train_loss:0.76950 +2025-04-19 13:10:25,035 INFO Epoch:36 val_res:0.601111 +2025-04-19 13:10:25,035 INFO Saving best model at Epoch 36 +2025-04-19 13:10:56,802 INFO Epoch:37 train_loss:0.76434 +2025-04-19 13:11:08,561 INFO Epoch:37 val_res:0.602444 +2025-04-19 13:11:08,561 INFO Saving best model at Epoch 37 +2025-04-19 13:11:41,043 INFO Epoch:38 train_loss:0.75803 +2025-04-19 13:11:53,179 INFO Epoch:38 val_res:0.601111 +2025-04-19 13:12:22,697 INFO Epoch:39 train_loss:0.78884 +2025-04-19 13:12:34,527 INFO Epoch:39 val_res:0.601333 +2025-04-19 13:13:04,861 INFO Epoch:40 train_loss:0.83042 +2025-04-19 13:13:16,721 INFO Epoch:40 val_res:0.606000 +2025-04-19 13:13:16,722 INFO Saving best model at Epoch 40 +2025-04-19 13:13:48,206 INFO Epoch:41 train_loss:0.76650 +2025-04-19 13:14:00,302 INFO Epoch:41 val_res:0.601556 +2025-04-19 13:14:30,477 INFO Epoch:42 train_loss:0.79279 +2025-04-19 13:14:42,533 INFO Epoch:42 val_res:0.602444 +2025-04-19 13:15:12,478 INFO Epoch:43 train_loss:0.72457 +2025-04-19 13:15:24,750 INFO Epoch:43 val_res:0.601111 +2025-04-19 13:15:55,162 INFO Epoch:44 train_loss:0.69733 +2025-04-19 13:16:07,450 INFO Epoch:44 val_res:0.599333 +2025-04-19 13:16:37,399 INFO Epoch:45 train_loss:0.72388 +2025-04-19 13:16:49,755 INFO Epoch:45 val_res:0.599111 +2025-04-19 13:17:20,291 INFO Epoch:46 train_loss:0.71279 +2025-04-19 13:17:32,508 INFO Epoch:46 val_res:0.598222 +2025-04-19 13:18:02,390 INFO Epoch:47 train_loss:0.69547 +2025-04-19 13:18:14,581 INFO Epoch:47 val_res:0.594889 +2025-04-19 13:18:44,319 INFO Epoch:48 train_loss:0.77879 +2025-04-19 13:18:56,479 INFO Epoch:48 val_res:0.596000 +2025-04-19 13:19:27,080 INFO Epoch:49 train_loss:0.70059 +2025-04-19 13:19:39,376 INFO Epoch:49 val_res:0.598000 +2025-04-19 13:20:10,223 INFO Epoch:50 train_loss:0.72344 +2025-04-19 13:20:22,080 INFO Epoch:50 val_res:0.594222 +2025-04-19 13:20:52,640 INFO Epoch:51 train_loss:0.76486 +2025-04-19 13:21:04,772 INFO Epoch:51 val_res:0.594222 +2025-04-19 13:21:34,997 INFO Epoch:52 train_loss:0.66267 +2025-04-19 13:21:47,197 INFO Epoch:52 val_res:0.591778 +2025-04-19 13:22:17,952 INFO Epoch:53 train_loss:0.66608 +2025-04-19 13:22:29,810 INFO Epoch:53 val_res:0.589556 +2025-04-19 13:22:59,853 INFO Epoch:54 train_loss:0.66467 +2025-04-19 13:23:11,779 INFO Epoch:54 val_res:0.588889 +2025-04-19 13:23:42,419 INFO Epoch:55 train_loss:0.65950 +2025-04-19 13:23:54,460 INFO Epoch:55 val_res:0.593111 +2025-04-19 13:24:24,527 INFO Epoch:56 train_loss:0.70092 +2025-04-19 13:24:36,528 INFO Epoch:56 val_res:0.588667 +2025-04-19 13:25:06,164 INFO Epoch:57 train_loss:0.68644 +2025-04-19 13:25:18,085 INFO Epoch:57 val_res:0.587778 +2025-04-19 13:25:49,637 INFO Epoch:58 train_loss:0.73120 +2025-04-19 13:26:01,517 INFO Epoch:58 val_res:0.584667 +2025-04-19 13:26:31,869 INFO Epoch:59 train_loss:0.70347 +2025-04-19 13:26:43,529 INFO Epoch:59 val_res:0.584222 +2025-04-19 13:27:13,636 INFO Epoch:60 train_loss:0.65800 +2025-04-19 13:27:25,441 INFO Epoch:60 val_res:0.581333 +2025-04-19 13:27:55,740 INFO Epoch:61 train_loss:0.65651 +2025-04-19 13:28:07,551 INFO Epoch:61 val_res:0.584444 +2025-04-19 13:28:37,856 INFO Epoch:62 train_loss:0.66116 +2025-04-19 13:28:49,556 INFO Epoch:62 val_res:0.579556 +2025-04-19 13:29:19,689 INFO Epoch:63 train_loss:0.64021 +2025-04-19 13:29:31,570 INFO Epoch:63 val_res:0.581111 +2025-04-19 13:30:02,921 INFO Epoch:64 train_loss:0.66504 +2025-04-19 13:30:14,619 INFO Epoch:64 val_res:0.579778 +2025-04-19 13:30:45,707 INFO Epoch:65 train_loss:0.66215 +2025-04-19 13:30:57,482 INFO Epoch:65 val_res:0.583778 +2025-04-19 13:31:28,383 INFO Epoch:66 train_loss:0.63458 +2025-04-19 13:31:39,920 INFO Epoch:66 val_res:0.572444 +2025-04-19 13:32:10,914 INFO Epoch:67 train_loss:0.62611 +2025-04-19 13:32:22,584 INFO Epoch:67 val_res:0.578667 +2025-04-19 13:32:53,270 INFO Epoch:68 train_loss:0.64313 +2025-04-19 13:33:05,129 INFO Epoch:68 val_res:0.573333 +2025-04-19 13:33:35,950 INFO Epoch:69 train_loss:0.63398 +2025-04-19 13:33:47,600 INFO Epoch:69 val_res:0.573778 +2025-04-19 13:34:18,805 INFO Epoch:70 train_loss:0.68720 +2025-04-19 13:34:30,818 INFO Epoch:70 val_res:0.572889 +2025-04-19 13:35:01,973 INFO Epoch:71 train_loss:0.66399 +2025-04-19 13:35:13,756 INFO Epoch:71 val_res:0.568222 +2025-04-19 13:35:44,317 INFO Epoch:72 train_loss:0.65446 +2025-04-19 13:35:56,009 INFO Epoch:72 val_res:0.572222 +2025-04-19 13:36:26,451 INFO Epoch:73 train_loss:0.61878 +2025-04-19 13:36:38,678 INFO Epoch:73 val_res:0.573111 +2025-04-19 13:37:09,436 INFO Epoch:74 train_loss:0.61217 +2025-04-19 13:37:21,432 INFO Epoch:74 val_res:0.574889 +2025-04-19 13:37:52,184 INFO Epoch:75 train_loss:0.62663 +2025-04-19 13:38:03,966 INFO Epoch:75 val_res:0.574889 +2025-04-19 13:38:34,946 INFO Epoch:76 train_loss:0.61494 +2025-04-19 13:38:46,782 INFO Epoch:76 val_res:0.570444 +2025-04-19 13:39:17,372 INFO Epoch:77 train_loss:0.63417 +2025-04-19 13:39:29,287 INFO Epoch:77 val_res:0.571333 +2025-04-19 13:40:00,253 INFO Epoch:78 train_loss:0.59638 +2025-04-19 13:40:12,048 INFO Epoch:78 val_res:0.569111 +2025-04-19 13:40:43,160 INFO Epoch:79 train_loss:0.61201 +2025-04-19 13:40:55,112 INFO Epoch:79 val_res:0.566889 +2025-04-19 13:41:26,044 INFO Epoch:80 train_loss:0.63103 +2025-04-19 13:41:38,122 INFO Epoch:80 val_res:0.572667 +2025-04-19 13:42:08,361 INFO Epoch:81 train_loss:0.62351 +2025-04-19 13:42:20,248 INFO Epoch:81 val_res:0.568444 +2025-04-19 13:42:50,363 INFO Epoch:82 train_loss:0.60877 +2025-04-19 13:43:02,133 INFO Epoch:82 val_res:0.562889 +2025-04-19 13:43:32,377 INFO Epoch:83 train_loss:0.63345 +2025-04-19 13:43:44,018 INFO Epoch:83 val_res:0.566222 +2025-04-19 13:44:15,054 INFO Epoch:84 train_loss:0.62518 +2025-04-19 13:44:26,684 INFO Epoch:84 val_res:0.560889 +2025-04-19 13:44:56,649 INFO Epoch:85 train_loss:0.67279 +2025-04-19 13:45:08,453 INFO Epoch:85 val_res:0.558889 +2025-04-19 13:45:38,757 INFO Epoch:86 train_loss:0.62730 +2025-04-19 13:45:50,007 INFO Epoch:86 val_res:0.566444 +2025-04-19 13:46:20,729 INFO Epoch:87 train_loss:0.59269 +2025-04-19 13:46:32,801 INFO Epoch:87 val_res:0.560000 +2025-04-19 13:47:03,528 INFO Epoch:88 train_loss:0.60908 +2025-04-19 13:47:15,566 INFO Epoch:88 val_res:0.560222 +2025-04-19 13:47:45,444 INFO Epoch:89 train_loss:0.63276 +2025-04-19 13:47:57,495 INFO Epoch:89 val_res:0.562889 +2025-04-19 13:48:27,387 INFO Epoch:90 train_loss:0.60204 +2025-04-19 13:48:39,238 INFO Epoch:90 val_res:0.558444 +2025-04-19 13:49:09,992 INFO Epoch:91 train_loss:0.57048 +2025-04-19 13:49:22,059 INFO Epoch:91 val_res:0.556667 +2025-04-19 13:49:52,590 INFO Epoch:92 train_loss:0.59987 +2025-04-19 13:50:04,246 INFO Epoch:92 val_res:0.558889 +2025-04-19 13:50:34,279 INFO Epoch:93 train_loss:0.57916 +2025-04-19 13:50:46,219 INFO Epoch:93 val_res:0.555778 +2025-04-19 13:51:15,986 INFO Epoch:94 train_loss:0.56990 +2025-04-19 13:51:28,017 INFO Epoch:94 val_res:0.553778 +2025-04-19 13:51:57,865 INFO Epoch:95 train_loss:0.56064 +2025-04-19 13:52:09,847 INFO Epoch:95 val_res:0.555778 +2025-04-19 13:52:40,068 INFO Epoch:96 train_loss:0.61432 +2025-04-19 13:52:52,068 INFO Epoch:96 val_res:0.552444 +2025-04-19 13:53:21,871 INFO Epoch:97 train_loss:0.59963 +2025-04-19 13:53:33,798 INFO Epoch:97 val_res:0.551556 +2025-04-19 13:54:03,639 INFO Epoch:98 train_loss:0.59141 +2025-04-19 13:54:15,577 INFO Epoch:98 val_res:0.556000 +2025-04-19 13:54:45,052 INFO Epoch:99 train_loss:0.61060 +2025-04-19 13:54:57,023 INFO Epoch:99 val_res:0.551333 +2025-04-19 13:54:57,784 INFO ===================================== +2025-04-19 13:54:57,785 INFO Start testing... +2025-04-19 13:54:57,785 INFO ===================================== +2025-04-19 13:55:10,555 INFO Incremental step 8 Testing res: 0.598889 +2025-04-19 13:55:10,558 INFO forgetting: 0.101000 +2025-04-19 13:55:10,563 INFO ***************New Step*************************** +2025-04-19 13:55:10,563 INFO Incremental step: 9 +2025-04-19 13:55:10,688 INFO actual size of exemplar set: 1440 +2025-04-19 13:55:47,284 INFO Epoch:0 train_loss:6.27762 +2025-04-19 13:56:00,783 INFO Epoch:0 val_res:0.544200 +2025-04-19 13:56:00,784 INFO Saving best model at Epoch 0 +2025-04-19 13:56:38,796 INFO Epoch:1 train_loss:1.73896 +2025-04-19 13:56:52,364 INFO Epoch:1 val_res:0.549000 +2025-04-19 13:56:52,364 INFO Saving best model at Epoch 1 +2025-04-19 13:57:29,242 INFO Epoch:2 train_loss:1.26736 +2025-04-19 13:57:42,190 INFO Epoch:2 val_res:0.553200 +2025-04-19 13:57:42,190 INFO Saving best model at Epoch 2 +2025-04-19 13:58:17,762 INFO Epoch:3 train_loss:1.13740 +2025-04-19 13:58:30,602 INFO Epoch:3 val_res:0.557200 +2025-04-19 13:58:30,603 INFO Saving best model at Epoch 3 +2025-04-19 13:59:07,048 INFO Epoch:4 train_loss:1.06683 +2025-04-19 13:59:19,386 INFO Epoch:4 val_res:0.557800 +2025-04-19 13:59:19,386 INFO Saving best model at Epoch 4 +2025-04-19 13:59:55,441 INFO Epoch:5 train_loss:1.01399 +2025-04-19 14:00:08,404 INFO Epoch:5 val_res:0.559000 +2025-04-19 14:00:08,404 INFO Saving best model at Epoch 5 +2025-04-19 14:00:43,711 INFO Epoch:6 train_loss:0.98006 +2025-04-19 14:00:57,272 INFO Epoch:6 val_res:0.558400 +2025-04-19 14:01:31,813 INFO Epoch:7 train_loss:0.94807 +2025-04-19 14:01:45,208 INFO Epoch:7 val_res:0.560400 +2025-04-19 14:01:45,208 INFO Saving best model at Epoch 7 +2025-04-19 14:02:20,711 INFO Epoch:8 train_loss:0.92271 +2025-04-19 14:02:34,078 INFO Epoch:8 val_res:0.562400 +2025-04-19 14:02:34,078 INFO Saving best model at Epoch 8 +2025-04-19 14:03:10,563 INFO Epoch:9 train_loss:0.90347 +2025-04-19 14:03:23,668 INFO Epoch:9 val_res:0.565000 +2025-04-19 14:03:23,668 INFO Saving best model at Epoch 9 +2025-04-19 14:03:59,407 INFO Epoch:10 train_loss:0.88429 +2025-04-19 14:04:12,697 INFO Epoch:10 val_res:0.564000 +2025-04-19 14:04:47,081 INFO Epoch:11 train_loss:0.87044 +2025-04-19 14:05:00,292 INFO Epoch:11 val_res:0.565800 +2025-04-19 14:05:00,293 INFO Saving best model at Epoch 11 +2025-04-19 14:05:35,639 INFO Epoch:12 train_loss:0.86275 +2025-04-19 14:05:48,948 INFO Epoch:12 val_res:0.568400 +2025-04-19 14:05:48,949 INFO Saving best model at Epoch 12 +2025-04-19 14:06:24,396 INFO Epoch:13 train_loss:0.85640 +2025-04-19 14:06:37,836 INFO Epoch:13 val_res:0.570800 +2025-04-19 14:06:37,836 INFO Saving best model at Epoch 13 +2025-04-19 14:07:13,724 INFO Epoch:14 train_loss:0.84272 +2025-04-19 14:07:27,247 INFO Epoch:14 val_res:0.569800 +2025-04-19 14:08:01,131 INFO Epoch:15 train_loss:0.84111 +2025-04-19 14:08:14,408 INFO Epoch:15 val_res:0.573200 +2025-04-19 14:08:14,414 INFO Saving best model at Epoch 15 +2025-04-19 14:08:49,423 INFO Epoch:16 train_loss:0.81569 +2025-04-19 14:09:02,606 INFO Epoch:16 val_res:0.573200 +2025-04-19 14:09:36,937 INFO Epoch:17 train_loss:0.80888 +2025-04-19 14:09:50,283 INFO Epoch:17 val_res:0.577600 +2025-04-19 14:09:50,283 INFO Saving best model at Epoch 17 +2025-04-19 14:10:26,173 INFO Epoch:18 train_loss:0.80739 +2025-04-19 14:10:39,510 INFO Epoch:18 val_res:0.579400 +2025-04-19 14:10:39,510 INFO Saving best model at Epoch 18 +2025-04-19 14:11:15,555 INFO Epoch:19 train_loss:0.78811 +2025-04-19 14:11:28,987 INFO Epoch:19 val_res:0.579400 +2025-04-19 14:12:03,431 INFO Epoch:20 train_loss:0.80256 +2025-04-19 14:12:16,124 INFO Epoch:20 val_res:0.581800 +2025-04-19 14:12:16,124 INFO Saving best model at Epoch 20 +2025-04-19 14:12:51,319 INFO Epoch:21 train_loss:0.85737 +2025-04-19 14:13:04,306 INFO Epoch:21 val_res:0.583400 +2025-04-19 14:13:04,307 INFO Saving best model at Epoch 21 +2025-04-19 14:13:38,907 INFO Epoch:22 train_loss:0.81537 +2025-04-19 14:13:52,573 INFO Epoch:22 val_res:0.583200 +2025-04-19 14:14:26,469 INFO Epoch:23 train_loss:0.78036 +2025-04-19 14:14:39,729 INFO Epoch:23 val_res:0.583200 +2025-04-19 14:15:13,738 INFO Epoch:24 train_loss:0.77724 +2025-04-19 14:15:26,956 INFO Epoch:24 val_res:0.587200 +2025-04-19 14:15:26,956 INFO Saving best model at Epoch 24 +2025-04-19 14:16:02,774 INFO Epoch:25 train_loss:0.78676 +2025-04-19 14:16:15,980 INFO Epoch:25 val_res:0.586600 +2025-04-19 14:16:49,647 INFO Epoch:26 train_loss:0.73715 +2025-04-19 14:17:02,797 INFO Epoch:26 val_res:0.589800 +2025-04-19 14:17:02,798 INFO Saving best model at Epoch 26 +2025-04-19 14:17:38,673 INFO Epoch:27 train_loss:0.74519 +2025-04-19 14:17:51,621 INFO Epoch:27 val_res:0.588800 +2025-04-19 14:18:25,113 INFO Epoch:28 train_loss:0.73395 +2025-04-19 14:18:38,397 INFO Epoch:28 val_res:0.590200 +2025-04-19 14:18:38,397 INFO Saving best model at Epoch 28 +2025-04-19 14:19:14,416 INFO Epoch:29 train_loss:0.73658 +2025-04-19 14:19:27,690 INFO Epoch:29 val_res:0.590800 +2025-04-19 14:19:27,691 INFO Saving best model at Epoch 29 +2025-04-19 14:20:03,248 INFO Epoch:30 train_loss:0.77118 +2025-04-19 14:20:16,685 INFO Epoch:30 val_res:0.589400 +2025-04-19 14:20:50,590 INFO Epoch:31 train_loss:0.72183 +2025-04-19 14:21:03,781 INFO Epoch:31 val_res:0.591400 +2025-04-19 14:21:03,781 INFO Saving best model at Epoch 31 +2025-04-19 14:21:40,250 INFO Epoch:32 train_loss:0.69993 +2025-04-19 14:21:53,599 INFO Epoch:32 val_res:0.593800 +2025-04-19 14:21:53,599 INFO Saving best model at Epoch 32 +2025-04-19 14:22:28,973 INFO Epoch:33 train_loss:0.75188 +2025-04-19 14:22:41,986 INFO Epoch:33 val_res:0.588600 +2025-04-19 14:23:16,029 INFO Epoch:34 train_loss:0.72965 +2025-04-19 14:23:29,032 INFO Epoch:34 val_res:0.591200 +2025-04-19 14:24:03,799 INFO Epoch:35 train_loss:0.69109 +2025-04-19 14:24:16,765 INFO Epoch:35 val_res:0.593600 +2025-04-19 14:24:51,536 INFO Epoch:36 train_loss:0.66429 +2025-04-19 14:25:04,788 INFO Epoch:36 val_res:0.592400 +2025-04-19 14:25:39,096 INFO Epoch:37 train_loss:0.66179 +2025-04-19 14:25:52,388 INFO Epoch:37 val_res:0.591400 +2025-04-19 14:26:27,641 INFO Epoch:38 train_loss:0.68920 +2025-04-19 14:26:40,916 INFO Epoch:38 val_res:0.593600 +2025-04-19 14:27:15,280 INFO Epoch:39 train_loss:0.67817 +2025-04-19 14:27:28,641 INFO Epoch:39 val_res:0.596400 +2025-04-19 14:27:28,642 INFO Saving best model at Epoch 39 +2025-04-19 14:28:05,005 INFO Epoch:40 train_loss:0.78567 +2025-04-19 14:28:18,459 INFO Epoch:40 val_res:0.594200 +2025-04-19 14:28:52,999 INFO Epoch:41 train_loss:0.69540 +2025-04-19 14:29:06,663 INFO Epoch:41 val_res:0.596600 +2025-04-19 14:29:06,663 INFO Saving best model at Epoch 41 +2025-04-19 14:29:42,923 INFO Epoch:42 train_loss:0.65583 +2025-04-19 14:29:56,268 INFO Epoch:42 val_res:0.593400 +2025-04-19 14:30:30,239 INFO Epoch:43 train_loss:0.67610 +2025-04-19 14:30:43,710 INFO Epoch:43 val_res:0.594400 +2025-04-19 14:31:18,569 INFO Epoch:44 train_loss:0.64573 +2025-04-19 14:31:31,773 INFO Epoch:44 val_res:0.590800 +2025-04-19 14:32:05,925 INFO Epoch:45 train_loss:0.65594 +2025-04-19 14:32:19,541 INFO Epoch:45 val_res:0.593000 +2025-04-19 14:32:53,837 INFO Epoch:46 train_loss:0.68491 +2025-04-19 14:33:07,178 INFO Epoch:46 val_res:0.594200 +2025-04-19 14:33:41,842 INFO Epoch:47 train_loss:0.66127 +2025-04-19 14:33:55,160 INFO Epoch:47 val_res:0.590800 +2025-04-19 14:34:29,961 INFO Epoch:48 train_loss:0.62313 +2025-04-19 14:34:43,031 INFO Epoch:48 val_res:0.590600 +2025-04-19 14:35:17,761 INFO Epoch:49 train_loss:0.61869 +2025-04-19 14:35:30,350 INFO Epoch:49 val_res:0.586000 +2025-04-19 14:36:05,295 INFO Epoch:50 train_loss:0.64728 +2025-04-19 14:36:18,488 INFO Epoch:50 val_res:0.586800 +2025-04-19 14:36:53,183 INFO Epoch:51 train_loss:0.65532 +2025-04-19 14:37:06,399 INFO Epoch:51 val_res:0.589800 +2025-04-19 14:37:41,538 INFO Epoch:52 train_loss:0.66712 +2025-04-19 14:37:54,783 INFO Epoch:52 val_res:0.589400 +2025-04-19 14:38:29,271 INFO Epoch:53 train_loss:0.65825 +2025-04-19 14:38:41,736 INFO Epoch:53 val_res:0.589200 +2025-04-19 14:39:16,309 INFO Epoch:54 train_loss:0.63870 +2025-04-19 14:39:29,541 INFO Epoch:54 val_res:0.583600 +2025-04-19 14:40:03,391 INFO Epoch:55 train_loss:0.60588 +2025-04-19 14:40:16,501 INFO Epoch:55 val_res:0.589400 +2025-04-19 14:40:51,016 INFO Epoch:56 train_loss:0.60823 +2025-04-19 14:41:03,880 INFO Epoch:56 val_res:0.586200 +2025-04-19 14:41:37,978 INFO Epoch:57 train_loss:0.61787 +2025-04-19 14:41:51,570 INFO Epoch:57 val_res:0.584200 +2025-04-19 14:42:26,755 INFO Epoch:58 train_loss:0.61658 +2025-04-19 14:42:39,761 INFO Epoch:58 val_res:0.580800 +2025-04-19 14:43:14,617 INFO Epoch:59 train_loss:0.60480 +2025-04-19 14:43:27,805 INFO Epoch:59 val_res:0.585400 +2025-04-19 14:44:03,097 INFO Epoch:60 train_loss:0.61898 +2025-04-19 14:44:16,459 INFO Epoch:60 val_res:0.581000 +2025-04-19 14:44:50,988 INFO Epoch:61 train_loss:0.62774 +2025-04-19 14:45:04,009 INFO Epoch:61 val_res:0.581600 +2025-04-19 14:45:38,675 INFO Epoch:62 train_loss:0.60877 +2025-04-19 14:45:52,027 INFO Epoch:62 val_res:0.581200 +2025-04-19 14:46:26,400 INFO Epoch:63 train_loss:0.60731 +2025-04-19 14:46:39,276 INFO Epoch:63 val_res:0.582200 +2025-04-19 14:47:13,722 INFO Epoch:64 train_loss:0.62041 +2025-04-19 14:47:26,388 INFO Epoch:64 val_res:0.578600 +2025-04-19 14:48:00,194 INFO Epoch:65 train_loss:0.66930 +2025-04-19 14:48:13,354 INFO Epoch:65 val_res:0.578400 +2025-04-19 14:48:46,893 INFO Epoch:66 train_loss:0.62163 +2025-04-19 14:49:00,154 INFO Epoch:66 val_res:0.578400 +2025-04-19 14:49:34,801 INFO Epoch:67 train_loss:0.58278 +2025-04-19 14:49:48,175 INFO Epoch:67 val_res:0.578400 +2025-04-19 14:50:22,115 INFO Epoch:68 train_loss:0.59618 +2025-04-19 14:50:35,107 INFO Epoch:68 val_res:0.574600 +2025-04-19 14:51:09,438 INFO Epoch:69 train_loss:0.57485 +2025-04-19 14:51:22,926 INFO Epoch:69 val_res:0.577200 +2025-04-19 14:51:58,009 INFO Epoch:70 train_loss:0.54561 +2025-04-19 14:52:10,983 INFO Epoch:70 val_res:0.574400 +2025-04-19 14:52:45,695 INFO Epoch:71 train_loss:0.60858 +2025-04-19 14:52:58,805 INFO Epoch:71 val_res:0.574000 +2025-04-19 14:53:32,585 INFO Epoch:72 train_loss:0.63096 +2025-04-19 14:53:46,208 INFO Epoch:72 val_res:0.572600 +2025-04-19 14:54:19,984 INFO Epoch:73 train_loss:0.55838 +2025-04-19 14:54:33,053 INFO Epoch:73 val_res:0.578800 +2025-04-19 14:55:06,723 INFO Epoch:74 train_loss:0.53557 +2025-04-19 14:55:19,764 INFO Epoch:74 val_res:0.575000 +2025-04-19 14:55:53,922 INFO Epoch:75 train_loss:0.61156 +2025-04-19 14:56:06,908 INFO Epoch:75 val_res:0.569600 +2025-04-19 14:56:41,358 INFO Epoch:76 train_loss:0.59115 +2025-04-19 14:56:54,488 INFO Epoch:76 val_res:0.570600 +2025-04-19 14:57:29,982 INFO Epoch:77 train_loss:0.57545 +2025-04-19 14:57:46,168 INFO Epoch:77 val_res:0.569800 +2025-04-19 14:58:29,942 INFO Epoch:78 train_loss:0.60005 +2025-04-19 14:58:46,226 INFO Epoch:78 val_res:0.567400 +2025-04-19 14:59:26,762 INFO Epoch:79 train_loss:0.64939 +2025-04-19 14:59:41,212 INFO Epoch:79 val_res:0.568400 +2025-04-19 15:00:16,454 INFO Epoch:80 train_loss:0.55075 +2025-04-19 15:00:29,504 INFO Epoch:80 val_res:0.565200 +2025-04-19 15:01:04,710 INFO Epoch:81 train_loss:0.53187 +2025-04-19 15:01:17,635 INFO Epoch:81 val_res:0.567600 +2025-04-19 15:01:52,699 INFO Epoch:82 train_loss:0.57822 +2025-04-19 15:02:05,633 INFO Epoch:82 val_res:0.570600 +2025-04-19 15:02:42,218 INFO Epoch:83 train_loss:0.55035 +2025-04-19 15:02:55,229 INFO Epoch:83 val_res:0.567800 +2025-04-19 15:03:29,829 INFO Epoch:84 train_loss:0.55175 +2025-04-19 15:03:42,813 INFO Epoch:84 val_res:0.565400 +2025-04-19 15:04:17,634 INFO Epoch:85 train_loss:0.55485 +2025-04-19 15:04:30,525 INFO Epoch:85 val_res:0.566200 +2025-04-19 15:05:04,490 INFO Epoch:86 train_loss:0.56475 +2025-04-19 15:05:17,263 INFO Epoch:86 val_res:0.563000 +2025-04-19 15:05:50,456 INFO Epoch:87 train_loss:0.56150 +2025-04-19 15:06:03,389 INFO Epoch:87 val_res:0.566800 +2025-04-19 15:06:37,402 INFO Epoch:88 train_loss:0.57672 +2025-04-19 15:06:50,668 INFO Epoch:88 val_res:0.563000 +2025-04-19 15:07:25,311 INFO Epoch:89 train_loss:0.54063 +2025-04-19 15:07:38,252 INFO Epoch:89 val_res:0.562800 +2025-04-19 15:08:12,245 INFO Epoch:90 train_loss:0.53206 +2025-04-19 15:08:25,293 INFO Epoch:90 val_res:0.559600 +2025-04-19 15:09:00,064 INFO Epoch:91 train_loss:0.56284 +2025-04-19 15:09:12,828 INFO Epoch:91 val_res:0.566200 +2025-04-19 15:09:47,557 INFO Epoch:92 train_loss:0.54232 +2025-04-19 15:10:00,573 INFO Epoch:92 val_res:0.561200 +2025-04-19 15:10:35,307 INFO Epoch:93 train_loss:0.50113 +2025-04-19 15:10:48,151 INFO Epoch:93 val_res:0.559400 +2025-04-19 15:11:22,122 INFO Epoch:94 train_loss:0.54409 +2025-04-19 15:11:35,061 INFO Epoch:94 val_res:0.558400 +2025-04-19 15:12:09,446 INFO Epoch:95 train_loss:0.58150 +2025-04-19 15:12:22,339 INFO Epoch:95 val_res:0.560000 +2025-04-19 15:12:56,299 INFO Epoch:96 train_loss:0.57395 +2025-04-19 15:13:09,059 INFO Epoch:96 val_res:0.557600 +2025-04-19 15:13:42,678 INFO Epoch:97 train_loss:0.52872 +2025-04-19 15:13:55,641 INFO Epoch:97 val_res:0.558400 +2025-04-19 15:14:29,525 INFO Epoch:98 train_loss:0.54460 +2025-04-19 15:14:42,424 INFO Epoch:98 val_res:0.556000 +2025-04-19 15:15:16,444 INFO Epoch:99 train_loss:0.52974 +2025-04-19 15:15:29,478 INFO Epoch:99 val_res:0.556600 +2025-04-19 15:15:30,240 INFO ===================================== +2025-04-19 15:15:30,241 INFO Start testing... +2025-04-19 15:15:30,241 INFO ===================================== +2025-04-19 15:15:45,633 INFO Incremental step 9 Testing res: 0.590800 +2025-04-19 15:15:45,638 INFO forgetting: 0.108222 +2025-04-19 15:15:45,640 INFO Average Accuracy: 0.700062 +2025-04-19 15:15:45,641 INFO Average Forgetting: 0.086610 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..e80be51e59d4fde4a88960179509b8e8d1c916b6 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..8eeb35a398d2b0bc5cbbdc2474a08e58604b1f2c Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..fdaa0ca7b317ee0a08d519b2781a4ebfeec3dd61 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..4d66ebc8749964382a919977597e18ec24994930 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..40e9044f263b142c418ef4cdebb5ca945ce63e01 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..d5dbf85d59655b5f668278954db8bc50c831cb5c Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..4c3ca8c0032adef2d7b3e49ffc165aa6fc6e753a Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..463149451f1d00148b0af9d753b4d2b41c0af751 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..8833e9c7d07239509fa08201758e0cdedc24b99c Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..4f06ac94935b43b30e6ac6226d04657535648bc2 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f1f7e865eec06aa76db3e563c0348faf12bf2eff --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f0a86dcbdedf860e11b596acaa8b1727775acdeadf43fc92d351f9c6d04c5da +size 114105937 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..11b822eb0e9634b16213a028d800669b423ffe5d --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaeaf64527d5f8626555383ac39c7fe6815d22936380a124bad5b234eba4a0d6 +size 114161297 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..4de9c60cf3c3fb0d64ac1418d97db4acfc220fbb --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84b0c9252e2ceb10de95e1d12eca147b0989e141f326188e66d8aa2d6a7fda5d +size 114216785 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a1006b6e68fdcf9f16882e29c5f088791aa4d904 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca01f18aeda743dce7e496f4adf96cac5a0bbcd29c16033af1136598d62b198 +size 114272081 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..40dca402700599e88b87ffc6fc7d3ba0d0c63641 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc2134aa735a10cd5a5817a9c11c54cd686c98804d7c203af80908f3bdf0f2d +size 114327377 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/train.log b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..1fddc558d43d8efafa1673ebfb987ab77928ad35 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_False-seed_0/train.log @@ -0,0 +1,1154 @@ +2025-04-18 06:26:02,862 INFO Namespace(class_num_per_step=6, dataset='ksounds', e_prompt=False, exemplar_batch_size=128, fixed_fc=False, infer_batch_size=128, inverse=False, inverse_ends=100, inverse_starts=0, lr=0.01, lr_decay=False, max_epoches=100, memory_size=500, milestones=[100], modality='audio-visual', num_classes=30, num_workers=4, prompt_dim=768, seed=0, train_batch_size=256, weight_decay=0.0001) +2025-04-18 06:26:02,863 INFO Training start time: 2025-04-18 06:26:02.863892 +2025-04-18 06:26:04,875 INFO ***************New Step*************************** +2025-04-18 06:26:04,875 INFO Incremental step: 0 +2025-04-18 06:28:27,654 INFO Epoch:0 train_loss:1.64542 +2025-04-18 06:28:30,508 INFO Epoch:0 val_res:0.416446 +2025-04-18 06:28:30,509 INFO Saving best model at Epoch 0 +2025-04-18 06:28:49,432 INFO Epoch:1 train_loss:1.32154 +2025-04-18 06:28:51,766 INFO Epoch:1 val_res:0.541114 +2025-04-18 06:28:51,766 INFO Saving best model at Epoch 1 +2025-04-18 06:29:11,672 INFO Epoch:2 train_loss:1.13255 +2025-04-18 06:29:14,009 INFO Epoch:2 val_res:0.652520 +2025-04-18 06:29:14,010 INFO Saving best model at Epoch 2 +2025-04-18 06:29:30,172 INFO Epoch:3 train_loss:0.96427 +2025-04-18 06:29:32,576 INFO Epoch:3 val_res:0.676393 +2025-04-18 06:29:32,576 INFO Saving best model at Epoch 3 +2025-04-18 06:29:49,108 INFO Epoch:4 train_loss:0.83648 +2025-04-18 06:29:51,463 INFO Epoch:4 val_res:0.700265 +2025-04-18 06:29:51,463 INFO Saving best model at Epoch 4 +2025-04-18 06:30:07,557 INFO Epoch:5 train_loss:0.75054 +2025-04-18 06:30:09,978 INFO Epoch:5 val_res:0.734748 +2025-04-18 06:30:09,978 INFO Saving best model at Epoch 5 +2025-04-18 06:30:25,721 INFO Epoch:6 train_loss:0.69696 +2025-04-18 06:30:28,105 INFO Epoch:6 val_res:0.745358 +2025-04-18 06:30:28,106 INFO Saving best model at Epoch 6 +2025-04-18 06:30:44,663 INFO Epoch:7 train_loss:0.64903 +2025-04-18 06:30:47,043 INFO Epoch:7 val_res:0.785146 +2025-04-18 06:30:47,044 INFO Saving best model at Epoch 7 +2025-04-18 06:31:03,031 INFO Epoch:8 train_loss:0.59788 +2025-04-18 06:31:05,311 INFO Epoch:8 val_res:0.793103 +2025-04-18 06:31:05,311 INFO Saving best model at Epoch 8 +2025-04-18 06:31:20,853 INFO Epoch:9 train_loss:0.54790 +2025-04-18 06:31:23,112 INFO Epoch:9 val_res:0.790451 +2025-04-18 06:31:36,775 INFO Epoch:10 train_loss:0.51499 +2025-04-18 06:31:39,160 INFO Epoch:10 val_res:0.806366 +2025-04-18 06:31:39,161 INFO Saving best model at Epoch 10 +2025-04-18 06:31:55,151 INFO Epoch:11 train_loss:0.49086 +2025-04-18 06:31:57,449 INFO Epoch:11 val_res:0.819629 +2025-04-18 06:31:57,449 INFO Saving best model at Epoch 11 +2025-04-18 06:32:21,148 INFO Epoch:12 train_loss:0.47041 +2025-04-18 06:32:23,944 INFO Epoch:12 val_res:0.819629 +2025-04-18 06:32:39,756 INFO Epoch:13 train_loss:0.45523 +2025-04-18 06:32:42,177 INFO Epoch:13 val_res:0.785146 +2025-04-18 06:32:58,137 INFO Epoch:14 train_loss:0.44889 +2025-04-18 06:33:00,412 INFO Epoch:14 val_res:0.809019 +2025-04-18 06:33:14,305 INFO Epoch:15 train_loss:0.42421 +2025-04-18 06:33:16,399 INFO Epoch:15 val_res:0.870027 +2025-04-18 06:33:16,399 INFO Saving best model at Epoch 15 +2025-04-18 06:33:30,521 INFO Epoch:16 train_loss:0.38365 +2025-04-18 06:33:32,686 INFO Epoch:16 val_res:0.848806 +2025-04-18 06:33:47,041 INFO Epoch:17 train_loss:0.37910 +2025-04-18 06:33:50,052 INFO Epoch:17 val_res:0.864721 +2025-04-18 06:34:04,018 INFO Epoch:18 train_loss:0.39714 +2025-04-18 06:34:06,543 INFO Epoch:18 val_res:0.870027 +2025-04-18 06:34:20,490 INFO Epoch:19 train_loss:0.38865 +2025-04-18 06:34:22,848 INFO Epoch:19 val_res:0.875332 +2025-04-18 06:34:22,848 INFO Saving best model at Epoch 19 +2025-04-18 06:34:40,435 INFO Epoch:20 train_loss:0.34805 +2025-04-18 06:34:42,847 INFO Epoch:20 val_res:0.862069 +2025-04-18 06:34:56,472 INFO Epoch:21 train_loss:0.35138 +2025-04-18 06:34:58,822 INFO Epoch:21 val_res:0.859416 +2025-04-18 06:35:13,511 INFO Epoch:22 train_loss:0.31694 +2025-04-18 06:35:16,241 INFO Epoch:22 val_res:0.883289 +2025-04-18 06:35:16,242 INFO Saving best model at Epoch 22 +2025-04-18 06:35:34,769 INFO Epoch:23 train_loss:0.30517 +2025-04-18 06:35:37,333 INFO Epoch:23 val_res:0.870027 +2025-04-18 06:35:51,467 INFO Epoch:24 train_loss:0.31528 +2025-04-18 06:35:54,226 INFO Epoch:24 val_res:0.877984 +2025-04-18 06:36:07,704 INFO Epoch:25 train_loss:0.32537 +2025-04-18 06:36:09,995 INFO Epoch:25 val_res:0.867374 +2025-04-18 06:36:24,743 INFO Epoch:26 train_loss:0.30163 +2025-04-18 06:36:27,344 INFO Epoch:26 val_res:0.885942 +2025-04-18 06:36:27,344 INFO Saving best model at Epoch 26 +2025-04-18 06:36:45,354 INFO Epoch:27 train_loss:0.29313 +2025-04-18 06:36:47,816 INFO Epoch:27 val_res:0.888594 +2025-04-18 06:36:47,816 INFO Saving best model at Epoch 27 +2025-04-18 06:37:05,237 INFO Epoch:28 train_loss:0.29709 +2025-04-18 06:37:07,802 INFO Epoch:28 val_res:0.851459 +2025-04-18 06:37:21,780 INFO Epoch:29 train_loss:0.29179 +2025-04-18 06:37:24,254 INFO Epoch:29 val_res:0.854111 +2025-04-18 06:37:39,826 INFO Epoch:30 train_loss:0.30165 +2025-04-18 06:37:42,246 INFO Epoch:30 val_res:0.888594 +2025-04-18 06:37:57,449 INFO Epoch:31 train_loss:0.27148 +2025-04-18 06:37:59,927 INFO Epoch:31 val_res:0.891247 +2025-04-18 06:37:59,927 INFO Saving best model at Epoch 31 +2025-04-18 06:38:17,606 INFO Epoch:32 train_loss:0.26907 +2025-04-18 06:38:20,193 INFO Epoch:32 val_res:0.877984 +2025-04-18 06:38:33,760 INFO Epoch:33 train_loss:0.26320 +2025-04-18 06:38:36,389 INFO Epoch:33 val_res:0.883289 +2025-04-18 06:38:50,793 INFO Epoch:34 train_loss:0.25309 +2025-04-18 06:38:53,265 INFO Epoch:34 val_res:0.901857 +2025-04-18 06:38:53,265 INFO Saving best model at Epoch 34 +2025-04-18 06:39:08,835 INFO Epoch:35 train_loss:0.26539 +2025-04-18 06:39:11,323 INFO Epoch:35 val_res:0.891247 +2025-04-18 06:39:26,014 INFO Epoch:36 train_loss:0.25618 +2025-04-18 06:39:28,368 INFO Epoch:36 val_res:0.893899 +2025-04-18 06:39:42,328 INFO Epoch:37 train_loss:0.24903 +2025-04-18 06:39:44,826 INFO Epoch:37 val_res:0.885942 +2025-04-18 06:39:59,289 INFO Epoch:38 train_loss:0.27117 +2025-04-18 06:40:01,713 INFO Epoch:38 val_res:0.907162 +2025-04-18 06:40:01,713 INFO Saving best model at Epoch 38 +2025-04-18 06:40:17,101 INFO Epoch:39 train_loss:0.24389 +2025-04-18 06:40:19,470 INFO Epoch:39 val_res:0.896552 +2025-04-18 06:40:34,254 INFO Epoch:40 train_loss:0.24607 +2025-04-18 06:40:36,802 INFO Epoch:40 val_res:0.872679 +2025-04-18 06:40:51,368 INFO Epoch:41 train_loss:0.24973 +2025-04-18 06:40:53,776 INFO Epoch:41 val_res:0.888594 +2025-04-18 06:41:07,785 INFO Epoch:42 train_loss:0.25650 +2025-04-18 06:41:10,248 INFO Epoch:42 val_res:0.883289 +2025-04-18 06:41:24,804 INFO Epoch:43 train_loss:0.23776 +2025-04-18 06:41:27,252 INFO Epoch:43 val_res:0.893899 +2025-04-18 06:41:40,945 INFO Epoch:44 train_loss:0.26604 +2025-04-18 06:41:43,366 INFO Epoch:44 val_res:0.896552 +2025-04-18 06:41:57,142 INFO Epoch:45 train_loss:0.22747 +2025-04-18 06:41:59,463 INFO Epoch:45 val_res:0.893899 +2025-04-18 06:42:13,882 INFO Epoch:46 train_loss:0.21294 +2025-04-18 06:42:16,181 INFO Epoch:46 val_res:0.912467 +2025-04-18 06:42:16,181 INFO Saving best model at Epoch 46 +2025-04-18 06:42:32,085 INFO Epoch:47 train_loss:0.21633 +2025-04-18 06:42:34,448 INFO Epoch:47 val_res:0.907162 +2025-04-18 06:42:48,335 INFO Epoch:48 train_loss:0.22107 +2025-04-18 06:42:50,953 INFO Epoch:48 val_res:0.907162 +2025-04-18 06:43:04,873 INFO Epoch:49 train_loss:0.21137 +2025-04-18 06:43:07,175 INFO Epoch:49 val_res:0.859416 +2025-04-18 06:43:21,813 INFO Epoch:50 train_loss:0.21941 +2025-04-18 06:43:24,364 INFO Epoch:50 val_res:0.912467 +2025-04-18 06:43:39,010 INFO Epoch:51 train_loss:0.20540 +2025-04-18 06:43:41,420 INFO Epoch:51 val_res:0.885942 +2025-04-18 06:43:55,602 INFO Epoch:52 train_loss:0.22734 +2025-04-18 06:43:57,982 INFO Epoch:52 val_res:0.896552 +2025-04-18 06:44:11,931 INFO Epoch:53 train_loss:0.22323 +2025-04-18 06:44:14,189 INFO Epoch:53 val_res:0.917772 +2025-04-18 06:44:14,189 INFO Saving best model at Epoch 53 +2025-04-18 06:44:30,388 INFO Epoch:54 train_loss:0.20772 +2025-04-18 06:44:32,928 INFO Epoch:54 val_res:0.901857 +2025-04-18 06:44:47,437 INFO Epoch:55 train_loss:0.20005 +2025-04-18 06:44:49,867 INFO Epoch:55 val_res:0.904509 +2025-04-18 06:45:04,583 INFO Epoch:56 train_loss:0.19445 +2025-04-18 06:45:06,827 INFO Epoch:56 val_res:0.872679 +2025-04-18 06:45:20,632 INFO Epoch:57 train_loss:0.21444 +2025-04-18 06:45:22,750 INFO Epoch:57 val_res:0.915119 +2025-04-18 06:45:38,690 INFO Epoch:58 train_loss:0.19691 +2025-04-18 06:45:40,949 INFO Epoch:58 val_res:0.891247 +2025-04-18 06:45:55,446 INFO Epoch:59 train_loss:0.19408 +2025-04-18 06:45:57,930 INFO Epoch:59 val_res:0.883289 +2025-04-18 06:46:12,672 INFO Epoch:60 train_loss:0.20830 +2025-04-18 06:46:15,242 INFO Epoch:60 val_res:0.915119 +2025-04-18 06:46:30,014 INFO Epoch:61 train_loss:0.21103 +2025-04-18 06:46:32,585 INFO Epoch:61 val_res:0.904509 +2025-04-18 06:46:46,835 INFO Epoch:62 train_loss:0.18774 +2025-04-18 06:46:49,372 INFO Epoch:62 val_res:0.912467 +2025-04-18 06:47:04,280 INFO Epoch:63 train_loss:0.17338 +2025-04-18 06:47:06,848 INFO Epoch:63 val_res:0.915119 +2025-04-18 06:47:22,284 INFO Epoch:64 train_loss:0.17824 +2025-04-18 06:47:25,063 INFO Epoch:64 val_res:0.904509 +2025-04-18 06:47:40,414 INFO Epoch:65 train_loss:0.18851 +2025-04-18 06:47:43,007 INFO Epoch:65 val_res:0.928382 +2025-04-18 06:47:43,007 INFO Saving best model at Epoch 65 +2025-04-18 06:47:59,047 INFO Epoch:66 train_loss:0.19319 +2025-04-18 06:48:01,564 INFO Epoch:66 val_res:0.912467 +2025-04-18 06:48:16,066 INFO Epoch:67 train_loss:0.21070 +2025-04-18 06:48:18,402 INFO Epoch:67 val_res:0.867374 +2025-04-18 06:48:32,677 INFO Epoch:68 train_loss:0.20050 +2025-04-18 06:48:35,236 INFO Epoch:68 val_res:0.909814 +2025-04-18 06:48:49,166 INFO Epoch:69 train_loss:0.18067 +2025-04-18 06:48:51,625 INFO Epoch:69 val_res:0.931035 +2025-04-18 06:48:51,625 INFO Saving best model at Epoch 69 +2025-04-18 06:49:06,769 INFO Epoch:70 train_loss:0.16850 +2025-04-18 06:49:09,129 INFO Epoch:70 val_res:0.891247 +2025-04-18 06:49:22,614 INFO Epoch:71 train_loss:0.16374 +2025-04-18 06:49:24,892 INFO Epoch:71 val_res:0.917772 +2025-04-18 06:49:38,587 INFO Epoch:72 train_loss:0.15190 +2025-04-18 06:49:40,932 INFO Epoch:72 val_res:0.907162 +2025-04-18 06:49:54,660 INFO Epoch:73 train_loss:0.15096 +2025-04-18 06:49:56,986 INFO Epoch:73 val_res:0.917772 +2025-04-18 06:50:10,574 INFO Epoch:74 train_loss:0.14460 +2025-04-18 06:50:13,112 INFO Epoch:74 val_res:0.920424 +2025-04-18 06:50:27,331 INFO Epoch:75 train_loss:0.14374 +2025-04-18 06:50:29,657 INFO Epoch:75 val_res:0.907162 +2025-04-18 06:50:43,094 INFO Epoch:76 train_loss:0.16272 +2025-04-18 06:50:45,575 INFO Epoch:76 val_res:0.928382 +2025-04-18 06:50:58,590 INFO Epoch:77 train_loss:0.15476 +2025-04-18 06:51:01,068 INFO Epoch:77 val_res:0.896552 +2025-04-18 06:51:14,592 INFO Epoch:78 train_loss:0.16294 +2025-04-18 06:51:17,041 INFO Epoch:78 val_res:0.893899 +2025-04-18 06:51:30,808 INFO Epoch:79 train_loss:0.15431 +2025-04-18 06:51:33,194 INFO Epoch:79 val_res:0.925729 +2025-04-18 06:51:46,435 INFO Epoch:80 train_loss:0.14898 +2025-04-18 06:51:48,717 INFO Epoch:80 val_res:0.920424 +2025-04-18 06:52:02,062 INFO Epoch:81 train_loss:0.14896 +2025-04-18 06:52:04,553 INFO Epoch:81 val_res:0.917772 +2025-04-18 06:52:18,930 INFO Epoch:82 train_loss:0.16762 +2025-04-18 06:52:21,343 INFO Epoch:82 val_res:0.896552 +2025-04-18 06:52:35,870 INFO Epoch:83 train_loss:0.14607 +2025-04-18 06:52:38,169 INFO Epoch:83 val_res:0.915119 +2025-04-18 06:52:53,104 INFO Epoch:84 train_loss:0.13220 +2025-04-18 06:52:55,475 INFO Epoch:84 val_res:0.923077 +2025-04-18 06:53:13,435 INFO Epoch:85 train_loss:0.15274 +2025-04-18 06:53:15,526 INFO Epoch:85 val_res:0.928382 +2025-04-18 06:53:39,438 INFO Epoch:86 train_loss:0.14612 +2025-04-18 06:53:41,980 INFO Epoch:86 val_res:0.907162 +2025-04-18 06:54:01,375 INFO Epoch:87 train_loss:0.12956 +2025-04-18 06:54:03,551 INFO Epoch:87 val_res:0.920424 +2025-04-18 06:54:22,411 INFO Epoch:88 train_loss:0.12641 +2025-04-18 06:54:24,916 INFO Epoch:88 val_res:0.933687 +2025-04-18 06:54:24,916 INFO Saving best model at Epoch 88 +2025-04-18 06:54:42,178 INFO Epoch:89 train_loss:0.14569 +2025-04-18 06:54:44,551 INFO Epoch:89 val_res:0.872679 +2025-04-18 06:54:59,712 INFO Epoch:90 train_loss:0.17245 +2025-04-18 06:55:02,610 INFO Epoch:90 val_res:0.917772 +2025-04-18 06:55:17,752 INFO Epoch:91 train_loss:0.16496 +2025-04-18 06:55:20,283 INFO Epoch:91 val_res:0.907162 +2025-04-18 06:55:36,414 INFO Epoch:92 train_loss:0.13284 +2025-04-18 06:55:39,059 INFO Epoch:92 val_res:0.901857 +2025-04-18 06:55:53,992 INFO Epoch:93 train_loss:0.14794 +2025-04-18 06:55:56,350 INFO Epoch:93 val_res:0.909814 +2025-04-18 06:56:11,424 INFO Epoch:94 train_loss:0.13333 +2025-04-18 06:56:14,065 INFO Epoch:94 val_res:0.933687 +2025-04-18 06:56:29,443 INFO Epoch:95 train_loss:0.12561 +2025-04-18 06:56:31,985 INFO Epoch:95 val_res:0.923077 +2025-04-18 06:56:46,265 INFO Epoch:96 train_loss:0.12251 +2025-04-18 06:56:48,985 INFO Epoch:96 val_res:0.912467 +2025-04-18 06:57:05,697 INFO Epoch:97 train_loss:0.14077 +2025-04-18 06:57:07,906 INFO Epoch:97 val_res:0.917772 +2025-04-18 06:57:22,591 INFO Epoch:98 train_loss:0.13342 +2025-04-18 06:57:24,922 INFO Epoch:98 val_res:0.904509 +2025-04-18 06:57:41,092 INFO Epoch:99 train_loss:0.12991 +2025-04-18 06:57:43,730 INFO Epoch:99 val_res:0.923077 +2025-04-18 06:57:44,940 INFO ===================================== +2025-04-18 06:57:44,941 INFO Start testing... +2025-04-18 06:57:44,941 INFO ===================================== +2025-04-18 06:58:04,581 INFO Incremental step 0 Testing res: 0.905914 +2025-04-18 06:58:04,585 INFO ***************New Step*************************** +2025-04-18 06:58:04,585 INFO Incremental step: 1 +2025-04-18 06:58:04,877 INFO actual size of exemplar set: 498 +2025-04-18 07:01:09,805 INFO Epoch:0 train_loss:1.50806 +2025-04-18 07:01:22,437 INFO Epoch:0 val_res:0.440260 +2025-04-18 07:01:22,437 INFO Saving best model at Epoch 0 +2025-04-18 07:02:21,833 INFO Epoch:1 train_loss:1.73077 +2025-04-18 07:02:33,635 INFO Epoch:1 val_res:0.419481 +2025-04-18 07:05:20,830 INFO Epoch:2 train_loss:1.13898 +2025-04-18 07:05:29,235 INFO Epoch:2 val_res:0.425974 +2025-04-18 07:07:12,137 INFO Epoch:3 train_loss:1.18601 +2025-04-18 07:07:16,641 INFO Epoch:3 val_res:0.401299 +2025-04-18 07:08:31,829 INFO Epoch:4 train_loss:1.18508 +2025-04-18 07:08:36,009 INFO Epoch:4 val_res:0.432468 +2025-04-18 07:10:35,777 INFO Epoch:5 train_loss:1.12470 +2025-04-18 07:10:41,198 INFO Epoch:5 val_res:0.409091 +2025-04-18 07:11:56,736 INFO Epoch:6 train_loss:1.06733 +2025-04-18 07:12:02,119 INFO Epoch:6 val_res:0.431169 +2025-04-18 07:13:30,874 INFO Epoch:7 train_loss:0.85710 +2025-04-18 07:13:34,713 INFO Epoch:7 val_res:0.444156 +2025-04-18 07:13:34,714 INFO Saving best model at Epoch 7 +2025-04-18 07:15:09,375 INFO Epoch:8 train_loss:0.70129 +2025-04-18 07:15:13,342 INFO Epoch:8 val_res:0.444156 +2025-04-18 07:16:19,591 INFO Epoch:9 train_loss:0.86532 +2025-04-18 07:16:23,424 INFO Epoch:9 val_res:0.440260 +2025-04-18 07:17:17,844 INFO Epoch:10 train_loss:0.76491 +2025-04-18 07:17:21,923 INFO Epoch:10 val_res:0.467532 +2025-04-18 07:17:21,923 INFO Saving best model at Epoch 10 +2025-04-18 07:18:28,199 INFO Epoch:11 train_loss:0.67376 +2025-04-18 07:18:32,115 INFO Epoch:11 val_res:0.453247 +2025-04-18 07:19:41,260 INFO Epoch:12 train_loss:0.67964 +2025-04-18 07:19:45,184 INFO Epoch:12 val_res:0.471429 +2025-04-18 07:19:45,185 INFO Saving best model at Epoch 12 +2025-04-18 07:20:35,645 INFO Epoch:13 train_loss:0.58495 +2025-04-18 07:20:39,682 INFO Epoch:13 val_res:0.479221 +2025-04-18 07:20:39,683 INFO Saving best model at Epoch 13 +2025-04-18 07:21:30,961 INFO Epoch:14 train_loss:0.55256 +2025-04-18 07:21:35,375 INFO Epoch:14 val_res:0.479221 +2025-04-18 07:22:18,248 INFO Epoch:15 train_loss:0.59282 +2025-04-18 07:22:23,453 INFO Epoch:15 val_res:0.451948 +2025-04-18 07:23:09,047 INFO Epoch:16 train_loss:0.56843 +2025-04-18 07:23:12,986 INFO Epoch:16 val_res:0.476623 +2025-04-18 07:23:54,839 INFO Epoch:17 train_loss:0.53213 +2025-04-18 07:23:59,259 INFO Epoch:17 val_res:0.483117 +2025-04-18 07:23:59,259 INFO Saving best model at Epoch 17 +2025-04-18 07:24:41,113 INFO Epoch:18 train_loss:0.60013 +2025-04-18 07:24:45,308 INFO Epoch:18 val_res:0.489610 +2025-04-18 07:24:45,309 INFO Saving best model at Epoch 18 +2025-04-18 07:25:27,469 INFO Epoch:19 train_loss:0.62322 +2025-04-18 07:25:31,656 INFO Epoch:19 val_res:0.459740 +2025-04-18 07:26:11,975 INFO Epoch:20 train_loss:0.53713 +2025-04-18 07:26:16,768 INFO Epoch:20 val_res:0.515584 +2025-04-18 07:26:16,768 INFO Saving best model at Epoch 20 +2025-04-18 07:27:04,508 INFO Epoch:21 train_loss:0.49847 +2025-04-18 07:27:09,581 INFO Epoch:21 val_res:0.514286 +2025-04-18 07:27:44,846 INFO Epoch:22 train_loss:0.48660 +2025-04-18 07:27:48,405 INFO Epoch:22 val_res:0.523377 +2025-04-18 07:27:48,405 INFO Saving best model at Epoch 22 +2025-04-18 07:28:24,358 INFO Epoch:23 train_loss:0.47953 +2025-04-18 07:28:28,534 INFO Epoch:23 val_res:0.509091 +2025-04-18 07:29:01,841 INFO Epoch:24 train_loss:0.47015 +2025-04-18 07:29:05,413 INFO Epoch:24 val_res:0.531169 +2025-04-18 07:29:05,413 INFO Saving best model at Epoch 24 +2025-04-18 07:29:39,530 INFO Epoch:25 train_loss:0.45047 +2025-04-18 07:29:43,001 INFO Epoch:25 val_res:0.533766 +2025-04-18 07:29:43,001 INFO Saving best model at Epoch 25 +2025-04-18 07:30:21,563 INFO Epoch:26 train_loss:0.48991 +2025-04-18 07:30:25,200 INFO Epoch:26 val_res:0.524675 +2025-04-18 07:31:03,492 INFO Epoch:27 train_loss:0.52328 +2025-04-18 07:31:07,593 INFO Epoch:27 val_res:0.541558 +2025-04-18 07:31:07,598 INFO Saving best model at Epoch 27 +2025-04-18 07:31:46,018 INFO Epoch:28 train_loss:0.47080 +2025-04-18 07:31:50,245 INFO Epoch:28 val_res:0.537662 +2025-04-18 07:32:27,362 INFO Epoch:29 train_loss:0.44758 +2025-04-18 07:32:31,429 INFO Epoch:29 val_res:0.528571 +2025-04-18 07:33:07,151 INFO Epoch:30 train_loss:0.43577 +2025-04-18 07:33:10,893 INFO Epoch:30 val_res:0.531169 +2025-04-18 07:33:47,688 INFO Epoch:31 train_loss:0.42475 +2025-04-18 07:33:52,001 INFO Epoch:31 val_res:0.557143 +2025-04-18 07:33:52,001 INFO Saving best model at Epoch 31 +2025-04-18 07:34:28,366 INFO Epoch:32 train_loss:0.41848 +2025-04-18 07:34:32,671 INFO Epoch:32 val_res:0.558442 +2025-04-18 07:34:32,671 INFO Saving best model at Epoch 32 +2025-04-18 07:35:07,482 INFO Epoch:33 train_loss:0.42471 +2025-04-18 07:35:11,338 INFO Epoch:33 val_res:0.546753 +2025-04-18 07:35:41,633 INFO Epoch:34 train_loss:0.41495 +2025-04-18 07:35:45,260 INFO Epoch:34 val_res:0.551948 +2025-04-18 07:36:17,833 INFO Epoch:35 train_loss:0.42776 +2025-04-18 07:36:22,310 INFO Epoch:35 val_res:0.545455 +2025-04-18 07:36:51,976 INFO Epoch:36 train_loss:0.47284 +2025-04-18 07:36:55,573 INFO Epoch:36 val_res:0.564935 +2025-04-18 07:36:55,573 INFO Saving best model at Epoch 36 +2025-04-18 07:37:27,611 INFO Epoch:37 train_loss:0.42778 +2025-04-18 07:37:31,505 INFO Epoch:37 val_res:0.579221 +2025-04-18 07:37:31,505 INFO Saving best model at Epoch 37 +2025-04-18 07:38:04,147 INFO Epoch:38 train_loss:0.40709 +2025-04-18 07:38:08,048 INFO Epoch:38 val_res:0.561039 +2025-04-18 07:38:38,725 INFO Epoch:39 train_loss:0.38285 +2025-04-18 07:38:42,604 INFO Epoch:39 val_res:0.561039 +2025-04-18 07:39:12,028 INFO Epoch:40 train_loss:0.39022 +2025-04-18 07:39:16,001 INFO Epoch:40 val_res:0.571429 +2025-04-18 07:39:47,309 INFO Epoch:41 train_loss:0.39082 +2025-04-18 07:39:50,620 INFO Epoch:41 val_res:0.570130 +2025-04-18 07:40:23,243 INFO Epoch:42 train_loss:0.38462 +2025-04-18 07:40:27,163 INFO Epoch:42 val_res:0.567532 +2025-04-18 07:41:00,810 INFO Epoch:43 train_loss:0.37600 +2025-04-18 07:41:04,438 INFO Epoch:43 val_res:0.590909 +2025-04-18 07:41:04,438 INFO Saving best model at Epoch 43 +2025-04-18 07:41:40,542 INFO Epoch:44 train_loss:0.38116 +2025-04-18 07:41:44,630 INFO Epoch:44 val_res:0.577922 +2025-04-18 07:42:17,291 INFO Epoch:45 train_loss:0.38408 +2025-04-18 07:42:21,031 INFO Epoch:45 val_res:0.580519 +2025-04-18 07:42:53,632 INFO Epoch:46 train_loss:0.36565 +2025-04-18 07:42:57,258 INFO Epoch:46 val_res:0.580519 +2025-04-18 07:43:29,993 INFO Epoch:47 train_loss:0.36271 +2025-04-18 07:43:34,375 INFO Epoch:47 val_res:0.588312 +2025-04-18 07:44:08,414 INFO Epoch:48 train_loss:0.36887 +2025-04-18 07:44:12,736 INFO Epoch:48 val_res:0.574026 +2025-04-18 07:44:46,623 INFO Epoch:49 train_loss:0.35607 +2025-04-18 07:44:51,168 INFO Epoch:49 val_res:0.589610 +2025-04-18 07:45:24,555 INFO Epoch:50 train_loss:0.36606 +2025-04-18 07:45:28,418 INFO Epoch:50 val_res:0.588312 +2025-04-18 07:46:02,816 INFO Epoch:51 train_loss:0.35703 +2025-04-18 07:46:06,756 INFO Epoch:51 val_res:0.575325 +2025-04-18 07:46:39,609 INFO Epoch:52 train_loss:0.36030 +2025-04-18 07:46:43,520 INFO Epoch:52 val_res:0.584416 +2025-04-18 07:47:16,706 INFO Epoch:53 train_loss:0.37112 +2025-04-18 07:47:20,698 INFO Epoch:53 val_res:0.593507 +2025-04-18 07:47:20,699 INFO Saving best model at Epoch 53 +2025-04-18 07:47:50,422 INFO Epoch:54 train_loss:0.36648 +2025-04-18 07:47:53,826 INFO Epoch:54 val_res:0.600000 +2025-04-18 07:47:53,827 INFO Saving best model at Epoch 54 +2025-04-18 07:48:27,275 INFO Epoch:55 train_loss:0.36947 +2025-04-18 07:48:30,916 INFO Epoch:55 val_res:0.600000 +2025-04-18 07:49:02,491 INFO Epoch:56 train_loss:0.37493 +2025-04-18 07:49:05,828 INFO Epoch:56 val_res:0.601299 +2025-04-18 07:49:05,829 INFO Saving best model at Epoch 56 +2025-04-18 07:49:36,802 INFO Epoch:57 train_loss:0.36626 +2025-04-18 07:49:40,109 INFO Epoch:57 val_res:0.587013 +2025-04-18 07:50:11,016 INFO Epoch:58 train_loss:0.37962 +2025-04-18 07:50:14,613 INFO Epoch:58 val_res:0.601299 +2025-04-18 07:50:45,474 INFO Epoch:59 train_loss:0.35964 +2025-04-18 07:50:48,894 INFO Epoch:59 val_res:0.605195 +2025-04-18 07:50:48,895 INFO Saving best model at Epoch 59 +2025-04-18 07:51:19,453 INFO Epoch:60 train_loss:0.35649 +2025-04-18 07:51:23,028 INFO Epoch:60 val_res:0.620779 +2025-04-18 07:51:23,028 INFO Saving best model at Epoch 60 +2025-04-18 07:51:56,685 INFO Epoch:61 train_loss:0.34497 +2025-04-18 07:52:00,523 INFO Epoch:61 val_res:0.590909 +2025-04-18 07:52:29,743 INFO Epoch:62 train_loss:0.34879 +2025-04-18 07:52:33,521 INFO Epoch:62 val_res:0.607792 +2025-04-18 07:53:01,372 INFO Epoch:63 train_loss:0.35150 +2025-04-18 07:53:04,956 INFO Epoch:63 val_res:0.607792 +2025-04-18 07:53:35,856 INFO Epoch:64 train_loss:0.32476 +2025-04-18 07:53:39,668 INFO Epoch:64 val_res:0.610390 +2025-04-18 07:54:08,230 INFO Epoch:65 train_loss:0.32075 +2025-04-18 07:54:11,673 INFO Epoch:65 val_res:0.605195 +2025-04-18 07:54:40,869 INFO Epoch:66 train_loss:0.31897 +2025-04-18 07:54:44,571 INFO Epoch:66 val_res:0.601299 +2025-04-18 07:55:14,506 INFO Epoch:67 train_loss:0.34853 +2025-04-18 07:55:18,581 INFO Epoch:67 val_res:0.606494 +2025-04-18 07:55:52,548 INFO Epoch:68 train_loss:0.34562 +2025-04-18 07:55:56,050 INFO Epoch:68 val_res:0.619480 +2025-04-18 07:56:27,068 INFO Epoch:69 train_loss:0.32669 +2025-04-18 07:56:31,418 INFO Epoch:69 val_res:0.628571 +2025-04-18 07:56:31,418 INFO Saving best model at Epoch 69 +2025-04-18 07:57:06,742 INFO Epoch:70 train_loss:0.33028 +2025-04-18 07:57:11,244 INFO Epoch:70 val_res:0.611688 +2025-04-18 07:57:43,628 INFO Epoch:71 train_loss:0.35467 +2025-04-18 07:57:47,521 INFO Epoch:71 val_res:0.618182 +2025-04-18 07:58:19,449 INFO Epoch:72 train_loss:0.35076 +2025-04-18 07:58:23,931 INFO Epoch:72 val_res:0.610390 +2025-04-18 07:58:53,742 INFO Epoch:73 train_loss:0.31506 +2025-04-18 07:58:57,258 INFO Epoch:73 val_res:0.618182 +2025-04-18 07:59:25,999 INFO Epoch:74 train_loss:0.31806 +2025-04-18 07:59:29,434 INFO Epoch:74 val_res:0.615584 +2025-04-18 07:59:58,170 INFO Epoch:75 train_loss:0.32750 +2025-04-18 08:00:01,937 INFO Epoch:75 val_res:0.602597 +2025-04-18 08:00:30,439 INFO Epoch:76 train_loss:0.32539 +2025-04-18 08:00:33,889 INFO Epoch:76 val_res:0.615584 +2025-04-18 08:01:03,407 INFO Epoch:77 train_loss:0.30671 +2025-04-18 08:01:07,141 INFO Epoch:77 val_res:0.620779 +2025-04-18 08:01:38,382 INFO Epoch:78 train_loss:0.33710 +2025-04-18 08:01:42,639 INFO Epoch:78 val_res:0.631169 +2025-04-18 08:01:42,639 INFO Saving best model at Epoch 78 +2025-04-18 08:02:14,627 INFO Epoch:79 train_loss:0.32361 +2025-04-18 08:02:18,222 INFO Epoch:79 val_res:0.619480 +2025-04-18 08:02:50,262 INFO Epoch:80 train_loss:0.32891 +2025-04-18 08:02:54,498 INFO Epoch:80 val_res:0.624675 +2025-04-18 08:03:23,336 INFO Epoch:81 train_loss:0.30368 +2025-04-18 08:03:26,654 INFO Epoch:81 val_res:0.623377 +2025-04-18 08:03:57,732 INFO Epoch:82 train_loss:0.29987 +2025-04-18 08:04:01,450 INFO Epoch:82 val_res:0.623377 +2025-04-18 08:04:32,530 INFO Epoch:83 train_loss:0.30871 +2025-04-18 08:04:36,300 INFO Epoch:83 val_res:0.618182 +2025-04-18 08:05:09,027 INFO Epoch:84 train_loss:0.30799 +2025-04-18 08:05:12,446 INFO Epoch:84 val_res:0.616883 +2025-04-18 08:05:41,708 INFO Epoch:85 train_loss:0.31053 +2025-04-18 08:05:45,530 INFO Epoch:85 val_res:0.622078 +2025-04-18 08:06:16,476 INFO Epoch:86 train_loss:0.30493 +2025-04-18 08:06:20,832 INFO Epoch:86 val_res:0.641558 +2025-04-18 08:06:20,832 INFO Saving best model at Epoch 86 +2025-04-18 08:06:51,624 INFO Epoch:87 train_loss:0.36110 +2025-04-18 08:06:55,033 INFO Epoch:87 val_res:0.625974 +2025-04-18 08:07:22,889 INFO Epoch:88 train_loss:0.32132 +2025-04-18 08:07:26,424 INFO Epoch:88 val_res:0.624675 +2025-04-18 08:07:55,936 INFO Epoch:89 train_loss:0.29093 +2025-04-18 08:07:59,329 INFO Epoch:89 val_res:0.644156 +2025-04-18 08:07:59,329 INFO Saving best model at Epoch 89 +2025-04-18 08:08:30,414 INFO Epoch:90 train_loss:0.28615 +2025-04-18 08:08:33,922 INFO Epoch:90 val_res:0.635065 +2025-04-18 08:09:02,840 INFO Epoch:91 train_loss:0.29156 +2025-04-18 08:09:06,192 INFO Epoch:91 val_res:0.635065 +2025-04-18 08:09:34,603 INFO Epoch:92 train_loss:0.30075 +2025-04-18 08:09:37,837 INFO Epoch:92 val_res:0.645455 +2025-04-18 08:09:37,838 INFO Saving best model at Epoch 92 +2025-04-18 08:10:08,569 INFO Epoch:93 train_loss:0.29064 +2025-04-18 08:10:11,967 INFO Epoch:93 val_res:0.645455 +2025-04-18 08:10:40,939 INFO Epoch:94 train_loss:0.29011 +2025-04-18 08:10:44,416 INFO Epoch:94 val_res:0.641558 +2025-04-18 08:11:13,815 INFO Epoch:95 train_loss:0.29029 +2025-04-18 08:11:17,497 INFO Epoch:95 val_res:0.640260 +2025-04-18 08:11:48,195 INFO Epoch:96 train_loss:0.28456 +2025-04-18 08:11:51,807 INFO Epoch:96 val_res:0.659740 +2025-04-18 08:11:51,808 INFO Saving best model at Epoch 96 +2025-04-18 08:12:22,628 INFO Epoch:97 train_loss:0.29201 +2025-04-18 08:12:26,017 INFO Epoch:97 val_res:0.651948 +2025-04-18 08:12:55,149 INFO Epoch:98 train_loss:0.27857 +2025-04-18 08:12:58,583 INFO Epoch:98 val_res:0.640260 +2025-04-18 08:13:28,710 INFO Epoch:99 train_loss:0.28040 +2025-04-18 08:13:32,910 INFO Epoch:99 val_res:0.640260 +2025-04-18 08:13:33,606 INFO ===================================== +2025-04-18 08:13:33,606 INFO Start testing... +2025-04-18 08:13:33,607 INFO ===================================== +2025-04-18 08:14:09,716 INFO Incremental step 1 Testing res: 0.610390 +2025-04-18 08:14:09,717 INFO forgetting: 0.083333 +2025-04-18 08:14:09,720 INFO ***************New Step*************************** +2025-04-18 08:14:09,720 INFO Incremental step: 2 +2025-04-18 08:14:09,887 INFO actual size of exemplar set: 492 +2025-04-18 08:17:23,662 INFO Epoch:0 train_loss:1.57901 +2025-04-18 08:17:42,207 INFO Epoch:0 val_res:0.401910 +2025-04-18 08:17:42,207 INFO Saving best model at Epoch 0 +2025-04-18 08:18:19,256 INFO Epoch:1 train_loss:1.64594 +2025-04-18 08:18:25,143 INFO Epoch:1 val_res:0.451389 +2025-04-18 08:18:25,144 INFO Saving best model at Epoch 1 +2025-04-18 08:19:07,947 INFO Epoch:2 train_loss:1.53199 +2025-04-18 08:19:13,915 INFO Epoch:2 val_res:0.477431 +2025-04-18 08:19:13,915 INFO Saving best model at Epoch 2 +2025-04-18 08:19:57,063 INFO Epoch:3 train_loss:1.15572 +2025-04-18 08:20:06,320 INFO Epoch:3 val_res:0.443576 +2025-04-18 08:20:50,595 INFO Epoch:4 train_loss:1.37094 +2025-04-18 08:20:58,618 INFO Epoch:4 val_res:0.469618 +2025-04-18 08:21:36,590 INFO Epoch:5 train_loss:1.26729 +2025-04-18 08:21:43,851 INFO Epoch:5 val_res:0.451389 +2025-04-18 08:22:24,544 INFO Epoch:6 train_loss:1.46960 +2025-04-18 08:22:31,971 INFO Epoch:6 val_res:0.470486 +2025-04-18 08:23:09,843 INFO Epoch:7 train_loss:1.17868 +2025-04-18 08:23:17,002 INFO Epoch:7 val_res:0.454861 +2025-04-18 08:23:57,439 INFO Epoch:8 train_loss:1.85986 +2025-04-18 08:24:04,854 INFO Epoch:8 val_res:0.434028 +2025-04-18 08:24:44,659 INFO Epoch:9 train_loss:1.44459 +2025-04-18 08:24:51,823 INFO Epoch:9 val_res:0.463542 +2025-04-18 08:25:29,473 INFO Epoch:10 train_loss:1.19771 +2025-04-18 08:25:36,526 INFO Epoch:10 val_res:0.461806 +2025-04-18 08:26:16,905 INFO Epoch:11 train_loss:1.46833 +2025-04-18 08:26:23,004 INFO Epoch:11 val_res:0.468750 +2025-04-18 08:26:59,156 INFO Epoch:12 train_loss:1.43234 +2025-04-18 08:27:06,168 INFO Epoch:12 val_res:0.494792 +2025-04-18 08:27:06,168 INFO Saving best model at Epoch 12 +2025-04-18 08:27:40,425 INFO Epoch:13 train_loss:1.20151 +2025-04-18 08:27:46,651 INFO Epoch:13 val_res:0.468750 +2025-04-18 08:28:21,583 INFO Epoch:14 train_loss:1.15015 +2025-04-18 08:28:28,932 INFO Epoch:14 val_res:0.476562 +2025-04-18 08:29:05,230 INFO Epoch:15 train_loss:1.25963 +2025-04-18 08:29:12,855 INFO Epoch:15 val_res:0.453125 +2025-04-18 08:29:51,094 INFO Epoch:16 train_loss:1.26156 +2025-04-18 08:29:56,609 INFO Epoch:16 val_res:0.477431 +2025-04-18 08:30:29,391 INFO Epoch:17 train_loss:0.90219 +2025-04-18 08:30:35,181 INFO Epoch:17 val_res:0.498264 +2025-04-18 08:30:35,182 INFO Saving best model at Epoch 17 +2025-04-18 08:31:12,292 INFO Epoch:18 train_loss:0.76978 +2025-04-18 08:31:19,438 INFO Epoch:18 val_res:0.506076 +2025-04-18 08:31:19,439 INFO Saving best model at Epoch 18 +2025-04-18 08:31:57,770 INFO Epoch:19 train_loss:0.70985 +2025-04-18 08:32:04,787 INFO Epoch:19 val_res:0.527778 +2025-04-18 08:32:04,787 INFO Saving best model at Epoch 19 +2025-04-18 08:32:42,060 INFO Epoch:20 train_loss:0.69165 +2025-04-18 08:32:48,252 INFO Epoch:20 val_res:0.528646 +2025-04-18 08:32:48,253 INFO Saving best model at Epoch 20 +2025-04-18 08:33:25,007 INFO Epoch:21 train_loss:0.69280 +2025-04-18 08:33:31,696 INFO Epoch:21 val_res:0.518229 +2025-04-18 08:34:09,912 INFO Epoch:22 train_loss:0.66168 +2025-04-18 08:34:17,152 INFO Epoch:22 val_res:0.535590 +2025-04-18 08:34:17,153 INFO Saving best model at Epoch 22 +2025-04-18 08:34:55,972 INFO Epoch:23 train_loss:0.66930 +2025-04-18 08:35:02,714 INFO Epoch:23 val_res:0.533854 +2025-04-18 08:35:40,681 INFO Epoch:24 train_loss:0.88202 +2025-04-18 08:35:47,161 INFO Epoch:24 val_res:0.516493 +2025-04-18 08:36:24,208 INFO Epoch:25 train_loss:0.80130 +2025-04-18 08:36:31,605 INFO Epoch:25 val_res:0.546007 +2025-04-18 08:36:31,605 INFO Saving best model at Epoch 25 +2025-04-18 08:37:09,513 INFO Epoch:26 train_loss:0.66231 +2025-04-18 08:37:15,789 INFO Epoch:26 val_res:0.543403 +2025-04-18 08:37:50,953 INFO Epoch:27 train_loss:0.63072 +2025-04-18 08:37:56,083 INFO Epoch:27 val_res:0.544271 +2025-04-18 08:38:29,880 INFO Epoch:28 train_loss:0.62714 +2025-04-18 08:38:36,258 INFO Epoch:28 val_res:0.527778 +2025-04-18 08:39:09,267 INFO Epoch:29 train_loss:0.64144 +2025-04-18 08:39:15,245 INFO Epoch:29 val_res:0.516493 +2025-04-18 08:39:49,142 INFO Epoch:30 train_loss:0.71966 +2025-04-18 08:39:55,026 INFO Epoch:30 val_res:0.514757 +2025-04-18 08:40:29,786 INFO Epoch:31 train_loss:1.07371 +2025-04-18 08:40:35,509 INFO Epoch:31 val_res:0.532986 +2025-04-18 08:41:09,281 INFO Epoch:32 train_loss:0.75578 +2025-04-18 08:41:14,597 INFO Epoch:32 val_res:0.535590 +2025-04-18 08:41:46,965 INFO Epoch:33 train_loss:0.63944 +2025-04-18 08:41:52,962 INFO Epoch:33 val_res:0.547743 +2025-04-18 08:41:52,962 INFO Saving best model at Epoch 33 +2025-04-18 08:42:29,711 INFO Epoch:34 train_loss:0.67052 +2025-04-18 08:42:35,327 INFO Epoch:34 val_res:0.540799 +2025-04-18 08:43:10,388 INFO Epoch:35 train_loss:0.97647 +2025-04-18 08:43:16,230 INFO Epoch:35 val_res:0.521701 +2025-04-18 08:43:52,317 INFO Epoch:36 train_loss:0.76458 +2025-04-18 08:43:58,166 INFO Epoch:36 val_res:0.535590 +2025-04-18 08:44:35,002 INFO Epoch:37 train_loss:0.63941 +2025-04-18 08:44:41,614 INFO Epoch:37 val_res:0.552083 +2025-04-18 08:44:41,615 INFO Saving best model at Epoch 37 +2025-04-18 08:45:19,138 INFO Epoch:38 train_loss:0.59829 +2025-04-18 08:45:25,019 INFO Epoch:38 val_res:0.546007 +2025-04-18 08:46:01,823 INFO Epoch:39 train_loss:0.57351 +2025-04-18 08:46:08,041 INFO Epoch:39 val_res:0.547743 +2025-04-18 08:46:40,745 INFO Epoch:40 train_loss:0.58257 +2025-04-18 08:46:46,759 INFO Epoch:40 val_res:0.547743 +2025-04-18 08:47:22,307 INFO Epoch:41 