DesonDai commited on Jun 10

Commit

cbeee86

verified ·

1 Parent(s): 212e9d7

Add files using upload-large-folder tool

Browse files

Files changed (20) hide show

logs/brainfm_frozen_clinicalbert_text_alignment.log +29 -0
logs/brainfm_frozen_mlp_b4.log +283 -0
logs/brainfm_lastblock_regalign.log +579 -0
logs/brainiac_frozen_clinicalbert_text_alignment.log +38 -0
logs/clinical_brainfm_frozen_v2.log +9 -0
logs/clinical_medicalnet_frozen.log +27 -0
logs/clinical_queue_gpu0_v2.log +7 -0
logs/download_swinunetr.log +344 -0
logs/eval_brainfm_frozen_clinicalbert_text_alignment_test.log +13 -0
logs/eval_brainiac_frozen_clinicalbert_text_alignment_test.log +15 -0
logs/eval_medicalnet_frozen_clinicalbert_text_alignment_test.log +13 -0
logs/eval_remap_pet_clinicalbert_text_alignment_b16_test.log +13 -0
logs/eval_remap_pet_layer4_regonly_test.log +19 -0
logs/medicalnet_e2e_mlp_20260514_120820.log +362 -0
logs/medicalnet_frozen_mlp_20260514_112810.log +542 -0
logs/medicalnet_layer4_regalign_20260515_010621.log +472 -0
logs/pet_suvr_baseline_20260514_053729.log +45 -0
logs/remap_pet_clinicalbert_text_alignment.log +31 -0
logs/remap_pet_layer4_cw05_20260518_001809.log +921 -0
logs/swinunetr_lastblock_regalign.log +1104 -0

logs/brainfm_frozen_clinicalbert_text_alignment.log ADDED Viewed

	@@ -0,0 +1,29 @@

+epoch=1 train_loss=2.759112 val_loss=2.728402
+saved_best runs/vlm/brainfm_frozen_clinicalbert_text_alignment_best.pt val_loss=2.728402
+epoch=2 train_loss=2.716902 val_loss=2.690928
+saved_best runs/vlm/brainfm_frozen_clinicalbert_text_alignment_best.pt val_loss=2.690928
+epoch=3 train_loss=2.638331 val_loss=2.705700
+epoch=4 train_loss=2.541846 val_loss=2.639537
+saved_best runs/vlm/brainfm_frozen_clinicalbert_text_alignment_best.pt val_loss=2.639537
+epoch=5 train_loss=2.416144 val_loss=2.584351
+saved_best runs/vlm/brainfm_frozen_clinicalbert_text_alignment_best.pt val_loss=2.584351
+epoch=6 train_loss=2.289599 val_loss=2.603122
+epoch=7 train_loss=2.273004 val_loss=2.463067
+saved_best runs/vlm/brainfm_frozen_clinicalbert_text_alignment_best.pt val_loss=2.463067
+epoch=8 train_loss=2.227303 val_loss=2.514658
+epoch=9 train_loss=2.156167 val_loss=2.530408
+epoch=10 train_loss=2.115417 val_loss=2.673176
+epoch=11 train_loss=2.156684 val_loss=2.570263
+epoch=12 train_loss=2.098581 val_loss=2.450834
+saved_best runs/vlm/brainfm_frozen_clinicalbert_text_alignment_best.pt val_loss=2.450834
+epoch=13 train_loss=1.945950 val_loss=2.404399
+saved_best runs/vlm/brainfm_frozen_clinicalbert_text_alignment_best.pt val_loss=2.404399
+epoch=14 train_loss=1.969623 val_loss=2.611268
+epoch=15 train_loss=1.997093 val_loss=2.527653
+epoch=16 train_loss=1.936637 val_loss=2.578666
+epoch=17 train_loss=1.972088 val_loss=2.530528
+epoch=18 train_loss=1.878474 val_loss=2.384205
+saved_best runs/vlm/brainfm_frozen_clinicalbert_text_alignment_best.pt val_loss=2.384205
+epoch=19 train_loss=1.830248 val_loss=2.498893
+epoch=20 train_loss=1.873818 val_loss=2.650826
+saved runs/vlm/brainfm_frozen_clinicalbert_text_alignment.pt

logs/brainfm_frozen_mlp_b4.log ADDED Viewed

	@@ -0,0 +1,283 @@

+device=cuda backbone=brainfm encoder_scope=none contrastive_weight=0.2 regression_weight=1.0 train=710 val=152
+epoch=1 step=20/178 loss=0.4166
+epoch=1 step=40/178 loss=0.2932
+epoch=1 step=60/178 loss=0.2968
+epoch=1 step=80/178 loss=0.2608
+epoch=1 step=100/178 loss=0.2693
+epoch=1 step=120/178 loss=0.2179
+epoch=1 step=140/178 loss=0.2559
+epoch=1 step=160/178 loss=0.2251
+epoch=1 train_loss=0.3091 train_contrastive=1.1857 train_regression=0.0720 val_loss=0.2182 val_contrastive=0.9190 val_regression=0.0344
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.2182 epoch=1
+epoch=2 step=20/178 loss=0.1846
+epoch=2 step=40/178 loss=0.1808
+epoch=2 step=60/178 loss=0.2131
+epoch=2 step=80/178 loss=0.1966
+epoch=2 step=100/178 loss=0.1501
+epoch=2 step=120/178 loss=0.2177
+epoch=2 step=140/178 loss=0.0977
+epoch=2 step=160/178 loss=0.0913
+epoch=2 train_loss=0.1676 train_contrastive=0.6618 train_regression=0.0353 val_loss=0.1703 val_contrastive=0.6968 val_regression=0.0309
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.1703 epoch=2
+epoch=3 step=20/178 loss=0.0681
+epoch=3 step=40/178 loss=0.0497
+epoch=3 step=60/178 loss=0.0778
+epoch=3 step=80/178 loss=0.1078
+epoch=3 step=100/178 loss=0.1356
+epoch=3 step=120/178 loss=0.1846
+epoch=3 step=140/178 loss=0.2267
+epoch=3 step=160/178 loss=0.0958
+epoch=3 train_loss=0.1207 train_contrastive=0.4470 train_regression=0.0313 val_loss=0.1454 val_contrastive=0.5633 val_regression=0.0327
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.1454 epoch=3
+epoch=4 step=20/178 loss=0.0786
+epoch=4 step=40/178 loss=0.0421
+epoch=4 step=60/178 loss=0.0321
+epoch=4 step=80/178 loss=0.0620
+epoch=4 step=100/178 loss=0.1472
+epoch=4 step=120/178 loss=0.0548
+epoch=4 step=140/178 loss=0.1153
+epoch=4 step=160/178 loss=0.1119
+epoch=4 train_loss=0.0922 train_contrastive=0.3241 train_regression=0.0274 val_loss=0.1375 val_contrastive=0.5518 val_regression=0.0271
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.1375 epoch=4
+epoch=5 step=20/178 loss=0.0400
+epoch=5 step=40/178 loss=0.1321
+epoch=5 step=60/178 loss=0.2660
+epoch=5 step=80/178 loss=0.0700
+epoch=5 step=100/178 loss=0.0505
+epoch=5 step=120/178 loss=0.0514
+epoch=5 step=140/178 loss=0.1134
+epoch=5 step=160/178 loss=0.0866
+epoch=5 train_loss=0.0838 train_contrastive=0.2922 train_regression=0.0253 val_loss=0.1286 val_contrastive=0.5216 val_regression=0.0243
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.1286 epoch=5
+epoch=6 step=20/178 loss=0.1178
+epoch=6 step=40/178 loss=0.0459
+epoch=6 step=60/178 loss=0.1233
+epoch=6 step=80/178 loss=0.0972
+epoch=6 step=100/178 loss=0.0333
+epoch=6 step=120/178 loss=0.1912
+epoch=6 step=140/178 loss=0.0934
+epoch=6 step=160/178 loss=0.0760
+epoch=6 train_loss=0.0815 train_contrastive=0.2792 train_regression=0.0257 val_loss=0.1914 val_contrastive=0.7649 val_regression=0.0384
+epoch=7 step=20/178 loss=0.0592
+epoch=7 step=40/178 loss=0.0573
+epoch=7 step=60/178 loss=0.1299
+epoch=7 step=80/178 loss=0.0768
+epoch=7 step=100/178 loss=0.0207
+epoch=7 step=120/178 loss=0.0373
+epoch=7 step=140/178 loss=0.0331
+epoch=7 step=160/178 loss=0.0210
+epoch=7 train_loss=0.0621 train_contrastive=0.2027 train_regression=0.0215 val_loss=0.1227 val_contrastive=0.4756 val_regression=0.0276
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.1227 epoch=7
+epoch=8 step=20/178 loss=0.0471
+epoch=8 step=40/178 loss=0.0370
+epoch=8 step=60/178 loss=0.0842
+epoch=8 step=80/178 loss=0.0727
+epoch=8 step=100/178 loss=0.0640
+epoch=8 step=120/178 loss=0.1532
+epoch=8 step=140/178 loss=0.1714
+epoch=8 step=160/178 loss=0.0372
+epoch=8 train_loss=0.0653 train_contrastive=0.2139 train_regression=0.0225 val_loss=0.1232 val_contrastive=0.5011 val_regression=0.0230
+epoch=9 step=20/178 loss=0.0269
+epoch=9 step=40/178 loss=0.1533
+epoch=9 step=60/178 loss=0.0636
+epoch=9 step=80/178 loss=0.0297
+epoch=9 step=100/178 loss=0.0362
+epoch=9 step=120/178 loss=0.0551
+epoch=9 step=140/178 loss=0.0992
+epoch=9 step=160/178 loss=0.0589
+epoch=9 train_loss=0.0639 train_contrastive=0.2128 train_regression=0.0214 val_loss=0.1477 val_contrastive=0.6358 val_regression=0.0205
+epoch=10 step=20/178 loss=0.0182
+epoch=10 step=40/178 loss=0.1428
+epoch=10 step=60/178 loss=0.0616
+epoch=10 step=80/178 loss=0.0109
+epoch=10 step=100/178 loss=0.0239
+epoch=10 step=120/178 loss=0.0238
+epoch=10 step=140/178 loss=0.0313
+epoch=10 step=160/178 loss=0.0326
+epoch=10 train_loss=0.0439 train_contrastive=0.1264 train_regression=0.0187 val_loss=0.1096 val_contrastive=0.4321 val_regression=0.0232
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.1096 epoch=10
+epoch=11 step=20/178 loss=0.0234
+epoch=11 step=40/178 loss=0.0168
+epoch=11 step=60/178 loss=0.0356
+epoch=11 step=80/178 loss=0.0267
+epoch=11 step=100/178 loss=0.0210
+epoch=11 step=120/178 loss=0.0271
+epoch=11 step=140/178 loss=0.0457
+epoch=11 step=160/178 loss=0.0188
+epoch=11 train_loss=0.0465 train_contrastive=0.1372 train_regression=0.0191 val_loss=0.1192 val_contrastive=0.4834 val_regression=0.0225
+epoch=12 step=20/178 loss=0.0913
+epoch=12 step=40/178 loss=0.0192
+epoch=12 step=60/178 loss=0.1212
+epoch=12 step=80/178 loss=0.0389
+epoch=12 step=100/178 loss=0.0469
+epoch=12 step=120/178 loss=0.0191
+epoch=12 step=140/178 loss=0.0145
+epoch=12 step=160/178 loss=0.0117
+epoch=12 train_loss=0.0517 train_contrastive=0.1613 train_regression=0.0195 val_loss=0.1144 val_contrastive=0.4707 val_regression=0.0203
+epoch=13 step=20/178 loss=0.0172
+epoch=13 step=40/178 loss=0.1017
+epoch=13 step=60/178 loss=0.0738
+epoch=13 step=80/178 loss=0.0993
+epoch=13 step=100/178 loss=0.0226
+epoch=13 step=120/178 loss=0.0264
+epoch=13 step=140/178 loss=0.0263
+epoch=13 step=160/178 loss=0.0525
+epoch=13 train_loss=0.0490 train_contrastive=0.1538 train_regression=0.0183 val_loss=0.1025 val_contrastive=0.4184 val_regression=0.0188
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.1025 epoch=13
+epoch=14 step=20/178 loss=0.0201
+epoch=14 step=40/178 loss=0.0863
+epoch=14 step=60/178 loss=0.0420
+epoch=14 step=80/178 loss=0.0558
+epoch=14 step=100/178 loss=0.0201
+epoch=14 step=120/178 loss=0.0698
+epoch=14 step=140/178 loss=0.0214
+epoch=14 step=160/178 loss=0.0929
+epoch=14 train_loss=0.0437 train_contrastive=0.1302 train_regression=0.0177 val_loss=0.1354 val_contrastive=0.5795 val_regression=0.0195
+epoch=15 step=20/178 loss=0.0132
+epoch=15 step=40/178 loss=0.0224
+epoch=15 step=60/178 loss=0.0207
+epoch=15 step=80/178 loss=0.0235
+epoch=15 step=100/178 loss=0.0164
+epoch=15 step=120/178 loss=0.0106
+epoch=15 step=140/178 loss=0.0133
+epoch=15 step=160/178 loss=0.0508
+epoch=15 train_loss=0.0357 train_contrastive=0.0989 train_regression=0.0159 val_loss=0.0941 val_contrastive=0.3671 val_regression=0.0207
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.0941 epoch=15
+epoch=16 step=20/178 loss=0.0205
+epoch=16 step=40/178 loss=0.0463
+epoch=16 step=60/178 loss=0.0754
+epoch=16 step=80/178 loss=0.0181
+epoch=16 step=100/178 loss=0.0710
+epoch=16 step=120/178 loss=0.0097
+epoch=16 step=140/178 loss=0.0192
+epoch=16 step=160/178 loss=0.0248
+epoch=16 train_loss=0.0399 train_contrastive=0.1174 train_regression=0.0164 val_loss=0.1007 val_contrastive=0.4153 val_regression=0.0176
+epoch=17 step=20/178 loss=0.0215
+epoch=17 step=40/178 loss=0.0163
+epoch=17 step=60/178 loss=0.0545
+epoch=17 step=80/178 loss=0.0567
+epoch=17 step=100/178 loss=0.0416
+epoch=17 step=120/178 loss=0.0988
+epoch=17 step=140/178 loss=0.0239
+epoch=17 step=160/178 loss=0.0401
+epoch=17 train_loss=0.0436 train_contrastive=0.1317 train_regression=0.0172 val_loss=0.1274 val_contrastive=0.5475 val_regression=0.0179
+epoch=18 step=20/178 loss=0.0247
+epoch=18 step=40/178 loss=0.0152
+epoch=18 step=60/178 loss=0.0290
+epoch=18 step=80/178 loss=0.0219
+epoch=18 step=100/178 loss=0.0184
+epoch=18 step=120/178 loss=0.0150
+epoch=18 step=140/178 loss=0.0105
+epoch=18 step=160/178 loss=0.0180
+epoch=18 train_loss=0.0343 train_contrastive=0.0945 train_regression=0.0154 val_loss=0.0942 val_contrastive=0.3796 val_regression=0.0183
+epoch=19 step=20/178 loss=0.0782
+epoch=19 step=40/178 loss=0.0284
+epoch=19 step=60/178 loss=0.0240
+epoch=19 step=80/178 loss=0.0220
+epoch=19 step=100/178 loss=0.0536
+epoch=19 step=120/178 loss=0.0114
+epoch=19 step=140/178 loss=0.0160
+epoch=19 step=160/178 loss=0.0570
+epoch=19 train_loss=0.0339 train_contrastive=0.0899 train_regression=0.0159 val_loss=0.0818 val_contrastive=0.3237 val_regression=0.0171
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.0818 epoch=19
+epoch=20 step=20/178 loss=0.0319
+epoch=20 step=40/178 loss=0.0361
+epoch=20 step=60/178 loss=0.0073
+epoch=20 step=80/178 loss=0.0566
+epoch=20 step=100/178 loss=0.0100
+epoch=20 step=120/178 loss=0.0447
+epoch=20 step=140/178 loss=0.0206
+epoch=20 step=160/178 loss=0.0209
+epoch=20 train_loss=0.0365 train_contrastive=0.1049 train_regression=0.0155 val_loss=0.1031 val_contrastive=0.4334 val_regression=0.0164
+epoch=21 step=20/178 loss=0.0093
+epoch=21 step=40/178 loss=0.0131
+epoch=21 step=60/178 loss=0.0188
+epoch=21 step=80/178 loss=0.0233
+epoch=21 step=100/178 loss=0.0512
+epoch=21 step=120/178 loss=0.0066
+epoch=21 step=140/178 loss=0.1038
+epoch=21 step=160/178 loss=0.0354
+epoch=21 train_loss=0.0370 train_contrastive=0.1085 train_regression=0.0153 val_loss=0.0931 val_contrastive=0.3736 val_regression=0.0184
+epoch=22 step=20/178 loss=0.2200
+epoch=22 step=40/178 loss=0.0217
+epoch=22 step=60/178 loss=0.0286
+epoch=22 step=80/178 loss=0.0206
+epoch=22 step=100/178 loss=0.0161
+epoch=22 step=120/178 loss=0.0186
+epoch=22 step=140/178 loss=0.0188
+epoch=22 step=160/178 loss=0.0813
+epoch=22 train_loss=0.0372 train_contrastive=0.1113 train_regression=0.0150 val_loss=0.0989 val_contrastive=0.3954 val_regression=0.0199
+epoch=23 step=20/178 loss=0.0221
+epoch=23 step=40/178 loss=0.0220
+epoch=23 step=60/178 loss=0.0104
+epoch=23 step=80/178 loss=0.1750
+epoch=23 step=100/178 loss=0.0190
+epoch=23 step=120/178 loss=0.0101
+epoch=23 step=140/178 loss=0.0117
+epoch=23 step=160/178 loss=0.0202
+epoch=23 train_loss=0.0330 train_contrastive=0.0954 train_regression=0.0140 val_loss=0.0655 val_contrastive=0.2487 val_regression=0.0157
+saved_best runs/foundation/brainfm_frozen_mlp_b4_best.pt val_loss=0.0655 epoch=23
+epoch=24 step=20/178 loss=0.0230
+epoch=24 step=40/178 loss=0.0232
+epoch=24 step=60/178 loss=0.0153
+epoch=24 step=80/178 loss=0.0074
+epoch=24 step=100/178 loss=0.0156
+epoch=24 step=120/178 loss=0.0085
+epoch=24 step=140/178 loss=0.0185
+epoch=24 step=160/178 loss=0.0328
+epoch=24 train_loss=0.0274 train_contrastive=0.0652 train_regression=0.0144 val_loss=0.0723 val_contrastive=0.2750 val_regression=0.0173
+epoch=25 step=20/178 loss=0.0122
+epoch=25 step=40/178 loss=0.0159
+epoch=25 step=60/178 loss=0.0172
+epoch=25 step=80/178 loss=0.0274
+epoch=25 step=100/178 loss=0.0115
+epoch=25 step=120/178 loss=0.0712
+epoch=25 step=140/178 loss=0.0139
+epoch=25 step=160/178 loss=0.0280
+epoch=25 train_loss=0.0318 train_contrastive=0.0843 train_regression=0.0149 val_loss=0.0865 val_contrastive=0.3437 val_regression=0.0177
+epoch=26 step=20/178 loss=0.0339
+epoch=26 step=40/178 loss=0.0092
+epoch=26 step=60/178 loss=0.0109
+epoch=26 step=80/178 loss=0.0783
+epoch=26 step=100/178 loss=0.0229
+epoch=26 step=120/178 loss=0.0231
+epoch=26 step=140/178 loss=0.0095
+epoch=26 step=160/178 loss=0.0069
+epoch=26 train_loss=0.0271 train_contrastive=0.0682 train_regression=0.0135 val_loss=0.0953 val_contrastive=0.3749 val_regression=0.0203
+epoch=27 step=20/178 loss=0.0177
+epoch=27 step=40/178 loss=0.0387
+epoch=27 step=60/178 loss=0.0218
+epoch=27 step=80/178 loss=0.0323
+epoch=27 step=100/178 loss=0.1063
+epoch=27 step=120/178 loss=0.0217
+epoch=27 step=140/178 loss=0.0123
+epoch=27 step=160/178 loss=0.0627
+epoch=27 train_loss=0.0339 train_contrastive=0.0979 train_regression=0.0143 val_loss=0.0812 val_contrastive=0.3090 val_regression=0.0194
+epoch=28 step=20/178 loss=0.0162
+epoch=28 step=40/178 loss=0.0098
+epoch=28 step=60/178 loss=0.0215
+epoch=28 step=80/178 loss=0.0205
+epoch=28 step=100/178 loss=0.0256
+epoch=28 step=120/178 loss=0.0127
+epoch=28 step=140/178 loss=0.0232
+epoch=28 step=160/178 loss=0.0140
+epoch=28 train_loss=0.0268 train_contrastive=0.0616 train_regression=0.0144 val_loss=0.1127 val_contrastive=0.4673 val_regression=0.0192
+epoch=29 step=20/178 loss=0.0154
+epoch=29 step=40/178 loss=0.0400
+epoch=29 step=60/178 loss=0.0103
+epoch=29 step=80/178 loss=0.0439
+epoch=29 step=100/178 loss=0.0154
+epoch=29 step=120/178 loss=0.0318
+epoch=29 step=140/178 loss=0.1055
+epoch=29 step=160/178 loss=0.0090
+epoch=29 train_loss=0.0324 train_contrastive=0.0897 train_regression=0.0144 val_loss=0.0844 val_contrastive=0.3341 val_regression=0.0175
+epoch=30 step=20/178 loss=0.0515
+epoch=30 step=40/178 loss=0.0134
+epoch=30 step=60/178 loss=0.0161
+epoch=30 step=80/178 loss=0.0872
+epoch=30 step=100/178 loss=0.0143
+epoch=30 step=120/178 loss=0.0141
+epoch=30 step=140/178 loss=0.0191
+epoch=30 step=160/178 loss=0.0147
+epoch=30 train_loss=0.0278 train_contrastive=0.0683 train_regression=0.0141 val_loss=0.1156 val_contrastive=0.4898 val_regression=0.0176
+saved runs/foundation/brainfm_frozen_mlp_b4.pt