train_loss:0.56993 +2025-04-18 08:47:28,333 INFO Epoch:41 val_res:0.539062 +2025-04-18 08:48:03,684 INFO Epoch:42 train_loss:0.56114 +2025-04-18 08:48:09,452 INFO Epoch:42 val_res:0.547743 +2025-04-18 08:48:45,415 INFO Epoch:43 train_loss:0.55077 +2025-04-18 08:48:51,490 INFO Epoch:43 val_res:0.553819 +2025-04-18 08:48:51,490 INFO Saving best model at Epoch 43 +2025-04-18 08:49:26,098 INFO Epoch:44 train_loss:0.54944 +2025-04-18 08:49:31,318 INFO Epoch:44 val_res:0.555556 +2025-04-18 08:49:31,319 INFO Saving best model at Epoch 44 +2025-04-18 08:50:09,032 INFO Epoch:45 train_loss:0.55014 +2025-04-18 08:50:14,533 INFO Epoch:45 val_res:0.557292 +2025-04-18 08:50:14,533 INFO Saving best model at Epoch 45 +2025-04-18 08:50:50,954 INFO Epoch:46 train_loss:0.60206 +2025-04-18 08:50:57,076 INFO Epoch:46 val_res:0.552951 +2025-04-18 08:51:33,054 INFO Epoch:47 train_loss:0.68551 +2025-04-18 08:51:38,700 INFO Epoch:47 val_res:0.542535 +2025-04-18 08:52:14,834 INFO Epoch:48 train_loss:0.60498 +2025-04-18 08:52:21,342 INFO Epoch:48 val_res:0.553819 +2025-04-18 08:52:58,234 INFO Epoch:49 train_loss:0.61147 +2025-04-18 08:53:04,459 INFO Epoch:49 val_res:0.566840 +2025-04-18 08:53:04,459 INFO Saving best model at Epoch 49 +2025-04-18 08:53:43,186 INFO Epoch:50 train_loss:0.56018 +2025-04-18 08:53:49,951 INFO Epoch:50 val_res:0.563368 +2025-04-18 08:54:26,442 INFO Epoch:51 train_loss:0.55038 +2025-04-18 08:54:31,489 INFO Epoch:51 val_res:0.557292 +2025-04-18 08:55:04,243 INFO Epoch:52 train_loss:0.55037 +2025-04-18 08:55:09,881 INFO Epoch:52 val_res:0.565972 +2025-04-18 08:55:45,257 INFO Epoch:53 train_loss:0.53409 +2025-04-18 08:55:51,648 INFO Epoch:53 val_res:0.573785 +2025-04-18 08:55:51,648 INFO Saving best model at Epoch 53 +2025-04-18 08:56:28,430 INFO Epoch:54 train_loss:0.53986 +2025-04-18 08:56:34,394 INFO Epoch:54 val_res:0.552083 +2025-04-18 08:57:07,088 INFO Epoch:55 train_loss:0.50228 +2025-04-18 08:57:13,146 INFO Epoch:55 val_res:0.561632 +2025-04-18 08:57:46,020 INFO Epoch:56 train_loss:0.53629 +2025-04-18 08:57:52,059 INFO Epoch:56 val_res:0.564236 +2025-04-18 08:58:27,178 INFO Epoch:57 train_loss:0.54620 +2025-04-18 08:58:32,944 INFO Epoch:57 val_res:0.569444 +2025-04-18 08:59:08,981 INFO Epoch:58 train_loss:0.51383 +2025-04-18 08:59:14,931 INFO Epoch:58 val_res:0.561632 +2025-04-18 08:59:51,944 INFO Epoch:59 train_loss:0.52611 +2025-04-18 08:59:57,733 INFO Epoch:59 val_res:0.556424 +2025-04-18 09:00:33,144 INFO Epoch:60 train_loss:0.56775 +2025-04-18 09:00:39,428 INFO Epoch:60 val_res:0.563368 +2025-04-18 09:01:17,176 INFO Epoch:61 train_loss:0.53660 +2025-04-18 09:01:23,423 INFO Epoch:61 val_res:0.574653 +2025-04-18 09:01:23,424 INFO Saving best model at Epoch 61 +2025-04-18 09:02:02,671 INFO Epoch:62 train_loss:0.52000 +2025-04-18 09:02:09,004 INFO Epoch:62 val_res:0.572049 +2025-04-18 09:02:44,418 INFO Epoch:63 train_loss:0.51859 +2025-04-18 09:02:49,479 INFO Epoch:63 val_res:0.570312 +2025-04-18 09:03:23,795 INFO Epoch:64 train_loss:0.50371 +2025-04-18 09:03:29,552 INFO Epoch:64 val_res:0.572049 +2025-04-18 09:04:04,052 INFO Epoch:65 train_loss:0.49933 +2025-04-18 09:04:10,267 INFO Epoch:65 val_res:0.568576 +2025-04-18 09:04:45,023 INFO Epoch:66 train_loss:0.53298 +2025-04-18 09:04:50,414 INFO Epoch:66 val_res:0.574653 +2025-04-18 09:05:24,602 INFO Epoch:67 train_loss:0.51321 +2025-04-18 09:05:29,713 INFO Epoch:67 val_res:0.571181 +2025-04-18 09:06:03,581 INFO Epoch:68 train_loss:0.50814 +2025-04-18 09:06:09,984 INFO Epoch:68 val_res:0.568576 +2025-04-18 09:06:45,433 INFO Epoch:69 train_loss:0.52265 +2025-04-18 09:06:51,231 INFO Epoch:69 val_res:0.572917 +2025-04-18 09:07:27,167 INFO Epoch:70 train_loss:0.52446 +2025-04-18 09:07:33,048 INFO Epoch:70 val_res:0.570312 +2025-04-18 09:08:10,438 INFO Epoch:71 train_loss:0.49203 +2025-04-18 09:08:17,186 INFO Epoch:71 val_res:0.573785 +2025-04-18 09:08:54,571 INFO Epoch:72 train_loss:0.50394 +2025-04-18 09:09:00,660 INFO Epoch:72 val_res:0.557292 +2025-04-18 09:09:37,100 INFO Epoch:73 train_loss:0.48738 +2025-04-18 09:09:43,751 INFO Epoch:73 val_res:0.592014 +2025-04-18 09:09:43,751 INFO Saving best model at Epoch 73 +2025-04-18 09:10:20,548 INFO Epoch:74 train_loss:0.50787 +2025-04-18 09:10:25,767 INFO Epoch:74 val_res:0.591146 +2025-04-18 09:10:59,271 INFO Epoch:75 train_loss:0.49150 +2025-04-18 09:11:05,160 INFO Epoch:75 val_res:0.581597 +2025-04-18 09:11:40,573 INFO Epoch:76 train_loss:0.46518 +2025-04-18 09:11:46,033 INFO Epoch:76 val_res:0.582465 +2025-04-18 09:12:21,158 INFO Epoch:77 train_loss:0.50377 +2025-04-18 09:12:26,338 INFO Epoch:77 val_res:0.578125 +2025-04-18 09:13:02,380 INFO Epoch:78 train_loss:0.46343 +2025-04-18 09:13:07,780 INFO Epoch:78 val_res:0.579861 +2025-04-18 09:13:40,179 INFO Epoch:79 train_loss:0.44652 +2025-04-18 09:13:45,634 INFO Epoch:79 val_res:0.590278 +2025-04-18 09:14:19,131 INFO Epoch:80 train_loss:0.47241 +2025-04-18 09:14:24,722 INFO Epoch:80 val_res:0.575521 +2025-04-18 09:14:58,011 INFO Epoch:81 train_loss:0.52174 +2025-04-18 09:15:03,857 INFO Epoch:81 val_res:0.592014 +2025-04-18 09:15:38,270 INFO Epoch:82 train_loss:0.46934 +2025-04-18 09:15:43,920 INFO Epoch:82 val_res:0.571181 +2025-04-18 09:16:17,923 INFO Epoch:83 train_loss:0.45770 +2025-04-18 09:16:23,571 INFO Epoch:83 val_res:0.580729 +2025-04-18 09:17:01,318 INFO Epoch:84 train_loss:0.48486 +2025-04-18 09:17:07,922 INFO Epoch:84 val_res:0.579861 +2025-04-18 09:17:45,081 INFO Epoch:85 train_loss:0.45200 +2025-04-18 09:17:50,595 INFO Epoch:85 val_res:0.585069 +2025-04-18 09:18:23,739 INFO Epoch:86 train_loss:0.45907 +2025-04-18 09:18:28,838 INFO Epoch:86 val_res:0.587674 +2025-04-18 09:19:01,448 INFO Epoch:87 train_loss:0.45561 +2025-04-18 09:19:07,058 INFO Epoch:87 val_res:0.577257 +2025-04-18 09:19:39,292 INFO Epoch:88 train_loss:0.43720 +2025-04-18 09:19:44,793 INFO Epoch:88 val_res:0.586806 +2025-04-18 09:20:18,887 INFO Epoch:89 train_loss:0.43375 +2025-04-18 09:20:24,812 INFO Epoch:89 val_res:0.592014 +2025-04-18 09:21:00,530 INFO Epoch:90 train_loss:0.42234 +2025-04-18 09:21:06,345 INFO Epoch:90 val_res:0.578125 +2025-04-18 09:21:41,165 INFO Epoch:91 train_loss:0.46090 +2025-04-18 09:21:46,888 INFO Epoch:91 val_res:0.582465 +2025-04-18 09:22:22,108 INFO Epoch:92 train_loss:0.43322 +2025-04-18 09:22:28,230 INFO Epoch:92 val_res:0.605035 +2025-04-18 09:22:28,230 INFO Saving best model at Epoch 92 +2025-04-18 09:23:08,377 INFO Epoch:93 train_loss:0.46964 +2025-04-18 09:23:14,899 INFO Epoch:93 val_res:0.584201 +2025-04-18 09:23:52,849 INFO Epoch:94 train_loss:0.49926 +2025-04-18 09:23:59,442 INFO Epoch:94 val_res:0.579861 +2025-04-18 09:24:36,982 INFO Epoch:95 train_loss:0.43983 +2025-04-18 09:24:42,704 INFO Epoch:95 val_res:0.597222 +2025-04-18 09:25:16,592 INFO Epoch:96 train_loss:0.44130 +2025-04-18 09:25:22,314 INFO Epoch:96 val_res:0.587674 +2025-04-18 09:25:56,366 INFO Epoch:97 train_loss:0.46166 +2025-04-18 09:26:01,768 INFO Epoch:97 val_res:0.599826 +2025-04-18 09:26:37,614 INFO Epoch:98 train_loss:0.42522 +2025-04-18 09:26:43,096 INFO Epoch:98 val_res:0.594618 +2025-04-18 09:27:12,348 INFO Epoch:99 train_loss:0.45061 +2025-04-18 09:27:17,006 INFO Epoch:99 val_res:0.592014 +2025-04-18 09:27:18,136 INFO ===================================== +2025-04-18 09:27:18,136 INFO Start testing... +2025-04-18 09:27:18,153 INFO ===================================== +2025-04-18 09:27:25,429 INFO Incremental step 2 Testing res: 0.581456 +2025-04-18 09:27:25,431 INFO forgetting: -0.022721 +2025-04-18 09:27:25,436 INFO ***************New Step*************************** +2025-04-18 09:27:25,436 INFO Incremental step: 3 +2025-04-18 09:27:25,690 INFO actual size of exemplar set: 486 +2025-04-18 09:30:16,711 INFO Epoch:0 train_loss:3.26035 +2025-04-18 09:30:40,726 INFO Epoch:0 val_res:0.367056 +2025-04-18 09:30:40,730 INFO Saving best model at Epoch 0 +2025-04-18 09:31:20,775 INFO Epoch:1 train_loss:2.12387 +2025-04-18 09:31:27,685 INFO Epoch:1 val_res:0.389105 +2025-04-18 09:31:27,692 INFO Saving best model at Epoch 1 +2025-04-18 09:32:09,569 INFO Epoch:2 train_loss:1.60222 +2025-04-18 09:32:16,674 INFO Epoch:2 val_res:0.399481 +2025-04-18 09:32:16,680 INFO Saving best model at Epoch 2 +2025-04-18 09:33:00,515 INFO Epoch:3 train_loss:1.47380 +2025-04-18 09:33:09,136 INFO Epoch:3 val_res:0.444877 +2025-04-18 09:33:09,143 INFO Saving best model at Epoch 3 +2025-04-18 09:33:50,149 INFO Epoch:4 train_loss:1.32700 +2025-04-18 09:33:56,683 INFO Epoch:4 val_res:0.435798 +2025-04-18 09:34:32,395 INFO Epoch:5 train_loss:1.24165 +2025-04-18 09:34:38,807 INFO Epoch:5 val_res:0.449416 +2025-04-18 09:34:38,814 INFO Saving best model at Epoch 5 +2025-04-18 09:35:17,979 INFO Epoch:6 train_loss:1.18927 +2025-04-18 09:35:24,669 INFO Epoch:6 val_res:0.445525 +2025-04-18 09:36:01,507 INFO Epoch:7 train_loss:1.05039 +2025-04-18 09:36:07,957 INFO Epoch:7 val_res:0.450713 +2025-04-18 09:36:07,957 INFO Saving best model at Epoch 7 +2025-04-18 09:36:47,734 INFO Epoch:8 train_loss:1.11084 +2025-04-18 09:36:54,744 INFO Epoch:8 val_res:0.440337 +2025-04-18 09:37:30,115 INFO Epoch:9 train_loss:1.16340 +2025-04-18 09:37:37,063 INFO Epoch:9 val_res:0.421530 +2025-04-18 09:38:13,433 INFO Epoch:10 train_loss:1.18063 +2025-04-18 09:38:20,689 INFO Epoch:10 val_res:0.448119 +2025-04-18 09:39:00,189 INFO Epoch:11 train_loss:1.10881 +2025-04-18 09:39:08,389 INFO Epoch:11 val_res:0.442931 +2025-04-18 09:39:47,301 INFO Epoch:12 train_loss:1.18872 +2025-04-18 09:39:55,750 INFO Epoch:12 val_res:0.450065 +2025-04-18 09:40:32,023 INFO Epoch:13 train_loss:1.02381 +2025-04-18 09:40:39,119 INFO Epoch:13 val_res:0.468223 +2025-04-18 09:40:39,126 INFO Saving best model at Epoch 13 +2025-04-18 09:41:18,271 INFO Epoch:14 train_loss:0.93624 +2025-04-18 09:41:25,660 INFO Epoch:14 val_res:0.486381 +2025-04-18 09:41:25,665 INFO Saving best model at Epoch 14 +2025-04-18 09:42:04,054 INFO Epoch:15 train_loss:0.77859 +2025-04-18 09:42:11,008 INFO Epoch:15 val_res:0.460441 +2025-04-18 09:42:45,804 INFO Epoch:16 train_loss:0.68813 +2025-04-18 09:42:52,215 INFO Epoch:16 val_res:0.477302 +2025-04-18 09:43:26,664 INFO Epoch:17 train_loss:0.66942 +2025-04-18 09:43:33,194 INFO Epoch:17 val_res:0.477302 +2025-04-18 09:44:07,974 INFO Epoch:18 train_loss:0.76079 +2025-04-18 09:44:15,100 INFO Epoch:18 val_res:0.493515 +2025-04-18 09:44:15,107 INFO Saving best model at Epoch 18 +2025-04-18 09:44:53,499 INFO Epoch:19 train_loss:0.69587 +2025-04-18 09:45:00,080 INFO Epoch:19 val_res:0.503243 +2025-04-18 09:45:00,081 INFO Saving best model at Epoch 19 +2025-04-18 09:45:38,540 INFO Epoch:20 train_loss:0.63448 +2025-04-18 09:45:45,794 INFO Epoch:20 val_res:0.485733 +2025-04-18 09:46:27,272 INFO Epoch:21 train_loss:0.71050 +2025-04-18 09:46:35,500 INFO Epoch:21 val_res:0.513619 +2025-04-18 09:46:35,506 INFO Saving best model at Epoch 21 +2025-04-18 09:47:15,631 INFO Epoch:22 train_loss:0.70530 +2025-04-18 09:47:22,392 INFO Epoch:22 val_res:0.512970 +2025-04-18 09:47:57,947 INFO Epoch:23 train_loss:0.61607 +2025-04-18 09:48:05,056 INFO Epoch:23 val_res:0.500648 +2025-04-18 09:48:41,747 INFO Epoch:24 train_loss:0.61336 +2025-04-18 09:48:48,424 INFO Epoch:24 val_res:0.504540 +2025-04-18 09:49:24,224 INFO Epoch:25 train_loss:0.60460 +2025-04-18 09:49:30,359 INFO Epoch:25 val_res:0.500648 +2025-04-18 09:50:03,791 INFO Epoch:26 train_loss:0.59471 +2025-04-18 09:50:10,252 INFO Epoch:26 val_res:0.500000 +2025-04-18 09:50:46,222 INFO Epoch:27 train_loss:0.58356 +2025-04-18 09:50:52,729 INFO Epoch:27 val_res:0.527886 +2025-04-18 09:50:52,730 INFO Saving best model at Epoch 27 +2025-04-18 09:51:30,407 INFO Epoch:28 train_loss:0.57922 +2025-04-18 09:51:37,237 INFO Epoch:28 val_res:0.515564 +2025-04-18 09:52:13,881 INFO Epoch:29 train_loss:0.64432 +2025-04-18 09:52:20,653 INFO Epoch:29 val_res:0.501297 +2025-04-18 09:52:59,110 INFO Epoch:30 train_loss:0.67543 +2025-04-18 09:53:06,522 INFO Epoch:30 val_res:0.518807 +2025-04-18 09:53:47,423 INFO Epoch:31 train_loss:0.67212 +2025-04-18 09:53:55,760 INFO Epoch:31 val_res:0.524643 +2025-04-18 09:54:31,735 INFO Epoch:32 train_loss:0.55228 +2025-04-18 09:54:38,433 INFO Epoch:32 val_res:0.527237 +2025-04-18 09:55:14,998 INFO Epoch:33 train_loss:0.54753 +2025-04-18 09:55:22,201 INFO Epoch:33 val_res:0.523346 +2025-04-18 09:55:56,979 INFO Epoch:34 train_loss:0.56626 +2025-04-18 09:56:03,992 INFO Epoch:34 val_res:0.518807 +2025-04-18 09:56:40,364 INFO Epoch:35 train_loss:0.57575 +2025-04-18 09:56:46,955 INFO Epoch:35 val_res:0.522049 +2025-04-18 09:57:21,122 INFO Epoch:36 train_loss:0.56352 +2025-04-18 09:57:27,844 INFO Epoch:36 val_res:0.525292 +2025-04-18 09:58:06,192 INFO Epoch:37 train_loss:0.60393 +2025-04-18 09:58:13,378 INFO Epoch:37 val_res:0.523995 +2025-04-18 09:58:49,526 INFO Epoch:38 train_loss:0.61605 +2025-04-18 09:58:56,769 INFO Epoch:38 val_res:0.529183 +2025-04-18 09:58:56,769 INFO Saving best model at Epoch 38 +2025-04-18 09:59:39,469 INFO Epoch:39 train_loss:0.65689 +2025-04-18 09:59:47,499 INFO Epoch:39 val_res:0.512970 +2025-04-18 10:00:26,950 INFO Epoch:40 train_loss:0.59092 +2025-04-18 10:00:33,754 INFO Epoch:40 val_res:0.531128 +2025-04-18 10:00:33,754 INFO Saving best model at Epoch 40 +2025-04-18 10:01:10,941 INFO Epoch:41 train_loss:0.55406 +2025-04-18 10:01:17,525 INFO Epoch:41 val_res:0.534371 +2025-04-18 10:01:17,526 INFO Saving best model at Epoch 41 +2025-04-18 10:01:55,334 INFO Epoch:42 train_loss:0.51763 +2025-04-18 10:02:02,925 INFO Epoch:42 val_res:0.527237 +2025-04-18 10:02:37,625 INFO Epoch:43 train_loss:0.49676 +2025-04-18 10:02:44,479 INFO Epoch:43 val_res:0.532425 +2025-04-18 10:03:20,537 INFO Epoch:44 train_loss:0.49396 +2025-04-18 10:03:27,354 INFO Epoch:44 val_res:0.539559 +2025-04-18 10:03:27,360 INFO Saving best model at Epoch 44 +2025-04-18 10:04:07,186 INFO Epoch:45 train_loss:0.51103 +2025-04-18 10:04:13,986 INFO Epoch:45 val_res:0.544747 +2025-04-18 10:04:13,993 INFO Saving best model at Epoch 45 +2025-04-18 10:04:53,610 INFO Epoch:46 train_loss:0.51747 +2025-04-18 10:05:01,492 INFO Epoch:46 val_res:0.522049 +2025-04-18 10:05:40,450 INFO Epoch:47 train_loss:0.48471 +2025-04-18 10:05:48,335 INFO Epoch:47 val_res:0.514916 +2025-04-18 10:06:29,656 INFO Epoch:48 train_loss:0.52128 +2025-04-18 10:06:38,645 INFO Epoch:48 val_res:0.533722 +2025-04-18 10:07:14,800 INFO Epoch:49 train_loss:0.51528 +2025-04-18 10:07:21,611 INFO Epoch:49 val_res:0.527886 +2025-04-18 10:07:57,782 INFO Epoch:50 train_loss:0.49123 +2025-04-18 10:08:04,959 INFO Epoch:50 val_res:0.536965 +2025-04-18 10:08:39,182 INFO Epoch:51 train_loss:0.48543 +2025-04-18 10:08:46,315 INFO Epoch:51 val_res:0.546693 +2025-04-18 10:08:46,320 INFO Saving best model at Epoch 51 +2025-04-18 10:09:24,427 INFO Epoch:52 train_loss:0.48990 +2025-04-18 10:09:30,927 INFO Epoch:52 val_res:0.546693 +2025-04-18 10:10:05,010 INFO Epoch:53 train_loss:0.49464 +2025-04-18 10:10:11,257 INFO Epoch:53 val_res:0.548638 +2025-04-18 10:10:11,259 INFO Saving best model at Epoch 53 +2025-04-18 10:10:48,438 INFO Epoch:54 train_loss:0.48166 +2025-04-18 10:10:55,154 INFO Epoch:54 val_res:0.554475 +2025-04-18 10:10:55,161 INFO Saving best model at Epoch 54 +2025-04-18 10:11:33,137 INFO Epoch:55 train_loss:0.47415 +2025-04-18 10:11:39,924 INFO Epoch:55 val_res:0.545396 +2025-04-18 10:12:14,386 INFO Epoch:56 train_loss:0.48520 +2025-04-18 10:12:21,170 INFO Epoch:56 val_res:0.555123 +2025-04-18 10:12:21,176 INFO Saving best model at Epoch 56 +2025-04-18 10:12:57,343 INFO Epoch:57 train_loss:0.47151 +2025-04-18 10:13:03,985 INFO Epoch:57 val_res:0.560311 +2025-04-18 10:13:03,991 INFO Saving best model at Epoch 57 +2025-04-18 10:13:40,053 INFO Epoch:58 train_loss:0.47844 +2025-04-18 10:13:46,522 INFO Epoch:58 val_res:0.564202 +2025-04-18 10:13:46,529 INFO Saving best model at Epoch 58 +2025-04-18 10:14:21,877 INFO Epoch:59 train_loss:0.47615 +2025-04-18 10:14:28,425 INFO Epoch:59 val_res:0.553826 +2025-04-18 10:15:02,166 INFO Epoch:60 train_loss:0.51427 +2025-04-18 10:15:09,199 INFO Epoch:60 val_res:0.536316 +2025-04-18 10:15:41,947 INFO Epoch:61 train_loss:0.51578 +2025-04-18 10:15:48,782 INFO Epoch:61 val_res:0.542802 +2025-04-18 10:16:21,718 INFO Epoch:62 train_loss:0.47154 +2025-04-18 10:16:28,729 INFO Epoch:62 val_res:0.560311 +2025-04-18 10:17:01,874 INFO Epoch:63 train_loss:0.44945 +2025-04-18 10:17:07,958 INFO Epoch:63 val_res:0.562905 +2025-04-18 10:17:40,813 INFO Epoch:64 train_loss:0.44074 +2025-04-18 10:17:46,785 INFO Epoch:64 val_res:0.557069 +2025-04-18 10:18:20,928 INFO Epoch:65 train_loss:0.43793 +2025-04-18 10:18:27,226 INFO Epoch:65 val_res:0.547341 +2025-04-18 10:19:00,301 INFO Epoch:66 train_loss:0.46313 +2025-04-18 10:19:06,155 INFO Epoch:66 val_res:0.553178 +2025-04-18 10:19:40,964 INFO Epoch:67 train_loss:0.43350 +2025-04-18 10:19:46,833 INFO Epoch:67 val_res:0.549935 +2025-04-18 10:20:19,944 INFO Epoch:68 train_loss:0.44985 +2025-04-18 10:20:25,952 INFO Epoch:68 val_res:0.555123 +2025-04-18 10:20:59,625 INFO Epoch:69 train_loss:0.47385 +2025-04-18 10:21:05,507 INFO Epoch:69 val_res:0.563554 +2025-04-18 10:21:38,457 INFO Epoch:70 train_loss:0.48171 +2025-04-18 10:21:44,839 INFO Epoch:70 val_res:0.557069 +2025-04-18 10:22:18,497 INFO Epoch:71 train_loss:0.46402 +2025-04-18 10:22:25,133 INFO Epoch:71 val_res:0.555772 +2025-04-18 10:22:58,890 INFO Epoch:72 train_loss:0.44648 +2025-04-18 10:23:05,603 INFO Epoch:72 val_res:0.563554 +2025-04-18 10:23:39,068 INFO Epoch:73 train_loss:0.41655 +2025-04-18 10:23:45,303 INFO Epoch:73 val_res:0.549935 +2025-04-18 10:24:17,829 INFO Epoch:74 train_loss:0.41993 +2025-04-18 10:24:24,514 INFO Epoch:74 val_res:0.562257 +2025-04-18 10:24:57,131 INFO Epoch:75 train_loss:0.45272 +2025-04-18 10:25:03,959 INFO Epoch:75 val_res:0.546044 +2025-04-18 10:25:35,670 INFO Epoch:76 train_loss:0.43583 +2025-04-18 10:25:41,883 INFO Epoch:76 val_res:0.565499 +2025-04-18 10:25:41,888 INFO Saving best model at Epoch 76 +2025-04-18 10:26:16,553 INFO Epoch:77 train_loss:0.43341 +2025-04-18 10:26:22,634 INFO Epoch:77 val_res:0.573930 +2025-04-18 10:26:22,641 INFO Saving best model at Epoch 77 +2025-04-18 10:26:57,497 INFO Epoch:78 train_loss:0.44804 +2025-04-18 10:27:03,903 INFO Epoch:78 val_res:0.559014 +2025-04-18 10:27:37,566 INFO Epoch:79 train_loss:0.44714 +2025-04-18 10:27:43,761 INFO Epoch:79 val_res:0.570039 +2025-04-18 10:28:15,813 INFO Epoch:80 train_loss:0.43064 +2025-04-18 10:28:22,439 INFO Epoch:80 val_res:0.564202 +2025-04-18 10:28:55,263 INFO Epoch:81 train_loss:0.43439 +2025-04-18 10:29:01,421 INFO Epoch:81 val_res:0.560311 +2025-04-18 10:29:32,631 INFO Epoch:82 train_loss:0.44449 +2025-04-18 10:29:38,840 INFO Epoch:82 val_res:0.551881 +2025-04-18 10:30:11,651 INFO Epoch:83 train_loss:0.43992 +2025-04-18 10:30:17,515 INFO Epoch:83 val_res:0.573281 +2025-04-18 10:30:48,295 INFO Epoch:84 train_loss:0.40251 +2025-04-18 10:30:54,312 INFO Epoch:84 val_res:0.572633 +2025-04-18 10:31:27,580 INFO Epoch:85 train_loss:0.41187 +2025-04-18 10:31:33,731 INFO Epoch:85 val_res:0.564202 +2025-04-18 10:32:07,687 INFO Epoch:86 train_loss:0.40841 +2025-04-18 10:32:13,639 INFO Epoch:86 val_res:0.568742 +2025-04-18 10:32:47,834 INFO Epoch:87 train_loss:0.41661 +2025-04-18 10:32:54,730 INFO Epoch:87 val_res:0.568093 +2025-04-18 10:33:28,782 INFO Epoch:88 train_loss:0.41256 +2025-04-18 10:33:35,433 INFO Epoch:88 val_res:0.571984 +2025-04-18 10:34:10,969 INFO Epoch:89 train_loss:0.39752 +2025-04-18 10:34:18,816 INFO Epoch:89 val_res:0.552529 +2025-04-18 10:34:53,265 INFO Epoch:90 train_loss:0.47753 +2025-04-18 10:35:00,777 INFO Epoch:90 val_res:0.571336 +2025-04-18 10:35:39,224 INFO Epoch:91 train_loss:0.47942 +2025-04-18 10:35:46,900 INFO Epoch:91 val_res:0.557069 +2025-04-18 10:36:21,523 INFO Epoch:92 train_loss:0.41659 +2025-04-18 10:36:28,990 INFO Epoch:92 val_res:0.551881 +2025-04-18 10:37:04,520 INFO Epoch:93 train_loss:0.40637 +2025-04-18 10:37:11,343 INFO Epoch:93 val_res:0.564202 +2025-04-18 10:37:47,531 INFO Epoch:94 train_loss:0.39121 +2025-04-18 10:37:54,449 INFO Epoch:94 val_res:0.573281 +2025-04-18 10:38:29,318 INFO Epoch:95 train_loss:0.43781 +2025-04-18 10:38:37,164 INFO Epoch:95 val_res:0.559663 +2025-04-18 10:39:13,963 INFO Epoch:96 train_loss:0.43641 +2025-04-18 10:39:21,555 INFO Epoch:96 val_res:0.573930 +2025-04-18 10:39:59,933 INFO Epoch:97 train_loss:0.41076 +2025-04-18 10:40:07,831 INFO Epoch:97 val_res:0.571984 +2025-04-18 10:40:45,153 INFO Epoch:98 train_loss:0.40754 +2025-04-18 10:40:52,720 INFO Epoch:98 val_res:0.557069 +2025-04-18 10:41:27,894 INFO Epoch:99 train_loss:0.37908 +2025-04-18 10:41:35,687 INFO Epoch:99 val_res:0.554475 +2025-04-18 10:41:36,723 INFO ===================================== +2025-04-18 10:41:36,724 INFO Start testing... +2025-04-18 10:41:36,725 INFO ===================================== +2025-04-18 10:41:53,240 INFO Incremental step 3 Testing res: 0.559223 +2025-04-18 10:41:53,243 INFO forgetting: 0.049195 +2025-04-18 10:41:53,251 INFO ***************New Step*************************** +2025-04-18 10:41:53,251 INFO Incremental step: 4 +2025-04-18 10:41:53,457 INFO actual size of exemplar set: 480 +2025-04-18 10:44:29,039 INFO Epoch:0 train_loss:2.50668 +2025-04-18 10:44:45,929 INFO Epoch:0 val_res:0.424242 +2025-04-18 10:44:45,935 INFO Saving best model at Epoch 0 +2025-04-18 10:45:24,582 INFO Epoch:1 train_loss:2.46402 +2025-04-18 10:45:33,216 INFO Epoch:1 val_res:0.431947 +2025-04-18 10:45:33,217 INFO Saving best model at Epoch 1 +2025-04-18 10:46:08,456 INFO Epoch:2 train_loss:2.81925 +2025-04-18 10:46:17,061 INFO Epoch:2 val_res:0.407807 +2025-04-18 10:46:51,174 INFO Epoch:3 train_loss:1.77503 +2025-04-18 10:46:59,695 INFO Epoch:3 val_res:0.442219 +2025-04-18 10:46:59,702 INFO Saving best model at Epoch 3 +2025-04-18 10:47:35,177 INFO Epoch:4 train_loss:1.36085 +2025-04-18 10:47:44,465 INFO Epoch:4 val_res:0.453005 +2025-04-18 10:47:44,466 INFO Saving best model at Epoch 4 +2025-04-18 10:48:19,422 INFO Epoch:5 train_loss:1.19531 +2025-04-18 10:48:28,955 INFO Epoch:5 val_res:0.447355 +2025-04-18 10:49:03,028 INFO Epoch:6 train_loss:1.17269 +2025-04-18 10:49:12,155 INFO Epoch:6 val_res:0.438624 +2025-04-18 10:49:47,681 INFO Epoch:7 train_loss:1.37304 +2025-04-18 10:49:55,642 INFO Epoch:7 val_res:0.420134 +2025-04-18 10:50:28,639 INFO Epoch:8 train_loss:1.44765 +2025-04-18 10:50:37,149 INFO Epoch:8 val_res:0.455059 +2025-04-18 10:50:37,150 INFO Saving best model at Epoch 8 +2025-04-18 10:51:14,369 INFO Epoch:9 train_loss:1.35754 +2025-04-18 10:51:22,889 INFO Epoch:9 val_res:0.451464 +2025-04-18 10:51:56,995 INFO Epoch:10 train_loss:1.23491 +2025-04-18 10:52:07,430 INFO Epoch:10 val_res:0.438110 +2025-04-18 10:52:43,295 INFO Epoch:11 train_loss:1.09762 +2025-04-18 10:52:52,739 INFO Epoch:11 val_res:0.456600 +2025-04-18 10:52:52,741 INFO Saving best model at Epoch 11 +2025-04-18 10:53:29,903 INFO Epoch:12 train_loss:1.03037 +2025-04-18 10:53:38,624 INFO Epoch:12 val_res:0.454545 +2025-04-18 10:54:14,325 INFO Epoch:13 train_loss:1.30094 +2025-04-18 10:54:23,347 INFO Epoch:13 val_res:0.451464 +2025-04-18 10:54:58,803 INFO Epoch:14 train_loss:1.04846 +2025-04-18 10:55:06,695 INFO Epoch:14 val_res:0.469440 +2025-04-18 10:55:06,702 INFO Saving best model at Epoch 14 +2025-04-18 10:55:46,427 INFO Epoch:15 train_loss:1.20273 +2025-04-18 10:55:55,074 INFO Epoch:15 val_res:0.462763 +2025-04-18 10:56:31,419 INFO Epoch:16 train_loss:1.18502 +2025-04-18 10:56:40,364 INFO Epoch:16 val_res:0.460195 +2025-04-18 10:57:17,696 INFO Epoch:17 train_loss:0.94809 +2025-04-18 10:57:26,791 INFO Epoch:17 val_res:0.467386 +2025-04-18 10:58:03,227 INFO Epoch:18 train_loss:0.80206 +2025-04-18 10:58:12,663 INFO Epoch:18 val_res:0.463790 +2025-04-18 10:58:51,083 INFO Epoch:19 train_loss:0.78098 +2025-04-18 10:59:00,214 INFO Epoch:19 val_res:0.459682 +2025-04-18 10:59:37,398 INFO Epoch:20 train_loss:0.86802 +2025-04-18 10:59:46,631 INFO Epoch:20 val_res:0.458654 +2025-04-18 11:00:24,002 INFO Epoch:21 train_loss:0.79494 +2025-04-18 11:00:33,874 INFO Epoch:21 val_res:0.466872 +2025-04-18 11:01:09,049 INFO Epoch:22 train_loss:0.76024 +2025-04-18 11:01:18,478 INFO Epoch:22 val_res:0.465845 +2025-04-18 11:01:55,950 INFO Epoch:23 train_loss:0.74351 +2025-04-18 11:02:05,054 INFO Epoch:23 val_res:0.460709 +2025-04-18 11:02:39,524 INFO Epoch:24 train_loss:0.80552 +2025-04-18 11:02:48,440 INFO Epoch:24 val_res:0.471495 +2025-04-18 11:02:48,447 INFO Saving best model at Epoch 24 +2025-04-18 11:03:30,087 INFO Epoch:25 train_loss:1.07658 +2025-04-18 11:03:39,413 INFO Epoch:25 val_res:0.441192 +2025-04-18 11:04:15,820 INFO Epoch:26 train_loss:1.15837 +2025-04-18 11:04:24,328 INFO Epoch:26 val_res:0.455573 +2025-04-18 11:05:00,413 INFO Epoch:27 train_loss:0.84614 +2025-04-18 11:05:09,079 INFO Epoch:27 val_res:0.471495 +2025-04-18 11:05:45,823 INFO Epoch:28 train_loss:0.73410 +2025-04-18 11:05:55,186 INFO Epoch:28 val_res:0.474576 +2025-04-18 11:05:55,192 INFO Saving best model at Epoch 28 +2025-04-18 11:06:32,803 INFO Epoch:29 train_loss:0.72939 +2025-04-18 11:06:42,838 INFO Epoch:29 val_res:0.471495 +2025-04-18 11:07:21,407 INFO Epoch:30 train_loss:0.68292 +2025-04-18 11:07:30,011 INFO Epoch:30 val_res:0.470467 +2025-04-18 11:08:05,879 INFO Epoch:31 train_loss:0.67884 +2025-04-18 11:08:14,717 INFO Epoch:31 val_res:0.469954 +2025-04-18 11:08:50,409 INFO Epoch:32 train_loss:0.67434 +2025-04-18 11:08:59,271 INFO Epoch:32 val_res:0.467899 +2025-04-18 11:09:36,633 INFO Epoch:33 train_loss:0.69726 +2025-04-18 11:09:44,853 INFO Epoch:33 val_res:0.465331 +2025-04-18 11:10:21,116 INFO Epoch:34 train_loss:0.69409 +2025-04-18 11:10:29,161 INFO Epoch:34 val_res:0.461736 +2025-04-18 11:11:06,990 INFO Epoch:35 train_loss:0.68210 +2025-04-18 11:11:16,151 INFO Epoch:35 val_res:0.475603 +2025-04-18 11:11:16,157 INFO Saving best model at Epoch 35 +2025-04-18 11:11:54,770 INFO Epoch:36 train_loss:0.67525 +2025-04-18 11:12:04,584 INFO Epoch:36 val_res:0.465845 +2025-04-18 11:12:42,222 INFO Epoch:37 train_loss:0.66799 +2025-04-18 11:12:51,704 INFO Epoch:37 val_res:0.471495 +2025-04-18 11:13:29,163 INFO Epoch:38 train_loss:0.66626 +2025-04-18 11:13:38,445 INFO Epoch:38 val_res:0.472008 +2025-04-18 11:14:13,756 INFO Epoch:39 train_loss:0.68608 +2025-04-18 11:14:22,552 INFO Epoch:39 val_res:0.485876 +2025-04-18 11:14:22,559 INFO Saving best model at Epoch 39 +2025-04-18 11:14:57,081 INFO Epoch:40 train_loss:0.68227 +2025-04-18 11:15:05,261 INFO Epoch:40 val_res:0.477658 +2025-04-18 11:15:40,397 INFO Epoch:41 train_loss:0.70208 +2025-04-18 11:15:48,995 INFO Epoch:41 val_res:0.477144 +2025-04-18 11:16:22,987 INFO Epoch:42 train_loss:0.67885 +2025-04-18 11:16:31,852 INFO Epoch:42 val_res:0.478172 +2025-04-18 11:17:08,056 INFO Epoch:43 train_loss:0.65137 +2025-04-18 11:17:23,057 INFO Epoch:43 val_res:0.481253 +2025-04-18 11:17:59,187 INFO Epoch:44 train_loss:0.63970 +2025-04-18 11:18:07,593 INFO Epoch:44 val_res:0.475603 +2025-04-18 11:18:44,049 INFO Epoch:45 train_loss:0.64140 +2025-04-18 11:18:54,066 INFO Epoch:45 val_res:0.472008 +2025-04-18 11:19:26,103 INFO Epoch:46 train_loss:0.64196 +2025-04-18 11:19:35,004 INFO Epoch:46 val_res:0.481253 +2025-04-18 11:20:12,978 INFO Epoch:47 train_loss:0.62547 +2025-04-18 11:20:23,021 INFO Epoch:47 val_res:0.478172 +2025-04-18 11:20:59,963 INFO Epoch:48 train_loss:0.64587 +2025-04-18 11:21:08,601 INFO Epoch:48 val_res:0.479712 +2025-04-18 11:21:48,690 INFO Epoch:49 train_loss:0.68383 +2025-04-18 11:21:58,388 INFO Epoch:49 val_res:0.472008 +2025-04-18 11:22:37,573 INFO Epoch:50 train_loss:0.65583 +2025-04-18 11:22:55,062 INFO Epoch:50 val_res:0.473035 +2025-04-18 11:23:32,505 INFO Epoch:51 train_loss:0.63091 +2025-04-18 11:23:42,396 INFO Epoch:51 val_res:0.477658 +2025-04-18 11:24:17,205 INFO Epoch:52 train_loss:0.59923 +2025-04-18 11:24:30,108 INFO Epoch:52 val_res:0.479199 +2025-04-18 11:25:08,745 INFO Epoch:53 train_loss:0.59629 +2025-04-18 11:25:17,516 INFO Epoch:53 val_res:0.479199 +2025-04-18 11:25:54,745 INFO Epoch:54 train_loss:0.58989 +2025-04-18 11:26:07,992 INFO Epoch:54 val_res:0.485362 +2025-04-18 11:26:45,587 INFO Epoch:55 train_loss:0.58887 +2025-04-18 11:26:55,150 INFO Epoch:55 val_res:0.477658 +2025-04-18 11:27:31,557 INFO Epoch:56 train_loss:0.61121 +2025-04-18 11:27:40,783 INFO Epoch:56 val_res:0.478685 +2025-04-18 11:28:18,038 INFO Epoch:57 train_loss:0.62188 +2025-04-18 11:28:27,922 INFO Epoch:57 val_res:0.491012 +2025-04-18 11:28:27,929 INFO Saving best model at Epoch 57 +2025-04-18 11:29:09,567 INFO Epoch:58 train_loss:0.63707 +2025-04-18 11:29:52,868 INFO Epoch:58 val_res:0.475090 +2025-04-18 11:30:28,281 INFO Epoch:59 train_loss:0.58936 +2025-04-18 11:30:39,036 INFO Epoch:59 val_res:0.485876 +2025-04-18 11:31:12,933 INFO Epoch:60 train_loss:0.58920 +2025-04-18 11:31:22,559 INFO Epoch:60 val_res:0.480226 +2025-04-18 11:31:59,065 INFO Epoch:61 train_loss:0.62452 +2025-04-18 11:32:09,070 INFO Epoch:61 val_res:0.478172 +2025-04-18 11:32:42,793 INFO Epoch:62 train_loss:0.62073 +2025-04-18 11:32:55,567 INFO Epoch:62 val_res:0.483308 +2025-04-18 11:33:30,581 INFO Epoch:63 train_loss:0.57965 +2025-04-18 11:33:40,352 INFO Epoch:63 val_res:0.477144 +2025-04-18 11:34:18,068 INFO Epoch:64 train_loss:0.57384 +2025-04-18 11:34:27,489 INFO Epoch:64 val_res:0.487930 +2025-04-18 11:35:03,866 INFO Epoch:65 train_loss:0.54976 +2025-04-18 11:35:12,376 INFO Epoch:65 val_res:0.484848 +2025-04-18 11:35:51,425 INFO Epoch:66 train_loss:0.56691 +2025-04-18 11:36:00,810 INFO Epoch:66 val_res:0.479199 +2025-04-18 11:36:41,102 INFO Epoch:67 train_loss:0.57298 +2025-04-18 11:36:49,985 INFO Epoch:67 val_res:0.484848 +2025-04-18 11:37:25,870 INFO Epoch:68 train_loss:0.61070 +2025-04-18 11:37:33,938 INFO Epoch:68 val_res:0.483308 +2025-04-18 11:38:08,704 INFO Epoch:69 train_loss:0.57847 +2025-04-18 11:38:16,899 INFO Epoch:69 val_res:0.488957 +2025-04-18 11:38:50,369 INFO Epoch:70 train_loss:0.61112 +2025-04-18 11:38:58,493 INFO Epoch:70 val_res:0.485362 +2025-04-18 11:39:33,661 INFO Epoch:71 train_loss:0.81338 +2025-04-18 11:39:41,599 INFO Epoch:71 val_res:0.476631 +2025-04-18 11:40:14,837 INFO Epoch:72 train_loss:0.76907 +2025-04-18 11:40:23,013 INFO Epoch:72 val_res:0.489471 +2025-04-18 11:40:56,570 INFO Epoch:73 train_loss:0.84412 +2025-04-18 11:41:05,653 INFO Epoch:73 val_res:0.473035 +2025-04-18 11:41:38,920 INFO Epoch:74 train_loss:0.95190 +2025-04-18 11:41:47,673 INFO Epoch:74 val_res:0.476117 +2025-04-18 11:42:21,415 INFO Epoch:75 train_loss:0.89278 +2025-04-18 11:42:30,285 INFO Epoch:75 val_res:0.480226 +2025-04-18 11:43:03,163 INFO Epoch:76 train_loss:0.69569 +2025-04-18 11:43:11,155 INFO Epoch:76 val_res:0.499230 +2025-04-18 11:43:11,163 INFO Saving best model at Epoch 76 +2025-04-18 11:43:45,225 INFO Epoch:77 train_loss:0.60674 +2025-04-18 11:43:53,209 INFO Epoch:77 val_res:0.495121 +2025-04-18 11:44:25,708 INFO Epoch:78 train_loss:0.57929 +2025-04-18 11:44:33,420 INFO Epoch:78 val_res:0.500770 +2025-04-18 11:44:33,432 INFO Saving best model at Epoch 78 +2025-04-18 11:45:07,211 INFO Epoch:79 train_loss:0.58624 +2025-04-18 11:45:14,776 INFO Epoch:79 val_res:0.489985 +2025-04-18 11:45:51,188 INFO Epoch:80 train_loss:0.53505 +2025-04-18 11:45:59,827 INFO Epoch:80 val_res:0.505393 +2025-04-18 11:45:59,834 INFO Saving best model at Epoch 80 +2025-04-18 11:46:37,755 INFO Epoch:81 train_loss:0.53370 +2025-04-18 11:46:47,127 INFO Epoch:81 val_res:0.496148 +2025-04-18 11:47:24,281 INFO Epoch:82 train_loss:0.51610 +2025-04-18 11:47:32,926 INFO Epoch:82 val_res:0.491012 +2025-04-18 11:48:07,582 INFO Epoch:83 train_loss:0.53244 +2025-04-18 11:48:17,151 INFO Epoch:83 val_res:0.483821 +2025-04-18 11:48:53,684 INFO Epoch:84 train_loss:0.53206 +2025-04-18 11:49:02,682 INFO Epoch:84 val_res:0.496148 +2025-04-18 11:49:36,271 INFO Epoch:85 train_loss:0.50370 +2025-04-18 11:49:45,231 INFO Epoch:85 val_res:0.502311 +2025-04-18 11:50:20,947 INFO Epoch:86 train_loss:0.54756 +2025-04-18 11:50:30,360 INFO Epoch:86 val_res:0.499230 +2025-04-18 11:51:06,059 INFO Epoch:87 train_loss:0.53069 +2025-04-18 11:51:14,981 INFO Epoch:87 val_res:0.499230 +2025-04-18 11:51:48,765 INFO Epoch:88 train_loss:0.55127 +2025-04-18 11:51:57,915 INFO Epoch:88 val_res:0.497175 +2025-04-18 11:52:34,648 INFO Epoch:89 train_loss:0.52779 +2025-04-18 11:52:43,044 INFO Epoch:89 val_res:0.489471 +2025-04-18 11:53:19,948 INFO Epoch:90 train_loss:0.50948 +2025-04-18 11:53:28,420 INFO Epoch:90 val_res:0.497689 +2025-04-18 11:54:05,321 INFO Epoch:91 train_loss:0.51462 +2025-04-18 11:54:13,668 INFO Epoch:91 val_res:0.487417 +2025-04-18 11:54:51,532 INFO Epoch:92 train_loss:0.51278 +2025-04-18 11:55:00,348 INFO Epoch:92 val_res:0.498202 +2025-04-18 11:55:35,807 INFO Epoch:93 train_loss:0.55387 +2025-04-18 11:55:44,877 INFO Epoch:93 val_res:0.500770 +2025-04-18 11:56:20,418 INFO Epoch:94 train_loss:0.53408 +2025-04-18 11:56:29,331 INFO Epoch:94 val_res:0.498716 +2025-04-18 11:57:05,230 INFO Epoch:95 train_loss:0.50154 +2025-04-18 11:57:14,008 INFO Epoch:95 val_res:0.502825 +2025-04-18 11:57:49,493 INFO Epoch:96 train_loss:0.51308 +2025-04-18 11:57:59,411 INFO Epoch:96 val_res:0.499743 +2025-04-18 11:58:33,314 INFO Epoch:97 train_loss:0.53322 +2025-04-18 11:58:43,650 INFO Epoch:97 val_res:0.493580 +2025-04-18 11:59:18,642 INFO Epoch:98 train_loss:0.51258 +2025-04-18 11:59:28,186 INFO Epoch:98 val_res:0.494093 +2025-04-18 12:00:04,359 INFO Epoch:99 train_loss:0.51560 +2025-04-18 12:00:13,275 INFO Epoch:99 val_res:0.499743 +2025-04-18 12:00:14,282 INFO ===================================== +2025-04-18 12:00:14,283 INFO Start testing... +2025-04-18 12:00:14,283 INFO ===================================== +2025-04-18 12:01:21,702 INFO Incremental step 4 Testing res: 0.480082 +2025-04-18 12:01:21,712 INFO forgetting: 0.087457 +2025-04-18 12:01:21,714 INFO Average Accuracy: 0.630496 +2025-04-18 12:01:21,714 INFO Average Forgetting: 0.049316 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..732e9f324e3d71883060289be37f0d7f0d44911d Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..e35c3ec4fe092bde010b11c4da5c25654b730c20 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..4647d8f5588dc8e73a2687f84ce57247f0aecfe6 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..27b27577a9080f7d507a124b0ec6ecf33afc0ba5 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..cd3fde48634327147f00e8c19a5b95ab056c93de Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_train_loss_step_4.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..8901e55c8ad85a230aae14d3e03dfd4b70e9ee83 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_0.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..dfc58523b384aff01e71cca20724d418966d1c36 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_1.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..04e80b9aacd3faad2a99e748322d513912069d76 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_2.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..650f50b7fc943ea17e2f7dbe3077115249acb650 Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_3.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..5ca79cd64a7e0484f977251080b85fc86641e6ec Binary files /dev/null and b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/fig/audio-visual_val_acc_step_4.png differ diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..586463fdf9c4077a5f5e94c444334dd4b685058d --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_0_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55661775d47097014d2cce4b3363340bee39355ace86842ad72426c901da75dd +size 114105937 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..674f6801671cacf5b5b7156b55c3d1321e9d5022 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_1_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836e0cac8ccd62dcb7313f2971935a2b872255566176fdc50f03d8ab690b4f3f +size 114161297 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..2336fc226b490399adcf6f8c4d0e7b2e77776d3a --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_2_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:890165fffe0241b1e0586c129ef905927f61fa7c808a7c839eadd5ba9253f05c +size 114216785 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..564804e565192d402f30c487074392c14ba7d282 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_3_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6762ffa964cda0e2b0e5b3d4058ce07e1b1ed573549e134b9abc727f0156c77 +size 114272081 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl new file mode 100644 index 0000000000000000000000000000000000000000..bc38c156075c9af5b77ee7f9d8cad569cb39a510 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/step_4_best_audio-visual_model.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe64348a1da58038f0894b5fe7cfdc3559836eab0c80410c27ee36bc80dc15a +size 114327377 diff --git a/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/train.log b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..3f4f34e6a6683685535fa566d1a6ae3fb301af80 --- /dev/null +++ b/Audio Visual Continual Learning/SSIL/save/ksounds/audio-visual/use-inverse_True-seed_0/train.log @@ -0,0 +1,1149 @@ +2025-04-18 06:26:03,124 INFO Namespace(class_num_per_step=6, dataset='ksounds', e_prompt=False, exemplar_batch_size=128, fixed_fc=False, infer_batch_size=128, inverse=True, inverse_ends=100, inverse_starts=0, lr=0.01, lr_decay=False, max_epoches=100, memory_size=500, milestones=[100], modality='audio-visual', num_classes=30, num_workers=4, prompt_dim=768, seed=0, train_batch_size=256, weight_decay=0.0001) +2025-04-18 06:26:03,126 INFO Training start time: 2025-04-18 06:26:03.126253 +2025-04-18 06:26:04,875 INFO ***************New Step*************************** +2025-04-18 06:26:04,875 INFO Incremental step: 0 +2025-04-18 06:28:27,599 INFO Epoch:0 train_loss:5.02258 +2025-04-18 06:28:30,509 INFO Epoch:0 val_res:0.458886 +2025-04-18 06:28:30,509 INFO Saving best model at Epoch 0 +2025-04-18 06:28:50,420 INFO Epoch:1 train_loss:4.33353 +2025-04-18 06:28:52,948 INFO Epoch:1 val_res:0.482759 +2025-04-18 06:28:52,948 INFO Saving best model at Epoch 1 +2025-04-18 06:29:08,940 INFO Epoch:2 train_loss:3.80189 +2025-04-18 06:29:11,369 INFO Epoch:2 val_res:0.644562 +2025-04-18 06:29:11,369 INFO Saving best model at Epoch 2 +2025-04-18 06:29:33,397 INFO Epoch:3 train_loss:3.34353 +2025-04-18 06:29:36,166 INFO Epoch:3 val_res:0.657825 +2025-04-18 06:29:36,167 INFO Saving best model at Epoch 3 +2025-04-18 06:29:57,159 INFO Epoch:4 train_loss:3.02479 +2025-04-18 06:29:59,831 INFO Epoch:4 val_res:0.734748 +2025-04-18 06:29:59,831 INFO Saving best model at Epoch 4 +2025-04-18 06:30:22,627 INFO Epoch:5 train_loss:2.74463 +2025-04-18 06:30:25,513 INFO Epoch:5 val_res:0.777188 +2025-04-18 06:30:25,513 INFO Saving best model at Epoch 5 +2025-04-18 06:30:41,367 INFO Epoch:6 train_loss:2.59444 +2025-04-18 06:30:43,758 INFO Epoch:6 val_res:0.798409 +2025-04-18 06:30:43,759 INFO Saving best model at Epoch 6 +2025-04-18 06:30:59,937 INFO Epoch:7 train_loss:2.41393 +2025-04-18 06:31:02,279 INFO Epoch:7 val_res:0.798409 +2025-04-18 06:31:16,138 INFO Epoch:8 train_loss:2.31799 +2025-04-18 06:31:18,564 INFO Epoch:8 val_res:0.798409 +2025-04-18 06:31:32,171 INFO Epoch:9 train_loss:2.27807 +2025-04-18 06:31:34,579 INFO Epoch:9 val_res:0.838196 +2025-04-18 06:31:34,579 INFO Saving best model at Epoch 9 +2025-04-18 06:31:49,842 INFO Epoch:10 train_loss:2.11887 +2025-04-18 06:31:52,249 INFO Epoch:10 val_res:0.856764 +2025-04-18 06:31:52,250 INFO Saving best model at Epoch 10 +2025-04-18 06:32:10,582 INFO Epoch:11 train_loss:1.99086 +2025-04-18 06:32:18,993 INFO Epoch:11 val_res:0.851459 +2025-04-18 06:32:36,574 INFO Epoch:12 train_loss:1.97089 +2025-04-18 06:32:39,381 INFO Epoch:12 val_res:0.835544 +2025-04-18 06:32:53,371 INFO Epoch:13 train_loss:1.89986 +2025-04-18 06:32:55,678 INFO Epoch:13 val_res:0.832891 +2025-04-18 06:33:08,863 INFO Epoch:14 train_loss:1.85421 +2025-04-18 06:33:11,350 INFO Epoch:14 val_res:0.862069 +2025-04-18 06:33:11,350 INFO Saving best model at Epoch 14 +2025-04-18 06:33:26,383 INFO Epoch:15 train_loss:1.81859 +2025-04-18 06:33:28,699 INFO Epoch:15 val_res:0.885942 +2025-04-18 06:33:28,699 INFO Saving best model at Epoch 15 +2025-04-18 06:33:44,272 INFO Epoch:16 train_loss:1.72604 +2025-04-18 06:33:46,794 INFO Epoch:16 val_res:0.793103 +2025-04-18 06:34:01,059 INFO Epoch:17 train_loss:1.77581 +2025-04-18 06:34:03,652 INFO Epoch:17 val_res:0.888594 +2025-04-18 06:34:03,653 INFO Saving best model at Epoch 17 +2025-04-18 06:34:19,588 INFO Epoch:18 train_loss:1.76941 +2025-04-18 06:34:22,107 INFO Epoch:18 val_res:0.893899 +2025-04-18 06:34:22,107 INFO Saving best model at Epoch 18 +2025-04-18 06:34:40,205 INFO Epoch:19 train_loss:1.69287 +2025-04-18 06:34:42,588 INFO Epoch:19 val_res:0.891247 +2025-04-18 06:34:57,311 INFO Epoch:20 train_loss:1.65879 +2025-04-18 06:34:59,827 INFO Epoch:20 val_res:0.888594 +2025-04-18 06:35:14,883 INFO Epoch:21 train_loss:1.68004 +2025-04-18 06:35:17,454 INFO Epoch:21 val_res:0.862069 +2025-04-18 06:35:32,280 INFO Epoch:22 train_loss:1.59439 +2025-04-18 06:35:34,769 INFO Epoch:22 val_res:0.912467 +2025-04-18 06:35:34,769 INFO Saving best model at Epoch 22 +2025-04-18 06:35:51,135 INFO Epoch:23 train_loss:1.53803 +2025-04-18 06:35:53,780 INFO Epoch:23 val_res:0.862069 +2025-04-18 06:36:09,431 INFO Epoch:24 train_loss:1.57634 +2025-04-18 06:36:11,953 INFO Epoch:24 val_res:0.893899 +2025-04-18 06:36:26,586 INFO Epoch:25 train_loss:1.57581 +2025-04-18 06:36:29,014 INFO Epoch:25 val_res:0.872679 +2025-04-18 06:36:43,837 INFO Epoch:26 train_loss:1.61244 +2025-04-18 06:36:46,244 INFO Epoch:26 val_res:0.867374 +2025-04-18 06:37:02,057 INFO Epoch:27 train_loss:1.58077 +2025-04-18 06:37:04,690 INFO Epoch:27 val_res:0.896552 +2025-04-18 06:37:19,656 INFO Epoch:28 train_loss:1.48160 +2025-04-18 06:37:22,226 INFO Epoch:28 val_res:0.920424 +2025-04-18 06:37:22,226 INFO Saving best model at Epoch 28 +2025-04-18 06:37:39,641 INFO Epoch:29 train_loss:1.46783 +2025-04-18 06:37:42,298 INFO Epoch:29 val_res:0.917772 +2025-04-18 06:37:57,365 INFO Epoch:30 train_loss:1.52086 +2025-04-18 06:37:59,871 INFO Epoch:30 val_res:0.901857 +2025-04-18 06:38:15,571 INFO Epoch:31 train_loss:1.53524 +2025-04-18 06:38:18,052 INFO Epoch:31 val_res:0.891247 +2025-04-18 06:38:32,797 INFO Epoch:32 train_loss:1.48146 +2025-04-18 06:38:35,579 INFO Epoch:32 val_res:0.893899 +2025-04-18 06:38:51,183 INFO Epoch:33 train_loss:1.44960 +2025-04-18 06:38:53,670 INFO Epoch:33 val_res:0.907162 +2025-04-18 06:39:08,963 INFO Epoch:34 train_loss:1.39090 +2025-04-18 06:39:11,522 INFO Epoch:34 val_res:0.901857 +2025-04-18 06:39:27,262 INFO Epoch:35 train_loss:1.50553 +2025-04-18 06:39:29,717 INFO Epoch:35 val_res:0.904509 +2025-04-18 06:39:44,139 INFO Epoch:36 train_loss:1.48877 +2025-04-18 06:39:46,703 INFO Epoch:36 val_res:0.891247 +2025-04-18 06:40:01,636 INFO Epoch:37 train_loss:1.44699 +2025-04-18 06:40:04,182 INFO Epoch:37 val_res:0.891247 +2025-04-18 06:40:18,259 INFO Epoch:38 train_loss:1.38603 +2025-04-18 06:40:20,805 INFO Epoch:38 val_res:0.896552 +2025-04-18 06:40:35,269 INFO Epoch:39 train_loss:1.43540 +2025-04-18 06:40:37,902 INFO Epoch:39 val_res:0.901857 +2025-04-18 06:40:51,924 INFO Epoch:40 train_loss:1.39841 +2025-04-18 06:40:54,255 INFO Epoch:40 val_res:0.925729 +2025-04-18 06:40:54,255 INFO Saving best model at Epoch 40 +2025-04-18 06:41:10,775 INFO Epoch:41 train_loss:1.41488 +2025-04-18 06:41:13,293 INFO Epoch:41 val_res:0.909814 +2025-04-18 06:41:27,439 INFO Epoch:42 train_loss:1.40223 +2025-04-18 06:41:29,972 INFO Epoch:42 val_res:0.907162 +2025-04-18 06:41:44,318 INFO Epoch:43 train_loss:1.37889 +2025-04-18 06:41:46,895 INFO Epoch:43 val_res:0.901857 +2025-04-18 06:42:00,842 INFO Epoch:44 train_loss:1.36736 +2025-04-18 06:42:03,445 INFO Epoch:44 val_res:0.904509 +2025-04-18 06:42:18,206 INFO Epoch:45 train_loss:1.32639 +2025-04-18 06:42:20,827 INFO Epoch:45 val_res:0.888594 +2025-04-18 06:42:34,896 INFO Epoch:46 train_loss:1.34647 +2025-04-18 06:42:37,537 INFO Epoch:46 val_res:0.907162 +2025-04-18 06:42:51,373 INFO Epoch:47 train_loss:1.32179 +2025-04-18 06:42:53,942 INFO Epoch:47 val_res:0.901857 +2025-04-18 06:43:08,378 INFO Epoch:48 train_loss:1.27824 +2025-04-18 06:43:10,798 INFO Epoch:48 val_res:0.920424 +2025-04-18 06:43:25,301 INFO Epoch:49 train_loss:1.28805 +2025-04-18 06:43:27,907 INFO Epoch:49 val_res:0.859416 +2025-04-18 06:43:41,941 INFO Epoch:50 train_loss:1.32093 +2025-04-18 06:43:44,516 INFO Epoch:50 val_res:0.904509 +2025-04-18 06:43:59,488 INFO Epoch:51 train_loss:1.24315 +2025-04-18 06:44:02,138 INFO Epoch:51 val_res:0.877984 +2025-04-18 06:44:16,438 INFO Epoch:52 train_loss:1.27458 +2025-04-18 06:44:18,770 INFO Epoch:52 val_res:0.923077 +2025-04-18 06:44:32,823 INFO Epoch:53 train_loss:1.30089 +2025-04-18 06:44:35,523 INFO Epoch:53 val_res:0.917772 +2025-04-18 06:44:49,291 INFO Epoch:54 train_loss:1.21562 +2025-04-18 06:44:51,575 INFO Epoch:54 val_res:0.923077 +2025-04-18 06:45:06,427 INFO Epoch:55 train_loss:1.24139 +2025-04-18 06:45:09,159 INFO Epoch:55 val_res:0.920424 +2025-04-18 06:45:23,231 INFO Epoch:56 train_loss:1.24108 +2025-04-18 06:45:25,655 INFO Epoch:56 val_res:0.891247 +2025-04-18 06:45:40,078 INFO Epoch:57 train_loss:1.20281 +2025-04-18 06:45:42,629 INFO Epoch:57 val_res:0.928382 +2025-04-18 06:45:42,630 INFO Saving best model at Epoch 57 +2025-04-18 06:45:57,934 INFO Epoch:58 train_loss:1.15713 +2025-04-18 06:46:00,303 INFO Epoch:58 val_res:0.936339 +2025-04-18 06:46:00,303 INFO Saving best model at Epoch 58 +2025-04-18 06:46:17,718 INFO Epoch:59 train_loss:1.17164 +2025-04-18 06:46:20,353 INFO Epoch:59 val_res:0.870027 +2025-04-18 06:46:33,893 INFO Epoch:60 train_loss:1.21613 +2025-04-18 06:46:36,337 INFO Epoch:60 val_res:0.917772 +2025-04-18 06:46:50,169 INFO Epoch:61 train_loss:1.19740 +2025-04-18 06:46:52,597 INFO Epoch:61 val_res:0.915119 +2025-04-18 06:47:07,496 INFO Epoch:62 train_loss:1.19675 +2025-04-18 06:47:10,234 INFO Epoch:62 val_res:0.883289 +2025-04-18 06:47:26,298 INFO Epoch:63 train_loss:1.15519 +2025-04-18 06:47:28,831 INFO Epoch:63 val_res:0.915119 +2025-04-18 06:47:44,921 INFO Epoch:64 train_loss:1.16206 +2025-04-18 06:47:47,967 INFO Epoch:64 val_res:0.928382 +2025-04-18 06:48:05,054 INFO Epoch:65 train_loss:1.15571 +2025-04-18 06:48:07,432 INFO Epoch:65 val_res:0.920424 +2025-04-18 06:48:21,644 INFO Epoch:66 train_loss:1.15391 +2025-04-18 06:48:24,173 INFO Epoch:66 val_res:0.896552 +2025-04-18 06:48:37,657 INFO Epoch:67 train_loss:1.16972 +2025-04-18 06:48:40,046 INFO Epoch:67 val_res:0.909814 +2025-04-18 06:48:53,505 INFO Epoch:68 train_loss:1.14851 +2025-04-18 06:48:55,900 INFO Epoch:68 val_res:0.920424 +2025-04-18 06:49:09,794 INFO Epoch:69 train_loss:1.15129 +2025-04-18 06:49:12,151 INFO Epoch:69 val_res:0.915119 +2025-04-18 06:49:25,667 INFO Epoch:70 train_loss:1.18546 +2025-04-18 06:49:28,086 INFO Epoch:70 val_res:0.904509 +2025-04-18 06:49:41,211 INFO Epoch:71 train_loss:1.14700 +2025-04-18 06:49:43,531 INFO Epoch:71 val_res:0.936339 +2025-04-18 06:49:56,587 INFO Epoch:72 train_loss:1.11511 +2025-04-18 06:49:59,086 INFO Epoch:72 val_res:0.909814 +2025-04-18 06:50:12,329 INFO Epoch:73 train_loss:1.13772 +2025-04-18 06:50:14,738 INFO Epoch:73 val_res:0.920424 +2025-04-18 06:50:27,403 INFO Epoch:74 train_loss:1.17029 +2025-04-18 06:50:29,703 INFO Epoch:74 val_res:0.925729 +2025-04-18 06:50:42,329 INFO Epoch:75 train_loss:1.06031 +2025-04-18 06:50:44,776 INFO Epoch:75 val_res:0.925729 +2025-04-18 06:50:57,527 INFO Epoch:76 train_loss:1.09343 +2025-04-18 06:51:00,023 INFO Epoch:76 val_res:0.923077 +2025-04-18 06:51:12,566 INFO Epoch:77 train_loss:1.14783 +2025-04-18 06:51:14,973 INFO Epoch:77 val_res:0.917772 +2025-04-18 06:51:28,077 INFO Epoch:78 train_loss:1.08606 +2025-04-18 06:51:30,439 INFO Epoch:78 val_res:0.923077 +2025-04-18 06:51:42,897 INFO Epoch:79 train_loss:1.04683 +2025-04-18 06:51:45,353 INFO Epoch:79 val_res:0.936339 +2025-04-18 06:51:58,319 INFO Epoch:80 train_loss:1.04500 +2025-04-18 06:52:00,610 INFO Epoch:80 val_res:0.938992 +2025-04-18 06:52:00,610 INFO Saving best model at Epoch 80 +2025-04-18 06:52:17,492 INFO Epoch:81 train_loss:1.12369 +2025-04-18 06:52:19,888 INFO Epoch:81 val_res:0.870027 +2025-04-18 06:52:33,748 INFO Epoch:82 train_loss:1.22020 +2025-04-18 06:52:36,205 INFO Epoch:82 val_res:0.856764 +2025-04-18 06:52:50,162 INFO Epoch:83 train_loss:1.13490 +2025-04-18 06:52:52,558 INFO Epoch:83 val_res:0.904509 +2025-04-18 06:53:09,640 INFO Epoch:84 train_loss:1.10272 +2025-04-18 06:53:12,135 INFO Epoch:84 val_res:0.917772 +2025-04-18 06:53:26,760 INFO Epoch:85 train_loss:1.13858 +2025-04-18 06:53:29,257 INFO Epoch:85 val_res:0.917772 +2025-04-18 06:53:52,460 INFO Epoch:86 train_loss:1.05898 +2025-04-18 06:53:54,963 INFO Epoch:86 val_res:0.915119 +2025-04-18 06:54:15,423 INFO Epoch:87 train_loss:1.04149 +2025-04-18 06:54:18,078 INFO Epoch:87 val_res:0.917772 +2025-04-18 06:54:33,100 INFO Epoch:88 train_loss:1.07066 +2025-04-18 06:54:35,488 INFO Epoch:88 val_res:0.925729 +2025-04-18 06:54:50,501 INFO Epoch:89 train_loss:1.05228 +2025-04-18 06:54:53,162 INFO Epoch:89 val_res:0.880637 +2025-04-18 06:55:09,168 INFO Epoch:90 train_loss:1.14692 +2025-04-18 06:55:11,758 INFO Epoch:90 val_res:0.891247 +2025-04-18 06:55:27,452 INFO Epoch:91 train_loss:1.15520 +2025-04-18 06:55:30,025 INFO Epoch:91 val_res:0.909814 +2025-04-18 06:55:47,013 INFO Epoch:92 train_loss:1.07946 +2025-04-18 06:55:49,588 INFO Epoch:92 val_res:0.917772 +2025-04-18 06:56:04,967 INFO Epoch:93 train_loss:1.05366 +2025-04-18 06:56:07,639 INFO Epoch:93 val_res:0.920424 +2025-04-18 06:56:25,365 INFO Epoch:94 train_loss:1.02265 +2025-04-18 06:56:28,135 INFO Epoch:94 val_res:0.928382 +2025-04-18 06:56:43,957 INFO Epoch:95 train_loss:1.02216 +2025-04-18 06:56:46,977 INFO Epoch:95 val_res:0.912467 +2025-04-18 06:57:03,169 INFO Epoch:96 train_loss:1.02484 +2025-04-18 06:57:05,915 INFO Epoch:96 val_res:0.925729 +2025-04-18 06:57:22,589 INFO Epoch:97 train_loss:1.04404 +2025-04-18 06:57:25,102 INFO Epoch:97 val_res:0.909814 +2025-04-18 06:57:41,370 INFO Epoch:98 train_loss:1.00680 +2025-04-18 06:57:44,351 INFO Epoch:98 val_res:0.909814 +2025-04-18 06:57:59,899 INFO Epoch:99 train_loss:1.03177 +2025-04-18 06:58:02,554 INFO Epoch:99 val_res:0.917772 +2025-04-18 06:58:03,434 INFO ===================================== +2025-04-18 06:58:03,435 INFO Start testing... +2025-04-18 06:58:03,435 INFO ===================================== +2025-04-18 06:58:10,356 INFO Incremental step 0 Testing res: 0.919355 +2025-04-18 06:58:10,360 INFO ***************New Step*************************** +2025-04-18 06:58:10,360 INFO Incremental step: 1 +2025-04-18 06:58:10,535 INFO actual size of exemplar set: 498 +2025-04-18 07:01:09,859 INFO Epoch:0 train_loss:3.77819 +2025-04-18 07:01:22,678 INFO Epoch:0 val_res:0.455844 +2025-04-18 07:01:22,679 INFO Saving best model at Epoch 0 +2025-04-18 07:02:20,951 INFO Epoch:1 train_loss:3.88434 +2025-04-18 07:02:33,570 INFO Epoch:1 val_res:0.437662 +2025-04-18 07:05:20,256 INFO Epoch:2 train_loss:3.28095 +2025-04-18 07:05:29,233 INFO Epoch:2 val_res:0.437662 +2025-04-18 07:07:12,130 INFO Epoch:3 train_loss:2.84904 +2025-04-18 07:07:16,422 INFO Epoch:3 val_res:0.455844 +2025-04-18 07:08:31,182 INFO Epoch:4 train_loss:2.76243 +2025-04-18 07:08:35,727 INFO Epoch:4 val_res:0.454545 +2025-04-18 07:10:35,591 INFO Epoch:5 train_loss:2.56981 +2025-04-18 07:10:41,047 INFO Epoch:5 val_res:0.466234 +2025-04-18 07:10:41,048 INFO Saving best model at Epoch 5 +2025-04-18 07:11:56,615 INFO Epoch:6 train_loss:2.73344 +2025-04-18 07:12:01,003 INFO Epoch:6 val_res:0.450649 +2025-04-18 07:13:30,370 INFO Epoch:7 train_loss:2.74989 +2025-04-18 07:13:34,646 INFO Epoch:7 val_res:0.466234 +2025-04-18 07:15:08,390 INFO Epoch:8 train_loss:2.48403 +2025-04-18 07:15:13,106 INFO Epoch:8 val_res:0.462338 +2025-04-18 07:16:19,509 INFO Epoch:9 train_loss:2.39233 +2025-04-18 07:16:24,011 INFO Epoch:9 val_res:0.463636 +2025-04-18 07:17:17,843 INFO Epoch:10 train_loss:2.49349 +2025-04-18 07:17:22,423 INFO Epoch:10 val_res:0.448052 +2025-04-18 07:18:28,392 INFO Epoch:11 train_loss:2.48901 +2025-04-18 07:18:32,425 INFO Epoch:11 val_res:0.479221 +2025-04-18 07:18:32,426 INFO Saving best model at Epoch 11 +2025-04-18 07:19:41,504 INFO Epoch:12 train_loss:2.35634 +2025-04-18 07:19:46,112 INFO Epoch:12 val_res:0.476623 +2025-04-18 07:20:40,517 INFO Epoch:13 train_loss:2.47191 +2025-04-18 07:20:45,141 INFO Epoch:13 val_res:0.464935 +2025-04-18 07:21:31,117 INFO Epoch:14 train_loss:2.25768 +2025-04-18 07:21:35,087 INFO Epoch:14 val_res:0.479221 +2025-04-18 07:22:16,164 INFO Epoch:15 train_loss:2.57665 +2025-04-18 07:22:20,311 INFO Epoch:15 val_res:0.471429 +2025-04-18 07:23:10,441 INFO Epoch:16 train_loss:2.41255 +2025-04-18 07:23:14,234 INFO Epoch:16 val_res:0.505195 +2025-04-18 07:23:14,235 INFO Saving best model at Epoch 16 +2025-04-18 07:23:59,795 INFO Epoch:17 train_loss:2.15711 +2025-04-18 07:24:05,409 INFO Epoch:17 val_res:0.509091 +2025-04-18 07:24:05,410 INFO Saving best model at Epoch 17 +2025-04-18 07:24:49,223 INFO Epoch:18 train_loss:2.32187 +2025-04-18 07:24:53,535 INFO Epoch:18 val_res:0.506494 +2025-04-18 07:25:37,763 INFO Epoch:19 train_loss:2.20796 +2025-04-18 07:25:42,663 INFO Epoch:19 val_res:0.522078 +2025-04-18 07:25:42,663 INFO Saving best model at Epoch 19 +2025-04-18 07:26:28,715 INFO Epoch:20 train_loss:2.25032 +2025-04-18 07:26:33,571 INFO Epoch:20 val_res:0.522078 +2025-04-18 07:27:14,651 INFO Epoch:21 train_loss:2.13188 +2025-04-18 07:27:19,096 INFO Epoch:21 val_res:0.487013 +2025-04-18 07:27:58,206 INFO Epoch:22 train_loss:2.22720 +2025-04-18 07:28:03,369 INFO Epoch:22 val_res:0.496104 +2025-04-18 07:28:44,733 INFO Epoch:23 train_loss:2.24335 +2025-04-18 07:28:49,749 INFO Epoch:23 val_res:0.524675 +2025-04-18 07:28:49,749 INFO Saving best model at Epoch 23 +2025-04-18 07:29:30,739 INFO Epoch:24 train_loss:2.34430 +2025-04-18 07:29:35,453 INFO Epoch:24 val_res:0.484416 +2025-04-18 07:30:09,960 INFO Epoch:25 train_loss:2.23954 +2025-04-18 07:30:14,927 INFO Epoch:25 val_res:0.519481 +2025-04-18 07:30:51,813 INFO Epoch:26 train_loss:2.00458 +2025-04-18 07:30:58,790 INFO Epoch:26 val_res:0.500000 +2025-04-18 07:31:37,097 INFO Epoch:27 train_loss:2.16695 +2025-04-18 07:31:41,579 INFO Epoch:27 val_res:0.549351 +2025-04-18 07:31:41,579 INFO Saving best model at Epoch 27 +2025-04-18 07:32:23,228 INFO Epoch:28 train_loss:1.89858 +2025-04-18 07:32:27,908 INFO Epoch:28 val_res:0.557143 +2025-04-18 07:32:27,908 INFO Saving best model at Epoch 28 +2025-04-18 07:33:06,286 INFO Epoch:29 train_loss:1.83687 +2025-04-18 07:33:10,858 INFO Epoch:29 val_res:0.562338 +2025-04-18 07:33:10,858 INFO Saving best model at Epoch 29 +2025-04-18 07:33:51,451 INFO Epoch:30 train_loss:1.83916 +2025-04-18 07:33:55,556 INFO Epoch:30 val_res:0.531169 +2025-04-18 07:34:33,581 INFO Epoch:31 train_loss:1.81764 +2025-04-18 07:34:37,644 INFO Epoch:31 val_res:0.559740 +2025-04-18 07:35:12,288 INFO Epoch:32 train_loss:1.78796 +2025-04-18 07:35:15,763 INFO Epoch:32 val_res:0.580519 +2025-04-18 07:35:15,763 INFO Saving best model at Epoch 32 +2025-04-18 07:35:49,657 INFO Epoch:33 train_loss:1.87561 +2025-04-18 07:35:53,321 INFO Epoch:33 val_res:0.549351 +2025-04-18 07:36:24,388 INFO Epoch:34 train_loss:2.02995 +2025-04-18 07:36:27,675 INFO Epoch:34 val_res:0.522078 +2025-04-18 07:36:59,641 INFO Epoch:35 train_loss:1.98105 +2025-04-18 07:37:03,168 INFO Epoch:35 val_res:0.559740 +2025-04-18 07:37:33,954 INFO Epoch:36 train_loss:2.16102 +2025-04-18 07:37:37,449 INFO Epoch:36 val_res:0.562338 +2025-04-18 07:38:09,454 INFO Epoch:37 train_loss:2.23973 +2025-04-18 07:38:13,008 INFO Epoch:37 val_res:0.592208 +2025-04-18 07:38:13,008 INFO Saving best model at Epoch 37 +2025-04-18 07:38:46,528 INFO Epoch:38 train_loss:2.18330 +2025-04-18 07:38:50,004 INFO Epoch:38 val_res:0.598701 +2025-04-18 07:38:50,004 INFO Saving best model at Epoch 38 +2025-04-18 07:39:22,706 INFO Epoch:39 train_loss:2.07114 +2025-04-18 07:39:26,560 INFO Epoch:39 val_res:0.529870 +2025-04-18 07:39:58,338 INFO Epoch:40 train_loss:2.01174 +2025-04-18 07:40:02,536 INFO Epoch:40 val_res:0.553247 +2025-04-18 07:40:34,330 INFO Epoch:41 train_loss:1.89293 +2025-04-18 07:40:38,263 INFO Epoch:41 val_res:0.576623 +2025-04-18 07:41:11,854 INFO Epoch:42 train_loss:1.79080 +2025-04-18 07:41:15,718 INFO Epoch:42 val_res:0.554545 +2025-04-18 07:41:48,031 INFO Epoch:43 train_loss:1.75179 +2025-04-18 07:41:51,977 INFO Epoch:43 val_res:0.598701 +2025-04-18 07:42:24,034 INFO Epoch:44 train_loss:1.69305 +2025-04-18 07:42:28,368 INFO Epoch:44 val_res:0.598701 +2025-04-18 07:43:02,496 