logs/brainfm_lastblock_regalign.log ADDED Viewed

	@@ -0,0 +1,579 @@

+device=cuda backbone=brainfm encoder_scope=last_block contrastive_weight=0.2 regression_weight=1.0 train=710 val=152
+epoch=1 step=20/355 loss=0.9660
+epoch=1 step=40/355 loss=0.9355
+epoch=1 step=60/355 loss=0.4120
+epoch=1 step=80/355 loss=0.3496
+epoch=1 step=100/355 loss=0.2487
+epoch=1 step=120/355 loss=0.3036
+epoch=1 step=140/355 loss=0.2167
+epoch=1 step=160/355 loss=0.1830
+epoch=1 step=180/355 loss=0.4667
+epoch=1 step=200/355 loss=0.2953
+epoch=1 step=220/355 loss=0.2468
+epoch=1 step=240/355 loss=0.2065
+epoch=1 step=260/355 loss=0.1906
+epoch=1 step=280/355 loss=0.1915
+epoch=1 step=300/355 loss=0.1659
+epoch=1 step=320/355 loss=0.2011
+epoch=1 step=340/355 loss=0.1512
+epoch=1 train_loss=0.3557 train_contrastive=0.6888 train_regression=0.2179 val_loss=0.1759 val_contrastive=0.6731 val_regression=0.0413
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.1759 epoch=1
+epoch=2 step=20/355 loss=0.1522
+epoch=2 step=40/355 loss=0.1863
+epoch=2 step=60/355 loss=0.1510
+epoch=2 step=80/355 loss=0.1390
+epoch=2 step=100/355 loss=0.1484
+epoch=2 step=120/355 loss=0.1371
+epoch=2 step=140/355 loss=0.1404
+epoch=2 step=160/355 loss=0.1437
+epoch=2 step=180/355 loss=0.1656
+epoch=2 step=200/355 loss=0.1425
+epoch=2 step=220/355 loss=0.1534
+epoch=2 step=240/355 loss=0.1363
+epoch=2 step=260/355 loss=0.1280
+epoch=2 step=280/355 loss=0.1524
+epoch=2 step=300/355 loss=0.1313
+epoch=2 step=320/355 loss=0.1521
+epoch=2 step=340/355 loss=0.1519
+epoch=2 train_loss=0.1561 train_contrastive=0.6325 train_regression=0.0296 val_loss=0.1536 val_contrastive=0.6297 val_regression=0.0276
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.1536 epoch=2
+epoch=3 step=20/355 loss=0.1071
+epoch=3 step=40/355 loss=0.1302
+epoch=3 step=60/355 loss=0.1230
+epoch=3 step=80/355 loss=0.1298
+epoch=3 step=100/355 loss=0.0994
+epoch=3 step=120/355 loss=0.1046
+epoch=3 step=140/355 loss=0.1523
+epoch=3 step=160/355 loss=0.1351
+epoch=3 step=180/355 loss=0.1203
+epoch=3 step=200/355 loss=0.1268
+epoch=3 step=220/355 loss=0.1143
+epoch=3 step=240/355 loss=0.1429
+epoch=3 step=260/355 loss=0.0623
+epoch=3 step=280/355 loss=0.1575
+epoch=3 step=300/355 loss=0.1279
+epoch=3 step=320/355 loss=0.1638
+epoch=3 step=340/355 loss=0.0728
+epoch=3 train_loss=0.1356 train_contrastive=0.5433 train_regression=0.0270 val_loss=0.1355 val_contrastive=0.5346 val_regression=0.0286
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.1355 epoch=3
+epoch=4 step=20/355 loss=0.1485
+epoch=4 step=40/355 loss=0.1207
+epoch=4 step=60/355 loss=0.1477
+epoch=4 step=80/355 loss=0.1738
+epoch=4 step=100/355 loss=0.1042
+epoch=4 step=120/355 loss=0.1541
+epoch=4 step=140/355 loss=0.1079
+epoch=4 step=160/355 loss=0.1402
+epoch=4 step=180/355 loss=0.1169
+epoch=4 step=200/355 loss=0.1467
+epoch=4 step=220/355 loss=0.1507
+epoch=4 step=240/355 loss=0.1500
+epoch=4 step=260/355 loss=0.0473
+epoch=4 step=280/355 loss=0.0782
+epoch=4 step=300/355 loss=0.1296
+epoch=4 step=320/355 loss=0.0901
+epoch=4 step=340/355 loss=0.0482
+epoch=4 train_loss=0.1070 train_contrastive=0.3859 train_regression=0.0299 val_loss=0.1160 val_contrastive=0.4283 val_regression=0.0303
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.1160 epoch=4
+epoch=5 step=20/355 loss=0.0800
+epoch=5 step=40/355 loss=0.1416
+epoch=5 step=60/355 loss=0.0511
+epoch=5 step=80/355 loss=0.0604
+epoch=5 step=100/355 loss=0.0389
+epoch=5 step=120/355 loss=0.0919
+epoch=5 step=140/355 loss=0.0296
+epoch=5 step=160/355 loss=0.0940
+epoch=5 step=180/355 loss=0.0554
+epoch=5 step=200/355 loss=0.1268
+epoch=5 step=220/355 loss=0.0623
+epoch=5 step=240/355 loss=0.1099
+epoch=5 step=260/355 loss=0.0261
+epoch=5 step=280/355 loss=0.1656
+epoch=5 step=300/355 loss=0.1081
+epoch=5 step=320/355 loss=0.0238
+epoch=5 step=340/355 loss=0.1093
+epoch=5 train_loss=0.0848 train_contrastive=0.2741 train_regression=0.0299 val_loss=0.1039 val_contrastive=0.3736 val_regression=0.0292
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.1039 epoch=5
+epoch=6 step=20/355 loss=0.1122
+epoch=6 step=40/355 loss=0.0576
+epoch=6 step=60/355 loss=0.1185
+epoch=6 step=80/355 loss=0.0406
+epoch=6 step=100/355 loss=0.0328
+epoch=6 step=120/355 loss=0.0811
+epoch=6 step=140/355 loss=0.0259
+epoch=6 step=160/355 loss=0.0713
+epoch=6 step=180/355 loss=0.0271
+epoch=6 step=200/355 loss=0.0249
+epoch=6 step=220/355 loss=0.0496
+epoch=6 step=240/355 loss=0.1822
+epoch=6 step=260/355 loss=0.0713
+epoch=6 step=280/355 loss=0.0356
+epoch=6 step=300/355 loss=0.0810
+epoch=6 step=320/355 loss=0.0405
+epoch=6 step=340/355 loss=0.0948
+epoch=6 train_loss=0.0757 train_contrastive=0.2394 train_regression=0.0278 val_loss=0.1001 val_contrastive=0.3512 val_regression=0.0298
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.1001 epoch=6
+epoch=7 step=20/355 loss=0.0348
+epoch=7 step=40/355 loss=0.0413
+epoch=7 step=60/355 loss=0.0510
+epoch=7 step=80/355 loss=0.0582
+epoch=7 step=100/355 loss=0.0481
+epoch=7 step=120/355 loss=0.0683
+epoch=7 step=140/355 loss=0.0505
+epoch=7 step=160/355 loss=0.0242
+epoch=7 step=180/355 loss=0.1753
+epoch=7 step=200/355 loss=0.0630
+epoch=7 step=220/355 loss=0.0576
+epoch=7 step=240/355 loss=0.0214
+epoch=7 step=260/355 loss=0.0241
+epoch=7 step=280/355 loss=0.0648
+epoch=7 step=300/355 loss=0.0263
+epoch=7 step=320/355 loss=0.0535
+epoch=7 step=340/355 loss=0.0284
+epoch=7 train_loss=0.0664 train_contrastive=0.2001 train_regression=0.0264 val_loss=0.0915 val_contrastive=0.3182 val_regression=0.0279
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0915 epoch=7
+epoch=8 step=20/355 loss=0.0756
+epoch=8 step=40/355 loss=0.0411
+epoch=8 step=60/355 loss=0.0276
+epoch=8 step=80/355 loss=0.0244
+epoch=8 step=100/355 loss=0.0883
+epoch=8 step=120/355 loss=0.0241
+epoch=8 step=140/355 loss=0.0248
+epoch=8 step=160/355 loss=0.0661
+epoch=8 step=180/355 loss=0.0220
+epoch=8 step=200/355 loss=0.1204
+epoch=8 step=220/355 loss=0.0262
+epoch=8 step=240/355 loss=0.0946
+epoch=8 step=260/355 loss=0.0378
+epoch=8 step=280/355 loss=0.0880
+epoch=8 step=300/355 loss=0.1085
+epoch=8 step=320/355 loss=0.0416
+epoch=8 step=340/355 loss=0.2077
+epoch=8 train_loss=0.0547 train_contrastive=0.1464 train_regression=0.0254 val_loss=0.0858 val_contrastive=0.2953 val_regression=0.0267
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0858 epoch=8
+epoch=9 step=20/355 loss=0.0202
+epoch=9 step=40/355 loss=0.0298
+epoch=9 step=60/355 loss=0.0400
+epoch=9 step=80/355 loss=0.0453
+epoch=9 step=100/355 loss=0.0188
+epoch=9 step=120/355 loss=0.0209
+epoch=9 step=140/355 loss=0.1028
+epoch=9 step=160/355 loss=0.0229
+epoch=9 step=180/355 loss=0.0369
+epoch=9 step=200/355 loss=0.0257
+epoch=9 step=220/355 loss=0.0361
+epoch=9 step=240/355 loss=0.1957
+epoch=9 step=260/355 loss=0.0757
+epoch=9 step=280/355 loss=0.0239
+epoch=9 step=300/355 loss=0.0424
+epoch=9 step=320/355 loss=0.0973
+epoch=9 step=340/355 loss=0.0688
+epoch=9 train_loss=0.0499 train_contrastive=0.1289 train_regression=0.0241 val_loss=0.0819 val_contrastive=0.2778 val_regression=0.0263
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0819 epoch=9
+epoch=10 step=20/355 loss=0.0577
+epoch=10 step=40/355 loss=0.0508
+epoch=10 step=60/355 loss=0.0233
+epoch=10 step=80/355 loss=0.0175
+epoch=10 step=100/355 loss=0.0254
+epoch=10 step=120/355 loss=0.1936
+epoch=10 step=140/355 loss=0.0286
+epoch=10 step=160/355 loss=0.0218
+epoch=10 step=180/355 loss=0.0389
+epoch=10 step=200/355 loss=0.0163
+epoch=10 step=220/355 loss=0.0451
+epoch=10 step=240/355 loss=0.0218
+epoch=10 step=260/355 loss=0.0682
+epoch=10 step=280/355 loss=0.0174
+epoch=10 step=300/355 loss=0.0511
+epoch=10 step=320/355 loss=0.0287
+epoch=10 step=340/355 loss=0.0199
+epoch=10 train_loss=0.0477 train_contrastive=0.1237 train_regression=0.0229 val_loss=0.0777 val_contrastive=0.2554 val_regression=0.0266
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0777 epoch=10
+epoch=11 step=20/355 loss=0.0374
+epoch=11 step=40/355 loss=0.0308
+epoch=11 step=60/355 loss=0.0168
+epoch=11 step=80/355 loss=0.0861
+epoch=11 step=100/355 loss=0.0175
+epoch=11 step=120/355 loss=0.0850
+epoch=11 step=140/355 loss=0.0680
+epoch=11 step=160/355 loss=0.0200
+epoch=11 step=180/355 loss=0.0307
+epoch=11 step=200/355 loss=0.0430
+epoch=11 step=220/355 loss=0.0376
+epoch=11 step=240/355 loss=0.0444
+epoch=11 step=260/355 loss=0.0391
+epoch=11 step=280/355 loss=0.0153
+epoch=11 step=300/355 loss=0.0610
+epoch=11 step=320/355 loss=0.0230
+epoch=11 step=340/355 loss=0.0249
+epoch=11 train_loss=0.0432 train_contrastive=0.1024 train_regression=0.0227 val_loss=0.0763 val_contrastive=0.2594 val_regression=0.0244
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0763 epoch=11
+epoch=12 step=20/355 loss=0.0140
+epoch=12 step=40/355 loss=0.0189
+epoch=12 step=60/355 loss=0.0233
+epoch=12 step=80/355 loss=0.0358
+epoch=12 step=100/355 loss=0.0189
+epoch=12 step=120/355 loss=0.0630
+epoch=12 step=140/355 loss=0.0180
+epoch=12 step=160/355 loss=0.0758
+epoch=12 step=180/355 loss=0.0250
+epoch=12 step=200/355 loss=0.0927
+epoch=12 step=220/355 loss=0.1203
+epoch=12 step=240/355 loss=0.1539
+epoch=12 step=260/355 loss=0.1003
+epoch=12 step=280/355 loss=0.0505
+epoch=12 step=300/355 loss=0.1018
+epoch=12 step=320/355 loss=0.0570
+epoch=12 step=340/355 loss=0.0205
+epoch=12 train_loss=0.0414 train_contrastive=0.1001 train_regression=0.0214 val_loss=0.0715 val_contrastive=0.2409 val_regression=0.0233
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0715 epoch=12
+epoch=13 step=20/355 loss=0.0149
+epoch=13 step=40/355 loss=0.0272
+epoch=13 step=60/355 loss=0.1200
+epoch=13 step=80/355 loss=0.0119
+epoch=13 step=100/355 loss=0.0262
+epoch=13 step=120/355 loss=0.1605
+epoch=13 step=140/355 loss=0.0156
+epoch=13 step=160/355 loss=0.0510
+epoch=13 step=180/355 loss=0.0225
+epoch=13 step=200/355 loss=0.0166
+epoch=13 step=220/355 loss=0.0590
+epoch=13 step=240/355 loss=0.0354
+epoch=13 step=260/355 loss=0.0226
+epoch=13 step=280/355 loss=0.0268
+epoch=13 step=300/355 loss=0.0539
+epoch=13 step=320/355 loss=0.0178
+epoch=13 step=340/355 loss=0.0319
+epoch=13 train_loss=0.0395 train_contrastive=0.0968 train_regression=0.0202 val_loss=0.0709 val_contrastive=0.2380 val_regression=0.0233
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0709 epoch=13
+epoch=14 step=20/355 loss=0.0197
+epoch=14 step=40/355 loss=0.1188
+epoch=14 step=60/355 loss=0.0831
+epoch=14 step=80/355 loss=0.0271
+epoch=14 step=100/355 loss=0.0169
+epoch=14 step=120/355 loss=0.0197
+epoch=14 step=140/355 loss=0.0275
+epoch=14 step=160/355 loss=0.0164
+epoch=14 step=180/355 loss=0.0949
+epoch=14 step=200/355 loss=0.0160
+epoch=14 step=220/355 loss=0.0314
+epoch=14 step=240/355 loss=0.0111
+epoch=14 step=260/355 loss=0.0229
+epoch=14 step=280/355 loss=0.0564
+epoch=14 step=300/355 loss=0.0560
+epoch=14 step=320/355 loss=0.0237
+epoch=14 step=340/355 loss=0.0140
+epoch=14 train_loss=0.0419 train_contrastive=0.1105 train_regression=0.0198 val_loss=0.0711 val_contrastive=0.2451 val_regression=0.0220
+epoch=15 step=20/355 loss=0.0167
+epoch=15 step=40/355 loss=0.0164
+epoch=15 step=60/355 loss=0.0228
+epoch=15 step=80/355 loss=0.0135
+epoch=15 step=100/355 loss=0.1073
+epoch=15 step=120/355 loss=0.0149
+epoch=15 step=140/355 loss=0.0399
+epoch=15 step=160/355 loss=0.0193
+epoch=15 step=180/355 loss=0.0269
+epoch=15 step=200/355 loss=0.0201
+epoch=15 step=220/355 loss=0.0160
+epoch=15 step=240/355 loss=0.0226
+epoch=15 step=260/355 loss=0.0316
+epoch=15 step=280/355 loss=0.0447
+epoch=15 step=300/355 loss=0.0300
+epoch=15 step=320/355 loss=0.0638
+epoch=15 step=340/355 loss=0.0164
+epoch=15 train_loss=0.0339 train_contrastive=0.0746 train_regression=0.0189 val_loss=0.0691 val_contrastive=0.2349 val_regression=0.0222
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0691 epoch=15
+epoch=16 step=20/355 loss=0.0491
+epoch=16 step=40/355 loss=0.0269
+epoch=16 step=60/355 loss=0.0137
+epoch=16 step=80/355 loss=0.0240
+epoch=16 step=100/355 loss=0.0282
+epoch=16 step=120/355 loss=0.0218
+epoch=16 step=140/355 loss=0.0223
+epoch=16 step=160/355 loss=0.0185
+epoch=16 step=180/355 loss=0.0921
+epoch=16 step=200/355 loss=0.0193
+epoch=16 step=220/355 loss=0.0789
+epoch=16 step=240/355 loss=0.0287
+epoch=16 step=260/355 loss=0.0217
+epoch=16 step=280/355 loss=0.0264
+epoch=16 step=300/355 loss=0.0197
+epoch=16 step=320/355 loss=0.0085
+epoch=16 step=340/355 loss=0.0108
+epoch=16 train_loss=0.0319 train_contrastive=0.0670 train_regression=0.0185 val_loss=0.0705 val_contrastive=0.2376 val_regression=0.0230
+epoch=17 step=20/355 loss=0.0176
+epoch=17 step=40/355 loss=0.0213
+epoch=17 step=60/355 loss=0.0201
+epoch=17 step=80/355 loss=0.0208
+epoch=17 step=100/355 loss=0.0327
+epoch=17 step=120/355 loss=0.0204
+epoch=17 step=140/355 loss=0.1332
+epoch=17 step=160/355 loss=0.0333
+epoch=17 step=180/355 loss=0.0176
+epoch=17 step=200/355 loss=0.0113
+epoch=17 step=220/355 loss=0.0394
+epoch=17 step=240/355 loss=0.0244
+epoch=17 step=260/355 loss=0.0208
+epoch=17 step=280/355 loss=0.0117
+epoch=17 step=300/355 loss=0.0109
+epoch=17 step=320/355 loss=0.2924
+epoch=17 step=340/355 loss=0.0189
+epoch=17 train_loss=0.0331 train_contrastive=0.0753 train_regression=0.0181 val_loss=0.0649 val_contrastive=0.2159 val_regression=0.0218
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0649 epoch=17
+epoch=18 step=20/355 loss=0.0307
+epoch=18 step=40/355 loss=0.0493
+epoch=18 step=60/355 loss=0.0187
+epoch=18 step=80/355 loss=0.0201
+epoch=18 step=100/355 loss=0.0118
+epoch=18 step=120/355 loss=0.0533
+epoch=18 step=140/355 loss=0.0105
+epoch=18 step=160/355 loss=0.0095
+epoch=18 step=180/355 loss=0.0112
+epoch=18 step=200/355 loss=0.0176
+epoch=18 step=220/355 loss=0.0542
+epoch=18 step=240/355 loss=0.0476
+epoch=18 step=260/355 loss=0.0151
+epoch=18 step=280/355 loss=0.0256
+epoch=18 step=300/355 loss=0.0256
+epoch=18 step=320/355 loss=0.0126
+epoch=18 step=340/355 loss=0.0242
+epoch=18 train_loss=0.0282 train_contrastive=0.0533 train_regression=0.0175 val_loss=0.0611 val_contrastive=0.2045 val_regression=0.0202
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0611 epoch=18
+epoch=19 step=20/355 loss=0.0290
+epoch=19 step=40/355 loss=0.0257
+epoch=19 step=60/355 loss=0.0560
+epoch=19 step=80/355 loss=0.0117
+epoch=19 step=100/355 loss=0.0351
+epoch=19 step=120/355 loss=0.0195
+epoch=19 step=140/355 loss=0.0307
+epoch=19 step=160/355 loss=0.0257
+epoch=19 step=180/355 loss=0.0535
+epoch=19 step=200/355 loss=0.0203
+epoch=19 step=220/355 loss=0.0192
+epoch=19 step=240/355 loss=0.0107
+epoch=19 step=260/355 loss=0.0126
+epoch=19 step=280/355 loss=0.0206
+epoch=19 step=300/355 loss=0.0115
+epoch=19 step=320/355 loss=0.0309
+epoch=19 step=340/355 loss=0.0102
+epoch=19 train_loss=0.0241 train_contrastive=0.0371 train_regression=0.0167 val_loss=0.0642 val_contrastive=0.2178 val_regression=0.0207
+epoch=20 step=20/355 loss=0.0341
+epoch=20 step=40/355 loss=0.0182
+epoch=20 step=60/355 loss=0.0131
+epoch=20 step=80/355 loss=0.0114
+epoch=20 step=100/355 loss=0.0212
+epoch=20 step=120/355 loss=0.0180
+epoch=20 step=140/355 loss=0.0148
+epoch=20 step=160/355 loss=0.0092
+epoch=20 step=180/355 loss=0.0470
+epoch=20 step=200/355 loss=0.0175
+epoch=20 step=220/355 loss=0.0174
+epoch=20 step=240/355 loss=0.0646
+epoch=20 step=260/355 loss=0.0734
+epoch=20 step=280/355 loss=0.0074
+epoch=20 step=300/355 loss=0.0113
+epoch=20 step=320/355 loss=0.0224
+epoch=20 step=340/355 loss=0.0089
+epoch=20 train_loss=0.0277 train_contrastive=0.0568 train_regression=0.0164 val_loss=0.0650 val_contrastive=0.2265 val_regression=0.0197
+epoch=21 step=20/355 loss=0.0554
+epoch=21 step=40/355 loss=0.0110
+epoch=21 step=60/355 loss=0.0104
+epoch=21 step=80/355 loss=0.0112
+epoch=21 step=100/355 loss=0.0132
+epoch=21 step=120/355 loss=0.0113
+epoch=21 step=140/355 loss=0.0133
+epoch=21 step=160/355 loss=0.0414
+epoch=21 step=180/355 loss=0.0097
+epoch=21 step=200/355 loss=0.0136
+epoch=21 step=220/355 loss=0.0097
+epoch=21 step=240/355 loss=0.0647
+epoch=21 step=260/355 loss=0.0148
+epoch=21 step=280/355 loss=0.0363
+epoch=21 step=300/355 loss=0.0224
+epoch=21 step=320/355 loss=0.0115
+epoch=21 step=340/355 loss=0.0194
+epoch=21 train_loss=0.0249 train_contrastive=0.0450 train_regression=0.0159 val_loss=0.0718 val_contrastive=0.2542 val_regression=0.0210
+epoch=22 step=20/355 loss=0.0259
+epoch=22 step=40/355 loss=0.0700
+epoch=22 step=60/355 loss=0.0193
+epoch=22 step=80/355 loss=0.0245
+epoch=22 step=100/355 loss=0.0164
+epoch=22 step=120/355 loss=0.0115
+epoch=22 step=140/355 loss=0.0067
+epoch=22 step=160/355 loss=0.0165
+epoch=22 step=180/355 loss=0.0108
+epoch=22 step=200/355 loss=0.0192
+epoch=22 step=220/355 loss=0.0199
+epoch=22 step=240/355 loss=0.0309
+epoch=22 step=260/355 loss=0.0177
+epoch=22 step=280/355 loss=0.0106
+epoch=22 step=300/355 loss=0.0456
+epoch=22 step=320/355 loss=0.0223
+epoch=22 step=340/355 loss=0.0179
+epoch=22 train_loss=0.0231 train_contrastive=0.0383 train_regression=0.0154 val_loss=0.0634 val_contrastive=0.2213 val_regression=0.0191
+epoch=23 step=20/355 loss=0.0094
+epoch=23 step=40/355 loss=0.0118
+epoch=23 step=60/355 loss=0.0370
+epoch=23 step=80/355 loss=0.0272
+epoch=23 step=100/355 loss=0.0163
+epoch=23 step=120/355 loss=0.0256
+epoch=23 step=140/355 loss=0.0078
+epoch=23 step=160/355 loss=0.0197
+epoch=23 step=180/355 loss=0.0175
+epoch=23 step=200/355 loss=0.0103
+epoch=23 step=220/355 loss=0.0177
+epoch=23 step=240/355 loss=0.0115
+epoch=23 step=260/355 loss=0.0182
+epoch=23 step=280/355 loss=0.0130
+epoch=23 step=300/355 loss=0.0152
+epoch=23 step=320/355 loss=0.0108
+epoch=23 step=340/355 loss=0.0131
+epoch=23 train_loss=0.0240 train_contrastive=0.0430 train_regression=0.0154 val_loss=0.0690 val_contrastive=0.2509 val_regression=0.0188
+epoch=24 step=20/355 loss=0.0286
+epoch=24 step=40/355 loss=0.0482
+epoch=24 step=60/355 loss=0.0179
+epoch=24 step=80/355 loss=0.0098
+epoch=24 step=100/355 loss=0.0113
+epoch=24 step=120/355 loss=0.0112
+epoch=24 step=140/355 loss=0.0350
+epoch=24 step=160/355 loss=0.0253
+epoch=24 step=180/355 loss=0.0130
+epoch=24 step=200/355 loss=0.0131
+epoch=24 step=220/355 loss=0.0081
+epoch=24 step=240/355 loss=0.0186
+epoch=24 step=260/355 loss=0.0090
+epoch=24 step=280/355 loss=0.0094
+epoch=24 step=300/355 loss=0.0082
+epoch=24 step=320/355 loss=0.0126
+epoch=24 step=340/355 loss=0.0075
+epoch=24 train_loss=0.0208 train_contrastive=0.0307 train_regression=0.0147 val_loss=0.0610 val_contrastive=0.2142 val_regression=0.0182
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0610 epoch=24
+epoch=25 step=20/355 loss=0.0357
+epoch=25 step=40/355 loss=0.0084
+epoch=25 step=60/355 loss=0.0153
+epoch=25 step=80/355 loss=0.0064
+epoch=25 step=100/355 loss=0.0107
+epoch=25 step=120/355 loss=0.0109
+epoch=25 step=140/355 loss=0.0259
+epoch=25 step=160/355 loss=0.0168
+epoch=25 step=180/355 loss=0.0192
+epoch=25 step=200/355 loss=0.0183
+epoch=25 step=220/355 loss=0.0152
+epoch=25 step=240/355 loss=0.0153
+epoch=25 step=260/355 loss=0.0131
+epoch=25 step=280/355 loss=0.0076
+epoch=25 step=300/355 loss=0.0090
+epoch=25 step=320/355 loss=0.0071
+epoch=25 step=340/355 loss=0.0234
+epoch=25 train_loss=0.0207 train_contrastive=0.0315 train_regression=0.0144 val_loss=0.0604 val_contrastive=0.2120 val_regression=0.0180
+saved_best runs/foundation/brainfm_lastblock_regalign_best.pt val_loss=0.0604 epoch=25
+epoch=26 step=20/355 loss=0.0245
+epoch=26 step=40/355 loss=0.0130
+epoch=26 step=60/355 loss=0.0118
+epoch=26 step=80/355 loss=0.0093
+epoch=26 step=100/355 loss=0.0383
+epoch=26 step=120/355 loss=0.0129
+epoch=26 step=140/355 loss=0.0232
+epoch=26 step=160/355 loss=0.0107
+epoch=26 step=180/355 loss=0.0233
+epoch=26 step=200/355 loss=0.0079
+epoch=26 step=220/355 loss=0.0100
+epoch=26 step=240/355 loss=0.0117
+epoch=26 step=260/355 loss=0.0640
+epoch=26 step=280/355 loss=0.0173
+epoch=26 step=300/355 loss=0.0179
+epoch=26 step=320/355 loss=0.0107
+epoch=26 step=340/355 loss=0.0100
+epoch=26 train_loss=0.0231 train_contrastive=0.0405 train_regression=0.0150 val_loss=0.0641 val_contrastive=0.2301 val_regression=0.0181
+epoch=27 step=20/355 loss=0.0336
+epoch=27 step=40/355 loss=0.0095
+epoch=27 step=60/355 loss=0.0154
+epoch=27 step=80/355 loss=0.0202
+epoch=27 step=100/355 loss=0.0082
+epoch=27 step=120/355 loss=0.0099
+epoch=27 step=140/355 loss=0.0325
+epoch=27 step=160/355 loss=0.0189
+epoch=27 step=180/355 loss=0.0132
+epoch=27 step=200/355 loss=0.0074
+epoch=27 step=220/355 loss=0.0383
+epoch=27 step=240/355 loss=0.0572
+epoch=27 step=260/355 loss=0.0095
+epoch=27 step=280/355 loss=0.0101
+epoch=27 step=300/355 loss=0.0157
+epoch=27 step=320/355 loss=0.0074
+epoch=27 step=340/355 loss=0.0133
+epoch=27 train_loss=0.0223 train_contrastive=0.0406 train_regression=0.0141 val_loss=0.0629 val_contrastive=0.2207 val_regression=0.0188
+epoch=28 step=20/355 loss=0.0140
+epoch=28 step=40/355 loss=0.0146
+epoch=28 step=60/355 loss=0.0103
+epoch=28 step=80/355 loss=0.0075
+epoch=28 step=100/355 loss=0.0084
+epoch=28 step=120/355 loss=0.0079
+epoch=28 step=140/355 loss=0.0287
+epoch=28 step=160/355 loss=0.0109
+epoch=28 step=180/355 loss=0.0145
+epoch=28 step=200/355 loss=0.0282
+epoch=28 step=220/355 loss=0.0095
+epoch=28 step=240/355 loss=0.0118
+epoch=28 step=260/355 loss=0.0220
+epoch=28 step=280/355 loss=0.0069
+epoch=28 step=300/355 loss=0.0132
+epoch=28 step=320/355 loss=0.0199
+epoch=28 step=340/355 loss=0.0107
+epoch=28 train_loss=0.0237 train_contrastive=0.0491 train_regression=0.0139 val_loss=0.0638 val_contrastive=0.2218 val_regression=0.0195
+epoch=29 step=20/355 loss=0.0123
+epoch=29 step=40/355 loss=0.0074
+epoch=29 step=60/355 loss=0.0639
+epoch=29 step=80/355 loss=0.0303
+epoch=29 step=100/355 loss=0.0084
+epoch=29 step=120/355 loss=0.0189
+epoch=29 step=140/355 loss=0.0199
+epoch=29 step=160/355 loss=0.0149
+epoch=29 step=180/355 loss=0.0212
+epoch=29 step=200/355 loss=0.0109
+epoch=29 step=220/355 loss=0.0165
+epoch=29 step=240/355 loss=0.0089
+epoch=29 step=260/355 loss=0.0098
+epoch=29 step=280/355 loss=0.0274
+epoch=29 step=300/355 loss=0.0174
+epoch=29 step=320/355 loss=0.0153
+epoch=29 step=340/355 loss=0.0524
+epoch=29 train_loss=0.0176 train_contrastive=0.0219 train_regression=0.0132 val_loss=0.0634 val_contrastive=0.2294 val_regression=0.0176
+epoch=30 step=20/355 loss=0.0068
+epoch=30 step=40/355 loss=0.0205
+epoch=30 step=60/355 loss=0.0077
+epoch=30 step=80/355 loss=0.0096
+epoch=30 step=100/355 loss=0.0060
+epoch=30 step=120/355 loss=0.0108
+epoch=30 step=140/355 loss=0.0085
+epoch=30 step=160/355 loss=0.0070
+epoch=30 step=180/355 loss=0.0132
+epoch=30 step=200/355 loss=0.0695
+epoch=30 step=220/355 loss=0.0091
+epoch=30 step=240/355 loss=0.0110
+epoch=30 step=260/355 loss=0.0099
+epoch=30 step=280/355 loss=0.0139
+epoch=30 step=300/355 loss=0.0159
+epoch=30 step=320/355 loss=0.0171
+epoch=30 step=340/355 loss=0.0171
+epoch=30 train_loss=0.0180 train_contrastive=0.0246 train_regression=0.0131 val_loss=0.0662 val_contrastive=0.2383 val_regression=0.0185
+saved runs/foundation/brainfm_lastblock_regalign.pt
+checkpoint=runs/foundation/brainfm_lastblock_regalign_best.pt
+manifest=metadata/splits/test.csv
+samples=153.000000
+mae=0.103681
+rmse=0.134011
+pearson=0.810821
+spearman=0.842864
+top5_high_overlap=0.474510
+top5_low_overlap=0.682353
+pet_to_suvr_recall@1=0.261438
+pet_to_suvr_recall@5=0.653595
+pet_to_suvr_recall@10=0.797386
+pet_to_suvr_mrr=0.445801
+pet_to_suvr_median_rank=3.000000
+suvr_to_pet_recall@1=0.320261
+suvr_to_pet_recall@5=0.705882
+suvr_to_pet_recall@10=0.862745
+suvr_to_pet_mrr=0.480437
+suvr_to_pet_median_rank=3.000000

logs/brainiac_frozen_clinicalbert_text_alignment.log ADDED Viewed

	@@ -0,0 +1,38 @@

+<frozen importlib._bootstrap_external>:1325: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead.
+brainiac_missing_keys=['blocks.0.norm_cross_attn.weight', 'blocks.0.norm_cross_attn.bias', 'blocks.0.cross_attn.out_proj.weight', 'blocks.0.cross_attn.out_proj.bias', 'blocks.0.cross_attn.to_q.weight', 'blocks.0.cross_attn.to_k.weight', 'blocks.0.cross_attn.to_v.weight', 'blocks.1.norm_cross_attn.weight']
+epoch=1 train_loss=2.764560 val_loss=2.736124
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.736124
+epoch=2 train_loss=2.764268 val_loss=2.736086
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.736086
+epoch=3 train_loss=2.764206 val_loss=2.736040
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.736040
+epoch=4 train_loss=2.764057 val_loss=2.735920
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.735920
+epoch=5 train_loss=2.769102 val_loss=2.736128
+epoch=6 train_loss=2.764342 val_loss=2.736061
+epoch=7 train_loss=2.764101 val_loss=2.735983
+epoch=8 train_loss=2.764013 val_loss=2.735949
+epoch=9 train_loss=2.763975 val_loss=2.735925
+epoch=10 train_loss=2.763926 val_loss=2.735906
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.735906
+epoch=11 train_loss=2.763883 val_loss=2.735878
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.735878
+epoch=12 train_loss=2.763790 val_loss=2.735849
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.735849
+epoch=13 train_loss=2.763783 val_loss=2.735814
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.735814
+epoch=14 train_loss=2.763669 val_loss=2.735761
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.735761
+epoch=15 train_loss=2.763530 val_loss=2.735700
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.735700
+epoch=16 train_loss=2.763358 val_loss=2.735607
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.735607
+epoch=17 train_loss=2.763164 val_loss=2.735474
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.735474
+epoch=18 train_loss=2.762954 val_loss=2.735278
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.735278
+epoch=19 train_loss=2.762326 val_loss=2.734944
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.734944
+epoch=20 train_loss=2.761598 val_loss=2.734263
+saved_best runs/vlm/brainiac_frozen_clinicalbert_text_alignment_best.pt val_loss=2.734263
+saved runs/vlm/brainiac_frozen_clinicalbert_text_alignment.pt

logs/clinical_brainfm_frozen_v2.log ADDED Viewed

	@@ -0,0 +1,9 @@

+checkpoint=runs/foundation/brainfm_frozen_mlp_b4_best.pt
+wrote=runs/clinical/brainfm_frozen_clinical_probe.csv
+{'task': 'clinical_label_3way', 'type': 'classification', 'n_train': 710, 'n_val': 152, 'n_test': 153, 'selected_param': 0.01, 'accuracy': 0.47058823529411764, 'balanced_accuracy': 0.5175103937393005, 'macro_f1': 0.4652422982544258, 'auroc': 0.6931153427588082}
+{'task': 'ad_vs_cn', 'type': 'classification', 'n_train': 332, 'n_val': 69, 'n_test': 59, 'selected_param': 0.03, 'accuracy': 0.7966101694915254, 'balanced_accuracy': 0.7971264367816092, 'macro_f1': 0.7965517241379311, 'auroc': 0.8563218390804598}
+{'task': 'pmci_vs_smci', 'type': 'classification', 'n_train': 269, 'n_val': 51, 'n_test': 69, 'selected_param': 0.01, 'accuracy': 0.6811594202898551, 'balanced_accuracy': 0.6397405660377358, 'macro_f1': 0.6127551020408163, 'auroc': 0.6745283018867925}
+{'task': 'adas11', 'type': 'regression', 'n_train': 709, 'n_val': 151, 'n_test': 153, 'selected_param': 10.0, 'mae': 4.282139976601195, 'rmse': 5.480145042903598, 'r2': 0.32613889915922456, 'pearson': 0.5797018703612662}
+{'task': 'mmse', 'type': 'regression', 'n_train': 710, 'n_val': 152, 'n_test': 153, 'selected_param': 30.0, 'mae': 1.9694834690467984, 'rmse': 2.3026492004399985, 'r2': 0.25421777643919574, 'pearson': 0.505845083282301}
+{'task': 'ravlt_immediate', 'type': 'regression', 'n_train': 708, 'n_val': 152, 'n_test': 153, 'selected_param': 100.0, 'mae': 9.170424006343668, 'rmse': 11.312929028342541, 'r2': 0.21188988221876404, 'pearson': 0.47212505391608034}
+{'task': 'ldeltotal', 'type': 'regression', 'n_train': 710, 'n_val': 152, 'n_test': 153, 'selected_param': 100.0, 'mae': 3.562318845512041, 'rmse': 4.488241324690821, 'r2': 0.12579547952704484, 'pearson': 0.38393521252994617}

logs/clinical_medicalnet_frozen.log ADDED Viewed

	@@ -0,0 +1,27 @@

+[2026-05-20 21:42:59] start medicalnet_frozen gpu=0 ckpt=runs/foundation/medicalnet_frozen_mlp.pt
+/data/Albus/miniconda3/lib/python3.13/site-packages/sklearn/linear_model/_ridge.py:228: LinAlgWarning: An ill-conditioned matrix detected: slice 0 has rcond = 1.49720591480218e-08.
+  return linalg.solve(A, Xy, assume_a="pos", overwrite_a=True).T
+/data/Albus/miniconda3/lib/python3.13/site-packages/sklearn/linear_model/_ridge.py:228: LinAlgWarning: An ill-conditioned matrix detected: slice 0 has rcond = 4.5439186635576334e-08.
+  return linalg.solve(A, Xy, assume_a="pos", overwrite_a=True).T
+/data/Albus/miniconda3/lib/python3.13/site-packages/sklearn/linear_model/_ridge.py:228: LinAlgWarning: An ill-conditioned matrix detected: slice 0 has rcond = 1.49720591480218e-08.
+  return linalg.solve(A, Xy, assume_a="pos", overwrite_a=True).T
+/data/Albus/miniconda3/lib/python3.13/site-packages/sklearn/linear_model/_ridge.py:228: LinAlgWarning: An ill-conditioned matrix detected: slice 0 has rcond = 4.5439186635576334e-08.
+  return linalg.solve(A, Xy, assume_a="pos", overwrite_a=True).T
+/data/Albus/miniconda3/lib/python3.13/site-packages/sklearn/linear_model/_ridge.py:228: LinAlgWarning: An ill-conditioned matrix detected: slice 0 has rcond = 1.3947890842302968e-08.
+  return linalg.solve(A, Xy, assume_a="pos", overwrite_a=True).T
+/data/Albus/miniconda3/lib/python3.13/site-packages/sklearn/linear_model/_ridge.py:228: LinAlgWarning: An ill-conditioned matrix detected: slice 0 has rcond = 4.5870219622656805e-08.
+  return linalg.solve(A, Xy, assume_a="pos", overwrite_a=True).T
+/data/Albus/miniconda3/lib/python3.13/site-packages/sklearn/linear_model/_ridge.py:228: LinAlgWarning: An ill-conditioned matrix detected: slice 0 has rcond = 1.4620239241480704e-08.
+  return linalg.solve(A, Xy, assume_a="pos", overwrite_a=True).T
+/data/Albus/miniconda3/lib/python3.13/site-packages/sklearn/linear_model/_ridge.py:228: LinAlgWarning: An ill-conditioned matrix detected: slice 0 has rcond = 4.5366498113708076e-08.
+  return linalg.solve(A, Xy, assume_a="pos", overwrite_a=True).T
+checkpoint=runs/foundation/medicalnet_frozen_mlp.pt
+wrote=runs/clinical/medicalnet_frozen_clinical_probe.csv
+{'task': 'clinical_label_3way', 'type': 'classification', 'n_train': 710, 'n_val': 152, 'n_test': 153, 'selected_param': 3.0, 'accuracy': 0.5098039215686274, 'balanced_accuracy': 0.6004565093339855, 'macro_f1': 0.5237936087251156, 'auroc': 0.7566618222435709}
+{'task': 'ad_vs_cn', 'type': 'classification', 'n_train': 332, 'n_val': 69, 'n_test': 59, 'selected_param': 10.0, 'accuracy': 0.847457627118644, 'balanced_accuracy': 0.8471264367816091, 'macro_f1': 0.8472821397756687, 'auroc': 0.9287356321839081}
+{'task': 'pmci_vs_smci', 'type': 'classification', 'n_train': 269, 'n_val': 51, 'n_test': 69, 'selected_param': 1.0, 'accuracy': 0.7536231884057971, 'balanced_accuracy': 0.7087264150943396, 'macro_f1': 0.6861118544286862, 'auroc': 0.7193396226415094}
+{'task': 'mmse', 'type': 'regression', 'n_train': 710, 'n_val': 152, 'n_test': 153, 'selected_param': 0.1, 'mae': 1.6980790281607434, 'rmse': 2.0698075362441353, 'r2': 0.39741766603509965, 'pearson': 0.6306824161848564}
+{'task': 'cdrsb', 'type': 'regression', 'n_train': 710, 'n_val': 152, 'n_test': 153, 'selected_param': 0.1, 'mae': 0.9332610976462271, 'rmse': 1.2408694149810637, 'r2': 0.4602913941112865, 'pearson': 0.6807554704991381}
+{'task': 'adas13', 'type': 'regression', 'n_train': 707, 'n_val': 151, 'n_test': 148, 'selected_param': 0.1, 'mae': 5.613972025948602, 'rmse': 6.89187601041344, 'r2': 0.45884119765611253, 'pearson': 0.6829717043712142}
+{'task': 'faq', 'type': 'regression', 'n_train': 704, 'n_val': 152, 'n_test': 153, 'selected_param': 0.03, 'mae': 4.200754661186068, 'rmse': 5.710462298860524, 'r2': 0.2874450721859123, 'pearson': 0.553097226301054}
+[2026-05-20 21:43:42] done medicalnet_frozen

logs/clinical_queue_gpu0_v2.log ADDED Viewed

	@@ -0,0 +1,7 @@

+[2026-05-20 23:44:05] start remap_pet gpu=0
+[2026-05-20 23:44:05] done remap_pet
+[2026-05-20 23:44:05] start medicalnet_frozen gpu=0
+[2026-05-20 23:44:05] done medicalnet_frozen
+[2026-05-20 23:44:05] start brainiac_frozen gpu=0
+[2026-05-20 23:44:06] done brainiac_frozen
+[2026-05-20 23:44:06] GPU0 queue DONE