INFO Epoch:45 train_loss:1.80054 +2025-04-18 07:43:06,368 INFO Epoch:45 val_res:0.583117 +2025-04-18 07:43:38,922 INFO Epoch:46 train_loss:1.74441 +2025-04-18 07:43:42,969 INFO Epoch:46 val_res:0.574026 +2025-04-18 07:44:16,464 INFO Epoch:47 train_loss:1.74835 +2025-04-18 07:44:20,300 INFO Epoch:47 val_res:0.584416 +2025-04-18 07:44:54,200 INFO Epoch:48 train_loss:1.96233 +2025-04-18 07:44:58,341 INFO Epoch:48 val_res:0.572727 +2025-04-18 07:45:30,275 INFO Epoch:49 train_loss:1.77661 +2025-04-18 07:45:34,402 INFO Epoch:49 val_res:0.580519 +2025-04-18 07:46:10,253 INFO Epoch:50 train_loss:1.67358 +2025-04-18 07:46:14,210 INFO Epoch:50 val_res:0.600000 +2025-04-18 07:46:14,211 INFO Saving best model at Epoch 50 +2025-04-18 07:46:49,733 INFO Epoch:51 train_loss:1.67459 +2025-04-18 07:46:53,285 INFO Epoch:51 val_res:0.566234 +2025-04-18 07:47:27,978 INFO Epoch:52 train_loss:1.78209 +2025-04-18 07:47:31,946 INFO Epoch:52 val_res:0.623377 +2025-04-18 07:47:31,946 INFO Saving best model at Epoch 52 +2025-04-18 07:48:07,070 INFO Epoch:53 train_loss:1.71901 +2025-04-18 07:48:11,254 INFO Epoch:53 val_res:0.631169 +2025-04-18 07:48:11,254 INFO Saving best model at Epoch 53 +2025-04-18 07:48:45,330 INFO Epoch:54 train_loss:1.67225 +2025-04-18 07:48:49,604 INFO Epoch:54 val_res:0.625974 +2025-04-18 07:49:25,089 INFO Epoch:55 train_loss:1.67485 +2025-04-18 07:49:29,834 INFO Epoch:55 val_res:0.610390 +2025-04-18 07:50:05,095 INFO Epoch:56 train_loss:1.83223 +2025-04-18 07:50:09,196 INFO Epoch:56 val_res:0.568831 +2025-04-18 07:50:40,325 INFO Epoch:57 train_loss:1.85476 +2025-04-18 07:50:44,735 INFO Epoch:57 val_res:0.574026 +2025-04-18 07:51:19,531 INFO Epoch:58 train_loss:1.74609 +2025-04-18 07:51:23,565 INFO Epoch:58 val_res:0.615584 +2025-04-18 07:51:56,794 INFO Epoch:59 train_loss:1.63420 +2025-04-18 07:52:00,484 INFO Epoch:59 val_res:0.627273 +2025-04-18 07:52:33,769 INFO Epoch:60 train_loss:1.60494 +2025-04-18 07:52:38,068 INFO Epoch:60 val_res:0.609091 +2025-04-18 07:53:11,408 INFO Epoch:61 train_loss:1.60009 +2025-04-18 07:53:15,312 INFO Epoch:61 val_res:0.640260 +2025-04-18 07:53:15,313 INFO Saving best model at Epoch 61 +2025-04-18 07:53:48,753 INFO Epoch:62 train_loss:1.58942 +2025-04-18 07:53:52,872 INFO Epoch:62 val_res:0.645455 +2025-04-18 07:53:52,873 INFO Saving best model at Epoch 62 +2025-04-18 07:54:25,081 INFO Epoch:63 train_loss:1.59683 +2025-04-18 07:54:28,946 INFO Epoch:63 val_res:0.622078 +2025-04-18 07:55:00,407 INFO Epoch:64 train_loss:1.53928 +2025-04-18 07:55:04,551 INFO Epoch:64 val_res:0.644156 +2025-04-18 07:55:36,356 INFO Epoch:65 train_loss:1.51888 +2025-04-18 07:55:40,652 INFO Epoch:65 val_res:0.612987 +2025-04-18 07:56:12,189 INFO Epoch:66 train_loss:1.50766 +2025-04-18 07:56:15,985 INFO Epoch:66 val_res:0.616883 +2025-04-18 07:56:45,646 INFO Epoch:67 train_loss:1.52250 +2025-04-18 07:56:49,374 INFO Epoch:67 val_res:0.618182 +2025-04-18 07:57:21,243 INFO Epoch:68 train_loss:1.50590 +2025-04-18 07:57:25,131 INFO Epoch:68 val_res:0.642857 +2025-04-18 07:57:55,305 INFO Epoch:69 train_loss:1.51927 +2025-04-18 07:57:58,894 INFO Epoch:69 val_res:0.644156 +2025-04-18 07:58:29,951 INFO Epoch:70 train_loss:1.56109 +2025-04-18 07:58:33,661 INFO Epoch:70 val_res:0.628571 +2025-04-18 07:59:04,636 INFO Epoch:71 train_loss:1.60607 +2025-04-18 07:59:08,282 INFO Epoch:71 val_res:0.642857 +2025-04-18 07:59:38,277 INFO Epoch:72 train_loss:1.54608 +2025-04-18 07:59:42,230 INFO Epoch:72 val_res:0.594805 +2025-04-18 08:00:12,925 INFO Epoch:73 train_loss:1.50164 +2025-04-18 08:00:16,583 INFO Epoch:73 val_res:0.629870 +2025-04-18 08:00:47,041 INFO Epoch:74 train_loss:1.52182 +2025-04-18 08:00:50,994 INFO Epoch:74 val_res:0.605195 +2025-04-18 08:01:20,726 INFO Epoch:75 train_loss:1.48638 +2025-04-18 08:01:24,664 INFO Epoch:75 val_res:0.627273 +2025-04-18 08:01:56,430 INFO Epoch:76 train_loss:1.50761 +2025-04-18 08:02:01,037 INFO Epoch:76 val_res:0.648052 +2025-04-18 08:02:01,037 INFO Saving best model at Epoch 76 +2025-04-18 08:02:36,736 INFO Epoch:77 train_loss:1.46060 +2025-04-18 08:02:41,355 INFO Epoch:77 val_res:0.641558 +2025-04-18 08:03:11,581 INFO Epoch:78 train_loss:1.54661 +2025-04-18 08:03:15,633 INFO Epoch:78 val_res:0.641558 +2025-04-18 08:03:44,988 INFO Epoch:79 train_loss:1.53300 +2025-04-18 08:03:48,474 INFO Epoch:79 val_res:0.611688 +2025-04-18 08:04:18,514 INFO Epoch:80 train_loss:1.42392 +2025-04-18 08:04:22,166 INFO Epoch:80 val_res:0.628571 +2025-04-18 08:04:51,072 INFO Epoch:81 train_loss:1.38998 +2025-04-18 08:04:54,995 INFO Epoch:81 val_res:0.641558 +2025-04-18 08:05:26,099 INFO Epoch:82 train_loss:1.40881 +2025-04-18 08:05:30,008 INFO Epoch:82 val_res:0.635065 +2025-04-18 08:06:01,733 INFO Epoch:83 train_loss:1.52817 +2025-04-18 08:06:05,341 INFO Epoch:83 val_res:0.624675 +2025-04-18 08:06:34,834 INFO Epoch:84 train_loss:1.43237 +2025-04-18 08:06:38,689 INFO Epoch:84 val_res:0.633766 +2025-04-18 08:07:08,903 INFO Epoch:85 train_loss:1.44576 +2025-04-18 08:07:12,631 INFO Epoch:85 val_res:0.658442 +2025-04-18 08:07:12,631 INFO Saving best model at Epoch 85 +2025-04-18 08:07:44,216 INFO Epoch:86 train_loss:1.43362 +2025-04-18 08:07:47,971 INFO Epoch:86 val_res:0.640260 +2025-04-18 08:08:18,999 INFO Epoch:87 train_loss:1.54030 +2025-04-18 08:08:23,040 INFO Epoch:87 val_res:0.636364 +2025-04-18 08:08:52,829 INFO Epoch:88 train_loss:1.42333 +2025-04-18 08:08:56,711 INFO Epoch:88 val_res:0.663636 +2025-04-18 08:08:56,711 INFO Saving best model at Epoch 88 +2025-04-18 08:09:28,402 INFO Epoch:89 train_loss:1.39060 +2025-04-18 08:09:31,990 INFO Epoch:89 val_res:0.646753 +2025-04-18 08:10:02,514 INFO Epoch:90 train_loss:1.37484 +2025-04-18 08:10:06,061 INFO Epoch:90 val_res:0.645455 +2025-04-18 08:10:35,274 INFO Epoch:91 train_loss:1.43949 +2025-04-18 08:10:39,254 INFO Epoch:91 val_res:0.631169 +2025-04-18 08:11:10,278 INFO Epoch:92 train_loss:1.45462 +2025-04-18 08:11:14,071 INFO Epoch:92 val_res:0.645455 +2025-04-18 08:11:45,010 INFO Epoch:93 train_loss:1.44641 +2025-04-18 08:11:48,892 INFO Epoch:93 val_res:0.659740 +2025-04-18 08:12:19,001 INFO Epoch:94 train_loss:1.41000 +2025-04-18 08:12:23,219 INFO Epoch:94 val_res:0.655844 +2025-04-18 08:12:52,848 INFO Epoch:95 train_loss:1.40318 +2025-04-18 08:12:56,643 INFO Epoch:95 val_res:0.666234 +2025-04-18 08:12:56,644 INFO Saving best model at Epoch 95 +2025-04-18 08:13:29,616 INFO Epoch:96 train_loss:1.42651 +2025-04-18 08:13:34,324 INFO Epoch:96 val_res:0.668831 +2025-04-18 08:13:34,325 INFO Saving best model at Epoch 96 +2025-04-18 08:14:08,536 INFO Epoch:97 train_loss:1.47640 +2025-04-18 08:14:12,399 INFO Epoch:97 val_res:0.671429 +2025-04-18 08:14:12,400 INFO Saving best model at Epoch 97 +2025-04-18 08:14:46,140 INFO Epoch:98 train_loss:1.34580 +2025-04-18 08:14:50,099 INFO Epoch:98 val_res:0.650649 +2025-04-18 08:15:23,596 INFO Epoch:99 train_loss:1.35363 +2025-04-18 08:15:27,088 INFO Epoch:99 val_res:0.631169 +2025-04-18 08:15:28,101 INFO ===================================== +2025-04-18 08:15:28,102 INFO Start testing... +2025-04-18 08:15:28,103 INFO ===================================== +2025-04-18 08:15:33,348 INFO Incremental step 1 Testing res: 0.635065 +2025-04-18 08:15:33,349 INFO forgetting: 0.115591 +2025-04-18 08:15:33,352 INFO ***************New Step*************************** +2025-04-18 08:15:33,352 INFO Incremental step: 2 +2025-04-18 08:15:33,781 INFO actual size of exemplar set: 492 +2025-04-18 08:17:23,584 INFO Epoch:0 train_loss:4.43817 +2025-04-18 08:17:42,456 INFO Epoch:0 val_res:0.434028 +2025-04-18 08:17:42,457 INFO Saving best model at Epoch 0 +2025-04-18 08:18:18,502 INFO Epoch:1 train_loss:4.35888 +2025-04-18 08:18:25,178 INFO Epoch:1 val_res:0.464410 +2025-04-18 08:18:25,178 INFO Saving best model at Epoch 1 +2025-04-18 08:19:08,117 INFO Epoch:2 train_loss:4.01742 +2025-04-18 08:19:14,381 INFO Epoch:2 val_res:0.469618 +2025-04-18 08:19:14,382 INFO Saving best model at Epoch 2 +2025-04-18 08:19:59,163 INFO Epoch:3 train_loss:3.75858 +2025-04-18 08:20:07,010 INFO Epoch:3 val_res:0.474826 +2025-04-18 08:20:07,012 INFO Saving best model at Epoch 3 +2025-04-18 08:20:52,155 INFO Epoch:4 train_loss:3.63801 +2025-04-18 08:20:58,592 INFO Epoch:4 val_res:0.492188 +2025-04-18 08:20:58,592 INFO Saving best model at Epoch 4 +2025-04-18 08:21:42,475 INFO Epoch:5 train_loss:3.33982 +2025-04-18 08:21:50,760 INFO Epoch:5 val_res:0.500868 +2025-04-18 08:21:50,761 INFO Saving best model at Epoch 5 +2025-04-18 08:22:35,277 INFO Epoch:6 train_loss:3.35505 +2025-04-18 08:22:42,109 INFO Epoch:6 val_res:0.471354 +2025-04-18 08:23:20,790 INFO Epoch:7 train_loss:3.31413 +2025-04-18 08:23:27,748 INFO Epoch:7 val_res:0.484375 +2025-04-18 08:24:07,881 INFO Epoch:8 train_loss:3.34977 +2025-04-18 08:24:14,366 INFO Epoch:8 val_res:0.476562 +2025-04-18 08:24:53,539 INFO Epoch:9 train_loss:3.21623 +2025-04-18 08:24:59,930 INFO Epoch:9 val_res:0.487847 +2025-04-18 08:25:37,284 INFO Epoch:10 train_loss:3.29011 +2025-04-18 08:25:43,607 INFO Epoch:10 val_res:0.480035 +2025-04-18 08:26:19,021 INFO Epoch:11 train_loss:3.25738 +2025-04-18 08:26:25,335 INFO Epoch:11 val_res:0.496528 +2025-04-18 08:27:03,854 INFO Epoch:12 train_loss:3.15834 +2025-04-18 08:27:10,584 INFO Epoch:12 val_res:0.513889 +2025-04-18 08:27:10,584 INFO Saving best model at Epoch 12 +2025-04-18 08:27:48,519 INFO Epoch:13 train_loss:3.11863 +2025-04-18 08:27:53,780 INFO Epoch:13 val_res:0.510417 +2025-04-18 08:28:29,793 INFO Epoch:14 train_loss:3.00511 +2025-04-18 08:28:35,746 INFO Epoch:14 val_res:0.493924 +2025-04-18 08:29:11,466 INFO Epoch:15 train_loss:3.03227 +2025-04-18 08:29:17,162 INFO Epoch:15 val_res:0.512153 +2025-04-18 08:29:52,102 INFO Epoch:16 train_loss:2.95963 +2025-04-18 08:29:57,964 INFO Epoch:16 val_res:0.509549 +2025-04-18 08:30:34,247 INFO Epoch:17 train_loss:2.83692 +2025-04-18 08:30:40,252 INFO Epoch:17 val_res:0.507812 +2025-04-18 08:31:13,289 INFO Epoch:18 train_loss:2.83646 +2025-04-18 08:31:19,755 INFO Epoch:18 val_res:0.512153 +2025-04-18 08:31:55,460 INFO Epoch:19 train_loss:2.86522 +2025-04-18 08:32:01,518 INFO Epoch:19 val_res:0.533854 +2025-04-18 08:32:01,519 INFO Saving best model at Epoch 19 +2025-04-18 08:32:42,372 INFO Epoch:20 train_loss:2.88309 +2025-04-18 08:32:49,863 INFO Epoch:20 val_res:0.508681 +2025-04-18 08:33:29,144 INFO Epoch:21 train_loss:2.95929 +2025-04-18 08:33:36,679 INFO Epoch:21 val_res:0.507812 +2025-04-18 08:34:22,468 INFO Epoch:22 train_loss:2.92330 +2025-04-18 08:34:29,788 INFO Epoch:22 val_res:0.531250 +2025-04-18 08:35:11,287 INFO Epoch:23 train_loss:2.98278 +2025-04-18 08:35:17,172 INFO Epoch:23 val_res:0.521701 +2025-04-18 08:35:51,697 INFO Epoch:24 train_loss:3.02867 +2025-04-18 08:35:57,361 INFO Epoch:24 val_res:0.519965 +2025-04-18 08:36:29,794 INFO Epoch:25 train_loss:2.89302 +2025-04-18 08:36:34,831 INFO Epoch:25 val_res:0.509549 +2025-04-18 08:37:07,145 INFO Epoch:26 train_loss:2.85299 +2025-04-18 08:37:12,227 INFO Epoch:26 val_res:0.517361 +2025-04-18 08:37:44,771 INFO Epoch:27 train_loss:2.81365 +2025-04-18 08:37:50,060 INFO Epoch:27 val_res:0.533854 +2025-04-18 08:38:24,049 INFO Epoch:28 train_loss:2.72783 +2025-04-18 08:38:29,711 INFO Epoch:28 val_res:0.530382 +2025-04-18 08:39:04,698 INFO Epoch:29 train_loss:2.70701 +2025-04-18 08:39:10,338 INFO Epoch:29 val_res:0.529514 +2025-04-18 08:39:44,388 INFO Epoch:30 train_loss:2.61125 +2025-04-18 08:39:50,197 INFO Epoch:30 val_res:0.542535 +2025-04-18 08:39:50,197 INFO Saving best model at Epoch 30 +2025-04-18 08:40:26,873 INFO Epoch:31 train_loss:2.51876 +2025-04-18 08:40:32,553 INFO Epoch:31 val_res:0.529514 +2025-04-18 08:41:07,703 INFO Epoch:32 train_loss:2.70830 +2025-04-18 08:41:12,911 INFO Epoch:32 val_res:0.531250 +2025-04-18 08:41:44,998 INFO Epoch:33 train_loss:2.90241 +2025-04-18 08:41:51,096 INFO Epoch:33 val_res:0.534722 +2025-04-18 08:42:26,880 INFO Epoch:34 train_loss:2.81269 +2025-04-18 08:42:32,933 INFO Epoch:34 val_res:0.549479 +2025-04-18 08:42:32,933 INFO Saving best model at Epoch 34 +2025-04-18 08:43:10,937 INFO Epoch:35 train_loss:2.78906 +2025-04-18 08:43:16,431 INFO Epoch:35 val_res:0.535590 +2025-04-18 08:43:51,596 INFO Epoch:36 train_loss:2.77937 +2025-04-18 08:43:57,593 INFO Epoch:36 val_res:0.536458 +2025-04-18 08:44:32,182 INFO Epoch:37 train_loss:2.55851 +2025-04-18 08:44:37,465 INFO Epoch:37 val_res:0.538194 +2025-04-18 08:45:09,028 INFO Epoch:38 train_loss:2.64766 +2025-04-18 08:45:14,745 INFO Epoch:38 val_res:0.557292 +2025-04-18 08:45:14,746 INFO Saving best model at Epoch 38 +2025-04-18 08:45:48,549 INFO Epoch:39 train_loss:2.59509 +2025-04-18 08:45:53,724 INFO Epoch:39 val_res:0.555556 +2025-04-18 08:46:25,658 INFO Epoch:40 train_loss:2.49570 +2025-04-18 08:46:30,755 INFO Epoch:40 val_res:0.539931 +2025-04-18 08:47:05,135 INFO Epoch:41 train_loss:2.43482 +2025-04-18 08:47:11,298 INFO Epoch:41 val_res:0.546875 +2025-04-18 08:47:48,167 INFO Epoch:42 train_loss:2.29940 +2025-04-18 08:47:54,134 INFO Epoch:42 val_res:0.543403 +2025-04-18 08:48:29,342 INFO Epoch:43 train_loss:2.32188 +2025-04-18 08:48:35,113 INFO Epoch:43 val_res:0.553819 +2025-04-18 08:49:11,115 INFO Epoch:44 train_loss:2.38422 +2025-04-18 08:49:16,410 INFO Epoch:44 val_res:0.541667 +2025-04-18 08:49:49,665 INFO Epoch:45 train_loss:2.48343 +2025-04-18 08:49:55,178 INFO Epoch:45 val_res:0.555556 +2025-04-18 08:50:30,692 INFO Epoch:46 train_loss:2.50387 +2025-04-18 08:50:36,731 INFO Epoch:46 val_res:0.550347 +2025-04-18 08:51:12,869 INFO Epoch:47 train_loss:2.32179 +2025-04-18 08:51:18,404 INFO Epoch:47 val_res:0.558160 +2025-04-18 08:51:18,404 INFO Saving best model at Epoch 47 +2025-04-18 08:51:55,029 INFO Epoch:48 train_loss:2.25617 +2025-04-18 08:52:00,693 INFO Epoch:48 val_res:0.552083 +2025-04-18 08:52:34,411 INFO Epoch:49 train_loss:2.32120 +2025-04-18 08:52:39,640 INFO Epoch:49 val_res:0.559028 +2025-04-18 08:52:39,640 INFO Saving best model at Epoch 49 +2025-04-18 08:53:15,106 INFO Epoch:50 train_loss:2.33361 +2025-04-18 08:53:20,147 INFO Epoch:50 val_res:0.546875 +2025-04-18 08:53:52,819 INFO Epoch:51 train_loss:2.49788 +2025-04-18 08:53:57,759 INFO Epoch:51 val_res:0.551215 +2025-04-18 08:54:30,504 INFO Epoch:52 train_loss:2.49607 +2025-04-18 08:54:35,402 INFO Epoch:52 val_res:0.561632 +2025-04-18 08:54:35,402 INFO Saving best model at Epoch 52 +2025-04-18 08:55:11,507 INFO Epoch:53 train_loss:2.45353 +2025-04-18 08:55:17,263 INFO Epoch:53 val_res:0.557292 +2025-04-18 08:55:53,413 INFO Epoch:54 train_loss:2.34880 +2025-04-18 08:55:59,769 INFO Epoch:54 val_res:0.566840 +2025-04-18 08:55:59,770 INFO Saving best model at Epoch 54 +2025-04-18 08:56:37,499 INFO Epoch:55 train_loss:2.15768 +2025-04-18 08:56:43,212 INFO Epoch:55 val_res:0.559028 +2025-04-18 08:57:19,125 INFO Epoch:56 train_loss:2.21181 +2025-04-18 08:57:24,111 INFO Epoch:56 val_res:0.565972 +2025-04-18 08:57:58,346 INFO Epoch:57 train_loss:2.21980 +2025-04-18 08:58:03,914 INFO Epoch:57 val_res:0.558160 +2025-04-18 08:58:40,838 INFO Epoch:58 train_loss:2.26327 +2025-04-18 08:58:46,676 INFO Epoch:58 val_res:0.559896 +2025-04-18 08:59:22,199 INFO Epoch:59 train_loss:2.30994 +2025-04-18 08:59:27,958 INFO Epoch:59 val_res:0.573785 +2025-04-18 08:59:27,958 INFO Saving best model at Epoch 59 +2025-04-18 09:00:04,387 INFO Epoch:60 train_loss:2.28922 +2025-04-18 09:00:09,689 INFO Epoch:60 val_res:0.564236 +2025-04-18 09:00:44,795 INFO Epoch:61 train_loss:2.22574 +2025-04-18 09:00:49,703 INFO Epoch:61 val_res:0.556424 +2025-04-18 09:01:22,726 INFO Epoch:62 train_loss:2.25754 +2025-04-18 09:01:27,800 INFO Epoch:62 val_res:0.564236 +2025-04-18 09:01:59,167 INFO Epoch:63 train_loss:2.30891 +2025-04-18 09:02:04,541 INFO Epoch:63 val_res:0.539062 +2025-04-18 09:02:36,242 INFO Epoch:64 train_loss:2.32985 +2025-04-18 09:02:41,910 INFO Epoch:64 val_res:0.572049 +2025-04-18 09:03:15,366 INFO Epoch:65 train_loss:2.23196 +2025-04-18 09:03:21,221 INFO Epoch:65 val_res:0.575521 +2025-04-18 09:03:21,221 INFO Saving best model at Epoch 65 +2025-04-18 09:04:00,565 INFO Epoch:66 train_loss:2.32655 +2025-04-18 09:04:06,155 INFO Epoch:66 val_res:0.554688 +2025-04-18 09:04:43,404 INFO Epoch:67 train_loss:2.28100 +2025-04-18 09:04:49,013 INFO Epoch:67 val_res:0.562500 +2025-04-18 09:05:23,831 INFO Epoch:68 train_loss:2.28046 +2025-04-18 09:05:28,880 INFO Epoch:68 val_res:0.576389 +2025-04-18 09:05:28,880 INFO Saving best model at Epoch 68 +2025-04-18 09:06:03,662 INFO Epoch:69 train_loss:2.04296 +2025-04-18 09:06:09,565 INFO Epoch:69 val_res:0.574653 +2025-04-18 09:06:45,597 INFO Epoch:70 train_loss:2.05600 +2025-04-18 09:06:51,484 INFO Epoch:70 val_res:0.578993 +2025-04-18 09:06:51,485 INFO Saving best model at Epoch 70 +2025-04-18 09:07:28,379 INFO Epoch:71 train_loss:2.11460 +2025-04-18 09:07:33,963 INFO Epoch:71 val_res:0.584201 +2025-04-18 09:07:33,963 INFO Saving best model at Epoch 71 +2025-04-18 09:08:11,464 INFO Epoch:72 train_loss:2.25978 +2025-04-18 09:08:17,544 INFO Epoch:72 val_res:0.587674 +2025-04-18 09:08:17,544 INFO Saving best model at Epoch 72 +2025-04-18 09:08:52,530 INFO Epoch:73 train_loss:2.21667 +2025-04-18 09:08:57,784 INFO Epoch:73 val_res:0.582465 +2025-04-18 09:09:29,715 INFO Epoch:74 train_loss:2.10296 +2025-04-18 09:09:35,014 INFO Epoch:74 val_res:0.590278 +2025-04-18 09:09:35,014 INFO Saving best model at Epoch 74 +2025-04-18 09:10:09,280 INFO Epoch:75 train_loss:2.12325 +2025-04-18 09:10:14,302 INFO Epoch:75 val_res:0.565104 +2025-04-18 09:10:46,502 INFO Epoch:76 train_loss:2.31056 +2025-04-18 09:10:52,325 INFO Epoch:76 val_res:0.561632 +2025-04-18 09:11:27,689 INFO Epoch:77 train_loss:2.23344 +2025-04-18 09:11:34,110 INFO Epoch:77 val_res:0.581597 +2025-04-18 09:12:11,347 INFO Epoch:78 train_loss:2.18001 +2025-04-18 09:12:17,076 INFO Epoch:78 val_res:0.569444 +2025-04-18 09:12:53,119 INFO Epoch:79 train_loss:1.99057 +2025-04-18 09:12:59,192 INFO Epoch:79 val_res:0.577257 +2025-04-18 09:13:31,165 INFO Epoch:80 train_loss:1.98742 +2025-04-18 09:13:36,797 INFO Epoch:80 val_res:0.571181 +2025-04-18 09:14:12,446 INFO Epoch:81 train_loss:2.33093 +2025-04-18 09:14:18,698 INFO Epoch:81 val_res:0.553819 +2025-04-18 09:14:53,266 INFO Epoch:82 train_loss:2.13742 +2025-04-18 09:14:58,967 INFO Epoch:82 val_res:0.584201 +2025-04-18 09:15:33,854 INFO Epoch:83 train_loss:2.22621 +2025-04-18 09:15:39,483 INFO Epoch:83 val_res:0.603299 +2025-04-18 09:15:39,483 INFO Saving best model at Epoch 83 +2025-04-18 09:16:13,871 INFO Epoch:84 train_loss:2.13400 +2025-04-18 09:16:19,461 INFO Epoch:84 val_res:0.578993 +2025-04-18 09:16:49,890 INFO Epoch:85 train_loss:2.12646 +2025-04-18 09:16:55,315 INFO Epoch:85 val_res:0.585938 +2025-04-18 09:17:26,110 INFO Epoch:86 train_loss:1.99597 +2025-04-18 09:17:31,171 INFO Epoch:86 val_res:0.575521 +2025-04-18 09:18:05,736 INFO Epoch:87 train_loss:1.99182 +2025-04-18 09:18:11,036 INFO Epoch:87 val_res:0.572917 +2025-04-18 09:18:44,890 INFO Epoch:88 train_loss:2.01408 +2025-04-18 09:18:50,577 INFO Epoch:88 val_res:0.581597 +2025-04-18 09:19:24,571 INFO Epoch:89 train_loss:2.09891 +2025-04-18 09:19:30,024 INFO Epoch:89 val_res:0.553819 +2025-04-18 09:20:04,320 INFO Epoch:90 train_loss:2.04089 +2025-04-18 09:20:08,961 INFO Epoch:90 val_res:0.565104 +2025-04-18 09:20:46,189 INFO Epoch:91 train_loss:2.11184 +2025-04-18 09:20:51,865 INFO Epoch:91 val_res:0.578125 +2025-04-18 09:21:28,917 INFO Epoch:92 train_loss:2.03090 +2025-04-18 09:21:34,587 INFO Epoch:92 val_res:0.592882 +2025-04-18 09:22:11,545 INFO Epoch:93 train_loss:2.06087 +2025-04-18 09:22:17,255 INFO Epoch:93 val_res:0.577257 +2025-04-18 09:22:51,588 INFO Epoch:94 train_loss:2.06224 +2025-04-18 09:22:57,385 INFO Epoch:94 val_res:0.586806 +2025-04-18 09:23:32,218 INFO Epoch:95 train_loss:1.91035 +2025-04-18 09:23:37,489 INFO Epoch:95 val_res:0.593750 +2025-04-18 09:24:10,890 INFO Epoch:96 train_loss:2.00289 +2025-04-18 09:24:15,802 INFO Epoch:96 val_res:0.589410 +2025-04-18 09:24:49,084 INFO Epoch:97 train_loss:2.03392 +2025-04-18 09:24:54,703 INFO Epoch:97 val_res:0.564236 +2025-04-18 09:25:29,733 INFO Epoch:98 train_loss:2.08503 +2025-04-18 09:25:35,365 INFO Epoch:98 val_res:0.584201 +2025-04-18 09:26:10,362 INFO Epoch:99 train_loss:2.10135 +2025-04-18 09:26:16,199 INFO Epoch:99 val_res:0.582465 +2025-04-18 09:26:17,113 INFO ===================================== +2025-04-18 09:26:17,114 INFO Start testing... +2025-04-18 09:26:17,115 INFO ===================================== +2025-04-18 09:26:51,932 INFO Incremental step 2 Testing res: 0.597054 +2025-04-18 09:26:51,934 INFO forgetting: -0.002972 +2025-04-18 09:26:51,937 INFO ***************New Step*************************** +2025-04-18 09:26:51,937 INFO Incremental step: 3 +2025-04-18 09:26:52,249 INFO actual size of exemplar set: 486 +2025-04-18 09:30:17,149 INFO Epoch:0 train_loss:4.66729 +2025-04-18 09:30:40,605 INFO Epoch:0 val_res:0.440337 +2025-04-18 09:30:40,610 INFO Saving best model at Epoch 0 +2025-04-18 09:31:21,831 INFO Epoch:1 train_loss:3.98251 +2025-04-18 09:31:28,292 INFO Epoch:1 val_res:0.453956 +2025-04-18 09:31:28,300 INFO Saving best model at Epoch 1 +2025-04-18 09:32:11,350 INFO Epoch:2 train_loss:3.71941 +2025-04-18 09:32:17,777 INFO Epoch:2 val_res:0.440337 +2025-04-18 09:32:52,576 INFO Epoch:3 train_loss:4.02004 +2025-04-18 09:32:59,078 INFO Epoch:3 val_res:0.435798 +2025-04-18 09:33:34,508 INFO Epoch:4 train_loss:3.76652 +2025-04-18 09:33:41,339 INFO Epoch:4 val_res:0.459792 +2025-04-18 09:33:41,346 INFO Saving best model at Epoch 4 +2025-04-18 09:34:22,579 INFO Epoch:5 train_loss:3.59864 +2025-04-18 09:34:29,754 INFO Epoch:5 val_res:0.444877 +2025-04-18 09:35:09,333 INFO Epoch:6 train_loss:3.40882 +2025-04-18 09:35:16,375 INFO Epoch:6 val_res:0.463035 +2025-04-18 09:35:16,379 INFO Saving best model at Epoch 6 +2025-04-18 09:36:00,667 INFO Epoch:7 train_loss:3.29792 +2025-04-18 09:36:08,364 INFO Epoch:7 val_res:0.454604 +2025-04-18 09:36:49,901 INFO Epoch:8 train_loss:3.21319 +2025-04-18 09:36:56,984 INFO Epoch:8 val_res:0.461738 +2025-04-18 09:37:36,295 INFO Epoch:9 train_loss:3.11569 +2025-04-18 09:37:43,059 INFO Epoch:9 val_res:0.468223 +2025-04-18 09:37:43,060 INFO Saving best model at Epoch 9 +2025-04-18 09:38:24,225 INFO Epoch:10 train_loss:3.19740 +2025-04-18 09:38:30,764 INFO Epoch:10 val_res:0.479896 +2025-04-18 09:38:30,765 INFO Saving best model at Epoch 10 +2025-04-18 09:39:10,391 INFO Epoch:11 train_loss:2.79645 +2025-04-18 09:39:16,704 INFO Epoch:11 val_res:0.473411 +2025-04-18 09:39:51,861 INFO Epoch:12 train_loss:2.87058 +2025-04-18 09:39:58,289 INFO Epoch:12 val_res:0.483139 +2025-04-18 09:39:58,296 INFO Saving best model at Epoch 12 +2025-04-18 09:40:39,698 INFO Epoch:13 train_loss:2.95180 +2025-04-18 09:40:46,635 INFO Epoch:13 val_res:0.470817 +2025-04-18 09:41:27,081 INFO Epoch:14 train_loss:3.09595 +2025-04-18 09:41:33,890 INFO Epoch:14 val_res:0.468872 +2025-04-18 09:42:13,620 INFO Epoch:15 train_loss:2.98181 +2025-04-18 09:42:21,003 INFO Epoch:15 val_res:0.505188 +2025-04-18 09:42:21,006 INFO Saving best model at Epoch 15 +2025-04-18 09:42:57,695 INFO Epoch:16 train_loss:2.87852 +2025-04-18 09:43:04,764 INFO Epoch:16 val_res:0.496757 +2025-04-18 09:43:44,770 INFO Epoch:17 train_loss:3.00748 +2025-04-18 09:43:51,749 INFO Epoch:17 val_res:0.503243 +2025-04-18 09:44:30,263 INFO Epoch:18 train_loss:2.97412 +2025-04-18 09:44:37,706 INFO Epoch:18 val_res:0.511025 +2025-04-18 09:44:37,713 INFO Saving best model at Epoch 18 +2025-04-18 09:45:18,291 INFO Epoch:19 train_loss:2.82353 +2025-04-18 09:45:25,154 INFO Epoch:19 val_res:0.512322 +2025-04-18 09:45:25,161 INFO Saving best model at Epoch 19 +2025-04-18 09:46:04,224 INFO Epoch:20 train_loss:2.76315 +2025-04-18 09:46:10,478 INFO Epoch:20 val_res:0.498703 +2025-04-18 09:46:47,040 INFO Epoch:21 train_loss:2.88516 +2025-04-18 09:46:53,076 INFO Epoch:21 val_res:0.509728 +2025-04-18 09:47:31,065 INFO Epoch:22 train_loss:2.83304 +2025-04-18 09:47:38,110 INFO Epoch:22 val_res:0.516213 +2025-04-18 09:47:38,117 INFO Saving best model at Epoch 22 +2025-04-18 09:48:19,981 INFO Epoch:23 train_loss:2.74975 +2025-04-18 09:48:27,224 INFO Epoch:23 val_res:0.506485 +2025-04-18 09:49:07,728 INFO Epoch:24 train_loss:2.74290 +2025-04-18 09:49:15,400 INFO Epoch:24 val_res:0.509079 +2025-04-18 09:49:51,870 INFO Epoch:25 train_loss:2.57665 +2025-04-18 09:49:58,507 INFO Epoch:25 val_res:0.525940 +2025-04-18 09:49:58,514 INFO Saving best model at Epoch 25 +2025-04-18 09:50:40,852 INFO Epoch:26 train_loss:2.66663 +2025-04-18 09:50:48,078 INFO Epoch:26 val_res:0.528534 +2025-04-18 09:50:48,085 INFO Saving best model at Epoch 26 +2025-04-18 09:51:29,514 INFO Epoch:27 train_loss:2.61519 +2025-04-18 09:51:36,544 INFO Epoch:27 val_res:0.518158 +2025-04-18 09:52:13,998 INFO Epoch:28 train_loss:2.71765 +2025-04-18 09:52:20,478 INFO Epoch:28 val_res:0.506485 +2025-04-18 09:52:56,618 INFO Epoch:29 train_loss:2.65323 +2025-04-18 09:53:03,325 INFO Epoch:29 val_res:0.525940 +2025-04-18 09:53:40,583 INFO Epoch:30 train_loss:2.62764 +2025-04-18 09:53:48,056 INFO Epoch:30 val_res:0.532425 +2025-04-18 09:53:48,060 INFO Saving best model at Epoch 30 +2025-04-18 09:54:27,136 INFO Epoch:31 train_loss:2.51099 +2025-04-18 09:54:34,397 INFO Epoch:31 val_res:0.533074 +2025-04-18 09:54:34,404 INFO Saving best model at Epoch 31 +2025-04-18 09:55:16,724 INFO Epoch:32 train_loss:2.42958 +2025-04-18 09:55:24,235 INFO Epoch:32 val_res:0.538262 +2025-04-18 09:55:24,242 INFO Saving best model at Epoch 32 +2025-04-18 09:56:06,099 INFO Epoch:33 train_loss:2.38590 +2025-04-18 09:56:13,085 INFO Epoch:33 val_res:0.538262 +2025-04-18 09:56:54,288 INFO Epoch:34 train_loss:2.62808 +2025-04-18 09:57:01,262 INFO Epoch:34 val_res:0.533074 +2025-04-18 09:57:38,965 INFO Epoch:35 train_loss:2.57692 +2025-04-18 09:57:45,821 INFO Epoch:35 val_res:0.528534 +2025-04-18 09:58:23,739 INFO Epoch:36 train_loss:2.39737 +2025-04-18 09:58:30,783 INFO Epoch:36 val_res:0.523346 +2025-04-18 09:59:06,762 INFO Epoch:37 train_loss:2.47191 +2025-04-18 09:59:12,631 INFO Epoch:37 val_res:0.542802 +2025-04-18 09:59:12,638 INFO Saving best model at Epoch 37 +2025-04-18 09:59:50,529 INFO Epoch:38 train_loss:2.37941 +2025-04-18 09:59:56,597 INFO Epoch:38 val_res:0.542153 +2025-04-18 10:00:33,406 INFO Epoch:39 train_loss:2.31758 +2025-04-18 10:00:40,820 INFO Epoch:39 val_res:0.540208 +2025-04-18 10:01:20,171 INFO Epoch:40 train_loss:2.28677 +2025-04-18 10:01:27,201 INFO Epoch:40 val_res:0.526589 +2025-04-18 10:02:06,160 INFO Epoch:41 train_loss:2.56915 +2025-04-18 10:02:12,879 INFO Epoch:41 val_res:0.545396 +2025-04-18 10:02:12,879 INFO Saving best model at Epoch 41 +2025-04-18 10:02:53,439 INFO Epoch:42 train_loss:2.41368 +2025-04-18 10:03:00,094 INFO Epoch:42 val_res:0.551232 +2025-04-18 10:03:00,095 INFO Saving best model at Epoch 42 +2025-04-18 10:03:43,754 INFO Epoch:43 train_loss:2.27438 +2025-04-18 10:03:50,557 INFO Epoch:43 val_res:0.525292 +2025-04-18 10:04:28,673 INFO Epoch:44 train_loss:2.35162 +2025-04-18 10:04:35,229 INFO Epoch:44 val_res:0.550584 +2025-04-18 10:05:15,569 INFO Epoch:45 train_loss:2.27837 +2025-04-18 10:05:21,939 INFO Epoch:45 val_res:0.550584 +2025-04-18 10:05:57,589 INFO Epoch:46 train_loss:2.29678 +2025-04-18 10:06:03,916 INFO Epoch:46 val_res:0.536316 +2025-04-18 10:06:40,992 INFO Epoch:47 train_loss:2.46584 +2025-04-18 10:06:47,673 INFO Epoch:47 val_res:0.559663 +2025-04-18 10:06:47,674 INFO Saving best model at Epoch 47 +2025-04-18 10:07:28,878 INFO Epoch:48 train_loss:2.35135 +2025-04-18 10:07:36,509 INFO Epoch:48 val_res:0.551881 +2025-04-18 10:08:13,410 INFO Epoch:49 train_loss:2.37257 +2025-04-18 10:08:20,791 INFO Epoch:49 val_res:0.553826 +2025-04-18 10:08:59,252 INFO Epoch:50 train_loss:2.35828 +2025-04-18 10:09:05,292 INFO Epoch:50 val_res:0.549935 +2025-04-18 10:09:41,150 INFO Epoch:51 train_loss:2.25309 +2025-04-18 10:09:47,115 INFO Epoch:51 val_res:0.555772 +2025-04-18 10:10:22,548 INFO Epoch:52 train_loss:2.14055 +2025-04-18 10:10:28,311 INFO Epoch:52 val_res:0.577173 +2025-04-18 10:10:28,318 INFO Saving best model at Epoch 52 +2025-04-18 10:11:07,727 INFO Epoch:53 train_loss:2.18594 +2025-04-18 10:11:14,108 INFO Epoch:53 val_res:0.555772 +2025-04-18 10:11:49,354 INFO Epoch:54 train_loss:2.14429 +2025-04-18 10:11:55,880 INFO Epoch:54 val_res:0.549935 +2025-04-18 10:12:32,077 INFO Epoch:55 train_loss:2.32697 +2025-04-18 10:12:37,951 INFO Epoch:55 val_res:0.556420 +2025-04-18 10:13:14,750 INFO Epoch:56 train_loss:2.20726 +2025-04-18 10:13:20,902 INFO Epoch:56 val_res:0.525940 +2025-04-18 10:13:56,006 INFO Epoch:57 train_loss:2.59228 +2025-04-18 10:14:02,106 INFO Epoch:57 val_res:0.570039 +2025-04-18 10:14:37,609 INFO Epoch:58 train_loss:2.35760 +2025-04-18 10:14:43,862 INFO Epoch:58 val_res:0.546693 +2025-04-18 10:15:19,895 INFO Epoch:59 train_loss:2.34849 +2025-04-18 10:15:25,988 INFO Epoch:59 val_res:0.537614 +2025-04-18 10:16:01,718 INFO Epoch:60 train_loss:2.32673 +2025-04-18 10:16:08,154 INFO Epoch:60 val_res:0.560311 +2025-04-18 10:16:42,151 INFO Epoch:61 train_loss:2.34084 +2025-04-18 10:16:48,126 INFO Epoch:61 val_res:0.578470 +2025-04-18 10:16:48,126 INFO Saving best model at Epoch 61 +2025-04-18 10:17:26,009 INFO Epoch:62 train_loss:2.28313 +2025-04-18 10:17:32,954 INFO Epoch:62 val_res:0.571336 +2025-04-18 10:18:08,880 INFO Epoch:63 train_loss:2.24810 +2025-04-18 10:18:15,472 INFO Epoch:63 val_res:0.555123 +2025-04-18 10:18:50,504 INFO Epoch:64 train_loss:2.18359 +2025-04-18 10:18:57,123 INFO Epoch:64 val_res:0.567445 +2025-04-18 10:19:33,525 INFO Epoch:65 train_loss:2.08381 +2025-04-18 10:19:40,044 INFO Epoch:65 val_res:0.569390 +2025-04-18 10:20:14,421 INFO Epoch:66 train_loss:2.05986 +2025-04-18 10:20:20,896 INFO Epoch:66 val_res:0.556420 +2025-04-18 10:20:56,137 INFO Epoch:67 train_loss:2.08000 +2025-04-18 10:21:02,584 INFO Epoch:67 val_res:0.554475 +2025-04-18 10:21:37,472 INFO Epoch:68 train_loss:2.06427 +2025-04-18 10:21:43,635 INFO Epoch:68 val_res:0.577173 +2025-04-18 10:22:19,533 INFO Epoch:69 train_loss:2.15200 +2025-04-18 10:22:25,769 INFO Epoch:69 val_res:0.561608 +2025-04-18 10:23:03,337 INFO Epoch:70 train_loss:2.11591 +2025-04-18 10:23:09,334 INFO Epoch:70 val_res:0.569390 +2025-04-18 10:23:44,180 INFO Epoch:71 train_loss:2.05244 +2025-04-18 10:23:50,298 INFO Epoch:71 val_res:0.578470 +2025-04-18 10:24:24,979 INFO Epoch:72 train_loss:2.11603 +2025-04-18 10:24:30,838 INFO Epoch:72 val_res:0.556420 +2025-04-18 10:25:05,976 INFO Epoch:73 train_loss:2.11257 +2025-04-18 10:25:12,087 INFO Epoch:73 val_res:0.568742 +2025-04-18 10:25:46,064 INFO Epoch:74 train_loss:2.13120 +2025-04-18 10:25:51,836 INFO Epoch:74 val_res:0.563554 +2025-04-18 10:26:25,763 INFO Epoch:75 train_loss:2.17229 +2025-04-18 10:26:31,492 INFO Epoch:75 val_res:0.579767 +2025-04-18 10:26:31,499 INFO Saving best model at Epoch 75 +2025-04-18 10:27:08,086 INFO Epoch:76 train_loss:2.17899 +2025-04-18 10:27:13,842 INFO Epoch:76 val_res:0.553826 +2025-04-18 10:27:47,754 INFO Epoch:77 train_loss:2.04811 +2025-04-18 10:27:53,438 INFO Epoch:77 val_res:0.592088 +2025-04-18 10:27:53,444 INFO Saving best model at Epoch 77 +2025-04-18 10:28:30,569 INFO Epoch:78 train_loss:2.19318 +2025-04-18 10:28:36,368 INFO Epoch:78 val_res:0.561608 +2025-04-18 10:29:11,085 INFO Epoch:79 train_loss:2.31813 +2025-04-18 10:29:16,953 INFO Epoch:79 val_res:0.573930 +2025-04-18 10:29:51,784 INFO Epoch:80 train_loss:2.28885 +2025-04-18 10:29:57,975 INFO Epoch:80 val_res:0.581712 +2025-04-18 10:30:32,405 INFO Epoch:81 train_loss:2.23469 +2025-04-18 10:30:38,412 INFO Epoch:81 val_res:0.582361 +2025-04-18 10:31:13,768 INFO Epoch:82 train_loss:2.17862 +2025-04-18 10:31:19,926 INFO Epoch:82 val_res:0.581712 +2025-04-18 10:31:54,731 INFO Epoch:83 train_loss:2.00293 +2025-04-18 10:32:00,975 INFO Epoch:83 val_res:0.568093 +2025-04-18 10:32:36,484 INFO Epoch:84 train_loss:1.95270 +2025-04-18 10:32:43,054 INFO Epoch:84 val_res:0.580415 +2025-04-18 10:33:21,089 INFO Epoch:85 train_loss:2.00007 +2025-04-18 10:33:27,581 INFO Epoch:85 val_res:0.568742 +2025-04-18 10:34:04,864 INFO Epoch:86 train_loss:2.10301 +2025-04-18 10:34:11,700 INFO Epoch:86 val_res:0.575875 +2025-04-18 10:34:52,488 INFO Epoch:87 train_loss:2.00719 +2025-04-18 10:34:59,153 INFO Epoch:87 val_res:0.584306 +2025-04-18 10:35:40,574 INFO Epoch:88 train_loss:1.98429 +2025-04-18 10:35:47,526 INFO Epoch:88 val_res:0.571984 +2025-04-18 10:36:26,713 INFO Epoch:89 train_loss:2.07838 +2025-04-18 10:36:33,418 INFO Epoch:89 val_res:0.558366 +2025-04-18 10:37:10,242 INFO Epoch:90 train_loss:2.06945 +2025-04-18 10:37:16,176 INFO Epoch:90 val_res:0.562257 +2025-04-18 10:37:54,675 INFO Epoch:91 train_loss:2.08803 +2025-04-18 10:38:01,153 INFO Epoch:91 val_res:0.564851 +2025-04-18 10:38:42,275 INFO Epoch:92 train_loss:2.03284 +2025-04-18 10:38:49,976 INFO Epoch:92 val_res:0.560960 +2025-04-18 10:39:31,360 INFO Epoch:93 train_loss:1.95993 +2025-04-18 10:39:39,517 INFO Epoch:93 val_res:0.570687 +2025-04-18 10:40:20,738 INFO Epoch:94 train_loss:1.93279 +2025-04-18 10:40:27,778 INFO Epoch:94 val_res:0.576524 +2025-04-18 10:41:04,082 INFO Epoch:95 train_loss:1.96059 +2025-04-18 10:41:10,678 INFO Epoch:95 val_res:0.563554 +2025-04-18 10:41:49,190 INFO Epoch:96 train_loss:1.85781 +2025-04-18 10:41:55,437 INFO Epoch:96 val_res:0.582361 +2025-04-18 10:42:29,959 INFO Epoch:97 train_loss:1.88373 +2025-04-18 10:42:36,049 INFO Epoch:97 val_res:0.567445 +2025-04-18 10:43:11,288 INFO Epoch:98 train_loss:1.93080 +2025-04-18 10:43:17,702 INFO Epoch:98 val_res:0.571984 +2025-04-18 10:43:52,797 INFO Epoch:99 train_loss:1.81492 +2025-04-18 10:43:59,008 INFO Epoch:99 val_res:0.571336 +2025-04-18 10:44:00,166 INFO ===================================== +2025-04-18 10:44:00,167 INFO Start testing... +2025-04-18 10:44:00,168 INFO ===================================== +2025-04-18 10:44:07,937 INFO Incremental step 3 Testing res: 0.572168 +2025-04-18 10:44:07,940 INFO forgetting: 0.060912 +2025-04-18 10:44:07,948 INFO ***************New Step*************************** +2025-04-18 10:44:07,948 INFO Incremental step: 4 +2025-04-18 10:44:08,220 INFO actual size of exemplar set: 480 +2025-04-18 10:44:42,618 INFO Epoch:0 train_loss:4.93091 +2025-04-18 10:44:50,858 INFO Epoch:0 val_res:0.395994 +2025-04-18 10:44:50,864 INFO Saving best model at Epoch 0 +2025-04-18 10:45:29,461 INFO Epoch:1 train_loss:5.10520 +2025-04-18 10:45:36,828 INFO Epoch:1 val_res:0.446841 +2025-04-18 10:45:36,829 INFO Saving best model at Epoch 1 +2025-04-18 10:46:14,623 INFO Epoch:2 train_loss:4.53940 +2025-04-18 10:46:22,083 INFO Epoch:2 val_res:0.450950 +2025-04-18 10:46:22,089 INFO Saving best model at Epoch 2 +2025-04-18 10:47:00,795 INFO Epoch:3 train_loss:4.21599 +2025-04-18 10:47:08,596 INFO Epoch:3 val_res:0.449923 +2025-04-18 10:47:44,316 INFO Epoch:4 train_loss:3.93873 +2025-04-18 10:47:52,453 INFO Epoch:4 val_res:0.458141 +2025-04-18 10:47:52,456 INFO Saving best model at Epoch 4 +2025-04-18 10:48:31,183 INFO Epoch:5 train_loss:3.95126 +2025-04-18 10:48:38,864 INFO Epoch:5 val_res:0.466872 +2025-04-18 10:48:38,871 INFO Saving best model at Epoch 5 +2025-04-18 10:49:19,308 INFO Epoch:6 train_loss:3.75417 +2025-04-18 10:49:27,221 INFO Epoch:6 val_res:0.457114 +2025-04-18 10:50:03,362 INFO Epoch:7 train_loss:3.85358 +2025-04-18 10:50:11,097 INFO Epoch:7 val_res:0.467899 +2025-04-18 10:50:11,104 INFO Saving best model at Epoch 7 +2025-04-18 10:50:48,843 INFO Epoch:8 train_loss:3.97652 +2025-04-18 10:50:56,354 INFO Epoch:8 val_res:0.466359 +2025-04-18 10:51:34,580 INFO Epoch:9 train_loss:3.73797 +2025-04-18 10:51:44,136 INFO Epoch:9 val_res:0.470467 +2025-04-18 10:51:44,136 INFO Saving best model at Epoch 9 +2025-04-18 10:52:27,038 INFO Epoch:10 train_loss:3.57536 +2025-04-18 10:52:36,696 INFO Epoch:10 val_res:0.458141 +2025-04-18 10:53:13,866 INFO Epoch:11 train_loss:3.46507 +2025-04-18 10:53:22,660 INFO Epoch:11 val_res:0.461222 +2025-04-18 10:54:01,418 INFO Epoch:12 train_loss:3.38476 +2025-04-18 10:54:11,301 INFO Epoch:12 val_res:0.450950 +2025-04-18 10:54:48,923 INFO Epoch:13 train_loss:3.47183 +2025-04-18 10:54:56,875 INFO Epoch:13 val_res:0.463277 +2025-04-18 10:55:34,949 INFO Epoch:14 train_loss:3.52641 +2025-04-18 10:55:43,259 INFO Epoch:14 val_res:0.466359 +2025-04-18 10:56:19,069 INFO Epoch:15 train_loss:3.26393 +2025-04-18 10:56:27,444 INFO Epoch:15 val_res:0.475090 +2025-04-18 10:56:27,452 INFO Saving best model at Epoch 15 +2025-04-18 10:57:08,295 INFO Epoch:16 train_loss:3.26332 +2025-04-18 10:57:17,752 INFO Epoch:16 val_res:0.464818 +2025-04-18 10:57:59,416 INFO Epoch:17 train_loss:3.20077 +2025-04-18 10:58:08,881 INFO Epoch:17 val_res:0.469954 +2025-04-18 10:58:48,527 INFO Epoch:18 train_loss:3.06944 +2025-04-18 10:58:57,440 INFO Epoch:18 val_res:0.474576 +2025-04-18 10:59:38,767 INFO Epoch:19 train_loss:3.19437 +2025-04-18 10:59:49,028 INFO Epoch:19 val_res:0.468927 +2025-04-18 11:00:30,683 INFO Epoch:20 train_loss:3.16798 +2025-04-18 11:00:40,592 INFO Epoch:20 val_res:0.481253 +2025-04-18 11:00:40,593 INFO Saving best model at Epoch 20 +2025-04-18 11:01:21,335 INFO Epoch:21 train_loss:3.15270 +2025-04-18 11:01:30,310 INFO Epoch:21 val_res:0.468413 +2025-04-18 11:02:09,753 INFO Epoch:22 train_loss:3.23905 +2025-04-18 11:02:18,954 INFO Epoch:22 val_res:0.480740 +2025-04-18 11:02:56,912 INFO Epoch:23 train_loss:3.25929 +2025-04-18 11:03:04,885 INFO Epoch:23 val_res:0.463790 +2025-04-18 11:03:42,529 INFO Epoch:24 train_loss:3.43291 +2025-04-18 11:03:51,603 INFO Epoch:24 val_res:0.459168 +2025-04-18 11:04:30,258 INFO Epoch:25 train_loss:3.22877 +2025-04-18 11:04:38,791 INFO Epoch:25 val_res:0.466872 +2025-04-18 11:05:17,091 INFO Epoch:26 train_loss:3.31319 +2025-04-18 11:05:25,963 INFO Epoch:26 val_res:0.469440 +2025-04-18 11:06:03,688 INFO Epoch:27 train_loss:3.39323 +2025-04-18 11:06:13,069 INFO Epoch:27 val_res:0.487417 +2025-04-18 11:06:13,075 INFO Saving best model at Epoch 27 +2025-04-18 11:06:54,649 INFO Epoch:28 train_loss:3.24935 +2025-04-18 11:07:04,164 INFO Epoch:28 val_res:0.459682 +2025-04-18 11:07:44,616 INFO Epoch:29 train_loss:3.07134 +2025-04-18 11:07:53,276 INFO Epoch:29 val_res:0.493580 +2025-04-18 11:07:53,277 INFO Saving best model at Epoch 29 +2025-04-18 11:08:33,769 INFO Epoch:30 train_loss:2.90148 +2025-04-18 11:08:43,209 INFO Epoch:30 val_res:0.480740 +2025-04-18 11:09:20,764 INFO Epoch:31 train_loss:3.03871 +2025-04-18 11:09:31,052 INFO Epoch:31 val_res:0.474576 +2025-04-18 11:10:11,007 INFO Epoch:32 train_loss:2.91255 +2025-04-18 11:10:20,215 INFO Epoch:32 val_res:0.458654 +2025-04-18 11:10:59,397 INFO Epoch:33 train_loss:3.16323 +2025-04-18 11:11:08,693 INFO Epoch:33 val_res:0.481767 +2025-04-18 11:11:48,307 INFO Epoch:34 train_loss:2.96570 +2025-04-18 11:11:57,080 INFO Epoch:34 val_res:0.469954 +2025-04-18 11:12:41,856 INFO Epoch:35 train_loss:2.94055 +2025-04-18 11:12:51,628 INFO Epoch:35 val_res:0.480226 +2025-04-18 11:13:36,218 INFO Epoch:36 train_loss:2.99215 +2025-04-18 11:13:44,692 INFO Epoch:36 val_res:0.482794 +2025-04-18 11:14:22,587 INFO Epoch:37 train_loss:3.12074 +2025-04-18 11:14:30,549 INFO Epoch:37 val_res:0.479199 +2025-04-18 11:15:09,373 INFO Epoch:38 train_loss:2.93254 +2025-04-18 11:15:17,628 INFO Epoch:38 val_res:0.483821 +2025-04-18 11:15:57,899 INFO Epoch:39 train_loss:2.89506 +2025-04-18 11:16:21,599 INFO Epoch:39 val_res:0.485362 +2025-04-18 11:17:02,323 INFO Epoch:40 train_loss:2.84657 +2025-04-18 11:17:22,906 INFO Epoch:40 val_res:0.464304 +2025-04-18 11:18:02,763 INFO Epoch:41 train_loss:2.83765 +2025-04-18 11:18:12,558 INFO Epoch:41 val_res:0.482280 +2025-04-18 11:18:55,680 INFO Epoch:42 train_loss:2.84189 +2025-04-18 11:19:06,330 INFO Epoch:42 val_res:0.473035 +2025-04-18 11:19:50,638 INFO Epoch:43 train_loss:2.88340 +2025-04-18 11:20:00,487 INFO Epoch:43 val_res:0.480226 +2025-04-18 11:20:45,343 INFO Epoch:44 train_loss:2.83881 +2025-04-18 11:20:55,084 INFO Epoch:44 val_res:0.496148 +2025-04-18 11:20:55,091 INFO Saving best model at Epoch 44 +2025-04-18 11:21:39,448 INFO Epoch:45 train_loss:2.79760 +2025-04-18 11:21:50,808 INFO Epoch:45 val_res:0.472522 +2025-04-18 11:22:33,321 INFO Epoch:46 train_loss:2.71118 +2025-04-18 11:22:55,120 INFO Epoch:46 val_res:0.488444 +2025-04-18 11:23:39,418 INFO Epoch:47 train_loss:2.85510 +2025-04-18 11:23:49,324 INFO Epoch:47 val_res:0.475090 +2025-04-18 11:24:29,495 INFO Epoch:48 train_loss:2.93647 +2025-04-18 11:24:40,847 INFO Epoch:48 val_res:0.491012 +2025-04-18 11:25:27,002 INFO Epoch:49 train_loss:2.85569 +2025-04-18 11:25:38,451 INFO Epoch:49 val_res:0.487930 +2025-04-18 11:26:28,407 INFO Epoch:50 train_loss:2.72799 +2025-04-18 11:26:38,954 INFO Epoch:50 val_res:0.491012 +2025-04-18 11:27:19,761 INFO Epoch:51 train_loss:2.75615 +2025-04-18 11:27:28,821 INFO Epoch:51 val_res:0.484848 +2025-04-18 11:28:13,270 INFO Epoch:52 train_loss:2.76886 +2025-04-18 11:28:25,411 INFO Epoch:52 val_res:0.475090 +2025-04-18 11:29:11,018 INFO Epoch:53 train_loss:2.78325 +2025-04-18 11:29:52,819 INFO Epoch:53 val_res:0.485362 +2025-04-18 11:30:32,426 INFO Epoch:54 train_loss:2.66083 +2025-04-18 11:30:40,461 INFO Epoch:54 val_res:0.487417 +2025-04-18 11:31:21,839 INFO Epoch:55 train_loss:2.70896 +2025-04-18 11:31:31,005 INFO Epoch:55 val_res:0.484848 +2025-04-18 11:32:14,267 INFO Epoch:56 train_loss:2.76102 +2025-04-18 11:32:25,126 INFO Epoch:56 val_res:0.493580 +2025-04-18 11:33:04,086 INFO Epoch:57 train_loss:2.76479 +2025-04-18 11:33:14,293 INFO Epoch:57 val_res:0.485876 +2025-04-18 11:33:57,705 INFO Epoch:58 train_loss:2.67131 +2025-04-18 11:34:07,367 INFO Epoch:58 val_res:0.491012 +2025-04-18 11:34:46,881 INFO Epoch:59 train_loss:2.50246 +2025-04-18 11:34:55,993 INFO Epoch:59 val_res:0.498202 +2025-04-18 11:34:55,999 INFO Saving best model at Epoch 59 +2025-04-18 11:35:36,926 INFO Epoch:60 train_loss:2.65105 +2025-04-18 11:35:46,358 INFO Epoch:60 val_res:0.486903 +2025-04-18 11:36:23,721 INFO Epoch:61 train_loss:2.63904 +2025-04-18 11:36:32,927 INFO Epoch:61 val_res:0.505907 +2025-04-18 11:36:32,934 INFO Saving best model at Epoch 61 +2025-04-18 11:37:13,561 INFO Epoch:62 train_loss:2.53298 +2025-04-18 11:37:22,236 INFO Epoch:62 val_res:0.499743 +2025-04-18 11:37:58,111 INFO Epoch:63 train_loss:2.50259 +2025-04-18 11:38:06,772 INFO Epoch:63 val_res:0.492553 +2025-04-18 11:38:41,374 INFO Epoch:64 train_loss:2.65262 +2025-04-18 11:38:49,873 INFO Epoch:64 val_res:0.500257 +2025-04-18 11:39:24,822 INFO Epoch:65 train_loss:2.79558 +2025-04-18 11:39:32,982 INFO Epoch:65 val_res:0.481253 +2025-04-18 11:40:09,605 INFO Epoch:66 train_loss:2.79339 +2025-04-18 11:40:17,533 INFO Epoch:66 val_res:0.485876 +2025-04-18 11:40:55,242 INFO Epoch:67 train_loss:2.66996 +2025-04-18 11:41:03,692 INFO Epoch:67 val_res:0.493580 +2025-04-18 11:41:41,573 INFO Epoch:68 train_loss:2.82196 +2025-04-18 11:41:49,477 INFO Epoch:68 val_res:0.498202 +2025-04-18 11:42:26,239 INFO Epoch:69 train_loss:2.69994 +2025-04-18 11:42:34,865 INFO Epoch:69 val_res:0.480226 +2025-04-18 11:43:10,372 INFO Epoch:70 train_loss:2.66689 +2025-04-18 11:43:17,655 INFO Epoch:70 val_res:0.500770 +2025-04-18 11:43:52,278 INFO Epoch:71 train_loss:2.65622 +2025-04-18 11:43:59,901 INFO Epoch:71 val_res:0.500257 +2025-04-18 11:44:35,158 INFO Epoch:72 train_loss:2.59255 +2025-04-18 11:44:42,838 INFO Epoch:72 val_res:0.517720 +2025-04-18 11:44:42,844 INFO Saving best model at Epoch 72 +2025-04-18 11:45:19,739 INFO Epoch:73 train_loss:2.61386 +2025-04-18 11:45:28,088 INFO Epoch:73 val_res:0.502825 +2025-04-18 11:46:05,681 INFO Epoch:74 train_loss:2.78128 +2025-04-18 11:46:14,194 INFO Epoch:74 val_res:0.503852 +2025-04-18 11:46:51,722 INFO Epoch:75 train_loss:2.74576 +2025-04-18 11:47:00,991 INFO Epoch:75 val_res:0.491525 +2025-04-18 11:47:39,630 INFO Epoch:76 train_loss:2.69963 +2025-04-18 11:47:47,334 INFO Epoch:76 val_res:0.492039 +2025-04-18 11:48:24,942 INFO Epoch:77 train_loss:2.61297 +2025-04-18 11:48:33,441 INFO Epoch:77 val_res:0.502311 +2025-04-18 11:49:10,561 INFO Epoch:78 train_loss:2.56728 +2025-04-18 11:49:19,802 INFO Epoch:78 val_res:0.493580 +2025-04-18 11:49:57,203 INFO Epoch:79 train_loss:2.56010 +2025-04-18 11:50:05,741 INFO Epoch:79 val_res:0.506934 +2025-04-18 11:50:43,463 INFO Epoch:80 train_loss:2.49379 +2025-04-18 11:50:52,706 INFO Epoch:80 val_res:0.495121 +2025-04-18 11:51:28,752 INFO Epoch:81 train_loss:2.39647 +2025-04-18 11:51:37,698 INFO Epoch:81 val_res:0.505907 +2025-04-18 11:52:16,761 INFO Epoch:82 train_loss:2.35326 +2025-04-18 11:52:27,098 INFO Epoch:82 val_res:0.490498 +2025-04-18 11:53:03,940 INFO Epoch:83 train_loss:2.58305 +2025-04-18 11:53:12,978 INFO Epoch:83 val_res:0.502825 +2025-04-18 11:53:51,779 INFO Epoch:84 train_loss:2.67183 +2025-04-18 11:54:01,975 INFO Epoch:84 val_res:0.511043 +2025-04-18 11:54:39,705 INFO Epoch:85 train_loss:2.38819 +2025-04-18 11:54:49,439 INFO Epoch:85 val_res:0.510529 +2025-04-18 11:55:26,759 INFO Epoch:86 train_loss:2.46283 +2025-04-18 11:55:36,391 INFO Epoch:86 val_res:0.496662 +2025-04-18 11:56:14,216 INFO Epoch:87 train_loss:2.46319 +2025-04-18 11:56:23,386 INFO Epoch:87 val_res:0.506420 +2025-04-18 11:57:02,847 INFO Epoch:88 train_loss:2.43209 +2025-04-18 11:57:11,498 INFO Epoch:88 val_res:0.489471 +2025-04-18 11:57:50,661 INFO Epoch:89 train_loss:2.47084 +2025-04-18 11:57:59,686 INFO Epoch:89 val_res:0.519774 +2025-04-18 11:57:59,693 INFO Saving best model at Epoch 89 +2025-04-18 11:58:39,438 INFO Epoch:90 train_loss:2.64583 +2025-04-18 11:58:47,534 INFO Epoch:90 val_res:0.499743 +2025-04-18 11:59:25,689 INFO Epoch:91 train_loss:2.40748 +2025-04-18 11:59:34,070 INFO Epoch:91 val_res:0.488957 +2025-04-18 12:00:12,309 INFO Epoch:92 train_loss:2.50401 +2025-04-18 12:00:20,357 INFO Epoch:92 val_res:0.499230 +2025-04-18 12:00:54,344 INFO Epoch:93 train_loss:2.37609 +2025-04-18 12:01:01,801 INFO Epoch:93 val_res:0.509502 +2025-04-18 12:01:38,340 INFO Epoch:94 train_loss:2.35573 +2025-04-18 12:01:47,389 INFO Epoch:94 val_res:0.497175 +2025-04-18 12:02:25,017 INFO Epoch:95 train_loss:2.48145 +2025-04-18 12:02:34,702 INFO Epoch:95 val_res:0.503338 +2025-04-18 12:03:16,682 INFO Epoch:96 train_loss:2.33424 +2025-04-18 12:03:27,699 INFO Epoch:96 val_res:0.510015 +2025-04-18 12:04:05,510 INFO Epoch:97 train_loss:2.28245 +2025-04-18 12:04:13,961 INFO Epoch:97 val_res:0.507961 +2025-04-18 12:04:49,593 INFO Epoch:98 train_loss:2.34367 +2025-04-18 12:04:58,054 INFO Epoch:98 val_res:0.498716 +2025-04-18 12:05:33,857 INFO Epoch:99 train_loss:2.43481 +2025-04-18 12:05:42,773 INFO Epoch:99 val_res:0.526451 +2025-04-18 12:05:42,779 INFO Saving best model at Epoch 99 +2025-04-18 12:05:45,080 INFO ===================================== +2025-04-18 12:05:45,081 INFO Start testing... +2025-04-18 12:05:45,082 INFO ===================================== +2025-04-18 12:05:54,253 INFO Incremental step 4 Testing res: 0.499489 +2025-04-18 12:05:54,262 INFO forgetting: 0.110694 +2025-04-18 12:05:54,265 INFO Average Accuracy: 0.647193 +2025-04-18 12:05:54,266 INFO Average Forgetting: 0.071056 diff --git a/Audio Visual Continual Learning/readme.md b/Audio Visual Continual Learning/readme.md new file mode 100644 index 0000000000000000000000000000000000000000..9a1aaf0417bc0dd4d2717d8bd59f704852c7b8db --- /dev/null +++ b/Audio Visual Continual Learning/readme.md @@ -0,0 +1 @@ +Our experiments were conducted under the same settings across three random seeds. Due to file size limitations, we have only uploaded the results from one random seed here. Should you require the complete results from all seeds, please feel free to contact us! \ No newline at end of file diff --git a/Audio Visual Question Answering/results/inverse_False_withmodified/avst.pt b/Audio Visual Question Answering/results/inverse_False_withmodified/avst.pt new file mode 100644 index 0000000000000000000000000000000000000000..7682c41c179ab2eb69649af36ec8110d84a5bead --- /dev/null +++ b/Audio Visual Question Answering/results/inverse_False_withmodified/avst.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3343e550953ada51c01963bbe9ac044aa9dcf60bb565c4c2a44f2ab589a014 +size 89479183 diff --git a/Audio Visual Question Answering/results/inverse_False_withmodified/test.log b/Audio Visual Question Answering/results/inverse_False_withmodified/test.log new file mode 100644 index 0000000000000000000000000000000000000000..456e7c47e2abce063ff1789c5e9c300ff3388f1e --- /dev/null +++ b/Audio Visual Question Answering/results/inverse_False_withmodified/test.log @@ -0,0 +1,4 @@ +2025-04-15 06:44:07,432 INFO +--------------- Audio-Visual Spatial-Temporal Model --------------- + +2025-04-15 06:44:11,906 INFO 9185 diff --git a/Audio Visual Question Answering/results/inverse_False_withmodified/train.log b/Audio Visual Question Answering/results/inverse_False_withmodified/train.log new file mode 100644 index 0000000000000000000000000000000000000000..b676f6778fcc38ee6f3bacb81dbac2897eb3b308 --- /dev/null +++ b/Audio Visual Question Answering/results/inverse_False_withmodified/train.log @@ -0,0 +1,607 @@ +2025-04-14 10:06:14,059 INFO +--------------- Audio-Visual Spatial-Temporal Model --------------- + +2025-04-14 10:06:20,696 INFO +-------------- loading pretrained models -------------- +2025-04-14 10:06:20,701 INFO +-------------- load pretrained models -------------- +2025-04-14 10:06:26,620 INFO Train Epoch: 1 [0/32087 (0%)] Loss: 4.116232 +2025-04-14 10:06:40,825 INFO Train Epoch: 1 [3200/32087 (10%)] Loss: 2.912177 +2025-04-14 10:06:55,589 INFO Train Epoch: 1 [6400/32087 (20%)] Loss: 2.592709 +2025-04-14 10:07:11,257 INFO Train Epoch: 1 [9600/32087 (30%)] Loss: 2.430404 +2025-04-14 10:07:25,924 INFO Train Epoch: 1 [12800/32087 (40%)] Loss: 1.924211 +2025-04-14 10:07:40,383 INFO Train Epoch: 1 [16000/32087 (50%)] Loss: 1.548823 +2025-04-14 10:07:54,825 INFO Train Epoch: 1 [19200/32087 (60%)] Loss: 1.496499 +2025-04-14 10:08:08,991 INFO Train Epoch: 1 [22400/32087 (70%)] Loss: 1.287289 +2025-04-14 10:08:23,402 INFO Train Epoch: 1 [25600/32087 (80%)] Loss: 1.251714 +2025-04-14 10:08:39,080 INFO Train Epoch: 1 [28800/32087 (90%)] Loss: 1.247350 +2025-04-14 10:08:55,560 INFO Train Epoch: 1 [32000/32087 (100%)] Loss: 1.337393 +2025-04-14 10:10:24,147 INFO Accuracy qa: 57.39 % +2025-04-14 10:10:29,330 INFO Train Epoch: 2 [0/32087 (0%)] Loss: 1.305069 +2025-04-14 10:10:50,560 INFO Train Epoch: 2 [3200/32087 (10%)] Loss: 1.235739 +2025-04-14 10:11:09,973 INFO Train Epoch: 2 [6400/32087 (20%)] Loss: 1.161323 +2025-04-14 10:11:27,369 INFO Train Epoch: 2 [9600/32087 (30%)] Loss: 1.374228 +2025-04-14 10:11:44,414 INFO Train Epoch: 2 [12800/32087 (40%)] Loss: 1.326506 +2025-04-14 10:12:02,253 INFO Train Epoch: 2 [16000/32087 (50%)] Loss: 1.276050 +2025-04-14 10:12:17,737 INFO Train Epoch: 2 [19200/32087 (60%)] Loss: 1.118607 +2025-04-14 10:12:33,230 INFO Train Epoch: 2 [22400/32087 (70%)] Loss: 1.050256 +2025-04-14 10:12:48,573 INFO Train Epoch: 2 [25600/32087 (80%)] Loss: 1.184920 +2025-04-14 10:13:04,027 INFO Train Epoch: 2 [28800/32087 (90%)] Loss: 1.601681 +2025-04-14 10:13:19,335 INFO Train Epoch: 2 [32000/32087 (100%)] Loss: 1.193360 +2025-04-14 10:14:48,136 INFO Accuracy qa: 59.83 % +2025-04-14 10:14:52,185 INFO Train Epoch: 3 [0/32087 (0%)] Loss: 1.120144 +2025-04-14 10:15:10,473 INFO Train Epoch: 3 [3200/32087 (10%)] Loss: 1.076162 +2025-04-14 10:15:29,479 INFO Train Epoch: 3 [6400/32087 (20%)] Loss: 1.274145 +2025-04-14 10:15:46,802 INFO Train Epoch: 3 [9600/32087 (30%)] Loss: 1.314330 +2025-04-14 10:16:03,559 INFO Train Epoch: 3 [12800/32087 (40%)] Loss: 1.260660 +2025-04-14 10:16:19,534 INFO Train Epoch: 3 [16000/32087 (50%)] Loss: 1.165454 +2025-04-14 10:16:37,259 INFO Train Epoch: 3 [19200/32087 (60%)] Loss: 1.024316 +2025-04-14 10:16:53,058 INFO Train Epoch: 3 [22400/32087 (70%)] Loss: 1.227625 +2025-04-14 10:17:08,859 INFO Train Epoch: 3 [25600/32087 (80%)] Loss: 1.147497 +2025-04-14 10:17:24,527 INFO Train Epoch: 3 [28800/32087 (90%)] Loss: 0.989699 +2025-04-14 10:17:41,070 INFO Train Epoch: 3 [32000/32087 (100%)] Loss: 1.284533 +2025-04-14 10:19:10,689 INFO Accuracy qa: 62.68 % +2025-04-14 10:19:14,989 INFO Train Epoch: 4 [0/32087 (0%)] Loss: 1.077864 +2025-04-14 10:19:33,311 INFO Train Epoch: 4 [3200/32087 (10%)] Loss: 1.165232 +2025-04-14 10:19:51,358 INFO Train Epoch: 4 [6400/32087 (20%)] Loss: 1.213727 +2025-04-14 10:20:09,331 INFO Train Epoch: 4 [9600/32087 (30%)] Loss: 1.189309 +2025-04-14 10:20:26,123 INFO Train Epoch: 4 [12800/32087 (40%)] Loss: 1.285532 +2025-04-14 10:20:42,530 INFO Train Epoch: 4 [16000/32087 (50%)] Loss: 1.161664 +2025-04-14 10:20:59,924 INFO Train Epoch: 4 [19200/32087 (60%)] Loss: 1.031834 +2025-04-14 10:21:16,674 INFO Train Epoch: 4 [22400/32087 (70%)] Loss: 1.133596 +2025-04-14 10:21:31,462 INFO Train Epoch: 4 [25600/32087 (80%)] Loss: 1.077555 +2025-04-14 10:21:46,324 INFO Train Epoch: 4 [28800/32087 (90%)] Loss: 1.027984 +2025-04-14 10:22:01,679 INFO Train Epoch: 4 [32000/32087 (100%)] Loss: 1.038210 +2025-04-14 10:23:36,492 INFO Accuracy qa: 63.90 % +2025-04-14 10:23:40,530 INFO Train Epoch: 5 [0/32087 (0%)] Loss: 1.021164 +2025-04-14 10:23:59,829 INFO Train Epoch: 5 [3200/32087 (10%)] Loss: 1.044590 +2025-04-14 10:24:18,927 INFO Train Epoch: 5 [6400/32087 (20%)] Loss: 0.991274 +2025-04-14 10:24:37,708 INFO Train Epoch: 5 [9600/32087 (30%)] Loss: 0.843805 +2025-04-14 10:24:53,955 INFO Train Epoch: 5 [12800/32087 (40%)] Loss: 1.141917 +2025-04-14 10:25:09,463 INFO Train Epoch: 5 [16000/32087 (50%)] Loss: 1.039022 +2025-04-14 10:25:24,858 INFO Train Epoch: 5 [19200/32087 (60%)] Loss: 1.121311 +2025-04-14 10:25:41,002 INFO Train Epoch: 5 [22400/32087 (70%)] Loss: 1.160397 +2025-04-14 10:25:56,704 INFO Train Epoch: 5 [25600/32087 (80%)] Loss: 0.985996 +2025-04-14 10:26:11,394 INFO Train Epoch: 5 [28800/32087 (90%)] Loss: 0.918077 +2025-04-14 10:26:26,336 INFO Train Epoch: 5 [32000/32087 (100%)] Loss: 1.046347 +2025-04-14 10:27:56,875 INFO Accuracy qa: 64.07 % +2025-04-14 10:28:01,228 INFO Train Epoch: 6 [0/32087 (0%)] Loss: 1.041995 +2025-04-14 10:28:20,963 INFO Train Epoch: 6 [3200/32087 (10%)] Loss: 1.042619 +2025-04-14 10:28:39,969 INFO Train Epoch: 6 [6400/32087 (20%)] Loss: 1.033579 +2025-04-14 10:29:00,720 INFO Train Epoch: 6 [9600/32087 (30%)] Loss: 1.023322 +2025-04-14 10:29:19,890 INFO Train Epoch: 6 [12800/32087 (40%)] Loss: 0.947652 +2025-04-14 10:29:38,900 INFO Train Epoch: 6 [16000/32087 (50%)] Loss: 1.059937 +2025-04-14 10:29:58,610 INFO Train Epoch: 6 [19200/32087 (60%)] Loss: 1.178450 +2025-04-14 10:30:18,117 INFO Train Epoch: 6 [22400/32087 (70%)] Loss: 1.257022 +2025-04-14 10:30:36,221 INFO Train Epoch: 6 [25600/32087 (80%)] Loss: 1.088816 +2025-04-14 10:30:55,482 INFO Train Epoch: 6 [28800/32087 (90%)] Loss: 1.153947 +2025-04-14 10:31:15,002 INFO Train Epoch: 6 [32000/32087 (100%)] Loss: 1.005849 +2025-04-14 10:32:49,736 INFO Accuracy qa: 62.63 % +2025-04-14 10:32:54,419 INFO Train Epoch: 7 [0/32087 (0%)] Loss: 1.293350 +2025-04-14 10:33:13,335 INFO Train Epoch: 7 [3200/32087 (10%)] Loss: 1.018439 +2025-04-14 10:33:30,819 INFO Train Epoch: 7 [6400/32087 (20%)] Loss: 1.021875 +2025-04-14 10:33:48,069 INFO Train Epoch: 7 [9600/32087 (30%)] Loss: 0.961218 +2025-04-14 10:34:04,837 INFO Train Epoch: 7 [12800/32087 (40%)] Loss: 1.080452 +2025-04-14 10:34:23,284 INFO Train Epoch: 7 [16000/32087 (50%)] Loss: 1.137430 +2025-04-14 10:34:40,884 INFO Train Epoch: 7 [19200/32087 (60%)] Loss: 1.048622 +2025-04-14 10:34:56,053 INFO Train Epoch: 7 [22400/32087 (70%)] Loss: 0.958658 +2025-04-14 10:35:14,278 INFO Train Epoch: 7 [25600/32087 (80%)] Loss: 1.127383 +2025-04-14 10:35:31,931 INFO Train Epoch: 7 [28800/32087 (90%)] Loss: 1.263847 +2025-04-14 10:35:49,275 INFO Train Epoch: 7 [32000/32087 (100%)] Loss: 1.046734 +2025-04-14 10:37:22,432 INFO Accuracy qa: 66.90 % +2025-04-14 10:37:27,714 INFO Train Epoch: 8 [0/32087 (0%)] Loss: 1.068177 +2025-04-14 10:37:45,600 INFO Train Epoch: 8 [3200/32087 (10%)] Loss: 1.063240 +2025-04-14 10:38:01,759 INFO Train Epoch: 8 [6400/32087 (20%)] Loss: 0.988839 +2025-04-14 10:38:16,690 INFO Train Epoch: 8 [9600/32087 (30%)] Loss: 1.111973 +2025-04-14 10:38:32,533 INFO Train Epoch: 8 [12800/32087 (40%)] Loss: 1.135432 +2025-04-14 10:38:49,153 INFO Train Epoch: 8 [16000/32087 (50%)] Loss: 1.024267 +2025-04-14 10:39:05,909 INFO Train Epoch: 8 [19200/32087 (60%)] Loss: 1.009243 +2025-04-14 10:39:22,747 INFO Train Epoch: 8 [22400/32087 (70%)] Loss: 1.035502 +2025-04-14 10:39:40,459 INFO Train Epoch: 8 [25600/32087 (80%)] Loss: 1.060812 +2025-04-14 10:39:59,658 INFO Train Epoch: 8 [28800/32087 (90%)] Loss: 0.819324 +2025-04-14 10:40:17,196 INFO Train Epoch: 8 [32000/32087 (100%)] Loss: 1.151201 +2025-04-14 10:41:53,518 INFO Accuracy qa: 65.88 % +2025-04-14 10:41:57,231 INFO Train Epoch: 9 [0/32087 (0%)] Loss: 0.931307 +2025-04-14 10:42:18,617 INFO Train Epoch: 9 [3200/32087 (10%)] Loss: 0.817029 +2025-04-14 10:42:34,739 INFO Train Epoch: 9 [6400/32087 (20%)] Loss: 1.078337 +2025-04-14 10:42:51,959 INFO Train Epoch: 9 [9600/32087 (30%)] Loss: 0.835384 +2025-04-14 10:43:08,775 INFO Train Epoch: 9 [12800/32087 (40%)] Loss: 0.964786 +2025-04-14 10:43:26,573 INFO Train Epoch: 9 [16000/32087 (50%)] Loss: 1.064829 +2025-04-14 10:43:44,267 INFO Train Epoch: 9 [19200/32087 (60%)] Loss: 1.412822 +2025-04-14 10:44:02,472 INFO Train Epoch: 9 [22400/32087 (70%)] Loss: 0.956784 +2025-04-14 10:44:19,403 INFO Train Epoch: 9 [25600/32087 (80%)] Loss: 0.963385 +2025-04-14 10:44:37,868 INFO Train Epoch: 9 [28800/32087 (90%)] Loss: 0.840900 +2025-04-14 10:44:54,203 INFO Train Epoch: 9 [32000/32087 (100%)] Loss: 1.289329 +2025-04-14 10:46:26,851 INFO Accuracy qa: 67.62 % +2025-04-14 10:46:32,305 INFO Train Epoch: 10 [0/32087 (0%)] Loss: 1.148871 +2025-04-14 10:46:50,716 INFO Train Epoch: 10 [3200/32087 (10%)] Loss: 0.703198 +2025-04-14 10:47:09,316 INFO Train Epoch: 10 [6400/32087 (20%)] Loss: 1.004502 +2025-04-14 10:47:27,245 INFO Train Epoch: 10 [9600/32087 (30%)] Loss: 1.083017 +2025-04-14 10:47:45,161 INFO Train Epoch: 10 [12800/32087 (40%)] Loss: 0.786507 +2025-04-14 10:48:03,588 INFO Train Epoch: 10 [16000/32087 (50%)] Loss: 0.903112 +2025-04-14 10:48:18,919 INFO Train Epoch: 10 [19200/32087 (60%)] Loss: 1.017982 +2025-04-14 10:48:35,330 INFO Train Epoch: 10 [22400/32087 (70%)] Loss: 1.084112 +2025-04-14 10:48:52,463 INFO Train Epoch: 10 [25600/32087 (80%)] Loss: 1.068478 +2025-04-14 10:49:09,099 INFO Train Epoch: 10 [28800/32087 (90%)] Loss: 1.032907 +2025-04-14 10:49:23,698 INFO Train Epoch: 10 [32000/32087 (100%)] Loss: 0.787199 +2025-04-14 10:50:53,428 INFO Accuracy qa: 69.05 % +2025-04-14 10:50:58,048 INFO Train Epoch: 11 [0/32087 (0%)] Loss: 0.818880 +2025-04-14 10:51:18,363 INFO Train Epoch: 11 [3200/32087 (10%)] Loss: 1.033633 +2025-04-14 10:51:37,066 INFO Train Epoch: 11 [6400/32087 (20%)] Loss: 0.747171 +2025-04-14 10:51:55,167 INFO Train Epoch: 11 [9600/32087 (30%)] Loss: 0.970158 +2025-04-14 10:52:12,775 INFO Train Epoch: 11 [12800/32087 (40%)] Loss: 0.688537 +2025-04-14 10:52:30,240 INFO Train Epoch: 11 [16000/32087 (50%)] Loss: 0.856929 +2025-04-14 10:52:48,705 INFO Train Epoch: 11 [19200/32087 (60%)] Loss: 0.956014 +2025-04-14 10:53:05,524 INFO Train Epoch: 11 [22400/32087 (70%)] Loss: 1.092961 +2025-04-14 10:53:23,677 INFO Train Epoch: 11 [25600/32087 (80%)] Loss: 0.821817 +2025-04-14 10:53:42,327 INFO Train Epoch: 11 [28800/32087 (90%)] Loss: 1.058851 +2025-04-14 10:53:58,575 INFO Train Epoch: 11 [32000/32087 (100%)] Loss: 0.923937 +2025-04-14 10:55:34,020 INFO Accuracy qa: 68.79 % +2025-04-14 10:55:38,131 INFO Train Epoch: 12 [0/32087 (0%)] Loss: 0.887854 +2025-04-14 10:55:56,622 INFO Train Epoch: 12 [3200/32087 (10%)] Loss: 0.838829 +2025-04-14 10:56:14,165 INFO Train Epoch: 12 [6400/32087 (20%)] Loss: 1.062656 +2025-04-14 10:56:32,551 INFO Train Epoch: 12 [9600/32087 (30%)] Loss: 1.039872 +2025-04-14 10:56:50,975 INFO Train Epoch: 12 [12800/32087 (40%)] Loss: 0.813762 +2025-04-14 10:57:08,798 INFO Train Epoch: 12 [16000/32087 (50%)] Loss: 0.819386 +2025-04-14 10:57:26,726 INFO Train Epoch: 12 [19200/32087 (60%)] Loss: 1.029181 +2025-04-14 10:57:43,595 INFO Train Epoch: 12 [22400/32087 (70%)] Loss: 1.019662 +2025-04-14 10:58:00,216 INFO Train Epoch: 12 [25600/32087 (80%)] Loss: 0.996342 +2025-04-14 10:58:18,221 INFO Train Epoch: 12 [28800/32087 (90%)] Loss: 0.955734 +2025-04-14 10:58:35,505 INFO Train Epoch: 12 [32000/32087 (100%)] Loss: 1.081076 +2025-04-14 11:00:09,301 INFO Accuracy qa: 68.27 % +2025-04-14 11:00:15,089 INFO Train Epoch: 13 [0/32087 (0%)] Loss: 0.918387 +2025-04-14 11:00:34,407 INFO Train Epoch: 13 [3200/32087 (10%)] Loss: 0.947561 +2025-04-14 11:00:55,506 INFO Train Epoch: 13 [6400/32087 (20%)] Loss: 0.860152 +2025-04-14 11:01:14,857 INFO Train Epoch: 13 [9600/32087 (30%)] Loss: 0.864925 +2025-04-14 11:01:35,226 INFO Train Epoch: 13 [12800/32087 (40%)] Loss: 0.926858 +2025-04-14 11:01:55,645 INFO Train Epoch: 13 [16000/32087 (50%)] Loss: 1.091918 +2025-04-14 11:02:15,860 INFO Train Epoch: 13 [19200/32087 (60%)] Loss: 0.874881 +2025-04-14 11:02:37,668 INFO Train Epoch: 13 [22400/32087 (70%)] Loss: 0.936576 +2025-04-14 11:02:59,038 INFO Train Epoch: 13 [25600/32087 (80%)] Loss: 0.687169 +2025-04-14 11:03:19,081 INFO Train Epoch: 13 [28800/32087 (90%)] Loss: 0.813923 +2025-04-14 11:03:37,507 INFO Train Epoch: 13 [32000/32087 (100%)] Loss: 0.805475 +2025-04-14 11:05:13,450 INFO Accuracy qa: 68.40 % +2025-04-14 11:05:16,423 INFO Train Epoch: 14 [0/32087 (0%)] Loss: 0.790639 +2025-04-14 11:05:36,158 INFO Train Epoch: 14 [3200/32087 (10%)] Loss: 0.833346 +2025-04-14 11:05:54,869 INFO Train Epoch: 14 [6400/32087 (20%)] Loss: 0.756430 +2025-04-14 11:06:15,297 INFO Train Epoch: 14 [9600/32087 (30%)] Loss: 0.761688 +2025-04-14 11:06:33,346 INFO Train Epoch: 14 [12800/32087 (40%)] Loss: 0.727501 +2025-04-14 11:06:50,690 INFO Train Epoch: 14 [16000/32087 (50%)] Loss: 0.886783 +2025-04-14 11:07:08,577 INFO Train Epoch: 14 [19200/32087 (60%)] Loss: 1.034792 +2025-04-14 11:07:26,353 INFO Train Epoch: 14 [22400/32087 (70%)] Loss: 1.063689 +2025-04-14 11:07:43,321 INFO Train Epoch: 14 [25600/32087 (80%)] Loss: 0.858555 +2025-04-14 11:08:01,288 INFO Train Epoch: 14 [28800/32087 (90%)] Loss: 1.123809 +2025-04-14 11:08:17,669 INFO Train Epoch: 14 [32000/32087 (100%)] Loss: 1.000464 +2025-04-14 11:09:57,030 INFO Accuracy qa: 67.66 % +2025-04-14 11:10:01,607 INFO Train Epoch: 15 [0/32087 (0%)] Loss: 0.764614 +2025-04-14 11:10:19,652 INFO Train Epoch: 15 [3200/32087 (10%)] Loss: 0.853157 +2025-04-14 11:10:39,592 INFO Train Epoch: 15 [6400/32087 (20%)] Loss: 0.841639 +2025-04-14 11:10:57,401 INFO Train Epoch: 15 [9600/32087 (30%)] Loss: 0.552053 +2025-04-14 11:11:14,958 INFO Train Epoch: 15 [12800/32087 (40%)] Loss: 0.858427 +2025-04-14 11:11:32,082 INFO Train Epoch: 15 [16000/32087 (50%)] Loss: 0.867070 +2025-04-14 11:11:48,353 INFO Train Epoch: 15 [19200/32087 (60%)] Loss: 1.005606 +2025-04-14 11:12:03,653 INFO Train Epoch: 15 [22400/32087 (70%)] Loss: 0.792342 +2025-04-14 11:12:19,752 INFO Train Epoch: 15 [25600/32087 (80%)] Loss: 1.013166 +2025-04-14 11:12:37,217 INFO Train Epoch: 15 [28800/32087 (90%)] Loss: 0.772247 +2025-04-14 11:12:54,697 INFO Train Epoch: 15 [32000/32087 (100%)] Loss: 0.867279 +2025-04-14 11:14:25,315 INFO Accuracy qa: 68.90 % +2025-04-14 11:14:28,893 INFO Train Epoch: 16 [0/32087 (0%)] Loss: 0.938562 +2025-04-14 11:14:47,369 INFO Train Epoch: 16 [3200/32087 (10%)] Loss: 0.738388 +2025-04-14 11:15:04,249 INFO Train Epoch: 16 [6400/32087 (20%)] Loss: 0.822716 +2025-04-14 11:15:21,825 INFO Train Epoch: 16 [9600/32087 (30%)] Loss: 0.841026 +2025-04-14 11:15:38,651 INFO Train Epoch: 16 [12800/32087 (40%)] Loss: 0.771318 +2025-04-14 11:15:56,080 INFO Train Epoch: 16 [16000/32087 (50%)] Loss: 0.716851 +2025-04-14 11:16:13,740 INFO Train Epoch: 16 [19200/32087 (60%)] Loss: 0.718580 +2025-04-14 11:16:31,421 INFO Train Epoch: 16 [22400/32087 (70%)] Loss: 0.621544 +2025-04-14 11:16:49,308 INFO Train Epoch: 16 [25600/32087 (80%)] Loss: 0.777349 +2025-04-14 11:17:07,181 INFO Train Epoch: 16 [28800/32087 (90%)] Loss: 0.698268 +2025-04-14 11:17:25,687 INFO Train Epoch: 16 [32000/32087 (100%)] Loss: 0.796646 +2025-04-14 11:19:02,753 INFO Accuracy qa: 70.62 % +2025-04-14 11:19:08,076 INFO Train Epoch: 17 [0/32087 (0%)] Loss: 0.771669 +2025-04-14 11:19:26,599 INFO Train Epoch: 17 [3200/32087 (10%)] Loss: 0.604975 +2025-04-14 11:19:43,669 INFO Train Epoch: 17 [6400/32087 (20%)] Loss: 0.824648 +2025-04-14 11:20:00,535 INFO Train Epoch: 17 [9600/32087 (30%)] Loss: 0.866311 +2025-04-14 11:20:16,638 INFO Train Epoch: 17 [12800/32087 (40%)] Loss: 0.690244 +2025-04-14 11:20:33,901 INFO Train Epoch: 17 [16000/32087 (50%)] Loss: 0.910449 +2025-04-14 11:20:50,563 INFO Train Epoch: 17 [19200/32087 (60%)] Loss: 0.719779 +2025-04-14 11:21:07,673 INFO Train Epoch: 17 [22400/32087 (70%)] Loss: 0.728833 +2025-04-14 11:21:26,821 INFO Train Epoch: 17 [25600/32087 (80%)] Loss: 0.750242 +2025-04-14 11:21:45,587 INFO Train Epoch: 17 [28800/32087 (90%)] Loss: 0.640429 +2025-04-14 11:22:03,410 INFO Train Epoch: 17 [32000/32087 (100%)] Loss: 0.817074 +2025-04-14 11:23:40,809 INFO Accuracy qa: 70.84 % +2025-04-14 11:23:45,156 INFO Train Epoch: 18 [0/32087 (0%)] Loss: 0.677503 +2025-04-14 11:24:04,740 INFO Train Epoch: 18 [3200/32087 (10%)] Loss: 0.712205 +2025-04-14 11:24:21,108 INFO Train Epoch: 18 [6400/32087 (20%)] Loss: 0.632094 +2025-04-14 11:24:36,426 INFO Train Epoch: 18 [9600/32087 (30%)] Loss: 0.898637 +2025-04-14 11:24:52,318 INFO Train Epoch: 18 [12800/32087 (40%)] Loss: 0.825847 +2025-04-14 11:25:08,787 INFO Train Epoch: 18 [16000/32087 (50%)] Loss: 0.774669 +2025-04-14 11:25:24,224 INFO Train Epoch: 18 [19200/32087 (60%)] Loss: 0.709135 +2025-04-14 11:25:39,405 INFO Train Epoch: 18 [22400/32087 (70%)] Loss: 0.762976 +2025-04-14 11:25:56,955 INFO Train Epoch: 18 [25600/32087 (80%)] Loss: 0.643087 +2025-04-14 11:26:14,560 INFO Train Epoch: 18 [28800/32087 (90%)] Loss: 0.717479 +2025-04-14 11:26:30,942 INFO Train Epoch: 18 [32000/32087 (100%)] Loss: 0.592599 +2025-04-14 11:28:05,739 INFO Accuracy qa: 70.64 % +2025-04-14 11:28:11,690 INFO Train Epoch: 19 [0/32087 (0%)] Loss: 0.609667 +2025-04-14 11:28:30,643 INFO Train Epoch: 19 [3200/32087 (10%)] Loss: 0.834933 +2025-04-14 11:28:48,303 INFO Train Epoch: 19 [6400/32087 (20%)] Loss: 0.783571 +2025-04-14 11:29:05,206 INFO Train Epoch: 19 [9600/32087 (30%)] Loss: 0.756572 +2025-04-14 11:29:21,993 INFO Train Epoch: 19 [12800/32087 (40%)] Loss: 0.830897 +2025-04-14 11:29:39,523 INFO Train Epoch: 19 [16000/32087 (50%)] Loss: 0.709871 +2025-04-14 11:29:55,632 INFO Train Epoch: 19 [19200/32087 (60%)] Loss: 0.617813 +2025-04-14 11:30:11,410 INFO Train Epoch: 19 [22400/32087 (70%)] Loss: 0.600891 +2025-04-14 11:30:27,852 INFO Train Epoch: 19 [25600/32087 (80%)] Loss: 0.635023 +2025-04-14 11:30:45,823 INFO Train Epoch: 19 [28800/32087 (90%)] Loss: 0.670409 +2025-04-14 11:31:00,559 INFO Train Epoch: 19 [32000/32087 (100%)] Loss: 0.694112 +2025-04-14 11:32:36,216 INFO Accuracy qa: 70.64 % +2025-04-14 11:32:41,024 INFO Train Epoch: 20 [0/32087 (0%)] Loss: 0.747571 +2025-04-14 11:32:59,431 INFO Train Epoch: 20 [3200/32087 (10%)] Loss: 0.574074 +2025-04-14 11:33:17,186 INFO Train Epoch: 20 [6400/32087 (20%)] Loss: 0.676822 +2025-04-14 11:33:34,052 INFO Train Epoch: 20 [9600/32087 (30%)] Loss: 0.724774 +2025-04-14 11:33:50,263 INFO Train Epoch: 20 [12800/32087 (40%)] Loss: 0.703091 +2025-04-14 11:34:06,793 INFO Train Epoch: 20 [16000/32087 (50%)] Loss: 0.824025 +2025-04-14 11:34:22,481 INFO Train Epoch: 20 [19200/32087 (60%)] Loss: 0.840704 +2025-04-14 11:34:40,057 INFO Train Epoch: 20 [22400/32087 (70%)] Loss: 0.836543 +2025-04-14 11:34:56,784 INFO Train Epoch: 20 [25600/32087 (80%)] Loss: 0.759252 +2025-04-14 11:35:14,238 INFO Train Epoch: 20 [28800/32087 (90%)] Loss: 0.831389 +2025-04-14 11:35:30,026 INFO Train Epoch: 20 [32000/32087 (100%)] Loss: 0.719333 +2025-04-14 11:37:09,807 INFO Accuracy qa: 70.53 % +2025-04-14 11:37:14,979 INFO Train Epoch: 21 [0/32087 (0%)] Loss: 0.582751 +2025-04-14 11:37:33,731 INFO Train Epoch: 21 [3200/32087 (10%)] Loss: 0.621306 +2025-04-14 11:37:51,601 INFO Train Epoch: 21 [6400/32087 (20%)] Loss: 0.791284 +2025-04-14 11:38:08,801 INFO Train Epoch: 21 [9600/32087 (30%)] Loss: 0.727633 +2025-04-14 11:38:27,186 INFO Train Epoch: 21 [12800/32087 (40%)] Loss: 0.788374 +2025-04-14 11:38:44,644 INFO Train Epoch: 21 [16000/32087 (50%)] Loss: 0.706321 +2025-04-14 11:39:00,338 INFO Train Epoch: 21 [19200/32087 (60%)] Loss: 0.690159 +2025-04-14 11:39:16,646 INFO Train Epoch: 21 [22400/32087 (70%)] Loss: 0.695284 +2025-04-14 11:39:34,954 INFO Train Epoch: 21 [25600/32087 (80%)] Loss: 0.753152 +2025-04-14 11:39:52,362 INFO Train Epoch: 21 [28800/32087 (90%)] Loss: 0.895881 +2025-04-14 11:40:08,496 INFO Train Epoch: 21 [32000/32087 (100%)] Loss: 0.755579 +2025-04-14 11:41:56,688 INFO Accuracy qa: 70.86 % +2025-04-14 11:42:02,768 INFO Train Epoch: 22 [0/32087 (0%)] Loss: 0.714718 +2025-04-14 11:42:19,464 INFO Train Epoch: 22 [3200/32087 (10%)] Loss: 0.740026 +2025-04-14 11:42:37,458 INFO Train Epoch: 22 [6400/32087 (20%)] Loss: 0.711799 +2025-04-14 11:42:56,540 INFO Train Epoch: 22 [9600/32087 (30%)] Loss: 0.610264 +2025-04-14 11:43:14,274 INFO Train Epoch: 22 [12800/32087 (40%)] Loss: 0.806327 +2025-04-14 11:43:31,194 INFO Train Epoch: 22 [16000/32087 (50%)] Loss: 0.564810 +2025-04-14 11:43:48,062 INFO Train Epoch: 22 [19200/32087 (60%)] Loss: 0.614478 +2025-04-14 11:44:04,065 INFO Train Epoch: 22 [22400/32087 (70%)] Loss: 0.873239 +2025-04-14 11:44:20,175 INFO Train Epoch: 22 [25600/32087 (80%)] Loss: 0.800922 +2025-04-14 11:44:37,981 INFO Train Epoch: 22 [28800/32087 (90%)] Loss: 0.686565 +2025-04-14 11:44:57,289 INFO Train Epoch: 22 [32000/32087 (100%)] Loss: 0.737539 +2025-04-14 11:46:34,509 INFO Accuracy qa: 71.12 % +2025-04-14 11:46:38,808 INFO Train Epoch: 23 [0/32087 (0%)] Loss: 0.749367 +2025-04-14 11:46:56,440 INFO Train Epoch: 23 [3200/32087 (10%)] Loss: 0.676091 +2025-04-14 11:47:15,307 INFO Train Epoch: 23 [6400/32087 (20%)] Loss: 0.636520 +2025-04-14 11:47:33,064 INFO Train Epoch: 23 [9600/32087 (30%)] Loss: 0.765544 +2025-04-14 11:47:50,382 INFO Train Epoch: 23 [12800/32087 (40%)] Loss: 0.706439 +2025-04-14 11:48:08,242 INFO Train Epoch: 23 [16000/32087 (50%)] Loss: 0.633525 +2025-04-14 11:48:25,623 INFO Train Epoch: 23 [19200/32087 (60%)] Loss: 0.752269 +2025-04-14 11:48:43,391 INFO Train Epoch: 23 [22400/32087 (70%)] Loss: 0.622035 +2025-04-14 11:48:59,866 INFO Train Epoch: 23 [25600/32087 (80%)] Loss: 0.712049 +2025-04-14 11:49:17,197 INFO Train Epoch: 23 [28800/32087 (90%)] Loss: 0.618920 +2025-04-14 11:49:33,737 INFO Train Epoch: 23 [32000/32087 (100%)] Loss: 0.643432 +2025-04-14 11:51:12,075 INFO Accuracy qa: 70.40 % +2025-04-14 11:51:16,250 INFO Train Epoch: 24 [0/32087 (0%)] Loss: 0.600986 +2025-04-14 11:51:34,771 INFO Train Epoch: 24 [3200/32087 (10%)] Loss: 0.657665 +2025-04-14 11:51:52,304 INFO Train Epoch: 24 [6400/32087 (20%)] Loss: 0.588879 +2025-04-14 11:52:09,431 INFO Train Epoch: 24 [9600/32087 (30%)] Loss: 0.718098 +2025-04-14 11:52:25,740 INFO Train Epoch: 24 [12800/32087 (40%)] Loss: 0.607994 +2025-04-14 11:52:42,459 INFO Train Epoch: 24 [16000/32087 (50%)] Loss: 0.585270 +2025-04-14 11:52:59,051 INFO Train Epoch: 24 [19200/32087 (60%)] Loss: 0.762849 +2025-04-14 11:53:15,376 INFO Train Epoch: 24 [22400/32087 (70%)] Loss: 0.686044 +2025-04-14 11:53:33,029 INFO Train Epoch: 24 [25600/32087 (80%)] Loss: 0.616578 +2025-04-14 11:53:51,244 INFO Train Epoch: 24 [28800/32087 (90%)] Loss: 0.581128 +2025-04-14 11:54:07,048 INFO Train Epoch: 24 [32000/32087 (100%)] Loss: 0.663288 +2025-04-14 11:55:42,026 INFO Accuracy qa: 70.79 % +2025-04-14 11:55:46,794 INFO Train Epoch: 25 [0/32087 (0%)] Loss: 0.593735 +2025-04-14 11:56:06,364 INFO Train Epoch: 25 [3200/32087 (10%)] Loss: 0.490637 +2025-04-14 11:56:24,325 INFO Train Epoch: 25 [6400/32087 (20%)] Loss: 0.606493 +2025-04-14 11:56:40,573 INFO Train Epoch: 25 [9600/32087 (30%)] Loss: 0.613104 +2025-04-14 11:56:56,727 INFO Train Epoch: 25 [12800/32087 (40%)] Loss: 0.704442 +2025-04-14 11:57:14,675 INFO Train Epoch: 25 [16000/32087 (50%)] Loss: 0.739563 +2025-04-14 11:57:31,254 INFO Train Epoch: 25 [19200/32087 (60%)] Loss: 0.538469 +2025-04-14 11:57:47,486 INFO Train Epoch: 25 [22400/32087 (70%)] Loss: 0.670775 +2025-04-14 11:58:04,235 INFO Train Epoch: 25 [25600/32087 (80%)] Loss: 0.621384 +2025-04-14 11:58:22,956 INFO Train Epoch: 25 [28800/32087 (90%)] Loss: 0.712447 +2025-04-14 11:58:39,775 INFO Train Epoch: 25 [32000/32087 (100%)] Loss: 0.766404 +2025-04-14 12:00:20,301 INFO Accuracy qa: 70.79 % +2025-04-14 12:00:23,855 INFO Train Epoch: 26 [0/32087 (0%)] Loss: 0.610533 +2025-04-14 12:00:43,040 INFO Train Epoch: 26 [3200/32087 (10%)] Loss: 0.733190 +2025-04-14 12:01:01,655 INFO Train Epoch: 26 [6400/32087 (20%)] Loss: 0.720093 +2025-04-14 12:01:18,737 INFO Train Epoch: 26 [9600/32087 (30%)] Loss: 0.851391 +2025-04-14 12:01:36,448 INFO Train Epoch: 26 [12800/32087 (40%)] Loss: 0.678067 +2025-04-14 12:01:54,192 INFO Train Epoch: 26 [16000/32087 (50%)] Loss: 0.753558 +2025-04-14 12:02:11,694 INFO Train Epoch: 26 [19200/32087 (60%)] Loss: 0.720080 +2025-04-14 12:02:29,425 INFO Train Epoch: 26 [22400/32087 (70%)] Loss: 0.709175 +2025-04-14 12:02:48,283 INFO Train Epoch: 26 [25600/32087 (80%)] Loss: 0.607958 +2025-04-14 12:03:06,717 INFO Train Epoch: 26 [28800/32087 (90%)] Loss: 0.800945 +2025-04-14 12:03:23,745 INFO Train Epoch: 26 [32000/32087 (100%)] Loss: 0.774466 +2025-04-14 12:04:59,998 INFO Accuracy qa: 70.49 % +2025-04-14 12:05:03,785 INFO Train Epoch: 27 [0/32087 (0%)] Loss: 0.623110 +2025-04-14 12:05:22,365 INFO Train Epoch: 27 [3200/32087 (10%)] Loss: 0.549226 +2025-04-14 12:05:38,989 INFO Train Epoch: 27 [6400/32087 (20%)] Loss: 0.605245 +2025-04-14 12:05:56,318 INFO Train Epoch: 27 [9600/32087 (30%)] Loss: 0.651225 +2025-04-14 12:06:14,428 INFO Train Epoch: 27 [12800/32087 (40%)] Loss: 0.706090 +2025-04-14 12:06:31,780 INFO Train Epoch: 27 [16000/32087 (50%)] Loss: 0.751013 +2025-04-14 12:06:48,614 INFO Train Epoch: 27 [19200/32087 (60%)] Loss: 0.620978 +2025-04-14 12:07:09,136 INFO Train Epoch: 27 [22400/32087 (70%)] Loss: 0.650444 +2025-04-14 12:07:28,421 INFO Train Epoch: 27 [25600/32087 (80%)] Loss: 0.684747 +2025-04-14 12:07:46,147 INFO Train Epoch: 27 [28800/32087 (90%)] Loss: 0.809503 +2025-04-14 12:08:02,268 INFO Train Epoch: 27 [32000/32087 (100%)] Loss: 0.558942 +2025-04-14 12:09:33,360 INFO Accuracy qa: 70.60 % +2025-04-14 12:09:37,134 INFO Train Epoch: 28 [0/32087 (0%)] Loss: 0.697776 +2025-04-14 12:09:53,288 INFO Train Epoch: 28 [3200/32087 (10%)] Loss: 0.819766 +2025-04-14 12:10:08,297 INFO Train Epoch: 28 [6400/32087 (20%)] Loss: 0.430684 +2025-04-14 12:10:24,250 INFO Train Epoch: 28 [9600/32087 (30%)] Loss: 0.662133 +2025-04-14 12:10:41,925 INFO Train Epoch: 28 [12800/32087 (40%)] Loss: 0.631626 +2025-04-14 12:10:59,061 INFO Train Epoch: 28 [16000/32087 (50%)] Loss: 0.640901 +2025-04-14 12:11:17,242 INFO Train Epoch: 28 [19200/32087 (60%)] Loss: 0.592357 +2025-04-14 12:11:36,599 INFO Train Epoch: 28 [22400/32087 (70%)] Loss: 0.456670 +2025-04-14 12:11:54,704 INFO Train Epoch: 28 [25600/32087 (80%)] Loss: 0.733413 +2025-04-14 12:12:12,612 INFO Train Epoch: 28 [28800/32087 (90%)] Loss: 0.607526 +2025-04-14 12:12:29,505 INFO Train Epoch: 28 [32000/32087 (100%)] Loss: 0.632048 +2025-04-14 12:14:01,268 INFO Accuracy qa: 70.47 % +2025-04-14 12:14:04,821 INFO Train Epoch: 29 [0/32087 (0%)] Loss: 0.731731 +2025-04-14 12:14:21,074 INFO Train Epoch: 29 [3200/32087 (10%)] Loss: 0.531439 +2025-04-14 12:14:36,768 INFO Train Epoch: 29 [6400/32087 (20%)] Loss: 0.676208 +2025-04-14 12:14:53,708 INFO Train Epoch: 29 [9600/32087 (30%)] Loss: 0.692990 +2025-04-14 12:15:12,190 INFO Train Epoch: 29 [12800/32087 (40%)] Loss: 0.737397 +2025-04-14 12:15:30,469 INFO Train Epoch: 29 [16000/32087 (50%)] Loss: 0.664378 +2025-04-14 12:15:51,720 INFO Train Epoch: 29 [19200/32087 (60%)] Loss: 0.596276 +2025-04-14 12:16:11,543 INFO Train Epoch: 29 [22400/32087 (70%)] Loss: 0.809036 +2025-04-14 12:16:30,464 INFO Train Epoch: 29 [25600/32087 (80%)] Loss: 0.679146 +2025-04-14 12:16:48,984 INFO Train Epoch: 29 [28800/32087 (90%)] Loss: 0.572784 +2025-04-14 12:17:07,870 INFO Train Epoch: 29 [32000/32087 (100%)] Loss: 0.458005 +2025-04-14 12:18:38,864 INFO Accuracy qa: 70.34 % +2025-04-14 12:18:42,249 INFO Train Epoch: 30 [0/32087 (0%)] Loss: 0.581886 +2025-04-14 12:18:58,746 INFO Train Epoch: 30 [3200/32087 (10%)] Loss: 0.516586 +2025-04-14 12:19:14,034 INFO Train Epoch: 30 [6400/32087 (20%)] Loss: 0.475624 +2025-04-14 12:19:30,387 INFO Train Epoch: 30 [9600/32087 (30%)] Loss: 0.608522 +2025-04-14 12:19:47,474 INFO Train Epoch: 30 [12800/32087 (40%)] Loss: 0.551751 +2025-04-14 12:20:06,869 INFO Train Epoch: 30 [16000/32087 (50%)] Loss: 0.601358 +2025-04-14 12:20:24,931 INFO Train Epoch: 30 [19200/32087 (60%)] Loss: 0.620605 +2025-04-14 12:20:44,869 INFO Train Epoch: 30 [22400/32087 (70%)] Loss: 0.742085 +2025-04-14 12:21:03,483 INFO Train Epoch: 30 [25600/32087 (80%)] Loss: 0.726946 +2025-04-14 12:21:22,202 INFO Train Epoch: 30 [28800/32087 (90%)] Loss: 0.556103 +2025-04-14 12:21:38,916 INFO Train Epoch: 30 [32000/32087 (100%)] Loss: 0.608546 +2025-04-14 12:23:07,754 INFO Accuracy qa: 70.73 % +2025-04-14 12:23:11,022 INFO Train Epoch: 31 [0/32087 (0%)] Loss: 0.643440 +2025-04-14 12:23:27,922 INFO Train Epoch: 31 [3200/32087 (10%)] Loss: 0.810614 +2025-04-14 12:23:43,884 INFO Train Epoch: 31 [6400/32087 (20%)] Loss: 0.771079 +2025-04-14 12:24:01,491 INFO Train Epoch: 31 [9600/32087 (30%)] Loss: 0.519430 +2025-04-14 12:24:21,035 INFO Train Epoch: 31 [12800/32087 (40%)] Loss: 0.653491 +2025-04-14 12:24:39,587 INFO Train Epoch: 31 [16000/32087 (50%)] Loss: 0.579019 +2025-04-14 12:25:00,718 INFO Train Epoch: 31 [19200/32087 (60%)] Loss: 0.478895 +2025-04-14 12:25:22,122 INFO Train Epoch: 31 [22400/32087 (70%)] Loss: 0.597875 +2025-04-14 12:25:41,354 INFO Train Epoch: 31 [25600/32087 (80%)] Loss: 0.608160 +2025-04-14 12:26:00,287 INFO Train Epoch: 31 [28800/32087 (90%)] Loss: 0.762652 +2025-04-14 12:26:18,014 INFO Train Epoch: 31 [32000/32087 (100%)] Loss: 0.682628 +2025-04-14 12:27:45,267 INFO Accuracy qa: 70.86 % +2025-04-14 12:27:48,846 INFO Train Epoch: 32 [0/32087 (0%)] Loss: 0.672898 +2025-04-14 12:28:04,383 INFO Train Epoch: 32 [3200/32087 (10%)] Loss: 0.563673 +2025-04-14 12:28:20,248 INFO Train Epoch: 32 [6400/32087 (20%)] Loss: 0.630636 +2025-04-14 12:28:37,348 INFO Train Epoch: 32 [9600/32087 (30%)] Loss: 0.581594 +2025-04-14 12:28:54,307 INFO Train Epoch: 32 [12800/32087 (40%)] Loss: 0.614571 +2025-04-14 12:29:11,247 INFO Train Epoch: 32 [16000/32087 (50%)] Loss: 0.505237 +2025-04-14 12:29:28,515 INFO Train Epoch: 32 [19200/32087 (60%)] Loss: 0.572276 +2025-04-14 12:29:47,916 INFO Train Epoch: 32 [22400/32087 (70%)] Loss: 0.668339 +2025-04-14 12:30:05,700 INFO Train Epoch: 32 [25600/32087 (80%)] Loss: 0.712636 +2025-04-14 12:30:23,926 INFO Train Epoch: 32 [28800/32087 (90%)] Loss: 0.547070 +2025-04-14 12:30:38,077 INFO Train Epoch: 32 [32000/32087 (100%)] Loss: 0.572704 +2025-04-14 12:32:06,874 INFO Accuracy qa: 70.73 % +2025-04-14 12:32:10,590 INFO Train Epoch: 33 [0/32087 (0%)] Loss: 0.646525 +2025-04-14 12:32:25,867 INFO Train Epoch: 33 [3200/32087 (10%)] Loss: 0.780382 +2025-04-14 12:32:41,146 INFO Train Epoch: 33 [6400/32087 (20%)] Loss: 0.489868 +2025-04-14 12:32:57,537 INFO Train Epoch: 33 [9600/32087 (30%)] Loss: 0.696315 +2025-04-14 12:33:14,721 INFO Train Epoch: 33 [12800/32087 (40%)] Loss: 0.635608 +2025-04-14 12:33:32,066 INFO Train Epoch: 33 [16000/32087 (50%)] Loss: 0.771603 +2025-04-14 12:33:49,390 INFO Train Epoch: 33 [19200/32087 (60%)] Loss: 0.448142 +2025-04-14 12:34:07,119 INFO Train Epoch: 33 [22400/32087 (70%)] Loss: 0.490192 +2025-04-14 12:34:24,056 INFO Train Epoch: 33 [25600/32087 (80%)] Loss: 0.619137 +2025-04-14 12:34:41,247 INFO Train Epoch: 33 [28800/32087 (90%)] Loss: 0.592780 +2025-04-14 12:34:56,442 INFO Train Epoch: 33 [32000/32087 (100%)] Loss: 0.724048 +2025-04-14 12:36:27,196 INFO Accuracy qa: 70.62 % +2025-04-14 12:36:31,506 INFO Train Epoch: 34 [0/32087 (0%)] Loss: 0.595895 +2025-04-14 12:36:47,082 INFO Train Epoch: 34 [3200/32087 (10%)] Loss: 0.628014 +2025-04-14 12:37:02,532 INFO Train Epoch: 34 [6400/32087 (20%)] Loss: 0.611953 +2025-04-14 12:37:18,298 INFO Train Epoch: 34 [9600/32087 (30%)] Loss: 0.626694 +2025-04-14 12:37:35,743 INFO Train Epoch: 34 [12800/32087 (40%)] Loss: 0.572099 +2025-04-14 12:37:53,219 INFO Train Epoch: 34 [16000/32087 (50%)] Loss: 0.674556 +2025-04-14 12:38:10,843 INFO Train Epoch: 34 [19200/32087 (60%)] Loss: 0.701211 +2025-04-14 12:38:29,783 INFO Train Epoch: 34 [22400/32087 (70%)] Loss: 0.669918 +2025-04-14 12:38:48,623 INFO Train Epoch: 34 [25600/32087 (80%)] Loss: 0.733288 +2025-04-14 12:39:05,885 INFO Train Epoch: 34 [28800/32087 (90%)] Loss: 0.637857 +2025-04-14 12:39:22,016 INFO Train Epoch: 34 [32000/32087 (100%)] Loss: 0.616864 +2025-04-14 12:40:52,897 INFO Accuracy qa: 70.55 % +2025-04-14 12:40:57,398 INFO Train Epoch: 35 [0/32087 (0%)] Loss: 0.650589 +2025-04-14 12:41:14,578 INFO Train Epoch: 35 [3200/32087 (10%)] Loss: 0.552875 +2025-04-14 12:41:31,775 INFO Train Epoch: 35 [6400/32087 (20%)] Loss: 0.639100 +2025-04-14 12:41:49,382 INFO Train Epoch: 35 [9600/32087 (30%)] Loss: 0.570760 +2025-04-14 12:42:06,233 INFO Train Epoch: 35 [12800/32087 (40%)] Loss: 0.649650 +2025-04-14 12:42:25,431 INFO Train Epoch: 35 [16000/32087 (50%)] Loss: 0.576978 +2025-04-14 12:42:44,897 INFO Train Epoch: 35 [19200/32087 (60%)] Loss: 0.641886 +2025-04-14 12:43:03,786 INFO Train Epoch: 35 [22400/32087 (70%)] Loss: 0.401278 +2025-04-14 12:43:22,481 INFO Train Epoch: 35 [25600/32087 (80%)] Loss: 0.455318 +2025-04-14 12:43:39,522 INFO Train Epoch: 35 [28800/32087 (90%)] Loss: 0.701826 +2025-04-14 12:43:57,503 INFO Train Epoch: 35 [32000/32087 (100%)] Loss: 0.715330 +2025-04-14 12:45:33,211 INFO Accuracy qa: 70.47 % +2025-04-14 12:45:37,761 INFO Train Epoch: 36 [0/32087 (0%)] Loss: 0.671124 +2025-04-14 12:45:53,163 INFO Train Epoch: 36 [3200/32087 (10%)] Loss: 0.671814 +2025-04-14 12:46:09,508 INFO Train Epoch: 36 [6400/32087 (20%)] Loss: 0.566698 +2025-04-14 12:46:25,154 INFO Train Epoch: 36 [9600/32087 (30%)] Loss: 0.650708 +2025-04-14 12:46:42,688 INFO Train Epoch: 36 [12800/32087 (40%)] Loss: 0.615676 +2025-04-14 12:47:01,428 INFO Train Epoch: 36 [16000/32087 (50%)] Loss: 0.621896 +2025-04-14 12:47:21,645 INFO Train Epoch: 36 [19200/32087 (60%)] Loss: 0.582328 +2025-04-14 12:47:41,498 INFO Train Epoch: 36 [22400/32087 (70%)] Loss: 0.493384 +2025-04-14 12:48:00,272 INFO Train Epoch: 36 [25600/32087 (80%)] Loss: 0.629357 +2025-04-14 12:48:20,055 INFO Train Epoch: 36 [28800/32087 (90%)] Loss: 0.651993 +2025-04-14 12:48:38,930 INFO Train Epoch: 36 [32000/32087 (100%)] Loss: 0.637720 +2025-04-14 12:50:09,457 INFO Accuracy qa: 70.49 % +2025-04-14 12:50:12,845 INFO Train Epoch: 37 [0/32087 (0%)] Loss: 0.504390 +2025-04-14 12:50:28,876 INFO Train Epoch: 37 [3200/32087 (10%)] Loss: 0.614401 +2025-04-14 12:50:44,706 INFO Train Epoch: 37 [6400/32087 (20%)] Loss: 0.585555 +2025-04-14 12:50:59,910 INFO Train Epoch: 37 [9600/32087 (30%)] Loss: 0.571244 +2025-04-14 12:51:17,877 INFO Train Epoch: 37 [12800/32087 (40%)] Loss: 0.623942 +2025-04-14 12:51:36,430 INFO Train Epoch: 37 [16000/32087 (50%)] Loss: 0.560291 +2025-04-14 12:51:56,001 INFO Train Epoch: 37 [19200/32087 (60%)] Loss: 0.732702 +2025-04-14 12:52:16,363 INFO Train Epoch: 37 [22400/32087 (70%)] Loss: 0.611534 +2025-04-14 12:52:36,373 INFO Train Epoch: 37 [25600/32087 (80%)] Loss: 0.494228 +2025-04-14 12:52:56,087 INFO Train Epoch: 37 [28800/32087 (90%)] Loss: 0.679501 +2025-04-14 12:53:15,122 INFO Train Epoch: 37 [32000/32087 (100%)] Loss: 0.588303 +2025-04-14 12:54:44,223 INFO Accuracy qa: 70.40 % +2025-04-14 12:54:48,257 INFO Train Epoch: 38 [0/32087 (0%)] Loss: 0.569972 +2025-04-14 12:55:03,125 INFO Train Epoch: 38 [3200/32087 (10%)] Loss: 0.548935 +2025-04-14 12:55:18,716 INFO Train Epoch: 38 [6400/32087 (20%)] Loss: 0.751212 +2025-04-14 12:55:34,458 INFO Train Epoch: 38 [9600/32087 (30%)] Loss: 0.546876 +2025-04-14 12:55:51,843 INFO Train Epoch: 38 [12800/32087 (40%)] Loss: 0.526685 +2025-04-14 12:56:12,098 INFO Train Epoch: 38 [16000/32087 (50%)] Loss: 0.550819 +2025-04-14 12:56:32,095 INFO Train Epoch: 38 [19200/32087 (60%)] Loss: 0.589054 +2025-04-14 12:56:51,434 INFO Train Epoch: 38 [22400/32087 (70%)] Loss: 0.594773 +2025-04-14 12:57:10,422 INFO Train Epoch: 38 [25600/32087 (80%)] Loss: 0.649792 +2025-04-14 12:57:29,005 INFO Train Epoch: 38 [28800/32087 (90%)] Loss: 0.567993 +2025-04-14 12:57:46,666 INFO Train Epoch: 38 [32000/32087 (100%)] Loss: 0.805216 +2025-04-14 12:59:17,163 INFO Accuracy qa: 70.47 % +2025-04-14 12:59:20,084 INFO Train Epoch: 39 [0/32087 (0%)] Loss: 0.666845 +2025-04-14 12:59:35,807 INFO Train Epoch: 39 [3200/32087 (10%)] Loss: 0.490193 +2025-04-14 12:59:51,911 INFO Train Epoch: 39 [6400/32087 (20%)] Loss: 0.546001 +2025-04-14 13:00:07,505 INFO Train Epoch: 39 [9600/32087 (30%)] Loss: 0.545262 +2025-04-14 13:00:25,338 INFO Train Epoch: 39 [12800/32087 (40%)] Loss: 0.630686 +2025-04-14 13:00:45,268 INFO Train Epoch: 39 [16000/32087 (50%)] Loss: 0.571589 +2025-04-14 13:01:04,812 INFO Train Epoch: 39 [19200/32087 (60%)] Loss: 0.578460 +2025-04-14 13:01:25,304 INFO Train Epoch: 39 [22400/32087 (70%)] Loss: 0.636516 +2025-04-14 13:01:44,271 INFO Train Epoch: 39 [25600/32087 (80%)] Loss: 0.692069 +2025-04-14 13:02:04,548 INFO Train Epoch: 39 [28800/32087 (90%)] Loss: 0.709365 +2025-04-14 13:02:22,964 INFO Train Epoch: 39 [32000/32087 (100%)] Loss: 0.611997 +2025-04-14 13:03:52,357 INFO Accuracy qa: 70.36 % +2025-04-14 13:03:56,699 INFO Train Epoch: 40 [0/32087 (0%)] Loss: 0.770646 +2025-04-14 13:04:13,824 INFO Train Epoch: 40 [3200/32087 (10%)] Loss: 0.598250 +2025-04-14 13:04:30,739 INFO Train Epoch: 40 [6400/32087 (20%)] Loss: 0.589789 +2025-04-14 13:04:47,684 INFO Train Epoch: 40 [9600/32087 (30%)] Loss: 0.597843 +2025-04-14 13:05:06,006 INFO Train Epoch: 40 [12800/32087 (40%)] Loss: 0.735591 +2025-04-14 13:05:24,008 INFO Train Epoch: 40 [16000/32087 (50%)] Loss: 0.671062 +2025-04-14 13:05:42,872 INFO Train Epoch: 40 [19200/32087 (60%)] Loss: 0.667658 +2025-04-14 13:06:01,520 INFO Train Epoch: 40 [22400/32087 (70%)] Loss: 0.571575 +2025-04-14 13:06:20,947 INFO Train Epoch: 40 [25600/32087 (80%)] Loss: 0.672325 +2025-04-14 13:06:39,359 INFO Train Epoch: 40 [28800/32087 (90%)] Loss: 0.634427 +2025-04-14 13:06:56,940 INFO Train Epoch: 40 [32000/32087 (100%)] Loss: 0.583131 +2025-04-14 13:08:26,053 INFO Accuracy qa: 70.69 % +2025-04-14 13:08:29,934 INFO Train Epoch: 41 [0/32087 (0%)] Loss: 0.725945 +2025-04-14 13:08:46,768 INFO Train Epoch: 41 [3200/32087 (10%)] Loss: 0.689241 +2025-04-14 13:09:03,448 INFO Train Epoch: 41 [6400/32087 (20%)] Loss: 0.658277 +2025-04-14 13:09:20,270 INFO Train Epoch: 41 [9600/32087 (30%)] Loss: 0.653906 +2025-04-14 13:09:37,623 INFO Train Epoch: 41 [12800/32087 (40%)] Loss: 0.615870 +2025-04-14 13:09:57,377 INFO Train Epoch: 41 [16000/32087 (50%)] Loss: 0.551505 +2025-04-14 13:10:16,860 INFO Train Epoch: 41 [19200/32087 (60%)] Loss: 0.535303 +2025-04-14 13:10:35,246 INFO Train Epoch: 41 [22400/32087 (70%)] Loss: 0.601657 +2025-04-14 13:10:53,908 INFO Train Epoch: 41 [25600/32087 (80%)] Loss: 0.666090 +2025-04-14 13:11:12,357 INFO Train Epoch: 41 [28800/32087 (90%)] Loss: 0.470653 +2025-04-14 13:11:29,801 INFO Train Epoch: 41 [32000/32087 (100%)] Loss: 0.508245 +2025-04-14 13:12:59,632 INFO Accuracy qa: 70.27 % +2025-04-14 13:13:04,076 INFO Train Epoch: 42 [0/32087 (0%)] Loss: 0.833985 +2025-04-14 13:13:20,066 INFO Train Epoch: 42 [3200/32087 (10%)] Loss: 0.796926 +2025-04-14 13:13:37,297 INFO Train Epoch: 42 [6400/32087 (20%)] Loss: 0.647254 +2025-04-14 13:13:54,054 INFO Train Epoch: 42 [9600/32087 (30%)] Loss: 0.582396 +2025-04-14 13:14:11,335 INFO Train Epoch: 42 [12800/32087 (40%)] Loss: 0.609601 +2025-04-14 13:14:28,004 INFO Train Epoch: 42 [16000/32087 (50%)] Loss: 0.613414 +2025-04-14 13:14:46,026 INFO Train Epoch: 42 [19200/32087 (60%)] Loss: 0.688948 +2025-04-14 13:15:04,583 INFO Train Epoch: 42 [22400/32087 (70%)] Loss: 0.461452 +2025-04-14 13:15:22,764 INFO Train Epoch: 42 [25600/32087 (80%)] Loss: 0.548741 +2025-04-14 13:15:40,263 INFO Train Epoch: 42 [28800/32087 (90%)] Loss: 0.620726 +2025-04-14 13:15:56,500 INFO Train Epoch: 42 [32000/32087 (100%)] Loss: 0.514604 +2025-04-14 13:17:24,898 INFO Accuracy qa: 70.60 % +2025-04-14 13:17:28,237 INFO Train Epoch: 43 [0/32087 (0%)] Loss: 0.517429 +2025-04-14 13:17:45,376 INFO Train Epoch: 43 [3200/32087 (10%)] Loss: 0.733209 +2025-04-14 13:18:02,035 INFO Train Epoch: 43 [6400/32087 (20%)] Loss: 0.631120 +2025-04-14 13:18:19,434 INFO Train Epoch: 43 [9600/32087 (30%)] Loss: 0.671074 +2025-04-14 13:18:37,698 INFO Train Epoch: 43 [12800/32087 (40%)] Loss: 0.554599 +2025-04-14 13:18:58,998 INFO Train Epoch: 43 [16000/32087 (50%)] Loss: 0.568469 +2025-04-14 13:19:18,680 INFO Train Epoch: 43 [19200/32087 (60%)] Loss: 0.579233 +2025-04-14 13:19:37,568 INFO Train Epoch: 43 [22400/32087 (70%)] Loss: 0.552572 +2025-04-14 13:19:56,406 INFO Train Epoch: 43 [25600/32087 (80%)] Loss: 0.674037 +2025-04-14 13:20:13,618 INFO Train Epoch: 43 [28800/32087 (90%)] Loss: 0.823370 +2025-04-14 13:20:29,464 INFO Train Epoch: 43 [32000/32087 (100%)] Loss: 0.609993 +2025-04-14 13:22:06,926 INFO Accuracy qa: 70.58 % +2025-04-14 13:22:11,082 INFO Train Epoch: 44 [0/32087 (0%)] Loss: 0.644415 +2025-04-14 13:22:29,741 INFO Train Epoch: 44 [3200/32087 (10%)] Loss: 0.804528 +2025-04-14 13:22:47,372 INFO Train Epoch: 44 [6400/32087 (20%)] Loss: 0.569654 +2025-04-14 13:23:05,128 INFO Train Epoch: 44 [9600/32087 (30%)] Loss: 0.504941 +2025-04-14 13:23:24,641 INFO Train Epoch: 44 [12800/32087 (40%)] Loss: 0.781437 +2025-04-14 13:23:43,572 INFO Train Epoch: 44 [16000/32087 (50%)] Loss: 0.720274 +2025-04-14 13:24:01,599 INFO Train Epoch: 44 [19200/32087 (60%)] Loss: 0.554746 +2025-04-14 13:24:18,719 INFO Train Epoch: 44 [22400/32087 (70%)] Loss: 0.801921 +2025-04-14 13:24:34,578 INFO Train Epoch: 44 [25600/32087 (80%)] Loss: 0.791838 +2025-04-14 13:24:50,389 INFO Train Epoch: 44 [28800/32087 (90%)] Loss: 0.626259 +2025-04-14 13:25:07,415 INFO Train Epoch: 44 [32000/32087 (100%)] Loss: 0.468935 +2025-04-14 13:26:39,308 INFO Accuracy qa: 70.58 % +2025-04-14 13:26:42,394 INFO Train Epoch: 45 [0/32087 (0%)] Loss: 0.606106 +2025-04-14 13:26:59,474 INFO Train Epoch: 45 [3200/32087 (10%)] Loss: 0.479094 +2025-04-14 13:27:15,591 INFO Train Epoch: 45 [6400/32087 (20%)] Loss: 0.640076 +2025-04-14 13:27:31,434 INFO Train Epoch: 45 [9600/32087 (30%)] Loss: 0.561473 +2025-04-14 13:27:51,343 INFO Train Epoch: 45 [12800/32087 (40%)] Loss: 0.512133 +2025-04-14 13:28:12,540 INFO Train Epoch: 45 [16000/32087 (50%)] Loss: 0.488609 +2025-04-14 13:28:29,759 INFO Train Epoch: 45 [19200/32087 (60%)] Loss: 0.694838 +2025-04-14 13:28:46,913 INFO Train Epoch: 45 [22400/32087 (70%)] Loss: 0.434174 +2025-04-14 13:29:03,572 INFO Train Epoch: 45 [25600/32087 (80%)] Loss: 0.505881 +2025-04-14 13:29:20,209 INFO Train Epoch: 45 [28800/32087 (90%)] Loss: 0.582464 +2025-04-14 13:29:37,802 INFO Train Epoch: 45 [32000/32087 (100%)] Loss: 0.544024 +2025-04-14 13:31:07,231 INFO Accuracy qa: 70.38 % +2025-04-14 13:31:11,105 INFO Train Epoch: 46 [0/32087 (0%)] Loss: 0.614903 +2025-04-14 13:31:26,384 INFO Train Epoch: 46 [3200/32087 (10%)] Loss: 0.622701 +2025-04-14 13:31:41,340 INFO Train Epoch: 46 [6400/32087 (20%)] Loss: 0.517651 +2025-04-14 13:31:56,164 INFO Train Epoch: 46 [9600/32087 (30%)] Loss: 0.687751 +2025-04-14 13:32:13,914 INFO Train Epoch: 46 [12800/32087 (40%)] Loss: 0.653728 +2025-04-14 13:32:31,236 INFO Train Epoch: 46 [16000/32087 (50%)] Loss: 0.653967 +2025-04-14 13:32:49,276 INFO Train Epoch: 46 [19200/32087 (60%)] Loss: 0.672709 +2025-04-14 13:33:07,522 INFO Train Epoch: 46 [22400/32087 (70%)] Loss: 0.595597 +2025-04-14 13:33:24,537 INFO Train Epoch: 46 [25600/32087 (80%)] Loss: 0.679047 +2025-04-14 13:33:41,911 INFO Train Epoch: 46 [28800/32087 (90%)] Loss: 0.783363 +2025-04-14 13:34:00,120 INFO Train Epoch: 46 [32000/32087 (100%)] Loss: 0.616173 +2025-04-14 13:35:28,852 INFO Accuracy qa: 70.34 % +2025-04-14 13:35:33,131 INFO Train Epoch: 47 [0/32087 (0%)] Loss: 0.636465 +2025-04-14 13:35:48,678 INFO Train Epoch: 47 [3200/32087 (10%)] Loss: 0.487795 +2025-04-14 13:36:04,730 INFO Train Epoch: 47 [6400/32087 (20%)] Loss: 0.764841 +2025-04-14 13:36:20,349 INFO Train Epoch: 47 [9600/32087 (30%)] Loss: 0.502017 +2025-04-14 13:36:36,713 INFO Train Epoch: 47 [12800/32087 (40%)] Loss: 0.630572 +2025-04-14 13:36:56,536 INFO Train Epoch: 47 [16000/32087 (50%)] Loss: 0.571741 +2025-04-14 13:37:13,607 INFO Train Epoch: 47 [19200/32087 (60%)] Loss: 0.598454 +2025-04-14 13:37:31,349 INFO Train Epoch: 47 [22400/32087 (70%)] Loss: 0.721337 +2025-04-14 13:37:48,376 INFO Train Epoch: 47 [25600/32087 (80%)] Loss: 0.609825 +2025-04-14 13:38:05,206 INFO Train Epoch: 47 [28800/32087 (90%)] Loss: 0.506734 +2025-04-14 13:38:22,269 INFO Train Epoch: 47 [32000/32087 (100%)] Loss: 0.599637 +2025-04-14 13:40:09,649 INFO Accuracy qa: 70.51 % +2025-04-14 13:40:12,936 INFO Train Epoch: 48 [0/32087 (0%)] Loss: 0.538905 +2025-04-14 13:40:29,564 INFO Train Epoch: 48 [3200/32087 (10%)] Loss: 0.760191 +2025-04-14 13:40:46,482 INFO Train Epoch: 48 [6400/32087 (20%)] Loss: 0.761594 +2025-04-14 13:41:02,713 INFO Train Epoch: 48 [9600/32087 (30%)] Loss: 0.593554 +2025-04-14 13:41:21,076 INFO Train Epoch: 48 [12800/32087 (40%)] Loss: 0.529282 +2025-04-14 13:41:38,373 INFO Train Epoch: 48 [16000/32087 (50%)] Loss: 0.560355 +2025-04-14 13:41:56,658 INFO Train Epoch: 48 [19200/32087 (60%)] Loss: 0.569702 +2025-04-14 13:42:13,657 INFO Train Epoch: 48 [22400/32087 (70%)] Loss: 0.551639 +2025-04-14 13:42:30,205 INFO Train Epoch: 48 [25600/32087 (80%)] Loss: 0.703420 +2025-04-14 13:42:48,598 INFO Train Epoch: 48 [28800/32087 (90%)] Loss: 0.588438 +2025-04-14 13:43:05,147 INFO Train Epoch: 48 [32000/32087 (100%)] Loss: 0.493890 +2025-04-14 13:44:40,310 INFO Accuracy qa: 70.45 % +2025-04-14 13:44:43,624 INFO Train Epoch: 49 [0/32087 (0%)] Loss: 0.577436 +2025-04-14 13:45:01,979 INFO Train Epoch: 49 [3200/32087 (10%)] Loss: 0.565174 +2025-04-14 13:45:18,855 INFO Train Epoch: 49 [6400/32087 (20%)] Loss: 0.605179 +2025-04-14 13:45:37,662 INFO Train Epoch: 49 [9600/32087 (30%)] Loss: 0.599188 +2025-04-14 13:45:55,604 INFO Train Epoch: 49 [12800/32087 (40%)] Loss: 0.448801 +2025-04-14 13:46:14,136 INFO Train Epoch: 49 [16000/32087 (50%)] Loss: 0.643802 +2025-04-14 13:46:32,821 INFO Train Epoch: 49 [19200/32087 (60%)] Loss: 0.597036 +2025-04-14 13:46:50,517 INFO Train Epoch: 49 [22400/32087 (70%)] Loss: 0.619440 +2025-04-14 13:47:10,190 INFO Train Epoch: 49 [25600/32087 (80%)] Loss: 0.583770 +2025-04-14 13:47:28,422 INFO Train Epoch: 49 [28800/32087 (90%)] Loss: 0.515052 +2025-04-14 13:47:45,468 INFO Train Epoch: 49 [32000/32087 (100%)] Loss: 0.635886 +2025-04-14 13:49:11,796 INFO Accuracy qa: 70.40 % +2025-04-14 13:49:16,539 INFO Train Epoch: 50 [0/32087 (0%)] Loss: 0.753554 +2025-04-14 13:49:31,845 INFO Train Epoch: 50 [3200/32087 (10%)] Loss: 0.595807 +2025-04-14 13:49:46,908 INFO Train Epoch: 50 [6400/32087 (20%)] Loss: 0.591684 +2025-04-14 13:50:02,157 INFO Train Epoch: 50 [9600/32087 (30%)] Loss: 0.576970 +2025-04-14 13:50:18,918 INFO Train Epoch: 50 [12800/32087 (40%)] Loss: 0.594030 +2025-04-14 13:50:35,924 INFO Train Epoch: 50 [16000/32087 (50%)] Loss: 0.489519 +2025-04-14 13:50:51,988 INFO Train Epoch: 50 [19200/32087 (60%)] Loss: 0.667313 +2025-04-14 13:51:07,992 INFO Train Epoch: 50 [22400/32087 (70%)] Loss: 0.657564 +2025-04-14 13:51:24,388 INFO Train Epoch: 50 [25600/32087 (80%)] Loss: 0.552114 +2025-04-14 13:51:41,964 INFO Train Epoch: 50 [28800/32087 (90%)] Loss: 0.512513 +2025-04-14 13:51:56,983 INFO Train Epoch: 50 [32000/32087 (100%)] Loss: 0.594433 +2025-04-14 13:53:23,985 INFO Accuracy qa: 70.45 % diff --git a/Audio Visual Question Answering/results/inverse_True_withmodified/avst.pt b/Audio Visual Question Answering/results/inverse_True_withmodified/avst.pt new file mode 100644 index 0000000000000000000000000000000000000000..7aba0e3dee495907b12b46c9c0281e7711a63b60 --- /dev/null +++ b/Audio Visual Question Answering/results/inverse_True_withmodified/avst.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bf69dcad5d61f8a3aab101c6a6433f5797910c88663a567b09ce50e648fa572 +size 89479183 diff --git a/Audio Visual Question Answering/results/inverse_True_withmodified/test.log b/Audio Visual Question Answering/results/inverse_True_withmodified/test.log new file mode 100644 index 0000000000000000000000000000000000000000..4db0828704dfb7dc7c123d5870f81c921d0b2745 --- /dev/null +++ b/Audio Visual Question Answering/results/inverse_True_withmodified/test.log @@ -0,0 +1,4 @@ +2025-04-15 06:43:06,301 INFO +--------------- Audio-Visual Spatial-Temporal Model --------------- + +2025-04-15 06:43:10,904 INFO 9185 diff --git a/Audio Visual Question Answering/results/inverse_True_withmodified/train.log b/Audio Visual Question Answering/results/inverse_True_withmodified/train.log new file mode 100644 index 0000000000000000000000000000000000000000..be97cc4d6011d1a00da2a56248c959c5e9344944 --- /dev/null +++ b/Audio Visual Question Answering/results/inverse_True_withmodified/train.log @@ -0,0 +1,607 @@ +2025-04-14 10:06:17,566 INFO +--------------- Audio-Visual Spatial-Temporal Model --------------- + +2025-04-14 10:06:24,410 INFO +-------------- loading pretrained models -------------- +2025-04-14 10:06:24,415 INFO +-------------- load pretrained models -------------- +2025-04-14 10:06:32,038 INFO Train Epoch: 1 [0/32087 (0%)] Loss: 11.622032 +2025-04-14 10:06:46,544 INFO Train Epoch: 1 [3200/32087 (10%)] Loss: 7.966428 +2025-04-14 10:07:00,529 INFO Train Epoch: 1 [6400/32087 (20%)] Loss: 6.332827 +2025-04-14 10:07:14,590 INFO Train Epoch: 1 [9600/32087 (30%)] Loss: 5.580876 +2025-04-14 10:07:28,575 INFO Train Epoch: 1 [12800/32087 (40%)] Loss: 4.635996 +2025-04-14 10:07:42,857 INFO Train Epoch: 1 [16000/32087 (50%)] Loss: 3.975565 +2025-04-14 10:07:57,004 INFO Train Epoch: 1 [19200/32087 (60%)] Loss: 4.056083 +2025-04-14 10:08:11,027 INFO Train Epoch: 1 [22400/32087 (70%)] Loss: 3.318463 +2025-04-14 10:08:25,857 INFO Train Epoch: 1 [25600/32087 (80%)] Loss: 3.197511 +2025-04-14 10:08:40,742 INFO Train Epoch: 1 [28800/32087 (90%)] Loss: 3.266074 +2025-04-14 10:08:55,876 INFO Train Epoch: 1 [32000/32087 (100%)] Loss: 3.557267 +2025-04-14 10:10:25,402 INFO Accuracy qa: 55.32 % +2025-04-14 10:10:29,470 INFO Train Epoch: 2 [0/32087 (0%)] Loss: 3.477628 +2025-04-14 10:10:50,703 INFO Train Epoch: 2 [3200/32087 (10%)] Loss: 3.314546 +2025-04-14 10:11:10,059 INFO Train Epoch: 2 [6400/32087 (20%)] Loss: 3.108188 +2025-04-14 10:11:28,924 INFO Train Epoch: 2 [9600/32087 (30%)] Loss: 3.463416 +2025-04-14 10:11:46,134 INFO Train Epoch: 2 [12800/32087 (40%)] Loss: 3.565001 +2025-04-14 10:12:03,037 INFO Train Epoch: 2 [16000/32087 (50%)] Loss: 3.506854 +2025-04-14 10:12:20,559 INFO Train Epoch: 2 [19200/32087 (60%)] Loss: 3.158259 +2025-04-14 10:12:37,574 INFO Train Epoch: 2 [22400/32087 (70%)] Loss: 2.740549 +2025-04-14 10:12:55,235 INFO Train Epoch: 2 [25600/32087 (80%)] Loss: 3.144042 +2025-04-14 10:13:13,124 INFO Train Epoch: 2 [28800/32087 (90%)] Loss: 4.429707 +2025-04-14 10:13:29,640 INFO Train Epoch: 2 [32000/32087 (100%)] Loss: 2.840772 +2025-04-14 10:14:58,288 INFO Accuracy qa: 62.15 % +2025-04-14 10:15:02,431 INFO Train Epoch: 3 [0/32087 (0%)] Loss: 2.685157 +2025-04-14 10:15:21,973 INFO Train Epoch: 3 [3200/32087 (10%)] Loss: 3.044084 +2025-04-14 10:15:40,736 INFO Train Epoch: 3 [6400/32087 (20%)] Loss: 3.646609 +2025-04-14 10:15:58,216 INFO Train Epoch: 3 [9600/32087 (30%)] Loss: 3.844256 +2025-04-14 10:16:14,864 INFO Train Epoch: 3 [12800/32087 (40%)] Loss: 3.529740 +2025-04-14 10:16:31,372 INFO Train Epoch: 3 [16000/32087 (50%)] Loss: 3.081593 +2025-04-14 10:16:47,808 INFO Train Epoch: 3 [19200/32087 (60%)] Loss: 2.759088 +2025-04-14 10:17:04,994 INFO Train Epoch: 3 [22400/32087 (70%)] Loss: 3.291650 +2025-04-14 10:17:21,610 INFO Train Epoch: 3 [25600/32087 (80%)] Loss: 3.223434 +2025-04-14 10:17:41,078 INFO Train Epoch: 3 [28800/32087 (90%)] Loss: 2.551131 +2025-04-14 10:17:57,927 INFO Train Epoch: 3 [32000/32087 (100%)] Loss: 3.506468 +2025-04-14 10:19:31,747 INFO Accuracy qa: 64.05 % +2025-04-14 10:19:37,562 INFO Train Epoch: 4 [0/32087 (0%)] Loss: 2.962555 +2025-04-14 10:19:57,906 INFO Train Epoch: 4 [3200/32087 (10%)] Loss: 3.185978 +2025-04-14 10:20:17,371 INFO Train Epoch: 4 [6400/32087 (20%)] Loss: 3.411052 +2025-04-14 10:20:34,953 INFO Train Epoch: 4 [9600/32087 (30%)] Loss: 3.246892 +2025-04-14 10:20:51,704 INFO Train Epoch: 4 [12800/32087 (40%)] Loss: 3.515233 +2025-04-14 10:21:09,964 INFO Train Epoch: 4 [16000/32087 (50%)] Loss: 3.138257 +2025-04-14 10:21:26,071 INFO Train Epoch: 4 [19200/32087 (60%)] Loss: 2.586519 +2025-04-14 10:21:42,326 INFO Train Epoch: 4 [22400/32087 (70%)] Loss: 3.200024 +2025-04-14 10:21:59,846 INFO Train Epoch: 4 [25600/32087 (80%)] Loss: 2.983869 +2025-04-14 10:22:17,194 INFO Train Epoch: 4 [28800/32087 (90%)] Loss: 2.871090 +2025-04-14 10:22:34,155 INFO Train Epoch: 4 [32000/32087 (100%)] Loss: 2.867598 +2025-04-14 10:24:01,464 INFO Accuracy qa: 64.70 % +2025-04-14 10:24:07,277 INFO Train Epoch: 5 [0/32087 (0%)] Loss: 2.840456 +2025-04-14 10:24:26,260 INFO Train Epoch: 5 [3200/32087 (10%)] Loss: 2.985722 +2025-04-14 10:24:45,077 INFO Train Epoch: 5 [6400/32087 (20%)] Loss: 2.590330 +2025-04-14 10:25:03,125 INFO Train Epoch: 5 [9600/32087 (30%)] Loss: 2.227215 +2025-04-14 10:25:21,195 INFO Train Epoch: 5 [12800/32087 (40%)] Loss: 3.091302 +2025-04-14 10:25:39,265 INFO Train Epoch: 5 [16000/32087 (50%)] Loss: 2.933866 +2025-04-14 10:25:56,352 INFO Train Epoch: 5 [19200/32087 (60%)] Loss: 3.221560 +2025-04-14 10:26:13,924 INFO Train Epoch: 5 [22400/32087 (70%)] Loss: 3.228529 +2025-04-14 10:26:32,073 INFO Train Epoch: 5 [25600/32087 (80%)] Loss: 2.685740 +2025-04-14 10:26:49,373 INFO Train Epoch: 5 [28800/32087 (90%)] Loss: 2.555318 +2025-04-14 10:27:06,356 INFO Train Epoch: 5 [32000/32087 (100%)] Loss: 2.919191 +2025-04-14 10:28:39,443 INFO Accuracy qa: 64.50 % +2025-04-14 10:28:43,482 INFO Train Epoch: 6 [0/32087 (0%)] Loss: 2.829801 +2025-04-14 10:29:04,538 INFO Train Epoch: 6 [3200/32087 (10%)] Loss: 2.890512 +2025-04-14 10:29:22,653 INFO Train Epoch: 6 [6400/32087 (20%)] Loss: 2.591017 +2025-04-14 10:29:41,116 INFO Train Epoch: 6 [9600/32087 (30%)] Loss: 2.754190 +2025-04-14 10:29:59,464 INFO Train Epoch: 6 [12800/32087 (40%)] Loss: 2.564554 +2025-04-14 10:30:17,264 INFO Train Epoch: 6 [16000/32087 (50%)] Loss: 2.845523 +2025-04-14 10:30:34,046 INFO Train Epoch: 6 [19200/32087 (60%)] Loss: 3.072495 +2025-04-14 10:30:52,585 INFO Train Epoch: 6 [22400/32087 (70%)] Loss: 3.225845 +2025-04-14 10:31:11,118 INFO Train Epoch: 6 [25600/32087 (80%)] Loss: 2.853663 +2025-04-14 10:31:27,528 INFO Train Epoch: 6 [28800/32087 (90%)] Loss: 3.069110 +2025-04-14 10:31:43,311 INFO Train Epoch: 6 [32000/32087 (100%)] Loss: 2.587582 +2025-04-14 10:33:10,927 INFO Accuracy qa: 65.11 % +2025-04-14 10:33:14,855 INFO Train Epoch: 7 [0/32087 (0%)] Loss: 3.413678 +2025-04-14 10:33:32,399 INFO Train Epoch: 7 [3200/32087 (10%)] Loss: 3.099248 +2025-04-14 10:33:46,723 INFO Train Epoch: 7 [6400/32087 (20%)] Loss: 2.698033 +2025-04-14 10:34:01,070 INFO Train Epoch: 7 [9600/32087 (30%)] Loss: 2.545485 +2025-04-14 10:34:15,841 INFO Train Epoch: 7 [12800/32087 (40%)] Loss: 2.954640 +2025-04-14 10:34:30,139 INFO Train Epoch: 7 [16000/32087 (50%)] Loss: 3.133637 +2025-04-14 10:34:44,211 INFO Train Epoch: 7 [19200/32087 (60%)] Loss: 2.777117 +2025-04-14 10:34:58,365 INFO Train Epoch: 7 [22400/32087 (70%)] Loss: 2.718230 +2025-04-14 10:35:12,997 INFO Train Epoch: 7 [25600/32087 (80%)] Loss: 3.112862 +2025-04-14 10:35:28,371 INFO Train Epoch: 7 [28800/32087 (90%)] Loss: 3.244114 +2025-04-14 10:35:42,552 INFO Train Epoch: 7 [32000/32087 (100%)] Loss: 3.126182 +2025-04-14 10:37:11,814 INFO Accuracy qa: 66.72 % +2025-04-14 10:37:16,121 INFO Train Epoch: 8 [0/32087 (0%)] Loss: 2.831265 +2025-04-14 10:37:35,772 INFO Train Epoch: 8 [3200/32087 (10%)] Loss: 2.829079 +2025-04-14 10:37:56,123 INFO Train Epoch: 8 [6400/32087 (20%)] Loss: 2.866598 +2025-04-14 10:38:13,944 INFO Train Epoch: 8 [9600/32087 (30%)] Loss: 2.974777 +2025-04-14 10:38:31,470 INFO Train Epoch: 8 [12800/32087 (40%)] Loss: 3.203767 +2025-04-14 10:38:49,108 INFO Train Epoch: 8 [16000/32087 (50%)] Loss: 2.761611 +2025-04-14 10:39:06,756 INFO Train Epoch: 8 [19200/32087 (60%)] Loss: 2.889176 +2025-04-14 10:39:22,167 INFO Train Epoch: 8 [22400/32087 (70%)] Loss: 2.584340 +2025-04-14 10:39:36,790 INFO Train Epoch: 8 [25600/32087 (80%)] Loss: 2.702292 +2025-04-14 10:39:53,792 INFO Train Epoch: 8 [28800/32087 (90%)] Loss: 2.120554 +2025-04-14 10:40:09,953 INFO Train Epoch: 8 [32000/32087 (100%)] Loss: 3.115854 +2025-04-14 10:41:44,097 INFO Accuracy qa: 66.42 % +2025-04-14 10:41:49,359 INFO Train Epoch: 9 [0/32087 (0%)] Loss: 2.265199 +2025-04-14 10:42:07,297 INFO Train Epoch: 9 [3200/32087 (10%)] Loss: 2.089161 +2025-04-14 10:42:24,100 INFO Train Epoch: 9 [6400/32087 (20%)] Loss: 2.783784 +2025-04-14 10:42:40,266 INFO Train Epoch: 9 [9600/32087 (30%)] Loss: 2.377862 +2025-04-14 10:42:56,113 INFO Train Epoch: 9 [12800/32087 (40%)] Loss: 2.734105 +2025-04-14 10:43:11,488 INFO Train Epoch: 9 [16000/32087 (50%)] Loss: 2.839205 +2025-04-14 10:43:28,779 INFO Train Epoch: 9 [19200/32087 (60%)] Loss: 3.936194 +2025-04-14 10:43:47,365 INFO Train Epoch: 9 [22400/32087 (70%)] Loss: 2.574344 +2025-04-14 10:44:04,795 INFO Train Epoch: 9 [25600/32087 (80%)] Loss: 2.408782 +2025-04-14 10:44:22,794 INFO Train Epoch: 9 [28800/32087 (90%)] Loss: 2.211250 +2025-04-14 10:44:40,403 INFO Train Epoch: 9 [32000/32087 (100%)] Loss: 3.131675 +2025-04-14 10:46:11,092 INFO Accuracy qa: 68.99 % +2025-04-14 10:46:17,110 INFO Train Epoch: 10 [0/32087 (0%)] Loss: 3.025797 +2025-04-14 10:46:36,002 INFO Train Epoch: 10 [3200/32087 (10%)] Loss: 1.968566 +2025-04-14 10:46:52,717 INFO Train Epoch: 10 [6400/32087 (20%)] Loss: 2.676024 +2025-04-14 10:47:09,752 INFO Train Epoch: 10 [9600/32087 (30%)] Loss: 3.077680 +2025-04-14 10:47:26,590 INFO Train Epoch: 10 [12800/32087 (40%)] Loss: 2.048267 +2025-04-14 10:47:43,451 INFO Train Epoch: 10 [16000/32087 (50%)] Loss: 2.511981 +2025-04-14 10:48:00,266 INFO Train Epoch: 10 [19200/32087 (60%)] Loss: 2.977329 +2025-04-14 10:48:16,918 INFO Train Epoch: 10 [22400/32087 (70%)] Loss: 2.815621 +2025-04-14 10:48:33,806 INFO Train Epoch: 10 [25600/32087 (80%)] Loss: 2.811388 +2025-04-14 10:48:50,853 INFO Train Epoch: 10 [28800/32087 (90%)] Loss: 2.758240 +2025-04-14 10:49:08,240 INFO Train Epoch: 10 [32000/32087 (100%)] Loss: 2.215829 +2025-04-14 10:50:37,369 INFO Accuracy qa: 69.31 % +2025-04-14 10:50:42,464 INFO Train Epoch: 11 [0/32087 (0%)] Loss: 2.207309 +2025-04-14 10:50:59,847 INFO Train Epoch: 11 [3200/32087 (10%)] Loss: 2.827793 +2025-04-14 10:51:18,326 INFO Train Epoch: 11 [6400/32087 (20%)] Loss: 2.027507 +2025-04-14 10:51:36,972 INFO Train Epoch: 11 [9600/32087 (30%)] Loss: 2.434179 +2025-04-14 10:51:53,968 INFO Train Epoch: 11 [12800/32087 (40%)] Loss: 1.895043 +2025-04-14 10:52:11,037 INFO Train Epoch: 11 [16000/32087 (50%)] Loss: 2.250888 +2025-04-14 10:52:28,443 INFO Train Epoch: 11 [19200/32087 (60%)] Loss: 2.429385 +2025-04-14 10:52:45,879 INFO Train Epoch: 11 [22400/32087 (70%)] Loss: 2.883027 +2025-04-14 10:53:02,688 INFO Train Epoch: 11 [25600/32087 (80%)] Loss: 2.180327 +2025-04-14 10:53:21,217 INFO Train Epoch: 11 [28800/32087 (90%)] Loss: 2.958961 +2025-04-14 10:53:40,004 INFO Train Epoch: 11 [32000/32087 (100%)] Loss: 2.497451 +2025-04-14 10:55:13,944 INFO Accuracy qa: 69.21 % +2025-04-14 10:55:18,444 INFO Train Epoch: 12 [0/32087 (0%)] Loss: 2.302964 +2025-04-14 10:55:36,647 INFO Train Epoch: 12 [3200/32087 (10%)] Loss: 2.392228 +2025-04-14 10:55:54,685 INFO Train Epoch: 12 [6400/32087 (20%)] Loss: 2.686726 +2025-04-14 10:56:12,674 INFO Train Epoch: 12 [9600/32087 (30%)] Loss: 2.761632 +2025-04-14 10:56:29,107 INFO Train Epoch: 12 [12800/32087 (40%)] Loss: 2.086712 +2025-04-14 10:56:45,299 INFO Train Epoch: 12 [16000/32087 (50%)] Loss: 2.175323 +2025-04-14 10:57:02,018 INFO Train Epoch: 12 [19200/32087 (60%)] Loss: 2.954361 +2025-04-14 10:57:18,455 INFO Train Epoch: 12 [22400/32087 (70%)] Loss: 2.707184 +2025-04-14 10:57:34,462 INFO Train Epoch: 12 [25600/32087 (80%)] Loss: 2.631850 +2025-04-14 10:57:53,213 INFO Train Epoch: 12 [28800/32087 (90%)] Loss: 2.395146 +2025-04-14 10:58:12,014 INFO Train Epoch: 12 [32000/32087 (100%)] Loss: 2.907135 +2025-04-14 10:59:43,222 INFO Accuracy qa: 69.82 % +2025-04-14 10:59:48,576 INFO Train Epoch: 13 [0/32087 (0%)] Loss: 2.477448 +2025-04-14 11:00:06,242 INFO Train Epoch: 13 [3200/32087 (10%)] Loss: 2.367127 +2025-04-14 11:00:24,692 INFO Train Epoch: 13 [6400/32087 (20%)] Loss: 2.174496 +2025-04-14 11:00:45,128 INFO Train Epoch: 13 [9600/32087 (30%)] Loss: 2.401116 +2025-04-14 11:01:03,830 INFO Train Epoch: 13 [12800/32087 (40%)] Loss: 2.515582 +2025-04-14 11:01:23,175 INFO Train Epoch: 13 [16000/32087 (50%)] Loss: 3.019231 +2025-04-14 11:01:41,875 INFO Train Epoch: 13 [19200/32087 (60%)] Loss: 2.441416 +2025-04-14 11:02:00,675 INFO Train Epoch: 13 [22400/32087 (70%)] Loss: 2.395626 +2025-04-14 11:02:19,240 INFO Train Epoch: 13 [25600/32087 (80%)] Loss: 1.872776 +2025-04-14 11:02:40,391 INFO Train Epoch: 13 [28800/32087 (90%)] Loss: 2.201559 +2025-04-14 11:03:01,039 INFO Train Epoch: 13 [32000/32087 (100%)] Loss: 2.327441 +2025-04-14 11:04:31,477 INFO Accuracy qa: 68.73 % +2025-04-14 11:04:36,310 INFO Train Epoch: 14 [0/32087 (0%)] Loss: 1.941030 +2025-04-14 11:04:53,868 INFO Train Epoch: 14 [3200/32087 (10%)] Loss: 2.409496 +2025-04-14 11:05:10,238 INFO Train Epoch: 14 [6400/32087 (20%)] Loss: 1.997568 +2025-04-14 11:05:27,046 INFO Train Epoch: 14 [9600/32087 (30%)] Loss: 2.140587 +2025-04-14 11:05:43,607 INFO Train Epoch: 14 [12800/32087 (40%)] Loss: 2.216097 +2025-04-14 11:06:01,458 INFO Train Epoch: 14 [16000/32087 (50%)] Loss: 2.222232 +2025-04-14 11:06:19,025 INFO Train Epoch: 14 [19200/32087 (60%)] Loss: 2.626497 +2025-04-14 11:06:34,817 INFO Train Epoch: 14 [22400/32087 (70%)] Loss: 3.013608 +2025-04-14 11:06:51,154 INFO Train Epoch: 14 [25600/32087 (80%)] Loss: 2.410749 +2025-04-14 11:07:07,393 INFO Train Epoch: 14 [28800/32087 (90%)] Loss: 2.759787 +2025-04-14 11:07:23,470 INFO Train Epoch: 14 [32000/32087 (100%)] Loss: 2.470065 +2025-04-14 11:08:54,287 INFO Accuracy qa: 68.23 % +2025-04-14 11:08:57,216 INFO Train Epoch: 15 [0/32087 (0%)] Loss: 2.164044 +2025-04-14 11:09:14,998 INFO Train Epoch: 15 [3200/32087 (10%)] Loss: 2.309292 +2025-04-14 11:09:32,347 INFO Train Epoch: 15 [6400/32087 (20%)] Loss: 2.054269 +2025-04-14 11:09:48,481 INFO Train Epoch: 15 [9600/32087 (30%)] Loss: 1.413484 +2025-04-14 11:10:06,109 INFO Train Epoch: 15 [12800/32087 (40%)] Loss: 2.200803 +2025-04-14 11:10:24,219 INFO Train Epoch: 15 [16000/32087 (50%)] Loss: 2.349898 +2025-04-14 11:10:41,760 INFO Train Epoch: 15 [19200/32087 (60%)] Loss: 2.834600 +2025-04-14 11:10:58,683 INFO Train Epoch: 15 [22400/32087 (70%)] Loss: 2.130057 +2025-04-14 11:11:15,379 INFO Train Epoch: 15 [25600/32087 (80%)] Loss: 2.656871 +2025-04-14 11:11:32,626 INFO Train Epoch: 15 [28800/32087 (90%)] Loss: 2.033748 +2025-04-14 11:11:49,866 INFO Train Epoch: 15 [32000/32087 (100%)] Loss: 2.464082 +2025-04-14 11:13:23,462 INFO Accuracy qa: 69.01 % +2025-04-14 11:13:28,586 INFO Train Epoch: 16 [0/32087 (0%)] Loss: 2.730976 +2025-04-14 11:13:46,557 INFO Train Epoch: 16 [3200/32087 (10%)] Loss: 2.081473 +2025-04-14 11:14:04,590 INFO Train Epoch: 16 [6400/32087 (20%)] Loss: 2.365848 +2025-04-14 11:14:21,841 INFO Train Epoch: 16 [9600/32087 (30%)] Loss: 2.265525 +2025-04-14 11:14:39,901 INFO Train Epoch: 16 [12800/32087 (40%)] Loss: 2.060698 +2025-04-14 11:14:57,071 INFO Train Epoch: 16 [16000/32087 (50%)] Loss: 2.007576 +2025-04-14 11:15:13,513 INFO Train Epoch: 16 [19200/32087 (60%)] Loss: 2.016070 +2025-04-14 11:15:29,172 INFO Train Epoch: 16 [22400/32087 (70%)] Loss: 1.634279 +2025-04-14 11:15:45,043 INFO Train Epoch: 16 [25600/32087 (80%)] Loss: 1.868987 +2025-04-14 11:16:01,510 INFO Train Epoch: 16 [28800/32087 (90%)] Loss: 1.808773 +2025-04-14 11:16:17,630 INFO Train Epoch: 16 [32000/32087 (100%)] Loss: 2.039295 +2025-04-14 11:17:51,269 INFO Accuracy qa: 71.49 % +2025-04-14 11:17:58,132 INFO Train Epoch: 17 [0/32087 (0%)] Loss: 2.186904 +2025-04-14 11:18:16,214 INFO Train Epoch: 17 [3200/32087 (10%)] Loss: 1.528638 +2025-04-14 11:18:33,881 INFO Train Epoch: 17 [6400/32087 (20%)] Loss: 2.274944 +2025-04-14 11:18:51,147 INFO Train Epoch: 17 [9600/32087 (30%)] Loss: 2.496756 +2025-04-14 11:19:07,528 INFO Train Epoch: 17 [12800/32087 (40%)] Loss: 2.012082 +2025-04-14 11:19:25,186 INFO Train Epoch: 17 [16000/32087 (50%)] Loss: 2.307909 +2025-04-14 11:19:42,060 INFO Train Epoch: 17 [19200/32087 (60%)] Loss: 1.757384 +2025-04-14 11:19:57,862 INFO Train Epoch: 17 [22400/32087 (70%)] Loss: 1.853231 +2025-04-14 11:20:13,308 INFO Train Epoch: 17 [25600/32087 (80%)] Loss: 1.910951 +2025-04-14 11:20:29,979 INFO Train Epoch: 17 [28800/32087 (90%)] Loss: 1.871676 +2025-04-14 11:20:45,720 INFO Train Epoch: 17 [32000/32087 (100%)] Loss: 2.104828 +2025-04-14 11:22:20,191 INFO Accuracy qa: 72.08 % +2025-04-14 11:22:24,080 INFO Train Epoch: 18 [0/32087 (0%)] Loss: 1.804527 +2025-04-14 11:22:42,194 INFO Train Epoch: 18 [3200/32087 (10%)] Loss: 1.952787 +2025-04-14 11:22:58,848 INFO Train Epoch: 18 [6400/32087 (20%)] Loss: 1.753386 +2025-04-14 11:23:15,278 INFO Train Epoch: 18 [9600/32087 (30%)] Loss: 2.451707 +2025-04-14 11:23:32,573 INFO Train Epoch: 18 [12800/32087 (40%)] Loss: 2.271036 +2025-04-14 11:23:50,507 INFO Train Epoch: 18 [16000/32087 (50%)] Loss: 2.043059 +2025-04-14 11:24:09,301 INFO Train Epoch: 18 [19200/32087 (60%)] Loss: 1.914523 +2025-04-14 11:24:25,188 INFO Train Epoch: 18 [22400/32087 (70%)] Loss: 2.054035 +2025-04-14 11:24:41,254 INFO Train Epoch: 18 [25600/32087 (80%)] Loss: 1.625604 +2025-04-14 11:24:57,433 INFO Train Epoch: 18 [28800/32087 (90%)] Loss: 1.881041 +2025-04-14 11:25:13,634 INFO Train Epoch: 18 [32000/32087 (100%)] Loss: 1.600718 +2025-04-14 11:26:48,450 INFO Accuracy qa: 71.66 % +2025-04-14 11:26:51,881 INFO Train Epoch: 19 [0/32087 (0%)] Loss: 1.811388 +2025-04-14 11:27:10,104 INFO Train Epoch: 19 [3200/32087 (10%)] Loss: 2.188547 +2025-04-14 11:27:26,833 INFO Train Epoch: 19 [6400/32087 (20%)] Loss: 1.925654 +2025-04-14 11:27:45,122 INFO Train Epoch: 19 [9600/32087 (30%)] Loss: 1.958713 +2025-04-14 11:28:03,204 INFO Train Epoch: 19 [12800/32087 (40%)] Loss: 2.221881 +2025-04-14 11:28:22,650 INFO Train Epoch: 19 [16000/32087 (50%)] Loss: 1.836220 +2025-04-14 11:28:41,526 INFO Train Epoch: 19 [19200/32087 (60%)] Loss: 1.724134 +2025-04-14 11:28:58,573 INFO Train Epoch: 19 [22400/32087 (70%)] Loss: 1.541091 +2025-04-14 11:29:14,925 INFO Train Epoch: 19 [25600/32087 (80%)] Loss: 2.052123 +2025-04-14 11:29:32,428 INFO Train Epoch: 19 [28800/32087 (90%)] Loss: 1.889899 +2025-04-14 11:29:49,402 INFO Train Epoch: 19 [32000/32087 (100%)] Loss: 1.810888 +2025-04-14 11:31:21,301 INFO Accuracy qa: 71.45 % +2025-04-14 11:31:25,038 INFO Train Epoch: 20 [0/32087 (0%)] Loss: 1.929562 +2025-04-14 11:31:43,038 INFO Train Epoch: 20 [3200/32087 (10%)] Loss: 1.605948 +2025-04-14 11:32:01,432 INFO Train Epoch: 20 [6400/32087 (20%)] Loss: 1.658590 +2025-04-14 11:32:18,345 INFO Train Epoch: 20 [9600/32087 (30%)] Loss: 2.013834 +2025-04-14 11:32:35,540 INFO Train Epoch: 20 [12800/32087 (40%)] Loss: 1.771504 +2025-04-14 11:32:53,695 INFO Train Epoch: 20 [16000/32087 (50%)] Loss: 2.270359 +2025-04-14 11:33:11,696 INFO Train Epoch: 20 [19200/32087 (60%)] Loss: 2.329185 +2025-04-14 11:33:29,254 INFO Train Epoch: 20 [22400/32087 (70%)] Loss: 2.286540 +2025-04-14 11:33:44,587 INFO Train Epoch: 20 [25600/32087 (80%)] Loss: 2.022787 +2025-04-14 11:34:01,109 INFO Train Epoch: 20 [28800/32087 (90%)] Loss: 1.980272 +2025-04-14 11:34:16,884 INFO Train Epoch: 20 [32000/32087 (100%)] Loss: 2.285983 +2025-04-14 11:35:47,394 INFO Accuracy qa: 71.51 % +2025-04-14 11:35:50,771 INFO Train Epoch: 21 [0/32087 (0%)] Loss: 1.643615 +2025-04-14 11:36:08,344 INFO Train Epoch: 21 [3200/32087 (10%)] Loss: 1.477320 +2025-04-14 11:36:25,580 INFO Train Epoch: 21 [6400/32087 (20%)] Loss: 1.968338 +2025-04-14 11:36:42,162 INFO Train Epoch: 21 [9600/32087 (30%)] Loss: 2.040718 +2025-04-14 11:36:57,930 INFO Train Epoch: 21 [12800/32087 (40%)] Loss: 1.988221 +2025-04-14 11:37:14,431 INFO Train Epoch: 21 [16000/32087 (50%)] Loss: 2.060714 +2025-04-14 11:37:29,975 INFO Train Epoch: 21 [19200/32087 (60%)] Loss: 1.762852 +2025-04-14 11:37:45,714 INFO Train Epoch: 21 [22400/32087 (70%)] Loss: 1.799708 +2025-04-14 11:38:01,980 INFO Train Epoch: 21 [25600/32087 (80%)] Loss: 1.849004 +2025-04-14 11:38:16,767 INFO Train Epoch: 21 [28800/32087 (90%)] Loss: 2.547897 +2025-04-14 11:38:30,785 INFO Train Epoch: 21 [32000/32087 (100%)] Loss: 2.147758 +2025-04-14 11:39:59,180 INFO Accuracy qa: 71.53 % +2025-04-14 11:40:04,500 INFO Train Epoch: 22 [0/32087 (0%)] Loss: 2.011289 +2025-04-14 11:40:23,178 INFO Train Epoch: 22 [3200/32087 (10%)] Loss: 2.053767 +2025-04-14 11:40:41,943 INFO Train Epoch: 22 [6400/32087 (20%)] Loss: 1.880548 +2025-04-14 11:41:00,933 INFO Train Epoch: 22 [9600/32087 (30%)] Loss: 1.543042 +2025-04-14 11:41:18,883 INFO Train Epoch: 22 [12800/32087 (40%)] Loss: 2.226666 +2025-04-14 11:41:36,548 INFO Train Epoch: 22 [16000/32087 (50%)] Loss: 1.588046 +2025-04-14 11:41:54,421 INFO Train Epoch: 22 [19200/32087 (60%)] Loss: 1.784705 +2025-04-14 11:42:11,777 INFO Train Epoch: 22 [22400/32087 (70%)] Loss: 2.218812 +2025-04-14 11:42:29,548 INFO Train Epoch: 22 [25600/32087 (80%)] Loss: 1.949282 +2025-04-14 11:42:47,371 INFO Train Epoch: 22 [28800/32087 (90%)] Loss: 1.845441 +2025-04-14 11:43:04,104 INFO Train Epoch: 22 [32000/32087 (100%)] Loss: 1.819900 +2025-04-14 11:44:35,335 INFO Accuracy qa: 71.75 % +2025-04-14 11:44:40,732 INFO Train Epoch: 23 [0/32087 (0%)] Loss: 1.980146 +2025-04-14 11:44:58,972 INFO Train Epoch: 23 [3200/32087 (10%)] Loss: 1.834643 +2025-04-14 11:45:14,884 INFO Train Epoch: 23 [6400/32087 (20%)] Loss: 1.803675 +2025-04-14 11:45:32,419 INFO Train Epoch: 23 [9600/32087 (30%)] Loss: 1.783807 +2025-04-14 11:45:47,835 INFO Train Epoch: 23 [12800/32087 (40%)] Loss: 1.753857 +2025-04-14 11:46:03,283 INFO Train Epoch: 23 [16000/32087 (50%)] Loss: 1.568612 +2025-04-14 11:46:18,053 INFO Train Epoch: 23 [19200/32087 (60%)] Loss: 1.894376 +2025-04-14 11:46:32,064 INFO Train Epoch: 23 [22400/32087 (70%)] Loss: 1.877248 +2025-04-14 11:46:46,958 INFO Train Epoch: 23 [25600/32087 (80%)] Loss: 2.150671 +2025-04-14 11:47:02,208 INFO Train Epoch: 23 [28800/32087 (90%)] Loss: 1.566593 +2025-04-14 11:47:18,250 INFO Train Epoch: 23 [32000/32087 (100%)] Loss: 1.848007 +2025-04-14 11:48:48,883 INFO Accuracy qa: 71.21 % +2025-04-14 11:48:53,955 INFO Train Epoch: 24 [0/32087 (0%)] Loss: 1.383599 +2025-04-14 11:49:11,348 INFO Train Epoch: 24 [3200/32087 (10%)] Loss: 1.811147 +2025-04-14 11:49:30,098 INFO Train Epoch: 24 [6400/32087 (20%)] Loss: 1.508247 +2025-04-14 11:49:48,576 INFO Train Epoch: 24 [9600/32087 (30%)] Loss: 1.817635 +2025-04-14 11:50:05,251 INFO Train Epoch: 24 [12800/32087 (40%)] Loss: 1.754737 +2025-04-14 11:50:21,844 INFO Train Epoch: 24 [16000/32087 (50%)] Loss: 1.594981 +2025-04-14 11:50:38,341 INFO Train Epoch: 24 [19200/32087 (60%)] Loss: 2.106387 +2025-04-14 11:50:53,420 INFO Train Epoch: 24 [22400/32087 (70%)] Loss: 1.840698 +2025-04-14 11:51:08,567 INFO Train Epoch: 24 [25600/32087 (80%)] Loss: 1.798980 +2025-04-14 11:51:24,357 INFO Train Epoch: 24 [28800/32087 (90%)] Loss: 1.560801 +2025-04-14 11:51:41,295 INFO Train Epoch: 24 [32000/32087 (100%)] Loss: 1.732810 +2025-04-14 11:53:13,030 INFO Accuracy qa: 71.58 % +2025-04-14 11:53:16,034 INFO Train Epoch: 25 [0/32087 (0%)] Loss: 1.621238 +2025-04-14 11:53:34,416 INFO Train Epoch: 25 [3200/32087 (10%)] Loss: 1.445688 +2025-04-14 11:53:52,413 INFO Train Epoch: 25 [6400/32087 (20%)] Loss: 1.700259 +2025-04-14 11:54:10,770 INFO Train Epoch: 25 [9600/32087 (30%)] Loss: 1.624262 +2025-04-14 11:54:26,836 INFO Train Epoch: 25 [12800/32087 (40%)] Loss: 1.885672 +2025-04-14 11:54:42,766 INFO Train Epoch: 25 [16000/32087 (50%)] Loss: 2.020451 +2025-04-14 11:54:58,191 INFO Train Epoch: 25 [19200/32087 (60%)] Loss: 1.394914 +2025-04-14 11:55:13,561 INFO Train Epoch: 25 [22400/32087 (70%)] Loss: 1.870853 +2025-04-14 11:55:27,517 INFO Train Epoch: 25 [25600/32087 (80%)] Loss: 1.732405 +2025-04-14 11:55:41,375 INFO Train Epoch: 25 [28800/32087 (90%)] Loss: 1.912666 +2025-04-14 11:55:56,912 INFO Train Epoch: 25 [32000/32087 (100%)] Loss: 1.920178 +2025-04-14 11:57:25,693 INFO Accuracy qa: 71.64 % +2025-04-14 11:57:30,813 INFO Train Epoch: 26 [0/32087 (0%)] Loss: 1.672088 +2025-04-14 11:57:47,748 INFO Train Epoch: 26 [3200/32087 (10%)] Loss: 1.858659 +2025-04-14 11:58:05,024 INFO Train Epoch: 26 [6400/32087 (20%)] Loss: 1.967774 +2025-04-14 11:58:21,750 INFO Train Epoch: 26 [9600/32087 (30%)] Loss: 2.317655 +2025-04-14 11:58:38,536 INFO Train Epoch: 26 [12800/32087 (40%)] Loss: 1.793976 +2025-04-14 11:58:54,342 INFO Train Epoch: 26 [16000/32087 (50%)] Loss: 2.259965 +2025-04-14 11:59:09,206 INFO Train Epoch: 26 [19200/32087 (60%)] Loss: 1.808893 +2025-04-14 11:59:24,341 INFO Train Epoch: 26 [22400/32087 (70%)] Loss: 1.746453 +2025-04-14 11:59:39,686 INFO Train Epoch: 26 [25600/32087 (80%)] Loss: 1.736254 +2025-04-14 11:59:54,539 INFO Train Epoch: 26 [28800/32087 (90%)] Loss: 2.047551 +2025-04-14 12:00:07,979 INFO Train Epoch: 26 [32000/32087 (100%)] Loss: 1.794919 +2025-04-14 12:01:36,063 INFO Accuracy qa: 71.64 % +2025-04-14 12:01:40,520 INFO Train Epoch: 27 [0/32087 (0%)] Loss: 1.875999 +2025-04-14 12:01:57,719 INFO Train Epoch: 27 [3200/32087 (10%)] Loss: 1.542502 +2025-04-14 12:02:14,603 INFO Train Epoch: 27 [6400/32087 (20%)] Loss: 1.782936 +2025-04-14 12:02:31,411 INFO Train Epoch: 27 [9600/32087 (30%)] Loss: 1.849737 +2025-04-14 12:02:48,051 INFO Train Epoch: 27 [12800/32087 (40%)] Loss: 1.854447 +2025-04-14 12:03:03,569 INFO Train Epoch: 27 [16000/32087 (50%)] Loss: 1.732907 +2025-04-14 12:03:20,136 INFO Train Epoch: 27 [19200/32087 (60%)] Loss: 1.710015 +2025-04-14 12:03:35,550 INFO Train Epoch: 27 [22400/32087 (70%)] Loss: 1.636459 +2025-04-14 12:03:50,411 INFO Train Epoch: 27 [25600/32087 (80%)] Loss: 1.644853 +2025-04-14 12:04:05,485 INFO Train Epoch: 27 [28800/32087 (90%)] Loss: 2.163440 +2025-04-14 12:04:19,797 INFO Train Epoch: 27 [32000/32087 (100%)] Loss: 1.563619 +2025-04-14 12:05:44,676 INFO Accuracy qa: 71.80 % +2025-04-14 12:05:48,516 INFO Train Epoch: 28 [0/32087 (0%)] Loss: 2.039181 +2025-04-14 12:06:07,206 INFO Train Epoch: 28 [3200/32087 (10%)] Loss: 1.923226 +2025-04-14 12:06:25,476 INFO Train Epoch: 28 [6400/32087 (20%)] Loss: 1.216511 +2025-04-14 12:06:43,094 INFO Train Epoch: 28 [9600/32087 (30%)] Loss: 1.904458 +2025-04-14 12:07:01,070 INFO Train Epoch: 28 [12800/32087 (40%)] Loss: 1.748990 +2025-04-14 12:07:18,594 INFO Train Epoch: 28 [16000/32087 (50%)] Loss: 1.676765 +2025-04-14 12:07:34,647 INFO Train Epoch: 28 [19200/32087 (60%)] Loss: 1.693467 +2025-04-14 12:07:50,366 INFO Train Epoch: 28 [22400/32087 (70%)] Loss: 1.496707 +2025-04-14 12:08:07,194 INFO Train Epoch: 28 [25600/32087 (80%)] Loss: 1.953846 +2025-04-14 12:08:25,163 INFO Train Epoch: 28 [28800/32087 (90%)] Loss: 1.464949 +2025-04-14 12:08:43,676 INFO Train Epoch: 28 [32000/32087 (100%)] Loss: 1.411911 +2025-04-14 12:10:13,938 INFO Accuracy qa: 71.08 % +2025-04-14 12:10:18,535 INFO Train Epoch: 29 [0/32087 (0%)] Loss: 1.843279 +2025-04-14 12:10:37,138 INFO Train Epoch: 29 [3200/32087 (10%)] Loss: 1.487913 +2025-04-14 12:10:54,985 INFO Train Epoch: 29 [6400/32087 (20%)] Loss: 1.888357 +2025-04-14 12:11:13,539 INFO Train Epoch: 29 [9600/32087 (30%)] Loss: 2.041191 +2025-04-14 12:11:32,184 INFO Train Epoch: 29 [12800/32087 (40%)] Loss: 1.974994 +2025-04-14 12:11:50,792 INFO Train Epoch: 29 [16000/32087 (50%)] Loss: 1.867643 +2025-04-14 12:12:08,471 INFO Train Epoch: 29 [19200/32087 (60%)] Loss: 1.817127 +2025-04-14 12:12:26,180 INFO Train Epoch: 29 [22400/32087 (70%)] Loss: 2.048498 +2025-04-14 12:12:42,597 INFO Train Epoch: 29 [25600/32087 (80%)] Loss: 1.944200 +2025-04-14 12:12:59,531 INFO Train Epoch: 29 [28800/32087 (90%)] Loss: 1.502115 +2025-04-14 12:13:15,182 INFO Train Epoch: 29 [32000/32087 (100%)] Loss: 1.305984 +2025-04-14 12:14:41,436 INFO Accuracy qa: 71.86 % +2025-04-14 12:14:45,265 INFO Train Epoch: 30 [0/32087 (0%)] Loss: 1.732786 +2025-04-14 12:15:03,460 INFO Train Epoch: 30 [3200/32087 (10%)] Loss: 1.410764 +2025-04-14 12:15:22,116 INFO Train Epoch: 30 [6400/32087 (20%)] Loss: 1.344167 +2025-04-14 12:15:41,623 INFO Train Epoch: 30 [9600/32087 (30%)] Loss: 1.641824 +2025-04-14 12:16:01,911 INFO Train Epoch: 30 [12800/32087 (40%)] Loss: 1.623741 +2025-04-14 12:16:21,418 INFO Train Epoch: 30 [16000/32087 (50%)] Loss: 1.619366 +2025-04-14 12:16:38,814 INFO Train Epoch: 30 [19200/32087 (60%)] Loss: 1.673946 +2025-04-14 12:16:56,939 INFO Train Epoch: 30 [22400/32087 (70%)] Loss: 2.048940 +2025-04-14 12:17:14,006 INFO Train Epoch: 30 [25600/32087 (80%)] Loss: 1.842792 +2025-04-14 12:17:30,669 INFO Train Epoch: 30 [28800/32087 (90%)] Loss: 1.621634 +2025-04-14 12:17:48,315 INFO Train Epoch: 30 [32000/32087 (100%)] Loss: 1.739386 +2025-04-14 12:19:17,998 INFO Accuracy qa: 71.47 % +2025-04-14 12:19:21,822 INFO Train Epoch: 31 [0/32087 (0%)] Loss: 1.553041 +2025-04-14 12:19:39,118 INFO Train Epoch: 31 [3200/32087 (10%)] Loss: 1.968312 +2025-04-14 12:19:56,282 INFO Train Epoch: 31 [6400/32087 (20%)] Loss: 2.112327 +2025-04-14 12:20:15,328 INFO Train Epoch: 31 [9600/32087 (30%)] Loss: 1.232487 +2025-04-14 12:20:35,511 INFO Train Epoch: 31 [12800/32087 (40%)] Loss: 1.729864 +2025-04-14 12:20:54,124 INFO Train Epoch: 31 [16000/32087 (50%)] Loss: 1.546580 +2025-04-14 12:21:11,985 INFO Train Epoch: 31 [19200/32087 (60%)] Loss: 1.419657 +2025-04-14 12:21:29,750 INFO Train Epoch: 31 [22400/32087 (70%)] Loss: 1.593950 +2025-04-14 12:21:46,148 INFO Train Epoch: 31 [25600/32087 (80%)] Loss: 1.659122 +2025-04-14 12:22:01,830 INFO Train Epoch: 31 [28800/32087 (90%)] Loss: 2.165666 +2025-04-14 12:22:16,908 INFO Train Epoch: 31 [32000/32087 (100%)] Loss: 1.785280 +2025-04-14 12:23:46,546 INFO Accuracy qa: 71.69 % +2025-04-14 12:23:50,574 INFO Train Epoch: 32 [0/32087 (0%)] Loss: 1.801426 +2025-04-14 12:24:10,374 INFO Train Epoch: 32 [3200/32087 (10%)] Loss: 1.365925 +2025-04-14 12:24:28,452 INFO Train Epoch: 32 [6400/32087 (20%)] Loss: 1.751614 +2025-04-14 12:24:48,271 INFO Train Epoch: 32 [9600/32087 (30%)] Loss: 1.528934 +2025-04-14 12:25:07,921 INFO Train Epoch: 32 [12800/32087 (40%)] Loss: 1.633207 +2025-04-14 12:25:28,749 INFO Train Epoch: 32 [16000/32087 (50%)] Loss: 1.267385 +2025-04-14 12:25:48,224 INFO Train Epoch: 32 [19200/32087 (60%)] Loss: 1.510287 +2025-04-14 12:26:06,813 INFO Train Epoch: 32 [22400/32087 (70%)] Loss: 1.852820 +2025-04-14 12:26:24,235 INFO Train Epoch: 32 [25600/32087 (80%)] Loss: 1.723915 +2025-04-14 12:26:40,667 INFO Train Epoch: 32 [28800/32087 (90%)] Loss: 1.433641 +2025-04-14 12:26:56,767 INFO Train Epoch: 32 [32000/32087 (100%)] Loss: 1.735658 +2025-04-14 12:28:26,046 INFO Accuracy qa: 71.82 % +2025-04-14 12:28:30,317 INFO Train Epoch: 33 [0/32087 (0%)] Loss: 1.664367 +2025-04-14 12:28:48,137 INFO Train Epoch: 33 [3200/32087 (10%)] Loss: 2.182146 +2025-04-14 12:29:06,275 INFO Train Epoch: 33 [6400/32087 (20%)] Loss: 1.351138 +2025-04-14 12:29:24,658 INFO Train Epoch: 33 [9600/32087 (30%)] Loss: 1.858460 +2025-04-14 12:29:44,109 INFO Train Epoch: 33 [12800/32087 (40%)] Loss: 1.827930 +2025-04-14 12:30:04,388 INFO Train Epoch: 33 [16000/32087 (50%)] Loss: 1.846271 +2025-04-14 12:30:22,882 INFO Train Epoch: 33 [19200/32087 (60%)] Loss: 1.179153 +2025-04-14 12:30:42,028 INFO Train Epoch: 33 [22400/32087 (70%)] Loss: 1.639112 +2025-04-14 12:30:58,674 INFO Train Epoch: 33 [25600/32087 (80%)] Loss: 1.597184 +2025-04-14 12:31:14,937 INFO Train Epoch: 33 [28800/32087 (90%)] Loss: 1.606682 +2025-04-14 12:31:30,394 INFO Train Epoch: 33 [32000/32087 (100%)] Loss: 1.892889 +2025-04-14 12:32:57,044 INFO Accuracy qa: 71.93 % +2025-04-14 12:33:00,211 INFO Train Epoch: 34 [0/32087 (0%)] Loss: 1.621415 +2025-04-14 12:33:19,032 INFO Train Epoch: 34 [3200/32087 (10%)] Loss: 1.748579 +2025-04-14 12:33:37,201 INFO Train Epoch: 34 [6400/32087 (20%)] Loss: 1.533403 +2025-04-14 12:33:57,029 INFO Train Epoch: 34 [9600/32087 (30%)] Loss: 1.584569 +2025-04-14 12:34:16,814 INFO Train Epoch: 34 [12800/32087 (40%)] Loss: 1.581811 +2025-04-14 12:34:36,154 INFO Train Epoch: 34 [16000/32087 (50%)] Loss: 1.666052 +2025-04-14 12:34:55,164 INFO Train Epoch: 34 [19200/32087 (60%)] Loss: 2.003026 +2025-04-14 12:35:14,399 INFO Train Epoch: 34 [22400/32087 (70%)] Loss: 1.791527 +2025-04-14 12:35:31,197 INFO Train Epoch: 34 [25600/32087 (80%)] Loss: 2.011735 +2025-04-14 12:35:47,253 INFO Train Epoch: 34 [28800/32087 (90%)] Loss: 1.866481 +2025-04-14 12:36:02,966 INFO Train Epoch: 34 [32000/32087 (100%)] Loss: 1.350339 +2025-04-14 12:37:27,403 INFO Accuracy qa: 71.77 % +2025-04-14 12:37:30,553 INFO Train Epoch: 35 [0/32087 (0%)] Loss: 1.690678 +2025-04-14 12:37:50,634 INFO Train Epoch: 35 [3200/32087 (10%)] Loss: 1.581624 +2025-04-14 12:38:08,524 INFO Train Epoch: 35 [6400/32087 (20%)] Loss: 1.682570 +2025-04-14 12:38:27,517 INFO Train Epoch: 35 [9600/32087 (30%)] Loss: 1.375736 +2025-04-14 12:38:47,275 INFO Train Epoch: 35 [12800/32087 (40%)] Loss: 1.747563 +2025-04-14 12:39:05,265 INFO Train Epoch: 35 [16000/32087 (50%)] Loss: 1.476827 +2025-04-14 12:39:23,832 INFO Train Epoch: 35 [19200/32087 (60%)] Loss: 1.952406 +2025-04-14 12:39:42,735 INFO Train Epoch: 35 [22400/32087 (70%)] Loss: 1.106436 +2025-04-14 12:40:00,474 INFO Train Epoch: 35 [25600/32087 (80%)] Loss: 1.144017 +2025-04-14 12:40:16,195 INFO Train Epoch: 35 [28800/32087 (90%)] Loss: 1.865865 +2025-04-14 12:40:31,699 INFO Train Epoch: 35 [32000/32087 (100%)] Loss: 1.905741 +2025-04-14 12:41:55,421 INFO Accuracy qa: 71.97 % +2025-04-14 12:41:58,826 INFO Train Epoch: 36 [0/32087 (0%)] Loss: 1.675551 +2025-04-14 12:42:17,350 INFO Train Epoch: 36 [3200/32087 (10%)] Loss: 1.572016 +2025-04-14 12:42:36,162 INFO Train Epoch: 36 [6400/32087 (20%)] Loss: 1.410715 +2025-04-14 12:42:56,198 INFO Train Epoch: 36 [9600/32087 (30%)] Loss: 1.779952 +2025-04-14 12:43:16,276 INFO Train Epoch: 36 [12800/32087 (40%)] Loss: 1.588209 +2025-04-14 12:43:35,605 INFO Train Epoch: 36 [16000/32087 (50%)] Loss: 1.688289 +2025-04-14 12:43:54,203 INFO Train Epoch: 36 [19200/32087 (60%)] Loss: 1.452470 +2025-04-14 12:44:11,519 INFO Train Epoch: 36 [22400/32087 (70%)] Loss: 1.314423 +2025-04-14 12:44:27,978 INFO Train Epoch: 36 [25600/32087 (80%)] Loss: 1.881660 +2025-04-14 12:44:44,625 INFO Train Epoch: 36 [28800/32087 (90%)] Loss: 1.603427 +2025-04-14 12:45:01,372 INFO Train Epoch: 36 [32000/32087 (100%)] Loss: 1.654059 +2025-04-14 12:46:28,306 INFO Accuracy qa: 71.88 % +2025-04-14 12:46:31,810 INFO Train Epoch: 37 [0/32087 (0%)] Loss: 1.251062 +2025-04-14 12:46:51,497 INFO Train Epoch: 37 [3200/32087 (10%)] Loss: 1.459497 +2025-04-14 12:47:11,920 INFO Train Epoch: 37 [6400/32087 (20%)] Loss: 1.687576 +2025-04-14 12:47:32,747 INFO Train Epoch: 37 [9600/32087 (30%)] Loss: 1.538274 +2025-04-14 12:47:50,704 INFO Train Epoch: 37 [12800/32087 (40%)] Loss: 1.626198 +2025-04-14 12:48:07,997 INFO Train Epoch: 37 [16000/32087 (50%)] Loss: 1.481548 +2025-04-14 12:48:24,563 INFO Train Epoch: 37 [19200/32087 (60%)] Loss: 2.007314 +2025-04-14 12:48:41,554 INFO Train Epoch: 37 [22400/32087 (70%)] Loss: 1.615080 +2025-04-14 12:48:57,602 INFO Train Epoch: 37 [25600/32087 (80%)] Loss: 1.308940 +2025-04-14 12:49:13,975 INFO Train Epoch: 37 [28800/32087 (90%)] Loss: 1.907174 +2025-04-14 12:49:29,912 INFO Train Epoch: 37 [32000/32087 (100%)] Loss: 1.500380 +2025-04-14 12:50:58,191 INFO Accuracy qa: 72.06 % +2025-04-14 12:51:02,725 INFO Train Epoch: 38 [0/32087 (0%)] Loss: 1.703857 +2025-04-14 12:51:21,344 INFO Train Epoch: 38 [3200/32087 (10%)] Loss: 1.460306 +2025-04-14 12:51:40,024 INFO Train Epoch: 38 [6400/32087 (20%)] Loss: 1.703429 +2025-04-14 12:51:58,943 INFO Train Epoch: 38 [9600/32087 (30%)] Loss: 1.662691 +2025-04-14 12:52:16,566 INFO Train Epoch: 38 [12800/32087 (40%)] Loss: 1.594960 +2025-04-14 12:52:32,331 INFO Train Epoch: 38 [16000/32087 (50%)] Loss: 1.540999 +2025-04-14 12:52:48,106 INFO Train Epoch: 38 [19200/32087 (60%)] Loss: 1.726789 +2025-04-14 12:53:04,131 INFO Train Epoch: 38 [22400/32087 (70%)] Loss: 1.263019 +2025-04-14 12:53:19,904 INFO Train Epoch: 38 [25600/32087 (80%)] Loss: 1.648858 +2025-04-14 12:53:35,837 INFO Train Epoch: 38 [28800/32087 (90%)] Loss: 1.385763 +2025-04-14 12:53:50,474 INFO Train Epoch: 38 [32000/32087 (100%)] Loss: 1.968780 +2025-04-14 12:55:18,277 INFO Accuracy qa: 72.06 % +2025-04-14 12:55:21,627 INFO Train Epoch: 39 [0/32087 (0%)] Loss: 1.806720 +2025-04-14 12:55:37,006 INFO Train Epoch: 39 [3200/32087 (10%)] Loss: 1.297430 +2025-04-14 12:55:54,165 INFO Train Epoch: 39 [6400/32087 (20%)] Loss: 1.465627 +2025-04-14 12:56:11,925 INFO Train Epoch: 39 [9600/32087 (30%)] Loss: 1.552283 +2025-04-14 12:56:30,325 INFO Train Epoch: 39 [12800/32087 (40%)] Loss: 1.668816 +2025-04-14 12:56:46,042 INFO Train Epoch: 39 [16000/32087 (50%)] Loss: 1.404655 +2025-04-14 12:57:02,265 INFO Train Epoch: 39 [19200/32087 (60%)] Loss: 1.551275 +2025-04-14 12:57:18,402 INFO Train Epoch: 39 [22400/32087 (70%)] Loss: 1.571038 +2025-04-14 12:57:34,274 INFO Train Epoch: 39 [25600/32087 (80%)] Loss: 1.777641 +2025-04-14 12:57:50,278 INFO Train Epoch: 39 [28800/32087 (90%)] Loss: 1.808465 +2025-04-14 12:58:05,576 INFO Train Epoch: 39 [32000/32087 (100%)] Loss: 1.460427 +2025-04-14 12:59:33,426 INFO Accuracy qa: 71.84 % +2025-04-14 12:59:36,087 INFO Train Epoch: 40 [0/32087 (0%)] Loss: 2.043795 +2025-04-14 12:59:53,496 INFO Train Epoch: 40 [3200/32087 (10%)] Loss: 1.641566 +2025-04-14 13:00:09,366 INFO Train Epoch: 40 [6400/32087 (20%)] Loss: 1.653883 +2025-04-14 13:00:27,062 INFO Train Epoch: 40 [9600/32087 (30%)] Loss: 1.536807 +2025-04-14 13:00:44,989 INFO Train Epoch: 40 [12800/32087 (40%)] Loss: 1.807557 +2025-04-14 13:01:02,368 INFO Train Epoch: 40 [16000/32087 (50%)] Loss: 1.860961 +2025-04-14 13:01:18,744 INFO Train Epoch: 40 [19200/32087 (60%)] Loss: 1.570569 +2025-04-14 13:01:35,360 INFO Train Epoch: 40 [22400/32087 (70%)] Loss: 1.426890 +2025-04-14 13:01:52,269 INFO Train Epoch: 40 [25600/32087 (80%)] Loss: 1.868774 +2025-04-14 13:02:08,647 INFO Train Epoch: 40 [28800/32087 (90%)] Loss: 1.797069 +2025-04-14 13:02:24,429 INFO Train Epoch: 40 [32000/32087 (100%)] Loss: 1.641819 +2025-04-14 13:03:50,692 INFO Accuracy qa: 71.88 % +2025-04-14 13:03:54,983 INFO Train Epoch: 41 [0/32087 (0%)] Loss: 1.825907 +2025-04-14 13:04:09,301 INFO Train Epoch: 41 [3200/32087 (10%)] Loss: 1.897207 +2025-04-14 13:04:24,136 INFO Train Epoch: 41 [6400/32087 (20%)] Loss: 1.950484 +2025-04-14 13:04:38,912 INFO Train Epoch: 41 [9600/32087 (30%)] Loss: 1.751337 +2025-04-14 13:04:54,833 INFO Train Epoch: 41 [12800/32087 (40%)] Loss: 1.833654 +2025-04-14 13:05:14,830 INFO Train Epoch: 41 [16000/32087 (50%)] Loss: 1.588642 +2025-04-14 13:05:34,973 INFO Train Epoch: 41 [19200/32087 (60%)] Loss: 1.484124 +2025-04-14 13:05:52,611 INFO Train Epoch: 41 [22400/32087 (70%)] Loss: 1.716994 +2025-04-14 13:06:10,212 INFO Train Epoch: 41 [25600/32087 (80%)] Loss: 1.915363 +2025-04-14 13:06:26,876 INFO Train Epoch: 41 [28800/32087 (90%)] Loss: 1.006339 +2025-04-14 13:06:42,653 INFO Train Epoch: 41 [32000/32087 (100%)] Loss: 1.249200 +2025-04-14 13:08:11,239 INFO Accuracy qa: 71.90 % +2025-04-14 13:08:13,866 INFO Train Epoch: 42 [0/32087 (0%)] Loss: 2.220984 +2025-04-14 13:08:29,286 INFO Train Epoch: 42 [3200/32087 (10%)] Loss: 1.993419 +2025-04-14 13:08:44,166 INFO Train Epoch: 42 [6400/32087 (20%)] Loss: 1.623710 +2025-04-14 13:08:59,376 INFO Train Epoch: 42 [9600/32087 (30%)] Loss: 1.521199 +2025-04-14 13:09:14,092 INFO Train Epoch: 42 [12800/32087 (40%)] Loss: 1.629239 +2025-04-14 13:09:29,921 INFO Train Epoch: 42 [16000/32087 (50%)] Loss: 1.592138 +2025-04-14 13:09:48,705 INFO Train Epoch: 42 [19200/32087 (60%)] Loss: 1.599995 +2025-04-14 13:10:07,273 INFO Train Epoch: 42 [22400/32087 (70%)] Loss: 1.178233 +2025-04-14 13:10:25,036 INFO Train Epoch: 42 [25600/32087 (80%)] Loss: 1.601707 +2025-04-14 13:10:42,996 INFO Train Epoch: 42 [28800/32087 (90%)] Loss: 1.753675 +2025-04-14 13:10:59,581 INFO Train Epoch: 42 [32000/32087 (100%)] Loss: 1.416129 +2025-04-14 13:12:31,154 INFO Accuracy qa: 71.84 % +2025-04-14 13:12:35,561 INFO Train Epoch: 43 [0/32087 (0%)] Loss: 1.404974 +2025-04-14 13:12:50,989 INFO Train Epoch: 43 [3200/32087 (10%)] Loss: 1.848935 +2025-04-14 13:13:06,324 INFO Train Epoch: 43 [6400/32087 (20%)] Loss: 1.512566 +2025-04-14 13:13:22,885 INFO Train Epoch: 43 [9600/32087 (30%)] Loss: 1.969816 +2025-04-14 13:13:40,178 INFO Train Epoch: 43 [12800/32087 (40%)] Loss: 1.354853 +2025-04-14 13:13:56,579 INFO Train Epoch: 43 [16000/32087 (50%)] Loss: 1.648754 +2025-04-14 13:14:17,288 INFO Train Epoch: 43 [19200/32087 (60%)] Loss: 1.707810 +2025-04-14 13:14:37,743 INFO Train Epoch: 43 [22400/32087 (70%)] Loss: 1.345973 +2025-04-14 13:14:56,765 INFO Train Epoch: 43 [25600/32087 (80%)] Loss: 1.884131 +2025-04-14 13:15:15,586 INFO Train Epoch: 43 [28800/32087 (90%)] Loss: 2.082732 +2025-04-14 13:15:33,175 INFO Train Epoch: 43 [32000/32087 (100%)] Loss: 1.682986 +2025-04-14 13:17:04,124 INFO Accuracy qa: 71.58 % +2025-04-14 13:17:07,063 INFO Train Epoch: 44 [0/32087 (0%)] Loss: 1.684651 +2025-04-14 13:17:21,457 INFO Train Epoch: 44 [3200/32087 (10%)] Loss: 1.903823 +2025-04-14 13:17:35,061 INFO Train Epoch: 44 [6400/32087 (20%)] Loss: 1.643220 +2025-04-14 13:17:48,541 INFO Train Epoch: 44 [9600/32087 (30%)] Loss: 1.464080 +2025-04-14 13:18:03,050 INFO Train Epoch: 44 [12800/32087 (40%)] Loss: 2.104725 +2025-04-14 13:18:17,829 INFO Train Epoch: 44 [16000/32087 (50%)] Loss: 1.954736 +2025-04-14 13:18:32,298 INFO Train Epoch: 44 [19200/32087 (60%)] Loss: 1.573968 +2025-04-14 13:18:51,183 INFO Train Epoch: 44 [22400/32087 (70%)] Loss: 2.064081 +2025-04-14 13:19:09,028 INFO Train Epoch: 44 [25600/32087 (80%)] Loss: 1.922572 +2025-04-14 13:19:25,772 INFO Train Epoch: 44 [28800/32087 (90%)] Loss: 1.622722 +2025-04-14 13:19:41,801 INFO Train Epoch: 44 [32000/32087 (100%)] Loss: 1.434941 +2025-04-14 13:21:12,133 INFO Accuracy qa: 71.73 % +2025-04-14 13:21:15,699 INFO Train Epoch: 45 [0/32087 (0%)] Loss: 1.723462 +2025-04-14 13:21:32,023 INFO Train Epoch: 45 [3200/32087 (10%)] Loss: 1.345611 +2025-04-14 13:21:46,442 INFO Train Epoch: 45 [6400/32087 (20%)] Loss: 1.688010 +2025-04-14 13:22:00,344 INFO Train Epoch: 45 [9600/32087 (30%)] Loss: 1.543148 +2025-04-14 13:22:15,438 INFO Train Epoch: 45 [12800/32087 (40%)] Loss: 1.561321 +2025-04-14 13:22:32,040 INFO Train Epoch: 45 [16000/32087 (50%)] Loss: 1.303997 +2025-04-14 13:22:47,714 INFO Train Epoch: 45 [19200/32087 (60%)] Loss: 1.856274 +2025-04-14 13:23:03,845 INFO Train Epoch: 45 [22400/32087 (70%)] Loss: 1.238098 +2025-04-14 13:23:21,741 INFO Train Epoch: 45 [25600/32087 (80%)] Loss: 1.506364 +2025-04-14 13:23:38,992 INFO Train Epoch: 45 [28800/32087 (90%)] Loss: 1.617465 +2025-04-14 13:23:55,561 INFO Train Epoch: 45 [32000/32087 (100%)] Loss: 1.389219 +2025-04-14 13:25:26,425 INFO Accuracy qa: 71.93 % +2025-04-14 13:25:30,768 INFO Train Epoch: 46 [0/32087 (0%)] Loss: 1.559295 +2025-04-14 13:25:49,574 INFO Train Epoch: 46 [3200/32087 (10%)] Loss: 1.724442 +2025-04-14 13:26:06,783 INFO Train Epoch: 46 [6400/32087 (20%)] Loss: 1.290711 +2025-04-14 13:26:23,354 INFO Train Epoch: 46 [9600/32087 (30%)] Loss: 1.826314 +2025-04-14 13:26:39,166 INFO Train Epoch: 46 [12800/32087 (40%)] Loss: 1.475802 +2025-04-14 13:26:56,466 INFO Train Epoch: 46 [16000/32087 (50%)] Loss: 1.733008 +2025-04-14 13:27:13,354 INFO Train Epoch: 46 [19200/32087 (60%)] Loss: 1.614449 +2025-04-14 13:27:29,616 INFO Train Epoch: 46 [22400/32087 (70%)] Loss: 1.580503 +2025-04-14 13:27:48,924 INFO Train Epoch: 46 [25600/32087 (80%)] Loss: 1.734365 +2025-04-14 13:28:07,478 INFO Train Epoch: 46 [28800/32087 (90%)] Loss: 1.992517 +2025-04-14 13:28:25,576 INFO Train Epoch: 46 [32000/32087 (100%)] Loss: 1.811169 +2025-04-14 13:29:58,358 INFO Accuracy qa: 71.88 % +2025-04-14 13:30:03,661 INFO Train Epoch: 47 [0/32087 (0%)] Loss: 1.777916 +2025-04-14 13:30:20,489 INFO Train Epoch: 47 [3200/32087 (10%)] Loss: 1.554604 +2025-04-14 13:30:35,761 INFO Train Epoch: 47 [6400/32087 (20%)] Loss: 1.833423 +2025-04-14 13:30:49,521 INFO Train Epoch: 47 [9600/32087 (30%)] Loss: 1.271141 +2025-04-14 13:31:03,358 INFO Train Epoch: 47 [12800/32087 (40%)] Loss: 1.704924 +2025-04-14 13:31:18,042 INFO Train Epoch: 47 [16000/32087 (50%)] Loss: 1.468066 +2025-04-14 13:31:33,917 INFO Train Epoch: 47 [19200/32087 (60%)] Loss: 1.500651 +2025-04-14 13:31:49,813 INFO Train Epoch: 47 [22400/32087 (70%)] Loss: 1.948024 +2025-04-14 13:32:06,894 INFO Train Epoch: 47 [25600/32087 (80%)] Loss: 1.584977 +2025-04-14 13:32:24,683 INFO Train Epoch: 47 [28800/32087 (90%)] Loss: 1.368591 +2025-04-14 13:32:40,492 INFO Train Epoch: 47 [32000/32087 (100%)] Loss: 1.605381 +2025-04-14 13:34:14,358 INFO Accuracy qa: 71.90 % +2025-04-14 13:34:18,237 INFO Train Epoch: 48 [0/32087 (0%)] Loss: 1.396995 +2025-04-14 13:34:35,579 INFO Train Epoch: 48 [3200/32087 (10%)] Loss: 2.122392 +2025-04-14 13:34:51,592 INFO Train Epoch: 48 [6400/32087 (20%)] Loss: 1.831773 +2025-04-14 13:35:07,381 INFO Train Epoch: 48 [9600/32087 (30%)] Loss: 1.409555 +2025-04-14 13:35:21,070 INFO Train Epoch: 48 [12800/32087 (40%)] Loss: 1.355483 +2025-04-14 13:35:35,401 INFO Train Epoch: 48 [16000/32087 (50%)] Loss: 1.483501 +2025-04-14 13:35:50,923 INFO Train Epoch: 48 [19200/32087 (60%)] Loss: 1.458693 +2025-04-14 13:36:06,314 INFO Train Epoch: 48 [22400/32087 (70%)] Loss: 1.440565 +2025-04-14 13:36:22,312 INFO Train Epoch: 48 [25600/32087 (80%)] Loss: 1.647538 +2025-04-14 13:36:39,070 INFO Train Epoch: 48 [28800/32087 (90%)] Loss: 1.462502 +2025-04-14 13:36:57,170 INFO Train Epoch: 48 [32000/32087 (100%)] Loss: 1.466850 +2025-04-14 13:38:45,199 INFO Accuracy qa: 71.90 % +2025-04-14 13:38:48,254 INFO Train Epoch: 49 [0/32087 (0%)] Loss: 1.480766 +2025-04-14 13:39:06,393 INFO Train Epoch: 49 [3200/32087 (10%)] Loss: 1.520067 +2025-04-14 13:39:22,757 INFO Train Epoch: 49 [6400/32087 (20%)] Loss: 1.688859 +2025-04-14 13:39:38,234 INFO Train Epoch: 49 [9600/32087 (30%)] Loss: 1.710435 +2025-04-14 13:39:52,848 INFO Train Epoch: 49 [12800/32087 (40%)] Loss: 1.233162 +2025-04-14 13:40:06,916 INFO Train Epoch: 49 [16000/32087 (50%)] Loss: 1.625142 +2025-04-14 13:40:22,479 INFO Train Epoch: 49 [19200/32087 (60%)] Loss: 1.468438 +2025-04-14 13:40:38,770 INFO Train Epoch: 49 [22400/32087 (70%)] Loss: 1.476254 +2025-04-14 13:40:56,580 INFO Train Epoch: 49 [25600/32087 (80%)] Loss: 1.481815 +2025-04-14 13:41:15,208 INFO Train Epoch: 49 [28800/32087 (90%)] Loss: 1.332523 +2025-04-14 13:41:32,087 INFO Train Epoch: 49 [32000/32087 (100%)] Loss: 1.673367 +2025-04-14 13:43:03,669 INFO Accuracy qa: 71.86 % +2025-04-14 13:43:06,897 INFO Train Epoch: 50 [0/32087 (0%)] Loss: 1.690150 +2025-04-14 13:43:26,558 INFO Train Epoch: 50 [3200/32087 (10%)] Loss: 1.594093 +2025-04-14 13:43:43,065 INFO Train Epoch: 50 [6400/32087 (20%)] Loss: 1.625661 +2025-04-14 13:43:57,016 INFO Train Epoch: 50 [9600/32087 (30%)] Loss: 1.517477 +2025-04-14 13:44:10,958 INFO Train Epoch: 50 [12800/32087 (40%)] Loss: 1.600173 +2025-04-14 13:44:24,764 INFO Train Epoch: 50 [16000/32087 (50%)] Loss: 1.404584 +2025-04-14 13:44:38,299 INFO Train Epoch: 50 [19200/32087 (60%)] Loss: 1.833001 +2025-04-14 13:44:53,502 INFO Train Epoch: 50 [22400/32087 (70%)] Loss: 1.611855 +2025-04-14 13:45:08,941 INFO Train Epoch: 50 [25600/32087 (80%)] Loss: 1.426065 +2025-04-14 13:45:25,479 INFO Train Epoch: 50 [28800/32087 (90%)] Loss: 1.404953 +2025-04-14 13:45:41,015 INFO Train Epoch: 50 [32000/32087 (100%)] Loss: 1.653485 +2025-04-14 13:47:13,136 INFO Accuracy qa: 71.82 % diff --git a/Audio Visual Question Answering/results/inverse_True_withoutmodified/avst.pt b/Audio Visual Question Answering/results/inverse_True_withoutmodified/avst.pt new file mode 100644 index 0000000000000000000000000000000000000000..55bf5ff87e27f32df58a7afa688b6996e62682cb --- /dev/null +++ b/Audio Visual Question Answering/results/inverse_True_withoutmodified/avst.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3135289b0eeff28cde1d9178a6ab47a3045c5162ed4c885bc18ae32034547c3 +size 89479183 diff --git a/Audio Visual Question Answering/results/inverse_True_withoutmodified/test.log b/Audio Visual Question Answering/results/inverse_True_withoutmodified/test.log new file mode 100644 index 0000000000000000000000000000000000000000..337c0e379ad15525b298322c3ce7d0baad1155bd --- /dev/null +++ b/Audio Visual Question Answering/results/inverse_True_withoutmodified/test.log @@ -0,0 +1,17 @@ +2025-04-14 14:09:20,375 INFO +--------------- Audio-Visual Spatial-Temporal Model --------------- + +2025-04-14 14:09:25,607 INFO 9185 +2025-04-14 14:10:34,333 INFO Audio Counting Accuracy: 78.18 % +2025-04-14 14:10:34,333 INFO Audio Cmp Accuracy: 63.39 % +2025-04-14 14:10:34,333 INFO Audio Accuracy: 72.70 % +2025-04-14 14:10:34,333 INFO Visual Counting Accuracy: 75.06 % +2025-04-14 14:10:34,334 INFO Visual Loc Accuracy: 75.98 % +2025-04-14 14:10:34,334 INFO Visual Accuracy: 75.53 % +2025-04-14 14:10:34,334 INFO AV Ext Accuracy: 82.91 % +2025-04-14 14:10:34,334 INFO AV counting Accuracy: 68.84 % +2025-04-14 14:10:34,334 INFO AV Loc Accuracy: 63.00 % +2025-04-14 14:10:34,335 INFO AV Cmp Accuracy: 61.52 % +2025-04-14 14:10:34,335 INFO AV Temporal Accuracy: 61.89 % +2025-04-14 14:10:34,335 INFO AV Accuracy: 67.81 % +2025-04-14 14:10:34,335 INFO Overall Accuracy: 70.71 % diff --git a/Audio Visual Question Answering/results/inverse_True_withoutmodified/train.log b/Audio Visual Question Answering/results/inverse_True_withoutmodified/train.log new file mode 100644 index 0000000000000000000000000000000000000000..e1a008cf845454abc51b88fab9333e0ee2b93a90 --- /dev/null +++ b/Audio Visual Question Answering/results/inverse_True_withoutmodified/train.log @@ -0,0 +1,607 @@ +2025-04-14 10:06:38,566 INFO +--------------- Audio-Visual Spatial-Temporal Model --------------- + +2025-04-14 10:06:45,599 INFO +-------------- loading pretrained models -------------- +2025-04-14 10:06:45,605 INFO +-------------- load pretrained models -------------- +2025-04-14 10:06:52,781 INFO Train Epoch: 1 [0/32087 (0%)] Loss: 11.622032 +2025-04-14 10:07:08,321 INFO Train Epoch: 1 [3200/32087 (10%)] Loss: 7.965600 +2025-04-14 10:07:21,076 INFO Train Epoch: 1 [6400/32087 (20%)] Loss: 6.312354 +2025-04-14 10:07:34,388 INFO Train Epoch: 1 [9600/32087 (30%)] Loss: 5.240974 +2025-04-14 10:07:47,232 INFO Train Epoch: 1 [12800/32087 (40%)] Loss: 4.238906 +2025-04-14 10:08:00,382 INFO Train Epoch: 1 [16000/32087 (50%)] Loss: 3.980130 +2025-04-14 10:08:13,568 INFO Train Epoch: 1 [19200/32087 (60%)] Loss: 4.087693 +2025-04-14 10:08:27,204 INFO Train Epoch: 1 [22400/32087 (70%)] Loss: 3.414510 +2025-04-14 10:08:42,179 INFO Train Epoch: 1 [25600/32087 (80%)] Loss: 3.239423 +2025-04-14 10:09:00,060 INFO Train Epoch: 1 [28800/32087 (90%)] Loss: 3.278737 +2025-04-14 10:09:15,393 INFO Train Epoch: 1 [32000/32087 (100%)] Loss: 3.607351 +2025-04-14 10:10:47,698 INFO Accuracy qa: 55.84 % +2025-04-14 10:10:52,419 INFO Train Epoch: 2 [0/32087 (0%)] Loss: 3.486021 +2025-04-14 10:11:12,802 INFO Train Epoch: 2 [3200/32087 (10%)] Loss: 3.356102 +2025-04-14 10:11:33,027 INFO Train Epoch: 2 [6400/32087 (20%)] Loss: 3.145207 +2025-04-14 10:11:49,444 INFO Train Epoch: 2 [9600/32087 (30%)] Loss: 3.446756 +2025-04-14 10:12:05,093 INFO Train Epoch: 2 [12800/32087 (40%)] Loss: 3.542494 +2025-04-14 10:12:19,165 INFO Train Epoch: 2 [16000/32087 (50%)] Loss: 3.509858 +2025-04-14 10:12:33,397 INFO Train Epoch: 2 [19200/32087 (60%)] Loss: 3.113601 +2025-04-14 10:12:47,552 INFO Train Epoch: 2 [22400/32087 (70%)] Loss: 2.705511 +2025-04-14 10:13:02,053 INFO Train Epoch: 2 [25600/32087 (80%)] Loss: 3.164816 +2025-04-14 10:13:18,796 INFO Train Epoch: 2 [28800/32087 (90%)] Loss: 4.394171 +2025-04-14 10:13:34,851 INFO Train Epoch: 2 [32000/32087 (100%)] Loss: 2.933322 +2025-04-14 10:15:07,730 INFO Accuracy qa: 62.44 % +2025-04-14 10:15:12,723 INFO Train Epoch: 3 [0/32087 (0%)] Loss: 2.692063 +2025-04-14 10:15:36,218 INFO Train Epoch: 3 [3200/32087 (10%)] Loss: 3.083926 +2025-04-14 10:15:57,463 INFO Train Epoch: 3 [6400/32087 (20%)] Loss: 3.736977 +2025-04-14 10:16:14,345 INFO Train Epoch: 3 [9600/32087 (30%)] Loss: 3.847872 +2025-04-14 10:16:31,004 INFO Train Epoch: 3 [12800/32087 (40%)] Loss: 3.511822 +2025-04-14 10:16:46,202 INFO Train Epoch: 3 [16000/32087 (50%)] Loss: 3.017560 +2025-04-14 10:17:00,620 INFO Train Epoch: 3 [19200/32087 (60%)] Loss: 2.859923 +2025-04-14 10:17:14,907 INFO Train Epoch: 3 [22400/32087 (70%)] Loss: 3.340359 +2025-04-14 10:17:29,724 INFO Train Epoch: 3 [25600/32087 (80%)] Loss: 3.204878 +2025-04-14 10:17:46,888 INFO Train Epoch: 3 [28800/32087 (90%)] Loss: 2.554320 +2025-04-14 10:18:04,181 INFO Train Epoch: 3 [32000/32087 (100%)] Loss: 3.605929 +2025-04-14 10:19:36,959 INFO Accuracy qa: 63.66 % +2025-04-14 10:19:43,036 INFO Train Epoch: 4 [0/32087 (0%)] Loss: 3.021378 +2025-04-14 10:20:04,975 INFO Train Epoch: 4 [3200/32087 (10%)] Loss: 3.164831 +2025-04-14 10:20:24,534 INFO Train Epoch: 4 [6400/32087 (20%)] Loss: 3.334928 +2025-04-14 10:20:41,823 INFO Train Epoch: 4 [9600/32087 (30%)] Loss: 3.270330 +2025-04-14 10:20:59,119 INFO Train Epoch: 4 [12800/32087 (40%)] Loss: 3.535134 +2025-04-14 10:21:15,553 INFO Train Epoch: 4 [16000/32087 (50%)] Loss: 3.132182 +2025-04-14 10:21:30,739 INFO Train Epoch: 4 [19200/32087 (60%)] Loss: 2.623670 +2025-04-14 10:21:46,611 INFO Train Epoch: 4 [22400/32087 (70%)] Loss: 3.262167 +2025-04-14 10:22:03,816 INFO Train Epoch: 4 [25600/32087 (80%)] Loss: 3.017179 +2025-04-14 10:22:21,855 INFO Train Epoch: 4 [28800/32087 (90%)] Loss: 2.849044 +2025-04-14 10:22:38,436 INFO Train Epoch: 4 [32000/32087 (100%)] Loss: 2.803123 +2025-04-14 10:24:10,922 INFO Accuracy qa: 64.90 % +2025-04-14 10:24:17,044 INFO Train Epoch: 5 [0/32087 (0%)] Loss: 2.830537 +2025-04-14 10:24:41,074 INFO Train Epoch: 5 [3200/32087 (10%)] Loss: 2.945999 +2025-04-14 10:25:00,687 INFO Train Epoch: 5 [6400/32087 (20%)] Loss: 2.532957 +2025-04-14 10:25:20,565 INFO Train Epoch: 5 [9600/32087 (30%)] Loss: 2.192365 +2025-04-14 10:25:39,977 INFO Train Epoch: 5 [12800/32087 (40%)] Loss: 3.106288 +2025-04-14 10:25:57,517 INFO Train Epoch: 5 [16000/32087 (50%)] Loss: 2.935057 +2025-04-14 10:26:15,564 INFO Train Epoch: 5 [19200/32087 (60%)] Loss: 3.121733 +2025-04-14 10:26:35,637 INFO Train Epoch: 5 [22400/32087 (70%)] Loss: 3.261246 +2025-04-14 10:26:55,790 INFO Train Epoch: 5 [25600/32087 (80%)] Loss: 2.639418 +2025-04-14 10:27:13,264 INFO Train Epoch: 5 [28800/32087 (90%)] Loss: 2.516587 +2025-04-14 10:27:30,343 INFO Train Epoch: 5 [32000/32087 (100%)] Loss: 2.968796 +2025-04-14 10:29:05,594 INFO Accuracy qa: 64.13 % +2025-04-14 10:29:09,655 INFO Train Epoch: 6 [0/32087 (0%)] Loss: 2.883001 +2025-04-14 10:29:28,565 INFO Train Epoch: 6 [3200/32087 (10%)] Loss: 2.891201 +2025-04-14 10:29:46,593 INFO Train Epoch: 6 [6400/32087 (20%)] Loss: 2.675770 +2025-04-14 10:30:05,430 INFO Train Epoch: 6 [9600/32087 (30%)] Loss: 2.733818 +2025-04-14 10:30:24,032 INFO Train Epoch: 6 [12800/32087 (40%)] Loss: 2.515875 +2025-04-14 10:30:44,205 INFO Train Epoch: 6 [16000/32087 (50%)] Loss: 2.799325 +2025-04-14 10:31:06,512 INFO Train Epoch: 6 [19200/32087 (60%)] Loss: 3.086923 +2025-04-14 10:31:26,516 INFO Train Epoch: 6 [22400/32087 (70%)] Loss: 3.272698 +2025-04-14 10:31:46,525 INFO Train Epoch: 6 [25600/32087 (80%)] Loss: 2.888942 +2025-04-14 10:32:05,200 INFO Train Epoch: 6 [28800/32087 (90%)] Loss: 3.059046 +2025-04-14 10:32:24,015 INFO Train Epoch: 6 [32000/32087 (100%)] Loss: 2.608231 +2025-04-14 10:33:55,515 INFO Accuracy qa: 65.07 % +2025-04-14 10:34:00,896 INFO Train Epoch: 7 [0/32087 (0%)] Loss: 3.431098 +2025-04-14 10:34:19,590 INFO Train Epoch: 7 [3200/32087 (10%)] Loss: 3.056443 +2025-04-14 10:34:36,958 INFO Train Epoch: 7 [6400/32087 (20%)] Loss: 2.711430 +2025-04-14 10:34:52,302 INFO Train Epoch: 7 [9600/32087 (30%)] Loss: 2.568222 +2025-04-14 10:35:11,134 INFO Train Epoch: 7 [12800/32087 (40%)] Loss: 3.004770 +2025-04-14 10:35:32,843 INFO Train Epoch: 7 [16000/32087 (50%)] Loss: 3.096447 +2025-04-14 10:35:52,215 INFO Train Epoch: 7 [19200/32087 (60%)] Loss: 2.742098 +2025-04-14 10:36:10,354 INFO Train Epoch: 7 [22400/32087 (70%)] Loss: 2.717525 +2025-04-14 10:36:28,631 INFO Train Epoch: 7 [25600/32087 (80%)] Loss: 2.999554 +2025-04-14 10:36:47,981 INFO Train Epoch: 7 [28800/32087 (90%)] Loss: 3.213421 +2025-04-14 10:37:05,935 INFO Train Epoch: 7 [32000/32087 (100%)] Loss: 3.091913 +2025-04-14 10:38:36,054 INFO Accuracy qa: 67.03 % +2025-04-14 10:38:40,293 INFO Train Epoch: 8 [0/32087 (0%)] Loss: 2.804677 +2025-04-14 10:38:56,772 INFO Train Epoch: 8 [3200/32087 (10%)] Loss: 2.764110 +2025-04-14 10:39:13,630 INFO Train Epoch: 8 [6400/32087 (20%)] Loss: 2.800756 +2025-04-14 10:39:31,064 INFO Train Epoch: 8 [9600/32087 (30%)] Loss: 2.946718 +2025-04-14 10:39:49,724 INFO Train Epoch: 8 [12800/32087 (40%)] Loss: 3.236446 +2025-04-14 10:40:09,227 INFO Train Epoch: 8 [16000/32087 (50%)] Loss: 2.734255 +2025-04-14 10:40:29,121 INFO Train Epoch: 8 [19200/32087 (60%)] Loss: 2.885514 +2025-04-14 10:40:48,455 INFO Train Epoch: 8 [22400/32087 (70%)] Loss: 2.574946 +2025-04-14 10:41:08,066 INFO Train Epoch: 8 [25600/32087 (80%)] Loss: 2.633442 +2025-04-14 10:41:27,041 INFO Train Epoch: 8 [28800/32087 (90%)] Loss: 2.136546 +2025-04-14 10:41:44,532 INFO Train Epoch: 8 [32000/32087 (100%)] Loss: 3.148151 +2025-04-14 10:43:14,193 INFO Accuracy qa: 66.33 % +2025-04-14 10:43:17,091 INFO Train Epoch: 9 [0/32087 (0%)] Loss: 2.245392 +2025-04-14 10:43:36,188 INFO Train Epoch: 9 [3200/32087 (10%)] Loss: 2.088453 +2025-04-14 10:43:55,023 INFO Train Epoch: 9 [6400/32087 (20%)] Loss: 2.864145 +2025-04-14 10:44:14,993 INFO Train Epoch: 9 [9600/32087 (30%)] Loss: 2.314387 +2025-04-14 10:44:35,422 INFO Train Epoch: 9 [12800/32087 (40%)] Loss: 2.686238 +2025-04-14 10:44:55,854 INFO Train Epoch: 9 [16000/32087 (50%)] Loss: 2.987717 +2025-04-14 10:45:16,556 INFO Train Epoch: 9 [19200/32087 (60%)] Loss: 3.890572 +2025-04-14 10:45:37,212 INFO Train Epoch: 9 [22400/32087 (70%)] Loss: 2.493755 +2025-04-14 10:45:58,060 INFO Train Epoch: 9 [25600/32087 (80%)] Loss: 2.422996 +2025-04-14 10:46:19,154 INFO Train Epoch: 9 [28800/32087 (90%)] Loss: 2.301137 +2025-04-14 10:46:38,558 INFO Train Epoch: 9 [32000/32087 (100%)] Loss: 3.198367 +2025-04-14 10:48:08,642 INFO Accuracy qa: 68.81 % +2025-04-14 10:48:12,660 INFO Train Epoch: 10 [0/32087 (0%)] Loss: 2.937159 +2025-04-14 10:48:31,836 INFO Train Epoch: 10 [3200/32087 (10%)] Loss: 1.894445 +2025-04-14 10:48:53,150 INFO Train Epoch: 10 [6400/32087 (20%)] Loss: 2.687035 +2025-04-14 10:49:13,210 INFO Train Epoch: 10 [9600/32087 (30%)] Loss: 3.030069 +2025-04-14 10:49:34,190 INFO Train Epoch: 10 [12800/32087 (40%)] Loss: 2.119335 +2025-04-14 10:49:58,065 INFO Train Epoch: 10 [16000/32087 (50%)] Loss: 2.526911 +2025-04-14 10:50:20,145 INFO Train Epoch: 10 [19200/32087 (60%)] Loss: 2.909201 +2025-04-14 10:50:42,549 INFO Train Epoch: 10 [22400/32087 (70%)] Loss: 2.943325 +2025-04-14 10:51:00,851 INFO Train Epoch: 10 [25600/32087 (80%)] Loss: 2.713989 +2025-04-14 10:51:19,688 INFO Train Epoch: 10 [28800/32087 (90%)] Loss: 2.812776 +2025-04-14 10:51:37,056 INFO Train Epoch: 10 [32000/32087 (100%)] Loss: 2.134148 +2025-04-14 10:53:01,536 INFO Accuracy qa: 69.58 % +2025-04-14 10:53:05,765 INFO Train Epoch: 11 [0/32087 (0%)] Loss: 2.108360 +2025-04-14 10:53:23,999 INFO Train Epoch: 11 [3200/32087 (10%)] Loss: 2.866842 +2025-04-14 10:53:42,706 INFO Train Epoch: 11 [6400/32087 (20%)] Loss: 2.067278 +2025-04-14 10:53:59,497 INFO Train Epoch: 11 [9600/32087 (30%)] Loss: 2.432280 +2025-04-14 10:54:17,526 INFO Train Epoch: 11 [12800/32087 (40%)] Loss: 1.771091 +2025-04-14 10:54:35,917 INFO Train Epoch: 11 [16000/32087 (50%)] Loss: 2.166154 +2025-04-14 10:54:52,526 INFO Train Epoch: 11 [19200/32087 (60%)] Loss: 2.538500 +2025-04-14 10:55:10,090 INFO Train Epoch: 11 [22400/32087 (70%)] Loss: 3.045098 +2025-04-14 10:55:29,980 INFO Train Epoch: 11 [25600/32087 (80%)] Loss: 2.229211 +2025-04-14 10:55:49,172 INFO Train Epoch: 11 [28800/32087 (90%)] Loss: 2.835342 +2025-04-14 10:56:06,453 INFO Train Epoch: 11 [32000/32087 (100%)] Loss: 2.495993 +2025-04-14 10:57:34,290 INFO Accuracy qa: 69.25 % +2025-04-14 10:57:38,106 INFO Train Epoch: 12 [0/32087 (0%)] Loss: 2.248176 +2025-04-14 10:57:59,456 INFO Train Epoch: 12 [3200/32087 (10%)] Loss: 2.405490 +2025-04-14 10:58:19,054 INFO Train Epoch: 12 [6400/32087 (20%)] Loss: 2.665315 +2025-04-14 10:58:37,799 INFO Train Epoch: 12 [9600/32087 (30%)] Loss: 2.817852 +2025-04-14 10:58:56,201 INFO Train Epoch: 12 [12800/32087 (40%)] Loss: 2.183017 +2025-04-14 10:59:14,957 INFO Train Epoch: 12 [16000/32087 (50%)] Loss: 2.124568 +2025-04-14 10:59:32,971 INFO Train Epoch: 12 [19200/32087 (60%)] Loss: 2.907912 +2025-04-14 10:59:53,722 INFO Train Epoch: 12 [22400/32087 (70%)] Loss: 2.602285 +2025-04-14 11:00:14,097 INFO Train Epoch: 12 [25600/32087 (80%)] Loss: 2.611593 +2025-04-14 11:00:33,515 INFO Train Epoch: 12 [28800/32087 (90%)] Loss: 2.537999 +2025-04-14 11:00:50,863 INFO Train Epoch: 12 [32000/32087 (100%)] Loss: 2.939048 +2025-04-14 11:02:18,610 INFO Accuracy qa: 70.40 % +2025-04-14 11:02:22,839 INFO Train Epoch: 13 [0/32087 (0%)] Loss: 2.420455 +2025-04-14 11:02:44,307 INFO Train Epoch: 13 [3200/32087 (10%)] Loss: 2.354044 +2025-04-14 11:03:04,426 INFO Train Epoch: 13 [6400/32087 (20%)] Loss: 2.056944 +2025-04-14 11:03:23,576 INFO Train Epoch: 13 [9600/32087 (30%)] Loss: 2.422443 +2025-04-14 11:03:42,872 INFO Train Epoch: 13 [12800/32087 (40%)] Loss: 2.480755 +2025-04-14 11:04:01,618 INFO Train Epoch: 13 [16000/32087 (50%)] Loss: 3.177324 +2025-04-14 11:04:19,074 INFO Train Epoch: 13 [19200/32087 (60%)] Loss: 2.415956 +2025-04-14 11:04:37,677 INFO Train Epoch: 13 [22400/32087 (70%)] Loss: 2.424115 +2025-04-14 11:04:55,912 INFO Train Epoch: 13 [25600/32087 (80%)] Loss: 1.903936 +2025-04-14 11:05:12,663 INFO Train Epoch: 13 [28800/32087 (90%)] Loss: 2.278404 +2025-04-14 11:05:28,591 INFO Train Epoch: 13 [32000/32087 (100%)] Loss: 2.322029 +2025-04-14 11:07:06,232 INFO Accuracy qa: 69.62 % +2025-04-14 11:07:11,317 INFO Train Epoch: 14 [0/32087 (0%)] Loss: 1.939461 +2025-04-14 11:07:33,694 INFO Train Epoch: 14 [3200/32087 (10%)] Loss: 2.427341 +2025-04-14 11:07:56,100 INFO Train Epoch: 14 [6400/32087 (20%)] Loss: 2.020065 +2025-04-14 11:08:16,306 INFO Train Epoch: 14 [9600/32087 (30%)] Loss: 2.091017 +2025-04-14 11:08:36,112 INFO Train Epoch: 14 [12800/32087 (40%)] Loss: 2.155982 +2025-04-14 11:08:55,767 INFO Train Epoch: 14 [16000/32087 (50%)] Loss: 2.395411 +2025-04-14 11:09:15,951 INFO Train Epoch: 14 [19200/32087 (60%)] Loss: 2.732013 +2025-04-14 11:09:35,224 INFO Train Epoch: 14 [22400/32087 (70%)] Loss: 3.010972 +2025-04-14 11:09:54,243 INFO Train Epoch: 14 [25600/32087 (80%)] Loss: 2.354290 +2025-04-14 11:10:12,298 INFO Train Epoch: 14 [28800/32087 (90%)] Loss: 2.782819 +2025-04-14 11:10:30,003 INFO Train Epoch: 14 [32000/32087 (100%)] Loss: 2.496970 +2025-04-14 11:11:57,476 INFO Accuracy qa: 68.25 % +2025-04-14 11:12:00,948 INFO Train Epoch: 15 [0/32087 (0%)] Loss: 2.133276 +2025-04-14 11:12:19,879 INFO Train Epoch: 15 [3200/32087 (10%)] Loss: 2.283743 +2025-04-14 11:12:39,311 INFO Train Epoch: 15 [6400/32087 (20%)] Loss: 2.093257 +2025-04-14 11:12:58,385 INFO Train Epoch: 15 [9600/32087 (30%)] Loss: 1.345488 +2025-04-14 11:13:17,475 INFO Train Epoch: 15 [12800/32087 (40%)] Loss: 2.201720 +2025-04-14 11:13:35,806 INFO Train Epoch: 15 [16000/32087 (50%)] Loss: 2.299014 +2025-04-14 11:13:56,197 INFO Train Epoch: 15 [19200/32087 (60%)] Loss: 2.880517 +2025-04-14 11:14:15,617 INFO Train Epoch: 15 [22400/32087 (70%)] Loss: 2.052952 +2025-04-14 11:14:32,007 INFO Train Epoch: 15 [25600/32087 (80%)] Loss: 2.646425 +2025-04-14 11:14:47,832 INFO Train Epoch: 15 [28800/32087 (90%)] Loss: 2.133982 +2025-04-14 11:15:02,515 INFO Train Epoch: 15 [32000/32087 (100%)] Loss: 2.435893 +2025-04-14 11:16:30,805 INFO Accuracy qa: 69.64 % +2025-04-14 11:16:33,917 INFO Train Epoch: 16 [0/32087 (0%)] Loss: 2.770658 +2025-04-14 11:16:54,049 INFO Train Epoch: 16 [3200/32087 (10%)] Loss: 2.114707 +2025-04-14 11:17:12,541 INFO Train Epoch: 16 [6400/32087 (20%)] Loss: 2.337739 +2025-04-14 11:17:32,054 INFO Train Epoch: 16 [9600/32087 (30%)] Loss: 2.165631 +2025-04-14 11:17:50,540 INFO Train Epoch: 16 [12800/32087 (40%)] Loss: 2.058621 +2025-04-14 11:18:10,643 INFO Train Epoch: 16 [16000/32087 (50%)] Loss: 2.025621 +2025-04-14 11:18:30,148 INFO Train Epoch: 16 [19200/32087 (60%)] Loss: 1.959853 +2025-04-14 11:18:49,251 INFO Train Epoch: 16 [22400/32087 (70%)] Loss: 1.649695 +2025-04-14 11:19:05,752 INFO Train Epoch: 16 [25600/32087 (80%)] Loss: 1.930649 +2025-04-14 11:19:22,547 INFO Train Epoch: 16 [28800/32087 (90%)] Loss: 1.944888 +2025-04-14 11:19:38,171 INFO Train Epoch: 16 [32000/32087 (100%)] Loss: 2.074628 +2025-04-14 11:21:08,399 INFO Accuracy qa: 71.95 % +2025-04-14 11:21:13,532 INFO Train Epoch: 17 [0/32087 (0%)] Loss: 2.053461 +2025-04-14 11:21:34,224 INFO Train Epoch: 17 [3200/32087 (10%)] Loss: 1.494969 +2025-04-14 11:21:53,479 INFO Train Epoch: 17 [6400/32087 (20%)] Loss: 2.271866 +2025-04-14 11:22:10,878 INFO Train Epoch: 17 [9600/32087 (30%)] Loss: 2.586744 +2025-04-14 11:22:29,435 INFO Train Epoch: 17 [12800/32087 (40%)] Loss: 1.925266 +2025-04-14 11:22:47,109 INFO Train Epoch: 17 [16000/32087 (50%)] Loss: 2.297150 +2025-04-14 11:23:05,349 INFO Train Epoch: 17 [19200/32087 (60%)] Loss: 1.843324 +2025-04-14 11:23:22,488 INFO Train Epoch: 17 [22400/32087 (70%)] Loss: 1.814588 +2025-04-14 11:23:38,173 INFO Train Epoch: 17 [25600/32087 (80%)] Loss: 1.766224 +2025-04-14 11:23:55,049 INFO Train Epoch: 17 [28800/32087 (90%)] Loss: 1.813595 +2025-04-14 11:24:10,647 INFO Train Epoch: 17 [32000/32087 (100%)] Loss: 2.039083 +2025-04-14 11:25:39,908 INFO Accuracy qa: 72.47 % +2025-04-14 11:25:44,111 INFO Train Epoch: 18 [0/32087 (0%)] Loss: 1.874120 +2025-04-14 11:26:03,733 INFO Train Epoch: 18 [3200/32087 (10%)] Loss: 2.051840 +2025-04-14 11:26:21,551 INFO Train Epoch: 18 [6400/32087 (20%)] Loss: 1.706292 +2025-04-14 11:26:41,312 INFO Train Epoch: 18 [9600/32087 (30%)] Loss: 2.305375 +2025-04-14 11:27:02,002 INFO Train Epoch: 18 [12800/32087 (40%)] Loss: 2.215552 +2025-04-14 11:27:22,419 INFO Train Epoch: 18 [16000/32087 (50%)] Loss: 1.982473 +2025-04-14 11:27:41,531 INFO Train Epoch: 18 [19200/32087 (60%)] Loss: 1.921500 +2025-04-14 11:27:58,637 INFO Train Epoch: 18 [22400/32087 (70%)] Loss: 1.899148 +2025-04-14 11:28:17,272 INFO Train Epoch: 18 [25600/32087 (80%)] Loss: 1.634368 +2025-04-14 11:28:36,293 INFO Train Epoch: 18 [28800/32087 (90%)] Loss: 2.000707 +2025-04-14 11:28:52,521 INFO Train Epoch: 18 [32000/32087 (100%)] Loss: 1.604654 +2025-04-14 11:30:23,461 INFO Accuracy qa: 72.58 % +2025-04-14 11:30:28,119 INFO Train Epoch: 19 [0/32087 (0%)] Loss: 1.698153 +2025-04-14 11:30:46,313 INFO Train Epoch: 19 [3200/32087 (10%)] Loss: 2.251816 +2025-04-14 11:31:05,669 INFO Train Epoch: 19 [6400/32087 (20%)] Loss: 1.913221 +2025-04-14 11:31:25,881 INFO Train Epoch: 19 [9600/32087 (30%)] Loss: 1.984487 +2025-04-14 11:31:46,123 INFO Train Epoch: 19 [12800/32087 (40%)] Loss: 2.163150 +2025-04-14 11:32:07,584 INFO Train Epoch: 19 [16000/32087 (50%)] Loss: 1.836262 +2025-04-14 11:32:23,349 INFO Train Epoch: 19 [19200/32087 (60%)] Loss: 1.674969 +2025-04-14 11:32:39,471 INFO Train Epoch: 19 [22400/32087 (70%)] Loss: 1.480457 +2025-04-14 11:32:57,056 INFO Train Epoch: 19 [25600/32087 (80%)] Loss: 2.022610 +2025-04-14 11:33:14,412 INFO Train Epoch: 19 [28800/32087 (90%)] Loss: 1.948217 +2025-04-14 11:33:29,878 INFO Train Epoch: 19 [32000/32087 (100%)] Loss: 1.777292 +2025-04-14 11:35:00,284 INFO Accuracy qa: 72.17 % +2025-04-14 11:35:04,992 INFO Train Epoch: 20 [0/32087 (0%)] Loss: 1.806003 +2025-04-14 11:35:25,129 INFO Train Epoch: 20 [3200/32087 (10%)] Loss: 1.586218 +2025-04-14 11:35:44,118 INFO Train Epoch: 20 [6400/32087 (20%)] Loss: 1.668882 +2025-04-14 11:36:04,878 INFO Train Epoch: 20 [9600/32087 (30%)] Loss: 2.059641 +2025-04-14 11:36:27,080 INFO Train Epoch: 20 [12800/32087 (40%)] Loss: 1.796649 +2025-04-14 11:36:47,052 INFO Train Epoch: 20 [16000/32087 (50%)] Loss: 2.269948 +2025-04-14 11:37:04,830 INFO Train Epoch: 20 [19200/32087 (60%)] Loss: 2.322330 +2025-04-14 11:37:21,216 INFO Train Epoch: 20 [22400/32087 (70%)] Loss: 2.193382 +2025-04-14 11:37:36,820 INFO Train Epoch: 20 [25600/32087 (80%)] Loss: 1.951292 +2025-04-14 11:37:52,679 INFO Train Epoch: 20 [28800/32087 (90%)] Loss: 1.945803 +2025-04-14 11:38:06,875 INFO Train Epoch: 20 [32000/32087 (100%)] Loss: 2.297598 +2025-04-14 11:39:32,725 INFO Accuracy qa: 72.10 % +2025-04-14 11:39:35,849 INFO Train Epoch: 21 [0/32087 (0%)] Loss: 1.609164 +2025-04-14 11:39:58,728 INFO Train Epoch: 21 [3200/32087 (10%)] Loss: 1.539059 +2025-04-14 11:40:19,446 INFO Train Epoch: 21 [6400/32087 (20%)] Loss: 1.966648 +2025-04-14 11:40:40,643 INFO Train Epoch: 21 [9600/32087 (30%)] Loss: 1.996237 +2025-04-14 11:41:01,640 INFO Train Epoch: 21 [12800/32087 (40%)] Loss: 1.980579 +2025-04-14 11:41:21,708 INFO Train Epoch: 21 [16000/32087 (50%)] Loss: 2.064622 +2025-04-14 11:41:41,669 INFO Train Epoch: 21 [19200/32087 (60%)] Loss: 1.796175 +2025-04-14 11:42:01,688 INFO Train Epoch: 21 [22400/32087 (70%)] Loss: 1.825450 +2025-04-14 11:42:20,844 INFO Train Epoch: 21 [25600/32087 (80%)] Loss: 1.848216 +2025-04-14 11:42:40,623 INFO Train Epoch: 21 [28800/32087 (90%)] Loss: 2.462565 +2025-04-14 11:43:00,612 INFO Train Epoch: 21 [32000/32087 (100%)] Loss: 2.150781 +2025-04-14 11:44:31,037 INFO Accuracy qa: 71.80 % +2025-04-14 11:44:35,815 INFO Train Epoch: 22 [0/32087 (0%)] Loss: 2.072798 +2025-04-14 11:44:58,241 INFO Train Epoch: 22 [3200/32087 (10%)] Loss: 2.029965 +2025-04-14 11:45:20,906 INFO Train Epoch: 22 [6400/32087 (20%)] Loss: 1.845814 +2025-04-14 11:45:41,479 INFO Train Epoch: 22 [9600/32087 (30%)] Loss: 1.551794 +2025-04-14 11:46:00,800 INFO Train Epoch: 22 [12800/32087 (40%)] Loss: 2.218961 +2025-04-14 11:46:19,700 INFO Train Epoch: 22 [16000/32087 (50%)] Loss: 1.525546 +2025-04-14 11:46:37,529 INFO Train Epoch: 22 [19200/32087 (60%)] Loss: 1.766831 +2025-04-14 11:46:56,324 INFO Train Epoch: 22 [22400/32087 (70%)] Loss: 2.317405 +2025-04-14 11:47:13,978 INFO Train Epoch: 22 [25600/32087 (80%)] Loss: 1.928162 +2025-04-14 11:47:34,215 INFO Train Epoch: 22 [28800/32087 (90%)] Loss: 1.734712 +2025-04-14 11:47:52,385 INFO Train Epoch: 22 [32000/32087 (100%)] Loss: 1.843994 +2025-04-14 11:49:24,071 INFO Accuracy qa: 72.19 % +2025-04-14 11:49:27,323 INFO Train Epoch: 23 [0/32087 (0%)] Loss: 2.011923 +2025-04-14 11:49:49,555 INFO Train Epoch: 23 [3200/32087 (10%)] Loss: 1.792078 +2025-04-14 11:50:07,028 INFO Train Epoch: 23 [6400/32087 (20%)] Loss: 1.837350 +2025-04-14 11:50:23,823 INFO Train Epoch: 23 [9600/32087 (30%)] Loss: 1.795320 +2025-04-14 11:50:41,200 INFO Train Epoch: 23 [12800/32087 (40%)] Loss: 1.758492 +2025-04-14 11:50:58,386 INFO Train Epoch: 23 [16000/32087 (50%)] Loss: 1.719031 +2025-04-14 11:51:16,462 INFO Train Epoch: 23 [19200/32087 (60%)] Loss: 1.838186 +2025-04-14 11:51:36,539 INFO Train Epoch: 23 [22400/32087 (70%)] Loss: 1.790306 +2025-04-14 11:51:56,424 INFO Train Epoch: 23 [25600/32087 (80%)] Loss: 2.113330 +2025-04-14 11:52:15,441 INFO Train Epoch: 23 [28800/32087 (90%)] Loss: 1.531642 +2025-04-14 11:52:32,137 INFO Train Epoch: 23 [32000/32087 (100%)] Loss: 1.745036 +2025-04-14 11:54:02,606 INFO Accuracy qa: 72.03 % +2025-04-14 11:54:06,147 INFO Train Epoch: 24 [0/32087 (0%)] Loss: 1.414125 +2025-04-14 11:54:23,585 INFO Train Epoch: 24 [3200/32087 (10%)] Loss: 1.838163 +2025-04-14 11:54:39,670 INFO Train Epoch: 24 [6400/32087 (20%)] Loss: 1.456350 +2025-04-14 11:54:55,694 INFO Train Epoch: 24 [9600/32087 (30%)] Loss: 1.674067 +2025-04-14 11:55:11,686 INFO Train Epoch: 24 [12800/32087 (40%)] Loss: 1.767379 +2025-04-14 11:55:27,811 INFO Train Epoch: 24 [16000/32087 (50%)] Loss: 1.609238 +2025-04-14 11:55:43,610 INFO Train Epoch: 24 [19200/32087 (60%)] Loss: 2.067226 +2025-04-14 11:56:02,565 INFO Train Epoch: 24 [22400/32087 (70%)] Loss: 1.904557 +2025-04-14 11:56:21,063 INFO Train Epoch: 24 [25600/32087 (80%)] Loss: 1.808369 +2025-04-14 11:56:39,657 INFO Train Epoch: 24 [28800/32087 (90%)] Loss: 1.586159 +2025-04-14 11:56:56,731 INFO Train Epoch: 24 [32000/32087 (100%)] Loss: 1.643426 +2025-04-14 11:58:29,883 INFO Accuracy qa: 71.95 % +2025-04-14 11:58:34,832 INFO Train Epoch: 25 [0/32087 (0%)] Loss: 1.674480 +2025-04-14 11:58:52,857 INFO Train Epoch: 25 [3200/32087 (10%)] Loss: 1.434650 +2025-04-14 11:59:09,643 INFO Train Epoch: 25 [6400/32087 (20%)] Loss: 1.627827 +2025-04-14 11:59:26,532 INFO Train Epoch: 25 [9600/32087 (30%)] Loss: 1.651554 +2025-04-14 11:59:42,859 INFO Train Epoch: 25 [12800/32087 (40%)] Loss: 1.827000 +2025-04-14 11:59:59,343 INFO Train Epoch: 25 [16000/32087 (50%)] Loss: 2.031860 +2025-04-14 12:00:16,111 