logs/download_swinunetr.log ADDED Viewed

	@@ -0,0 +1,344 @@

+--2026-05-19 23:01:19--  https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/model_swinvit.pt
+Resolving github.com (github.com)... 140.82.116.4
+Connecting to github.com (github.com)|140.82.116.4|:443... connected.
+HTTP request sent, awaiting response... 302 Found
+Location: https://release-assets.githubusercontent.com/github-production-release-asset/366729051/c7bc9f02-a8fb-4527-b311-e308fce79182?sp=r&sv=2018-11-09&sr=b&spr=https&se=2026-05-19T15%3A56%3A10Z&rscd=attachment%3B+filename%3Dmodel_swinvit.pt&rsct=application%2Foctet-stream&skoid=96c2d410-5711-43a1-aedd-ab1947aa7ab0&sktid=398a6654-997b-47e9-b12b-9515b896b4de&skt=2026-05-19T14%3A55%3A27Z&ske=2026-05-19T15%3A56%3A10Z&sks=b&skv=2018-11-09&sig=3Vb6kLPe6TMVkIDXN0GUxCb%2BVofmkob2lFAG9kfsFyA%3D&jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmVsZWFzZS1hc3NldHMuZ2l0aHVidXNlcmNvbnRlbnQuY29tIiwia2V5Ijoia2V5MSIsImV4cCI6MTc3OTIwNjQ4MCwibmJmIjoxNzc5MjAyODgwLCJwYXRoIjoicmVsZWFzZWFzc2V0cHJvZHVjdGlvbi5ibG9iLmNvcmUud2luZG93cy5uZXQifQ.SnZvQg3UxoaNsRNa5q-kwR7-6w1q8iEQ4TcKE9g5bN4&response-content-disposition=attachment%3B%20filename%3Dmodel_swinvit.pt&response-content-type=application%2Foctet-stream [following]
+--2026-05-19 23:01:20--  https://release-assets.githubusercontent.com/github-production-release-asset/366729051/c7bc9f02-a8fb-4527-b311-e308fce79182?sp=r&sv=2018-11-09&sr=b&spr=https&se=2026-05-19T15%3A56%3A10Z&rscd=attachment%3B+filename%3Dmodel_swinvit.pt&rsct=application%2Foctet-stream&skoid=96c2d410-5711-43a1-aedd-ab1947aa7ab0&sktid=398a6654-997b-47e9-b12b-9515b896b4de&skt=2026-05-19T14%3A55%3A27Z&ske=2026-05-19T15%3A56%3A10Z&sks=b&skv=2018-11-09&sig=3Vb6kLPe6TMVkIDXN0GUxCb%2BVofmkob2lFAG9kfsFyA%3D&jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmVsZWFzZS1hc3NldHMuZ2l0aHVidXNlcmNvbnRlbnQuY29tIiwia2V5Ijoia2V5MSIsImV4cCI6MTc3OTIwNjQ4MCwibmJmIjoxNzc5MjAyODgwLCJwYXRoIjoicmVsZWFzZWFzc2V0cHJvZHVjdGlvbi5ibG9iLmNvcmUud2luZG93cy5uZXQifQ.SnZvQg3UxoaNsRNa5q-kwR7-6w1q8iEQ4TcKE9g5bN4&response-content-disposition=attachment%3B%20filename%3Dmodel_swinvit.pt&response-content-type=application%2Foctet-stream
+Resolving release-assets.githubusercontent.com (release-assets.githubusercontent.com)... 185.199.109.133, 185.199.111.133, 185.199.108.133, ...
+Connecting to release-assets.githubusercontent.com (release-assets.githubusercontent.com)|185.199.109.133|:443... connected.
+HTTP request sent, awaiting response... 200 OK
+Length: 411162269 (392M) [application/octet-stream]
+Saving to: ‘pretrained/swinunetr/model_swinvit.pt’
+     0K .......... .......... .......... .......... ..........  0%  209K 31m59s
+    50K .......... .......... .......... .......... ..........  0%  135K 40m47s
+   100K .......... .......... .......... .......... ..........  0%  293K 34m47s
+   150K .......... .......... .......... .......... ..........  0% 72.9K 49m1s
+   200K .......... .......... .......... .......... ..........  0%  347K 43m3s
+   250K .......... .......... .......... .......... ..........  0% 1.27M 36m44s
+   300K .......... .......... .......... .......... ..........  0%  127K 39m0s
+   350K .......... .......... .......... .......... ..........  0% 97.1K 42m44s
+   400K .......... .......... .......... .......... ..........  0% 88.8K 46m21s
+   450K .......... .......... .......... .......... ..........  0%  207K 44m56s
+   500K .......... .......... .......... .......... ..........  0% 63.2K 50m28s
+   550K .......... .......... .......... .......... ..........  0% 96.4K 52m2s
+   600K .......... .......... .......... .......... ..........  0% 70.1K 55m21s
+   650K .......... .......... .......... .......... ..........  0% 54.0K 60m13s
+   700K .......... .......... .......... .......... ..........  0% 51.8K 64m48s
+   750K .......... .......... .......... .......... ..........  0% 29.7K 74m48s
+   800K .......... .......... .......... .......... ..........  0% 38.0K 80m44s
+   850K .......... .......... .......... .......... ..........  0% 44.0K 84m40s
+   900K .......... .......... .......... .......... ..........  0% 37.9K 89m28s
+   950K .......... .......... .......... .......... ..........  0% 48.3K 91m53s
+  1000K .......... .......... .......... .......... ..........  0% 41.3K 95m11s
+  1050K .......... .......... .......... .......... ..........  0% 32.6K 1h40m
+  1100K .......... .......... .......... .......... ..........  0% 25.4K 1h47m
+  1150K .......... .......... .......... .......... ..........  0% 17.5K 1h58m
+  1200K .......... .......... .......... .......... ..........  0% 17.1K 2h9m
+  1250K .......... .......... .......... .......... ..........  0% 13.4K 2h23m
+  1300K .......... .......... .......... .......... ..........  0% 18.6K 2h31m
+  1350K .......... .......... .......... .......... ..........  0% 29.0K 2h34m
+  1400K .......... .......... .......... .......... ..........  0% 45.5K 2h34m
+  1450K .......... .......... .......... .......... ..........  0% 55.3K 2h32m
+  1500K .......... .......... .......... .......... ..........  0% 62.9K 2h31m
+  1550K .......... .......... .......... .......... ..........  0% 29.4K 2h33m
+  1600K .......... .......... .......... .......... ..........  0% 52.4K 2h32m
+  1650K .......... .......... .......... .......... ..........  0% 63.7K 2h31m
+  1700K .......... .......... .......... .......... ..........  0% 75.9K 2h29m
+  1750K .......... .......... .......... .......... ..........  0% 58.0K 2h28m
+  1800K .......... .......... .......... .......... ..........  0% 61.9K 2h27m
+  1850K .......... .......... .......... .......... ..........  0% 83.6K 2h25m
+  1900K .......... .......... .......... .......... ..........  0% 47.7K 2h25m
+  1950K .......... .......... .......... .......... ..........  0% 38.0K 2h26m
+  2000K .......... .......... .......... .......... ..........  0% 45.4K 2h26m
+  2050K .......... .......... .......... .......... ..........  0% 60.1K 2h25m
+  2100K .......... .......... .......... .......... ..........  0% 38.0K 2h26m
+  2150K .......... .......... .......... .......... ..........  0% 39.3K 2h26m
+  2200K .......... .......... .......... .......... ..........  0% 20.3K 2h30m
+  2250K .......... .......... .......... .......... ..........  0% 23.5K 2h33m
+  2300K .......... .......... .......... .......... ..........  0% 23.1K 2h36m
+  2350K .......... .......... .......... .......... ..........  0% 19.3K 2h40m
+  2400K .......... .......... .......... .......... ..........  0% 45.8K 2h39m
+  2450K .......... .......... .......... .......... ..........  0% 50.1K 2h39m
+  2500K .......... .......... .......... .......... ..........  0% 50.0K 2h38m
+  2550K .......... .......... .......... .......... ..........  0% 45.2K 2h38m
+  2600K .......... .......... .......... .......... ..........  0% 38.7K 2h38m
+  2650K .......... .......... .......... .......... ..........  0% 39.3K 2h38m
+  2700K .......... .......... .......... .......... ..........  0% 25.8K 2h40m
+  2750K .......... .......... .......... .......... ..........  0% 19.0K 2h44m
+  2800K .......... .......... .......... .......... ..........  0% 32.5K 2h44m
+  2850K .......... .......... .......... .......... ..........  0% 30.3K 2h45m
+  2900K .......... .......... .......... .......... ..........  0% 35.0K 2h46m
+  2950K .......... .......... .......... .......... ..........  0% 36.5K 2h46m
+  3000K .......... .......... .......... .......... ..........  0% 33.9K 2h46m
+  3050K .......... .......... .......... .......... ..........  0% 43.9K 2h46m
+  3100K .......... .......... .......... .......... ..........  0% 44.3K 2h46m
+  3150K .......... .......... .......... .......... ..........  0% 31.8K 2h46m
+  3200K .......... .......... .......... .......... ..........  0% 37.7K 2h46m
+  3250K .......... .......... .......... .......... ..........  0% 32.3K 2h47m
+  3300K .......... .......... .......... .......... ..........  0% 18.6K 2h50m
+  3350K .......... .......... .......... .......... ..........  0% 36.3K 2h50m
+  3400K .......... .......... .......... .......... ..........  0% 66.1K 2h49m
+  3450K .......... .......... .......... .......... ..........  0% 64.5K 2h48m
+  3500K .......... .......... .......... .......... ..........  0%  294K 2h46m
+  3550K .......... .......... .......... .......... ..........  0% 64.9K 2h45m
+  3600K .......... .......... .......... .......... ..........  0%  125K 2h43m
+  3650K .......... .......... .......... .......... ..........  0%  107K 2h42m
+  3700K .......... .......... .......... .......... ..........  0% 75.7K 2h41m
+  3750K .......... .......... .......... .......... ..........  0% 91.9K 2h40m
+  3800K .......... .......... .......... .......... ..........  0% 62.1K 2h39m
+  3850K .......... .......... .......... .......... ..........  0% 52.1K 2h39m
+  3900K .......... .......... .......... .......... ..........  0% 47.0K 2h38m
+  3950K .......... .......... .......... .......... ..........  0% 26.9K 2h40m
+  4000K .......... .......... .......... .......... ..........  1% 26.8K 2h41m
+  4050K .......... .......... .......... .......... ..........  1% 26.9K 2h42m
+  4100K .......... .......... .......... .......... ..........  1% 26.5K 2h43m
+  4150K .......... .......... .......... .......... ..........  1% 29.3K 2h43m
+  4200K .......... .......... .......... .......... ..........  1% 39.8K 2h43m
+  4250K .......... .......... .......... .......... ..........  1% 39.2K 2h43m
+  4300K .......... .......... .......... .......... ..........  1% 50.6K 2h43m
+  4350K .......... .......... .......... .......... ..........  1% 44.1K 2h43m
+  4400K .......... .......... .......... .......... ..........  1% 44.9K 2h43m
+  4450K .......... .......... .......... .......... ..........  1% 27.1K 2h44m
+  4500K .......... .......... .......... .......... ..........  1% 29.3K 2h44m
+  4550K .......... .......... .......... .......... ..........  1% 27.9K 2h45m
+  4600K .......... .......... .......... .......... ..........  1% 34.0K 2h45m
+  4650K .......... .......... .......... .......... ..........  1% 46.0K 2h45m
+  4700K .......... .......... .......... .......... ..........  1% 48.4K 2h45m
+  4750K .......... .......... .......... .......... ..........  1% 24.4K 2h46m
+  4800K .......... .......... .......... .......... ..........  1% 31.9K 2h46m
+  4850K .......... .......... .......... .......... ..........  1% 32.3K 2h47m
+  4900K .......... .......... .......... .......... ..........  1% 35.0K 2h47m
+  4950K .......... .......... .......... .......... ..........  1% 26.0K 2h48m
+  5000K .......... .......... .......... .......... ..........  1% 36.9K 2h48m
+  5050K .......... .......... .......... .......... ..........  1% 56.6K 2h47m
+  5100K .......... .......... .......... .......... ..........  1% 56.5K 2h47m
+  5150K .......... .......... .......... .......... ..........  1% 41.2K 2h47m
+  5200K .......... .......... .......... .......... ..........  1% 54.4K 2h46m
+  5250K .......... .......... .......... .......... ..........  1% 31.9K 2h46m
+  5300K .......... .......... .......... .......... ..........  1% 26.1K 2h47m
+  5350K .......... .......... .......... .......... ..........  1% 42.4K 2h47m
+  5400K .......... .......... .......... .......... ..........  1% 34.8K 2h47m
+  5450K .......... .......... .......... .......... ..........  1% 34.6K 2h47m
+  5500K .......... .......... .......... .......... ..........  1% 39.4K 2h47m
+  5550K .......... .......... .......... .......... ..........  1% 20.8K 2h49m
+  5600K .......... .......... .......... .......... ..........  1% 25.8K 2h49m
+  5650K .......... .......... .......... .......... ..........  1% 29.4K 2h50m
+  5700K .......... .......... .......... .......... ..........  1% 26.4K 2h51m
+  5750K .......... .......... .......... .......... ..........  1% 23.5K 2h52m
+  5800K .......... .......... .......... .......... ..........  1% 39.4K 2h51m
+  5850K .......... .......... .......... .......... ..........  1% 49.6K 2h51m
+  5900K .......... .......... .......... .......... ..........  1% 51.1K 2h51m
+  5950K .......... .......... .......... .......... ..........  1% 41.4K 2h51m
+  6000K .......... .......... .......... .......... ..........  1% 45.9K 2h50m
+  6050K .......... .......... .......... .......... ..........  1% 49.8K 2h50m
+  6100K .......... .......... .......... .......... ..........  1% 46.3K 2h50m
+  6150K .......... .......... .......... .......... ..........  1% 55.1K 2h49m
+  6200K .......... .......... .......... .......... ..........  1% 47.4K 2h49m
+  6250K .......... .......... .......... .......... ..........  1% 57.7K 2h49m
+  6300K .......... .......... .......... .......... ..........  1% 55.6K 2h48m
+  6350K .......... .......... .......... .......... ..........  1% 27.7K 2h49m
+  6400K .......... .......... .......... .......... ..........  1% 42.7K 2h49m
+  6450K .......... .......... .......... .......... ..........  1% 60.1K 2h48m
+  6500K .......... .......... .......... .......... ..........  1% 37.9K 2h48m
+  6550K .......... .......... .......... .......... ..........  1% 34.0K 2h48m
+  6600K .......... .......... .......... .......... ..........  1% 43.8K 2h48m
+  6650K .......... .......... .......... .......... ..........  1% 31.8K 2h48m
+  6700K .......... .......... .......... .......... ..........  1% 31.7K 2h49m
+  6750K .......... .......... .......... .......... ..........  1% 21.1K 2h50m
+  6800K .......... .......... .......... .......... ..........  1% 29.7K 2h50m
+  6850K .......... .......... .......... .......... ..........  1% 34.7K 2h50m
+  6900K .......... .......... .......... .......... ..........  1% 18.6K 2h51m
+  6950K .......... .......... .......... .......... ..........  1% 20.5K 2h53m
+  7000K .......... .......... .......... .......... ..........  1% 24.5K 2h53m
+  7050K .......... .......... .......... .......... ..........  1% 30.3K 2h53m
+  7100K .......... .......... .......... .......... ..........  1% 42.9K 2h53m
+  7150K .......... .......... .......... .......... ..........  1% 28.0K 2h54m
+  7200K .......... .......... .......... .......... ..........  1% 38.3K 2h54m
+  7250K .......... .......... .......... .......... ..........  1% 37.8K 2h54m
+  7300K .......... .......... .......... .......... ..........  1% 40.1K 2h54m
+  7350K .......... .......... .......... .......... ..........  1% 32.8K 2h54m
+  7400K .......... .......... .......... .......... ..........  1% 29.5K 2h54m
+  7450K .......... .......... .......... .......... ..........  1% 37.9K 2h54m
+  7500K .......... .......... .......... .......... ..........  1% 42.3K 2h54m
+  7550K .......... .......... .......... .......... ..........  1% 28.1K 2h54m
+  7600K .......... .......... .......... .......... ..........  1% 44.1K 2h54m
+  7650K .......... .......... .......... .......... ..........  1% 49.9K 2h54m
+  7700K .......... .......... .......... .......... ..........  1% 63.4K 2h53m
+  7750K .......... .......... .......... .......... ..........  1% 35.1K 2h53m
+  7800K .......... .......... .......... .......... ..........  1% 29.7K 2h54m
+  7850K .......... .......... .......... .......... ..........  1% 40.5K 2h53m
+  7900K .......... .......... .......... .......... ..........  1% 42.5K 2h53m
+  7950K .......... .......... .......... .......... ..........  1% 30.1K 2h54m
+  8000K .......... .......... .......... .......... ..........  2% 51.1K 2h53m
+  8050K .......... .......... .......... .......... ..........  2% 44.2K 2h53m
+  8100K .......... .......... .......... .......... ..........  2% 39.2K 2h53m
+  8150K .......... .......... .......... .......... ..........  2% 41.8K 2h53m
+  8200K .......... .......... .......... .......... ..........  2% 37.2K 2h53m
+  8250K .......... .......... .......... .......... ..........  2% 43.0K 2h53m
+  8300K .......... .......... .......... .......... ..........  2% 38.5K 2h53m
+  8350K .......... .......... .......... .......... ..........  2% 22.9K 2h53m
+  8400K .......... .......... .......... .......... ..........  2% 43.4K 2h53m
+  8450K .......... .......... .......... .......... ..........  2% 55.4K 2h53m
+  8500K .......... .......... .......... .......... ..........  2% 39.3K 2h53m
+  8550K .......... .......... .......... .......... ..........  2% 39.2K 2h53m
+  8600K .......... .......... .......... .......... ..........  2% 47.3K 2h53m
+  8650K .......... .......... .......... .......... ..........  2% 27.2K 2h53m
+  8700K .......... .......... .......... .......... ..........  2% 23.1K 2h53m
+  8750K .......... .......... .......... .......... ..........  2% 21.0K 2h54m
+  8800K .......... .......... .......... .......... ..........  2% 35.6K 2h54m
+  8850K .......... .......... .......... .......... ..........  2% 34.2K 2h54m
+  8900K .......... .......... .......... .......... ..........  2% 22.7K 2h55m
+  8950K .......... .......... .......... .......... ..........  2% 30.4K 2h55m
+  9000K .......... .......... .......... .......... ..........  2% 26.5K 2h56m
+  9050K .......... .......... .......... .......... ..........  2% 29.8K 2h56m
+  9100K .......... .......... .......... .......... ..........  2% 32.6K 2h56m
+  9150K .......... .......... .......... .......... ..........  2% 32.9K 2h56m
+  9200K .......... .......... .......... .......... ..........  2% 51.7K 2h56m
+  9250K .......... .......... .......... .......... ..........  2% 64.9K 2h55m
+  9300K .......... .......... .......... .......... ..........  2% 78.6K 2h55m
+  9350K .......... .......... .......... .......... ..........  2% 64.0K 2h54m
+  9400K .......... .......... .......... .......... ..........  2% 66.1K 2h54m
+  9450K .......... .......... .......... .......... ..........  2% 53.7K 2h54m
+  9500K .......... .......... .......... .......... ..........  2% 40.5K 2h53m
+  9550K .......... .......... .......... .......... ..........  2% 34.1K 2h54m
+  9600K .......... .......... .......... .......... ..........  2% 31.0K 2h54m
+  9650K .......... .......... .......... .......... ..........  2% 37.2K 2h54m
+  9700K .......... .......... .......... .......... ..........  2% 34.9K 2h54m
+  9750K .......... .......... .......... .......... ..........  2% 29.5K 2h54m
+  9800K .......... .......... .......... .......... ..........  2% 28.7K 2h54m
+  9850K .......... .......... .......... .......... ..........  2% 32.7K 2h54m
+  9900K .......... .......... .......... .......... ..........  2% 37.6K 2h54m
+  9950K .......... .......... .......... .......... ..........  2% 36.8K 2h54m
+ 10000K .......... .......... .......... .......... ..........  2% 61.6K 2h54m
+ 10050K .......... .......... .......... .......... ..........  2% 69.5K 2h54m
+ 10100K .......... .......... .......... .......... ..........  2% 64.1K 2h53m
+ 10150K .......... .......... .......... .......... ..........  2% 88.8K 2h53m
+ 10200K .......... .......... .......... .......... ..........  2% 40.9K 2h53m
+ 10250K .......... .......... .......... .......... ..........  2% 52.1K 2h52m
+ 10300K .......... .......... .......... .......... ..........  2% 54.7K 2h52m
+ 10350K .......... .......... .......... .......... ..........  2% 54.6K 2h52m
+ 10400K .......... .......... .......... .......... ..........  2% 29.8K 2h52m
+ 10450K .......... .......... .......... .......... ..........  2% 68.2K 2h52m
+ 10500K .......... .......... .......... .......... ..........  2% 35.5K 2h52m
+ 10550K .......... .......... .......... .......... ..........  2% 46.8K 2h51m
+ 10600K .......... .......... .......... .......... ..........  2% 29.6K 2h52m
+ 10650K .......... .......... .......... .......... ..........  2% 34.6K 2h52m
+ 10700K .......... .......... .......... .......... ..........  2% 34.1K 2h52m
+ 10750K .......... .......... .......... .......... ..........  2% 15.3K 2h53m
+ 10800K .......... .......... .......... .......... ..........  2% 24.5K 2h53m
+ 10850K .......... .......... .......... .......... ..........  2% 23.9K 2h54m
+ 10900K .......... .......... .......... .......... ..........  2% 15.5K 2h55m
+ 10950K .......... .......... .......... .......... ..........  2% 32.1K 2h55m
+ 11000K .......... .......... .......... .......... ..........  2% 31.3K 2h55m
+ 11050K .......... .......... .......... .......... ..........  2% 24.7K 2h55m
+ 11100K .......... .......... .......... .......... ..........  2% 34.6K 2h55m
+ 11150K .......... .......... .......... .......... ..........  2% 26.2K 2h56m
+ 11200K .......... .......... .......... .......... ..........  2% 45.1K 2h56m
+ 11250K .......... .......... .......... .......... ..........  2% 35.4K 2h56m
+ 11300K .......... .......... .......... .......... ..........  2%  100K 2h55m
+ 11350K .......... .......... .......... .......... ..........  2% 60.6K 2h55m
+ 11400K .......... .......... .......... .......... ..........  2% 69.4K 2h54m
+ 11450K .......... .......... .......... .......... ..........  2% 69.9K 2h54m
+ 11500K .......... .......... .......... .......... ..........  2% 84.5K 2h54m
+ 11550K .......... .......... .......... .......... ..........  2% 56.9K 2h53m
+ 11600K .......... .......... .......... .......... ..........  2% 81.8K 2h53m
+ 11650K .......... .......... .......... .......... ..........  2% 73.5K 2h52m
+ 11700K .......... .......... .......... .......... ..........  2% 57.6K 2h52m
+ 11750K .......... .......... .......... .......... ..........  2% 74.3K 2h52m
+ 11800K .......... .......... .......... .......... ..........  2% 45.9K 2h52m
+ 11850K .......... .......... .......... .......... ..........  2% 48.0K 2h51m
+ 11900K .......... .......... .......... .......... ..........  2% 53.9K 2h51m
+ 11950K .......... .......... .......... .......... ..........  2% 50.3K 2h51m
+ 12000K .......... .......... .......... .......... ..........  3% 73.9K 2h51m
+ 12050K .......... .......... .......... .......... ..........  3% 91.9K 2h50m
+ 12100K .......... .......... .......... .......... ..........  3% 70.9K 2h50m
+ 12150K .......... .......... .......... .......... ..........  3% 87.0K 2h49m
+ 12200K .......... .......... .......... .......... ..........  3% 66.2K 2h49m
+ 12250K .......... .......... .......... .......... ..........  3% 61.3K 2h49m
+ 12300K .......... .......... .......... .......... ..........  3% 49.1K 2h49m
+ 12350K .......... .......... .......... .......... ..........  3% 34.1K 2h49m
+ 12400K .......... .......... .......... .......... ..........  3% 67.9K 2h48m
+ 12450K .......... .......... .......... .......... ..........  3% 65.7K 2h48m
+ 12500K .......... .......... .......... .......... ..........  3% 54.3K 2h48m
+ 12550K .......... .......... .......... .......... ..........  3% 50.6K 2h48m
+ 12600K .......... .......... .......... .......... ..........  3% 30.2K 2h48m
+ 12650K .......... .......... .......... .......... ..........  3% 26.8K 2h48m
+ 12700K .......... .......... .......... .......... ..........  3% 28.9K 2h48m
+ 12750K .......... .......... .......... .......... ..........  3% 19.1K 2h49m
+ 12800K .......... .......... .......... .......... ..........  3% 42.4K 2h49m
+ 12850K .......... .......... .......... .......... ..........  3% 45.2K 2h49m
+ 12900K .......... .......... .......... .......... ..........  3% 44.7K 2h49m
+ 12950K .......... .......... .......... .......... ..........  3% 38.5K 2h49m
+ 13000K .......... .......... .......... .......... ..........  3% 47.8K 2h48m
+ 13050K .......... .......... .......... .......... ..........  3% 50.4K 2h48m
+ 13100K .......... .......... .......... .......... ..........  3% 36.1K 2h48m
+ 13150K .......... .......... .......... .......... ..........  3% 23.1K 2h49m
+ 13200K .......... .......... .......... .......... ..........  3% 34.8K 2h49m
+ 13250K .......... .......... .......... .......... ..........  3% 32.3K 2h49m
+ 13300K .......... .......... .......... .......... ..........  3% 41.4K 2h49m
+ 13350K .......... .......... .......... .......... ..........  3% 42.5K 2h49m
+ 13400K .......... .......... .......... .......... ..........  3% 42.3K 2h49m
+ 13450K .......... .......... .......... .......... ..........  3% 31.1K 2h49m
+ 13500K .......... .......... .......... .......... ..........  3% 48.5K 2h49m
+ 13550K .......... .......... .......... .......... ..........  3% 44.7K 2h48m
+ 13600K .......... .......... .......... .......... ..........  3% 59.4K 2h48m
+ 13650K .......... .......... .......... .......... ..........  3% 88.4K 2h48m
+ 13700K .......... .......... .......... .......... ..........  3% 67.6K 2h48m
+ 13750K .......... .......... .......... .......... ..........  3% 47.7K 2h47m
+ 13800K .......... .......... .......... .......... ..........  3% 48.3K 2h47m
+ 13850K .......... .......... .......... .......... ..........  3% 36.7K 2h47m
+ 13900K .......... .......... .......... .......... ..........  3% 52.5K 2h47m
+ 13950K .......... .......... .......... .......... ..........  3% 26.0K 2h47m
+ 14000K .......... .......... .......... .......... ..........  3% 32.1K 2h47m
+ 14050K .......... .......... .......... .......... ..........  3% 41.1K 2h47m
+ 14100K .......... .......... .......... .......... ..........  3% 47.7K 2h47m
+ 14150K .......... .......... .......... .......... ..........  3% 49.6K 2h47m
+ 14200K .......... .......... .......... .......... ..........  3% 64.4K 2h47m
+ 14250K .......... .......... .......... .......... ..........  3% 53.1K 2h47m
+ 14300K .......... .......... .......... .......... ..........  3% 47.5K 2h47m
+ 14350K .......... .......... .......... .......... ..........  3% 35.2K 2h47m
+ 14400K .......... .......... .......... .......... ..........  3% 71.7K 2h46m
+ 14450K .......... .......... .......... .......... ..........  3% 49.3K 2h46m
+ 14500K .......... .......... .......... .......... ..........  3% 42.6K 2h46m
+ 14550K .......... .......... .......... .......... ..........  3% 41.6K 2h46m
+ 14600K .......... .......... .......... .......... ..........  3% 36.2K 2h46m
+ 14650K .......... .......... .......... .......... ..........  3% 32.6K 2h46m
+ 14700K .......... .......... .......... .......... ..........  3% 21.6K 2h47m
+ 14750K .......... .......... .......... .......... ..........  3% 24.1K 2h47m
+ 14800K .......... .......... .......... .......... ..........  3% 43.1K 2h47m
+ 14850K .......... .......... .......... .......... ..........  3% 25.0K 2h47m
+ 14900K .......... .......... .......... .......... ..........  3% 34.4K 2h47m
+ 14950K .......... .......... .......... .......... ..........  3% 34.7K 2h47m
+ 15000K .......... .......... .......... .......... ..........  3% 47.3K 2h47m
+ 15050K .......... .......... .......... .......... ..........  3% 51.7K 2h47m
+ 15100K .......... .......... .......... .......... ..........  3% 43.2K 2h47m
+ 15150K .......... .......... .......... .......... ..........  3% 30.9K 2h47m
+ 15200K .......... .......... .......... .......... ..........  3% 37.4K 2h47m
+ 15250K .......... .......... .......... .......... ..........  3% 34.3K 2h47m
+ 15300K .......... .......... .......... .......... ..........  3% 35.4K 2h47m
+ 15350K .......... .......... .......... .......... ..........  3% 39.1K 2h47m
+ 15400K .......... .......... .......... .......... ..........  3% 35.3K 2h47m
+ 15450K .......... .......... .......... .......... ..........  3% 27.2K 2h47m
+ 15500K .......... .......... .......... .......... ..........  3% 41.8K 2h47m
+ 15550K .......... .......... .......... .......... ..........  3% 35.0K 2h47m
+ 15600K .......... .......... .......... .......... ..........  3% 37.3K 2h47m
+ 15650K .......... .......... .......... .......... ..........  3% 24.5K 2h47m
+ 15700K .......... .......... .......... .......... ..........  3% 34.2K 2h47m
+ 15750K .......... .......... .......... .......... ..........  3% 40.0K 2h47m
+ 15800K .......... .......... .......... .......... ..........  3% 30.3K 2h48m
+ 15850K .......... .......... .......... .......... ..........  3% 30.0K 2h48m
+ 15900K .......... .......... .......... .......... ..........  3% 33.5K 2h48m
+ 15950K .......... .......... .......... .......... ..........  3% 26.7K 2h48m
+ 16000K .......... .......... .......... .......... ..........  3% 40.8K 2h48m
+ 16050K .......... .......... .......... .......... ..........  4% 43.6K 2h48m
+ 16100K .......... .......... .......... .......... ..........  4% 45.0K 2h48m
+ 16150K .......... .......... .......... .......... ..........  4% 29.9K 2h48m
+ 16200K .......... .......... .......... .......... ..........  4% 34.3K 2h48m
+ 16250K .......... .......... .......... .......... ..........  4% 30.6K 2h48m
+ 16300K .......... .......... .......... .......... ..........  4% 47.0K 2h48m
+ 16350K .......... .......... .......... .......... ..........  4% 33.9K 2h48m
+ 16400K .......... .......... .......... .......... ..........  4% 46.6K 2h48m
+ 16450K .......... .......... .......... .......... ..........  4% 40.3K 2h48m
+ 16500K .......... .......... .......... .......... ..........  4% 30.5K 2h48m
+ 16550K .........

logs/eval_brainfm_frozen_clinicalbert_text_alignment_test.log ADDED Viewed

	@@ -0,0 +1,13 @@

+samples=153.000000
+pet_to_text_recall@1=0.026144
+pet_to_text_recall@5=0.183007
+pet_to_text_recall@10=0.320261
+pet_to_text_mrr=0.118863
+pet_to_text_median_rank=18.000000
+text_to_pet_recall@1=0.052288
+text_to_pet_recall@5=0.163399
+text_to_pet_recall@10=0.300654
+text_to_pet_mrr=0.130506
+text_to_pet_median_rank=24.000000
+retrieved_text_low_overlap=0.698039
+retrieved_text_high_overlap=0.460131

logs/eval_brainiac_frozen_clinicalbert_text_alignment_test.log ADDED Viewed

	@@ -0,0 +1,15 @@

+<frozen importlib._bootstrap_external>:1325: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead.
+brainiac_missing_keys=['blocks.0.norm_cross_attn.weight', 'blocks.0.norm_cross_attn.bias', 'blocks.0.cross_attn.out_proj.weight', 'blocks.0.cross_attn.out_proj.bias', 'blocks.0.cross_attn.to_q.weight', 'blocks.0.cross_attn.to_k.weight', 'blocks.0.cross_attn.to_v.weight', 'blocks.1.norm_cross_attn.weight']
+samples=153.000000
+pet_to_text_recall@1=0.006536
+pet_to_text_recall@5=0.039216
+pet_to_text_recall@10=0.098039
+pet_to_text_mrr=0.042449
+pet_to_text_median_rank=60.000000
+text_to_pet_recall@1=0.006536
+text_to_pet_recall@5=0.045752
+text_to_pet_recall@10=0.098039
+text_to_pet_mrr=0.051439
+text_to_pet_median_rank=47.000000
+retrieved_text_low_overlap=0.658824
+retrieved_text_high_overlap=0.264052

logs/eval_medicalnet_frozen_clinicalbert_text_alignment_test.log ADDED Viewed

	@@ -0,0 +1,13 @@

+samples=153.000000
+pet_to_text_recall@1=0.019608
+pet_to_text_recall@5=0.143791
+pet_to_text_recall@10=0.261438
+pet_to_text_mrr=0.100858
+pet_to_text_median_rank=28.000000
+text_to_pet_recall@1=0.019608
+text_to_pet_recall@5=0.091503
+text_to_pet_recall@10=0.202614
+text_to_pet_mrr=0.082982
+text_to_pet_median_rank=27.000000
+retrieved_text_low_overlap=0.657516
+retrieved_text_high_overlap=0.435294

logs/eval_remap_pet_clinicalbert_text_alignment_b16_test.log ADDED Viewed

	@@ -0,0 +1,13 @@

+samples=153.000000
+pet_to_text_recall@1=0.098039
+pet_to_text_recall@5=0.392157
+pet_to_text_recall@10=0.509804
+pet_to_text_mrr=0.238607
+pet_to_text_median_rank=10.000000
+text_to_pet_recall@1=0.143791
+text_to_pet_recall@5=0.339869
+text_to_pet_recall@10=0.516340
+text_to_pet_mrr=0.247619
+text_to_pet_median_rank=10.000000
+retrieved_text_low_overlap=0.718954
+retrieved_text_high_overlap=0.577778

logs/eval_remap_pet_layer4_regonly_test.log ADDED Viewed

	@@ -0,0 +1,19 @@

+checkpoint=runs/foundation/remap_pet_layer4_regonly_best.pt
+manifest=metadata/splits/test.csv
+samples=153.000000
+mae=0.054897
+rmse=0.071004
+pearson=0.953775
+spearman=0.953489
+top5_high_overlap=0.673203
+top5_low_overlap=0.800000
+pet_to_suvr_recall@1=0.006536
+pet_to_suvr_recall@5=0.039216
+pet_to_suvr_recall@10=0.078431
+pet_to_suvr_mrr=0.040011
+pet_to_suvr_median_rank=76.000000
+suvr_to_pet_recall@1=0.006536
+suvr_to_pet_recall@5=0.013072
+suvr_to_pet_recall@10=0.052288
+suvr_to_pet_mrr=0.031512
+suvr_to_pet_median_rank=83.000000

logs/medicalnet_e2e_mlp_20260514_120820.log ADDED Viewed

	@@ -0,0 +1,362 @@

+device=cuda backbone=medicalnet freeze=False train=710 val=152
+epoch=1 step=20/355 loss=1.7291
+epoch=1 step=40/355 loss=2.0697
+epoch=1 step=60/355 loss=1.3781
+epoch=1 step=80/355 loss=1.2936
+epoch=1 step=100/355 loss=1.1288
+epoch=1 step=120/355 loss=0.5669
+epoch=1 step=140/355 loss=0.5478
+epoch=1 step=160/355 loss=0.6675
+epoch=1 step=180/355 loss=0.4337
+epoch=1 step=200/355 loss=0.5617
+epoch=1 step=220/355 loss=0.6273
+epoch=1 step=240/355 loss=0.5123
+epoch=1 step=260/355 loss=0.3632
+epoch=1 step=280/355 loss=0.2594
+epoch=1 step=300/355 loss=0.2675
+epoch=1 step=320/355 loss=0.4442
+epoch=1 step=340/355 loss=0.7137
+epoch=1 train_loss=0.8704 val_loss=1.1125
+epoch=2 step=20/355 loss=0.4088
+epoch=2 step=40/355 loss=0.4540
+epoch=2 step=60/355 loss=0.6546
+epoch=2 step=80/355 loss=0.5718
+epoch=2 step=100/355 loss=0.6167
+epoch=2 step=120/355 loss=0.5142
+epoch=2 step=140/355 loss=0.7527
+epoch=2 step=160/355 loss=0.3024
+epoch=2 step=180/355 loss=0.2995
+epoch=2 step=200/355 loss=0.4137
+epoch=2 step=220/355 loss=0.3324
+epoch=2 step=240/355 loss=0.5955
+epoch=2 step=260/355 loss=0.3217
+epoch=2 step=280/355 loss=0.6049
+epoch=2 step=300/355 loss=0.1080
+epoch=2 step=320/355 loss=0.1326
+epoch=2 step=340/355 loss=0.6991
+epoch=2 train_loss=0.3565 val_loss=0.9938
+epoch=3 step=20/355 loss=0.0755
+epoch=3 step=40/355 loss=0.0457
+epoch=3 step=60/355 loss=0.4925
+epoch=3 step=80/355 loss=0.2098
+epoch=3 step=100/355 loss=0.0647
+epoch=3 step=120/355 loss=0.0376
+epoch=3 step=140/355 loss=0.3832
+epoch=3 step=160/355 loss=0.4781
+epoch=3 step=180/355 loss=0.0646
+epoch=3 step=200/355 loss=0.0353
+epoch=3 step=220/355 loss=0.6863
+epoch=3 step=240/355 loss=0.5207
+epoch=3 step=260/355 loss=0.0346
+epoch=3 step=280/355 loss=0.0676
+epoch=3 step=300/355 loss=0.0571
+epoch=3 step=320/355 loss=0.0431
+epoch=3 step=340/355 loss=1.1316
+epoch=3 train_loss=0.2423 val_loss=0.9443
+epoch=4 step=20/355 loss=0.2084
+epoch=4 step=40/355 loss=0.0371
+epoch=4 step=60/355 loss=0.4983
+epoch=4 step=80/355 loss=0.0408
+epoch=4 step=100/355 loss=0.1476
+epoch=4 step=120/355 loss=0.4777
+epoch=4 step=140/355 loss=0.0755
+epoch=4 step=160/355 loss=0.1086
+epoch=4 step=180/355 loss=0.0537
+epoch=4 step=200/355 loss=0.0370
+epoch=4 step=220/355 loss=0.1785
+epoch=4 step=240/355 loss=0.0284
+epoch=4 step=260/355 loss=0.2298
+epoch=4 step=280/355 loss=0.0362
+epoch=4 step=300/355 loss=0.1042
+epoch=4 step=320/355 loss=0.3428
+epoch=4 step=340/355 loss=0.0396
+epoch=4 train_loss=0.1701 val_loss=0.9392
+epoch=5 step=20/355 loss=0.6897
+epoch=5 step=40/355 loss=0.6286
+epoch=5 step=60/355 loss=0.0211
+epoch=5 step=80/355 loss=0.0195
+epoch=5 step=100/355 loss=0.0504
+epoch=5 step=120/355 loss=0.1279
+epoch=5 step=140/355 loss=0.0363
+epoch=5 step=160/355 loss=0.6442
+epoch=5 step=180/355 loss=0.0329
+epoch=5 step=200/355 loss=0.0792
+epoch=5 step=220/355 loss=0.1221
+epoch=5 step=240/355 loss=0.6071
+epoch=5 step=260/355 loss=0.1128
+epoch=5 step=280/355 loss=0.1639
+epoch=5 step=300/355 loss=0.3038
+epoch=5 step=320/355 loss=0.0998
+epoch=5 step=340/355 loss=0.0382
+epoch=5 train_loss=0.1378 val_loss=0.5826
+epoch=6 step=20/355 loss=0.0500
+epoch=6 step=40/355 loss=0.0480
+epoch=6 step=60/355 loss=0.0541
+epoch=6 step=80/355 loss=0.0763
+epoch=6 step=100/355 loss=0.0316
+epoch=6 step=120/355 loss=0.0415
+epoch=6 step=140/355 loss=0.0179
+epoch=6 step=160/355 loss=0.2815
+epoch=6 step=180/355 loss=0.1224
+epoch=6 step=200/355 loss=0.0416
+epoch=6 step=220/355 loss=0.2788
+epoch=6 step=240/355 loss=0.3295
+epoch=6 step=260/355 loss=0.0253
+epoch=6 step=280/355 loss=0.1750
+epoch=6 step=300/355 loss=0.0212
+epoch=6 step=320/355 loss=0.5720
+epoch=6 step=340/355 loss=0.0668
+epoch=6 train_loss=0.1022 val_loss=0.9072
+epoch=7 step=20/355 loss=0.4288
+epoch=7 step=40/355 loss=0.0241
+epoch=7 step=60/355 loss=0.0272
+epoch=7 step=80/355 loss=0.0230
+epoch=7 step=100/355 loss=0.1833
+epoch=7 step=120/355 loss=0.0244
+epoch=7 step=140/355 loss=0.1190
+epoch=7 step=160/355 loss=0.3262
+epoch=7 step=180/355 loss=0.0847
+epoch=7 step=200/355 loss=0.0306
+epoch=7 step=220/355 loss=0.0374
+epoch=7 step=240/355 loss=0.0371
+epoch=7 step=260/355 loss=0.0157
+epoch=7 step=280/355 loss=0.0116
+epoch=7 step=300/355 loss=0.0217
+epoch=7 step=320/355 loss=0.0558
+epoch=7 step=340/355 loss=0.0506
+epoch=7 train_loss=0.0894 val_loss=0.7226
+epoch=8 step=20/355 loss=0.0396
+epoch=8 step=40/355 loss=0.0211
+epoch=8 step=60/355 loss=0.0245
+epoch=8 step=80/355 loss=0.5736
+epoch=8 step=100/355 loss=0.0264
+epoch=8 step=120/355 loss=0.1206
+epoch=8 step=140/355 loss=0.1805
+epoch=8 step=160/355 loss=0.2731
+epoch=8 step=180/355 loss=0.0316
+epoch=8 step=200/355 loss=0.1357
+epoch=8 step=220/355 loss=0.0484
+epoch=8 step=240/355 loss=0.0244
+epoch=8 step=260/355 loss=0.0469
+epoch=8 step=280/355 loss=0.1649
+epoch=8 step=300/355 loss=0.0824
+epoch=8 step=320/355 loss=0.0186
+epoch=8 step=340/355 loss=0.0369
+epoch=8 train_loss=0.1007 val_loss=0.6244
+epoch=9 step=20/355 loss=0.0324
+epoch=9 step=40/355 loss=0.0187
+epoch=9 step=60/355 loss=0.0657
+epoch=9 step=80/355 loss=0.0193
+epoch=9 step=100/355 loss=0.0648
+epoch=9 step=120/355 loss=0.0373
+epoch=9 step=140/355 loss=0.0200
+epoch=9 step=160/355 loss=0.1999
+epoch=9 step=180/355 loss=0.0805
+epoch=9 step=200/355 loss=0.0152
+epoch=9 step=220/355 loss=0.0261
+epoch=9 step=240/355 loss=0.0184
+epoch=9 step=260/355 loss=0.0529
+epoch=9 step=280/355 loss=0.1735
+epoch=9 step=300/355 loss=0.7191
+epoch=9 step=320/355 loss=0.2836
+epoch=9 step=340/355 loss=0.0095
+epoch=9 train_loss=0.0882 val_loss=0.5627
+epoch=10 step=20/355 loss=0.0978
+epoch=10 step=40/355 loss=0.0373
+epoch=10 step=60/355 loss=0.0255
+epoch=10 step=80/355 loss=0.0288
+epoch=10 step=100/355 loss=0.0619
+epoch=10 step=120/355 loss=0.0408
+epoch=10 step=140/355 loss=0.0336
+epoch=10 step=160/355 loss=0.0645
+epoch=10 step=180/355 loss=0.0240
+epoch=10 step=200/355 loss=0.1750
+epoch=10 step=220/355 loss=0.0519
+epoch=10 step=240/355 loss=0.0281
+epoch=10 step=260/355 loss=0.0430
+epoch=10 step=280/355 loss=0.5299
+epoch=10 step=300/355 loss=0.0101
+epoch=10 step=320/355 loss=0.0183
+epoch=10 step=340/355 loss=0.0143
+epoch=10 train_loss=0.0777 val_loss=0.7069
+epoch=11 step=20/355 loss=0.0124
+epoch=11 step=40/355 loss=0.0505
+epoch=11 step=60/355 loss=0.0165
+epoch=11 step=80/355 loss=0.0219
+epoch=11 step=100/355 loss=0.0135
+epoch=11 step=120/355 loss=0.2434
+epoch=11 step=140/355 loss=0.0195
+epoch=11 step=160/355 loss=0.0423
+epoch=11 step=180/355 loss=0.0383
+epoch=11 step=200/355 loss=0.0311
+epoch=11 step=220/355 loss=0.0759
+epoch=11 step=240/355 loss=0.0368
+epoch=11 step=260/355 loss=0.0431
+epoch=11 step=280/355 loss=0.0507
+epoch=11 step=300/355 loss=0.0459
+epoch=11 step=320/355 loss=0.0831
+epoch=11 step=340/355 loss=0.0717
+epoch=11 train_loss=0.0623 val_loss=0.9227
+epoch=12 step=20/355 loss=0.0110
+epoch=12 step=40/355 loss=0.0206
+epoch=12 step=60/355 loss=0.0711
+epoch=12 step=80/355 loss=0.3893
+epoch=12 step=100/355 loss=0.0185
+epoch=12 step=120/355 loss=0.0152
+epoch=12 step=140/355 loss=0.0227
+epoch=12 step=160/355 loss=0.0218
+epoch=12 step=180/355 loss=0.0430
+epoch=12 step=200/355 loss=0.0143
+epoch=12 step=220/355 loss=0.0209
+epoch=12 step=240/355 loss=0.0258
+epoch=12 step=260/355 loss=0.0994
+epoch=12 step=280/355 loss=0.1140
+epoch=12 step=300/355 loss=0.1215
+epoch=12 step=320/355 loss=0.0644
+epoch=12 step=340/355 loss=0.0201
+epoch=12 train_loss=0.0600 val_loss=0.9394
+epoch=13 step=20/355 loss=0.0547
+epoch=13 step=40/355 loss=0.0161
+epoch=13 step=60/355 loss=0.0313
+epoch=13 step=80/355 loss=0.0693
+epoch=13 step=100/355 loss=0.1003
+epoch=13 step=120/355 loss=0.0413
+epoch=13 step=140/355 loss=0.0222
+epoch=13 step=160/355 loss=0.0556
+epoch=13 step=180/355 loss=0.0736
+epoch=13 step=200/355 loss=0.0116
+epoch=13 step=220/355 loss=0.0257
+epoch=13 step=240/355 loss=0.4209
+epoch=13 step=260/355 loss=0.0155
+epoch=13 step=280/355 loss=0.0350
+epoch=13 step=300/355 loss=0.1024
+epoch=13 step=320/355 loss=0.3678
+epoch=13 step=340/355 loss=0.0212
+epoch=13 train_loss=0.0596 val_loss=0.3922
+epoch=14 step=20/355 loss=0.0349
+epoch=14 step=40/355 loss=0.0106
+epoch=14 step=60/355 loss=0.0321
+epoch=14 step=80/355 loss=0.0373
+epoch=14 step=100/355 loss=0.0123
+epoch=14 step=120/355 loss=0.0289
+epoch=14 step=140/355 loss=0.0127
+epoch=14 step=160/355 loss=0.0186
+epoch=14 step=180/355 loss=0.0197
+epoch=14 step=200/355 loss=0.0709
+epoch=14 step=220/355 loss=0.1070
+epoch=14 step=240/355 loss=0.0116
+epoch=14 step=260/355 loss=0.0204
+epoch=14 step=280/355 loss=0.2690
+epoch=14 step=300/355 loss=0.1164
+epoch=14 step=320/355 loss=0.0385
+epoch=14 step=340/355 loss=0.0108
+epoch=14 train_loss=0.0544 val_loss=0.4749
+epoch=15 step=20/355 loss=0.0091
+epoch=15 step=40/355 loss=0.0863
+epoch=15 step=60/355 loss=0.0210
+epoch=15 step=80/355 loss=0.0101
+epoch=15 step=100/355 loss=0.0336
+epoch=15 step=120/355 loss=0.0304
+epoch=15 step=140/355 loss=0.0166
+epoch=15 step=160/355 loss=0.0421
+epoch=15 step=180/355 loss=0.0171
+epoch=15 step=200/355 loss=0.0144
+epoch=15 step=220/355 loss=0.0665
+epoch=15 step=240/355 loss=0.0336
+epoch=15 step=260/355 loss=0.0585
+epoch=15 step=280/355 loss=0.0138
+epoch=15 step=300/355 loss=0.0098
+epoch=15 step=320/355 loss=0.0202
+epoch=15 step=340/355 loss=0.0569
+epoch=15 train_loss=0.0486 val_loss=0.4334
+epoch=16 step=20/355 loss=0.0428
+epoch=16 step=40/355 loss=0.0256
+epoch=16 step=60/355 loss=0.0265
+epoch=16 step=80/355 loss=0.2160
+epoch=16 step=100/355 loss=0.0134
+epoch=16 step=120/355 loss=0.0144
+epoch=16 step=140/355 loss=0.0273
+epoch=16 step=160/355 loss=0.0182
+epoch=16 step=180/355 loss=0.0179
+epoch=16 step=200/355 loss=0.0157
+epoch=16 step=220/355 loss=0.0375
+epoch=16 step=240/355 loss=0.0162
+epoch=16 step=260/355 loss=0.0216
+epoch=16 step=280/355 loss=0.0213
+epoch=16 step=300/355 loss=0.0194
+epoch=16 step=320/355 loss=0.0235
+epoch=16 step=340/355 loss=0.0172
+epoch=16 train_loss=0.0485 val_loss=0.5940
+epoch=17 step=20/355 loss=0.5675
+epoch=17 step=40/355 loss=0.0965
+epoch=17 step=60/355 loss=0.0104
+epoch=17 step=80/355 loss=0.0580
+epoch=17 step=100/355 loss=0.0151
+epoch=17 step=120/355 loss=0.0084
+epoch=17 step=140/355 loss=0.0204
+epoch=17 step=160/355 loss=0.8225
+epoch=17 step=180/355 loss=0.0104
+epoch=17 step=200/355 loss=0.0105
+epoch=17 step=220/355 loss=0.3046
+epoch=17 step=240/355 loss=0.0105
+epoch=17 step=260/355 loss=0.0137
+epoch=17 step=280/355 loss=0.0630
+epoch=17 step=300/355 loss=0.0241
+epoch=17 step=320/355 loss=0.0362
+epoch=17 step=340/355 loss=0.0060
+epoch=17 train_loss=0.0456 val_loss=0.2909
+epoch=18 step=20/355 loss=0.0295
+epoch=18 step=40/355 loss=0.0110
+epoch=18 step=60/355 loss=0.0078
+epoch=18 step=80/355 loss=0.0265
+epoch=18 step=100/355 loss=0.0303
+epoch=18 step=120/355 loss=0.0697
+epoch=18 step=140/355 loss=0.0365
+epoch=18 step=160/355 loss=0.0161
+epoch=18 step=180/355 loss=0.0083
+epoch=18 step=200/355 loss=0.0261
+epoch=18 step=220/355 loss=0.0678
+epoch=18 step=240/355 loss=0.0103
+epoch=18 step=260/355 loss=0.0205
+epoch=18 step=280/355 loss=0.0158
+epoch=18 step=300/355 loss=0.5490
+epoch=18 step=320/355 loss=0.0732
+epoch=18 step=340/355 loss=0.0196
+epoch=18 train_loss=0.0421 val_loss=0.4196
+epoch=19 step=20/355 loss=0.0100
+epoch=19 step=40/355 loss=0.0196
+epoch=19 step=60/355 loss=0.0100
+epoch=19 step=80/355 loss=0.0083
+epoch=19 step=100/355 loss=0.0171
+epoch=19 step=120/355 loss=0.0301
+epoch=19 step=140/355 loss=0.0174
+epoch=19 step=160/355 loss=0.0245
+epoch=19 step=180/355 loss=0.0107
+epoch=19 step=200/355 loss=0.3947
+epoch=19 step=220/355 loss=0.0147
+epoch=19 step=240/355 loss=0.0158
+epoch=19 step=260/355 loss=0.0371
+epoch=19 step=280/355 loss=0.0099
+epoch=19 step=300/355 loss=0.0267
+epoch=19 step=320/355 loss=0.0354
+epoch=19 step=340/355 loss=0.0249
+epoch=19 train_loss=0.0393 val_loss=0.2621
+epoch=20 step=20/355 loss=0.0090
+epoch=20 step=40/355 loss=0.1945
+epoch=20 step=60/355 loss=0.0075
+epoch=20 step=80/355 loss=0.0121
+epoch=20 step=100/355 loss=0.0126
+epoch=20 step=120/355 loss=0.0182
+epoch=20 step=140/355 loss=0.0097
+epoch=20 step=160/355 loss=0.0081
+epoch=20 step=180/355 loss=0.0109
+epoch=20 step=200/355 loss=0.0110
+epoch=20 step=220/355 loss=0.0147
+epoch=20 step=240/355 loss=0.0320
+epoch=20 step=260/355 loss=0.0206
+epoch=20 step=280/355 loss=0.0555
+epoch=20 step=300/355 loss=0.3074
+epoch=20 step=320/355 loss=0.0734
+epoch=20 step=340/355 loss=0.0259
+epoch=20 train_loss=0.0433 val_loss=0.3849
+saved runs/foundation/medicalnet_e2e_mlp.pt