INFO Train Epoch: 25 [19200/32087 (60%)] Loss: 1.426465 +2025-04-14 12:00:36,580 INFO Train Epoch: 25 [22400/32087 (70%)] Loss: 1.853296 +2025-04-14 12:00:56,654 INFO Train Epoch: 25 [25600/32087 (80%)] Loss: 1.739469 +2025-04-14 12:01:14,413 INFO Train Epoch: 25 [28800/32087 (90%)] Loss: 1.872587 +2025-04-14 12:01:32,700 INFO Train Epoch: 25 [32000/32087 (100%)] Loss: 2.027354 +2025-04-14 12:03:03,739 INFO Accuracy qa: 72.08 % +2025-04-14 12:03:07,271 INFO Train Epoch: 26 [0/32087 (0%)] Loss: 1.780359 +2025-04-14 12:03:28,073 INFO Train Epoch: 26 [3200/32087 (10%)] Loss: 1.844555 +2025-04-14 12:03:46,428 INFO Train Epoch: 26 [6400/32087 (20%)] Loss: 2.039570 +2025-04-14 12:04:04,909 INFO Train Epoch: 26 [9600/32087 (30%)] Loss: 2.331376 +2025-04-14 12:04:22,475 INFO Train Epoch: 26 [12800/32087 (40%)] Loss: 1.786943 +2025-04-14 12:04:43,672 INFO Train Epoch: 26 [16000/32087 (50%)] Loss: 2.150998 +2025-04-14 12:05:03,762 INFO Train Epoch: 26 [19200/32087 (60%)] Loss: 1.665090 +2025-04-14 12:05:24,454 INFO Train Epoch: 26 [22400/32087 (70%)] Loss: 1.760691 +2025-04-14 12:05:43,521 INFO Train Epoch: 26 [25600/32087 (80%)] Loss: 1.740227 +2025-04-14 12:06:03,720 INFO Train Epoch: 26 [28800/32087 (90%)] Loss: 2.076025 +2025-04-14 12:06:21,444 INFO Train Epoch: 26 [32000/32087 (100%)] Loss: 1.859889 +2025-04-14 12:07:55,208 INFO Accuracy qa: 71.99 % +2025-04-14 12:07:59,097 INFO Train Epoch: 27 [0/32087 (0%)] Loss: 1.904171 +2025-04-14 12:08:17,424 INFO Train Epoch: 27 [3200/32087 (10%)] Loss: 1.570187 +2025-04-14 12:08:35,713 INFO Train Epoch: 27 [6400/32087 (20%)] Loss: 1.760596 +2025-04-14 12:08:52,830 INFO Train Epoch: 27 [9600/32087 (30%)] Loss: 1.696624 +2025-04-14 12:09:09,300 INFO Train Epoch: 27 [12800/32087 (40%)] Loss: 1.869858 +2025-04-14 12:09:28,190 INFO Train Epoch: 27 [16000/32087 (50%)] Loss: 1.878072 +2025-04-14 12:09:47,573 INFO Train Epoch: 27 [19200/32087 (60%)] Loss: 1.624918 +2025-04-14 12:10:07,698 INFO Train Epoch: 27 [22400/32087 (70%)] Loss: 1.682402 +2025-04-14 12:10:26,445 INFO Train Epoch: 27 [25600/32087 (80%)] Loss: 1.647079 +2025-04-14 12:10:44,969 INFO Train Epoch: 27 [28800/32087 (90%)] Loss: 2.183108 +2025-04-14 12:11:03,285 INFO Train Epoch: 27 [32000/32087 (100%)] Loss: 1.502120 +2025-04-14 12:12:36,942 INFO Accuracy qa: 72.14 % +2025-04-14 12:12:41,252 INFO Train Epoch: 28 [0/32087 (0%)] Loss: 1.981027 +2025-04-14 12:12:58,991 INFO Train Epoch: 28 [3200/32087 (10%)] Loss: 1.896780 +2025-04-14 12:13:16,358 INFO Train Epoch: 28 [6400/32087 (20%)] Loss: 1.212755 +2025-04-14 12:13:34,603 INFO Train Epoch: 28 [9600/32087 (30%)] Loss: 1.959053 +2025-04-14 12:13:52,841 INFO Train Epoch: 28 [12800/32087 (40%)] Loss: 1.723585 +2025-04-14 12:14:12,125 INFO Train Epoch: 28 [16000/32087 (50%)] Loss: 1.714482 +2025-04-14 12:14:33,447 INFO Train Epoch: 28 [19200/32087 (60%)] Loss: 1.672344 +2025-04-14 12:14:53,466 INFO Train Epoch: 28 [22400/32087 (70%)] Loss: 1.418555 +2025-04-14 12:15:13,116 INFO Train Epoch: 28 [25600/32087 (80%)] Loss: 1.836178 +2025-04-14 12:15:32,134 INFO Train Epoch: 28 [28800/32087 (90%)] Loss: 1.442317 +2025-04-14 12:15:53,073 INFO Train Epoch: 28 [32000/32087 (100%)] Loss: 1.416609 +2025-04-14 12:17:28,442 INFO Accuracy qa: 71.95 % +2025-04-14 12:17:32,507 INFO Train Epoch: 29 [0/32087 (0%)] Loss: 1.855221 +2025-04-14 12:17:50,010 INFO Train Epoch: 29 [3200/32087 (10%)] Loss: 1.477351 +2025-04-14 12:18:06,773 INFO Train Epoch: 29 [6400/32087 (20%)] Loss: 1.854123 +2025-04-14 12:18:25,113 INFO Train Epoch: 29 [9600/32087 (30%)] Loss: 1.982599 +2025-04-14 12:18:46,204 INFO Train Epoch: 29 [12800/32087 (40%)] Loss: 2.021195 +2025-04-14 12:19:07,556 INFO Train Epoch: 29 [16000/32087 (50%)] Loss: 1.896845 +2025-04-14 12:19:28,055 INFO Train Epoch: 29 [19200/32087 (60%)] Loss: 1.813936 +2025-04-14 12:19:48,033 INFO Train Epoch: 29 [22400/32087 (70%)] Loss: 1.990085 +2025-04-14 12:20:08,777 INFO Train Epoch: 29 [25600/32087 (80%)] Loss: 1.885434 +2025-04-14 12:20:31,371 INFO Train Epoch: 29 [28800/32087 (90%)] Loss: 1.506265 +2025-04-14 12:20:53,689 INFO Train Epoch: 29 [32000/32087 (100%)] Loss: 1.395984 +2025-04-14 12:22:25,313 INFO Accuracy qa: 72.23 % +2025-04-14 12:22:30,084 INFO Train Epoch: 30 [0/32087 (0%)] Loss: 1.799727 +2025-04-14 12:22:52,205 INFO Train Epoch: 30 [3200/32087 (10%)] Loss: 1.339992 +2025-04-14 12:23:13,450 INFO Train Epoch: 30 [6400/32087 (20%)] Loss: 1.438607 +2025-04-14 12:23:35,423 INFO Train Epoch: 30 [9600/32087 (30%)] Loss: 1.614639 +2025-04-14 12:23:54,661 INFO Train Epoch: 30 [12800/32087 (40%)] Loss: 1.573700 +2025-04-14 12:24:15,568 INFO Train Epoch: 30 [16000/32087 (50%)] Loss: 1.657360 +2025-04-14 12:24:35,717 INFO Train Epoch: 30 [19200/32087 (60%)] Loss: 1.687486 +2025-04-14 12:24:58,285 INFO Train Epoch: 30 [22400/32087 (70%)] Loss: 1.986454 +2025-04-14 12:25:20,032 INFO Train Epoch: 30 [25600/32087 (80%)] Loss: 1.833438 +2025-04-14 12:25:40,091 INFO Train Epoch: 30 [28800/32087 (90%)] Loss: 1.645882 +2025-04-14 12:25:57,354 INFO Train Epoch: 30 [32000/32087 (100%)] Loss: 1.727249 +2025-04-14 12:27:25,865 INFO Accuracy qa: 72.03 % +2025-04-14 12:27:31,584 INFO Train Epoch: 31 [0/32087 (0%)] Loss: 1.578964 +2025-04-14 12:27:52,608 INFO Train Epoch: 31 [3200/32087 (10%)] Loss: 2.056818 +2025-04-14 12:28:11,510 INFO Train Epoch: 31 [6400/32087 (20%)] Loss: 2.024736 +2025-04-14 12:28:29,454 INFO Train Epoch: 31 [9600/32087 (30%)] Loss: 1.401700 +2025-04-14 12:28:49,674 INFO Train Epoch: 31 [12800/32087 (40%)] Loss: 1.741670 +2025-04-14 12:29:07,977 INFO Train Epoch: 31 [16000/32087 (50%)] Loss: 1.524657 +2025-04-14 12:29:29,424 INFO Train Epoch: 31 [19200/32087 (60%)] Loss: 1.393100 +2025-04-14 12:29:51,588 INFO Train Epoch: 31 [22400/32087 (70%)] Loss: 1.560466 +2025-04-14 12:30:10,472 INFO Train Epoch: 31 [25600/32087 (80%)] Loss: 1.688342 +2025-04-14 12:30:29,235 INFO Train Epoch: 31 [28800/32087 (90%)] Loss: 2.020736 +2025-04-14 12:30:45,257 INFO Train Epoch: 31 [32000/32087 (100%)] Loss: 1.852272 +2025-04-14 12:32:14,683 INFO Accuracy qa: 72.19 % +2025-04-14 12:32:17,603 INFO Train Epoch: 32 [0/32087 (0%)] Loss: 1.837324 +2025-04-14 12:32:36,071 INFO Train Epoch: 32 [3200/32087 (10%)] Loss: 1.356313 +2025-04-14 12:32:53,502 INFO Train Epoch: 32 [6400/32087 (20%)] Loss: 1.726659 +2025-04-14 12:33:11,708 INFO Train Epoch: 32 [9600/32087 (30%)] Loss: 1.434246 +2025-04-14 12:33:30,172 INFO Train Epoch: 32 [12800/32087 (40%)] Loss: 1.588535 +2025-04-14 12:33:48,782 INFO Train Epoch: 32 [16000/32087 (50%)] Loss: 1.280924 +2025-04-14 12:34:09,404 INFO Train Epoch: 32 [19200/32087 (60%)] Loss: 1.508965 +2025-04-14 12:34:30,347 INFO Train Epoch: 32 [22400/32087 (70%)] Loss: 1.830431 +2025-04-14 12:34:48,723 INFO Train Epoch: 32 [25600/32087 (80%)] Loss: 1.735842 +2025-04-14 12:35:07,015 INFO Train Epoch: 32 [28800/32087 (90%)] Loss: 1.366565 +2025-04-14 12:35:23,238 INFO Train Epoch: 32 [32000/32087 (100%)] Loss: 1.748628 +2025-04-14 12:36:48,322 INFO Accuracy qa: 72.03 % +2025-04-14 12:36:52,753 INFO Train Epoch: 33 [0/32087 (0%)] Loss: 1.738757 +2025-04-14 12:37:13,103 INFO Train Epoch: 33 [3200/32087 (10%)] Loss: 2.114880 +2025-04-14 12:37:29,652 INFO Train Epoch: 33 [6400/32087 (20%)] Loss: 1.490788 +2025-04-14 12:37:47,464 INFO Train Epoch: 33 [9600/32087 (30%)] Loss: 1.956565 +2025-04-14 12:38:05,980 INFO Train Epoch: 33 [12800/32087 (40%)] Loss: 1.862638 +2025-04-14 12:38:27,043 INFO Train Epoch: 33 [16000/32087 (50%)] Loss: 2.020386 +2025-04-14 12:38:46,749 INFO Train Epoch: 33 [19200/32087 (60%)] Loss: 1.114220 +2025-04-14 12:39:04,401 INFO Train Epoch: 33 [22400/32087 (70%)] Loss: 1.578699 +2025-04-14 12:39:21,781 INFO Train Epoch: 33 [25600/32087 (80%)] Loss: 1.770019 +2025-04-14 12:39:40,058 INFO Train Epoch: 33 [28800/32087 (90%)] Loss: 1.627707 +2025-04-14 12:39:55,970 INFO Train Epoch: 33 [32000/32087 (100%)] Loss: 1.923615 +2025-04-14 12:41:21,596 INFO Accuracy qa: 72.08 % +2025-04-14 12:41:24,743 INFO Train Epoch: 34 [0/32087 (0%)] Loss: 1.630535 +2025-04-14 12:41:43,433 INFO Train Epoch: 34 [3200/32087 (10%)] Loss: 1.775863 +2025-04-14 12:42:00,553 INFO Train Epoch: 34 [6400/32087 (20%)] Loss: 1.527276 +2025-04-14 12:42:18,999 INFO Train Epoch: 34 [9600/32087 (30%)] Loss: 1.530616 +2025-04-14 12:42:38,058 INFO Train Epoch: 34 [12800/32087 (40%)] Loss: 1.676584 +2025-04-14 12:42:58,104 INFO Train Epoch: 34 [16000/32087 (50%)] Loss: 1.739800 +2025-04-14 12:43:18,188 INFO Train Epoch: 34 [19200/32087 (60%)] Loss: 1.861743 +2025-04-14 12:43:35,976 INFO Train Epoch: 34 [22400/32087 (70%)] Loss: 1.819747 +2025-04-14 12:43:53,678 INFO Train Epoch: 34 [25600/32087 (80%)] Loss: 2.039750 +2025-04-14 12:44:10,968 INFO Train Epoch: 34 [28800/32087 (90%)] Loss: 1.707945 +2025-04-14 12:44:26,114 INFO Train Epoch: 34 [32000/32087 (100%)] Loss: 1.480588 +2025-04-14 12:45:54,130 INFO Accuracy qa: 72.21 % +2025-04-14 12:45:56,797 INFO Train Epoch: 35 [0/32087 (0%)] Loss: 1.715782 +2025-04-14 12:46:15,885 INFO Train Epoch: 35 [3200/32087 (10%)] Loss: 1.511289 +2025-04-14 12:46:33,376 INFO Train Epoch: 35 [6400/32087 (20%)] Loss: 1.696959 +2025-04-14 12:46:50,390 INFO Train Epoch: 35 [9600/32087 (30%)] Loss: 1.416888 +2025-04-14 12:47:08,603 INFO Train Epoch: 35 [12800/32087 (40%)] Loss: 1.793710 +2025-04-14 12:47:27,716 INFO Train Epoch: 35 [16000/32087 (50%)] Loss: 1.461148 +2025-04-14 12:47:45,760 INFO Train Epoch: 35 [19200/32087 (60%)] Loss: 1.907256 +2025-04-14 12:48:02,847 INFO Train Epoch: 35 [22400/32087 (70%)] Loss: 1.118536 +2025-04-14 12:48:20,183 INFO Train Epoch: 35 [25600/32087 (80%)] Loss: 1.123066 +2025-04-14 12:48:37,417 INFO Train Epoch: 35 [28800/32087 (90%)] Loss: 1.844507 +2025-04-14 12:48:51,794 INFO Train Epoch: 35 [32000/32087 (100%)] Loss: 1.929952 +2025-04-14 12:50:19,128 INFO Accuracy qa: 72.34 % +2025-04-14 12:50:23,055 INFO Train Epoch: 36 [0/32087 (0%)] Loss: 1.872965 +2025-04-14 12:50:42,326 INFO Train Epoch: 36 [3200/32087 (10%)] Loss: 1.572053 +2025-04-14 12:51:00,725 INFO Train Epoch: 36 [6400/32087 (20%)] Loss: 1.449090 +2025-04-14 12:51:18,701 INFO Train Epoch: 36 [9600/32087 (30%)] Loss: 1.825141 +2025-04-14 12:51:39,994 INFO Train Epoch: 36 [12800/32087 (40%)] Loss: 1.553216 +2025-04-14 12:51:59,591 INFO Train Epoch: 36 [16000/32087 (50%)] Loss: 1.631071 +2025-04-14 12:52:19,061 INFO Train Epoch: 36 [19200/32087 (60%)] Loss: 1.461725 +2025-04-14 12:52:37,976 INFO Train Epoch: 36 [22400/32087 (70%)] Loss: 1.314526 +2025-04-14 12:52:57,220 INFO Train Epoch: 36 [25600/32087 (80%)] Loss: 1.860008 +2025-04-14 12:53:15,625 INFO Train Epoch: 36 [28800/32087 (90%)] Loss: 1.612849 +2025-04-14 12:53:30,304 INFO Train Epoch: 36 [32000/32087 (100%)] Loss: 1.691073 +2025-04-14 12:54:56,343 INFO Accuracy qa: 72.17 % +2025-04-14 12:55:01,234 INFO Train Epoch: 37 [0/32087 (0%)] Loss: 1.355526 +2025-04-14 12:55:18,763 INFO Train Epoch: 37 [3200/32087 (10%)] Loss: 1.500384 +2025-04-14 12:55:36,653 INFO Train Epoch: 37 [6400/32087 (20%)] Loss: 1.792744 +2025-04-14 12:55:58,041 INFO Train Epoch: 37 [9600/32087 (30%)] Loss: 1.500546 +2025-04-14 12:56:17,818 INFO Train Epoch: 37 [12800/32087 (40%)] Loss: 1.619806 +2025-04-14 12:56:38,113 INFO Train Epoch: 37 [16000/32087 (50%)] Loss: 1.422303 +2025-04-14 12:56:57,436 INFO Train Epoch: 37 [19200/32087 (60%)] Loss: 1.933563 +2025-04-14 12:57:16,045 INFO Train Epoch: 37 [22400/32087 (70%)] Loss: 1.504056 +2025-04-14 12:57:34,568 INFO Train Epoch: 37 [25600/32087 (80%)] Loss: 1.266483 +2025-04-14 12:57:51,296 INFO Train Epoch: 37 [28800/32087 (90%)] Loss: 1.832270 +2025-04-14 12:58:05,662 INFO Train Epoch: 37 [32000/32087 (100%)] Loss: 1.501593 +2025-04-14 12:59:32,862 INFO Accuracy qa: 72.32 % +2025-04-14 12:59:36,467 INFO Train Epoch: 38 [0/32087 (0%)] Loss: 1.691063 +2025-04-14 12:59:56,841 INFO Train Epoch: 38 [3200/32087 (10%)] Loss: 1.521386 +2025-04-14 13:00:14,163 INFO Train Epoch: 38 [6400/32087 (20%)] Loss: 1.843277 +2025-04-14 13:00:34,356 INFO Train Epoch: 38 [9600/32087 (30%)] Loss: 1.734233 +2025-04-14 13:00:54,298 INFO Train Epoch: 38 [12800/32087 (40%)] Loss: 1.586819 +2025-04-14 13:01:13,596 INFO Train Epoch: 38 [16000/32087 (50%)] Loss: 1.539544 +2025-04-14 13:01:32,794 INFO Train Epoch: 38 [19200/32087 (60%)] Loss: 1.804545 +2025-04-14 13:01:51,337 INFO Train Epoch: 38 [22400/32087 (70%)] Loss: 1.250725 +2025-04-14 13:02:10,000 INFO Train Epoch: 38 [25600/32087 (80%)] Loss: 1.675895 +2025-04-14 13:02:27,036 INFO Train Epoch: 38 [28800/32087 (90%)] Loss: 1.441445 +2025-04-14 13:02:43,002 INFO Train Epoch: 38 [32000/32087 (100%)] Loss: 2.040500 +2025-04-14 13:04:08,693 INFO Accuracy qa: 72.23 % +2025-04-14 13:04:11,844 INFO Train Epoch: 39 [0/32087 (0%)] Loss: 1.816972 +2025-04-14 13:04:32,806 INFO Train Epoch: 39 [3200/32087 (10%)] Loss: 1.332884 +2025-04-14 13:04:50,966 INFO Train Epoch: 39 [6400/32087 (20%)] Loss: 1.528789 +2025-04-14 13:05:12,102 INFO Train Epoch: 39 [9600/32087 (30%)] Loss: 1.528836 +2025-04-14 13:05:32,257 INFO Train Epoch: 39 [12800/32087 (40%)] Loss: 1.557734 +2025-04-14 13:05:50,293 INFO Train Epoch: 39 [16000/32087 (50%)] Loss: 1.391184 +2025-04-14 13:06:08,530 INFO Train Epoch: 39 [19200/32087 (60%)] Loss: 1.510569 +2025-04-14 13:06:25,778 INFO Train Epoch: 39 [22400/32087 (70%)] Loss: 1.548232 +2025-04-14 13:06:44,402 INFO Train Epoch: 39 [25600/32087 (80%)] Loss: 1.746763 +2025-04-14 13:07:01,783 INFO Train Epoch: 39 [28800/32087 (90%)] Loss: 1.779842 +2025-04-14 13:07:17,692 INFO Train Epoch: 39 [32000/32087 (100%)] Loss: 1.450032 +2025-04-14 13:08:47,269 INFO Accuracy qa: 72.21 % +2025-04-14 13:08:52,105 INFO Train Epoch: 40 [0/32087 (0%)] Loss: 2.020732 +2025-04-14 13:09:11,884 INFO Train Epoch: 40 [3200/32087 (10%)] Loss: 1.551450 +2025-04-14 13:09:30,598 INFO Train Epoch: 40 [6400/32087 (20%)] Loss: 1.568301 +2025-04-14 13:09:50,734 INFO Train Epoch: 40 [9600/32087 (30%)] Loss: 1.471283 +2025-04-14 13:10:10,928 INFO Train Epoch: 40 [12800/32087 (40%)] Loss: 1.722839 +2025-04-14 13:10:28,237 INFO Train Epoch: 40 [16000/32087 (50%)] Loss: 1.855974 +2025-04-14 13:10:46,880 INFO Train Epoch: 40 [19200/32087 (60%)] Loss: 1.596722 +2025-04-14 13:11:04,072 INFO Train Epoch: 40 [22400/32087 (70%)] Loss: 1.462081 +2025-04-14 13:11:21,834 INFO Train Epoch: 40 [25600/32087 (80%)] Loss: 1.828652 +2025-04-14 13:11:38,312 INFO Train Epoch: 40 [28800/32087 (90%)] Loss: 1.867502 +2025-04-14 13:11:54,551 INFO Train Epoch: 40 [32000/32087 (100%)] Loss: 1.545294 +2025-04-14 13:13:20,085 INFO Accuracy qa: 72.14 % +2025-04-14 13:13:24,485 INFO Train Epoch: 41 [0/32087 (0%)] Loss: 1.916310 +2025-04-14 13:13:43,693 INFO Train Epoch: 41 [3200/32087 (10%)] Loss: 1.924943 +2025-04-14 13:14:02,227 INFO Train Epoch: 41 [6400/32087 (20%)] Loss: 1.678710 +2025-04-14 13:14:21,878 INFO Train Epoch: 41 [9600/32087 (30%)] Loss: 1.730602 +2025-04-14 13:14:40,295 INFO Train Epoch: 41 [12800/32087 (40%)] Loss: 1.806675 +2025-04-14 13:14:58,000 INFO Train Epoch: 41 [16000/32087 (50%)] Loss: 1.556456 +2025-04-14 13:15:15,615 INFO Train Epoch: 41 [19200/32087 (60%)] Loss: 1.408659 +2025-04-14 13:15:33,039 INFO Train Epoch: 41 [22400/32087 (70%)] Loss: 1.735960 +2025-04-14 13:15:49,779 INFO Train Epoch: 41 [25600/32087 (80%)] Loss: 1.810587 +2025-04-14 13:16:05,113 INFO Train Epoch: 41 [28800/32087 (90%)] Loss: 1.032327 +2025-04-14 13:16:20,511 INFO Train Epoch: 41 [32000/32087 (100%)] Loss: 1.277197 +2025-04-14 13:17:49,729 INFO Accuracy qa: 72.27 % +2025-04-14 13:17:54,092 INFO Train Epoch: 42 [0/32087 (0%)] Loss: 2.188370 +2025-04-14 13:18:15,002 INFO Train Epoch: 42 [3200/32087 (10%)] Loss: 2.025401 +2025-04-14 13:18:36,005 INFO Train Epoch: 42 [6400/32087 (20%)] Loss: 1.542981 +2025-04-14 13:18:56,640 INFO Train Epoch: 42 [9600/32087 (30%)] Loss: 1.576555 +2025-04-14 13:19:16,042 INFO Train Epoch: 42 [12800/32087 (40%)] Loss: 1.523107 +2025-04-14 13:19:33,701 INFO Train Epoch: 42 [16000/32087 (50%)] Loss: 1.587229 +2025-04-14 13:19:51,735 INFO Train Epoch: 42 [19200/32087 (60%)] Loss: 1.713000 +2025-04-14 13:20:09,115 INFO Train Epoch: 42 [22400/32087 (70%)] Loss: 1.164041 +2025-04-14 13:20:26,403 INFO Train Epoch: 42 [25600/32087 (80%)] Loss: 1.631903 +2025-04-14 13:20:43,786 INFO Train Epoch: 42 [28800/32087 (90%)] Loss: 1.777994 +2025-04-14 13:21:02,881 INFO Train Epoch: 42 [32000/32087 (100%)] Loss: 1.430958 +2025-04-14 13:22:32,712 INFO Accuracy qa: 72.08 % +2025-04-14 13:22:36,614 INFO Train Epoch: 43 [0/32087 (0%)] Loss: 1.401459 +2025-04-14 13:22:55,350 INFO Train Epoch: 43 [3200/32087 (10%)] Loss: 1.834039 +2025-04-14 13:23:12,886 INFO Train Epoch: 43 [6400/32087 (20%)] Loss: 1.624680 +2025-04-14 13:23:30,354 INFO Train Epoch: 43 [9600/32087 (30%)] Loss: 1.826452 +2025-04-14 13:23:47,489 INFO Train Epoch: 43 [12800/32087 (40%)] Loss: 1.426255 +2025-04-14 13:24:04,347 INFO Train Epoch: 43 [16000/32087 (50%)] Loss: 1.701214 +2025-04-14 13:24:21,176 INFO Train Epoch: 43 [19200/32087 (60%)] Loss: 1.706947 +2025-04-14 13:24:38,299 INFO Train Epoch: 43 [22400/32087 (70%)] Loss: 1.403629 +2025-04-14 13:24:55,804 INFO Train Epoch: 43 [25600/32087 (80%)] Loss: 1.811090 +2025-04-14 13:25:14,859 INFO Train Epoch: 43 [28800/32087 (90%)] Loss: 2.068933 +2025-04-14 13:25:31,152 INFO Train Epoch: 43 [32000/32087 (100%)] Loss: 1.727444 +2025-04-14 13:26:59,976 INFO Accuracy qa: 71.97 % +2025-04-14 13:27:04,178 INFO Train Epoch: 44 [0/32087 (0%)] Loss: 1.637239 +2025-04-14 13:27:21,743 INFO Train Epoch: 44 [3200/32087 (10%)] Loss: 2.015133 +2025-04-14 13:27:39,560 INFO Train Epoch: 44 [6400/32087 (20%)] Loss: 1.673677 +2025-04-14 13:27:55,066 INFO Train Epoch: 44 [9600/32087 (30%)] Loss: 1.457575 +2025-04-14 13:28:11,129 INFO Train Epoch: 44 [12800/32087 (40%)] Loss: 2.091758 +2025-04-14 13:28:27,167 INFO Train Epoch: 44 [16000/32087 (50%)] Loss: 2.000785 +2025-04-14 13:28:43,675 INFO Train Epoch: 44 [19200/32087 (60%)] Loss: 1.614348 +2025-04-14 13:29:00,040 INFO Train Epoch: 44 [22400/32087 (70%)] Loss: 2.123912 +2025-04-14 13:29:16,177 INFO Train Epoch: 44 [25600/32087 (80%)] Loss: 1.947338 +2025-04-14 13:29:34,733 INFO Train Epoch: 44 [28800/32087 (90%)] Loss: 1.634453 +2025-04-14 13:29:51,371 INFO Train Epoch: 44 [32000/32087 (100%)] Loss: 1.473607 +2025-04-14 13:31:17,569 INFO Accuracy qa: 72.14 % +2025-04-14 13:31:22,691 INFO Train Epoch: 45 [0/32087 (0%)] Loss: 1.578863 +2025-04-14 13:31:40,170 INFO Train Epoch: 45 [3200/32087 (10%)] Loss: 1.435711 +2025-04-14 13:31:58,635 INFO Train Epoch: 45 [6400/32087 (20%)] Loss: 1.664162 +2025-04-14 13:32:15,283 INFO Train Epoch: 45 [9600/32087 (30%)] Loss: 1.645000 +2025-04-14 13:32:31,141 INFO Train Epoch: 45 [12800/32087 (40%)] Loss: 1.437680 +2025-04-14 13:32:47,046 INFO Train Epoch: 45 [16000/32087 (50%)] Loss: 1.423404 +2025-04-14 13:33:02,275 INFO Train Epoch: 45 [19200/32087 (60%)] Loss: 1.735272 +2025-04-14 13:33:17,381 INFO Train Epoch: 45 [22400/32087 (70%)] Loss: 1.324839 +2025-04-14 13:33:33,034 INFO Train Epoch: 45 [25600/32087 (80%)] Loss: 1.480595 +2025-04-14 13:33:50,162 INFO Train Epoch: 45 [28800/32087 (90%)] Loss: 1.687765 +2025-04-14 13:34:06,817 INFO Train Epoch: 45 [32000/32087 (100%)] Loss: 1.353075 +2025-04-14 13:35:38,621 INFO Accuracy qa: 72.27 % +2025-04-14 13:35:43,582 INFO Train Epoch: 46 [0/32087 (0%)] Loss: 1.555158 +2025-04-14 13:36:01,224 INFO Train Epoch: 46 [3200/32087 (10%)] Loss: 1.672212 +2025-04-14 13:36:22,283 INFO Train Epoch: 46 [6400/32087 (20%)] Loss: 1.357624 +2025-04-14 13:36:40,367 INFO Train Epoch: 46 [9600/32087 (30%)] Loss: 1.869128 +2025-04-14 13:36:59,281 INFO Train Epoch: 46 [12800/32087 (40%)] Loss: 1.515464 +2025-04-14 13:37:17,298 INFO Train Epoch: 46 [16000/32087 (50%)] Loss: 1.677261 +2025-04-14 13:37:35,232 INFO Train Epoch: 46 [19200/32087 (60%)] Loss: 1.599875 +2025-04-14 13:37:53,814 INFO Train Epoch: 46 [22400/32087 (70%)] Loss: 1.646566 +2025-04-14 13:38:11,593 INFO Train Epoch: 46 [25600/32087 (80%)] Loss: 1.772264 +2025-04-14 13:38:30,835 INFO Train Epoch: 46 [28800/32087 (90%)] Loss: 2.088386 +2025-04-14 13:38:49,560 INFO Train Epoch: 46 [32000/32087 (100%)] Loss: 1.785739 +2025-04-14 13:40:33,170 INFO Accuracy qa: 72.23 % +2025-04-14 13:40:36,892 INFO Train Epoch: 47 [0/32087 (0%)] Loss: 1.755934 +2025-04-14 13:40:58,280 INFO Train Epoch: 47 [3200/32087 (10%)] Loss: 1.521026 +2025-04-14 13:41:16,355 INFO Train Epoch: 47 [6400/32087 (20%)] Loss: 1.892884 +2025-04-14 13:41:34,475 INFO Train Epoch: 47 [9600/32087 (30%)] Loss: 1.315836 +2025-04-14 13:41:51,422 INFO Train Epoch: 47 [12800/32087 (40%)] Loss: 1.738328 +2025-04-14 13:42:07,896 INFO Train Epoch: 47 [16000/32087 (50%)] Loss: 1.496789 +2025-04-14 13:42:24,149 INFO Train Epoch: 47 [19200/32087 (60%)] Loss: 1.396057 +2025-04-14 13:42:43,143 INFO Train Epoch: 47 [22400/32087 (70%)] Loss: 1.878811 +2025-04-14 13:43:03,600 INFO Train Epoch: 47 [25600/32087 (80%)] Loss: 1.689620 +2025-04-14 13:43:22,928 INFO Train Epoch: 47 [28800/32087 (90%)] Loss: 1.414576 +2025-04-14 13:43:41,233 INFO Train Epoch: 47 [32000/32087 (100%)] Loss: 1.689756 +2025-04-14 13:45:12,717 INFO Accuracy qa: 72.21 % +2025-04-14 13:45:16,611 INFO Train Epoch: 48 [0/32087 (0%)] Loss: 1.507289 +2025-04-14 13:45:35,581 INFO Train Epoch: 48 [3200/32087 (10%)] Loss: 2.040421 +2025-04-14 13:45:53,685 INFO Train Epoch: 48 [6400/32087 (20%)] Loss: 1.870388 +2025-04-14 13:46:11,020 INFO Train Epoch: 48 [9600/32087 (30%)] Loss: 1.369739 +2025-04-14 13:46:28,267 INFO Train Epoch: 48 [12800/32087 (40%)] Loss: 1.326036 +2025-04-14 13:46:45,527 INFO Train Epoch: 48 [16000/32087 (50%)] Loss: 1.492090 +2025-04-14 13:47:05,145 INFO Train Epoch: 48 [19200/32087 (60%)] Loss: 1.556185 +2025-04-14 13:47:26,015 INFO Train Epoch: 48 [22400/32087 (70%)] Loss: 1.477036 +2025-04-14 13:47:44,224 INFO Train Epoch: 48 [25600/32087 (80%)] Loss: 1.732765 +2025-04-14 13:48:01,376 INFO Train Epoch: 48 [28800/32087 (90%)] Loss: 1.444252 +2025-04-14 13:48:17,292 INFO Train Epoch: 48 [32000/32087 (100%)] Loss: 1.501027 +2025-04-14 13:49:41,985 INFO Accuracy qa: 72.21 % +2025-04-14 13:49:44,800 INFO Train Epoch: 49 [0/32087 (0%)] Loss: 1.455574 +2025-04-14 13:50:01,778 INFO Train Epoch: 49 [3200/32087 (10%)] Loss: 1.466876 +2025-04-14 13:50:17,311 INFO Train Epoch: 49 [6400/32087 (20%)] Loss: 1.673058 +2025-04-14 13:50:32,891 INFO Train Epoch: 49 [9600/32087 (30%)] Loss: 1.718216 +2025-04-14 13:50:48,055 INFO Train Epoch: 49 [12800/32087 (40%)] Loss: 1.215444 +2025-04-14 13:51:03,098 INFO Train Epoch: 49 [16000/32087 (50%)] Loss: 1.503464 +2025-04-14 13:51:18,237 INFO Train Epoch: 49 [19200/32087 (60%)] Loss: 1.555008 +2025-04-14 13:51:32,962 INFO Train Epoch: 49 [22400/32087 (70%)] Loss: 1.507930 +2025-04-14 13:51:47,692 INFO Train Epoch: 49 [25600/32087 (80%)] Loss: 1.550807 +2025-04-14 13:52:02,137 INFO Train Epoch: 49 [28800/32087 (90%)] Loss: 1.291102 +2025-04-14 13:52:15,416 INFO Train Epoch: 49 [32000/32087 (100%)] Loss: 1.750930 +2025-04-14 13:53:44,127 INFO Accuracy qa: 72.14 % +2025-04-14 13:53:48,070 INFO Train Epoch: 50 [0/32087 (0%)] Loss: 1.732504 +2025-04-14 13:54:01,583 INFO Train Epoch: 50 [3200/32087 (10%)] Loss: 1.677675 +2025-04-14 13:54:15,008 INFO Train Epoch: 50 [6400/32087 (20%)] Loss: 1.589832 +2025-04-14 13:54:28,576 INFO Train Epoch: 50 [9600/32087 (30%)] Loss: 1.503274 +2025-04-14 13:54:42,501 INFO Train Epoch: 50 [12800/32087 (40%)] Loss: 1.653764 +2025-04-14 13:54:56,713 INFO Train Epoch: 50 [16000/32087 (50%)] Loss: 1.351678 +2025-04-14 13:55:11,774 INFO Train Epoch: 50 [19200/32087 (60%)] Loss: 1.925586 +2025-04-14 13:55:26,757 INFO Train Epoch: 50 [22400/32087 (70%)] Loss: 1.576057 +2025-04-14 13:55:41,114 INFO Train Epoch: 50 [25600/32087 (80%)] Loss: 1.437671 +2025-04-14 13:55:55,400 INFO Train Epoch: 50 [28800/32087 (90%)] Loss: 1.352255 +2025-04-14 13:56:08,528 INFO Train Epoch: 50 [32000/32087 (100%)] Loss: 1.616134 +2025-04-14 13:57:42,187 INFO Accuracy qa: 72.17 % diff --git a/Audio Visual Question Answering/results_baseline/inverse_False_withmodified/net_grd_baseline.pt b/Audio Visual Question Answering/results_baseline/inverse_False_withmodified/net_grd_baseline.pt new file mode 100644 index 0000000000000000000000000000000000000000..007d535302744c4838816bfd8cefd7f2fc30c71e --- /dev/null +++ b/Audio Visual Question Answering/results_baseline/inverse_False_withmodified/net_grd_baseline.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82eec7e405ae952314d90e96096d45dcc251da50524c7887bdab3fd65ca0cfb +size 88163031 diff --git a/Audio Visual Question Answering/results_baseline/inverse_False_withmodified/test.log b/Audio Visual Question Answering/results_baseline/inverse_False_withmodified/test.log new file mode 100644 index 0000000000000000000000000000000000000000..9fff539b04cfbbfbe220aac1cebf56dde0275a35 --- /dev/null +++ b/Audio Visual Question Answering/results_baseline/inverse_False_withmodified/test.log @@ -0,0 +1,4 @@ +2025-04-15 08:02:16,955 INFO +--------------- MUSIC-AVQA baseline --------------- + +2025-04-15 08:02:21,455 INFO 9185 diff --git a/Audio Visual Question Answering/results_baseline/inverse_False_withmodified/train.log b/Audio Visual Question Answering/results_baseline/inverse_False_withmodified/train.log new file mode 100644 index 0000000000000000000000000000000000000000..85a52796890dd5ec535d67903e72620739fa9731 --- /dev/null +++ b/Audio Visual Question Answering/results_baseline/inverse_False_withmodified/train.log @@ -0,0 +1,603 @@ +2025-04-14 14:17:57,579 INFO +--------------- MUSIC-AVQA baseline --------------- + +2025-04-14 14:18:08,341 INFO Train Epoch: 1 [0/32087 (0%)] Loss: 3.748658 +2025-04-14 14:18:19,993 INFO Train Epoch: 1 [3200/32087 (10%)] Loss: 2.469455 +2025-04-14 14:18:32,403 INFO Train Epoch: 1 [6400/32087 (20%)] Loss: 2.512029 +2025-04-14 14:18:44,821 INFO Train Epoch: 1 [9600/32087 (30%)] Loss: 2.044057 +2025-04-14 14:18:57,454 INFO Train Epoch: 1 [12800/32087 (40%)] Loss: 1.652638 +2025-04-14 14:19:10,266 INFO Train Epoch: 1 [16000/32087 (50%)] Loss: 1.373239 +2025-04-14 14:19:23,294 INFO Train Epoch: 1 [19200/32087 (60%)] Loss: 1.175516 +2025-04-14 14:19:36,312 INFO Train Epoch: 1 [22400/32087 (70%)] Loss: 0.859500 +2025-04-14 14:19:49,100 INFO Train Epoch: 1 [25600/32087 (80%)] Loss: 1.052017 +2025-04-14 14:20:01,958 INFO Train Epoch: 1 [28800/32087 (90%)] Loss: 1.167990 +2025-04-14 14:20:15,451 INFO Train Epoch: 1 [32000/32087 (100%)] Loss: 0.973030 +2025-04-14 14:20:50,158 INFO Accuracy qa: 54.04 % +2025-04-14 14:20:52,796 INFO Train Epoch: 2 [0/32087 (0%)] Loss: 1.230717 +2025-04-14 14:21:05,374 INFO Train Epoch: 2 [3200/32087 (10%)] Loss: 0.936774 +2025-04-14 14:21:17,642 INFO Train Epoch: 2 [6400/32087 (20%)] Loss: 1.092624 +2025-04-14 14:21:30,070 INFO Train Epoch: 2 [9600/32087 (30%)] Loss: 0.972659 +2025-04-14 14:21:42,352 INFO Train Epoch: 2 [12800/32087 (40%)] Loss: 1.087369 +2025-04-14 14:21:54,528 INFO Train Epoch: 2 [16000/32087 (50%)] Loss: 1.058805 +2025-04-14 14:22:06,627 INFO Train Epoch: 2 [19200/32087 (60%)] Loss: 0.902593 +2025-04-14 14:22:18,800 INFO Train Epoch: 2 [22400/32087 (70%)] Loss: 1.118770 +2025-04-14 14:22:31,497 INFO Train Epoch: 2 [25600/32087 (80%)] Loss: 1.004256 +2025-04-14 14:22:43,959 INFO Train Epoch: 2 [28800/32087 (90%)] Loss: 0.925751 +2025-04-14 14:22:56,329 INFO Train Epoch: 2 [32000/32087 (100%)] Loss: 0.955239 +2025-04-14 14:23:28,109 INFO Accuracy qa: 62.05 % +2025-04-14 14:23:31,081 INFO Train Epoch: 3 [0/32087 (0%)] Loss: 0.963718 +2025-04-14 14:23:43,901 INFO Train Epoch: 3 [3200/32087 (10%)] Loss: 0.726559 +2025-04-14 14:23:56,900 INFO Train Epoch: 3 [6400/32087 (20%)] Loss: 0.954995 +2025-04-14 14:24:10,697 INFO Train Epoch: 3 [9600/32087 (30%)] Loss: 0.869079 +2025-04-14 14:24:24,930 INFO Train Epoch: 3 [12800/32087 (40%)] Loss: 0.692641 +2025-04-14 14:24:38,564 INFO Train Epoch: 3 [16000/32087 (50%)] Loss: 0.855914 +2025-04-14 14:24:52,344 INFO Train Epoch: 3 [19200/32087 (60%)] Loss: 0.803273 +2025-04-14 14:25:06,824 INFO Train Epoch: 3 [22400/32087 (70%)] Loss: 0.942282 +2025-04-14 14:25:22,575 INFO Train Epoch: 3 [25600/32087 (80%)] Loss: 0.759781 +2025-04-14 14:25:38,224 INFO Train Epoch: 3 [28800/32087 (90%)] Loss: 0.738816 +2025-04-14 14:25:52,891 INFO Train Epoch: 3 [32000/32087 (100%)] Loss: 0.874127 +2025-04-14 14:26:26,163 INFO Accuracy qa: 62.37 % +2025-04-14 14:26:29,150 INFO Train Epoch: 4 [0/32087 (0%)] Loss: 0.687705 +2025-04-14 14:26:42,271 INFO Train Epoch: 4 [3200/32087 (10%)] Loss: 0.678445 +2025-04-14 14:26:56,253 INFO Train Epoch: 4 [6400/32087 (20%)] Loss: 0.775658 +2025-04-14 14:27:09,849 INFO Train Epoch: 4 [9600/32087 (30%)] Loss: 0.877971 +2025-04-14 14:27:22,689 INFO Train Epoch: 4 [12800/32087 (40%)] Loss: 0.724577 +2025-04-14 14:27:35,896 INFO Train Epoch: 4 [16000/32087 (50%)] Loss: 1.063815 +2025-04-14 14:27:48,903 INFO Train Epoch: 4 [19200/32087 (60%)] Loss: 0.809659 +2025-04-14 14:28:02,569 INFO Train Epoch: 4 [22400/32087 (70%)] Loss: 1.035689 +2025-04-14 14:28:16,448 INFO Train Epoch: 4 [25600/32087 (80%)] Loss: 0.802716 +2025-04-14 14:28:30,148 INFO Train Epoch: 4 [28800/32087 (90%)] Loss: 0.711378 +2025-04-14 14:28:43,850 INFO Train Epoch: 4 [32000/32087 (100%)] Loss: 0.891144 +2025-04-14 14:29:18,431 INFO Accuracy qa: 64.68 % +2025-04-14 14:29:21,407 INFO Train Epoch: 5 [0/32087 (0%)] Loss: 0.732121 +2025-04-14 14:29:34,935 INFO Train Epoch: 5 [3200/32087 (10%)] Loss: 0.807356 +2025-04-14 14:29:49,301 INFO Train Epoch: 5 [6400/32087 (20%)] Loss: 0.926937 +2025-04-14 14:30:03,565 INFO Train Epoch: 5 [9600/32087 (30%)] Loss: 0.788969 +2025-04-14 14:30:18,025 INFO Train Epoch: 5 [12800/32087 (40%)] Loss: 0.534106 +2025-04-14 14:30:31,304 INFO Train Epoch: 5 [16000/32087 (50%)] Loss: 0.853122 +2025-04-14 14:30:44,961 INFO Train Epoch: 5 [19200/32087 (60%)] Loss: 0.823971 +2025-04-14 14:30:57,316 INFO Train Epoch: 5 [22400/32087 (70%)] Loss: 0.616571 +2025-04-14 14:31:10,179 INFO Train Epoch: 5 [25600/32087 (80%)] Loss: 1.070337 +2025-04-14 14:31:22,721 INFO Train Epoch: 5 [28800/32087 (90%)] Loss: 0.785500 +2025-04-14 14:31:35,703 INFO Train Epoch: 5 [32000/32087 (100%)] Loss: 0.877317 +2025-04-14 14:32:07,530 INFO Accuracy qa: 64.98 % +2025-04-14 14:32:10,340 INFO Train Epoch: 6 [0/32087 (0%)] Loss: 0.881466 +2025-04-14 14:32:22,244 INFO Train Epoch: 6 [3200/32087 (10%)] Loss: 0.579762 +2025-04-14 14:32:34,792 INFO Train Epoch: 6 [6400/32087 (20%)] Loss: 0.969297 +2025-04-14 14:32:47,535 INFO Train Epoch: 6 [9600/32087 (30%)] Loss: 0.702170 +2025-04-14 14:33:00,127 INFO Train Epoch: 6 [12800/32087 (40%)] Loss: 0.719408 +2025-04-14 14:33:12,341 INFO Train Epoch: 6 [16000/32087 (50%)] Loss: 0.661466 +2025-04-14 14:33:24,768 INFO Train Epoch: 6 [19200/32087 (60%)] Loss: 0.834484 +2025-04-14 14:33:37,255 INFO Train Epoch: 6 [22400/32087 (70%)] Loss: 0.973938 +2025-04-14 14:33:49,857 INFO Train Epoch: 6 [25600/32087 (80%)] Loss: 0.870671 +2025-04-14 14:34:02,149 INFO Train Epoch: 6 [28800/32087 (90%)] Loss: 0.790747 +2025-04-14 14:34:14,637 INFO Train Epoch: 6 [32000/32087 (100%)] Loss: 0.766353 +2025-04-14 14:34:47,448 INFO Accuracy qa: 65.90 % +2025-04-14 14:34:50,373 INFO Train Epoch: 7 [0/32087 (0%)] Loss: 0.650753 +2025-04-14 14:35:02,298 INFO Train Epoch: 7 [3200/32087 (10%)] Loss: 0.738368 +2025-04-14 14:35:14,621 INFO Train Epoch: 7 [6400/32087 (20%)] Loss: 0.850812 +2025-04-14 14:35:27,198 INFO Train Epoch: 7 [9600/32087 (30%)] Loss: 0.814818 +2025-04-14 14:35:39,405 INFO Train Epoch: 7 [12800/32087 (40%)] Loss: 0.757387 +2025-04-14 14:35:51,639 INFO Train Epoch: 7 [16000/32087 (50%)] Loss: 0.781272 +2025-04-14 14:36:04,186 INFO Train Epoch: 7 [19200/32087 (60%)] Loss: 0.624504 +2025-04-14 14:36:16,454 INFO Train Epoch: 7 [22400/32087 (70%)] Loss: 0.717362 +2025-04-14 14:36:28,700 INFO Train Epoch: 7 [25600/32087 (80%)] Loss: 0.838556 +2025-04-14 14:36:41,169 INFO Train Epoch: 7 [28800/32087 (90%)] Loss: 0.764017 +2025-04-14 14:36:53,145 INFO Train Epoch: 7 [32000/32087 (100%)] Loss: 0.869078 +2025-04-14 14:37:25,181 INFO Accuracy qa: 67.03 % +2025-04-14 14:37:27,842 INFO Train Epoch: 8 [0/32087 (0%)] Loss: 0.704335 +2025-04-14 14:37:40,253 INFO Train Epoch: 8 [3200/32087 (10%)] Loss: 0.830902 +2025-04-14 14:37:52,630 INFO Train Epoch: 8 [6400/32087 (20%)] Loss: 0.599758 +2025-04-14 14:38:04,899 INFO Train Epoch: 8 [9600/32087 (30%)] Loss: 0.609450 +2025-04-14 14:38:17,291 INFO Train Epoch: 8 [12800/32087 (40%)] Loss: 0.940926 +2025-04-14 14:38:29,971 INFO Train Epoch: 8 [16000/32087 (50%)] Loss: 0.841493 +2025-04-14 14:38:42,387 INFO Train Epoch: 8 [19200/32087 (60%)] Loss: 0.679657 +2025-04-14 14:38:54,717 INFO Train Epoch: 8 [22400/32087 (70%)] Loss: 0.717753 +2025-04-14 14:39:07,012 INFO Train Epoch: 8 [25600/32087 (80%)] Loss: 0.818785 +2025-04-14 14:39:19,278 INFO Train Epoch: 8 [28800/32087 (90%)] Loss: 0.783846 +2025-04-14 14:39:32,160 INFO Train Epoch: 8 [32000/32087 (100%)] Loss: 0.627204 +2025-04-14 14:40:05,248 INFO Accuracy qa: 67.81 % +2025-04-14 14:40:07,867 INFO Train Epoch: 9 [0/32087 (0%)] Loss: 0.574387 +2025-04-14 14:40:20,263 INFO Train Epoch: 9 [3200/32087 (10%)] Loss: 0.982323 +2025-04-14 14:40:32,385 INFO Train Epoch: 9 [6400/32087 (20%)] Loss: 0.687463 +2025-04-14 14:40:44,834 INFO Train Epoch: 9 [9600/32087 (30%)] Loss: 0.704794 +2025-04-14 14:40:56,819 INFO Train Epoch: 9 [12800/32087 (40%)] Loss: 0.891445 +2025-04-14 14:41:09,033 INFO Train Epoch: 9 [16000/32087 (50%)] Loss: 0.574989 +2025-04-14 14:41:21,518 INFO Train Epoch: 9 [19200/32087 (60%)] Loss: 0.760325 +2025-04-14 14:41:33,699 INFO Train Epoch: 9 [22400/32087 (70%)] Loss: 0.727403 +2025-04-14 14:41:45,956 INFO Train Epoch: 9 [25600/32087 (80%)] Loss: 0.908998 +2025-04-14 14:41:58,407 INFO Train Epoch: 9 [28800/32087 (90%)] Loss: 0.497075 +2025-04-14 14:42:10,812 INFO Train Epoch: 9 [32000/32087 (100%)] Loss: 0.647731 +2025-04-14 14:42:43,366 INFO Accuracy qa: 65.33 % +2025-04-14 14:42:45,206 INFO Train Epoch: 10 [0/32087 (0%)] Loss: 0.740184 +2025-04-14 14:42:57,174 INFO Train Epoch: 10 [3200/32087 (10%)] Loss: 0.805410 +2025-04-14 14:43:09,411 INFO Train Epoch: 10 [6400/32087 (20%)] Loss: 0.642435 +2025-04-14 14:43:21,809 INFO Train Epoch: 10 [9600/32087 (30%)] Loss: 0.499125 +2025-04-14 14:43:34,248 INFO Train Epoch: 10 [12800/32087 (40%)] Loss: 0.711131 +2025-04-14 14:43:46,582 INFO Train Epoch: 10 [16000/32087 (50%)] Loss: 0.640703 +2025-04-14 14:43:58,962 INFO Train Epoch: 10 [19200/32087 (60%)] Loss: 0.712707 +2025-04-14 14:44:11,547 INFO Train Epoch: 10 [22400/32087 (70%)] Loss: 0.775041 +2025-04-14 14:44:24,074 INFO Train Epoch: 10 [25600/32087 (80%)] Loss: 0.703806 +2025-04-14 14:44:36,485 INFO Train Epoch: 10 [28800/32087 (90%)] Loss: 0.698243 +2025-04-14 14:44:48,911 INFO Train Epoch: 10 [32000/32087 (100%)] Loss: 0.723881 +2025-04-14 14:45:20,938 INFO Accuracy qa: 66.81 % +2025-04-14 14:45:23,017 INFO Train Epoch: 11 [0/32087 (0%)] Loss: 0.609235 +2025-04-14 14:45:35,130 INFO Train Epoch: 11 [3200/32087 (10%)] Loss: 0.520900 +2025-04-14 14:45:47,338 INFO Train Epoch: 11 [6400/32087 (20%)] Loss: 0.654686 +2025-04-14 14:45:59,674 INFO Train Epoch: 11 [9600/32087 (30%)] Loss: 0.539687 +2025-04-14 14:46:11,851 INFO Train Epoch: 11 [12800/32087 (40%)] Loss: 0.823144 +2025-04-14 14:46:24,047 INFO Train Epoch: 11 [16000/32087 (50%)] Loss: 0.805605 +2025-04-14 14:46:36,133 INFO Train Epoch: 11 [19200/32087 (60%)] Loss: 0.766869 +2025-04-14 14:46:48,268 INFO Train Epoch: 11 [22400/32087 (70%)] Loss: 0.742409 +2025-04-14 14:47:00,375 INFO Train Epoch: 11 [25600/32087 (80%)] Loss: 0.721632 +2025-04-14 14:47:12,503 INFO Train Epoch: 11 [28800/32087 (90%)] Loss: 0.565072 +2025-04-14 14:47:24,762 INFO Train Epoch: 11 [32000/32087 (100%)] Loss: 0.634429 +2025-04-14 14:47:57,283 INFO Accuracy qa: 66.57 % +2025-04-14 14:47:58,845 INFO Train Epoch: 12 [0/32087 (0%)] Loss: 0.486993 +2025-04-14 14:48:11,285 INFO Train Epoch: 12 [3200/32087 (10%)] Loss: 0.610902 +2025-04-14 14:48:24,138 INFO Train Epoch: 12 [6400/32087 (20%)] Loss: 0.636889 +2025-04-14 14:48:36,789 INFO Train Epoch: 12 [9600/32087 (30%)] Loss: 0.654084 +2025-04-14 14:48:49,629 INFO Train Epoch: 12 [12800/32087 (40%)] Loss: 0.645148 +2025-04-14 14:49:02,759 INFO Train Epoch: 12 [16000/32087 (50%)] Loss: 0.720895 +2025-04-14 14:49:15,723 INFO Train Epoch: 12 [19200/32087 (60%)] Loss: 0.755761 +2025-04-14 14:49:28,612 INFO Train Epoch: 12 [22400/32087 (70%)] Loss: 0.727799 +2025-04-14 14:49:41,661 INFO Train Epoch: 12 [25600/32087 (80%)] Loss: 0.646018 +2025-04-14 14:49:54,924 INFO Train Epoch: 12 [28800/32087 (90%)] Loss: 0.850734 +2025-04-14 14:50:08,286 INFO Train Epoch: 12 [32000/32087 (100%)] Loss: 0.553886 +2025-04-14 14:50:47,506 INFO Accuracy qa: 68.38 % +2025-04-14 14:50:50,118 INFO Train Epoch: 13 [0/32087 (0%)] Loss: 0.522811 +2025-04-14 14:51:04,564 INFO Train Epoch: 13 [3200/32087 (10%)] Loss: 0.908134 +2025-04-14 14:51:18,991 INFO Train Epoch: 13 [6400/32087 (20%)] Loss: 0.561489 +2025-04-14 14:51:33,672 INFO Train Epoch: 13 [9600/32087 (30%)] Loss: 0.762143 +2025-04-14 14:51:48,242 INFO Train Epoch: 13 [12800/32087 (40%)] Loss: 0.657722 +2025-04-14 14:52:02,906 INFO Train Epoch: 13 [16000/32087 (50%)] Loss: 0.634774 +2025-04-14 14:52:17,313 INFO Train Epoch: 13 [19200/32087 (60%)] Loss: 0.520440 +2025-04-14 14:52:31,938 INFO Train Epoch: 13 [22400/32087 (70%)] Loss: 0.466883 +2025-04-14 14:52:46,592 INFO Train Epoch: 13 [25600/32087 (80%)] Loss: 0.550255 +2025-04-14 14:53:00,841 INFO Train Epoch: 13 [28800/32087 (90%)] Loss: 0.813409 +2025-04-14 14:53:14,725 INFO Train Epoch: 13 [32000/32087 (100%)] Loss: 0.649376 +2025-04-14 14:53:49,203 INFO Accuracy qa: 68.31 % +2025-04-14 14:53:51,252 INFO Train Epoch: 14 [0/32087 (0%)] Loss: 0.630542 +2025-04-14 14:54:05,289 INFO Train Epoch: 14 [3200/32087 (10%)] Loss: 0.583081 +2025-04-14 14:54:19,750 INFO Train Epoch: 14 [6400/32087 (20%)] Loss: 0.546500 +2025-04-14 14:54:34,180 INFO Train Epoch: 14 [9600/32087 (30%)] Loss: 0.624152 +2025-04-14 14:54:48,600 INFO Train Epoch: 14 [12800/32087 (40%)] Loss: 0.626860 +2025-04-14 14:55:02,988 INFO Train Epoch: 14 [16000/32087 (50%)] Loss: 0.593618 +2025-04-14 14:55:17,473 INFO Train Epoch: 14 [19200/32087 (60%)] Loss: 0.620419 +2025-04-14 14:55:31,929 INFO Train Epoch: 14 [22400/32087 (70%)] Loss: 0.685997 +2025-04-14 14:55:46,018 INFO Train Epoch: 14 [25600/32087 (80%)] Loss: 0.548067 +2025-04-14 14:56:00,326 INFO Train Epoch: 14 [28800/32087 (90%)] Loss: 0.519149 +2025-04-14 14:56:14,405 INFO Train Epoch: 14 [32000/32087 (100%)] Loss: 0.627435 +2025-04-14 14:56:52,379 INFO Accuracy qa: 68.16 % +2025-04-14 14:56:54,371 INFO Train Epoch: 15 [0/32087 (0%)] Loss: 0.539981 +2025-04-14 14:57:08,396 INFO Train Epoch: 15 [3200/32087 (10%)] Loss: 0.511049 +2025-04-14 14:57:22,850 INFO Train Epoch: 15 [6400/32087 (20%)] Loss: 0.459164 +2025-04-14 14:57:37,529 INFO Train Epoch: 15 [9600/32087 (30%)] Loss: 0.513373 +2025-04-14 14:57:51,660 INFO Train Epoch: 15 [12800/32087 (40%)] Loss: 0.607146 +2025-04-14 14:58:06,039 INFO Train Epoch: 15 [16000/32087 (50%)] Loss: 0.507954 +2025-04-14 14:58:20,264 INFO Train Epoch: 15 [19200/32087 (60%)] Loss: 0.657954 +2025-04-14 14:58:34,263 INFO Train Epoch: 15 [22400/32087 (70%)] Loss: 0.572126 +2025-04-14 14:58:48,377 INFO Train Epoch: 15 [25600/32087 (80%)] Loss: 0.551456 +2025-04-14 14:59:02,745 INFO Train Epoch: 15 [28800/32087 (90%)] Loss: 0.607193 +2025-04-14 14:59:17,135 INFO Train Epoch: 15 [32000/32087 (100%)] Loss: 0.609222 +2025-04-14 14:59:50,785 INFO Accuracy qa: 69.47 % +2025-04-14 14:59:53,351 INFO Train Epoch: 16 [0/32087 (0%)] Loss: 0.498819 +2025-04-14 15:00:07,968 INFO Train Epoch: 16 [3200/32087 (10%)] Loss: 0.554174 +2025-04-14 15:00:22,179 INFO Train Epoch: 16 [6400/32087 (20%)] Loss: 0.464033 +2025-04-14 15:00:36,656 INFO Train Epoch: 16 [9600/32087 (30%)] Loss: 0.292295 +2025-04-14 15:00:51,095 INFO Train Epoch: 16 [12800/32087 (40%)] Loss: 0.482548 +2025-04-14 15:01:05,498 INFO Train Epoch: 16 [16000/32087 (50%)] Loss: 0.583068 +2025-04-14 15:01:19,795 INFO Train Epoch: 16 [19200/32087 (60%)] Loss: 0.393269 +2025-04-14 15:01:33,989 INFO Train Epoch: 16 [22400/32087 (70%)] Loss: 0.547395 +2025-04-14 15:01:48,013 INFO Train Epoch: 16 [25600/32087 (80%)] Loss: 0.478925 +2025-04-14 15:02:02,176 INFO Train Epoch: 16 [28800/32087 (90%)] Loss: 0.544820 +2025-04-14 15:02:16,596 INFO Train Epoch: 16 [32000/32087 (100%)] Loss: 0.405596 +2025-04-14 15:02:49,187 INFO Accuracy qa: 71.16 % +2025-04-14 15:02:51,753 INFO Train Epoch: 17 [0/32087 (0%)] Loss: 0.358559 +2025-04-14 15:03:06,189 INFO Train Epoch: 17 [3200/32087 (10%)] Loss: 0.453536 +2025-04-14 15:03:20,425 INFO Train Epoch: 17 [6400/32087 (20%)] Loss: 0.407055 +2025-04-14 15:03:34,596 INFO Train Epoch: 17 [9600/32087 (30%)] Loss: 0.585037 +2025-04-14 15:03:48,756 INFO Train Epoch: 17 [12800/32087 (40%)] Loss: 0.489782 +2025-04-14 15:04:02,997 INFO Train Epoch: 17 [16000/32087 (50%)] Loss: 0.460630 +2025-04-14 15:04:17,044 INFO Train Epoch: 17 [19200/32087 (60%)] Loss: 0.397849 +2025-04-14 15:04:31,310 INFO Train Epoch: 17 [22400/32087 (70%)] Loss: 0.473267 +2025-04-14 15:04:45,550 INFO Train Epoch: 17 [25600/32087 (80%)] Loss: 0.472716 +2025-04-14 15:05:00,040 INFO Train Epoch: 17 [28800/32087 (90%)] Loss: 0.549537 +2025-04-14 15:05:14,579 INFO Train Epoch: 17 [32000/32087 (100%)] Loss: 0.376043 +2025-04-14 15:05:51,820 INFO Accuracy qa: 71.51 % +2025-04-14 15:05:54,975 INFO Train Epoch: 18 [0/32087 (0%)] Loss: 0.607610 +2025-04-14 15:06:09,188 INFO Train Epoch: 18 [3200/32087 (10%)] Loss: 0.448239 +2025-04-14 15:06:23,627 INFO Train Epoch: 18 [6400/32087 (20%)] Loss: 0.404951 +2025-04-14 15:06:37,789 INFO Train Epoch: 18 [9600/32087 (30%)] Loss: 0.561295 +2025-04-14 15:06:51,667 INFO Train Epoch: 18 [12800/32087 (40%)] Loss: 0.455650 +2025-04-14 15:07:05,746 INFO Train Epoch: 18 [16000/32087 (50%)] Loss: 0.399630 +2025-04-14 15:07:20,071 INFO Train Epoch: 18 [19200/32087 (60%)] Loss: 0.447092 +2025-04-14 15:07:34,171 INFO Train Epoch: 18 [22400/32087 (70%)] Loss: 0.422124 +2025-04-14 15:07:48,170 INFO Train Epoch: 18 [25600/32087 (80%)] Loss: 0.294847 +2025-04-14 15:08:02,532 INFO Train Epoch: 18 [28800/32087 (90%)] Loss: 0.537189 +2025-04-14 15:08:17,071 INFO Train Epoch: 18 [32000/32087 (100%)] Loss: 0.496066 +2025-04-14 15:08:51,367 INFO Accuracy qa: 70.86 % +2025-04-14 15:08:53,657 INFO Train Epoch: 19 [0/32087 (0%)] Loss: 0.504271 +2025-04-14 15:09:07,381 INFO Train Epoch: 19 [3200/32087 (10%)] Loss: 0.449314 +2025-04-14 15:09:21,985 INFO Train Epoch: 19 [6400/32087 (20%)] Loss: 0.390788 +2025-04-14 15:09:36,679 INFO Train Epoch: 19 [9600/32087 (30%)] Loss: 0.320827 +2025-04-14 15:09:51,603 INFO Train Epoch: 19 [12800/32087 (40%)] Loss: 0.423193 +2025-04-14 15:10:05,932 INFO Train Epoch: 19 [16000/32087 (50%)] Loss: 0.400965 +2025-04-14 15:10:20,631 INFO Train Epoch: 19 [19200/32087 (60%)] Loss: 0.392463 +2025-04-14 15:10:35,580 INFO Train Epoch: 19 [22400/32087 (70%)] Loss: 0.423693 +2025-04-14 15:10:50,363 INFO Train Epoch: 19 [25600/32087 (80%)] Loss: 0.453645 +2025-04-14 15:11:05,563 INFO Train Epoch: 19 [28800/32087 (90%)] Loss: 0.562508 +2025-04-14 15:11:20,995 INFO Train Epoch: 19 [32000/32087 (100%)] Loss: 0.451541 +2025-04-14 15:11:55,971 INFO Accuracy qa: 71.01 % +2025-04-14 15:11:57,948 INFO Train Epoch: 20 [0/32087 (0%)] Loss: 0.492438 +2025-04-14 15:12:12,368 INFO Train Epoch: 20 [3200/32087 (10%)] Loss: 0.425355 +2025-04-14 15:12:26,557 INFO Train Epoch: 20 [6400/32087 (20%)] Loss: 0.472641 +2025-04-14 15:12:41,180 INFO Train Epoch: 20 [9600/32087 (30%)] Loss: 0.382261 +2025-04-14 15:12:55,641 INFO Train Epoch: 20 [12800/32087 (40%)] Loss: 0.373050 +2025-04-14 15:13:09,842 INFO Train Epoch: 20 [16000/32087 (50%)] Loss: 0.390363 +2025-04-14 15:13:24,155 INFO Train Epoch: 20 [19200/32087 (60%)] Loss: 0.361524 +2025-04-14 15:13:38,787 INFO Train Epoch: 20 [22400/32087 (70%)] Loss: 0.486935 +2025-04-14 15:13:53,142 INFO Train Epoch: 20 [25600/32087 (80%)] Loss: 0.432264 +2025-04-14 15:14:07,633 INFO Train Epoch: 20 [28800/32087 (90%)] Loss: 0.295397 +2025-04-14 15:14:22,375 INFO Train Epoch: 20 [32000/32087 (100%)] Loss: 0.429794 +2025-04-14 15:14:56,566 INFO Accuracy qa: 70.90 % +2025-04-14 15:14:58,947 INFO Train Epoch: 21 [0/32087 (0%)] Loss: 0.411657 +2025-04-14 15:15:13,250 INFO Train Epoch: 21 [3200/32087 (10%)] Loss: 0.395721 +2025-04-14 15:15:28,286 INFO Train Epoch: 21 [6400/32087 (20%)] Loss: 0.434773 +2025-04-14 15:15:43,288 INFO Train Epoch: 21 [9600/32087 (30%)] Loss: 0.515563 +2025-04-14 15:15:58,168 INFO Train Epoch: 21 [12800/32087 (40%)] Loss: 0.410945 +2025-04-14 15:16:12,903 INFO Train Epoch: 21 [16000/32087 (50%)] Loss: 0.365098 +2025-04-14 15:16:27,766 INFO Train Epoch: 21 [19200/32087 (60%)] Loss: 0.427239 +2025-04-14 15:16:42,616 INFO Train Epoch: 21 [22400/32087 (70%)] Loss: 0.397249 +2025-04-14 15:16:57,748 INFO Train Epoch: 21 [25600/32087 (80%)] Loss: 0.396574 +2025-04-14 15:17:12,677 INFO Train Epoch: 21 [28800/32087 (90%)] Loss: 0.615883 +2025-04-14 15:17:27,751 INFO Train Epoch: 21 [32000/32087 (100%)] Loss: 0.328292 +2025-04-14 15:17:59,180 INFO Accuracy qa: 70.64 % +2025-04-14 15:18:01,358 INFO Train Epoch: 22 [0/32087 (0%)] Loss: 0.428090 +2025-04-14 15:18:14,305 INFO Train Epoch: 22 [3200/32087 (10%)] Loss: 0.298848 +2025-04-14 15:18:28,117 INFO Train Epoch: 22 [6400/32087 (20%)] Loss: 0.367736 +2025-04-14 15:18:42,225 INFO Train Epoch: 22 [9600/32087 (30%)] Loss: 0.452265 +2025-04-14 15:18:56,361 INFO Train Epoch: 22 [12800/32087 (40%)] Loss: 0.410381 +2025-04-14 15:19:10,442 INFO Train Epoch: 22 [16000/32087 (50%)] Loss: 0.470510 +2025-04-14 15:19:25,008 INFO Train Epoch: 22 [19200/32087 (60%)] Loss: 0.436858 +2025-04-14 15:19:39,230 INFO Train Epoch: 22 [22400/32087 (70%)] Loss: 0.452778 +2025-04-14 15:19:53,369 INFO Train Epoch: 22 [25600/32087 (80%)] Loss: 0.456377 +2025-04-14 15:20:07,516 INFO Train Epoch: 22 [28800/32087 (90%)] Loss: 0.474582 +2025-04-14 15:20:21,932 INFO Train Epoch: 22 [32000/32087 (100%)] Loss: 0.481697 +2025-04-14 15:20:55,299 INFO Accuracy qa: 71.10 % +2025-04-14 15:20:57,581 INFO Train Epoch: 23 [0/32087 (0%)] Loss: 0.515297 +2025-04-14 15:21:11,356 INFO Train Epoch: 23 [3200/32087 (10%)] Loss: 0.348741 +2025-04-14 15:21:25,455 INFO Train Epoch: 23 [6400/32087 (20%)] Loss: 0.423429 +2025-04-14 15:21:39,498 INFO Train Epoch: 23 [9600/32087 (30%)] Loss: 0.387431 +2025-04-14 15:21:53,907 INFO Train Epoch: 23 [12800/32087 (40%)] Loss: 0.436827 +2025-04-14 15:22:08,309 INFO Train Epoch: 23 [16000/32087 (50%)] Loss: 0.522530 +2025-04-14 15:22:22,800 INFO Train Epoch: 23 [19200/32087 (60%)] Loss: 0.520885 +2025-04-14 15:22:36,997 INFO Train Epoch: 23 [22400/32087 (70%)] Loss: 0.471026 +2025-04-14 15:22:51,237 INFO Train Epoch: 23 [25600/32087 (80%)] Loss: 0.585396 +2025-04-14 15:23:05,792 INFO Train Epoch: 23 [28800/32087 (90%)] Loss: 0.420453 +2025-04-14 15:23:20,021 INFO Train Epoch: 23 [32000/32087 (100%)] Loss: 0.414895 +2025-04-14 15:23:54,002 INFO Accuracy qa: 70.36 % +2025-04-14 15:23:55,719 INFO Train Epoch: 24 [0/32087 (0%)] Loss: 0.478016 +2025-04-14 15:24:09,504 INFO Train Epoch: 24 [3200/32087 (10%)] Loss: 0.321173 +2025-04-14 15:24:23,543 INFO Train Epoch: 24 [6400/32087 (20%)] Loss: 0.282437 +2025-04-14 15:24:37,777 INFO Train Epoch: 24 [9600/32087 (30%)] Loss: 0.454622 +2025-04-14 15:24:52,128 INFO Train Epoch: 24 [12800/32087 (40%)] Loss: 0.489627 +2025-04-14 15:25:06,544 INFO Train Epoch: 24 [16000/32087 (50%)] Loss: 0.415470 +2025-04-14 15:25:21,156 INFO Train Epoch: 24 [19200/32087 (60%)] Loss: 0.752461 +2025-04-14 15:25:35,366 INFO Train Epoch: 24 [22400/32087 (70%)] Loss: 0.317691 +2025-04-14 15:25:49,846 INFO Train Epoch: 24 [25600/32087 (80%)] Loss: 0.389530 +2025-04-14 15:26:04,362 INFO Train Epoch: 24 [28800/32087 (90%)] Loss: 0.430646 +2025-04-14 15:26:18,790 INFO Train Epoch: 24 [32000/32087 (100%)] Loss: 0.303241 +2025-04-14 15:26:53,815 INFO Accuracy qa: 70.58 % +2025-04-14 15:26:56,105 INFO Train Epoch: 25 [0/32087 (0%)] Loss: 0.399365 +2025-04-14 15:27:09,252 INFO Train Epoch: 25 [3200/32087 (10%)] Loss: 0.249212 +2025-04-14 15:27:23,342 INFO Train Epoch: 25 [6400/32087 (20%)] Loss: 0.405327 +2025-04-14 15:27:37,607 INFO Train Epoch: 25 [9600/32087 (30%)] Loss: 0.332031 +2025-04-14 15:27:51,845 INFO Train Epoch: 25 [12800/32087 (40%)] Loss: 0.369043 +2025-04-14 15:28:05,984 INFO Train Epoch: 25 [16000/32087 (50%)] Loss: 0.333941 +2025-04-14 15:28:20,237 INFO Train Epoch: 25 [19200/32087 (60%)] Loss: 0.375099 +2025-04-14 15:28:34,719 INFO Train Epoch: 25 [22400/32087 (70%)] Loss: 0.294251 +2025-04-14 15:28:49,098 INFO Train Epoch: 25 [25600/32087 (80%)] Loss: 0.485260 +2025-04-14 15:29:03,488 INFO Train Epoch: 25 [28800/32087 (90%)] Loss: 0.500676 +2025-04-14 15:29:17,833 INFO Train Epoch: 25 [32000/32087 (100%)] Loss: 0.435197 +2025-04-14 15:29:51,375 INFO Accuracy qa: 70.58 % +2025-04-14 15:29:53,080 INFO Train Epoch: 26 [0/32087 (0%)] Loss: 0.436568 +2025-04-14 15:30:07,289 INFO Train Epoch: 26 [3200/32087 (10%)] Loss: 0.427261 +2025-04-14 15:30:21,413 INFO Train Epoch: 26 [6400/32087 (20%)] Loss: 0.362913 +2025-04-14 15:30:35,767 INFO Train Epoch: 26 [9600/32087 (30%)] Loss: 0.335162 +2025-04-14 15:30:50,012 INFO Train Epoch: 26 [12800/32087 (40%)] Loss: 0.399109 +2025-04-14 15:31:04,216 INFO Train Epoch: 26 [16000/32087 (50%)] Loss: 0.456947 +2025-04-14 15:31:18,161 INFO Train Epoch: 26 [19200/32087 (60%)] Loss: 0.355262 +2025-04-14 15:31:32,383 INFO Train Epoch: 26 [22400/32087 (70%)] Loss: 0.309171 +2025-04-14 15:31:46,663 INFO Train Epoch: 26 [25600/32087 (80%)] Loss: 0.497337 +2025-04-14 15:32:00,658 INFO Train Epoch: 26 [28800/32087 (90%)] Loss: 0.453177 +2025-04-14 15:32:14,689 INFO Train Epoch: 26 [32000/32087 (100%)] Loss: 0.647822 +2025-04-14 15:32:47,455 INFO Accuracy qa: 70.16 % +2025-04-14 15:32:49,482 INFO Train Epoch: 27 [0/32087 (0%)] Loss: 0.304147 +2025-04-14 15:33:03,161 INFO Train Epoch: 27 [3200/32087 (10%)] Loss: 0.503516 +2025-04-14 15:33:17,323 INFO Train Epoch: 27 [6400/32087 (20%)] Loss: 0.535159 +2025-04-14 15:33:31,325 INFO Train Epoch: 27 [9600/32087 (30%)] Loss: 0.515824 +2025-04-14 15:33:45,617 INFO Train Epoch: 27 [12800/32087 (40%)] Loss: 0.376788 +2025-04-14 15:33:59,924 INFO Train Epoch: 27 [16000/32087 (50%)] Loss: 0.277113 +2025-04-14 15:34:14,323 INFO Train Epoch: 27 [19200/32087 (60%)] Loss: 0.388971 +2025-04-14 15:34:28,726 INFO Train Epoch: 27 [22400/32087 (70%)] Loss: 0.493557 +2025-04-14 15:34:43,025 INFO Train Epoch: 27 [25600/32087 (80%)] Loss: 0.268435 +2025-04-14 15:34:56,976 INFO Train Epoch: 27 [28800/32087 (90%)] Loss: 0.408261 +2025-04-14 15:35:10,948 INFO Train Epoch: 27 [32000/32087 (100%)] Loss: 0.415133 +2025-04-14 15:35:44,296 INFO Accuracy qa: 70.47 % +2025-04-14 15:35:46,607 INFO Train Epoch: 28 [0/32087 (0%)] Loss: 0.402012 +2025-04-14 15:36:00,391 INFO Train Epoch: 28 [3200/32087 (10%)] Loss: 0.379079 +2025-04-14 15:36:14,550 INFO Train Epoch: 28 [6400/32087 (20%)] Loss: 0.301410 +2025-04-14 15:36:28,731 INFO Train Epoch: 28 [9600/32087 (30%)] Loss: 0.428549 +2025-04-14 15:36:42,857 INFO Train Epoch: 28 [12800/32087 (40%)] Loss: 0.362689 +2025-04-14 15:36:57,228 INFO Train Epoch: 28 [16000/32087 (50%)] Loss: 0.338179 +2025-04-14 15:37:11,654 INFO Train Epoch: 28 [19200/32087 (60%)] Loss: 0.411055 +2025-04-14 15:37:25,905 INFO Train Epoch: 28 [22400/32087 (70%)] Loss: 0.328807 +2025-04-14 15:37:40,453 INFO Train Epoch: 28 [25600/32087 (80%)] Loss: 0.464241 +2025-04-14 15:37:54,356 INFO Train Epoch: 28 [28800/32087 (90%)] Loss: 0.544202 +2025-04-14 15:38:08,464 INFO Train Epoch: 28 [32000/32087 (100%)] Loss: 0.475289 +2025-04-14 15:38:41,679 INFO Accuracy qa: 70.55 % +2025-04-14 15:38:43,954 INFO Train Epoch: 29 [0/32087 (0%)] Loss: 0.326966 +2025-04-14 15:38:57,426 INFO Train Epoch: 29 [3200/32087 (10%)] Loss: 0.439511 +2025-04-14 15:39:11,632 INFO Train Epoch: 29 [6400/32087 (20%)] Loss: 0.373688 +2025-04-14 15:39:26,017 INFO Train Epoch: 29 [9600/32087 (30%)] Loss: 0.323172 +2025-04-14 15:39:40,288 INFO Train Epoch: 29 [12800/32087 (40%)] Loss: 0.382010 +2025-04-14 15:39:54,518 INFO Train Epoch: 29 [16000/32087 (50%)] Loss: 0.531698 +2025-04-14 15:40:08,715 INFO Train Epoch: 29 [19200/32087 (60%)] Loss: 0.399400 +2025-04-14 15:40:23,147 INFO Train Epoch: 29 [22400/32087 (70%)] Loss: 0.409291 +2025-04-14 15:40:37,233 INFO Train Epoch: 29 [25600/32087 (80%)] Loss: 0.410595 +2025-04-14 15:40:51,385 INFO Train Epoch: 29 [28800/32087 (90%)] Loss: 0.298709 +2025-04-14 15:41:05,789 INFO Train Epoch: 29 [32000/32087 (100%)] Loss: 0.433653 +2025-04-14 15:41:38,584 INFO Accuracy qa: 69.75 % +2025-04-14 15:41:40,326 INFO Train Epoch: 30 [0/32087 (0%)] Loss: 0.431440 +2025-04-14 15:41:54,863 INFO Train Epoch: 30 [3200/32087 (10%)] Loss: 0.460647 +2025-04-14 15:42:09,377 INFO Train Epoch: 30 [6400/32087 (20%)] Loss: 0.400744 +2025-04-14 15:42:23,820 INFO Train Epoch: 30 [9600/32087 (30%)] Loss: 0.452608 +2025-04-14 15:42:38,426 INFO Train Epoch: 30 [12800/32087 (40%)] Loss: 0.275536 +2025-04-14 15:42:53,040 INFO Train Epoch: 30 [16000/32087 (50%)] Loss: 0.308003 +2025-04-14 15:43:07,586 INFO Train Epoch: 30 [19200/32087 (60%)] Loss: 0.414392 +2025-04-14 15:43:22,319 INFO Train Epoch: 30 [22400/32087 (70%)] Loss: 0.269553 +2025-04-14 15:43:36,920 INFO Train Epoch: 30 [25600/32087 (80%)] Loss: 0.344221 +2025-04-14 15:43:50,876 INFO Train Epoch: 30 [28800/32087 (90%)] Loss: 0.249594 +2025-04-14 15:44:04,976 INFO Train Epoch: 30 [32000/32087 (100%)] Loss: 0.346776 +2025-04-14 15:44:39,762 INFO Accuracy qa: 70.23 % +2025-04-14 15:44:41,506 INFO Train Epoch: 31 [0/32087 (0%)] Loss: 0.256671 +2025-04-14 15:44:56,174 INFO Train Epoch: 31 [3200/32087 (10%)] Loss: 0.329786 +2025-04-14 15:45:11,239 INFO Train Epoch: 31 [6400/32087 (20%)] Loss: 0.406742 +2025-04-14 15:45:26,690 INFO Train Epoch: 31 [9600/32087 (30%)] Loss: 0.308391 +2025-04-14 15:45:42,152 INFO Train Epoch: 31 [12800/32087 (40%)] Loss: 0.295223 +2025-04-14 15:45:57,421 INFO Train Epoch: 31 [16000/32087 (50%)] Loss: 0.351301 +2025-04-14 15:46:12,793 INFO Train Epoch: 31 [19200/32087 (60%)] Loss: 0.466063 +2025-04-14 15:46:28,172 INFO Train Epoch: 31 [22400/32087 (70%)] Loss: 0.463400 +2025-04-14 15:46:43,404 INFO Train Epoch: 31 [25600/32087 (80%)] Loss: 0.277279 +2025-04-14 15:46:58,436 INFO Train Epoch: 31 [28800/32087 (90%)] Loss: 0.325072 +2025-04-14 15:47:13,852 INFO Train Epoch: 31 [32000/32087 (100%)] Loss: 0.356026 +2025-04-14 15:47:50,461 INFO Accuracy qa: 70.14 % +2025-04-14 15:47:52,451 INFO Train Epoch: 32 [0/32087 (0%)] Loss: 0.436268 +2025-04-14 15:48:06,269 INFO Train Epoch: 32 [3200/32087 (10%)] Loss: 0.358692 +2025-04-14 15:48:20,674 INFO Train Epoch: 32 [6400/32087 (20%)] Loss: 0.262249 +2025-04-14 15:48:34,740 INFO Train Epoch: 32 [9600/32087 (30%)] Loss: 0.332275 +2025-04-14 15:48:49,278 INFO Train Epoch: 32 [12800/32087 (40%)] Loss: 0.373519 +2025-04-14 15:49:03,425 INFO Train Epoch: 32 [16000/32087 (50%)] Loss: 0.438990 +2025-04-14 15:49:17,549 INFO Train Epoch: 32 [19200/32087 (60%)] Loss: 0.313400 +2025-04-14 15:49:31,534 INFO Train Epoch: 32 [22400/32087 (70%)] Loss: 0.312576 +2025-04-14 15:49:45,792 INFO Train Epoch: 32 [25600/32087 (80%)] Loss: 0.332384 +2025-04-14 15:50:00,011 INFO Train Epoch: 32 [28800/32087 (90%)] Loss: 0.311460 +2025-04-14 15:50:14,171 INFO Train Epoch: 32 [32000/32087 (100%)] Loss: 0.287200 +2025-04-14 15:50:48,841 INFO Accuracy qa: 70.27 % +2025-04-14 15:50:51,153 INFO Train Epoch: 33 [0/32087 (0%)] Loss: 0.297336 +2025-04-14 15:51:04,936 INFO Train Epoch: 33 [3200/32087 (10%)] Loss: 0.306098 +2025-04-14 15:51:19,229 INFO Train Epoch: 33 [6400/32087 (20%)] Loss: 0.489985 +2025-04-14 15:51:33,848 INFO Train Epoch: 33 [9600/32087 (30%)] Loss: 0.353734 +2025-04-14 15:51:48,620 INFO Train Epoch: 33 [12800/32087 (40%)] Loss: 0.282860 +2025-04-14 15:52:02,921 INFO Train Epoch: 33 [16000/32087 (50%)] Loss: 0.324503 +2025-04-14 15:52:17,121 INFO Train Epoch: 33 [19200/32087 (60%)] Loss: 0.282040 +2025-04-14 15:52:31,397 INFO Train Epoch: 33 [22400/32087 (70%)] Loss: 0.353538 +2025-04-14 15:52:45,627 INFO Train Epoch: 33 [25600/32087 (80%)] Loss: 0.456073 +2025-04-14 15:53:00,023 INFO Train Epoch: 33 [28800/32087 (90%)] Loss: 0.318838 +2025-04-14 15:53:14,283 INFO Train Epoch: 33 [32000/32087 (100%)] Loss: 0.378579 +2025-04-14 15:53:47,582 INFO Accuracy qa: 70.53 % +2025-04-14 15:53:49,847 INFO Train Epoch: 34 [0/32087 (0%)] Loss: 0.280281 +2025-04-14 15:54:03,110 INFO Train Epoch: 34 [3200/32087 (10%)] Loss: 0.363319 +2025-04-14 15:54:17,492 INFO Train Epoch: 34 [6400/32087 (20%)] Loss: 0.368088 +2025-04-14 15:54:31,892 INFO Train