logs/medicalnet_frozen_mlp_20260514_112810.log ADDED Viewed

	@@ -0,0 +1,542 @@

+device=cuda backbone=medicalnet freeze=True train=710 val=152
+epoch=1 step=10/178 loss=1.5952
+epoch=1 step=20/178 loss=1.5082
+epoch=1 step=30/178 loss=1.4166
+epoch=1 step=40/178 loss=1.4155
+epoch=1 step=50/178 loss=1.4100
+epoch=1 step=60/178 loss=1.4034
+epoch=1 step=70/178 loss=1.4084
+epoch=1 step=80/178 loss=1.4025
+epoch=1 step=90/178 loss=1.4103
+epoch=1 step=100/178 loss=1.4187
+epoch=1 step=110/178 loss=1.4202
+epoch=1 step=120/178 loss=1.4129
+epoch=1 step=130/178 loss=1.4084
+epoch=1 step=140/178 loss=1.4104
+epoch=1 step=150/178 loss=1.4100
+epoch=1 step=160/178 loss=1.4081
+epoch=1 step=170/178 loss=1.4133
+epoch=1 train_loss=1.4572 val_loss=1.4114
+epoch=2 step=10/178 loss=1.4150
+epoch=2 step=20/178 loss=1.4276
+epoch=2 step=30/178 loss=1.3954
+epoch=2 step=40/178 loss=1.3987
+epoch=2 step=50/178 loss=1.3997
+epoch=2 step=60/178 loss=1.4106
+epoch=2 step=70/178 loss=1.4335
+epoch=2 step=80/178 loss=1.4034
+epoch=2 step=90/178 loss=1.4077
+epoch=2 step=100/178 loss=1.4000
+epoch=2 step=110/178 loss=1.4047
+epoch=2 step=120/178 loss=1.3974
+epoch=2 step=130/178 loss=1.4028
+epoch=2 step=140/178 loss=1.4020
+epoch=2 step=150/178 loss=1.3994
+epoch=2 step=160/178 loss=1.4343
+epoch=2 step=170/178 loss=1.3955
+epoch=2 train_loss=1.4077 val_loss=1.4096
+epoch=3 step=10/178 loss=1.4006
+epoch=3 step=20/178 loss=1.3962
+epoch=3 step=30/178 loss=1.4143
+epoch=3 step=40/178 loss=1.4020
+epoch=3 step=50/178 loss=1.3948
+epoch=3 step=60/178 loss=1.4028
+epoch=3 step=70/178 loss=1.4234
+epoch=3 step=80/178 loss=1.4162
+epoch=3 step=90/178 loss=1.4021
+epoch=3 step=100/178 loss=1.3977
+epoch=3 step=110/178 loss=1.4137
+epoch=3 step=120/178 loss=1.3988
+epoch=3 step=130/178 loss=1.4072
+epoch=3 step=140/178 loss=1.4127
+epoch=3 step=150/178 loss=1.4049
+epoch=3 step=160/178 loss=1.4016
+epoch=3 step=170/178 loss=1.4142
+epoch=3 train_loss=1.4066 val_loss=1.4129
+epoch=4 step=10/178 loss=1.4073
+epoch=4 step=20/178 loss=1.4091
+epoch=4 step=30/178 loss=1.4063
+epoch=4 step=40/178 loss=1.3955
+epoch=4 step=50/178 loss=1.3967
+epoch=4 step=60/178 loss=1.4059
+epoch=4 step=70/178 loss=1.4049
+epoch=4 step=80/178 loss=1.4006
+epoch=4 step=90/178 loss=1.3938
+epoch=4 step=100/178 loss=1.4549
+epoch=4 step=110/178 loss=1.4076
+epoch=4 step=120/178 loss=1.4169
+epoch=4 step=130/178 loss=1.4047
+epoch=4 step=140/178 loss=1.4052
+epoch=4 step=150/178 loss=1.4011
+epoch=4 step=160/178 loss=1.4088
+epoch=4 step=170/178 loss=1.4072
+epoch=4 train_loss=1.4066 val_loss=1.4088
+epoch=5 step=10/178 loss=1.3987
+epoch=5 step=20/178 loss=1.4084
+epoch=5 step=30/178 loss=1.4803
+epoch=5 step=40/178 loss=1.4125
+epoch=5 step=50/178 loss=1.3970
+epoch=5 step=60/178 loss=1.4229
+epoch=5 step=70/178 loss=1.3933
+epoch=5 step=80/178 loss=1.3989
+epoch=5 step=90/178 loss=1.4268
+epoch=5 step=100/178 loss=1.4024
+epoch=5 step=110/178 loss=1.3977
+epoch=5 step=120/178 loss=1.4043
+epoch=5 step=130/178 loss=1.4362
+epoch=5 step=140/178 loss=1.4045
+epoch=5 step=150/178 loss=1.4059
+epoch=5 step=160/178 loss=1.4086
+epoch=5 step=170/178 loss=1.4319
+epoch=5 train_loss=1.4050 val_loss=1.4101
+epoch=6 step=10/178 loss=1.4378
+epoch=6 step=20/178 loss=1.4166
+epoch=6 step=30/178 loss=1.3937
+epoch=6 step=40/178 loss=1.4087
+epoch=6 step=50/178 loss=1.4218
+epoch=6 step=60/178 loss=1.4105
+epoch=6 step=70/178 loss=1.4117
+epoch=6 step=80/178 loss=1.4271
+epoch=6 step=90/178 loss=1.4045
+epoch=6 step=100/178 loss=1.3996
+epoch=6 step=110/178 loss=1.4065
+epoch=6 step=120/178 loss=1.3948
+epoch=6 step=130/178 loss=1.3976
+epoch=6 step=140/178 loss=1.4002
+epoch=6 step=150/178 loss=1.3922
+epoch=6 step=160/178 loss=1.4021
+epoch=6 step=170/178 loss=1.4092
+epoch=6 train_loss=1.4051 val_loss=1.4118
+epoch=7 step=10/178 loss=1.3943
+epoch=7 step=20/178 loss=1.3961
+epoch=7 step=30/178 loss=1.3954
+epoch=7 step=40/178 loss=1.4317
+epoch=7 step=50/178 loss=1.4207
+epoch=7 step=60/178 loss=1.4021
+epoch=7 step=70/178 loss=1.3968
+epoch=7 step=80/178 loss=1.4296
+epoch=7 step=90/178 loss=1.3916
+epoch=7 step=100/178 loss=1.4028
+epoch=7 step=110/178 loss=1.3977
+epoch=7 step=120/178 loss=1.4142
+epoch=7 step=130/178 loss=1.4183
+epoch=7 step=140/178 loss=1.3941
+epoch=7 step=150/178 loss=1.3956
+epoch=7 step=160/178 loss=1.3893
+epoch=7 step=170/178 loss=1.4087
+epoch=7 train_loss=1.4051 val_loss=1.4085
+epoch=8 step=10/178 loss=1.4158
+epoch=8 step=20/178 loss=1.4041
+epoch=8 step=30/178 loss=1.3905
+epoch=8 step=40/178 loss=1.4109
+epoch=8 step=50/178 loss=1.3867
+epoch=8 step=60/178 loss=1.3926
+epoch=8 step=70/178 loss=1.4738
+epoch=8 step=80/178 loss=1.3974
+epoch=8 step=90/178 loss=1.4153
+epoch=8 step=100/178 loss=1.3781
+epoch=8 step=110/178 loss=1.4471
+epoch=8 step=120/178 loss=1.4140
+epoch=8 step=130/178 loss=1.4324
+epoch=8 step=140/178 loss=1.4064
+epoch=8 step=150/178 loss=1.4308
+epoch=8 step=160/178 loss=1.3907
+epoch=8 step=170/178 loss=1.3917
+epoch=8 train_loss=1.4028 val_loss=1.4032
+epoch=9 step=10/178 loss=1.3987
+epoch=9 step=20/178 loss=1.4054
+epoch=9 step=30/178 loss=1.4037
+epoch=9 step=40/178 loss=1.3993
+epoch=9 step=50/178 loss=1.4020
+epoch=9 step=60/178 loss=1.3908
+epoch=9 step=70/178 loss=1.3851
+epoch=9 step=80/178 loss=1.4038
+epoch=9 step=90/178 loss=1.4051
+epoch=9 step=100/178 loss=1.4050
+epoch=9 step=110/178 loss=1.4035
+epoch=9 step=120/178 loss=1.4049
+epoch=9 step=130/178 loss=1.4043
+epoch=9 step=140/178 loss=1.4134
+epoch=9 step=150/178 loss=1.3986
+epoch=9 step=160/178 loss=1.3774
+epoch=9 step=170/178 loss=1.4016
+epoch=9 train_loss=1.4000 val_loss=1.3986
+epoch=10 step=10/178 loss=1.3900
+epoch=10 step=20/178 loss=1.3911
+epoch=10 step=30/178 loss=1.3982
+epoch=10 step=40/178 loss=1.3867
+epoch=10 step=50/178 loss=1.3756
+epoch=10 step=60/178 loss=1.3725
+epoch=10 step=70/178 loss=1.3882
+epoch=10 step=80/178 loss=1.4218
+epoch=10 step=90/178 loss=1.4632
+epoch=10 step=100/178 loss=1.3928
+epoch=10 step=110/178 loss=1.4419
+epoch=10 step=120/178 loss=1.3926
+epoch=10 step=130/178 loss=1.3957
+epoch=10 step=140/178 loss=1.3904
+epoch=10 step=150/178 loss=1.4013
+epoch=10 step=160/178 loss=1.4604
+epoch=10 step=170/178 loss=1.3981
+epoch=10 train_loss=1.3991 val_loss=1.3957
+epoch=11 step=10/178 loss=1.3576
+epoch=11 step=20/178 loss=1.3862
+epoch=11 step=30/178 loss=1.3973
+epoch=11 step=40/178 loss=1.3731
+epoch=11 step=50/178 loss=1.3913
+epoch=11 step=60/178 loss=1.3538
+epoch=11 step=70/178 loss=1.4088
+epoch=11 step=80/178 loss=1.3221
+epoch=11 step=90/178 loss=1.3805
+epoch=11 step=100/178 loss=1.5164
+epoch=11 step=110/178 loss=1.4240
+epoch=11 step=120/178 loss=1.4084
+epoch=11 step=130/178 loss=1.4141
+epoch=11 step=140/178 loss=1.3903
+epoch=11 step=150/178 loss=1.4068
+epoch=11 step=160/178 loss=1.3754
+epoch=11 step=170/178 loss=1.3887
+epoch=11 train_loss=1.3963 val_loss=1.3956
+epoch=12 step=10/178 loss=1.4150
+epoch=12 step=20/178 loss=1.3850
+epoch=12 step=30/178 loss=1.3970
+epoch=12 step=40/178 loss=1.4002
+epoch=12 step=50/178 loss=1.3263
+epoch=12 step=60/178 loss=1.3791
+epoch=12 step=70/178 loss=1.3711
+epoch=12 step=80/178 loss=1.3573
+epoch=12 step=90/178 loss=1.3844
+epoch=12 step=100/178 loss=1.3263
+epoch=12 step=110/178 loss=1.4737
+epoch=12 step=120/178 loss=1.5467
+epoch=12 step=130/178 loss=1.4005
+epoch=12 step=140/178 loss=1.4015
+epoch=12 step=150/178 loss=1.3805
+epoch=12 step=160/178 loss=1.3869
+epoch=12 step=170/178 loss=1.3881
+epoch=12 train_loss=1.4020 val_loss=1.3993
+epoch=13 step=10/178 loss=1.4033
+epoch=13 step=20/178 loss=1.3997
+epoch=13 step=30/178 loss=1.3841
+epoch=13 step=40/178 loss=1.3917
+epoch=13 step=50/178 loss=1.3827
+epoch=13 step=60/178 loss=1.3647
+epoch=13 step=70/178 loss=1.3848
+epoch=13 step=80/178 loss=1.4095
+epoch=13 step=90/178 loss=1.3896
+epoch=13 step=100/178 loss=1.3880
+epoch=13 step=110/178 loss=1.3839
+epoch=13 step=120/178 loss=1.3809
+epoch=13 step=130/178 loss=1.3833
+epoch=13 step=140/178 loss=1.3799
+epoch=13 step=150/178 loss=1.3740
+epoch=13 step=160/178 loss=1.3752
+epoch=13 step=170/178 loss=1.3870
+epoch=13 train_loss=1.3851 val_loss=1.3833
+epoch=14 step=10/178 loss=1.3754
+epoch=14 step=20/178 loss=1.4004
+epoch=14 step=30/178 loss=1.4568
+epoch=14 step=40/178 loss=1.3926
+epoch=14 step=50/178 loss=1.3239
+epoch=14 step=60/178 loss=1.5053
+epoch=14 step=70/178 loss=1.7521
+epoch=14 step=80/178 loss=1.4060
+epoch=14 step=90/178 loss=1.3868
+epoch=14 step=100/178 loss=1.3974
+epoch=14 step=110/178 loss=1.3958
+epoch=14 step=120/178 loss=1.3740
+epoch=14 step=130/178 loss=1.3867
+epoch=14 step=140/178 loss=1.3832
+epoch=14 step=150/178 loss=1.3849
+epoch=14 step=160/178 loss=1.3982
+epoch=14 step=170/178 loss=1.4416
+epoch=14 train_loss=1.3915 val_loss=1.3844
+epoch=15 step=10/178 loss=1.4209
+epoch=15 step=20/178 loss=1.3766
+epoch=15 step=30/178 loss=1.4042
+epoch=15 step=40/178 loss=1.3681
+epoch=15 step=50/178 loss=1.3786
+epoch=15 step=60/178 loss=1.3919
+epoch=15 step=70/178 loss=1.3271
+epoch=15 step=80/178 loss=1.3513
+epoch=15 step=90/178 loss=1.3727
+epoch=15 step=100/178 loss=1.4909
+epoch=15 step=110/178 loss=1.4560
+epoch=15 step=120/178 loss=1.4186
+epoch=15 step=130/178 loss=1.3826
+epoch=15 step=140/178 loss=1.3632
+epoch=15 step=150/178 loss=1.3759
+epoch=15 step=160/178 loss=1.4080
+epoch=15 step=170/178 loss=1.3748
+epoch=15 train_loss=1.3914 val_loss=1.3905
+epoch=16 step=10/178 loss=1.3748
+epoch=16 step=20/178 loss=1.3842
+epoch=16 step=30/178 loss=1.3843
+epoch=16 step=40/178 loss=1.3777
+epoch=16 step=50/178 loss=1.3650
+epoch=16 step=60/178 loss=1.4129
+epoch=16 step=70/178 loss=1.4008
+epoch=16 step=80/178 loss=1.3025
+epoch=16 step=90/178 loss=1.3930
+epoch=16 step=100/178 loss=1.3828
+epoch=16 step=110/178 loss=1.3649
+epoch=16 step=120/178 loss=1.3673
+epoch=16 step=130/178 loss=1.3240
+epoch=16 step=140/178 loss=1.3417
+epoch=16 step=150/178 loss=1.3020
+epoch=16 step=160/178 loss=1.2323
+epoch=16 step=170/178 loss=1.2291
+epoch=16 train_loss=1.3602 val_loss=1.3963
+epoch=17 step=10/178 loss=1.3455
+epoch=17 step=20/178 loss=1.3734
+epoch=17 step=30/178 loss=1.4196
+epoch=17 step=40/178 loss=1.4061
+epoch=17 step=50/178 loss=1.3952
+epoch=17 step=60/178 loss=1.3914
+epoch=17 step=70/178 loss=1.3822
+epoch=17 step=80/178 loss=1.3532
+epoch=17 step=90/178 loss=1.1675
+epoch=17 step=100/178 loss=1.4179
+epoch=17 step=110/178 loss=1.4783
+epoch=17 step=120/178 loss=1.5648
+epoch=17 step=130/178 loss=1.3419
+epoch=17 step=140/178 loss=1.3324
+epoch=17 step=150/178 loss=1.3711
+epoch=17 step=160/178 loss=1.3573
+epoch=17 step=170/178 loss=1.3572
+epoch=17 train_loss=1.3774 val_loss=1.3612
+epoch=18 step=10/178 loss=1.3788
+epoch=18 step=20/178 loss=1.3841
+epoch=18 step=30/178 loss=1.2745
+epoch=18 step=40/178 loss=1.3373
+epoch=18 step=50/178 loss=1.3512
+epoch=18 step=60/178 loss=1.2809
+epoch=18 step=70/178 loss=1.4669
+epoch=18 step=80/178 loss=1.4112
+epoch=18 step=90/178 loss=1.3835
+epoch=18 step=100/178 loss=1.3529
+epoch=18 step=110/178 loss=1.4034
+epoch=18 step=120/178 loss=1.3859
+epoch=18 step=130/178 loss=1.3970
+epoch=18 step=140/178 loss=1.3896
+epoch=18 step=150/178 loss=1.3713
+epoch=18 step=160/178 loss=1.3206
+epoch=18 step=170/178 loss=1.3908
+epoch=18 train_loss=1.3753 val_loss=1.3652
+epoch=19 step=10/178 loss=1.3473
+epoch=19 step=20/178 loss=1.3775
+epoch=19 step=30/178 loss=1.3207
+epoch=19 step=40/178 loss=1.2859
+epoch=19 step=50/178 loss=1.2426
+epoch=19 step=60/178 loss=1.3315
+epoch=19 step=70/178 loss=1.4643
+epoch=19 step=80/178 loss=1.3025
+epoch=19 step=90/178 loss=1.4461
+epoch=19 step=100/178 loss=1.3686
+epoch=19 step=110/178 loss=1.3963
+epoch=19 step=120/178 loss=1.3488
+epoch=19 step=130/178 loss=1.3543
+epoch=19 step=140/178 loss=1.4044
+epoch=19 step=150/178 loss=1.3650
+epoch=19 step=160/178 loss=1.3396
+epoch=19 step=170/178 loss=1.3237
+epoch=19 train_loss=1.3445 val_loss=1.3004
+epoch=20 step=10/178 loss=1.3046
+epoch=20 step=20/178 loss=1.4973
+epoch=20 step=30/178 loss=1.6909
+epoch=20 step=40/178 loss=1.3332
+epoch=20 step=50/178 loss=1.3892
+epoch=20 step=60/178 loss=1.4028
+epoch=20 step=70/178 loss=1.3656
+epoch=20 step=80/178 loss=1.3796
+epoch=20 step=90/178 loss=1.3914
+epoch=20 step=100/178 loss=1.4139
+epoch=20 step=110/178 loss=1.3511
+epoch=20 step=120/178 loss=1.3378
+epoch=20 step=130/178 loss=1.3462
+epoch=20 step=140/178 loss=1.3874
+epoch=20 step=150/178 loss=1.3579
+epoch=20 step=160/178 loss=1.3292
+epoch=20 step=170/178 loss=1.4033
+epoch=20 train_loss=1.3895 val_loss=1.3625
+epoch=21 step=10/178 loss=1.3659
+epoch=21 step=20/178 loss=1.2781
+epoch=21 step=30/178 loss=1.2499
+epoch=21 step=40/178 loss=1.3146
+epoch=21 step=50/178 loss=1.3096
+epoch=21 step=60/178 loss=1.3437
+epoch=21 step=70/178 loss=1.4003
+epoch=21 step=80/178 loss=1.3276
+epoch=21 step=90/178 loss=1.3025
+epoch=21 step=100/178 loss=1.3094
+epoch=21 step=110/178 loss=1.4212
+epoch=21 step=120/178 loss=1.2791
+epoch=21 step=130/178 loss=1.3724
+epoch=21 step=140/178 loss=1.3141
+epoch=21 step=150/178 loss=1.3310
+epoch=21 step=160/178 loss=1.3597
+epoch=21 step=170/178 loss=1.2791
+epoch=21 train_loss=1.3192 val_loss=1.3334
+epoch=22 step=10/178 loss=1.2556
+epoch=22 step=20/178 loss=1.1199
+epoch=22 step=30/178 loss=1.4295
+epoch=22 step=40/178 loss=1.2060
+epoch=22 step=50/178 loss=1.0376
+epoch=22 step=60/178 loss=1.3155
+epoch=22 step=70/178 loss=1.3805
+epoch=22 step=80/178 loss=1.3407
+epoch=22 step=90/178 loss=1.2070
+epoch=22 step=100/178 loss=1.2878
+epoch=22 step=110/178 loss=1.1424
+epoch=22 step=120/178 loss=1.1131
+epoch=22 step=130/178 loss=1.5043
+epoch=22 step=140/178 loss=1.4505
+epoch=22 step=150/178 loss=1.4540
+epoch=22 step=160/178 loss=1.3931
+epoch=22 step=170/178 loss=1.3701
+epoch=22 train_loss=1.3337 val_loss=1.3887
+epoch=23 step=10/178 loss=1.3593
+epoch=23 step=20/178 loss=1.3293
+epoch=23 step=30/178 loss=1.3192
+epoch=23 step=40/178 loss=1.2911
+epoch=23 step=50/178 loss=1.2787
+epoch=23 step=60/178 loss=1.3884
+epoch=23 step=70/178 loss=1.2451
+epoch=23 step=80/178 loss=1.3038
+epoch=23 step=90/178 loss=1.3253
+epoch=23 step=100/178 loss=1.2599
+epoch=23 step=110/178 loss=1.2817
+epoch=23 step=120/178 loss=1.2496
+epoch=23 step=130/178 loss=1.2147
+epoch=23 step=140/178 loss=1.6829
+epoch=23 step=150/178 loss=1.4823
+epoch=23 step=160/178 loss=1.3060
+epoch=23 step=170/178 loss=1.1992
+epoch=23 train_loss=1.3307 val_loss=1.3407
+epoch=24 step=10/178 loss=1.3069
+epoch=24 step=20/178 loss=1.2668
+epoch=24 step=30/178 loss=1.2822
+epoch=24 step=40/178 loss=1.3459
+epoch=24 step=50/178 loss=1.2107
+epoch=24 step=60/178 loss=1.6015
+epoch=24 step=70/178 loss=1.2982
+epoch=24 step=80/178 loss=1.2763
+epoch=24 step=90/178 loss=0.9334
+epoch=24 step=100/178 loss=1.4272
+epoch=24 step=110/178 loss=1.3631
+epoch=24 step=120/178 loss=1.2822
+epoch=24 step=130/178 loss=1.3843
+epoch=24 step=140/178 loss=1.3117
+epoch=24 step=150/178 loss=1.2282
+epoch=24 step=160/178 loss=1.2870
+epoch=24 step=170/178 loss=1.7064
+epoch=24 train_loss=1.3173 val_loss=1.4503
+epoch=25 step=10/178 loss=1.3868
+epoch=25 step=20/178 loss=1.3465
+epoch=25 step=30/178 loss=1.4084
+epoch=25 step=40/178 loss=1.3755
+epoch=25 step=50/178 loss=1.3225
+epoch=25 step=60/178 loss=1.3925
+epoch=25 step=70/178 loss=1.3322
+epoch=25 step=80/178 loss=1.0577
+epoch=25 step=90/178 loss=1.2586
+epoch=25 step=100/178 loss=1.2181
+epoch=25 step=110/178 loss=1.3015
+epoch=25 step=120/178 loss=1.0567
+epoch=25 step=130/178 loss=1.3604
+epoch=25 step=140/178 loss=1.0624
+epoch=25 step=150/178 loss=1.3386
+epoch=25 step=160/178 loss=1.2326
+epoch=25 step=170/178 loss=1.8504
+epoch=25 train_loss=1.3277 val_loss=1.9118
+epoch=26 step=10/178 loss=1.3679
+epoch=26 step=20/178 loss=1.2950
+epoch=26 step=30/178 loss=1.3312
+epoch=26 step=40/178 loss=1.3556
+epoch=26 step=50/178 loss=1.2999
+epoch=26 step=60/178 loss=1.3630
+epoch=26 step=70/178 loss=1.4084
+epoch=26 step=80/178 loss=1.3611
+epoch=26 step=90/178 loss=1.3059
+epoch=26 step=100/178 loss=1.3623
+epoch=26 step=110/178 loss=1.2691
+epoch=26 step=120/178 loss=1.2604
+epoch=26 step=130/178 loss=1.3907
+epoch=26 step=140/178 loss=1.3561
+epoch=26 step=150/178 loss=1.3879
+epoch=26 step=160/178 loss=1.2184
+epoch=26 step=170/178 loss=1.3363
+epoch=26 train_loss=1.3688 val_loss=1.3396
+epoch=27 step=10/178 loss=1.3547
+epoch=27 step=20/178 loss=1.3316
+epoch=27 step=30/178 loss=1.3523
+epoch=27 step=40/178 loss=1.2835
+epoch=27 step=50/178 loss=1.1419
+epoch=27 step=60/178 loss=1.2870
+epoch=27 step=70/178 loss=1.1819
+epoch=27 step=80/178 loss=1.3417
+epoch=27 step=90/178 loss=1.2144
+epoch=27 step=100/178 loss=1.2442
+epoch=27 step=110/178 loss=0.9941
+epoch=27 step=120/178 loss=0.9420
+epoch=27 step=130/178 loss=1.1001
+epoch=27 step=140/178 loss=1.3778
+epoch=27 step=150/178 loss=1.3204
+epoch=27 step=160/178 loss=1.1843
+epoch=27 step=170/178 loss=1.2331
+epoch=27 train_loss=1.2786 val_loss=1.2615
+epoch=28 step=10/178 loss=1.2408
+epoch=28 step=20/178 loss=1.3972
+epoch=28 step=30/178 loss=1.3041
+epoch=28 step=40/178 loss=1.3562
+epoch=28 step=50/178 loss=1.4628
+epoch=28 step=60/178 loss=1.2640
+epoch=28 step=70/178 loss=1.2198
+epoch=28 step=80/178 loss=1.2644
+epoch=28 step=90/178 loss=1.2648
+epoch=28 step=100/178 loss=1.2375
+epoch=28 step=110/178 loss=1.3106
+epoch=28 step=120/178 loss=1.3851
+epoch=28 step=130/178 loss=1.2328
+epoch=28 step=140/178 loss=1.0662
+epoch=28 step=150/178 loss=1.5889
+epoch=28 step=160/178 loss=1.5528
+epoch=28 step=170/178 loss=1.3632
+epoch=28 train_loss=1.3056 val_loss=1.3224
+epoch=29 step=10/178 loss=1.2092
+epoch=29 step=20/178 loss=1.3045
+epoch=29 step=30/178 loss=1.3131
+epoch=29 step=40/178 loss=1.3246
+epoch=29 step=50/178 loss=1.1317
+epoch=29 step=60/178 loss=1.3210
+epoch=29 step=70/178 loss=1.1854
+epoch=29 step=80/178 loss=1.0391
+epoch=29 step=90/178 loss=1.4365
+epoch=29 step=100/178 loss=1.2638
+epoch=29 step=110/178 loss=1.5110
+epoch=29 step=120/178 loss=1.2098
+epoch=29 step=130/178 loss=1.2418
+epoch=29 step=140/178 loss=1.1076
+epoch=29 step=150/178 loss=1.2613
+epoch=29 step=160/178 loss=1.4235
+epoch=29 step=170/178 loss=1.2397
+epoch=29 train_loss=1.2517 val_loss=1.3533
+epoch=30 step=10/178 loss=1.3654
+epoch=30 step=20/178 loss=0.9463
+epoch=30 step=30/178 loss=1.2087
+epoch=30 step=40/178 loss=1.3775
+epoch=30 step=50/178 loss=1.0815
+epoch=30 step=60/178 loss=1.3356
+epoch=30 step=70/178 loss=1.3253
+epoch=30 step=80/178 loss=1.2903
+epoch=30 step=90/178 loss=1.2190
+epoch=30 step=100/178 loss=1.3355
+epoch=30 step=110/178 loss=1.3246
+epoch=30 step=120/178 loss=1.1909
+epoch=30 step=130/178 loss=1.2294
+epoch=30 step=140/178 loss=2.0862
+epoch=30 step=150/178 loss=1.2557
+epoch=30 step=160/178 loss=1.3420
+epoch=30 step=170/178 loss=1.3210
+epoch=30 train_loss=1.2653 val_loss=1.2899
+saved runs/foundation/medicalnet_frozen_mlp.pt