Epoch: 34 [9600/32087 (30%)] Loss: 0.356653 +2025-04-14 15:54:46,099 INFO Train Epoch: 34 [12800/32087 (40%)] Loss: 0.253442 +2025-04-14 15:55:00,200 INFO Train Epoch: 34 [16000/32087 (50%)] Loss: 0.403006 +2025-04-14 15:55:14,338 INFO Train Epoch: 34 [19200/32087 (60%)] Loss: 0.287260 +2025-04-14 15:55:28,743 INFO Train Epoch: 34 [22400/32087 (70%)] Loss: 0.521270 +2025-04-14 15:55:43,136 INFO Train Epoch: 34 [25600/32087 (80%)] Loss: 0.340840 +2025-04-14 15:55:57,597 INFO Train Epoch: 34 [28800/32087 (90%)] Loss: 0.309371 +2025-04-14 15:56:12,111 INFO Train Epoch: 34 [32000/32087 (100%)] Loss: 0.262279 +2025-04-14 15:56:45,429 INFO Accuracy qa: 70.34 % +2025-04-14 15:56:47,158 INFO Train Epoch: 35 [0/32087 (0%)] Loss: 0.208316 +2025-04-14 15:57:01,903 INFO Train Epoch: 35 [3200/32087 (10%)] Loss: 0.317090 +2025-04-14 15:57:16,645 INFO Train Epoch: 35 [6400/32087 (20%)] Loss: 0.199312 +2025-04-14 15:57:30,826 INFO Train Epoch: 35 [9600/32087 (30%)] Loss: 0.300051 +2025-04-14 15:57:44,633 INFO Train Epoch: 35 [12800/32087 (40%)] Loss: 0.376196 +2025-04-14 15:57:58,747 INFO Train Epoch: 35 [16000/32087 (50%)] Loss: 0.330614 +2025-04-14 15:58:12,947 INFO Train Epoch: 35 [19200/32087 (60%)] Loss: 0.275474 +2025-04-14 15:58:27,189 INFO Train Epoch: 35 [22400/32087 (70%)] Loss: 0.377741 +2025-04-14 15:58:41,992 INFO Train Epoch: 35 [25600/32087 (80%)] Loss: 0.376853 +2025-04-14 15:58:56,260 INFO Train Epoch: 35 [28800/32087 (90%)] Loss: 0.293444 +2025-04-14 15:59:10,605 INFO Train Epoch: 35 [32000/32087 (100%)] Loss: 0.303881 +2025-04-14 15:59:44,699 INFO Accuracy qa: 70.36 % +2025-04-14 15:59:46,446 INFO Train Epoch: 36 [0/32087 (0%)] Loss: 0.290714 +2025-04-14 16:00:00,966 INFO Train Epoch: 36 [3200/32087 (10%)] Loss: 0.285794 +2025-04-14 16:00:15,047 INFO Train Epoch: 36 [6400/32087 (20%)] Loss: 0.269435 +2025-04-14 16:00:28,993 INFO Train Epoch: 36 [9600/32087 (30%)] Loss: 0.358402 +2025-04-14 16:00:42,826 INFO Train Epoch: 36 [12800/32087 (40%)] Loss: 0.321135 +2025-04-14 16:00:56,822 INFO Train Epoch: 36 [16000/32087 (50%)] Loss: 0.357185 +2025-04-14 16:01:11,013 INFO Train Epoch: 36 [19200/32087 (60%)] Loss: 0.380775 +2025-04-14 16:01:25,236 INFO Train Epoch: 36 [22400/32087 (70%)] Loss: 0.277599 +2025-04-14 16:01:39,702 INFO Train Epoch: 36 [25600/32087 (80%)] Loss: 0.228135 +2025-04-14 16:01:53,866 INFO Train Epoch: 36 [28800/32087 (90%)] Loss: 0.391240 +2025-04-14 16:02:08,045 INFO Train Epoch: 36 [32000/32087 (100%)] Loss: 0.301292 +2025-04-14 16:02:41,631 INFO Accuracy qa: 70.27 % +2025-04-14 16:02:43,664 INFO Train Epoch: 37 [0/32087 (0%)] Loss: 0.368728 +2025-04-14 16:02:57,769 INFO Train Epoch: 37 [3200/32087 (10%)] Loss: 0.210750 +2025-04-14 16:03:11,509 INFO Train Epoch: 37 [6400/32087 (20%)] Loss: 0.384422 +2025-04-14 16:03:25,778 INFO Train Epoch: 37 [9600/32087 (30%)] Loss: 0.295780 +2025-04-14 16:03:39,728 INFO Train Epoch: 37 [12800/32087 (40%)] Loss: 0.249489 +2025-04-14 16:03:54,233 INFO Train Epoch: 37 [16000/32087 (50%)] Loss: 0.321911 +2025-04-14 16:04:08,666 INFO Train Epoch: 37 [19200/32087 (60%)] Loss: 0.303345 +2025-04-14 16:04:23,140 INFO Train Epoch: 37 [22400/32087 (70%)] Loss: 0.239900 +2025-04-14 16:04:37,538 INFO Train Epoch: 37 [25600/32087 (80%)] Loss: 0.340470 +2025-04-14 16:04:51,936 INFO Train Epoch: 37 [28800/32087 (90%)] Loss: 0.258845 +2025-04-14 16:05:06,301 INFO Train Epoch: 37 [32000/32087 (100%)] Loss: 0.332176 +2025-04-14 16:05:39,377 INFO Accuracy qa: 70.29 % +2025-04-14 16:05:41,077 INFO Train Epoch: 38 [0/32087 (0%)] Loss: 0.345750 +2025-04-14 16:05:54,724 INFO Train Epoch: 38 [3200/32087 (10%)] Loss: 0.272077 +2025-04-14 16:06:08,682 INFO Train Epoch: 38 [6400/32087 (20%)] Loss: 0.239858 +2025-04-14 16:06:22,585 INFO Train Epoch: 38 [9600/32087 (30%)] Loss: 0.362736 +2025-04-14 16:06:36,917 INFO Train Epoch: 38 [12800/32087 (40%)] Loss: 0.299098 +2025-04-14 16:06:51,175 INFO Train Epoch: 38 [16000/32087 (50%)] Loss: 0.322828 +2025-04-14 16:07:05,686 INFO Train Epoch: 38 [19200/32087 (60%)] Loss: 0.262026 +2025-04-14 16:07:20,180 INFO Train Epoch: 38 [22400/32087 (70%)] Loss: 0.317026 +2025-04-14 16:07:34,644 INFO Train Epoch: 38 [25600/32087 (80%)] Loss: 0.218645 +2025-04-14 16:07:49,278 INFO Train Epoch: 38 [28800/32087 (90%)] Loss: 0.287380 +2025-04-14 16:08:03,887 INFO Train Epoch: 38 [32000/32087 (100%)] Loss: 0.312913 +2025-04-14 16:08:36,854 INFO Accuracy qa: 70.18 % +2025-04-14 16:08:39,254 INFO Train Epoch: 39 [0/32087 (0%)] Loss: 0.363203 +2025-04-14 16:08:52,833 INFO Train Epoch: 39 [3200/32087 (10%)] Loss: 0.337565 +2025-04-14 16:09:07,528 INFO Train Epoch: 39 [6400/32087 (20%)] Loss: 0.338999 +2025-04-14 16:09:22,691 INFO Train Epoch: 39 [9600/32087 (30%)] Loss: 0.304459 +2025-04-14 16:09:37,834 INFO Train Epoch: 39 [12800/32087 (40%)] Loss: 0.571618 +2025-04-14 16:09:53,026 INFO Train Epoch: 39 [16000/32087 (50%)] Loss: 0.411012 +2025-04-14 16:10:08,461 INFO Train Epoch: 39 [19200/32087 (60%)] Loss: 0.447543 +2025-04-14 16:10:23,942 INFO Train Epoch: 39 [22400/32087 (70%)] Loss: 0.332857 +2025-04-14 16:10:39,286 INFO Train Epoch: 39 [25600/32087 (80%)] Loss: 0.194348 +2025-04-14 16:10:54,106 INFO Train Epoch: 39 [28800/32087 (90%)] Loss: 0.478468 +2025-04-14 16:11:08,966 INFO Train Epoch: 39 [32000/32087 (100%)] Loss: 0.445513 +2025-04-14 16:11:46,286 INFO Accuracy qa: 70.21 % +2025-04-14 16:11:48,233 INFO Train Epoch: 40 [0/32087 (0%)] Loss: 0.434028 +2025-04-14 16:12:01,505 INFO Train Epoch: 40 [3200/32087 (10%)] Loss: 0.382160 +2025-04-14 16:12:15,426 INFO Train Epoch: 40 [6400/32087 (20%)] Loss: 0.261920 +2025-04-14 16:12:28,766 INFO Train Epoch: 40 [9600/32087 (30%)] Loss: 0.333875 +2025-04-14 16:12:42,065 INFO Train Epoch: 40 [12800/32087 (40%)] Loss: 0.435508 +2025-04-14 16:12:55,728 INFO Train Epoch: 40 [16000/32087 (50%)] Loss: 0.194823 +2025-04-14 16:13:09,100 INFO Train Epoch: 40 [19200/32087 (60%)] Loss: 0.282765 +2025-04-14 16:13:22,240 INFO Train Epoch: 40 [22400/32087 (70%)] Loss: 0.326201 +2025-04-14 16:13:34,675 INFO Train Epoch: 40 [25600/32087 (80%)] Loss: 0.333090 +2025-04-14 16:13:47,011 INFO Train Epoch: 40 [28800/32087 (90%)] Loss: 0.342557 +2025-04-14 16:13:59,346 INFO Train Epoch: 40 [32000/32087 (100%)] Loss: 0.447330 +2025-04-14 16:14:31,852 INFO Accuracy qa: 70.12 % +2025-04-14 16:14:33,659 INFO Train Epoch: 41 [0/32087 (0%)] Loss: 0.247747 +2025-04-14 16:14:45,578 INFO Train Epoch: 41 [3200/32087 (10%)] Loss: 0.209977 +2025-04-14 16:14:57,716 INFO Train Epoch: 41 [6400/32087 (20%)] Loss: 0.273577 +2025-04-14 16:15:10,467 INFO Train Epoch: 41 [9600/32087 (30%)] Loss: 0.303026 +2025-04-14 16:15:23,074 INFO Train Epoch: 41 [12800/32087 (40%)] Loss: 0.335784 +2025-04-14 16:15:35,237 INFO Train Epoch: 41 [16000/32087 (50%)] Loss: 0.398487 +2025-04-14 16:15:47,425 INFO Train Epoch: 41 [19200/32087 (60%)] Loss: 0.345756 +2025-04-14 16:15:59,834 INFO Train Epoch: 41 [22400/32087 (70%)] Loss: 0.270619 +2025-04-14 16:16:12,000 INFO Train Epoch: 41 [25600/32087 (80%)] Loss: 0.305709 +2025-04-14 16:16:24,485 INFO Train Epoch: 41 [28800/32087 (90%)] Loss: 0.320216 +2025-04-14 16:16:36,775 INFO Train Epoch: 41 [32000/32087 (100%)] Loss: 0.363959 +2025-04-14 16:17:09,062 INFO Accuracy qa: 70.18 % +2025-04-14 16:17:10,877 INFO Train Epoch: 42 [0/32087 (0%)] Loss: 0.351947 +2025-04-14 16:17:22,920 INFO Train Epoch: 42 [3200/32087 (10%)] Loss: 0.326250 +2025-04-14 16:17:35,339 INFO Train Epoch: 42 [6400/32087 (20%)] Loss: 0.352251 +2025-04-14 16:17:47,679 INFO Train Epoch: 42 [9600/32087 (30%)] Loss: 0.283677 +2025-04-14 16:18:00,210 INFO Train Epoch: 42 [12800/32087 (40%)] Loss: 0.325471 +2025-04-14 16:18:12,562 INFO Train Epoch: 42 [16000/32087 (50%)] Loss: 0.367707 +2025-04-14 16:18:24,924 INFO Train Epoch: 42 [19200/32087 (60%)] Loss: 0.293233 +2025-04-14 16:18:37,067 INFO Train Epoch: 42 [22400/32087 (70%)] Loss: 0.513675 +2025-04-14 16:18:49,426 INFO Train Epoch: 42 [25600/32087 (80%)] Loss: 0.334395 +2025-04-14 16:19:01,727 INFO Train Epoch: 42 [28800/32087 (90%)] Loss: 0.279686 +2025-04-14 16:19:14,336 INFO Train Epoch: 42 [32000/32087 (100%)] Loss: 0.196025 +2025-04-14 16:19:46,653 INFO Accuracy qa: 70.18 % +2025-04-14 16:19:48,217 INFO Train Epoch: 43 [0/32087 (0%)] Loss: 0.234842 +2025-04-14 16:20:00,447 INFO Train Epoch: 43 [3200/32087 (10%)] Loss: 0.375847 +2025-04-14 16:20:12,612 INFO Train Epoch: 43 [6400/32087 (20%)] Loss: 0.418695 +2025-04-14 16:20:24,769 INFO Train Epoch: 43 [9600/32087 (30%)] Loss: 0.415224 +2025-04-14 16:20:37,106 INFO Train Epoch: 43 [12800/32087 (40%)] Loss: 0.296194 +2025-04-14 16:20:49,326 INFO Train Epoch: 43 [16000/32087 (50%)] Loss: 0.284926 +2025-04-14 16:21:01,689 INFO Train Epoch: 43 [19200/32087 (60%)] Loss: 0.373342 +2025-04-14 16:21:14,103 INFO Train Epoch: 43 [22400/32087 (70%)] Loss: 0.392645 +2025-04-14 16:21:26,487 INFO Train Epoch: 43 [25600/32087 (80%)] Loss: 0.367347 +2025-04-14 16:21:39,205 INFO Train Epoch: 43 [28800/32087 (90%)] Loss: 0.424383 +2025-04-14 16:21:51,760 INFO Train Epoch: 43 [32000/32087 (100%)] Loss: 0.378179 +2025-04-14 16:22:24,656 INFO Accuracy qa: 70.23 % +2025-04-14 16:22:26,704 INFO Train Epoch: 44 [0/32087 (0%)] Loss: 0.284770 +2025-04-14 16:22:38,610 INFO Train Epoch: 44 [3200/32087 (10%)] Loss: 0.311916 +2025-04-14 16:22:51,068 INFO Train Epoch: 44 [6400/32087 (20%)] Loss: 0.318195 +2025-04-14 16:23:03,708 INFO Train Epoch: 44 [9600/32087 (30%)] Loss: 0.342634 +2025-04-14 16:23:16,330 INFO Train Epoch: 44 [12800/32087 (40%)] Loss: 0.317877 +2025-04-14 16:23:29,493 INFO Train Epoch: 44 [16000/32087 (50%)] Loss: 0.531025 +2025-04-14 16:23:42,573 INFO Train Epoch: 44 [19200/32087 (60%)] Loss: 0.332298 +2025-04-14 16:23:55,854 INFO Train Epoch: 44 [22400/32087 (70%)] Loss: 0.244434 +2025-04-14 16:24:09,520 INFO Train Epoch: 44 [25600/32087 (80%)] Loss: 0.301041 +2025-04-14 16:24:23,207 INFO Train Epoch: 44 [28800/32087 (90%)] Loss: 0.347274 +2025-04-14 16:24:36,715 INFO Train Epoch: 44 [32000/32087 (100%)] Loss: 0.342077 +2025-04-14 16:25:09,960 INFO Accuracy qa: 70.01 % +2025-04-14 16:25:12,173 INFO Train Epoch: 45 [0/32087 (0%)] Loss: 0.233230 +2025-04-14 16:25:24,914 INFO Train Epoch: 45 [3200/32087 (10%)] Loss: 0.335224 +2025-04-14 16:25:38,613 INFO Train Epoch: 45 [6400/32087 (20%)] Loss: 0.341809 +2025-04-14 16:25:51,908 INFO Train Epoch: 45 [9600/32087 (30%)] Loss: 0.333212 +2025-04-14 16:26:04,969 INFO Train Epoch: 45 [12800/32087 (40%)] Loss: 0.276439 +2025-04-14 16:26:18,046 INFO Train Epoch: 45 [16000/32087 (50%)] Loss: 0.412035 +2025-04-14 16:26:31,341 INFO Train Epoch: 45 [19200/32087 (60%)] Loss: 0.264620 +2025-04-14 16:26:44,478 INFO Train Epoch: 45 [22400/32087 (70%)] Loss: 0.310168 +2025-04-14 16:26:57,523 INFO Train Epoch: 45 [25600/32087 (80%)] Loss: 0.359707 +2025-04-14 16:27:10,863 INFO Train Epoch: 45 [28800/32087 (90%)] Loss: 0.295354 +2025-04-14 16:27:24,061 INFO Train Epoch: 45 [32000/32087 (100%)] Loss: 0.287207 +2025-04-14 16:27:57,811 INFO Accuracy qa: 70.23 % +2025-04-14 16:27:59,932 INFO Train Epoch: 46 [0/32087 (0%)] Loss: 0.255365 +2025-04-14 16:28:12,633 INFO Train Epoch: 46 [3200/32087 (10%)] Loss: 0.332240 +2025-04-14 16:28:26,191 INFO Train Epoch: 46 [6400/32087 (20%)] Loss: 0.302733 +2025-04-14 16:28:39,859 INFO Train Epoch: 46 [9600/32087 (30%)] Loss: 0.272879 +2025-04-14 16:28:53,046 INFO Train Epoch: 46 [12800/32087 (40%)] Loss: 0.418990 +2025-04-14 16:29:06,026 INFO Train Epoch: 46 [16000/32087 (50%)] Loss: 0.270354 +2025-04-14 16:29:19,169 INFO Train Epoch: 46 [19200/32087 (60%)] Loss: 0.194637 +2025-04-14 16:29:32,584 INFO Train Epoch: 46 [22400/32087 (70%)] Loss: 0.355486 +2025-04-14 16:29:46,622 INFO Train Epoch: 46 [25600/32087 (80%)] Loss: 0.305614 +2025-04-14 16:30:00,188 INFO Train Epoch: 46 [28800/32087 (90%)] Loss: 0.226349 +2025-04-14 16:30:13,731 INFO Train Epoch: 46 [32000/32087 (100%)] Loss: 0.403578 +2025-04-14 16:30:46,247 INFO Accuracy qa: 70.21 % +2025-04-14 16:30:47,820 INFO Train Epoch: 47 [0/32087 (0%)] Loss: 0.265008 +2025-04-14 16:31:01,038 INFO Train Epoch: 47 [3200/32087 (10%)] Loss: 0.365004 +2025-04-14 16:31:14,207 INFO Train Epoch: 47 [6400/32087 (20%)] Loss: 0.280385 +2025-04-14 16:31:27,550 INFO Train Epoch: 47 [9600/32087 (30%)] Loss: 0.292269 +2025-04-14 16:31:41,142 INFO Train Epoch: 47 [12800/32087 (40%)] Loss: 0.363880 +2025-04-14 16:31:54,569 INFO Train Epoch: 47 [16000/32087 (50%)] Loss: 0.408092 +2025-04-14 16:32:07,456 INFO Train Epoch: 47 [19200/32087 (60%)] Loss: 0.351260 +2025-04-14 16:32:20,804 INFO Train Epoch: 47 [22400/32087 (70%)] Loss: 0.425936 +2025-04-14 16:32:33,892 INFO Train Epoch: 47 [25600/32087 (80%)] Loss: 0.289339 +2025-04-14 16:32:47,280 INFO Train Epoch: 47 [28800/32087 (90%)] Loss: 0.413497 +2025-04-14 16:33:00,952 INFO Train Epoch: 47 [32000/32087 (100%)] Loss: 0.435255 +2025-04-14 16:33:34,207 INFO Accuracy qa: 70.14 % +2025-04-14 16:33:36,305 INFO Train Epoch: 48 [0/32087 (0%)] Loss: 0.315743 +2025-04-14 16:33:50,506 INFO Train Epoch: 48 [3200/32087 (10%)] Loss: 0.227937 +2025-04-14 16:34:05,629 INFO Train Epoch: 48 [6400/32087 (20%)] Loss: 0.214569 +2025-04-14 16:34:21,610 INFO Train Epoch: 48 [9600/32087 (30%)] Loss: 0.269374 +2025-04-14 16:34:37,037 INFO Train Epoch: 48 [12800/32087 (40%)] Loss: 0.312959 +2025-04-14 16:34:52,592 INFO Train Epoch: 48 [16000/32087 (50%)] Loss: 0.270418 +2025-04-14 16:35:08,907 INFO Train Epoch: 48 [19200/32087 (60%)] Loss: 0.413987 +2025-04-14 16:35:25,356 INFO Train Epoch: 48 [22400/32087 (70%)] Loss: 0.412776 +2025-04-14 16:35:40,626 INFO Train Epoch: 48 [25600/32087 (80%)] Loss: 0.251437 +2025-04-14 16:35:56,156 INFO Train Epoch: 48 [28800/32087 (90%)] Loss: 0.434258 +2025-04-14 16:36:12,482 INFO Train Epoch: 48 [32000/32087 (100%)] Loss: 0.295672 +2025-04-14 16:36:44,732 INFO Accuracy qa: 70.14 % +2025-04-14 16:36:46,304 INFO Train Epoch: 49 [0/32087 (0%)] Loss: 0.235770 +2025-04-14 16:36:59,384 INFO Train Epoch: 49 [3200/32087 (10%)] Loss: 0.380877 +2025-04-14 16:37:12,272 INFO Train Epoch: 49 [6400/32087 (20%)] Loss: 0.299272 +2025-04-14 16:37:25,545 INFO Train Epoch: 49 [9600/32087 (30%)] Loss: 0.372259 +2025-04-14 16:37:38,863 INFO Train Epoch: 49 [12800/32087 (40%)] Loss: 0.255064 +2025-04-14 16:37:52,469 INFO Train Epoch: 49 [16000/32087 (50%)] Loss: 0.211307 +2025-04-14 16:38:05,215 INFO Train Epoch: 49 [19200/32087 (60%)] Loss: 0.362848 +2025-04-14 16:38:17,828 INFO Train Epoch: 49 [22400/32087 (70%)] Loss: 0.290487 +2025-04-14 16:38:30,850 INFO Train Epoch: 49 [25600/32087 (80%)] Loss: 0.333140 +2025-04-14 16:38:43,773 INFO Train Epoch: 49 [28800/32087 (90%)] Loss: 0.299995 +2025-04-14 16:38:57,071 INFO Train Epoch: 49 [32000/32087 (100%)] Loss: 0.402821 +2025-04-14 16:39:29,494 INFO Accuracy qa: 70.18 % +2025-04-14 16:39:31,096 INFO Train Epoch: 50 [0/32087 (0%)] Loss: 0.361564 +2025-04-14 16:39:44,349 INFO Train Epoch: 50 [3200/32087 (10%)] Loss: 0.324960 +2025-04-14 16:39:57,832 INFO Train Epoch: 50 [6400/32087 (20%)] Loss: 0.416954 +2025-04-14 16:40:11,530 INFO Train Epoch: 50 [9600/32087 (30%)] Loss: 0.248217 +2025-04-14 16:40:25,300 INFO Train Epoch: 50 [12800/32087 (40%)] Loss: 0.321716 +2025-04-14 16:40:39,089 INFO Train Epoch: 50 [16000/32087 (50%)] Loss: 0.481065 +2025-04-14 16:40:52,765 INFO Train Epoch: 50 [19200/32087 (60%)] Loss: 0.387674 +2025-04-14 16:41:07,100 INFO Train Epoch: 50 [22400/32087 (70%)] Loss: 0.375402 +2025-04-14 16:41:20,683 INFO Train Epoch: 50 [25600/32087 (80%)] Loss: 0.323695 +2025-04-14 16:41:34,198 INFO Train Epoch: 50 [28800/32087 (90%)] Loss: 0.322419 +2025-04-14 16:41:47,900 INFO Train Epoch: 50 [32000/32087 (100%)] Loss: 0.311156 +2025-04-14 16:42:22,842 INFO Accuracy qa: 70.18 % diff --git a/Audio Visual Question Answering/results_baseline/inverse_True_withmodified/net_grd_baseline.pt b/Audio Visual Question Answering/results_baseline/inverse_True_withmodified/net_grd_baseline.pt new file mode 100644 index 0000000000000000000000000000000000000000..79fd11cd470b19bff843c427d6b07cafd0d91be8 --- /dev/null +++ b/Audio Visual Question Answering/results_baseline/inverse_True_withmodified/net_grd_baseline.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d57cdad9ad820d61b359a57da9b72f86272fd7ae41a2e7d19b1c41e13e382a +size 88163031 diff --git a/Audio Visual Question Answering/results_baseline/inverse_True_withmodified/test.log b/Audio Visual Question Answering/results_baseline/inverse_True_withmodified/test.log new file mode 100644 index 0000000000000000000000000000000000000000..a1f81db8f816c298c733a89d1086a4e0e5d9be7c --- /dev/null +++ b/Audio Visual Question Answering/results_baseline/inverse_True_withmodified/test.log @@ -0,0 +1,4 @@ +2025-04-15 08:00:57,230 INFO +--------------- MUSIC-AVQA baseline --------------- + +2025-04-15 08:01:01,782 INFO 9185 diff --git a/Audio Visual Question Answering/results_baseline/inverse_True_withmodified/train.log b/Audio Visual Question Answering/results_baseline/inverse_True_withmodified/train.log new file mode 100644 index 0000000000000000000000000000000000000000..8adaccda13af331fd825e5f102af09680d5b5327 --- /dev/null +++ b/Audio Visual Question Answering/results_baseline/inverse_True_withmodified/train.log @@ -0,0 +1,603 @@ +2025-04-14 14:17:58,143 INFO +--------------- MUSIC-AVQA baseline --------------- + +2025-04-14 14:18:08,961 INFO Train Epoch: 1 [0/32087 (0%)] Loss: 11.135600 +2025-04-14 14:18:20,726 INFO Train Epoch: 1 [3200/32087 (10%)] Loss: 7.364690 +2025-04-14 14:18:34,138 INFO Train Epoch: 1 [6400/32087 (20%)] Loss: 7.068512 +2025-04-14 14:18:47,397 INFO Train Epoch: 1 [9600/32087 (30%)] Loss: 5.195554 +2025-04-14 14:19:01,058 INFO Train Epoch: 1 [12800/32087 (40%)] Loss: 4.540992 +2025-04-14 14:19:14,036 INFO Train Epoch: 1 [16000/32087 (50%)] Loss: 3.749426 +2025-04-14 14:19:26,835 INFO Train Epoch: 1 [19200/32087 (60%)] Loss: 3.440375 +2025-04-14 14:19:39,979 INFO Train Epoch: 1 [22400/32087 (70%)] Loss: 2.632962 +2025-04-14 14:19:53,327 INFO Train Epoch: 1 [25600/32087 (80%)] Loss: 2.970006 +2025-04-14 14:20:06,524 INFO Train Epoch: 1 [28800/32087 (90%)] Loss: 3.507218 +2025-04-14 14:20:19,323 INFO Train Epoch: 1 [32000/32087 (100%)] Loss: 3.124297 +2025-04-14 14:20:52,368 INFO Accuracy qa: 55.73 % +2025-04-14 14:20:55,294 INFO Train Epoch: 2 [0/32087 (0%)] Loss: 3.768878 +2025-04-14 14:21:07,592 INFO Train Epoch: 2 [3200/32087 (10%)] Loss: 2.867080 +2025-04-14 14:21:20,925 INFO Train Epoch: 2 [6400/32087 (20%)] Loss: 3.399297 +2025-04-14 14:21:34,200 INFO Train Epoch: 2 [9600/32087 (30%)] Loss: 2.777150 +2025-04-14 14:21:47,975 INFO Train Epoch: 2 [12800/32087 (40%)] Loss: 3.441352 +2025-04-14 14:22:01,784 INFO Train Epoch: 2 [16000/32087 (50%)] Loss: 3.115479 +2025-04-14 14:22:15,350 INFO Train Epoch: 2 [19200/32087 (60%)] Loss: 2.768426 +2025-04-14 14:22:29,310 INFO Train Epoch: 2 [22400/32087 (70%)] Loss: 3.576672 +2025-04-14 14:22:43,312 INFO Train Epoch: 2 [25600/32087 (80%)] Loss: 2.977846 +2025-04-14 14:22:57,502 INFO Train Epoch: 2 [28800/32087 (90%)] Loss: 2.827591 +2025-04-14 14:23:11,359 INFO Train Epoch: 2 [32000/32087 (100%)] Loss: 3.049961 +2025-04-14 14:23:46,563 INFO Accuracy qa: 62.79 % +2025-04-14 14:23:49,545 INFO Train Epoch: 3 [0/32087 (0%)] Loss: 3.177167 +2025-04-14 14:24:02,333 INFO Train Epoch: 3 [3200/32087 (10%)] Loss: 2.328886 +2025-04-14 14:24:14,795 INFO Train Epoch: 3 [6400/32087 (20%)] Loss: 2.852230 +2025-04-14 14:24:27,019 INFO Train Epoch: 3 [9600/32087 (30%)] Loss: 2.911072 +2025-04-14 14:24:39,244 INFO Train Epoch: 3 [12800/32087 (40%)] Loss: 2.305881 +2025-04-14 14:24:51,518 INFO Train Epoch: 3 [16000/32087 (50%)] Loss: 2.624299 +2025-04-14 14:25:03,736 INFO Train Epoch: 3 [19200/32087 (60%)] Loss: 2.508310 +2025-04-14 14:25:15,658 INFO Train Epoch: 3 [22400/32087 (70%)] Loss: 2.873042 +2025-04-14 14:25:27,969 INFO Train Epoch: 3 [25600/32087 (80%)] Loss: 2.535102 +2025-04-14 14:25:39,871 INFO Train Epoch: 3 [28800/32087 (90%)] Loss: 2.430094 +2025-04-14 14:25:52,107 INFO Train Epoch: 3 [32000/32087 (100%)] Loss: 2.868173 +2025-04-14 14:26:24,702 INFO Accuracy qa: 62.92 % +2025-04-14 14:26:27,747 INFO Train Epoch: 4 [0/32087 (0%)] Loss: 2.363784 +2025-04-14 14:26:39,347 INFO Train Epoch: 4 [3200/32087 (10%)] Loss: 2.216491 +2025-04-14 14:26:51,510 INFO Train Epoch: 4 [6400/32087 (20%)] Loss: 2.490469 +2025-04-14 14:27:03,661 INFO Train Epoch: 4 [9600/32087 (30%)] Loss: 2.854316 +2025-04-14 14:27:15,766 INFO Train Epoch: 4 [12800/32087 (40%)] Loss: 2.491021 +2025-04-14 14:27:27,791 INFO Train Epoch: 4 [16000/32087 (50%)] Loss: 3.040612 +2025-04-14 14:27:39,904 INFO Train Epoch: 4 [19200/32087 (60%)] Loss: 2.597455 +2025-04-14 14:27:52,491 INFO Train Epoch: 4 [22400/32087 (70%)] Loss: 3.134664 +2025-04-14 14:28:04,413 INFO Train Epoch: 4 [25600/32087 (80%)] Loss: 2.519042 +2025-04-14 14:28:16,502 INFO Train Epoch: 4 [28800/32087 (90%)] Loss: 2.391088 +2025-04-14 14:28:28,669 INFO Train Epoch: 4 [32000/32087 (100%)] Loss: 2.792679 +2025-04-14 14:29:00,229 INFO Accuracy qa: 66.05 % +2025-04-14 14:29:03,100 INFO Train Epoch: 5 [0/32087 (0%)] Loss: 2.406091 +2025-04-14 14:29:15,161 INFO Train Epoch: 5 [3200/32087 (10%)] Loss: 2.652058 +2025-04-14 14:29:27,373 INFO Train Epoch: 5 [6400/32087 (20%)] Loss: 2.703589 +2025-04-14 14:29:40,003 INFO Train Epoch: 5 [9600/32087 (30%)] Loss: 2.465648 +2025-04-14 14:29:52,210 INFO Train Epoch: 5 [12800/32087 (40%)] Loss: 1.994576 +2025-04-14 14:30:04,926 INFO Train Epoch: 5 [16000/32087 (50%)] Loss: 2.687036 +2025-04-14 14:30:17,685 INFO Train Epoch: 5 [19200/32087 (60%)] Loss: 2.728695 +2025-04-14 14:30:31,074 INFO Train Epoch: 5 [22400/32087 (70%)] Loss: 2.126622 +2025-04-14 14:30:43,754 INFO Train Epoch: 5 [25600/32087 (80%)] Loss: 3.467501 +2025-04-14 14:30:56,683 INFO Train Epoch: 5 [28800/32087 (90%)] Loss: 2.565040 +2025-04-14 14:31:09,459 INFO Train Epoch: 5 [32000/32087 (100%)] Loss: 2.874238 +2025-04-14 14:31:41,387 INFO Accuracy qa: 65.88 % +2025-04-14 14:31:43,286 INFO Train Epoch: 6 [0/32087 (0%)] Loss: 2.863434 +2025-04-14 14:31:56,626 INFO Train Epoch: 6 [3200/32087 (10%)] Loss: 2.078894 +2025-04-14 14:32:10,671 INFO Train Epoch: 6 [6400/32087 (20%)] Loss: 3.209615 +2025-04-14 14:32:23,785 INFO Train Epoch: 6 [9600/32087 (30%)] Loss: 2.259924 +2025-04-14 14:32:36,665 INFO Train Epoch: 6 [12800/32087 (40%)] Loss: 2.197019 +2025-04-14 14:32:49,943 INFO Train Epoch: 6 [16000/32087 (50%)] Loss: 2.184758 +2025-04-14 14:33:03,939 INFO Train Epoch: 6 [19200/32087 (60%)] Loss: 2.701153 +2025-04-14 14:33:17,408 INFO Train Epoch: 6 [22400/32087 (70%)] Loss: 3.102221 +2025-04-14 14:33:30,142 INFO Train Epoch: 6 [25600/32087 (80%)] Loss: 2.797102 +2025-04-14 14:33:42,753 INFO Train Epoch: 6 [28800/32087 (90%)] Loss: 2.565823 +2025-04-14 14:33:55,380 INFO Train Epoch: 6 [32000/32087 (100%)] Loss: 2.482361 +2025-04-14 14:34:27,648 INFO Accuracy qa: 66.29 % +2025-04-14 14:34:30,653 INFO Train Epoch: 7 [0/32087 (0%)] Loss: 2.143065 +2025-04-14 14:34:43,564 INFO Train Epoch: 7 [3200/32087 (10%)] Loss: 2.529385 +2025-04-14 14:34:56,792 INFO Train Epoch: 7 [6400/32087 (20%)] Loss: 2.817671 +2025-04-14 14:35:09,966 INFO Train Epoch: 7 [9600/32087 (30%)] Loss: 2.729116 +2025-04-14 14:35:23,410 INFO Train Epoch: 7 [12800/32087 (40%)] Loss: 2.662685 +2025-04-14 14:35:36,863 INFO Train Epoch: 7 [16000/32087 (50%)] Loss: 2.341216 +2025-04-14 14:35:50,314 INFO Train Epoch: 7 [19200/32087 (60%)] Loss: 1.942506 +2025-04-14 14:36:04,297 INFO Train Epoch: 7 [22400/32087 (70%)] Loss: 2.287499 +2025-04-14 14:36:17,044 INFO Train Epoch: 7 [25600/32087 (80%)] Loss: 2.728823 +2025-04-14 14:36:29,856 INFO Train Epoch: 7 [28800/32087 (90%)] Loss: 2.278559 +2025-04-14 14:36:42,739 INFO Train Epoch: 7 [32000/32087 (100%)] Loss: 2.720886 +2025-04-14 14:37:14,499 INFO Accuracy qa: 67.86 % +2025-04-14 14:37:16,897 INFO Train Epoch: 8 [0/32087 (0%)] Loss: 2.202731 +2025-04-14 14:37:31,054 INFO Train Epoch: 8 [3200/32087 (10%)] Loss: 2.642355 +2025-04-14 14:37:46,536 INFO Train Epoch: 8 [6400/32087 (20%)] Loss: 1.894911 +2025-04-14 14:38:01,240 INFO Train Epoch: 8 [9600/32087 (30%)] Loss: 2.171402 +2025-04-14 14:38:16,369 INFO Train Epoch: 8 [12800/32087 (40%)] Loss: 3.051813 +2025-04-14 14:38:31,125 INFO Train Epoch: 8 [16000/32087 (50%)] Loss: 2.584575 +2025-04-14 14:38:45,732 INFO Train Epoch: 8 [19200/32087 (60%)] Loss: 2.197372 +2025-04-14 14:39:01,312 INFO Train Epoch: 8 [22400/32087 (70%)] Loss: 2.315194 +2025-04-14 14:39:15,622 INFO Train Epoch: 8 [25600/32087 (80%)] Loss: 2.601215 +2025-04-14 14:39:29,146 INFO Train Epoch: 8 [28800/32087 (90%)] Loss: 2.497694 +2025-04-14 14:39:42,367 INFO Train Epoch: 8 [32000/32087 (100%)] Loss: 1.996875 +2025-04-14 14:40:17,679 INFO Accuracy qa: 68.12 % +2025-04-14 14:40:20,101 INFO Train Epoch: 9 [0/32087 (0%)] Loss: 1.774943 +2025-04-14 14:40:33,688 INFO Train Epoch: 9 [3200/32087 (10%)] Loss: 2.804988 +2025-04-14 14:40:46,734 INFO Train Epoch: 9 [6400/32087 (20%)] Loss: 2.042873 +2025-04-14 14:40:59,738 INFO Train Epoch: 9 [9600/32087 (30%)] Loss: 2.495772 +2025-04-14 14:41:12,975 INFO Train Epoch: 9 [12800/32087 (40%)] Loss: 2.850308 +2025-04-14 14:41:26,559 INFO Train Epoch: 9 [16000/32087 (50%)] Loss: 2.021014 +2025-04-14 14:41:40,212 INFO Train Epoch: 9 [19200/32087 (60%)] Loss: 2.506781 +2025-04-14 14:41:52,977 INFO Train Epoch: 9 [22400/32087 (70%)] Loss: 2.217717 +2025-04-14 14:42:05,560 INFO Train Epoch: 9 [25600/32087 (80%)] Loss: 2.857388 +2025-04-14 14:42:17,973 INFO Train Epoch: 9 [28800/32087 (90%)] Loss: 1.855416 +2025-04-14 14:42:31,528 INFO Train Epoch: 9 [32000/32087 (100%)] Loss: 2.070795 +2025-04-14 14:43:09,359 INFO Accuracy qa: 66.96 % +2025-04-14 14:43:10,989 INFO Train Epoch: 10 [0/32087 (0%)] Loss: 2.371837 +2025-04-14 14:43:24,726 INFO Train Epoch: 10 [3200/32087 (10%)] Loss: 2.575379 +2025-04-14 14:43:38,511 INFO Train Epoch: 10 [6400/32087 (20%)] Loss: 2.097819 +2025-04-14 14:43:51,720 INFO Train Epoch: 10 [9600/32087 (30%)] Loss: 1.650034 +2025-04-14 14:44:04,820 INFO Train Epoch: 10 [12800/32087 (40%)] Loss: 2.479388 +2025-04-14 14:44:18,141 INFO Train Epoch: 10 [16000/32087 (50%)] Loss: 2.076856 +2025-04-14 14:44:31,295 INFO Train Epoch: 10 [19200/32087 (60%)] Loss: 2.371568 +2025-04-14 14:44:43,979 INFO Train Epoch: 10 [22400/32087 (70%)] Loss: 2.603400 +2025-04-14 14:44:56,606 INFO Train Epoch: 10 [25600/32087 (80%)] Loss: 2.304941 +2025-04-14 14:45:09,537 INFO Train Epoch: 10 [28800/32087 (90%)] Loss: 2.431160 +2025-04-14 14:45:22,778 INFO Train Epoch: 10 [32000/32087 (100%)] Loss: 2.523741 +2025-04-14 14:45:55,391 INFO Accuracy qa: 67.64 % +2025-04-14 14:45:56,992 INFO Train Epoch: 11 [0/32087 (0%)] Loss: 1.969835 +2025-04-14 14:46:13,050 INFO Train Epoch: 11 [3200/32087 (10%)] Loss: 1.890190 +2025-04-14 14:46:30,207 INFO Train Epoch: 11 [6400/32087 (20%)] Loss: 2.269903 +2025-04-14 14:46:46,325 INFO Train Epoch: 11 [9600/32087 (30%)] Loss: 1.800577 +2025-04-14 14:47:02,894 INFO Train Epoch: 11 [12800/32087 (40%)] Loss: 2.799940 +2025-04-14 14:47:19,550 INFO Train Epoch: 11 [16000/32087 (50%)] Loss: 2.686574 +2025-04-14 14:47:34,990 INFO Train Epoch: 11 [19200/32087 (60%)] Loss: 2.556901 +2025-04-14 14:47:50,295 INFO Train Epoch: 11 [22400/32087 (70%)] Loss: 2.293682 +2025-04-14 14:48:05,772 INFO Train Epoch: 11 [25600/32087 (80%)] Loss: 2.325539 +2025-04-14 14:48:21,703 INFO Train Epoch: 11 [28800/32087 (90%)] Loss: 1.822499 +2025-04-14 14:48:37,092 INFO Train Epoch: 11 [32000/32087 (100%)] Loss: 2.333703 +2025-04-14 14:49:15,954 INFO Accuracy qa: 66.96 % +2025-04-14 14:49:18,309 INFO Train Epoch: 12 [0/32087 (0%)] Loss: 1.658885 +2025-04-14 14:49:32,606 INFO Train Epoch: 12 [3200/32087 (10%)] Loss: 1.999010 +2025-04-14 14:49:47,294 INFO Train Epoch: 12 [6400/32087 (20%)] Loss: 2.226998 +2025-04-14 14:50:02,097 INFO Train Epoch: 12 [9600/32087 (30%)] Loss: 2.034227 +2025-04-14 14:50:16,458 INFO Train Epoch: 12 [12800/32087 (40%)] Loss: 2.246187 +2025-04-14 14:50:31,013 INFO Train Epoch: 12 [16000/32087 (50%)] Loss: 2.537183 +2025-04-14 14:50:45,226 INFO Train Epoch: 12 [19200/32087 (60%)] Loss: 2.441936 +2025-04-14 14:50:59,530 INFO Train Epoch: 12 [22400/32087 (70%)] Loss: 2.197194 +2025-04-14 14:51:13,948 INFO Train Epoch: 12 [25600/32087 (80%)] Loss: 2.192695 +2025-04-14 14:51:28,253 INFO Train Epoch: 12 [28800/32087 (90%)] Loss: 2.615499 +2025-04-14 14:51:42,423 INFO Train Epoch: 12 [32000/32087 (100%)] Loss: 1.740682 +2025-04-14 14:52:15,199 INFO Accuracy qa: 69.29 % +2025-04-14 14:52:18,009 INFO Train Epoch: 13 [0/32087 (0%)] Loss: 1.852137 +2025-04-14 14:52:31,659 INFO Train Epoch: 13 [3200/32087 (10%)] Loss: 2.806625 +2025-04-14 14:52:45,401 INFO Train Epoch: 13 [6400/32087 (20%)] Loss: 1.991782 +2025-04-14 14:52:59,144 INFO Train Epoch: 13 [9600/32087 (30%)] Loss: 2.398249 +2025-04-14 14:53:13,021 INFO Train Epoch: 13 [12800/32087 (40%)] Loss: 2.429417 +2025-04-14 14:53:26,895 INFO Train Epoch: 13 [16000/32087 (50%)] Loss: 2.391937 +2025-04-14 14:53:40,708 INFO Train Epoch: 13 [19200/32087 (60%)] Loss: 1.826731 +2025-04-14 14:53:54,793 INFO Train Epoch: 13 [22400/32087 (70%)] Loss: 1.672943 +2025-04-14 14:54:08,789 INFO Train Epoch: 13 [25600/32087 (80%)] Loss: 2.010278 +2025-04-14 14:54:22,889 INFO Train Epoch: 13 [28800/32087 (90%)] Loss: 2.221467 +2025-04-14 14:54:37,033 INFO Train Epoch: 13 [32000/32087 (100%)] Loss: 2.078877 +2025-04-14 14:55:10,251 INFO Accuracy qa: 69.55 % +2025-04-14 14:55:13,322 INFO Train Epoch: 14 [0/32087 (0%)] Loss: 2.089366 +2025-04-14 14:55:26,760 INFO Train Epoch: 14 [3200/32087 (10%)] Loss: 2.124581 +2025-04-14 14:55:40,567 INFO Train Epoch: 14 [6400/32087 (20%)] Loss: 2.059298 +2025-04-14 14:55:54,416 INFO Train Epoch: 14 [9600/32087 (30%)] Loss: 2.186012 +2025-04-14 14:56:08,067 INFO Train Epoch: 14 [12800/32087 (40%)] Loss: 1.890198 +2025-04-14 14:56:22,365 INFO Train Epoch: 14 [16000/32087 (50%)] Loss: 1.956767 +2025-04-14 14:56:36,949 INFO Train Epoch: 14 [19200/32087 (60%)] Loss: 2.014162 +2025-04-14 14:56:51,859 INFO Train Epoch: 14 [22400/32087 (70%)] Loss: 2.113208 +2025-04-14 14:57:06,342 INFO Train Epoch: 14 [25600/32087 (80%)] Loss: 1.866607 +2025-04-14 14:57:20,694 INFO Train Epoch: 14 [28800/32087 (90%)] Loss: 1.694198 +2025-04-14 14:57:35,082 INFO Train Epoch: 14 [32000/32087 (100%)] Loss: 2.004131 +2025-04-14 14:58:09,493 INFO Accuracy qa: 68.73 % +2025-04-14 14:58:11,757 INFO Train Epoch: 15 [0/32087 (0%)] Loss: 1.884372 +2025-04-14 14:58:25,356 INFO Train Epoch: 15 [3200/32087 (10%)] Loss: 1.494891 +2025-04-14 14:58:39,060 INFO Train Epoch: 15 [6400/32087 (20%)] Loss: 1.586338 +2025-04-14 14:58:52,751 INFO Train Epoch: 15 [9600/32087 (30%)] Loss: 1.375357 +2025-04-14 14:59:06,505 INFO Train Epoch: 15 [12800/32087 (40%)] Loss: 2.249859 +2025-04-14 14:59:20,788 INFO Train Epoch: 15 [16000/32087 (50%)] Loss: 2.026973 +2025-04-14 14:59:34,840 INFO Train Epoch: 15 [19200/32087 (60%)] Loss: 1.851288 +2025-04-14 14:59:48,537 INFO Train Epoch: 15 [22400/32087 (70%)] Loss: 1.736784 +2025-04-14 15:00:02,391 INFO Train Epoch: 15 [25600/32087 (80%)] Loss: 1.660698 +2025-04-14 15:00:16,521 INFO Train Epoch: 15 [28800/32087 (90%)] Loss: 2.056398 +2025-04-14 15:00:30,446 INFO Train Epoch: 15 [32000/32087 (100%)] Loss: 1.996087 +2025-04-14 15:01:03,418 INFO Accuracy qa: 68.73 % +2025-04-14 15:01:05,139 INFO Train Epoch: 16 [0/32087 (0%)] Loss: 1.614007 +2025-04-14 15:01:18,962 INFO Train Epoch: 16 [3200/32087 (10%)] Loss: 1.731161 +2025-04-14 15:01:32,670 INFO Train Epoch: 16 [6400/32087 (20%)] Loss: 1.656567 +2025-04-14 15:01:46,561 INFO Train Epoch: 16 [9600/32087 (30%)] Loss: 1.315323 +2025-04-14 15:02:00,637 INFO Train Epoch: 16 [12800/32087 (40%)] Loss: 1.695956 +2025-04-14 15:02:14,703 INFO Train Epoch: 16 [16000/32087 (50%)] Loss: 1.802196 +2025-04-14 15:02:28,878 INFO Train Epoch: 16 [19200/32087 (60%)] Loss: 1.382340 +2025-04-14 15:02:42,817 INFO Train Epoch: 16 [22400/32087 (70%)] Loss: 1.810975 +2025-04-14 15:02:56,770 INFO Train Epoch: 16 [25600/32087 (80%)] Loss: 1.480571 +2025-04-14 15:03:10,988 INFO Train Epoch: 16 [28800/32087 (90%)] Loss: 1.615031 +2025-04-14 15:03:25,194 INFO Train Epoch: 16 [32000/32087 (100%)] Loss: 1.544230 +2025-04-14 15:03:58,382 INFO Accuracy qa: 72.03 % +2025-04-14 15:04:01,434 INFO Train Epoch: 17 [0/32087 (0%)] Loss: 1.189268 +2025-04-14 15:04:14,410 INFO Train Epoch: 17 [3200/32087 (10%)] Loss: 1.386506 +2025-04-14 15:04:28,341 INFO Train Epoch: 17 [6400/32087 (20%)] Loss: 1.414261 +2025-04-14 15:04:42,231 INFO Train Epoch: 17 [9600/32087 (30%)] Loss: 1.728883 +2025-04-14 15:04:56,126 INFO Train Epoch: 17 [12800/32087 (40%)] Loss: 1.466467 +2025-04-14 15:05:10,175 INFO Train Epoch: 17 [16000/32087 (50%)] Loss: 1.439550 +2025-04-14 15:05:24,219 INFO Train Epoch: 17 [19200/32087 (60%)] Loss: 1.513353 +2025-04-14 15:05:38,191 INFO Train Epoch: 17 [22400/32087 (70%)] Loss: 1.531892 +2025-04-14 15:05:52,377 INFO Train Epoch: 17 [25600/32087 (80%)] Loss: 1.723068 +2025-04-14 15:06:06,534 INFO Train Epoch: 17 [28800/32087 (90%)] Loss: 1.954127 +2025-04-14 15:06:20,612 INFO Train Epoch: 17 [32000/32087 (100%)] Loss: 1.439090 +2025-04-14 15:06:54,071 INFO Accuracy qa: 71.97 % +2025-04-14 15:06:56,319 INFO Train Epoch: 18 [0/32087 (0%)] Loss: 1.734136 +2025-04-14 15:07:09,288 INFO Train Epoch: 18 [3200/32087 (10%)] Loss: 1.326802 +2025-04-14 15:07:22,999 INFO Train Epoch: 18 [6400/32087 (20%)] Loss: 1.173816 +2025-04-14 15:07:36,881 INFO Train Epoch: 18 [9600/32087 (30%)] Loss: 2.032619 +2025-04-14 15:07:51,079 INFO Train Epoch: 18 [12800/32087 (40%)] Loss: 1.200576 +2025-04-14 15:08:05,009 INFO Train Epoch: 18 [16000/32087 (50%)] Loss: 1.298542 +2025-04-14 15:08:18,796 INFO Train Epoch: 18 [19200/32087 (60%)] Loss: 1.721962 +2025-04-14 15:08:32,873 INFO Train Epoch: 18 [22400/32087 (70%)] Loss: 1.402735 +2025-04-14 15:08:46,741 INFO Train Epoch: 18 [25600/32087 (80%)] Loss: 1.212229 +2025-04-14 15:09:00,758 INFO Train Epoch: 18 [28800/32087 (90%)] Loss: 1.785019 +2025-04-14 15:09:14,977 INFO Train Epoch: 18 [32000/32087 (100%)] Loss: 1.821638 +2025-04-14 15:09:47,495 INFO Accuracy qa: 71.10 % +2025-04-14 15:09:49,762 INFO Train Epoch: 19 [0/32087 (0%)] Loss: 1.667534 +2025-04-14 15:10:03,196 INFO Train Epoch: 19 [3200/32087 (10%)] Loss: 1.439339 +2025-04-14 15:10:17,345 INFO Train Epoch: 19 [6400/32087 (20%)] Loss: 1.404895 +2025-04-14 15:10:31,371 INFO Train Epoch: 19 [9600/32087 (30%)] Loss: 1.132032 +2025-04-14 15:10:45,224 INFO Train Epoch: 19 [12800/32087 (40%)] Loss: 1.413681 +2025-04-14 15:10:59,189 INFO Train Epoch: 19 [16000/32087 (50%)] Loss: 1.361715 +2025-04-14 15:11:13,018 INFO Train Epoch: 19 [19200/32087 (60%)] Loss: 1.466890 +2025-04-14 15:11:26,469 INFO Train Epoch: 19 [22400/32087 (70%)] Loss: 1.491165 +2025-04-14 15:11:40,289 INFO Train Epoch: 19 [25600/32087 (80%)] Loss: 1.526748 +2025-04-14 15:11:54,034 INFO Train Epoch: 19 [28800/32087 (90%)] Loss: 1.732161 +2025-04-14 15:12:07,912 INFO Train Epoch: 19 [32000/32087 (100%)] Loss: 1.422803 +2025-04-14 15:12:40,413 INFO Accuracy qa: 71.66 % +2025-04-14 15:12:42,136 INFO Train Epoch: 20 [0/32087 (0%)] Loss: 1.587152 +2025-04-14 15:12:55,680 INFO Train Epoch: 20 [3200/32087 (10%)] Loss: 1.459405 +2025-04-14 15:13:09,136 INFO Train Epoch: 20 [6400/32087 (20%)] Loss: 1.661721 +2025-04-14 15:13:22,901 INFO Train Epoch: 20 [9600/32087 (30%)] Loss: 1.293485 +2025-04-14 15:13:36,807 INFO Train Epoch: 20 [12800/32087 (40%)] Loss: 1.361293 +2025-04-14 15:13:50,681 INFO Train Epoch: 20 [16000/32087 (50%)] Loss: 1.392581 +2025-04-14 15:14:04,862 INFO Train Epoch: 20 [19200/32087 (60%)] Loss: 1.155551 +2025-04-14 15:14:18,687 INFO Train Epoch: 20 [22400/32087 (70%)] Loss: 1.384133 +2025-04-14 15:14:32,608 INFO Train Epoch: 20 [25600/32087 (80%)] Loss: 1.426189 +2025-04-14 15:14:46,317 INFO Train Epoch: 20 [28800/32087 (90%)] Loss: 1.035568 +2025-04-14 15:15:00,156 INFO Train Epoch: 20 [32000/32087 (100%)] Loss: 1.210291 +2025-04-14 15:15:33,173 INFO Accuracy qa: 71.69 % +2025-04-14 15:15:35,180 INFO Train Epoch: 21 [0/32087 (0%)] Loss: 1.281746 +2025-04-14 15:15:48,920 INFO Train Epoch: 21 [3200/32087 (10%)] Loss: 1.572526 +2025-04-14 15:16:02,846 INFO Train Epoch: 21 [6400/32087 (20%)] Loss: 1.399281 +2025-04-14 15:16:16,414 INFO Train Epoch: 21 [9600/32087 (30%)] Loss: 1.533154 +2025-04-14 15:16:30,581 INFO Train Epoch: 21 [12800/32087 (40%)] Loss: 1.496311 +2025-04-14 15:16:44,449 INFO Train Epoch: 21 [16000/32087 (50%)] Loss: 1.302092 +2025-04-14 15:16:58,425 INFO Train Epoch: 21 [19200/32087 (60%)] Loss: 1.212559 +2025-04-14 15:17:12,210 INFO Train Epoch: 21 [22400/32087 (70%)] Loss: 1.426744 +2025-04-14 15:17:26,235 INFO Train Epoch: 21 [25600/32087 (80%)] Loss: 1.320012 +2025-04-14 15:17:40,543 INFO Train Epoch: 21 [28800/32087 (90%)] Loss: 1.772485 +2025-04-14 15:17:54,830 INFO Train Epoch: 21 [32000/32087 (100%)] Loss: 1.317016 +2025-04-14 15:18:27,314 INFO Accuracy qa: 71.34 % +2025-04-14 15:18:29,026 INFO Train Epoch: 22 [0/32087 (0%)] Loss: 1.364080 +2025-04-14 15:18:42,946 INFO Train Epoch: 22 [3200/32087 (10%)] Loss: 1.215907 +2025-04-14 15:18:56,572 INFO Train Epoch: 22 [6400/32087 (20%)] Loss: 1.309923 +2025-04-14 15:19:10,766 INFO Train Epoch: 22 [9600/32087 (30%)] Loss: 1.632397 +2025-04-14 15:19:24,489 INFO Train Epoch: 22 [12800/32087 (40%)] Loss: 1.456175 +2025-04-14 15:19:38,284 INFO Train Epoch: 22 [16000/32087 (50%)] Loss: 1.523539 +2025-04-14 15:19:52,229 INFO Train Epoch: 22 [19200/32087 (60%)] Loss: 1.520789 +2025-04-14 15:20:05,998 INFO Train Epoch: 22 [22400/32087 (70%)] Loss: 1.362636 +2025-04-14 15:20:19,663 INFO Train Epoch: 22 [25600/32087 (80%)] Loss: 1.459766 +2025-04-14 15:20:33,140 INFO Train Epoch: 22 [28800/32087 (90%)] Loss: 1.307739 +2025-04-14 15:20:47,094 INFO Train Epoch: 22 [32000/32087 (100%)] Loss: 1.609144 +2025-04-14 15:21:21,194 INFO Accuracy qa: 71.51 % +2025-04-14 15:21:22,920 INFO Train Epoch: 23 [0/32087 (0%)] Loss: 1.528927 +2025-04-14 15:21:36,652 INFO Train Epoch: 23 [3200/32087 (10%)] Loss: 1.161787 +2025-04-14 15:21:50,498 INFO Train Epoch: 23 [6400/32087 (20%)] Loss: 1.350181 +2025-04-14 15:22:04,768 INFO Train Epoch: 23 [9600/32087 (30%)] Loss: 1.220997 +2025-04-14 15:22:18,813 INFO Train Epoch: 23 [12800/32087 (40%)] Loss: 1.472888 +2025-04-14 15:22:32,622 INFO Train Epoch: 23 [16000/32087 (50%)] Loss: 1.781322 +2025-04-14 15:22:46,573 INFO Train Epoch: 23 [19200/32087 (60%)] Loss: 1.541409 +2025-04-14 15:23:00,660 INFO Train Epoch: 23 [22400/32087 (70%)] Loss: 1.488214 +2025-04-14 15:23:14,197 INFO Train Epoch: 23 [25600/32087 (80%)] Loss: 1.675114 +2025-04-14 15:23:27,806 INFO Train Epoch: 23 [28800/32087 (90%)] Loss: 1.555519 +2025-04-14 15:23:41,687 INFO Train Epoch: 23 [32000/32087 (100%)] Loss: 1.477430 +2025-04-14 15:24:14,922 INFO Accuracy qa: 70.99 % +2025-04-14 15:24:16,620 INFO Train Epoch: 24 [0/32087 (0%)] Loss: 1.334311 +2025-04-14 15:24:30,653 INFO Train Epoch: 24 [3200/32087 (10%)] Loss: 1.098074 +2025-04-14 15:24:44,548 INFO Train Epoch: 24 [6400/32087 (20%)] Loss: 0.990158 +2025-04-14 15:24:58,402 INFO Train Epoch: 24 [9600/32087 (30%)] Loss: 1.506355 +2025-04-14 15:25:12,213 INFO Train Epoch: 24 [12800/32087 (40%)] Loss: 1.511699 +2025-04-14 15:25:26,069 INFO Train Epoch: 24 [16000/32087 (50%)] Loss: 1.468122 +2025-04-14 15:25:40,010 INFO Train Epoch: 24 [19200/32087 (60%)] Loss: 1.916146 +2025-04-14 15:25:54,057 INFO Train Epoch: 24 [22400/32087 (70%)] Loss: 1.325317 +2025-04-14 15:26:08,205 INFO Train Epoch: 24 [25600/32087 (80%)] Loss: 1.366385 +2025-04-14 15:26:22,096 INFO Train Epoch: 24 [28800/32087 (90%)] Loss: 1.558526 +2025-04-14 15:26:36,233 INFO Train Epoch: 24 [32000/32087 (100%)] Loss: 1.200974 +2025-04-14 15:27:09,704 INFO Accuracy qa: 70.77 % +2025-04-14 15:27:11,979 INFO Train Epoch: 25 [0/32087 (0%)] Loss: 1.220865 +2025-04-14 15:27:25,556 INFO Train Epoch: 25 [3200/32087 (10%)] Loss: 0.975509 +2025-04-14 15:27:39,619 INFO Train Epoch: 25 [6400/32087 (20%)] Loss: 1.274383 +2025-04-14 15:27:53,537 INFO Train Epoch: 25 [9600/32087 (30%)] Loss: 1.130132 +2025-04-14 15:28:07,504 INFO Train Epoch: 25 [12800/32087 (40%)] Loss: 1.324600 +2025-04-14 15:28:21,602 INFO Train Epoch: 25 [16000/32087 (50%)] Loss: 1.217446 +2025-04-14 15:28:35,797 INFO Train Epoch: 25 [19200/32087 (60%)] Loss: 1.272881 +2025-04-14 15:28:49,688 INFO Train Epoch: 25 [22400/32087 (70%)] Loss: 1.243825 +2025-04-14 15:29:03,424 INFO Train Epoch: 25 [25600/32087 (80%)] Loss: 1.413268 +2025-04-14 15:29:17,277 INFO Train Epoch: 25 [28800/32087 (90%)] Loss: 1.530634 +2025-04-14 15:29:31,250 INFO Train Epoch: 25 [32000/32087 (100%)] Loss: 1.630217 +2025-04-14 15:30:04,955 INFO Accuracy qa: 70.92 % +2025-04-14 15:30:06,701 INFO Train Epoch: 26 [0/32087 (0%)] Loss: 1.359354 +2025-04-14 15:30:20,828 INFO Train Epoch: 26 [3200/32087 (10%)] Loss: 1.705080 +2025-04-14 15:30:34,909 INFO Train Epoch: 26 [6400/32087 (20%)] Loss: 1.133947 +2025-04-14 15:30:49,230 INFO Train Epoch: 26 [9600/32087 (30%)] Loss: 1.171215 +2025-04-14 15:31:03,439 INFO Train Epoch: 26 [12800/32087 (40%)] Loss: 1.322767 +2025-04-14 15:31:17,933 INFO Train Epoch: 26 [16000/32087 (50%)] Loss: 1.618781 +2025-04-14 15:31:32,167 INFO Train Epoch: 26 [19200/32087 (60%)] Loss: 1.182920 +2025-04-14 15:31:46,493 INFO Train Epoch: 26 [22400/32087 (70%)] Loss: 1.129005 +2025-04-14 15:32:00,467 INFO Train Epoch: 26 [25600/32087 (80%)] Loss: 1.877835 +2025-04-14 15:32:14,314 INFO Train Epoch: 26 [28800/32087 (90%)] Loss: 1.451003 +2025-04-14 15:32:28,108 INFO Train Epoch: 26 [32000/32087 (100%)] Loss: 1.844427 +2025-04-14 15:33:01,670 INFO Accuracy qa: 70.62 % +2025-04-14 15:33:03,383 INFO Train Epoch: 27 [0/32087 (0%)] Loss: 1.070627 +2025-04-14 15:33:17,185 INFO Train Epoch: 27 [3200/32087 (10%)] Loss: 1.518910 +2025-04-14 15:33:31,309 INFO Train Epoch: 27 [6400/32087 (20%)] Loss: 1.634652 +2025-04-14 15:33:45,313 INFO Train Epoch: 27 [9600/32087 (30%)] Loss: 1.509062 +2025-04-14 15:33:59,227 INFO Train Epoch: 27 [12800/32087 (40%)] Loss: 1.521756 +2025-04-14 15:34:13,182 INFO Train Epoch: 27 [16000/32087 (50%)] Loss: 1.150321 +2025-04-14 15:34:27,196 INFO Train Epoch: 27 [19200/32087 (60%)] Loss: 1.444854 +2025-04-14 15:34:41,219 INFO Train Epoch: 27 [22400/32087 (70%)] Loss: 1.489728 +2025-04-14 15:34:55,244 INFO Train Epoch: 27 [25600/32087 (80%)] Loss: 1.112922 +2025-04-14 15:35:09,022 INFO Train Epoch: 27 [28800/32087 (90%)] Loss: 1.396098 +2025-04-14 15:35:22,706 INFO Train Epoch: 27 [32000/32087 (100%)] Loss: 1.107670 +2025-04-14 15:35:56,736 INFO Accuracy qa: 71.08 % +2025-04-14 15:35:58,981 INFO Train Epoch: 28 [0/32087 (0%)] Loss: 1.410431 +2025-04-14 15:36:12,260 INFO Train Epoch: 28 [3200/32087 (10%)] Loss: 1.227545 +2025-04-14 15:36:26,488 INFO Train Epoch: 28 [6400/32087 (20%)] Loss: 1.068847 +2025-04-14 15:36:40,524 INFO Train Epoch: 28 [9600/32087 (30%)] Loss: 1.305654 +2025-04-14 15:36:54,596 INFO Train Epoch: 28 [12800/32087 (40%)] Loss: 1.357095 +2025-04-14 15:37:08,662 INFO Train Epoch: 28 [16000/32087 (50%)] Loss: 1.281338 +2025-04-14 15:37:22,466 INFO Train Epoch: 28 [19200/32087 (60%)] Loss: 1.353451 +2025-04-14 15:37:36,425 INFO Train Epoch: 28 [22400/32087 (70%)] Loss: 1.137635 +2025-04-14 15:37:50,424 INFO Train Epoch: 28 [25600/32087 (80%)] Loss: 1.578852 +2025-04-14 15:38:04,309 INFO Train Epoch: 28 [28800/32087 (90%)] Loss: 1.609752 +2025-04-14 15:38:18,188 INFO Train Epoch: 28 [32000/32087 (100%)] Loss: 1.575051 +2025-04-14 15:38:51,484 INFO Accuracy qa: 70.01 % +2025-04-14 15:38:53,755 INFO Train Epoch: 29 [0/32087 (0%)] Loss: 1.004837 +2025-04-14 15:39:07,366 INFO Train Epoch: 29 [3200/32087 (10%)] Loss: 1.267815 +2025-04-14 15:39:21,173 INFO Train Epoch: 29 [6400/32087 (20%)] Loss: 1.438410 +2025-04-14 15:39:35,387 INFO Train Epoch: 29 [9600/32087 (30%)] Loss: 1.216938 +2025-04-14 15:39:49,343 INFO Train Epoch: 29 [12800/32087 (40%)] Loss: 1.386056 +2025-04-14 15:40:03,224 INFO Train Epoch: 29 [16000/32087 (50%)] Loss: 1.513560 +2025-04-14 15:40:17,057 INFO Train Epoch: 29 [19200/32087 (60%)] Loss: 1.377951 +2025-04-14 15:40:30,651 INFO Train Epoch: 29 [22400/32087 (70%)] Loss: 1.023791 +2025-04-14 15:40:44,265 INFO Train Epoch: 29 [25600/32087 (80%)] Loss: 1.412185 +2025-04-14 15:40:58,267 INFO Train Epoch: 29 [28800/32087 (90%)] Loss: 1.168814 +2025-04-14 15:41:12,250 INFO Train Epoch: 29 [32000/32087 (100%)] Loss: 1.351866 +2025-04-14 15:41:45,448 INFO Accuracy qa: 70.03 % +2025-04-14 15:41:47,151 INFO Train Epoch: 30 [0/32087 (0%)] Loss: 1.249411 +2025-04-14 15:42:01,238 INFO Train Epoch: 30 [3200/32087 (10%)] Loss: 1.305138 +2025-04-14 15:42:15,129 INFO Train Epoch: 30 [6400/32087 (20%)] Loss: 1.195331 +2025-04-14 15:42:29,290 INFO Train Epoch: 30 [9600/32087 (30%)] Loss: 1.559551 +2025-04-14 15:42:43,364 INFO Train Epoch: 30 [12800/32087 (40%)] Loss: 1.038340 +2025-04-14 15:42:57,275 INFO Train Epoch: 30 [16000/32087 (50%)] Loss: 1.172440 +2025-04-14 15:43:11,056 INFO Train Epoch: 30 [19200/32087 (60%)] Loss: 1.500852 +2025-04-14 15:43:25,014 INFO Train Epoch: 30 [22400/32087 (70%)] Loss: 0.991163 +2025-04-14 15:43:38,877 INFO Train Epoch: 30 [25600/32087 (80%)] Loss: 1.275930 +2025-04-14 15:43:52,852 INFO Train Epoch: 30 [28800/32087 (90%)] Loss: 0.999658 +2025-04-14 15:44:06,963 INFO Train Epoch: 30 [32000/32087 (100%)] Loss: 1.088133 +2025-04-14 15:44:40,177 INFO Accuracy qa: 70.66 % +2025-04-14 15:44:42,409 INFO Train Epoch: 31 [0/32087 (0%)] Loss: 1.068491 +2025-04-14 15:44:55,933 INFO Train Epoch: 31 [3200/32087 (10%)] Loss: 1.144268 +2025-04-14 15:45:09,726 INFO Train Epoch: 31 [6400/32087 (20%)] Loss: 1.098773 +2025-04-14 15:45:23,466 INFO Train Epoch: 31 [9600/32087 (30%)] Loss: 1.093706 +2025-04-14 15:45:37,523 INFO Train Epoch: 31 [12800/32087 (40%)] Loss: 1.048974 +2025-04-14 15:45:51,571 INFO Train Epoch: 31 [16000/32087 (50%)] Loss: 1.219713 +2025-04-14 15:46:05,402 INFO Train Epoch: 31 [19200/32087 (60%)] Loss: 1.418314 +2025-04-14 15:46:19,247 INFO Train Epoch: 31 [22400/32087 (70%)] Loss: 1.450232 +2025-04-14 15:46:33,068 INFO Train Epoch: 31 [25600/32087 (80%)] Loss: 1.071911 +2025-04-14 15:46:47,025 INFO Train Epoch: 31 [28800/32087 (90%)] Loss: 1.399607 +2025-04-14 15:47:00,727 INFO Train Epoch: 31 [32000/32087 (100%)] Loss: 1.426662 +2025-04-14 15:47:33,388 INFO Accuracy qa: 70.71 % +2025-04-14 15:47:35,098 INFO Train Epoch: 32 [0/32087 (0%)] Loss: 1.571388 +2025-04-14 15:47:48,775 INFO Train Epoch: 32 [3200/32087 (10%)] Loss: 1.365967 +2025-04-14 15:48:03,021 INFO Train Epoch: 32 [6400/32087 (20%)] Loss: 1.057338 +2025-04-14 15:48:17,186 INFO Train Epoch: 32 [9600/32087 (30%)] Loss: 1.219872 +2025-04-14 15:48:31,020 INFO Train Epoch: 32 [12800/32087 (40%)] Loss: 1.261514 +2025-04-14 15:48:45,176 INFO Train Epoch: 32 [16000/32087 (50%)] Loss: 1.230883 +2025-04-14 15:48:59,053 INFO Train Epoch: 32 [19200/32087 (60%)] Loss: 1.097843 +2025-04-14 15:49:13,098 INFO Train Epoch: 32 [22400/32087 (70%)] Loss: 1.114130 +2025-04-14 15:49:27,067 INFO Train Epoch: 32 [25600/32087 (80%)] Loss: 1.114713 +2025-04-14 15:49:40,807 INFO Train Epoch: 32 [28800/32087 (90%)] Loss: 1.083059 +2025-04-14 15:49:54,905 INFO Train Epoch: 32 [32000/32087 (100%)] Loss: 1.052729 +2025-04-14 15:50:28,723 INFO Accuracy qa: 70.32 % +2025-04-14 15:50:30,426 INFO Train Epoch: 33 [0/32087 (0%)] Loss: 0.961800 +2025-04-14 15:50:44,233 INFO Train Epoch: 33 [3200/32087 (10%)] Loss: 1.096520 +2025-04-14 15:50:58,158 INFO Train Epoch: 33 [6400/32087 (20%)] Loss: 1.397968 +2025-04-14 15:51:12,206 INFO Train Epoch: 33 [9600/32087 (30%)] Loss: 1.337318 +2025-04-14 15:51:25,948 INFO Train Epoch: 33 [12800/32087 (40%)] Loss: 0.973715 +2025-04-14 15:51:39,817 INFO Train Epoch: 33 [16000/32087 (50%)] Loss: 1.352910 +2025-04-14 15:51:53,653 INFO Train Epoch: 33 [19200/32087 (60%)] Loss: 0.943302 +2025-04-14 15:52:07,414 INFO Train Epoch: 33 [22400/32087 (70%)] Loss: 1.128665 +2025-04-14 15:52:21,421 INFO Train Epoch: 33 [25600/32087 (80%)] Loss: 1.353906 +2025-04-14 15:52:35,088 INFO Train Epoch: 33 [28800/32087 (90%)] Loss: 1.135355 +2025-04-14 15:52:48,968 INFO Train Epoch: 33 [32000/32087 (100%)] Loss: 1.024516 +2025-04-14 15:53:22,909 INFO Accuracy qa: 70.55 % +2025-04-14 15:53:25,180 INFO Train Epoch: 34 [0/32087 (0%)] Loss: 1.092468 +2025-04-14 15:53:38,417 INFO Train Epoch: 34 [3200/32087 (10%)] Loss: 1.122719 +2025-04-14 15:53:52,460 INFO Train Epoch: 34 [6400/32087 (20%)] Loss: 1.001611 +2025-04-14 15:54:06,676 INFO Train Epoch: 34 [9600/32087 (30%)] Loss: 1.258438 +2025-04-14 15:54:20,977 INFO Train Epoch: 34 [12800/32087 (40%)] Loss: 0.972571 +2025-04-14 15:54:35,295 INFO Train Epoch: 34 [16000/32087 (50%)] Loss: 1.303179 +2025-04-14 15:54:49,193 INFO Train Epoch: 34 [19200/32087 (60%)] Loss: 1.293040 +2025-04-14 15:55:02,972 INFO Train Epoch: 34 [22400/32087 (70%)] Loss: 1.481661 +2025-04-14 15:55:16,990 INFO Train Epoch: 34 [25600/32087 (80%)] Loss: 1.312235 +2025-04-14 15:55:30,951 INFO Train Epoch: 34 [28800/32087 (90%)] Loss: 0.981278 +2025-04-14 15:55:45,020 INFO Train Epoch: 34 [32000/32087 (100%)] Loss: 0.947054 +2025-04-14 15:56:17,758 INFO Accuracy qa: 70.51 % +2025-04-14 15:56:19,491 INFO Train Epoch: 35 [0/32087 (0%)] Loss: 0.803793 +2025-04-14 15:56:33,535 INFO Train Epoch: 35 [3200/32087 (10%)] Loss: 1.059652 +2025-04-14 15:56:47,372 INFO Train Epoch: 35 [6400/32087 (20%)] Loss: 0.855455 +2025-04-14 15:57:01,545 INFO Train Epoch: 35 [9600/32087 (30%)] Loss: 1.318344 +2025-04-14 15:57:15,497 INFO Train Epoch: 35 [12800/32087 (40%)] Loss: 1.214198 +2025-04-14 15:57:29,429 INFO Train Epoch: 35 [16000/32087 (50%)] Loss: 1.125304 +2025-04-14 15:57:43,028 INFO Train Epoch: 35 [19200/32087 (60%)] Loss: 1.087428 +2025-04-14 15:57:56,744 INFO Train Epoch: 35 [22400/32087 (70%)] Loss: 1.183899 +2025-04-14 15:58:10,824 INFO Train Epoch: 35 [25600/32087 (80%)] Loss: 1.207738 +2025-04-14 15:58:24,929 INFO Train Epoch: 35 [28800/32087 (90%)] Loss: 1.112619 +2025-04-14 15:58:39,026 INFO Train Epoch: 35 [32000/32087 (100%)] Loss: 1.036679 +2025-04-14 15:59:12,646 INFO Accuracy qa: 70.49 % +2025-04-14 15:59:14,931 INFO Train Epoch: 36 [0/32087 (0%)] Loss: 0.934388 +2025-04-14 15:59:28,315 INFO Train Epoch: 36 [3200/32087 (10%)] Loss: 1.072914 +2025-04-14 15:59:42,004 INFO Train Epoch: 36 [6400/32087 (20%)] Loss: 1.056508 +2025-04-14 15:59:56,065 INFO Train Epoch: 36 [9600/32087 (30%)] Loss: 1.115561 +2025-04-14 16:00:10,021 INFO Train Epoch: 36 [12800/32087 (40%)] Loss: 1.129617 +2025-04-14 16:00:23,669 INFO Train Epoch: 36 [16000/32087 (50%)] Loss: 1.206685 +2025-04-14 16:00:37,308 INFO Train Epoch: 36 [19200/32087 (60%)] Loss: 1.247410 +2025-04-14 16:00:51,292 INFO Train Epoch: 36 [22400/32087 (70%)] Loss: 0.980174 +2025-04-14 16:01:05,233 INFO Train Epoch: 36 [25600/32087 (80%)] Loss: 1.017554 +2025-04-14 16:01:19,092 INFO Train Epoch: 36 [28800/32087 (90%)] Loss: 1.377258 +2025-04-14 16:01:32,915 INFO Train Epoch: 36 [32000/32087 (100%)] Loss: 0.955107 +2025-04-14 16:02:07,228 INFO Accuracy qa: 70.34 % +2025-04-14 16:02:09,472 INFO Train Epoch: 37 [0/32087 (0%)] Loss: 1.175567 +2025-04-14 16:02:22,551 INFO Train Epoch: 37 [3200/32087 (10%)] Loss: 0.896168 +2025-04-14 16:02:36,799 INFO Train Epoch: 37 [6400/32087 (20%)] Loss: 1.196256 +2025-04-14 16:02:50,666 INFO Train Epoch: 37 [9600/32087 (30%)] Loss: 0.901373 +2025-04-14 16:03:04,311 INFO Train Epoch: 37 [12800/32087 (40%)] Loss: 0.730149 +2025-04-14 16:03:18,382 INFO Train Epoch: 37 [16000/32087 (50%)] Loss: 1.272219 +2025-04-14 16:03:32,174 INFO Train Epoch: 37 [19200/32087 (60%)] Loss: 1.166499 +2025-04-14 16:03:46,002 INFO Train Epoch: 37 [22400/32087 (70%)] Loss: 0.866865 +2025-04-14 16:04:00,252 INFO Train Epoch: 37 [25600/32087 (80%)] Loss: 1.102007 +2025-04-14 16:04:14,019 INFO Train Epoch: 37 [28800/32087 (90%)] Loss: 1.026422 +2025-04-14 16:04:28,190 INFO Train Epoch: 37 [32000/32087 (100%)] Loss: 1.361139 +2025-04-14 16:05:01,841 INFO Accuracy qa: 70.40 % +2025-04-14 16:05:03,855 INFO Train Epoch: 38 [0/32087 (0%)] Loss: 0.981053 +2025-04-14 16:05:17,591 INFO Train Epoch: 38 [3200/32087 (10%)] Loss: 1.071973 +2025-04-14 16:05:31,523 INFO Train Epoch: 38 [6400/32087 (20%)] Loss: 1.109308 +2025-04-14 16:05:45,533 INFO Train Epoch: 38 [9600/32087 (30%)] Loss: 1.207691 +2025-04-14 16:05:59,519 INFO Train Epoch: 38 [12800/32087 (40%)] Loss: 1.121625 +2025-04-14 16:06:13,883 INFO Train Epoch: 38 [16000/32087 (50%)] Loss: 1.229412 +2025-04-14 16:06:28,082 INFO Train Epoch: 38 [19200/32087 (60%)] Loss: 0.973406 +2025-04-14 16:06:42,100 INFO Train Epoch: 38 [22400/32087 (70%)] Loss: 1.097390 +2025-04-14 16:06:56,124 INFO Train Epoch: 38 [25600/32087 (80%)] Loss: 1.058053 +2025-04-14 16:07:10,164 INFO Train Epoch: 38 [28800/32087 (90%)] Loss: 0.967222 +2025-04-14 16:07:24,248 INFO Train Epoch: 38 [32000/32087 (100%)] Loss: 1.132282 +2025-04-14 16:07:57,544 INFO Accuracy qa: 70.38 % +2025-04-14 16:07:59,788 INFO Train Epoch: 39 [0/32087 (0%)] Loss: 1.280275 +2025-04-14 16:08:13,100 INFO Train Epoch: 39 [3200/32087 (10%)] Loss: 1.123376 +2025-04-14 16:08:27,041 INFO Train Epoch: 39 [6400/32087 (20%)] Loss: 1.082417 +2025-04-14 16:08:40,962 INFO Train Epoch: 39 [9600/32087 (30%)] Loss: 1.081819 +2025-04-14 16:08:54,675 INFO Train Epoch: 39 [12800/32087 (40%)] Loss: 1.852101 +2025-04-14 16:09:08,494 INFO Train Epoch: 39 [16000/32087 (50%)] Loss: 1.362719 +2025-04-14 16:09:22,256 INFO Train Epoch: 39 [19200/32087 (60%)] Loss: 1.468794 +2025-04-14 16:09:36,258 INFO Train Epoch: 39 [22400/32087 (70%)] Loss: 1.152336 +2025-04-14 16:09:50,171 INFO Train Epoch: 39 [25600/32087 (80%)] Loss: 0.765931 +2025-04-14 16:10:04,095 INFO Train Epoch: 39 [28800/32087 (90%)] Loss: 1.444844 +2025-04-14 16:10:18,020 INFO Train Epoch: 39 [32000/32087 (100%)] Loss: 1.414259 +2025-04-14 16:10:50,780 INFO Accuracy qa: 70.16 % +2025-04-14 16:10:52,806 INFO Train Epoch: 40 [0/32087 (0%)] Loss: 1.363008 +2025-04-14 16:11:07,411 INFO Train Epoch: 40 [3200/32087 (10%)] Loss: 1.270178 +2025-04-14 16:11:22,204 INFO Train Epoch: 40 [6400/32087 (20%)] Loss: 1.120820 +2025-04-14 16:11:36,766 INFO Train Epoch: 40 [9600/32087 (30%)] Loss: 1.248718 +2025-04-14 16:11:51,555 INFO Train Epoch: 40 [12800/32087 (40%)] Loss: 1.309836 +2025-04-14 16:12:06,567 INFO Train Epoch: 40 [16000/32087 (50%)] Loss: 0.857864 +2025-04-14 16:12:21,485 INFO Train Epoch: 40 [19200/32087 (60%)] Loss: 1.375324 +2025-04-14 16:12:36,024 INFO Train Epoch: 40 [22400/32087 (70%)] Loss: 1.127910 +2025-04-14 16:12:50,482 INFO Train Epoch: 40 [25600/32087 (80%)] Loss: 1.029247 +2025-04-14 16:13:05,064 INFO Train Epoch: 40 [28800/32087 (90%)] Loss: 1.237222 +2025-04-14 16:13:19,972 INFO Train Epoch: 40 [32000/32087 (100%)] Loss: 1.230181 +2025-04-14 16:13:56,525 INFO Accuracy qa: 70.29 % +2025-04-14 16:13:58,415 INFO Train Epoch: 41 [0/32087 (0%)] Loss: 0.797689 +2025-04-14 16:14:11,548 INFO Train Epoch: 41 [3200/32087 (10%)] Loss: 0.928391 +2025-04-14 16:14:24,382 INFO Train Epoch: 41 [6400/32087 (20%)] Loss: 1.067061 +2025-04-14 16:14:37,082 INFO Train Epoch: 41 [9600/32087 (30%)] Loss: 0.915776 +2025-04-14 16:14:50,794 INFO Train Epoch: 41 [12800/32087 (40%)] Loss: 1.040523 +2025-04-14 16:15:04,693 INFO Train Epoch: 41 [16000/32087 (50%)] Loss: 1.155865 +2025-04-14 16:15:18,622 INFO Train Epoch: 41 [19200/32087 (60%)] Loss: 1.193954 +2025-04-14 16:15:31,497 INFO Train Epoch: 41 [22400/32087 (70%)] Loss: 1.012382 +2025-04-14 16:15:44,508 INFO Train Epoch: 41 [25600/32087 (80%)] Loss: 1.060197 +2025-04-14 16:15:57,762 INFO Train Epoch: 41 [28800/32087 (90%)] Loss: 1.380591 +2025-04-14 16:16:11,608 INFO Train Epoch: 41 [32000/32087 (100%)] Loss: 1.035012 +2025-04-14 16:16:44,043 INFO Accuracy qa: 70.18 % +2025-04-14 16:16:45,930 INFO Train Epoch: 42 [0/32087 (0%)] Loss: 1.259471 +2025-04-14 16:16:58,247 INFO Train Epoch: 42 [3200/32087 (10%)] Loss: 1.248025 +2025-04-14 16:17:10,789 INFO Train Epoch: 42 [6400/32087 (20%)] Loss: 1.118725 +2025-04-14 16:17:23,437 INFO Train Epoch: 42 [9600/32087 (30%)] Loss: 1.070838 +2025-04-14 16:17:37,301 INFO Train Epoch: 42 [12800/32087 (40%)] Loss: 1.257685 +2025-04-14 16:17:50,719 INFO Train Epoch: 42 [16000/32087 (50%)] Loss: 1.179398 +2025-04-14 16:18:03,877 INFO Train Epoch: 42 [19200/32087 (60%)] Loss: 0.956313 +2025-04-14 16:18:17,765 INFO Train Epoch: 42 [22400/32087 (70%)] Loss: 1.289486 +2025-04-14 16:18:31,619 INFO Train Epoch: 42 [25600/32087 (80%)] Loss: 1.135438 +2025-04-14 16:18:45,341 INFO Train Epoch: 42 [28800/32087 (90%)] Loss: 1.070216 +2025-04-14 16:18:58,601 INFO Train Epoch: 42 [32000/32087 (100%)] Loss: 0.755413 +2025-04-14 16:19:31,359 INFO Accuracy qa: 70.18 % +2025-04-14 16:19:33,509 INFO Train Epoch: 43 [0/32087 (0%)] Loss: 1.036316 +2025-04-14 16:19:45,962 INFO Train Epoch: 43 [3200/32087 (10%)] Loss: 1.145295 +2025-04-14 16:19:58,468 INFO Train Epoch: 43 [6400/32087 (20%)] Loss: 1.223648 +2025-04-14 16:20:10,981 INFO Train Epoch: 43 [9600/32087 (30%)] Loss: 1.337210 +2025-04-14 16:20:24,375 INFO Train Epoch: 43 [12800/32087 (40%)] Loss: 1.145402 +2025-04-14 16:20:38,448 INFO Train Epoch: 43 [16000/32087 (50%)] Loss: 0.807985 +2025-04-14 16:20:52,419 INFO Train Epoch: 43 [19200/32087 (60%)] Loss: 1.250480 +2025-04-14 16:21:06,186 INFO Train Epoch: 43 [22400/32087 (70%)] Loss: 1.212962 +2025-04-14 16:21:20,106 INFO Train Epoch: 43 [25600/32087 (80%)] Loss: 0.947185 +2025-04-14 16:21:33,498 INFO Train Epoch: 43 [28800/32087 (90%)] Loss: 1.289358 +2025-04-14 16:21:46,845 INFO Train Epoch: 43 [32000/32087 (100%)] Loss: 1.173409 +2025-04-14 16:22:20,210 INFO Accuracy qa: 70.36 % +2025-04-14 16:22:21,806 INFO Train Epoch: 44 [0/32087 (0%)] Loss: 1.068802 +2025-04-14 16:22:34,913 INFO Train Epoch: 44 [3200/32087 (10%)] Loss: 1.041638 +2025-04-14 16:22:48,330 INFO Train Epoch: 44 [6400/32087 (20%)] Loss: 1.048922 +2025-04-14 16:23:00,727 INFO Train Epoch: 44 [9600/32087 (30%)] Loss: 1.119901 +2025-04-14 16:23:13,327 INFO Train Epoch: 44 [12800/32087 (40%)] Loss: 1.301465 +2025-04-14 16:23:25,377 INFO Train Epoch: 44 [16000/32087 (50%)] Loss: 1.638507 +2025-04-14 16:23:37,727 INFO Train Epoch: 44 [19200/32087 (60%)] Loss: 0.996827 +2025-04-14 16:23:50,154 INFO Train Epoch: 44 [22400/32087 (70%)] Loss: 0.965535 +2025-04-14 16:24:02,591 INFO Train Epoch: 44 [25600/32087 (80%)] Loss: 1.133291 +2025-04-14 16:24:14,997 INFO Train Epoch: 44 [28800/32087 (90%)] Loss: 1.017752 +2025-04-14 16:24:27,466 INFO Train Epoch: 44 [32000/32087 (100%)] Loss: 0.999141 +2025-04-14 16:24:59,562 INFO Accuracy qa: 70.05 % +2025-04-14 16:25:01,624 INFO Train Epoch: 45 [0/32087 (0%)] Loss: 0.812700 +2025-04-14 16:25:13,560 INFO Train Epoch: 45 [3200/32087 (10%)] Loss: 1.143864 +2025-04-14 16:25:25,773 INFO Train Epoch: 45 [6400/32087 (20%)] Loss: 1.246268 +2025-04-14 16:25:37,939 INFO Train Epoch: 45 [9600/32087 (30%)] Loss: 1.312093 +2025-04-14 16:25:50,376 INFO Train Epoch: 45 [12800/32087 (40%)] Loss: 0.980238 +2025-04-14 16:26:02,634 INFO Train Epoch: 45 [16000/32087 (50%)] Loss: 1.217008 +2025-04-14 16:26:15,014 INFO Train Epoch: 45 [19200/32087 (60%)] Loss: 1.012972 +2025-04-14 16:26:27,417 INFO Train Epoch: 45 [22400/32087 (70%)] Loss: 1.228560 +2025-04-14 16:26:39,673 INFO Train Epoch: 45 [25600/32087 (80%)] Loss: 1.117418 +2025-04-14 16:26:52,019 INFO Train Epoch: 45 [28800/32087 (90%)] Loss: 1.115655 +2025-04-14 16:27:04,464 INFO Train Epoch: 45 [32000/32087 (100%)] Loss: 1.008935 +2025-04-14 16:27:37,968 INFO Accuracy qa: 70.34 % +2025-04-14 16:27:39,776 INFO Train Epoch: 46 [0/32087 (0%)] Loss: 1.146436 +2025-04-14 16:27:52,088 INFO Train Epoch: 46 [3200/32087 (10%)] Loss: 0.948270 +2025-04-14 16:28:04,176 INFO Train Epoch: 46 [6400/32087 (20%)] Loss: 1.026464 +2025-04-14 16:28:16,534 INFO Train Epoch: 46 [9600/32087 (30%)] Loss: 0.939644 +2025-04-14 16:28:28,793 INFO Train Epoch: 46 [12800/32087 (40%)] Loss: 1.219899 +2025-04-14 16:28:41,053 INFO Train Epoch: 46 [16000/32087 (50%)] Loss: 1.232412 +2025-04-14 16:28:53,233 INFO Train Epoch: 46 [19200/32087 (60%)] Loss: 0.730089 +2025-04-14 16:29:05,550 INFO Train Epoch: 46 [22400/32087 (70%)] Loss: 1.054330 +2025-04-14 16:29:17,855 INFO Train Epoch: 46 [25600/32087 (80%)] Loss: 1.078625 +2025-04-14 16:29:30,319 INFO Train Epoch: 46 [28800/32087 (90%)] Loss: 0.817645 +2025-04-14 16:29:42,742 INFO Train Epoch: 46 [32000/32087 (100%)] Loss: 0.953936 +2025-04-14 16:30:14,789 INFO Accuracy qa: 70.45 % +2025-04-14 16:30:16,892 INFO Train Epoch: 47 [0/32087 (0%)] Loss: 1.051514 +2025-04-14 16:30:28,974 INFO Train Epoch: 47 [3200/32087 (10%)] Loss: 1.200181 +2025-04-14 16:30:41,024 INFO Train Epoch: 47 [6400/32087 (20%)] Loss: 1.102969 +2025-04-14 16:30:53,342 INFO Train Epoch: 47 [9600/32087 (30%)] Loss: 1.015830 +2025-04-14 16:31:05,671 INFO Train Epoch: 47 [12800/32087 (40%)] Loss: 1.195024 +2025-04-14 16:31:17,759 INFO Train Epoch: 47 [16000/32087 (50%)] Loss: 1.361721 +2025-04-14 16:31:29,783 INFO Train Epoch: 47 [19200/32087 (60%)] Loss: 1.281212 +2025-04-14 16:31:41,867 INFO Train Epoch: 47 [22400/32087 (70%)] Loss: 1.239997 +2025-04-14 16:31:53,887 INFO Train Epoch: 47 [25600/32087 (80%)] Loss: 1.004044 +2025-04-14 16:32:06,040 INFO Train Epoch: 47 [28800/32087 (90%)] Loss: 1.506974 +2025-04-14 16:32:18,294 INFO Train Epoch: 47 [32000/32087 (100%)] Loss: 1.074370 +2025-04-14 16:32:52,027 INFO Accuracy qa: 70.38 % +2025-04-14 16:32:53,660 INFO Train Epoch: 48 [0/32087 (0%)] Loss: 1.197109 +2025-04-14 16:33:06,091 INFO Train Epoch: 48 [3200/32087 (10%)] Loss: 0.893133 +2025-04-14 16:33:18,378 INFO Train Epoch: 48 [6400/32087 (20%)] Loss: 0.823600 +2025-04-14 16:33:30,730 INFO Train Epoch: 48 [9600/32087 (30%)] Loss: 0.951417 +2025-04-14 16:33:43,107 INFO Train Epoch: 48 [12800/32087 (40%)] Loss: 1.036641 +2025-04-14 16:33:55,476 INFO Train Epoch: 48 [16000/32087 (50%)] Loss: 1.033993 +2025-04-14 16:34:07,630 INFO Train Epoch: 48 [19200/32087 (60%)] Loss: 1.496556 +2025-04-14 16:34:19,889 INFO Train Epoch: 48 [22400/32087 (70%)] Loss: 1.052388 +2025-04-14 16:34:32,236 INFO Train Epoch: 48 [25600/32087 (80%)] Loss: 1.029319 +2025-04-14 16:34:44,524 INFO Train Epoch: 48 [28800/32087 (90%)] Loss: 1.367575 +2025-04-14 16:34:56,941 INFO Train Epoch: 48 [32000/32087 (100%)] Loss: 1.205381 +2025-04-14 16:35:28,302 INFO Accuracy qa: 70.27 % +2025-04-14 16:35:30,348 INFO Train Epoch: 49 [0/32087 (0%)] Loss: 0.937453 +2025-04-14 16:35:42,324 INFO Train Epoch: 49 [3200/32087 (10%)] Loss: 1.357297 +2025-04-14 16:35:54,568 INFO Train Epoch: 49 [6400/32087 (20%)] Loss: 1.112666 +2025-04-14 16:36:06,797 INFO Train Epoch: 49 [9600/32087 (30%)] Loss: 1.294127 +2025-04-14 16:36:19,234 INFO Train Epoch: 49 [12800/32087 (40%)] Loss: 1.094179 +2025-04-14 16:36:31,278 INFO Train Epoch: 49 [16000/32087 (50%)] Loss: 0.816241 +2025-04-14 16:36:43,733 INFO Train Epoch: 49 [19200/32087 (60%)] Loss: 1.360119 +2025-04-14 16:36:56,203 INFO Train Epoch: 49 [22400/32087 (70%)] Loss: 0.991480 +2025-04-14 16:37:08,489 INFO Train Epoch: 49 [25600/32087 (80%)] Loss: 1.003609 +2025-04-14 16:37:20,905 INFO Train Epoch: 49 [28800/32087 (90%)] Loss: 0.998425 +2025-04-14 16:37:33,436 INFO Train Epoch: 49 [32000/32087 (100%)] Loss: 1.257859 +2025-04-14 16:38:06,387 INFO Accuracy qa: 70.27 % +2025-04-14 16:38:08,187 INFO Train Epoch: 50 [0/32087 (0%)] Loss: 1.152279 +2025-04-14 16:38:20,147 INFO Train Epoch: 50 [3200/32087 (10%)] Loss: 1.082869 +2025-04-14 16:38:32,505 INFO Train Epoch: 50 [6400/32087 (20%)] Loss: 1.287799 +2025-04-14 16:38:44,907 INFO Train Epoch: 50 [9600/32087 (30%)] Loss: 0.990492 +2025-04-14 16:38:57,465 INFO Train Epoch: 50 [12800/32087 (40%)] Loss: 1.316678 +2025-04-14 16:39:09,629 INFO Train Epoch: 50 [16000/32087 (50%)] Loss: 1.495275 +2025-04-14 16:39:22,246 INFO Train Epoch: 50 [19200/32087 (60%)] Loss: 1.071815 +2025-04-14 16:39:34,378 INFO Train Epoch: 50 [22400/32087 (70%)] Loss: 1.229977 +2025-04-14 16:39:46,844 INFO Train Epoch: 50 [25600/32087 (80%)] Loss: 1.109273 +2025-04-14 16:39:59,218 INFO Train Epoch: 50 [28800/32087 (90%)] Loss: 1.044874 +2025-04-14 16:40:11,632 INFO Train Epoch: 50 [32000/32087 (100%)] Loss: 0.940745 +2025-04-14 16:40:43,373 INFO Accuracy qa: 70.38 % diff --git a/Audio Visual Question Answering/results_baseline/inverse_True_withoutmodified/net_grd_baseline.pt b/Audio Visual Question Answering/results_baseline/inverse_True_withoutmodified/net_grd_baseline.pt new file mode 100644 index 0000000000000000000000000000000000000000..18e566b33d17b09aead1bdfbf331ab158545b7f7 --- /dev/null +++ b/Audio Visual Question Answering/results_baseline/inverse_True_withoutmodified/net_grd_baseline.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c409c35b8658d6c614b15fba9d5c36d3523633780b5635abbbc70cfa3f0c6012 +size 88163031 diff --git a/Audio Visual Question Answering/results_baseline/inverse_True_withoutmodified/test.log b/Audio Visual Question Answering/results_baseline/inverse_True_withoutmodified/test.log new file mode 100644 index 0000000000000000000000000000000000000000..1a956278c50bb39a128c4aaf35b8f393e1a2e09b --- /dev/null +++ b/Audio Visual Question Answering/results_baseline/inverse_True_withoutmodified/test.log @@ -0,0 +1,17 @@ +2025-04-15 04:09:12,777 INFO +--------------- MUSIC-AVQA baseline --------------- + +2025-04-15 04:09:18,340 INFO 9185 +2025-04-15 04:11:27,963 INFO Audio Counting Accuracy: 78.47 % +2025-04-15 04:11:27,964 INFO Audio Cmp Accuracy: 62.73 % +2025-04-15 04:11:27,964 INFO Audio Accuracy: 72.64 % +2025-04-15 04:11:27,964 INFO Visual Counting Accuracy: 75.40 % +2025-04-15 04:11:27,965 INFO Visual Loc Accuracy: 77.93 % +2025-04-15 04:11:27,965 INFO Visual Accuracy: 76.68 % +2025-04-15 04:11:27,965 INFO AV Ext Accuracy: 82.11 % +2025-04-15 04:11:27,965 INFO AV counting Accuracy: 67.27 % +2025-04-15 04:11:27,965 INFO AV Loc Accuracy: 62.03 % +2025-04-15 04:11:27,966 INFO AV Cmp Accuracy: 62.87 % +2025-04-15 04:11:27,966 INFO AV Temporal Accuracy: 63.59 % +2025-04-15 04:11:27,966 INFO AV Accuracy: 67.65 % +2025-04-15 04:11:27,966 INFO Overall Accuracy: 70.92 % diff --git a/Audio Visual Question Answering/results_baseline/inverse_True_withoutmodified/train.log b/Audio Visual Question Answering/results_baseline/inverse_True_withoutmodified/train.log new file mode 100644 index 0000000000000000000000000000000000000000..3484b1e3041992a58661cd7cf2dbce26c029c955 --- /dev/null +++ b/Audio Visual Question Answering/results_baseline/inverse_True_withoutmodified/train.log @@ -0,0 +1,603 @@ +2025-04-14 15:17:57,879 INFO +--------------- MUSIC-AVQA baseline --------------- + +2025-04-14 15:18:07,945 INFO Train Epoch: 1 [0/32087 (0%)] Loss: 11.135600 +2025-04-14 15:18:20,666 INFO Train Epoch: 1 [3200/32087 (10%)] Loss: 7.515569 +2025-04-14 15:18:34,287 INFO Train Epoch: 1 [6400/32087 (20%)] Loss: 6.403431 +2025-04-14 15:18:47,896 INFO Train Epoch: 1 [9600/32087 (30%)] Loss: 5.115645 +2025-04-14 15:19:01,502 INFO Train Epoch: 1 [12800/32087 (40%)] Loss: 4.511546 +2025-04-14 15:19:15,331 INFO Train Epoch: 1 [16000/32087 (50%)] Loss: 3.774347 +2025-04-14 15:19:29,042 INFO Train Epoch: 1 [19200/32087 (60%)] Loss: 3.427492 +2025-04-14 15:19:42,683 INFO Train Epoch: 1 [22400/32087 (70%)] Loss: 2.737287 +2025-04-14 15:19:56,413 INFO Train Epoch: 1 [25600/32087 (80%)] Loss: 3.076939 +2025-04-14 15:20:09,881 INFO Train Epoch: 1 [28800/32087 (90%)] Loss: 3.556587 +2025-04-14 15:20:23,596 INFO Train Epoch: 1 [32000/32087 (100%)] Loss: 3.129028 +2025-04-14 15:20:56,812 INFO Accuracy qa: 53.73 % +2025-04-14 15:20:59,233 INFO Train Epoch: 2 [0/32087 (0%)] Loss: 3.905127 +2025-04-14 15:21:13,010 INFO Train Epoch: 2 [3200/32087 (10%)] Loss: 2.890590 +2025-04-14 15:21:26,706 INFO Train Epoch: 2 [6400/32087 (20%)] Loss: 3.396507 +2025-04-14 15:21:40,477 INFO Train Epoch: 2 [9600/32087 (30%)] Loss: 2.768883 +2025-04-14 15:21:54,825 INFO Train Epoch: 2 [12800/32087 (40%)] Loss: 3.427296 +2025-04-14 15:22:08,877 INFO Train Epoch: 2 [16000/32087 (50%)] Loss: 3.095849 +2025-04-14 15:22:23,067 INFO Train Epoch: 2 [19200/32087 (60%)] Loss: 2.808541 +2025-04-14 15:22:37,260 INFO Train Epoch: 2 [22400/32087 (70%)] Loss: 3.626723 +2025-04-14 15:22:51,336 INFO Train Epoch: 2 [25600/32087 (80%)] Loss: 2.892708 +2025-04-14 15:23:05,443 INFO Train Epoch: 2 [28800/32087 (90%)] Loss: 2.831100 +2025-04-14 15:23:19,619 INFO Train Epoch: 2 [32000/32087 (100%)] Loss: 3.043860 +2025-04-14 15:23:51,777 INFO Accuracy qa: 61.59 % +2025-04-14 15:23:54,710 INFO Train Epoch: 3 [0/32087 (0%)] Loss: 3.097731 +2025-04-14 15:24:07,561 INFO Train Epoch: 3 [3200/32087 (10%)] Loss: 2.318350 +2025-04-14 15:24:20,966 INFO Train Epoch: 3 [6400/32087 (20%)] Loss: 2.891464 +2025-04-14 15:24:34,329 INFO Train Epoch: 3 [9600/32087 (30%)] Loss: 2.845299 +2025-04-14 15:24:48,022 INFO Train Epoch: 3 [12800/32087 (40%)] Loss: 2.281038 +2025-04-14 15:25:02,036 INFO Train Epoch: 3 [16000/32087 (50%)] Loss: 2.573402 +2025-04-14 15:25:16,244 INFO Train Epoch: 3 [19200/32087 (60%)] Loss: 2.548342 +2025-04-14 15:25:29,899 INFO Train Epoch: 3 [22400/32087 (70%)] Loss: 2.905825 +2025-04-14 15:25:43,449 INFO Train Epoch: 3 [25600/32087 (80%)] Loss: 2.584547 +2025-04-14 15:25:57,301 INFO Train Epoch: 3 [28800/32087 (90%)] Loss: 2.406285 +2025-04-14 15:26:11,363 INFO Train Epoch: 3 [32000/32087 (100%)] Loss: 2.847617 +2025-04-14 15:26:44,865 INFO Accuracy qa: 63.44 % +2025-04-14 15:26:47,838 INFO Train Epoch: 4 [0/32087 (0%)] Loss: 2.311478 +2025-04-14 15:27:00,261 INFO Train Epoch: 4 [3200/32087 (10%)] Loss: 2.183423 +2025-04-14 15:27:13,460 INFO Train Epoch: 4 [6400/32087 (20%)] Loss: 2.411172 +2025-04-14 15:27:26,621 INFO Train Epoch: 4 [9600/32087 (30%)] Loss: 2.878412 +2025-04-14 15:27:40,080 INFO Train Epoch: 4 [12800/32087 (40%)] Loss: 2.430877 +2025-04-14 15:27:53,363 INFO Train Epoch: 4 [16000/32087 (50%)] Loss: 3.129171 +2025-04-14 15:28:06,732 INFO Train Epoch: 4 [19200/32087 (60%)] Loss: 2.618443 +2025-04-14 15:28:20,497 INFO Train Epoch: 4 [22400/32087 (70%)] Loss: 3.107086 +2025-04-14 15:28:34,231 INFO Train Epoch: 4 [25600/32087 (80%)] Loss: 2.545347 +2025-04-14 15:28:48,080 INFO Train Epoch: 4 [28800/32087 (90%)] Loss: 2.413653 +2025-04-14 15:29:02,006 INFO Train Epoch: 4 [32000/32087 (100%)] Loss: 2.828787 +2025-04-14 15:29:33,687 INFO Accuracy qa: 66.12 % +2025-04-14 15:29:36,653 INFO Train Epoch: 5 [0/32087 (0%)] Loss: 2.480087 +2025-04-14 15:29:50,797 INFO Train Epoch: 5 [3200/32087 (10%)] Loss: 2.718246 +2025-04-14 15:30:06,073 INFO Train Epoch: 5 [6400/32087 (20%)] Loss: 2.603300 +2025-04-14 15:30:20,224 INFO Train Epoch: 5 [9600/32087 (30%)] Loss: 2.414829 +2025-04-14 15:30:34,342 INFO Train Epoch: 5 [12800/32087 (40%)] Loss: 1.932797 +2025-04-14 15:30:48,593 INFO Train Epoch: 5 [16000/32087 (50%)] Loss: 2.665281 +2025-04-14 15:31:02,678 INFO Train Epoch: 5 [19200/32087 (60%)] Loss: 2.733557 +2025-04-14 15:31:16,661 INFO Train Epoch: 5 [22400/32087 (70%)] Loss: 2.105427 +2025-04-14 15:31:30,673 INFO Train Epoch: 5 [25600/32087 (80%)] Loss: 3.472435 +2025-04-14 15:31:44,648 INFO Train Epoch: 5 [28800/32087 (90%)] Loss: 2.649908 +2025-04-14 15:31:58,744 INFO Train Epoch: 5 [32000/32087 (100%)] Loss: 2.842057 +2025-04-14 15:32:32,477 INFO Accuracy qa: 65.92 % +2025-04-14 15:32:34,629 INFO Train Epoch: 6 [0/32087 (0%)] Loss: 2.881934 +2025-04-14 15:32:46,855 INFO Train Epoch: 6 [3200/32087 (10%)] Loss: 2.092627 +2025-04-14 15:33:00,158 INFO Train Epoch: 6 [6400/32087 (20%)] Loss: 3.131755 +2025-04-14 15:33:13,475 INFO Train Epoch: 6 [9600/32087 (30%)] Loss: 2.211718 +2025-04-14 15:33:26,886 INFO Train Epoch: 6 [12800/32087 (40%)] Loss: 2.222342 +2025-04-14 15:33:40,172 INFO Train Epoch: 6 [16000/32087 (50%)] Loss: 2.193327 +2025-04-14 15:33:53,663 INFO Train Epoch: 6 [19200/32087 (60%)] Loss: 2.709028 +2025-04-14 15:34:06,963 INFO Train Epoch: 6 [22400/32087 (70%)] Loss: 3.162528 +2025-04-14 15:34:20,670 INFO Train Epoch: 6 [25600/32087 (80%)] Loss: 2.789366 +2025-04-14 15:34:34,572 INFO Train Epoch: 6 [28800/32087 (90%)] Loss: 2.611482 +2025-04-14 15:34:48,125 INFO Train Epoch: 6 [32000/32087 (100%)] Loss: 2.579437 +2025-04-14 15:35:20,632 INFO Accuracy qa: 66.66 % +2025-04-14 15:35:23,028 INFO Train Epoch: 7 [0/32087 (0%)] Loss: 2.172957 +2025-04-14 15:35:35,938 INFO Train Epoch: 7 [3200/32087 (10%)] Loss: 2.497073 +2025-04-14 15:35:49,430 INFO Train Epoch: 7 [6400/32087 (20%)] Loss: 2.784234 +2025-04-14 15:36:02,705 INFO Train Epoch: 7 [9600/32087 (30%)] Loss: 2.725910 +2025-04-14 15:36:16,314 INFO Train Epoch: 7 [12800/32087 (40%)] Loss: 2.608016 +2025-04-14 15:36:29,865 INFO Train Epoch: 7 [16000/32087 (50%)] Loss: 2.333024 +2025-04-14 15:36:43,510 INFO Train Epoch: 7 [19200/32087 (60%)] Loss: 1.897214 +2025-04-14 15:36:57,376 INFO Train Epoch: 7 [22400/32087 (70%)] Loss: 2.317708 +2025-04-14 15:37:10,992 INFO Train Epoch: 7 [25600/32087 (80%)] Loss: 2.595676 +2025-04-14 15:37:24,446 INFO Train Epoch: 7 [28800/32087 (90%)] Loss: 2.279654 +2025-04-14 15:37:38,037 INFO Train Epoch: 7 [32000/32087 (100%)] Loss: 2.803933 +2025-04-14 15:38:09,873 INFO Accuracy qa: 67.77 % +2025-04-14 15:38:12,258 INFO Train Epoch: 8 [0/32087 (0%)] Loss: 2.169433 +2025-04-14 15:38:25,418 INFO Train Epoch: 8 [3200/32087 (10%)] Loss: 2.648071 +2025-04-14 15:38:37,936 INFO Train Epoch: 8 [6400/32087 (20%)] Loss: 1.879018 +2025-04-14 15:38:51,229 INFO Train Epoch: 8 [9600/32087 (30%)] Loss: 2.087878 +2025-04-14 15:39:04,666 INFO Train Epoch: 8 [12800/32087 (40%)] Loss: 3.203558 +2025-04-14 15:39:18,531 INFO Train Epoch: 8 [16000/32087 (50%)] Loss: 2.601429 +2025-04-14 15:39:32,022 INFO Train Epoch: 8 [19200/32087 (60%)] Loss: 2.141890 +2025-04-14 15:39:45,975 INFO Train Epoch: 8 [22400/32087 (70%)] Loss: 2.356131 +2025-04-14 15:39:59,921 INFO Train Epoch: 8 [25600/32087 (80%)] Loss: 2.562300 +2025-04-14 15:40:13,801 INFO Train Epoch: 8 [28800/32087 (90%)] Loss: 2.453749 +2025-04-14 15:40:27,647 INFO Train Epoch: 8 [32000/32087 (100%)] Loss: 2.008130 +2025-04-14 15:40:59,600 INFO Accuracy qa: 69.03 % +2025-04-14 15:41:02,298 INFO Train Epoch: 9 [0/32087 (0%)] Loss: 1.787706 +2025-04-14 15:41:14,991 INFO Train Epoch: 9 [3200/32087 (10%)] Loss: 2.706975 +2025-04-14 15:41:28,294 INFO Train Epoch: 9 [6400/32087 (20%)] Loss: 2.039730 +2025-04-14 15:41:41,133 INFO Train Epoch: 9 [9600/32087 (30%)] Loss: 2.423317 +2025-04-14 15:41:54,548 INFO Train Epoch: 9 [12800/32087 (40%)] Loss: 2.897566 +2025-04-14 15:42:08,197 INFO Train Epoch: 9 [16000/32087 (50%)] Loss: 2.096435 +2025-04-14 15:42:21,663 INFO Train Epoch: 9 [19200/32087 (60%)] Loss: 2.512495 +2025-04-14 15:42:35,333 INFO Train Epoch: 9 [22400/32087 (70%)] Loss: 2.172550 +2025-04-14 15:42:48,901 INFO Train Epoch: 9 [25600/32087 (80%)] Loss: 3.006302 +2025-04-14 15:43:02,669 INFO Train Epoch: 9 [28800/32087 (90%)] Loss: 1.878482 +2025-04-14 15:43:16,346 INFO Train Epoch: 9 [32000/32087 (100%)] Loss: 2.083698 +2025-04-14 15:43:51,516 INFO Accuracy qa: 67.38 % +2025-04-14 15:43:53,682 INFO Train Epoch: 10 [0/32087 (0%)] Loss: 2.321567 +2025-04-14 15:44:06,586 INFO Train Epoch: 10 [3200/32087 (10%)] Loss: 2.553441 +2025-04-14 15:44:20,019 INFO Train Epoch: 10 [6400/32087 (20%)] Loss: 2.181719 +2025-04-14 15:44:32,947 INFO Train Epoch: 10 [9600/32087 (30%)] Loss: 1.695812 +2025-04-14 15:44:46,144 INFO Train Epoch: 10 [12800/32087 (40%)] Loss: 2.388026 +2025-04-14 15:44:59,680 INFO Train Epoch: 10 [16000/32087 (50%)] Loss: 2.051748 +2025-04-14 15:45:13,662 INFO Train Epoch: 10 [19200/32087 (60%)] Loss: 2.478138 +2025-04-14 15:45:27,853 INFO Train Epoch: 10 [22400/32087 (70%)] Loss: 2.601507 +2025-04-14 15:45:41,913 INFO Train Epoch: 10 [25600/32087 (80%)] Loss: 2.234280 +2025-04-14 15:45:56,171 INFO Train Epoch: 10 [28800/32087 (90%)] Loss: 2.265858 +2025-04-14 15:46:10,601 INFO Train Epoch: 10 [32000/32087 (100%)] Loss: 2.573050 +2025-04-14 15:46:43,820 INFO Accuracy qa: 67.99 % +2025-04-14 15:46:45,716 INFO Train Epoch: 11 [0/32087 (0%)] Loss: 1.976808 +2025-04-14 15:46:59,668 INFO Train Epoch: 11 [3200/32087 (10%)] Loss: 1.892946 +2025-04-14 15:47:13,804 INFO Train Epoch: 11 [6400/32087 (20%)] Loss: 2.119398 +2025-04-14 15:47:26,881 INFO Train Epoch: 11 [9600/32087 (30%)] Loss: 1.719394 +2025-04-14 15:47:40,495 INFO Train Epoch: 11 [12800/32087 (40%)] Loss: 2.838490 +2025-04-14 15:47:53,655 INFO Train Epoch: 11 [16000/32087 (50%)] Loss: 2.703791 +2025-04-14 15:48:07,319 INFO Train Epoch: 11 [19200/32087 (60%)] Loss: 2.464610 +2025-04-14 15:48:20,999 INFO Train Epoch: 11 [22400/32087 (70%)] Loss: 2.311304 +2025-04-14 15:48:34,384 INFO Train Epoch: 11 [25600/32087 (80%)] Loss: 2.286319 +2025-04-14 15:48:48,050 INFO Train Epoch: 11 [28800/32087 (90%)] Loss: 1.824527 +2025-04-14 15:49:01,673 INFO Train Epoch: 11 [32000/32087 (100%)] Loss: 2.296593 +2025-04-14 15:49:33,489 INFO Accuracy qa: 66.64 % +2025-04-14 15:49:35,593 INFO Train Epoch: 12 [0/32087 (0%)] Loss: 1.695118 +2025-04-14 15:49:48,624 INFO Train Epoch: 12 [3200/32087 (10%)] Loss: 2.103788 +2025-04-14 15:50:02,099 INFO Train Epoch: 12 [6400/32087 (20%)] Loss: 2.241559 +2025-04-14 15:50:15,456 INFO Train Epoch: 12 [9600/32087 (30%)] Loss: 2.085806 +2025-04-14 15:50:28,292 INFO Train Epoch: 12 [12800/32087 (40%)] Loss: 2.058067 +2025-04-14 15:50:41,228 INFO Train Epoch: 12 [16000/32087 (50%)] Loss: 2.434670 +2025-04-14 15:50:54,196 INFO Train Epoch: 12 [19200/32087 (60%)] Loss: 2.413311 +2025-04-14 15:51:07,487 INFO Train Epoch: 12 [22400/32087 (70%)] Loss: 2.176975 +2025-04-14 15:51:21,008 INFO Train Epoch: 12 [25600/32087 (80%)] Loss: 2.193158 +2025-04-14 15:51:34,515 INFO Train Epoch: 12 [28800/32087 (90%)] Loss: 2.606184 +2025-04-14 15:51:48,331 INFO Train Epoch: 12 [32000/32087 (100%)] Loss: 1.758198 +2025-04-14 15:52:22,311 INFO Accuracy qa: 69.64 % +2025-04-14 15:52:25,018 INFO Train Epoch: 13 [0/32087 (0%)] Loss: 1.828833 +2025-04-14 15:52:37,850 INFO Train Epoch: 13 [3200/32087 (10%)] Loss: 2.656002 +2025-04-14 15:52:51,175 INFO Train Epoch: 13 [6400/32087 (20%)] Loss: 1.913951 +2025-04-14 15:53:04,522 INFO Train Epoch: 13 [9600/32087 (30%)] Loss: 2.419507 +2025-04-14 15:53:17,539 INFO Train Epoch: 13 [12800/32087 (40%)] Loss: 2.441936 +2025-04-14 15:53:30,735 INFO Train Epoch: 13 [16000/32087 (50%)] Loss: 2.326372 +2025-04-14 15:53:43,709 INFO Train Epoch: 13 [19200/32087 (60%)] Loss: 2.011961 +2025-04-14 15:53:56,822 INFO Train Epoch: 13 [22400/32087 (70%)] Loss: 1.626130 +2025-04-14 15:54:10,139 INFO Train Epoch: 13 [25600/32087 (80%)] Loss: 1.969332 +2025-04-14 15:54:23,284 INFO Train Epoch: 13 [28800/32087 (90%)] Loss: 2.380863 +2025-04-14 15:54:36,943 INFO Train Epoch: 13 [32000/32087 (100%)] Loss: 2.136717 +2025-04-14 15:55:08,952 INFO Accuracy qa: 69.55 % +2025-04-14 15:55:10,807 INFO Train Epoch: 14 [0/32087 (0%)] Loss: 2.141968 +2025-04-14 15:55:23,893 INFO Train Epoch: 14 [3200/32087 (10%)] Loss: 1.925545 +2025-04-14 15:55:37,519 INFO Train Epoch: 14 [6400/32087 (20%)] Loss: 1.968329 +2025-04-14 15:55:51,047 INFO Train Epoch: 14 [9600/32087 (30%)] Loss: 2.273413 +2025-04-14 15:56:04,409 INFO Train Epoch: 14 [12800/32087 (40%)] Loss: 1.829256 +2025-04-14 15:56:17,548 INFO Train Epoch: 14 [16000/32087 (50%)] Loss: 1.940376 +2025-04-14 15:56:31,088 INFO Train Epoch: 14 [19200/32087 (60%)] Loss: 2.044642 +2025-04-14 15:56:44,458 INFO Train Epoch: 14 [22400/32087 (70%)] Loss: 2.018488 +2025-04-14 15:56:57,510 INFO Train Epoch: 14 [25600/32087 (80%)] Loss: 1.778365 +2025-04-14 15:57:11,005 INFO Train Epoch: 14 [28800/32087 (90%)] Loss: 1.629250 +2025-04-14 15:57:24,505 INFO Train Epoch: 14 [32000/32087 (100%)] Loss: 1.950531 +2025-04-14 15:57:56,728 INFO Accuracy qa: 69.05 % +2025-04-14 15:57:58,851 INFO Train Epoch: 15 [0/32087 (0%)] Loss: 1.757184 +2025-04-14 15:58:12,022 INFO Train Epoch: 15 [3200/32087 (10%)] Loss: 1.645620 +2025-04-14 15:58:25,432 INFO Train Epoch: 15 [6400/32087 (20%)] Loss: 1.624566 +2025-04-14 15:58:38,813 INFO Train Epoch: 15 [9600/32087 (30%)] Loss: 1.391591 +2025-04-14 15:58:51,906 INFO Train Epoch: 15 [12800/32087 (40%)] Loss: 2.065203 +2025-04-14 15:59:04,920 INFO Train Epoch: 15 [16000/32087 (50%)] Loss: 1.997791 +2025-04-14 15:59:17,879 INFO Train Epoch: 15 [19200/32087 (60%)] Loss: 1.858514 +2025-04-14 15:59:30,726 INFO Train Epoch: 15 [22400/32087 (70%)] Loss: 1.659363 +2025-04-14 15:59:43,372 INFO Train Epoch: 15 [25600/32087 (80%)] Loss: 1.748473 +2025-04-14 15:59:56,376 INFO Train Epoch: 15 [28800/32087 (90%)] Loss: 1.884887 +2025-04-14 16:00:09,810 INFO Train Epoch: 15 [32000/32087 (100%)] Loss: 1.886942 +2025-04-14 16:00:42,264 INFO Accuracy qa: 69.90 % +2025-04-14 16:00:44,908 INFO Train Epoch: 16 [0/32087 (0%)] Loss: 1.537591 +2025-04-14 16:00:57,720 INFO Train Epoch: 16 [3200/32087 (10%)] Loss: 1.742700 +2025-04-14 16:01:11,008 INFO Train Epoch: 16 [6400/32087 (20%)] Loss: 1.663741 +2025-04-14 16:01:24,167 INFO Train Epoch: 16 [9600/32087 (30%)] Loss: 1.209799 +2025-04-14 16:01:37,394 INFO Train Epoch: 16 [12800/32087 (40%)] Loss: 1.695505 +2025-04-14 16:01:50,855 INFO Train Epoch: 16 [16000/32087 (50%)] Loss: 1.902475 +2025-04-14 16:02:04,348 INFO Train Epoch: 16 [19200/32087 (60%)] Loss: 1.273223 +2025-04-14 16:02:17,094 INFO Train Epoch: 16 [22400/32087 (70%)] Loss: 1.802919 +2025-04-14 16:02:29,800 INFO Train Epoch: 16 [25600/32087 (80%)] Loss: 1.506123 +2025-04-14 16:02:42,495 INFO Train Epoch: 16 [28800/32087 (90%)] Loss: 1.628849 +2025-04-14 16:02:55,540 INFO Train Epoch: 16 [32000/32087 (100%)] Loss: 1.463236 +2025-04-14 16:03:27,705 INFO Accuracy qa: 71.84 % +2025-04-14 16:03:30,376 INFO Train Epoch: 17 [0/32087 (0%)] Loss: 1.128230 +2025-04-14 16:03:43,494 INFO Train Epoch: 17 [3200/32087 (10%)] Loss: 1.353115 +2025-04-14 16:03:56,816 INFO Train Epoch: 17 [6400/32087 (20%)] Loss: 1.372408 +2025-04-14 16:04:09,919 INFO Train Epoch: 17 [9600/32087 (30%)] Loss: 1.681904 +2025-04-14 16:04:23,468 INFO Train Epoch: 17 [12800/32087 (40%)] Loss: 1.421748 +2025-04-14 16:04:36,673 INFO Train Epoch: 17 [16000/32087 (50%)] Loss: 1.472007 +2025-04-14 16:04:49,830 INFO Train Epoch: 17 [19200/32087 (60%)] Loss: 1.539092 +2025-04-14 16:05:03,134 INFO Train Epoch: 17 [22400/32087 (70%)] Loss: 1.575089 +2025-04-14 16:05:16,133 INFO Train Epoch: 17 [25600/32087 (80%)] Loss: 1.760026 +2025-04-14 16:05:28,875 INFO Train Epoch: 17 [28800/32087 (90%)] Loss: 1.800133 +2025-04-14 16:05:41,574 INFO Train Epoch: 17 [32000/32087 (100%)] Loss: 1.437880 +2025-04-14 16:06:13,705 INFO Accuracy qa: 72.54 % +2025-04-14 16:06:16,137 INFO Train Epoch: 18 [0/32087 (0%)] Loss: 1.739983 +2025-04-14 16:06:29,541 INFO Train Epoch: 18 [3200/32087 (10%)] Loss: 1.373638 +2025-04-14 16:06:42,621 INFO Train Epoch: 18 [6400/32087 (20%)] Loss: 1.172835 +2025-04-14 16:06:55,802 INFO Train Epoch: 18 [9600/32087 (30%)] Loss: 2.088341 +2025-04-14 16:07:09,066 INFO Train Epoch: 18 [12800/32087 (40%)] Loss: 1.148532 +2025-04-14 16:07:22,585 INFO Train Epoch: 18 [16000/32087 (50%)] Loss: 1.321159 +2025-04-14 16:07:35,946 INFO Train Epoch: 18 [19200/32087 (60%)] Loss: 1.727188 +2025-04-14 16:07:49,442 INFO Train Epoch: 18 [22400/32087 (70%)] Loss: 1.397194 +2025-04-14 16:08:02,960 INFO Train Epoch: 18 [25600/32087 (80%)] Loss: 1.232448 +2025-04-14 16:08:15,858 INFO Train Epoch: 18 [28800/32087 (90%)] Loss: 1.716235 +2025-04-14 16:08:28,677 INFO Train Epoch: 18 [32000/32087 (100%)] Loss: 1.715469 +2025-04-14 16:09:01,215 INFO Accuracy qa: 71.80 % +2025-04-14 16:09:03,417 INFO Train Epoch: 19 [0/32087 (0%)] Loss: 1.634575 +2025-04-14 16:09:16,862 INFO Train Epoch: 19 [3200/32087 (10%)] Loss: 1.407509 +2025-04-14 16:09:30,609 INFO Train Epoch: 19 [6400/32087 (20%)] Loss: 1.321844 +2025-04-14 16:09:44,872 INFO Train Epoch: 19 [9600/32087 (30%)] Loss: 1.161771 +2025-04-14 16:09:59,175 INFO Train Epoch: 19 [12800/32087 (40%)] Loss: 1.403232 +2025-04-14 16:10:13,230 INFO Train Epoch: 19 [16000/32087 (50%)] Loss: 1.400282 +2025-04-14 16:10:27,445 INFO Train Epoch: 19 [19200/32087 (60%)] Loss: 1.457407 +2025-04-14 16:10:41,662 INFO Train Epoch: 19 [22400/32087 (70%)] Loss: 1.479548 +2025-04-14 16:10:55,288 INFO Train Epoch: 19 [25600/32087 (80%)] Loss: 1.592712 +2025-04-14 16:11:09,145 INFO Train Epoch: 19 [28800/32087 (90%)] Loss: 1.755597 +2025-04-14 16:11:22,284 INFO Train Epoch: 19 [32000/32087 (100%)] Loss: 1.444914 +2025-04-14 16:11:54,843 INFO Accuracy qa: 72.19 % +2025-04-14 16:11:56,411 INFO Train Epoch: 20 [0/32087 (0%)] Loss: 1.670952 +2025-04-14 16:12:08,809 INFO Train Epoch: 20 [3200/32087 (10%)] Loss: 1.526420 +2025-04-14 16:12:21,276 INFO Train Epoch: 20 [6400/32087 (20%)] Loss: 1.618121 +2025-04-14 16:12:33,844 INFO Train Epoch: 20 [9600/32087 (30%)] Loss: 1.343908 +2025-04-14 16:12:46,615 INFO Train Epoch: 20 [12800/32087 (40%)] Loss: 1.271165 +2025-04-14 16:12:59,215 INFO Train Epoch: 20 [16000/32087 (50%)] Loss: 1.381534 +2025-04-14 16:13:11,798 INFO Train Epoch: 20 [19200/32087 (60%)] Loss: 1.170091 +2025-04-14 16:13:24,532 INFO Train Epoch: 20 [22400/32087 (70%)] Loss: 1.315907 +2025-04-14 16:13:37,517 INFO Train Epoch: 20 [25600/32087 (80%)] Loss: 1.620570 +2025-04-14 16:13:49,889 INFO Train Epoch: 20 [28800/32087 (90%)] Loss: 1.016572 +2025-04-14 16:14:02,905 INFO Train Epoch: 20 [32000/32087 (100%)] Loss: 1.198674 +2025-04-14 16:14:35,579 INFO Accuracy qa: 71.58 % +2025-04-14 16:14:37,700 INFO Train Epoch: 21 [0/32087 (0%)] Loss: 1.234134 +2025-04-14 16:14:51,116 INFO Train Epoch: 21 [3200/32087 (10%)] Loss: 1.539608 +2025-04-14 16:15:04,293 INFO Train Epoch: 21 [6400/32087 (20%)] Loss: 1.383539 +2025-04-14 16:15:17,749 INFO Train Epoch: 21 [9600/32087 (30%)] Loss: 1.498547 +2025-04-14 16:15:30,600 INFO Train Epoch: 21 [12800/32087 (40%)] Loss: 1.526502 +2025-04-14 16:15:43,640 INFO Train Epoch: 21 [16000/32087 (50%)] Loss: 1.281208 +2025-04-14 16:15:56,797 INFO Train Epoch: 21 [19200/32087 (60%)] Loss: 1.216002 +2025-04-14 16:16:10,477 INFO Train Epoch: 21 [22400/32087 (70%)] Loss: 1.417350 +2025-04-14 16:16:23,328 INFO Train Epoch: 21 [25600/32087 (80%)] Loss: 1.230229 +2025-04-14 16:16:35,950 INFO Train Epoch: 21 [28800/32087 (90%)] Loss: 1.679161 +2025-04-14 16:16:48,617 INFO Train Epoch: 21 [32000/32087 (100%)] Loss: 1.285198 +2025-04-14 16:17:20,977 INFO Accuracy qa: 72.06 % +2025-04-14 16:17:22,848 INFO Train Epoch: 22 [0/32087 (0%)] Loss: 1.377838 +2025-04-14 16:17:36,058 INFO Train Epoch: 22 [3200/32087 (10%)] Loss: 1.255880 +2025-04-14 16:17:49,333 INFO Train Epoch: 22 [6400/32087 (20%)] Loss: 1.272598 +2025-04-14 16:18:02,751 INFO Train Epoch: 22 [9600/32087 (30%)] Loss: 1.619715 +2025-04-14 16:18:16,389 INFO Train Epoch: 22 [12800/32087 (40%)] Loss: 1.399689 +2025-04-14 16:18:29,598 INFO Train Epoch: 22 [16000/32087 (50%)] Loss: 1.398642 +2025-04-14 16:18:43,786 INFO Train Epoch: 22 [19200/32087 (60%)] Loss: 1.599114 +2025-04-14 16:18:57,469 INFO Train Epoch: 22 [22400/32087 (70%)] Loss: 1.367048 +2025-04-14 16:19:10,236 INFO Train Epoch: 22 [25600/32087 (80%)] Loss: 1.475595 +2025-04-14 16:19:22,854 INFO Train Epoch: 22 [28800/32087 (90%)] Loss: 1.312716 +2025-04-14 16:19:35,680 INFO Train Epoch: 22 [32000/32087 (100%)] Loss: 1.628692 +2025-04-14 16:20:08,561 INFO Accuracy qa: 72.14 % +2025-04-14 16:20:10,434 INFO Train Epoch: 23 [0/32087 (0%)] Loss: 1.428658 +2025-04-14 16:20:25,017 INFO Train Epoch: 23 [3200/32087 (10%)] Loss: 1.093634 +2025-04-14 16:20:41,466 INFO Train Epoch: 23 [6400/32087 (20%)] Loss: 1.351095 +2025-04-14 16:20:58,195 INFO Train Epoch: 23 [9600/32087 (30%)] Loss: 1.208269 +2025-04-14 16:21:14,606 INFO Train Epoch: 23 [12800/32087 (40%)] Loss: 1.378064 +2025-04-14 16:21:30,292 INFO Train Epoch: 23 [16000/32087 (50%)] Loss: 1.797503 +2025-04-14 16:21:44,933 INFO Train Epoch: 23 [19200/32087 (60%)] Loss: 1.579328 +2025-04-14 16:21:59,676 INFO Train Epoch: 23 [22400/32087 (70%)] Loss: 1.418642 +2025-04-14 16:22:14,015 INFO Train Epoch: 23 [25600/32087 (80%)] Loss: 1.752732 +2025-04-14 16:22:29,162 INFO Train Epoch: 23 [28800/32087 (90%)] Loss: 1.493417 +2025-04-14 16:22:44,309 INFO Train Epoch: 23 [32000/32087 (100%)] Loss: 1.482284 +2025-04-14 16:23:19,882 INFO Accuracy qa: 71.56 % +2025-04-14 16:23:21,940 INFO Train Epoch: 24 [0/32087 (0%)] Loss: 1.417673 +2025-04-14 16:23:36,342 INFO Train Epoch: 24 [3200/32087 (10%)] Loss: 1.100834 +2025-04-14 16:23:51,302 INFO Train Epoch: 24 [6400/32087 (20%)] Loss: 0.962537 +2025-04-14 16:24:06,112 INFO Train Epoch: 24 [9600/32087 (30%)] Loss: 1.408003 +2025-04-14 16:24:20,805 INFO Train Epoch: 24 [12800/32087 (40%)] Loss: 1.484404 +2025-04-14 16:24:35,440 INFO Train Epoch: 24 [16000/32087 (50%)] Loss: 1.464694 +2025-04-14 16:24:49,534 INFO Train Epoch: 24 [19200/32087 (60%)] Loss: 1.805289 +2025-04-14 16:25:04,060 INFO Train Epoch: 24 [22400/32087 (70%)] Loss: 1.410170 +2025-04-14 16:25:18,628 INFO Train Epoch: 24 [25600/32087 (80%)] Loss: 1.351630 +2025-04-14 16:25:33,378 INFO Train Epoch: 24 [28800/32087 (90%)] Loss: 1.546398 +2025-04-14 16:25:48,457 INFO Train Epoch: 24 [32000/32087 (100%)] Loss: 1.033657 +2025-04-14 16:26:22,570 INFO Accuracy qa: 71.73 % +2025-04-14 16:26:24,882 INFO Train Epoch: 25 [0/32087 (0%)] Loss: 1.271814 +2025-04-14 16:26:38,803 INFO Train Epoch: 25 [3200/32087 (10%)] Loss: 0.905586 +2025-04-14 16:26:53,589 INFO Train Epoch: 25 [6400/32087 (20%)] Loss: 1.261273 +2025-04-14 16:27:08,243 INFO Train Epoch: 25 [9600/32087 (30%)] Loss: 1.111011 +2025-04-14 16:27:22,974 INFO Train Epoch: 25 [12800/32087 (40%)] Loss: 1.366525 +2025-04-14 16:27:37,412 INFO Train Epoch: 25 [16000/32087 (50%)] Loss: 1.173212 +2025-04-14 16:27:51,954 INFO Train Epoch: 25 [19200/32087 (60%)] Loss: 1.296127 +2025-04-14 16:28:06,203 INFO Train Epoch: 25 [22400/32087 (70%)] Loss: 1.300316 +2025-04-14 16:28:20,848 INFO Train Epoch: 25 [25600/32087 (80%)] Loss: 1.362329 +2025-04-14 16:28:35,590 INFO Train Epoch: 25 [28800/32087 (90%)] Loss: 1.671485 +2025-04-14 16:28:50,692 INFO Train Epoch: 25 [32000/32087 (100%)] Loss: 1.686480 +2025-04-14 16:29:24,969 INFO Accuracy qa: 71.71 % +2025-04-14 16:29:26,978 INFO Train Epoch: 26 [0/32087 (0%)] Loss: 1.303631 +2025-04-14 16:29:41,482 INFO Train Epoch: 26 [3200/32087 (10%)] Loss: 1.529521 +2025-04-14 16:29:56,233 INFO Train Epoch: 26 [6400/32087 (20%)] Loss: 1.194274 +2025-04-14 16:30:11,020 INFO Train Epoch: 26 [9600/32087 (30%)] Loss: 1.164389 +2025-04-14 16:30:25,530 INFO Train Epoch: 26 [12800/32087 (40%)] Loss: 1.259025 +2025-04-14 16:30:39,914 INFO Train Epoch: 26 [16000/32087 (50%)] Loss: 1.587996 +2025-04-14 16:30:54,493 INFO Train Epoch: 26 [19200/32087 (60%)] Loss: 1.226884 +2025-04-14 16:31:09,380 INFO Train Epoch: 26 [22400/32087 (70%)] Loss: 1.021981 +2025-04-14 16:31:24,346 INFO Train Epoch: 26 [25600/32087 (80%)] Loss: 1.695841 +2025-04-14 16:31:39,016 INFO Train Epoch: 26 [28800/32087 (90%)] Loss: 1.534498 +2025-04-14 16:31:53,854 INFO Train Epoch: 26 [32000/32087 (100%)] Loss: 1.835898 +2025-04-14 16:32:30,392 INFO Accuracy qa: 71.27 % +2025-04-14 16:32:32,141 INFO Train Epoch: 27 [0/32087 (0%)] Loss: 1.131737 +2025-04-14 16:32:46,696 INFO Train Epoch: 27 [3200/32087 (10%)] Loss: 1.419108 +2025-04-14 16:33:01,029 INFO Train Epoch: 27 [6400/32087 (20%)] Loss: 1.702862 +2025-04-14 16:33:15,440 INFO Train Epoch: 27 [9600/32087 (30%)] Loss: 1.469259 +2025-04-14 16:33:29,714 INFO Train Epoch: 27 [12800/32087 (40%)] Loss: 1.596338 +2025-04-14 16:33:44,112 INFO Train Epoch: 27 [16000/32087 (50%)] Loss: 1.128749 +2025-04-14 16:33:59,135 INFO Train Epoch: 27 [19200/32087 (60%)] Loss: 1.512181 +2025-04-14 16:34:14,109 INFO Train Epoch: 27 [22400/32087 (70%)] Loss: 1.577461 +2025-04-14 16:34:28,935 INFO Train Epoch: 27 [25600/32087 (80%)] Loss: 1.114469 +2025-04-14 16:34:43,563 INFO Train Epoch: 27 [28800/32087 (90%)] Loss: 1.309362 +2025-04-14 16:34:58,391 INFO Train Epoch: 27 [32000/32087 (100%)] Loss: 1.187225 +2025-04-14 16:35:32,304 INFO Accuracy qa: 71.34 % +2025-04-14 16:35:34,059 INFO Train Epoch: 28 [0/32087 (0%)] Loss: 1.318724 +2025-04-14 16:35:48,783 INFO Train Epoch: 28 [3200/32087 (10%)] Loss: 1.239210 +2025-04-14 16:36:03,478 INFO Train Epoch: 28 [6400/32087 (20%)] Loss: 1.113993 +2025-04-14 16:36:18,147 INFO Train Epoch: 28 [9600/32087 (30%)] Loss: 1.300851 +2025-04-14 16:36:32,876 INFO Train Epoch: 28 [12800/32087 (40%)] Loss: 1.366935 +2025-04-14 16:36:47,370 INFO Train Epoch: 28 [16000/32087 (50%)] Loss: 1.294946 +2025-04-14 16:37:01,607 INFO Train Epoch: 28 [19200/32087 (60%)] Loss: 1.301892 +2025-04-14 16:37:16,061 INFO Train Epoch: 28 [22400/32087 (70%)] Loss: 1.188942 +2025-04-14 16:37:30,428 INFO Train Epoch: 28 [25600/32087 (80%)] Loss: 1.590055 +2025-04-14 16:37:44,755 INFO Train Epoch: 28 [28800/32087 (90%)] Loss: 1.476447 +2025-04-14 16:37:59,210 INFO Train Epoch: 28 [32000/32087 (100%)] Loss: 1.523286 +2025-04-14 16:38:34,024 INFO Accuracy qa: 71.32 % +2025-04-14 16:38:35,798 INFO Train Epoch: 29 [0/32087 (0%)] Loss: 1.060059 +2025-04-14 16:38:50,301 INFO Train Epoch: 29 [3200/32087 (10%)] Loss: 1.304170 +2025-04-14 16:39:04,696 INFO Train Epoch: 29 [6400/32087 (20%)] Loss: 1.407019 +2025-04-14 16:39:19,134 INFO Train Epoch: 29 [9600/32087 (30%)] Loss: 1.208230 +2025-04-14 16:39:33,517 INFO Train Epoch: 29 [12800/32087 (40%)] Loss: 1.337666 +2025-04-14 16:39:48,300 INFO Train Epoch: 29 [16000/32087 (50%)] Loss: 1.544255 +2025-04-14 16:40:02,922 INFO Train Epoch: 29 [19200/32087 (60%)] Loss: 1.368075 +2025-04-14 16:40:17,537 INFO Train Epoch: 29 [22400/32087 (70%)] Loss: 1.059949 +2025-04-14 16:40:32,301 INFO Train Epoch: 29 [25600/32087 (80%)] Loss: 1.520222 +2025-04-14 16:40:47,152 INFO Train Epoch: 29 [28800/32087 (90%)] Loss: 1.198744 +2025-04-14 16:41:02,685 INFO Train Epoch: 29 [32000/32087 (100%)] Loss: 1.437149 +2025-04-14 16:41:41,112 INFO Accuracy qa: 70.38 % +2025-04-14 16:41:42,993 INFO Train Epoch: 30 [0/32087 (0%)] Loss: 1.276138 +2025-04-14 16:41:58,335 INFO Train Epoch: 30 [3200/32087 (10%)] Loss: 1.213932 +2025-04-14 16:42:14,245 INFO Train Epoch: 30 [6400/32087 (20%)] Loss: 1.197269 +2025-04-14 16:42:28,677 INFO Train Epoch: 30 [9600/32087 (30%)] Loss: 1.484650 +2025-04-14 16:42:43,552 INFO Train Epoch: 30 [12800/32087 (40%)] Loss: 1.065109 +2025-04-14 16:42:58,181 INFO Train Epoch: 30 [16000/32087 (50%)] Loss: 1.166862 +2025-04-14 16:43:12,717 INFO Train Epoch: 30 [19200/32087 (60%)] Loss: 1.530882 +2025-04-14 16:43:26,798 INFO Train Epoch: 30 [22400/32087 (70%)] Loss: 1.054926 +2025-04-14 16:43:41,205 INFO Train Epoch: 30 [25600/32087 (80%)] Loss: 1.197361 +2025-04-14 16:43:56,117 INFO Train Epoch: 30 [28800/32087 (90%)] Loss: 0.988193 +2025-04-14 16:44:10,861 INFO Train Epoch: 30 [32000/32087 (100%)] Loss: 1.128545 +2025-04-14 16:44:47,709 INFO Accuracy qa: 71.19 % +2025-04-14 16:44:49,942 INFO Train Epoch: 31 [0/32087 (0%)] Loss: 0.992790 +2025-04-14 16:45:02,468 INFO Train Epoch: 31 [3200/32087 (10%)] Loss: 1.165673 +2025-04-14 16:45:15,313 INFO Train Epoch: 31 [6400/32087 (20%)] Loss: 1.054454 +2025-04-14 16:45:27,262 INFO Train Epoch: 31 [9600/32087 (30%)] Loss: 1.049855 +2025-04-14 16:45:39,528 INFO Train Epoch: 31 [12800/32087 (40%)] Loss: 0.937418 +2025-04-14 16:45:51,702 INFO Train Epoch: 31 [16000/32087 (50%)] Loss: 1.234088 +2025-04-14 16:46:04,258 INFO Train Epoch: 31 [19200/32087 (60%)] Loss: 1.321619 +2025-04-14 16:46:16,167 INFO Train Epoch: 31 [22400/32087 (70%)] Loss: 1.430048 +2025-04-14 16:46:28,445 INFO Train Epoch: 31 [25600/32087 (80%)] Loss: 1.004496 +2025-04-14 16:46:40,790 INFO Train Epoch: 31 [28800/32087 (90%)] Loss: 1.271076 +2025-04-14 16:46:52,908 INFO Train Epoch: 31 [32000/32087 (100%)] Loss: 1.421043 +2025-04-14 16:47:29,192 INFO Accuracy qa: 71.36 % +2025-04-14 16:47:30,737 INFO Train Epoch: 32 [0/32087 (0%)] Loss: 1.509404 +2025-04-14 16:47:44,887 INFO Train Epoch: 32 [3200/32087 (10%)] Loss: 1.266135 +2025-04-14 16:47:59,839 INFO Train Epoch: 32 [6400/32087 (20%)] Loss: 1.091886 +2025-04-14 16:48:15,523 INFO Train Epoch: 32 [9600/32087 (30%)] Loss: 1.213302 +2025-04-14 16:48:30,923 INFO Train Epoch: 32 [12800/32087 (40%)] Loss: 1.190835 +2025-04-14 16:48:46,831 INFO Train Epoch: 32 [16000/32087 (50%)] Loss: 1.123373 +2025-04-14 16:49:02,610 INFO Train Epoch: 32 [19200/32087 (60%)] Loss: 1.140915 +2025-04-14 16:49:17,898 INFO Train Epoch: 32 [22400/32087 (70%)] Loss: 1.013944 +2025-04-14 16:49:32,948 INFO Train Epoch: 32 [25600/32087 (80%)] Loss: 1.165292 +2025-04-14 16:49:48,312 INFO Train Epoch: 32 [28800/32087 (90%)] Loss: 1.180278 +2025-04-14 16:50:03,615 INFO Train Epoch: 32 [32000/32087 (100%)] Loss: 0.998217 +2025-04-14 16:50:36,673 INFO Accuracy qa: 71.27 % +2025-04-14 16:50:38,471 INFO Train Epoch: 33 [0/32087 (0%)] Loss: 0.957365 +2025-04-14 16:50:50,705 INFO Train Epoch: 33 [3200/32087 (10%)] Loss: 1.061234 +2025-04-14 16:51:02,999 INFO Train Epoch: 33 [6400/32087 (20%)] Loss: 1.393252 +2025-04-14 16:51:14,818 INFO Train Epoch: 33 [9600/32087 (30%)] Loss: 1.303969 +2025-04-14 16:51:26,806 INFO Train Epoch: 33 [12800/32087 (40%)] Loss: 0.965411 +2025-04-14 16:51:38,861 INFO Train Epoch: 33 [16000/32087 (50%)] Loss: 1.349821 +2025-04-14 16:51:50,795 INFO Train Epoch: 33 [19200/32087 (60%)] Loss: 0.959870 +2025-04-14 16:52:02,604 INFO Train Epoch: 33 [22400/32087 (70%)] Loss: 1.192546 +2025-04-14 16:52:14,755 INFO Train Epoch: 33 [25600/32087 (80%)] Loss: 1.206248 +2025-04-14 16:52:26,383 INFO Train Epoch: 33 [28800/32087 (90%)] Loss: 1.120848 +2025-04-14 16:52:38,291 INFO Train Epoch: 33 [32000/32087 (100%)] Loss: 1.060432 +2025-04-14 16:53:17,839 INFO Accuracy qa: 71.23 % +2025-04-14 16:53:19,435 INFO Train Epoch: 34 [0/32087 (0%)] Loss: 0.985194 +2025-04-14 16:53:33,334 INFO Train Epoch: 34 [3200/32087 (10%)] Loss: 1.089304 +2025-04-14 16:53:48,323 INFO Train Epoch: 34 [6400/32087 (20%)] Loss: 0.948056 +2025-04-14 16:54:03,946 INFO Train Epoch: 34 [9600/32087 (30%)] Loss: 1.247806 +2025-04-14 16:54:19,886 INFO Train Epoch: 34 [12800/32087 (40%)] Loss: 1.044794 +2025-04-14 16:54:36,103 INFO Train Epoch: 34 [16000/32087 (50%)] Loss: 1.407818 +2025-04-14 16:54:50,341 INFO Train Epoch: 34 [19200/32087 (60%)] Loss: 1.277192 +2025-04-14 16:55:05,057 INFO Train Epoch: 34 [22400/32087 (70%)] Loss: 1.363928 +2025-04-14 16:55:21,731 INFO Train Epoch: 34 [25600/32087 (80%)] Loss: 1.205126 +2025-04-14 16:55:37,848 INFO Train Epoch: 34 [28800/32087 (90%)] Loss: 1.063198 +2025-04-14 16:55:53,098 INFO Train Epoch: 34 [32000/32087 (100%)] Loss: 0.962559 +2025-04-14 16:56:25,257 INFO Accuracy qa: 71.27 % +2025-04-14 16:56:26,837 INFO Train Epoch: 35 [0/32087 (0%)] Loss: 0.742259 +2025-04-14 16:56:39,380 INFO Train Epoch: 35 [3200/32087 (10%)] Loss: 1.022227 +2025-04-14 16:56:52,018 INFO Train Epoch: 35 [6400/32087 (20%)] Loss: 0.836173 +2025-04-14 16:57:04,053 INFO Train Epoch: 35 [9600/32087 (30%)] Loss: 1.203934 +2025-04-14 16:57:16,407 INFO Train Epoch: 35 [12800/32087 (40%)] Loss: 1.228650 +2025-04-14 16:57:28,679 INFO Train Epoch: 35 [16000/32087 (50%)] Loss: 1.166560 +2025-04-14 16:57:40,891 INFO Train Epoch: 35 [19200/32087 (60%)] Loss: 1.041919 +2025-04-14 16:57:53,114 INFO Train Epoch: 35 [22400/32087 (70%)] Loss: 1.260582 +2025-04-14 16:58:05,812 INFO Train Epoch: 35 [25600/32087 (80%)] Loss: 1.042564 +2025-04-14 16:58:17,770 INFO Train Epoch: 35 [28800/32087 (90%)] Loss: 1.153443 +2025-04-14 16:58:29,400 INFO Train Epoch: 35 [32000/32087 (100%)] Loss: 1.087134 +2025-04-14 16:59:00,198 INFO Accuracy qa: 71.34 % +2025-04-14 16:59:02,018 INFO Train Epoch: 36 [0/32087 (0%)] Loss: 0.861278 +2025-04-14 16:59:13,822 INFO Train Epoch: 36 [3200/32087 (10%)] Loss: 1.113311 +2025-04-14 16:59:26,145 INFO Train Epoch: 36 [6400/32087 (20%)] Loss: 1.007959 +2025-04-14 16:59:37,990 INFO Train Epoch: 36 [9600/32087 (30%)] Loss: 1.128334 +2025-04-14 16:59:50,408 INFO Train Epoch: 36 [12800/32087 (40%)] Loss: 1.162521 +2025-04-14 17:00:01,962 INFO Train Epoch: 36 [16000/32087 (50%)] Loss: 1.304286 +2025-04-14 17:00:14,025 INFO Train Epoch: 36 [19200/32087 (60%)] Loss: 1.231667 +2025-04-14 17:00:26,117 INFO Train Epoch: 36 [22400/32087 (70%)] Loss: 1.037692 +2025-04-14 17:00:38,199 INFO Train Epoch: 36 [25600/32087 (80%)] Loss: 0.995646 +2025-04-14 17:00:49,915 INFO Train Epoch: 36 [28800/32087 (90%)] Loss: 1.265806 +2025-04-14 17:01:01,919 INFO Train Epoch: 36 [32000/32087 (100%)] Loss: 0.963718 +2025-04-14 17:01:35,860 INFO Accuracy qa: 71.08 % +2025-04-14 17:01:37,879 INFO Train Epoch: 37 [0/32087 (0%)] Loss: 1.263004 +2025-04-14 17:01:49,644 INFO Train Epoch: 37 [3200/32087 (10%)] Loss: 0.949353 +2025-04-14 17:02:01,600 INFO Train Epoch: 37 [6400/32087 (20%)] Loss: 1.107719 +2025-04-14 17:02:14,343 INFO Train Epoch: 37 [9600/32087 (30%)] Loss: 0.900571 +2025-04-14 17:02:27,034 INFO Train Epoch: 37 [12800/32087 (40%)] Loss: 0.765683 +2025-04-14 17:02:39,984 INFO Train Epoch: 37 [16000/32087 (50%)] Loss: 1.338126 +2025-04-14 17:02:52,986 INFO Train Epoch: 37 [19200/32087 (60%)] Loss: 1.192139 +2025-04-14 17:03:05,614 INFO Train Epoch: 37 [22400/32087 (70%)] Loss: 0.961155 +2025-04-14 17:03:19,135 INFO Train Epoch: 37 [25600/32087 (80%)] Loss: 1.029552 +2025-04-14 17:03:31,807 INFO Train Epoch: 37 [28800/32087 (90%)] Loss: 1.064262 +2025-04-14 17:03:45,012 INFO Train Epoch: 37 [32000/32087 (100%)] Loss: 1.297306 +2025-04-14 17:04:17,679 INFO Accuracy qa: 71.23 % +2025-04-14 17:04:19,712 INFO Train Epoch: 38 [0/32087 (0%)] Loss: 0.921603 +2025-04-14 17:04:31,539 INFO Train Epoch: 38 [3200/32087 (10%)] Loss: 1.090812 +2025-04-14 17:04:43,445 INFO Train Epoch: 38 [6400/32087 (20%)] Loss: 1.101650 +2025-04-14 17:04:55,271 INFO Train Epoch: 38 [9600/32087 (30%)] Loss: 1.234356 +2025-04-14 17:05:07,074 INFO Train Epoch: 38 [12800/32087 (40%)] Loss: 1.107433 +2025-04-14 17:05:18,887 INFO Train Epoch: 38 [16000/32087 (50%)] Loss: 1.344490 +2025-04-14 17:05:30,655 INFO Train Epoch: 38 [19200/32087 (60%)] Loss: 1.034579 +2025-04-14 17:05:42,551 INFO Train Epoch: 38 [22400/32087 (70%)] Loss: 1.158781 +2025-04-14 17:05:54,498 INFO Train Epoch: 38 [25600/32087 (80%)] Loss: 1.035312 +2025-04-14 17:06:06,597 INFO Train Epoch: 38 [28800/32087 (90%)] Loss: 0.924619 +2025-04-14 17:06:18,482 INFO Train Epoch: 38 [32000/32087 (100%)] Loss: 1.144595 +2025-04-14 17:06:52,440 INFO Accuracy qa: 71.23 % +2025-04-14 17:06:54,184 INFO Train Epoch: 39 [0/32087 (0%)] Loss: 1.340553 +2025-04-14 17:07:05,948 INFO Train Epoch: 39 [3200/32087 (10%)] Loss: 1.008247 +2025-04-14 17:07:18,150 INFO Train Epoch: 39 [6400/32087 (20%)] Loss: 1.002121 +2025-04-14 17:07:29,969 INFO Train Epoch: 39 [9600/32087 (30%)] Loss: 1.021495 +2025-04-14 17:07:41,939 INFO Train Epoch: 39 [12800/32087 (40%)] Loss: 1.919221 +2025-04-14 17:07:54,055 INFO Train Epoch: 39 [16000/32087 (50%)] Loss: 1.274848 +2025-04-14 17:08:06,232 INFO Train Epoch: 39 [19200/32087 (60%)] Loss: 1.389547 +2025-04-14 17:08:18,292 INFO Train Epoch: 39 [22400/32087 (70%)] Loss: 1.068595 +2025-04-14 17:08:30,326 INFO Train Epoch: 39 [25600/32087 (80%)] Loss: 0.757258 +2025-04-14 17:08:42,617 INFO Train Epoch: 39 [28800/32087 (90%)] Loss: 1.619613 +2025-04-14 17:08:54,513 INFO Train Epoch: 39 [32000/32087 (100%)] Loss: 1.420740 +2025-04-14 17:09:29,604 INFO Accuracy qa: 71.08 % +2025-04-14 17:09:31,371 INFO Train Epoch: 40 [0/32087 (0%)] Loss: 1.296414 +2025-04-14 17:09:43,659 INFO Train Epoch: 40 [3200/32087 (10%)] Loss: 1.270660 +2025-04-14 17:09:55,894 INFO Train Epoch: 40 [6400/32087 (20%)] Loss: 0.961881 +2025-04-14 17:10:07,544 INFO Train Epoch: 40 [9600/32087 (30%)] Loss: 1.178846 +2025-04-14 17:10:19,334 INFO Train Epoch: 40 [12800/32087 (40%)] Loss: 1.220220 +2025-04-14 17:10:31,372 INFO Train Epoch: 40 [16000/32087 (50%)] Loss: 0.770477 +2025-04-14 17:10:43,919 INFO Train Epoch: 40 [19200/32087 (60%)] Loss: 1.229638 +2025-04-14 17:10:58,394 INFO Train Epoch: 40 [22400/32087 (70%)] Loss: 1.075097 +2025-04-14 17:11:13,796 INFO Train Epoch: 40 [25600/32087 (80%)] Loss: 0.942109 +2025-04-14 17:11:28,500 INFO Train Epoch: 40 [28800/32087 (90%)] Loss: 1.151010 +2025-04-14 17:11:43,160 INFO Train Epoch: 40 [32000/32087 (100%)] Loss: 1.288893 +2025-04-14 17:12:15,065 INFO Accuracy qa: 71.27 % +2025-04-14 17:12:17,076 INFO Train Epoch: 41 [0/32087 (0%)] Loss: 0.844097 +2025-04-14 17:12:28,970 INFO Train Epoch: 41 [3200/32087 (10%)] Loss: 0.828676 +2025-04-14 17:12:41,440 INFO Train Epoch: 41 [6400/32087 (20%)] Loss: 1.118597 +2025-04-14 17:12:53,329 INFO Train Epoch: 41 [9600/32087 (30%)] Loss: 0.919447 +2025-04-14 17:13:05,663 INFO Train Epoch: 41 [12800/32087 (40%)] Loss: 1.040540 +2025-04-14 17:13:17,536 INFO Train Epoch: 41 [16000/32087 (50%)] Loss: 1.251085 +2025-04-14 17:13:29,821 INFO Train Epoch: 41 [19200/32087 (60%)] Loss: 1.123519 +2025-04-14 17:13:41,541 INFO Train Epoch: 41 [22400/32087 (70%)] Loss: 1.068689 +2025-04-14 17:13:53,610 INFO Train Epoch: 41 [25600/32087 (80%)] Loss: 1.097159 +2025-04-14 17:14:05,745 INFO Train Epoch: 41 [28800/32087 (90%)] Loss: 1.315287 +2025-04-14 17:14:17,966 INFO Train Epoch: 41 [32000/32087 (100%)] Loss: 1.078490 +2025-04-14 17:14:49,217 INFO Accuracy qa: 71.12 % +2025-04-14 17:14:50,992 INFO Train Epoch: 42 [0/32087 (0%)] Loss: 1.283802 +2025-04-14 17:15:03,295 INFO Train Epoch: 42 [3200/32087 (10%)] Loss: 1.129979 +2025-04-14 17:15:15,479 INFO Train Epoch: 42 [6400/32087 (20%)] Loss: 1.004087 +2025-04-14 17:15:27,466 INFO Train Epoch: 42 [9600/32087 (30%)] Loss: 1.060067 +2025-04-14 17:15:39,558 INFO Train Epoch: 42 [12800/32087 (40%)] Loss: 1.154301 +2025-04-14 17:15:51,577 INFO Train Epoch: 42 [16000/32087 (50%)] Loss: 1.258031 +2025-04-14 17:16:03,540 INFO Train Epoch: 42 [19200/32087 (60%)] Loss: 1.024739 +2025-04-14 17:16:15,722 INFO Train Epoch: 42 [22400/32087 (70%)] Loss: 1.466765 +2025-04-14 17:16:27,724 INFO Train Epoch: 42 [25600/32087 (80%)] Loss: 1.063897 +2025-04-14 17:16:39,812 INFO Train Epoch: 42 [28800/32087 (90%)] Loss: 1.074008 +2025-04-14 17:16:51,725 INFO Train Epoch: 42 [32000/32087 (100%)] Loss: 0.777154 +2025-04-14 17:17:22,083 INFO Accuracy qa: 71.23 % +2025-04-14 17:17:23,615 INFO Train Epoch: 43 [0/32087 (0%)] Loss: 0.898081 +2025-04-14 17:17:35,729 INFO Train Epoch: 43 [3200/32087 (10%)] Loss: 1.207707 +2025-04-14 17:17:48,075 INFO Train Epoch: 43 [6400/32087 (20%)] Loss: 1.175846 +2025-04-14 17:18:00,014 INFO Train Epoch: 43 [9600/32087 (30%)] Loss: 1.297335 +2025-04-14 17:18:11,853 INFO Train Epoch: 43 [12800/32087 (40%)] Loss: 1.128549 +2025-04-14 17:18:24,032 INFO Train Epoch: 43 [16000/32087 (50%)] Loss: 0.890594 +2025-04-14 17:18:35,725 INFO Train Epoch: 43 [19200/32087 (60%)] Loss: 1.301436 +2025-04-14 17:18:47,686 INFO Train Epoch: 43 [22400/32087 (70%)] Loss: 1.087520 +2025-04-14 17:18:59,618 INFO Train Epoch: 43 [25600/32087 (80%)] Loss: 1.051109 +2025-04-14 17:19:11,579 INFO Train Epoch: 43 [28800/32087 (90%)] Loss: 1.304634 +2025-04-14 17:19:23,747 INFO Train Epoch: 43 [32000/32087 (100%)] Loss: 1.231428 +2025-04-14 17:19:55,758 INFO Accuracy qa: 71.16 % +2025-04-14 17:19:57,747 INFO Train Epoch: 44 [0/32087 (0%)] Loss: 1.078103 +2025-04-14 17:20:09,785 INFO Train Epoch: 44 [3200/32087 (10%)] Loss: 1.137572 +2025-04-14 17:20:21,671 INFO Train Epoch: 44 [6400/32087 (20%)] Loss: 1.089292 +2025-04-14 17:20:33,378 INFO Train Epoch: 44 [9600/32087 (30%)] Loss: 1.223647 +2025-04-14 17:20:44,939 INFO Train Epoch: 44 [12800/32087 (40%)] Loss: 1.256744 +2025-04-14 17:20:56,672 INFO Train Epoch: 44 [16000/32087 (50%)] Loss: 1.546921 +2025-04-14 17:21:08,381 INFO Train Epoch: 44 [19200/32087 (60%)] Loss: 0.968469 +2025-04-14 17:21:20,397 INFO Train Epoch: 44 [22400/32087 (70%)] Loss: 0.965111 +2025-04-14 17:21:31,956 INFO Train Epoch: 44 [25600/32087 (80%)] Loss: 1.148766 +2025-04-14 17:21:44,126 INFO Train Epoch: 44 [28800/32087 (90%)] Loss: 0.919860 +2025-04-14 17:21:55,562 INFO Train Epoch: 44 [32000/32087 (100%)] Loss: 0.992715 +2025-04-14 17:22:28,512 INFO Accuracy qa: 71.01 % +2025-04-14 17:22:30,505 INFO Train Epoch: 45 [0/32087 (0%)] Loss: 0.878378 +2025-04-14 17:22:41,660 INFO Train Epoch: 45 [3200/32087 (10%)] Loss: 1.090439 +2025-04-14 17:22:53,254 INFO Train Epoch: 45 [6400/32087 (20%)] Loss: 1.183931 +2025-04-14 17:23:04,771 INFO Train Epoch: 45 [9600/32087 (30%)] Loss: 1.424661 +2025-04-14 17:23:16,538 INFO Train Epoch: 45 [12800/32087 (40%)] Loss: 0.998055 +2025-04-14 17:23:28,078 INFO Train Epoch: 45 [16000/32087 (50%)] Loss: 1.241812 +2025-04-14 17:23:39,542 INFO Train Epoch: 45 [19200/32087 (60%)] Loss: 1.086902 +2025-04-14 17:23:50,982 INFO Train Epoch: 45 [22400/32087 (70%)] Loss: 1.122455 +2025-04-14 17:24:02,479 INFO Train Epoch: 45 [25600/32087 (80%)] Loss: 1.220640 +2025-04-14 17:24:14,066 INFO Train Epoch: 45 [28800/32087 (90%)] Loss: 0.980948 +2025-04-14 17:24:25,898 INFO Train Epoch: 45 [32000/32087 (100%)] Loss: 0.956387 +2025-04-14 17:24:55,255 INFO Accuracy qa: 71.03 % +2025-04-14 17:24:57,010 INFO Train Epoch: 46 [0/32087 (0%)] Loss: 1.014603 +2025-04-14 17:25:08,769 INFO Train Epoch: 46 [3200/32087 (10%)] Loss: 0.876959 +2025-04-14 17:25:20,772 INFO Train Epoch: 46 [6400/32087 (20%)] Loss: 0.990248 +2025-04-14 17:25:33,428 INFO Train Epoch: 46 [9600/32087 (30%)] Loss: 0.902608 +2025-04-14 17:25:44,934 INFO Train Epoch: 46 [12800/32087 (40%)] Loss: 1.188756 +2025-04-14 17:25:56,970 INFO Train Epoch: 46 [16000/32087 (50%)] Loss: 1.188833 +2025-04-14 17:26:08,560 INFO Train Epoch: 46 [19200/32087 (60%)] Loss: 0.785005 +2025-04-14 17:26:20,161 INFO Train Epoch: 46 [22400/32087 (70%)] Loss: 1.099592 +2025-04-14 17:26:31,698 INFO Train Epoch: 46 [25600/32087 (80%)] Loss: 1.001798 +2025-04-14 17:26:43,569 INFO Train Epoch: 46 [28800/32087 (90%)] Loss: 0.826305 +2025-04-14 17:26:55,222 INFO Train Epoch: 46 [32000/32087 (100%)] Loss: 1.041277 +2025-04-14 17:27:25,986 INFO Accuracy qa: 71.01 % +2025-04-14 17:27:27,942 INFO Train Epoch: 47 [0/32087 (0%)] Loss: 1.044432 +2025-04-14 17:27:39,244 INFO Train Epoch: 47 [3200/32087 (10%)] Loss: 1.346154 +2025-04-14 17:27:51,028 INFO Train Epoch: 47 [6400/32087 (20%)] Loss: 1.067593 +2025-04-14 17:28:02,387 INFO Train Epoch: 47 [9600/32087 (30%)] Loss: 1.078120 +2025-04-14 17:28:14,054 INFO Train Epoch: 47 [12800/32087 (40%)] Loss: 1.209712 +2025-04-14 17:28:25,478 INFO Train Epoch: 47 [16000/32087 (50%)] Loss: 1.250421 +2025-04-14 17:28:36,892 INFO Train Epoch: 47 [19200/32087 (60%)] Loss: 1.265690 +2025-04-14 17:28:48,508 INFO Train Epoch: 47 [22400/32087 (70%)] Loss: 1.218788 +2025-04-14 17:29:00,001 INFO Train Epoch: 47 [25600/32087 (80%)] Loss: 1.079243 +2025-04-14 17:29:11,402 INFO Train Epoch: 47 [28800/32087 (90%)] Loss: 1.357848 +2025-04-14 17:29:22,959 INFO Train Epoch: 47 [32000/32087 (100%)] Loss: 1.000008 +2025-04-14 17:29:52,308 INFO Accuracy qa: 71.01 % +2025-04-14 17:29:54,298 INFO Train Epoch: 48 [0/32087 (0%)] Loss: 1.220099 +2025-04-14 17:30:05,638 INFO Train Epoch: 48 [3200/32087 (10%)] Loss: 0.873385 +2025-04-14 17:30:17,215 INFO Train Epoch: 48 [6400/32087 (20%)] Loss: 0.791650 +2025-04-14 17:30:28,840 INFO Train Epoch: 48 [9600/32087 (30%)] Loss: 0.834297 +2025-04-14 17:30:40,612 INFO Train Epoch: 48 [12800/32087 (40%)] Loss: 0.998682 +2025-04-14 17:30:52,623 INFO Train Epoch: 48 [16000/32087 (50%)] Loss: 1.004108 +2025-04-14 17:31:04,144 INFO Train Epoch: 48 [19200/32087 (60%)] Loss: 1.439249 +2025-04-14 17:31:16,114 INFO Train Epoch: 48 [22400/32087 (70%)] Loss: 1.071636 +2025-04-14 17:31:27,745 INFO Train Epoch: 48 [25600/32087 (80%)] Loss: 1.125055 +2025-04-14 17:31:39,350 INFO Train Epoch: 48 [28800/32087 (90%)] Loss: 1.215484 +2025-04-14 17:31:51,105 INFO Train Epoch: 48 [32000/32087 (100%)] Loss: 1.118038 +2025-04-14 17:32:20,637 INFO Accuracy qa: 70.90 % +2025-04-14 17:32:22,658 INFO Train Epoch: 49 [0/32087 (0%)] Loss: 0.937542 +2025-04-14 17:32:33,745 INFO Train Epoch: 49 [3200/32087 (10%)] Loss: 1.298466 +2025-04-14 17:32:45,706 INFO Train Epoch: 49 [6400/32087 (20%)] Loss: 1.043157 +2025-04-14 17:32:57,224 INFO Train Epoch: 49 [9600/32087 (30%)] Loss: 1.273492 +2025-04-14 17:33:09,089 INFO Train Epoch: 49 [12800/32087 (40%)] Loss: 0.969522 +2025-04-14 17:33:20,658 INFO Train Epoch: 49 [16000/32087 (50%)] Loss: 0.867939 +2025-04-14 17:33:32,343 INFO Train Epoch: 49 [19200/32087 (60%)] Loss: 1.203378 +2025-04-14 17:33:43,995 INFO Train Epoch: 49 [22400/32087 (70%)] Loss: 1.018293 +2025-04-14 17:33:55,585 INFO Train Epoch: 49 [25600/32087 (80%)] Loss: 1.057197 +2025-04-14 17:34:07,064 INFO Train Epoch: 49 [28800/32087 (90%)] Loss: 0.979851 +2025-04-14 17:34:18,843 INFO Train Epoch: 49 [32000/32087 (100%)] Loss: 1.320943 +2025-04-14 17:34:47,827 INFO Accuracy qa: 70.88 % +2025-04-14 17:34:49,809 INFO Train Epoch: 50 [0/32087 (0%)] Loss: 1.047415 +2025-04-14 17:35:05,116 INFO Train Epoch: 50 [3200/32087 (10%)] Loss: 1.072508 +2025-04-14 17:35:20,431 INFO Train Epoch: 50 [6400/32087 (20%)] Loss: 1.238715 +2025-04-14 17:35:33,135 INFO Train Epoch: 50 [9600/32087 (30%)] Loss: 0.940699 +2025-04-14 17:35:44,678 INFO Train Epoch: 50 [12800/32087 (40%)] Loss: 1.313683 +2025-04-14 17:35:56,313 INFO Train Epoch: 50 [16000/32087 (50%)] Loss: 1.601629 +2025-04-14 17:36:08,577 INFO Train Epoch: 50 [19200/32087 (60%)] Loss: 1.145945 +2025-04-14 17:36:20,203 INFO Train Epoch: 50 [22400/32087 (70%)] Loss: 1.316768 +2025-04-14 17:36:33,335 INFO Train Epoch: 50 [25600/32087 (80%)] Loss: 1.057281 +2025-04-14 17:36:47,188 INFO Train Epoch: 50 [28800/32087 (90%)] Loss: 1.080678 +2025-04-14 17:37:00,765 INFO Train Epoch: 50 [32000/32087 (100%)] Loss: 0.917198 +2025-04-14 17:37:30,298 INFO Accuracy qa: 70.90 %