logs/medicalnet_layer4_regalign_20260515_010621.log ADDED Viewed

	@@ -0,0 +1,472 @@

+device=cuda backbone=medicalnet encoder_scope=layer4 contrastive_weight=0.2 regression_weight=1.0 train=710 val=152
+epoch=1 step=20/178 loss=0.5695
+epoch=1 step=40/178 loss=0.4670
+epoch=1 step=60/178 loss=0.4990
+epoch=1 step=80/178 loss=0.4114
+epoch=1 step=100/178 loss=0.3235
+epoch=1 step=120/178 loss=0.3386
+epoch=1 step=140/178 loss=0.2960
+epoch=1 step=160/178 loss=0.3249
+epoch=1 train_loss=0.4610 train_contrastive=1.1986 train_regression=0.2213 val_loss=0.3246 val_contrastive=1.1284 val_regression=0.0990
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.3246 epoch=1
+epoch=2 step=20/178 loss=0.3291
+epoch=2 step=40/178 loss=0.2420
+epoch=2 step=60/178 loss=0.1662
+epoch=2 step=80/178 loss=0.2206
+epoch=2 step=100/178 loss=0.1549
+epoch=2 step=120/178 loss=0.2099
+epoch=2 step=140/178 loss=0.1493
+epoch=2 step=160/178 loss=0.0928
+epoch=2 train_loss=0.2044 train_contrastive=0.7564 train_regression=0.0531 val_loss=0.2592 val_contrastive=0.9270 val_regression=0.0738
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.2592 epoch=2
+epoch=3 step=20/178 loss=0.1225
+epoch=3 step=40/178 loss=0.1370
+epoch=3 step=60/178 loss=0.1120
+epoch=3 step=80/178 loss=0.1508
+epoch=3 step=100/178 loss=0.0971
+epoch=3 step=120/178 loss=0.0517
+epoch=3 step=140/178 loss=0.0852
+epoch=3 step=160/178 loss=0.0851
+epoch=3 train_loss=0.1139 train_contrastive=0.3956 train_regression=0.0348 val_loss=0.2015 val_contrastive=0.6531 val_regression=0.0709
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.2015 epoch=3
+epoch=4 step=20/178 loss=0.0761
+epoch=4 step=40/178 loss=0.1037
+epoch=4 step=60/178 loss=0.0748
+epoch=4 step=80/178 loss=0.0261
+epoch=4 step=100/178 loss=0.0551
+epoch=4 step=120/178 loss=0.0721
+epoch=4 step=140/178 loss=0.0237
+epoch=4 step=160/178 loss=0.0303
+epoch=4 train_loss=0.0800 train_contrastive=0.2453 train_regression=0.0309 val_loss=0.1444 val_contrastive=0.4504 val_regression=0.0543
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.1444 epoch=4
+epoch=5 step=20/178 loss=0.0382
+epoch=5 step=40/178 loss=0.0326
+epoch=5 step=60/178 loss=0.0840
+epoch=5 step=80/178 loss=0.1162
+epoch=5 step=100/178 loss=0.0869
+epoch=5 step=120/178 loss=0.0642
+epoch=5 step=140/178 loss=0.0467
+epoch=5 step=160/178 loss=0.0475
+epoch=5 train_loss=0.0616 train_contrastive=0.1745 train_regression=0.0267 val_loss=0.1456 val_contrastive=0.4431 val_regression=0.0570
+epoch=6 step=20/178 loss=0.1513
+epoch=6 step=40/178 loss=0.0445
+epoch=6 step=60/178 loss=0.0346
+epoch=6 step=80/178 loss=0.0547
+epoch=6 step=100/178 loss=0.0471
+epoch=6 step=120/178 loss=0.0291
+epoch=6 step=140/178 loss=0.0719
+epoch=6 step=160/178 loss=0.0315
+epoch=6 train_loss=0.0536 train_contrastive=0.1500 train_regression=0.0236 val_loss=0.1343 val_contrastive=0.4231 val_regression=0.0497
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.1343 epoch=6
+epoch=7 step=20/178 loss=0.0512
+epoch=7 step=40/178 loss=0.0506
+epoch=7 step=60/178 loss=0.0857
+epoch=7 step=80/178 loss=0.0428
+epoch=7 step=100/178 loss=0.0762
+epoch=7 step=120/178 loss=0.0699
+epoch=7 step=140/178 loss=0.0391
+epoch=7 step=160/178 loss=0.0114
+epoch=7 train_loss=0.0464 train_contrastive=0.1212 train_regression=0.0222 val_loss=0.0861 val_contrastive=0.2735 val_regression=0.0314
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0861 epoch=7
+epoch=8 step=20/178 loss=0.0389
+epoch=8 step=40/178 loss=0.0411
+epoch=8 step=60/178 loss=0.0272
+epoch=8 step=80/178 loss=0.1154
+epoch=8 step=100/178 loss=0.0269
+epoch=8 step=120/178 loss=0.0251
+epoch=8 step=140/178 loss=0.0214
+epoch=8 step=160/178 loss=0.0200
+epoch=8 train_loss=0.0377 train_contrastive=0.0903 train_regression=0.0197 val_loss=0.0808 val_contrastive=0.2648 val_regression=0.0279
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0808 epoch=8
+epoch=9 step=20/178 loss=0.0456
+epoch=9 step=40/178 loss=0.0258
+epoch=9 step=60/178 loss=0.0318
+epoch=9 step=80/178 loss=0.0696
+epoch=9 step=100/178 loss=0.0691
+epoch=9 step=120/178 loss=0.0437
+epoch=9 step=140/178 loss=0.0367
+epoch=9 step=160/178 loss=0.0417
+epoch=9 train_loss=0.0352 train_contrastive=0.0806 train_regression=0.0190 val_loss=0.1123 val_contrastive=0.3220 val_regression=0.0479
+epoch=10 step=20/178 loss=0.0176
+epoch=10 step=40/178 loss=0.0148
+epoch=10 step=60/178 loss=0.0291
+epoch=10 step=80/178 loss=0.0272
+epoch=10 step=100/178 loss=0.0162
+epoch=10 step=120/178 loss=0.0320
+epoch=10 step=140/178 loss=0.0444
+epoch=10 step=160/178 loss=0.0460
+epoch=10 train_loss=0.0284 train_contrastive=0.0566 train_regression=0.0171 val_loss=0.0684 val_contrastive=0.2031 val_regression=0.0278
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0684 epoch=10
+epoch=11 step=20/178 loss=0.0206
+epoch=11 step=40/178 loss=0.0283
+epoch=11 step=60/178 loss=0.0239
+epoch=11 step=80/178 loss=0.0181
+epoch=11 step=100/178 loss=0.0407
+epoch=11 step=120/178 loss=0.0482
+epoch=11 step=140/178 loss=0.0295
+epoch=11 step=160/178 loss=0.0141
+epoch=11 train_loss=0.0303 train_contrastive=0.0647 train_regression=0.0174 val_loss=0.0611 val_contrastive=0.2064 val_regression=0.0198
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0611 epoch=11
+epoch=12 step=20/178 loss=0.0336
+epoch=12 step=40/178 loss=0.0166
+epoch=12 step=60/178 loss=0.0272
+epoch=12 step=80/178 loss=0.0325
+epoch=12 step=100/178 loss=0.0258
+epoch=12 step=120/178 loss=0.0094
+epoch=12 step=140/178 loss=0.0175
+epoch=12 step=160/178 loss=0.0155
+epoch=12 train_loss=0.0257 train_contrastive=0.0526 train_regression=0.0151 val_loss=0.0662 val_contrastive=0.1967 val_regression=0.0269
+epoch=13 step=20/178 loss=0.0153
+epoch=13 step=40/178 loss=0.0432
+epoch=13 step=60/178 loss=0.0245
+epoch=13 step=80/178 loss=0.0333
+epoch=13 step=100/178 loss=0.0297
+epoch=13 step=120/178 loss=0.0197
+epoch=13 step=140/178 loss=0.0165
+epoch=13 step=160/178 loss=0.0371
+epoch=13 train_loss=0.0248 train_contrastive=0.0452 train_regression=0.0158 val_loss=0.0480 val_contrastive=0.1451 val_regression=0.0189
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0480 epoch=13
+epoch=14 step=20/178 loss=0.0124
+epoch=14 step=40/178 loss=0.0600
+epoch=14 step=60/178 loss=0.0115
+epoch=14 step=80/178 loss=0.0225
+epoch=14 step=100/178 loss=0.0487
+epoch=14 step=120/178 loss=0.0182
+epoch=14 step=140/178 loss=0.0176
+epoch=14 step=160/178 loss=0.0408
+epoch=14 train_loss=0.0218 train_contrastive=0.0371 train_regression=0.0144 val_loss=0.0578 val_contrastive=0.1804 val_regression=0.0217
+epoch=15 step=20/178 loss=0.0107
+epoch=15 step=40/178 loss=0.0143
+epoch=15 step=60/178 loss=0.0150
+epoch=15 step=80/178 loss=0.0072
+epoch=15 step=100/178 loss=0.0096
+epoch=15 step=120/178 loss=0.0256
+epoch=15 step=140/178 loss=0.0138
+epoch=15 step=160/178 loss=0.0209
+epoch=15 train_loss=0.0213 train_contrastive=0.0392 train_regression=0.0135 val_loss=0.0467 val_contrastive=0.1301 val_regression=0.0207
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0467 epoch=15
+epoch=16 step=20/178 loss=0.0184
+epoch=16 step=40/178 loss=0.0109
+epoch=16 step=60/178 loss=0.0202
+epoch=16 step=80/178 loss=0.0120
+epoch=16 step=100/178 loss=0.0271
+epoch=16 step=120/178 loss=0.0150
+epoch=16 step=140/178 loss=0.0195
+epoch=16 step=160/178 loss=0.0218
+epoch=16 train_loss=0.0237 train_contrastive=0.0489 train_regression=0.0139 val_loss=0.0505 val_contrastive=0.1513 val_regression=0.0202
+epoch=17 step=20/178 loss=0.0289
+epoch=17 step=40/178 loss=0.0142
+epoch=17 step=60/178 loss=0.0330
+epoch=17 step=80/178 loss=0.0075
+epoch=17 step=100/178 loss=0.0124
+epoch=17 step=120/178 loss=0.0102
+epoch=17 step=140/178 loss=0.0583
+epoch=17 step=160/178 loss=0.0163
+epoch=17 train_loss=0.0218 train_contrastive=0.0404 train_regression=0.0137 val_loss=0.0669 val_contrastive=0.1708 val_regression=0.0327
+epoch=18 step=20/178 loss=0.0079
+epoch=18 step=40/178 loss=0.0088
+epoch=18 step=60/178 loss=0.0100
+epoch=18 step=80/178 loss=0.0126
+epoch=18 step=100/178 loss=0.0070
+epoch=18 step=120/178 loss=0.0271
+epoch=18 step=140/178 loss=0.0197
+epoch=18 step=160/178 loss=0.0317
+epoch=18 train_loss=0.0188 train_contrastive=0.0321 train_regression=0.0124 val_loss=0.0461 val_contrastive=0.1444 val_regression=0.0172
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0461 epoch=18
+epoch=19 step=20/178 loss=0.0105
+epoch=19 step=40/178 loss=0.0114
+epoch=19 step=60/178 loss=0.0089
+epoch=19 step=80/178 loss=0.0273
+epoch=19 step=100/178 loss=0.0093
+epoch=19 step=120/178 loss=0.0197
+epoch=19 step=140/178 loss=0.0075
+epoch=19 step=160/178 loss=0.0147
+epoch=19 train_loss=0.0181 train_contrastive=0.0309 train_regression=0.0120 val_loss=0.0475 val_contrastive=0.1460 val_regression=0.0183
+epoch=20 step=20/178 loss=0.0132
+epoch=20 step=40/178 loss=0.0082
+epoch=20 step=60/178 loss=0.0581
+epoch=20 step=80/178 loss=0.0153
+epoch=20 step=100/178 loss=0.0232
+epoch=20 step=120/178 loss=0.0099
+epoch=20 step=140/178 loss=0.0119
+epoch=20 step=160/178 loss=0.0178
+epoch=20 train_loss=0.0180 train_contrastive=0.0305 train_regression=0.0119 val_loss=0.0371 val_contrastive=0.1078 val_regression=0.0156
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0371 epoch=20
+epoch=21 step=20/178 loss=0.0347
+epoch=21 step=40/178 loss=0.0513
+epoch=21 step=60/178 loss=0.0215
+epoch=21 step=80/178 loss=0.0070
+epoch=21 step=100/178 loss=0.0085
+epoch=21 step=120/178 loss=0.0059
+epoch=21 step=140/178 loss=0.0202
+epoch=21 step=160/178 loss=0.0174
+epoch=21 train_loss=0.0188 train_contrastive=0.0305 train_regression=0.0127 val_loss=0.0421 val_contrastive=0.1003 val_regression=0.0220
+epoch=22 step=20/178 loss=0.0131
+epoch=22 step=40/178 loss=0.0097
+epoch=22 step=60/178 loss=0.0688
+epoch=22 step=80/178 loss=0.0111
+epoch=22 step=100/178 loss=0.0109
+epoch=22 step=120/178 loss=0.0081
+epoch=22 step=140/178 loss=0.0103
+epoch=22 step=160/178 loss=0.0110
+epoch=22 train_loss=0.0157 train_contrastive=0.0234 train_regression=0.0110 val_loss=0.0361 val_contrastive=0.0934 val_regression=0.0175
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0361 epoch=22
+epoch=23 step=20/178 loss=0.0114
+epoch=23 step=40/178 loss=0.0089
+epoch=23 step=60/178 loss=0.0122
+epoch=23 step=80/178 loss=0.0132
+epoch=23 step=100/178 loss=0.0124
+epoch=23 step=120/178 loss=0.0175
+epoch=23 step=140/178 loss=0.0209
+epoch=23 step=160/178 loss=0.0084
+epoch=23 train_loss=0.0167 train_contrastive=0.0279 train_regression=0.0111 val_loss=0.0312 val_contrastive=0.0855 val_regression=0.0141
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0312 epoch=23
+epoch=24 step=20/178 loss=0.0410
+epoch=24 step=40/178 loss=0.0084
+epoch=24 step=60/178 loss=0.0100
+epoch=24 step=80/178 loss=0.0537
+epoch=24 step=100/178 loss=0.0116
+epoch=24 step=120/178 loss=0.0194
+epoch=24 step=140/178 loss=0.0057
+epoch=24 step=160/178 loss=0.0064
+epoch=24 train_loss=0.0163 train_contrastive=0.0260 train_regression=0.0111 val_loss=0.0383 val_contrastive=0.1163 val_regression=0.0150
+epoch=25 step=20/178 loss=0.0166
+epoch=25 step=40/178 loss=0.0158
+epoch=25 step=60/178 loss=0.0167
+epoch=25 step=80/178 loss=0.0081
+epoch=25 step=100/178 loss=0.0102
+epoch=25 step=120/178 loss=0.0106
+epoch=25 step=140/178 loss=0.0273
+epoch=25 step=160/178 loss=0.0065
+epoch=25 train_loss=0.0153 train_contrastive=0.0207 train_regression=0.0111 val_loss=0.0369 val_contrastive=0.0945 val_regression=0.0180
+epoch=26 step=20/178 loss=0.0075
+epoch=26 step=40/178 loss=0.1161
+epoch=26 step=60/178 loss=0.0174
+epoch=26 step=80/178 loss=0.0112
+epoch=26 step=100/178 loss=0.0180
+epoch=26 step=120/178 loss=0.0098
+epoch=26 step=140/178 loss=0.0090
+epoch=26 step=160/178 loss=0.0116
+epoch=26 train_loss=0.0162 train_contrastive=0.0278 train_regression=0.0107 val_loss=0.0282 val_contrastive=0.0757 val_regression=0.0131
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0282 epoch=26
+epoch=27 step=20/178 loss=0.0073
+epoch=27 step=40/178 loss=0.0076
+epoch=27 step=60/178 loss=0.0119
+epoch=27 step=80/178 loss=0.0053
+epoch=27 step=100/178 loss=0.0240
+epoch=27 step=120/178 loss=0.0343
+epoch=27 step=140/178 loss=0.0066
+epoch=27 step=160/178 loss=0.0222
+epoch=27 train_loss=0.0153 train_contrastive=0.0242 train_regression=0.0105 val_loss=0.0389 val_contrastive=0.0921 val_regression=0.0205
+epoch=28 step=20/178 loss=0.0118
+epoch=28 step=40/178 loss=0.0071
+epoch=28 step=60/178 loss=0.0061
+epoch=28 step=80/178 loss=0.0142
+epoch=28 step=100/178 loss=0.0090
+epoch=28 step=120/178 loss=0.0122
+epoch=28 step=140/178 loss=0.0090
+epoch=28 step=160/178 loss=0.0091
+epoch=28 train_loss=0.0151 train_contrastive=0.0243 train_regression=0.0103 val_loss=0.0345 val_contrastive=0.0873 val_regression=0.0171
+epoch=29 step=20/178 loss=0.0369
+epoch=29 step=40/178 loss=0.0107
+epoch=29 step=60/178 loss=0.0153
+epoch=29 step=80/178 loss=0.0074
+epoch=29 step=100/178 loss=0.0085
+epoch=29 step=120/178 loss=0.0288
+epoch=29 step=140/178 loss=0.0208
+epoch=29 step=160/178 loss=0.0088
+epoch=29 train_loss=0.0127 train_contrastive=0.0151 train_regression=0.0097 val_loss=0.0364 val_contrastive=0.0829 val_regression=0.0198
+epoch=30 step=20/178 loss=0.0186
+epoch=30 step=40/178 loss=0.0104
+epoch=30 step=60/178 loss=0.0285
+epoch=30 step=80/178 loss=0.0220
+epoch=30 step=100/178 loss=0.0176
+epoch=30 step=120/178 loss=0.0163
+epoch=30 step=140/178 loss=0.0166
+epoch=30 step=160/178 loss=0.0054
+epoch=30 train_loss=0.0127 train_contrastive=0.0165 train_regression=0.0094 val_loss=0.0323 val_contrastive=0.0615 val_regression=0.0200
+epoch=31 step=20/178 loss=0.0205
+epoch=31 step=40/178 loss=0.0076
+epoch=31 step=60/178 loss=0.0095
+epoch=31 step=80/178 loss=0.0150
+epoch=31 step=100/178 loss=0.0316
+epoch=31 step=120/178 loss=0.0069
+epoch=31 step=140/178 loss=0.0106
+epoch=31 step=160/178 loss=0.0173
+epoch=31 train_loss=0.0133 train_contrastive=0.0179 train_regression=0.0097 val_loss=0.0327 val_contrastive=0.0591 val_regression=0.0208
+epoch=32 step=20/178 loss=0.0118
+epoch=32 step=40/178 loss=0.0116
+epoch=32 step=60/178 loss=0.0037
+epoch=32 step=80/178 loss=0.0199
+epoch=32 step=100/178 loss=0.0065
+epoch=32 step=120/178 loss=0.0160
+epoch=32 step=140/178 loss=0.0137
+epoch=32 step=160/178 loss=0.0051
+epoch=32 train_loss=0.0118 train_contrastive=0.0151 train_regression=0.0088 val_loss=0.0674 val_contrastive=0.1351 val_regression=0.0403
+epoch=33 step=20/178 loss=0.0059
+epoch=33 step=40/178 loss=0.0102
+epoch=33 step=60/178 loss=0.0075
+epoch=33 step=80/178 loss=0.0228
+epoch=33 step=100/178 loss=0.0106
+epoch=33 step=120/178 loss=0.0062
+epoch=33 step=140/178 loss=0.0184
+epoch=33 step=160/178 loss=0.0140
+epoch=33 train_loss=0.0125 train_contrastive=0.0158 train_regression=0.0094 val_loss=0.0478 val_contrastive=0.0985 val_regression=0.0281
+epoch=34 step=20/178 loss=0.0067
+epoch=34 step=40/178 loss=0.0124
+epoch=34 step=60/178 loss=0.0044
+epoch=34 step=80/178 loss=0.0126
+epoch=34 step=100/178 loss=0.0133
+epoch=34 step=120/178 loss=0.0088
+epoch=34 step=140/178 loss=0.0084
+epoch=34 step=160/178 loss=0.0111
+epoch=34 train_loss=0.0119 train_contrastive=0.0117 train_regression=0.0096 val_loss=0.0279 val_contrastive=0.0793 val_regression=0.0121
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0279 epoch=34
+epoch=35 step=20/178 loss=0.0077
+epoch=35 step=40/178 loss=0.0071
+epoch=35 step=60/178 loss=0.0083
+epoch=35 step=80/178 loss=0.0123
+epoch=35 step=100/178 loss=0.0086
+epoch=35 step=120/178 loss=0.0397
+epoch=35 step=140/178 loss=0.0774
+epoch=35 step=160/178 loss=0.0098
+epoch=35 train_loss=0.0130 train_contrastive=0.0187 train_regression=0.0093 val_loss=0.0437 val_contrastive=0.0831 val_regression=0.0271
+epoch=36 step=20/178 loss=0.0063
+epoch=36 step=40/178 loss=0.0098
+epoch=36 step=60/178 loss=0.0045
+epoch=36 step=80/178 loss=0.0123
+epoch=36 step=100/178 loss=0.0067
+epoch=36 step=120/178 loss=0.0101
+epoch=36 step=140/178 loss=0.0133
+epoch=36 step=160/178 loss=0.0192
+epoch=36 train_loss=0.0116 train_contrastive=0.0148 train_regression=0.0086 val_loss=0.0230 val_contrastive=0.0541 val_regression=0.0122
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0230 epoch=36
+epoch=37 step=20/178 loss=0.0087
+epoch=37 step=40/178 loss=0.0175
+epoch=37 step=60/178 loss=0.0099
+epoch=37 step=80/178 loss=0.0057
+epoch=37 step=100/178 loss=0.0131
+epoch=37 step=120/178 loss=0.0404
+epoch=37 step=140/178 loss=0.0066
+epoch=37 step=160/178 loss=0.0130
+epoch=37 train_loss=0.0107 train_contrastive=0.0112 train_regression=0.0084 val_loss=0.0317 val_contrastive=0.1081 val_regression=0.0101
+epoch=38 step=20/178 loss=0.0157
+epoch=38 step=40/178 loss=0.0060
+epoch=38 step=60/178 loss=0.0111
+epoch=38 step=80/178 loss=0.0418
+epoch=38 step=100/178 loss=0.0085
+epoch=38 step=120/178 loss=0.0116
+epoch=38 step=140/178 loss=0.0073
+epoch=38 step=160/178 loss=0.0072
+epoch=38 train_loss=0.0120 train_contrastive=0.0141 train_regression=0.0092 val_loss=0.0467 val_contrastive=0.1251 val_regression=0.0217
+epoch=39 step=20/178 loss=0.0186
+epoch=39 step=40/178 loss=0.0054
+epoch=39 step=60/178 loss=0.0075
+epoch=39 step=80/178 loss=0.0081
+epoch=39 step=100/178 loss=0.0043
+epoch=39 step=120/178 loss=0.0063
+epoch=39 step=140/178 loss=0.0152
+epoch=39 step=160/178 loss=0.0068
+epoch=39 train_loss=0.0135 train_contrastive=0.0201 train_regression=0.0094 val_loss=0.0174 val_contrastive=0.0357 val_regression=0.0102
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0174 epoch=39
+epoch=40 step=20/178 loss=0.0131
+epoch=40 step=40/178 loss=0.0122
+epoch=40 step=60/178 loss=0.0090
+epoch=40 step=80/178 loss=0.0063
+epoch=40 step=100/178 loss=0.0095
+epoch=40 step=120/178 loss=0.0043
+epoch=40 step=140/178 loss=0.0061
+epoch=40 step=160/178 loss=0.0087
+epoch=40 train_loss=0.0109 train_contrastive=0.0118 train_regression=0.0086 val_loss=0.0261 val_contrastive=0.0544 val_regression=0.0152
+epoch=41 step=20/178 loss=0.0091
+epoch=41 step=40/178 loss=0.0056
+epoch=41 step=60/178 loss=0.0058
+epoch=41 step=80/178 loss=0.0080
+epoch=41 step=100/178 loss=0.0094
+epoch=41 step=120/178 loss=0.0075
+epoch=41 step=140/178 loss=0.0336
+epoch=41 step=160/178 loss=0.0171
+epoch=41 train_loss=0.0099 train_contrastive=0.0101 train_regression=0.0079 val_loss=0.0144 val_contrastive=0.0261 val_regression=0.0092
+saved_best runs/foundation/medicalnet_layer4_regalign_best.pt val_loss=0.0144 epoch=41
+epoch=42 step=20/178 loss=0.0062
+epoch=42 step=40/178 loss=0.0066
+epoch=42 step=60/178 loss=0.0043
+epoch=42 step=80/178 loss=0.0054
+epoch=42 step=100/178 loss=0.0150
+epoch=42 step=120/178 loss=0.0050
+epoch=42 step=140/178 loss=0.0058
+epoch=42 step=160/178 loss=0.0126
+epoch=42 train_loss=0.0084 train_contrastive=0.0058 train_regression=0.0073 val_loss=0.0148 val_contrastive=0.0231 val_regression=0.0101
+epoch=43 step=20/178 loss=0.0177
+epoch=43 step=40/178 loss=0.0083
+epoch=43 step=60/178 loss=0.0041
+epoch=43 step=80/178 loss=0.0098
+epoch=43 step=100/178 loss=0.0083
+epoch=43 step=120/178 loss=0.0072
+epoch=43 step=140/178 loss=0.0085
+epoch=43 step=160/178 loss=0.0063
+epoch=43 train_loss=0.0091 train_contrastive=0.0077 train_regression=0.0076 val_loss=0.0274 val_contrastive=0.0908 val_regression=0.0092
+epoch=44 step=20/178 loss=0.0082
+epoch=44 step=40/178 loss=0.0043
+epoch=44 step=60/178 loss=0.0069
+epoch=44 step=80/178 loss=0.0117
+epoch=44 step=100/178 loss=0.0042
+epoch=44 step=120/178 loss=0.0041
+epoch=44 step=140/178 loss=0.0086
+epoch=44 step=160/178 loss=0.0067
+epoch=44 train_loss=0.0091 train_contrastive=0.0074 train_regression=0.0076 val_loss=0.0312 val_contrastive=0.0403 val_regression=0.0231
+epoch=45 step=20/178 loss=0.0109
+epoch=45 step=40/178 loss=0.0067
+epoch=45 step=60/178 loss=0.0073
+epoch=45 step=80/178 loss=0.1179
+epoch=45 step=100/178 loss=0.0113
+epoch=45 step=120/178 loss=0.0273
+epoch=45 step=140/178 loss=0.0249
+epoch=45 step=160/178 loss=0.0077
+epoch=45 train_loss=0.0106 train_contrastive=0.0139 train_regression=0.0078 val_loss=0.0526 val_contrastive=0.1484 val_regression=0.0230
+epoch=46 step=20/178 loss=0.0156
+epoch=46 step=40/178 loss=0.0102
+epoch=46 step=60/178 loss=0.0075
+epoch=46 step=80/178 loss=0.0090
+epoch=46 step=100/178 loss=0.0131
+epoch=46 step=120/178 loss=0.0099
+epoch=46 step=140/178 loss=0.0044
+epoch=46 step=160/178 loss=0.0101
+epoch=46 train_loss=0.0110 train_contrastive=0.0124 train_regression=0.0085 val_loss=0.0151 val_contrastive=0.0314 val_regression=0.0088
+epoch=47 step=20/178 loss=0.0132
+epoch=47 step=40/178 loss=0.0074
+epoch=47 step=60/178 loss=0.0047
+epoch=47 step=80/178 loss=0.0069
+epoch=47 step=100/178 loss=0.0056
+epoch=47 step=120/178 loss=0.0054
+epoch=47 step=140/178 loss=0.0062
+epoch=47 step=160/178 loss=0.0091
+epoch=47 train_loss=0.0083 train_contrastive=0.0066 train_regression=0.0070 val_loss=0.0274 val_contrastive=0.0309 val_regression=0.0212
+epoch=48 step=20/178 loss=0.0123
+epoch=48 step=40/178 loss=0.0057
+epoch=48 step=60/178 loss=0.0040
+epoch=48 step=80/178 loss=0.0038
+epoch=48 step=100/178 loss=0.0058
+epoch=48 step=120/178 loss=0.0068
+epoch=48 step=140/178 loss=0.0036
+epoch=48 step=160/178 loss=0.0136
+epoch=48 train_loss=0.0076 train_contrastive=0.0040 train_regression=0.0068 val_loss=0.0170 val_contrastive=0.0404 val_regression=0.0089
+epoch=49 step=20/178 loss=0.0119
+epoch=49 step=40/178 loss=0.0044
+epoch=49 step=60/178 loss=0.0302
+epoch=49 step=80/178 loss=0.0093
+epoch=49 step=100/178 loss=0.0128
+epoch=49 step=120/178 loss=0.0049
+epoch=49 step=140/178 loss=0.0055
+epoch=49 step=160/178 loss=0.0143
+epoch=49 train_loss=0.0113 train_contrastive=0.0144 train_regression=0.0084 val_loss=0.0284 val_contrastive=0.0891 val_regression=0.0106
+epoch=50 step=20/178 loss=0.0160
+epoch=50 step=40/178 loss=0.0087
+epoch=50 step=60/178 loss=0.0074
+epoch=50 step=80/178 loss=0.0065
+epoch=50 step=100/178 loss=0.0170
+epoch=50 step=120/178 loss=0.0124
+epoch=50 step=140/178 loss=0.0099
+epoch=50 step=160/178 loss=0.0085
+epoch=50 train_loss=0.0132 train_contrastive=0.0182 train_regression=0.0095 val_loss=0.0375 val_contrastive=0.0633 val_regression=0.0249
+saved runs/foundation/medicalnet_layer4_regalign.pt

logs/pet_suvr_baseline_20260514_053729.log ADDED Viewed

	@@ -0,0 +1,45 @@

+Traceback (most recent call last):
+  File "/data/Albus/Brain/scripts/train_pet_vlm_baseline.py", line 141, in <module>
+    main()
+    ~~~~^^
+  File "/data/Albus/Brain/scripts/train_pet_vlm_baseline.py", line 111, in main
+    outputs = model(image, suvr)
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+           ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/data/Albus/Brain/scripts/train_pet_vlm_baseline.py", line 61, in forward
+    pet_z = nn.functional.normalize(self.pet_encoder(image), dim=-1)
+                                    ~~~~~~~~~~~~~~~~^^^^^^^
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+           ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/data/Albus/Brain/scripts/train_pet_vlm_baseline.py", line 34, in forward
+    x = self.net(image).flatten(1)
+        ~~~~~~~~^^^^^^^
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+           ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/container.py", line 253, in forward
+    input = module(input)
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+           ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/conv.py", line 723, in forward
+    return self._conv_forward(input, self.weight, self.bias)
+           ~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/data/Albus/envs/brain/lib/python3.13/site-packages/torch/nn/modules/conv.py", line 718, in _conv_forward
+    return F.conv3d(
+           ~~~~~~~~^
+        input, weight, bias, self.stride, self.padding, self.dilation, self.groups
+        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+    )
+    ^
+RuntimeError: Input type (double) and bias type (float) should be the same

logs/remap_pet_clinicalbert_text_alignment.log ADDED Viewed

	@@ -0,0 +1,31 @@

+epoch=1 train_loss=2.050857 val_loss=2.023221
+saved_best runs/vlm/remap_pet_clinicalbert_text_alignment_best.pt val_loss=2.023221
+epoch=2 train_loss=1.949654 val_loss=2.057414
+epoch=3 train_loss=1.792545 val_loss=1.741596
+saved_best runs/vlm/remap_pet_clinicalbert_text_alignment_best.pt val_loss=1.741596
+epoch=4 train_loss=1.686597 val_loss=1.575960
+saved_best runs/vlm/remap_pet_clinicalbert_text_alignment_best.pt val_loss=1.575960
+epoch=5 train_loss=1.457122 val_loss=1.649946
+epoch=6 train_loss=1.383680 val_loss=1.551173
+saved_best runs/vlm/remap_pet_clinicalbert_text_alignment_best.pt val_loss=1.551173
+epoch=7 train_loss=1.412239 val_loss=1.793168
+epoch=8 train_loss=1.452098 val_loss=1.503126
+saved_best runs/vlm/remap_pet_clinicalbert_text_alignment_best.pt val_loss=1.503126
+epoch=9 train_loss=1.199663 val_loss=1.481054
+saved_best runs/vlm/remap_pet_clinicalbert_text_alignment_best.pt val_loss=1.481054
+epoch=10 train_loss=1.264917 val_loss=1.499033
+epoch=11 train_loss=1.166008 val_loss=1.358933
+saved_best runs/vlm/remap_pet_clinicalbert_text_alignment_best.pt val_loss=1.358933
+epoch=12 train_loss=1.100818 val_loss=1.334609
+saved_best runs/vlm/remap_pet_clinicalbert_text_alignment_best.pt val_loss=1.334609
+epoch=13 train_loss=1.123345 val_loss=1.457138
+epoch=14 train_loss=1.122591 val_loss=1.316918
+saved_best runs/vlm/remap_pet_clinicalbert_text_alignment_best.pt val_loss=1.316918
+epoch=15 train_loss=1.028799 val_loss=1.517640
+epoch=16 train_loss=1.017136 val_loss=1.161362
+saved_best runs/vlm/remap_pet_clinicalbert_text_alignment_best.pt val_loss=1.161362
+epoch=17 train_loss=0.954026 val_loss=1.292254
+epoch=18 train_loss=0.939139 val_loss=1.260427
+epoch=19 train_loss=0.964784 val_loss=1.296234
+epoch=20 train_loss=0.995706 val_loss=1.401276
+saved runs/vlm/remap_pet_clinicalbert_text_alignment.pt

logs/remap_pet_layer4_cw05_20260518_001809.log ADDED Viewed

	@@ -0,0 +1,921 @@

+device=cuda backbone=medicalnet encoder_scope=layer4 contrastive_weight=0.5 regression_weight=1.0 train=710 val=152
+epoch=1 step=10/178 loss=1.5546
+epoch=1 step=20/178 loss=1.2528
+epoch=1 step=30/178 loss=1.0056
+epoch=1 step=40/178 loss=0.9843
+epoch=1 step=50/178 loss=0.8715
+epoch=1 step=60/178 loss=0.7154
+epoch=1 step=70/178 loss=0.7661
+epoch=1 step=80/178 loss=0.7476
+epoch=1 step=90/178 loss=0.7010
+epoch=1 step=100/178 loss=0.7132
+epoch=1 step=110/178 loss=0.8336
+epoch=1 step=120/178 loss=0.5922
+epoch=1 step=130/178 loss=0.6447
+epoch=1 step=140/178 loss=0.6022
+epoch=1 step=150/178 loss=0.5228
+epoch=1 step=160/178 loss=0.5160
+epoch=1 step=170/178 loss=0.6245
+epoch=1 train_loss=0.8176 train_contrastive=1.0707 train_regression=0.2822 val_loss=0.6879 val_contrastive=0.9800 val_regression=0.1979
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.6879 epoch=1
+epoch=2 step=10/178 loss=0.3111
+epoch=2 step=20/178 loss=0.4726
+epoch=2 step=30/178 loss=0.6651
+epoch=2 step=40/178 loss=0.4262
+epoch=2 step=50/178 loss=0.4203
+epoch=2 step=60/178 loss=0.4443
+epoch=2 step=70/178 loss=0.3662
+epoch=2 step=80/178 loss=0.4006
+epoch=2 step=90/178 loss=0.3361
+epoch=2 step=100/178 loss=0.2482
+epoch=2 step=110/178 loss=0.2855
+epoch=2 step=120/178 loss=0.1775
+epoch=2 step=130/178 loss=0.2561
+epoch=2 step=140/178 loss=0.3227
+epoch=2 step=150/178 loss=0.1498
+epoch=2 step=160/178 loss=0.1552
+epoch=2 step=170/178 loss=0.1645
+epoch=2 train_loss=0.3413 train_contrastive=0.4827 train_regression=0.1000 val_loss=0.6581 val_contrastive=0.8968 val_regression=0.2097
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.6581 epoch=2
+epoch=3 step=10/178 loss=0.1924
+epoch=3 step=20/178 loss=0.1615
+epoch=3 step=30/178 loss=0.1694
+epoch=3 step=40/178 loss=0.1237
+epoch=3 step=50/178 loss=0.3640
+epoch=3 step=60/178 loss=0.2168
+epoch=3 step=70/178 loss=0.1498
+epoch=3 step=80/178 loss=0.1941
+epoch=3 step=90/178 loss=0.1713
+epoch=3 step=100/178 loss=0.3401
+epoch=3 step=110/178 loss=0.1357
+epoch=3 step=120/178 loss=0.1989
+epoch=3 step=130/178 loss=0.1399
+epoch=3 step=140/178 loss=0.2238
+epoch=3 step=150/178 loss=0.1396
+epoch=3 step=160/178 loss=0.1680
+epoch=3 step=170/178 loss=0.1487
+epoch=3 train_loss=0.1971 train_contrastive=0.2735 train_regression=0.0604 val_loss=0.3178 val_contrastive=0.4660 val_regression=0.0848
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.3178 epoch=3
+epoch=4 step=10/178 loss=0.1035
+epoch=4 step=20/178 loss=0.1660
+epoch=4 step=30/178 loss=0.0788
+epoch=4 step=40/178 loss=0.2376
+epoch=4 step=50/178 loss=0.1254
+epoch=4 step=60/178 loss=0.1664
+epoch=4 step=70/178 loss=0.1509
+epoch=4 step=80/178 loss=0.0896
+epoch=4 step=90/178 loss=0.1049
+epoch=4 step=100/178 loss=0.1374
+epoch=4 step=110/178 loss=0.0653
+epoch=4 step=120/178 loss=0.0548
+epoch=4 step=130/178 loss=0.2146
+epoch=4 step=140/178 loss=0.0862
+epoch=4 step=150/178 loss=0.1177
+epoch=4 step=160/178 loss=0.0471
+epoch=4 step=170/178 loss=0.0432
+epoch=4 train_loss=0.1339 train_contrastive=0.1793 train_regression=0.0442 val_loss=0.3990 val_contrastive=0.5791 val_regression=0.1094
+epoch=5 step=10/178 loss=0.0415
+epoch=5 step=20/178 loss=0.1181
+epoch=5 step=30/178 loss=0.1415
+epoch=5 step=40/178 loss=0.0669
+epoch=5 step=50/178 loss=0.2588
+epoch=5 step=60/178 loss=0.0394
+epoch=5 step=70/178 loss=0.1626
+epoch=5 step=80/178 loss=0.0433
+epoch=5 step=90/178 loss=0.0646
+epoch=5 step=100/178 loss=0.1819
+epoch=5 step=110/178 loss=0.0966
+epoch=5 step=120/178 loss=0.0547
+epoch=5 step=130/178 loss=0.0888
+epoch=5 step=140/178 loss=0.0972
+epoch=5 step=150/178 loss=0.0649
+epoch=5 step=160/178 loss=0.0279
+epoch=5 step=170/178 loss=0.1538
+epoch=5 train_loss=0.1052 train_contrastive=0.1376 train_regression=0.0364 val_loss=0.2510 val_contrastive=0.3530 val_regression=0.0745
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.2510 epoch=5
+epoch=6 step=10/178 loss=0.0856
+epoch=6 step=20/178 loss=0.0840
+epoch=6 step=30/178 loss=0.0679
+epoch=6 step=40/178 loss=0.0847
+epoch=6 step=50/178 loss=0.1179
+epoch=6 step=60/178 loss=0.0383
+epoch=6 step=70/178 loss=0.1044
+epoch=6 step=80/178 loss=0.0993
+epoch=6 step=90/178 loss=0.1270
+epoch=6 step=100/178 loss=0.0250
+epoch=6 step=110/178 loss=0.0548
+epoch=6 step=120/178 loss=0.0908
+epoch=6 step=130/178 loss=0.0327
+epoch=6 step=140/178 loss=0.0502
+epoch=6 step=150/178 loss=0.0509
+epoch=6 step=160/178 loss=0.1680
+epoch=6 step=170/178 loss=0.0518
+epoch=6 train_loss=0.0850 train_contrastive=0.1037 train_regression=0.0331 val_loss=0.3682 val_contrastive=0.4773 val_regression=0.1296
+epoch=7 step=10/178 loss=0.1542
+epoch=7 step=20/178 loss=0.1208
+epoch=7 step=30/178 loss=0.0476
+epoch=7 step=40/178 loss=0.0647
+epoch=7 step=50/178 loss=0.0983
+epoch=7 step=60/178 loss=0.1245
+epoch=7 step=70/178 loss=0.0345
+epoch=7 step=80/178 loss=0.0294
+epoch=7 step=90/178 loss=0.0401
+epoch=7 step=100/178 loss=0.0909
+epoch=7 step=110/178 loss=0.0203
+epoch=7 step=120/178 loss=0.0547
+epoch=7 step=130/178 loss=0.0988
+epoch=7 step=140/178 loss=0.1945
+epoch=7 step=150/178 loss=0.0535
+epoch=7 step=160/178 loss=0.0779
+epoch=7 step=170/178 loss=0.0928
+epoch=7 train_loss=0.0772 train_contrastive=0.0904 train_regression=0.0321 val_loss=0.1633 val_contrastive=0.2556 val_regression=0.0355
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.1633 epoch=7
+epoch=8 step=10/178 loss=0.0860
+epoch=8 step=20/178 loss=0.0576
+epoch=8 step=30/178 loss=0.0308
+epoch=8 step=40/178 loss=0.0449
+epoch=8 step=50/178 loss=0.1274
+epoch=8 step=60/178 loss=0.0213
+epoch=8 step=70/178 loss=0.0347
+epoch=8 step=80/178 loss=0.0382
+epoch=8 step=90/178 loss=0.1131
+epoch=8 step=100/178 loss=0.0455
+epoch=8 step=110/178 loss=0.0272
+epoch=8 step=120/178 loss=0.0431
+epoch=8 step=130/178 loss=0.0583
+epoch=8 step=140/178 loss=0.1814
+epoch=8 step=150/178 loss=0.0524
+epoch=8 step=160/178 loss=0.0551
+epoch=8 step=170/178 loss=0.1310
+epoch=8 train_loss=0.0638 train_contrastive=0.0696 train_regression=0.0290 val_loss=0.2277 val_contrastive=0.3234 val_regression=0.0660
+epoch=9 step=10/178 loss=0.0431
+epoch=9 step=20/178 loss=0.0416
+epoch=9 step=30/178 loss=0.0762
+epoch=9 step=40/178 loss=0.0457
+epoch=9 step=50/178 loss=0.0408
+epoch=9 step=60/178 loss=0.1224
+epoch=9 step=70/178 loss=0.0951
+epoch=9 step=80/178 loss=0.0547
+epoch=9 step=90/178 loss=0.0429
+epoch=9 step=100/178 loss=0.0750
+epoch=9 step=110/178 loss=0.0286
+epoch=9 step=120/178 loss=0.1846
+epoch=9 step=130/178 loss=0.0325
+epoch=9 step=140/178 loss=0.0516
+epoch=9 step=150/178 loss=0.0194
+epoch=9 step=160/178 loss=0.0496
+epoch=9 step=170/178 loss=0.0229
+epoch=9 train_loss=0.0651 train_contrastive=0.0729 train_regression=0.0287 val_loss=0.1572 val_contrastive=0.2314 val_regression=0.0416
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.1572 epoch=9
+epoch=10 step=10/178 loss=0.0460
+epoch=10 step=20/178 loss=0.0273
+epoch=10 step=30/178 loss=0.0449
+epoch=10 step=40/178 loss=0.0608
+epoch=10 step=50/178 loss=0.0274
+epoch=10 step=60/178 loss=0.0463
+epoch=10 step=70/178 loss=0.0375
+epoch=10 step=80/178 loss=0.0371
+epoch=10 step=90/178 loss=0.0374
+epoch=10 step=100/178 loss=0.0637
+epoch=10 step=110/178 loss=0.0161
+epoch=10 step=120/178 loss=0.0349
+epoch=10 step=130/178 loss=0.0678
+epoch=10 step=140/178 loss=0.0558
+epoch=10 step=150/178 loss=0.0214
+epoch=10 step=160/178 loss=0.0224
+epoch=10 step=170/178 loss=0.0257
+epoch=10 train_loss=0.0486 train_contrastive=0.0488 train_regression=0.0242 val_loss=0.1285 val_contrastive=0.1802 val_regression=0.0384
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.1285 epoch=10
+epoch=11 step=10/178 loss=0.0538
+epoch=11 step=20/178 loss=0.0192
+epoch=11 step=30/178 loss=0.0370
+epoch=11 step=40/178 loss=0.0197
+epoch=11 step=50/178 loss=0.0205
+epoch=11 step=60/178 loss=0.0304
+epoch=11 step=70/178 loss=0.1066
+epoch=11 step=80/178 loss=0.0378
+epoch=11 step=90/178 loss=0.0405
+epoch=11 step=100/178 loss=0.0331
+epoch=11 step=110/178 loss=0.0346
+epoch=11 step=120/178 loss=0.0179
+epoch=11 step=130/178 loss=0.0314
+epoch=11 step=140/178 loss=0.0280
+epoch=11 step=150/178 loss=0.0130
+epoch=11 step=160/178 loss=0.0224
+epoch=11 step=170/178 loss=0.0278
+epoch=11 train_loss=0.0501 train_contrastive=0.0528 train_regression=0.0237 val_loss=0.1280 val_contrastive=0.1947 val_regression=0.0306
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.1280 epoch=11
+epoch=12 step=10/178 loss=0.0240
+epoch=12 step=20/178 loss=0.0400
+epoch=12 step=30/178 loss=0.0303
+epoch=12 step=40/178 loss=0.0488
+epoch=12 step=50/178 loss=0.0302
+epoch=12 step=60/178 loss=0.0338
+epoch=12 step=70/178 loss=0.0242
+epoch=12 step=80/178 loss=0.0558
+epoch=12 step=90/178 loss=0.0487
+epoch=12 step=100/178 loss=0.2737
+epoch=12 step=110/178 loss=0.0803
+epoch=12 step=120/178 loss=0.0977
+epoch=12 step=130/178 loss=0.2132
+epoch=12 step=140/178 loss=0.0312
+epoch=12 step=150/178 loss=0.0151
+epoch=12 step=160/178 loss=0.0530
+epoch=12 step=170/178 loss=0.0216
+epoch=12 train_loss=0.0614 train_contrastive=0.0700 train_regression=0.0264 val_loss=0.1038 val_contrastive=0.1412 val_regression=0.0332
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.1038 epoch=12
+epoch=13 step=10/178 loss=0.0440
+epoch=13 step=20/178 loss=0.0881
+epoch=13 step=30/178 loss=0.0744
+epoch=13 step=40/178 loss=0.0144
+epoch=13 step=50/178 loss=0.0430
+epoch=13 step=60/178 loss=0.1645
+epoch=13 step=70/178 loss=0.1044
+epoch=13 step=80/178 loss=0.0666
+epoch=13 step=90/178 loss=0.0325
+epoch=13 step=100/178 loss=0.0236
+epoch=13 step=110/178 loss=0.0297
+epoch=13 step=120/178 loss=0.0174
+epoch=13 step=130/178 loss=0.0563
+epoch=13 step=140/178 loss=0.0233
+epoch=13 step=150/178 loss=0.0186
+epoch=13 step=160/178 loss=0.0162
+epoch=13 step=170/178 loss=0.0344
+epoch=13 train_loss=0.0449 train_contrastive=0.0456 train_regression=0.0221 val_loss=0.0942 val_contrastive=0.1221 val_regression=0.0332
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.0942 epoch=13
+epoch=14 step=10/178 loss=0.0144
+epoch=14 step=20/178 loss=0.0273
+epoch=14 step=30/178 loss=0.0180
+epoch=14 step=40/178 loss=0.0373
+epoch=14 step=50/178 loss=0.0214
+epoch=14 step=60/178 loss=0.0232
+epoch=14 step=70/178 loss=0.0734
+epoch=14 step=80/178 loss=0.0236
+epoch=14 step=90/178 loss=0.0588
+epoch=14 step=100/178 loss=0.0165
+epoch=14 step=110/178 loss=0.0319
+epoch=14 step=120/178 loss=0.0478
+epoch=14 step=130/178 loss=0.0343
+epoch=14 step=140/178 loss=0.0323
+epoch=14 step=150/178 loss=0.0210
+epoch=14 step=160/178 loss=0.0593
+epoch=14 step=170/178 loss=0.0257
+epoch=14 train_loss=0.0367 train_contrastive=0.0306 train_regression=0.0214 val_loss=0.1407 val_contrastive=0.1877 val_regression=0.0468
+epoch=15 step=10/178 loss=0.0134
+epoch=15 step=20/178 loss=0.0303
+epoch=15 step=30/178 loss=0.0197
+epoch=15 step=40/178 loss=0.0752
+epoch=15 step=50/178 loss=0.0603
+epoch=15 step=60/178 loss=0.0165
+epoch=15 step=70/178 loss=0.0202
+epoch=15 step=80/178 loss=0.0264
+epoch=15 step=90/178 loss=0.0260
+epoch=15 step=100/178 loss=0.0155
+epoch=15 step=110/178 loss=0.0236
+epoch=15 step=120/178 loss=0.0196
+epoch=15 step=130/178 loss=0.0125
+epoch=15 step=140/178 loss=0.0272
+epoch=15 step=150/178 loss=0.0317
+epoch=15 step=160/178 loss=0.0129
+epoch=15 step=170/178 loss=0.0496
+epoch=15 train_loss=0.0388 train_contrastive=0.0373 train_regression=0.0201 val_loss=0.1244 val_contrastive=0.1611 val_regression=0.0438
+epoch=16 step=10/178 loss=0.0171
+epoch=16 step=20/178 loss=0.0216
+epoch=16 step=30/178 loss=0.0124
+epoch=16 step=40/178 loss=0.0358
+epoch=16 step=50/178 loss=0.0162
+epoch=16 step=60/178 loss=0.0508
+epoch=16 step=70/178 loss=0.0603
+epoch=16 step=80/178 loss=0.0431
+epoch=16 step=90/178 loss=0.0240
+epoch=16 step=100/178 loss=0.0186
+epoch=16 step=110/178 loss=0.0254
+epoch=16 step=120/178 loss=0.0144
+epoch=16 step=130/178 loss=0.0303
+epoch=16 step=140/178 loss=0.0136
+epoch=16 step=150/178 loss=0.0335
+epoch=16 step=160/178 loss=0.0274
+epoch=16 step=170/178 loss=0.0248
+epoch=16 train_loss=0.0386 train_contrastive=0.0379 train_regression=0.0196 val_loss=0.1289 val_contrastive=0.1792 val_regression=0.0393
+epoch=17 step=10/178 loss=0.0188
+epoch=17 step=20/178 loss=0.0165
+epoch=17 step=30/178 loss=0.0089
+epoch=17 step=40/178 loss=0.0473
+epoch=17 step=50/178 loss=0.0285
+epoch=17 step=60/178 loss=0.0375
+epoch=17 step=70/178 loss=0.0270
+epoch=17 step=80/178 loss=0.0215
+epoch=17 step=90/178 loss=0.0146
+epoch=17 step=100/178 loss=0.0315
+epoch=17 step=110/178 loss=0.0824
+epoch=17 step=120/178 loss=0.0222
+epoch=17 step=130/178 loss=0.0328
+epoch=17 step=140/178 loss=0.0211
+epoch=17 step=150/178 loss=0.0759
+epoch=17 step=160/178 loss=0.0183
+epoch=17 step=170/178 loss=0.0467
+epoch=17 train_loss=0.0316 train_contrastive=0.0276 train_regression=0.0178 val_loss=0.0773 val_contrastive=0.1089 val_regression=0.0229
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.0773 epoch=17
+epoch=18 step=10/178 loss=0.0597
+epoch=18 step=20/178 loss=0.0602
+epoch=18 step=30/178 loss=0.0375
+epoch=18 step=40/178 loss=0.0338
+epoch=18 step=50/178 loss=0.0162
+epoch=18 step=60/178 loss=0.0736
+epoch=18 step=70/178 loss=0.0095
+epoch=18 step=80/178 loss=0.0334
+epoch=18 step=90/178 loss=0.0263
+epoch=18 step=100/178 loss=0.0125
+epoch=18 step=110/178 loss=0.0901
+epoch=18 step=120/178 loss=0.0150
+epoch=18 step=130/178 loss=0.0410
+epoch=18 step=140/178 loss=0.0475
+epoch=18 step=150/178 loss=0.0271
+epoch=18 step=160/178 loss=0.0259
+epoch=18 step=170/178 loss=0.0185
+epoch=18 train_loss=0.0336 train_contrastive=0.0311 train_regression=0.0180 val_loss=0.1542 val_contrastive=0.2158 val_regression=0.0463
+epoch=19 step=10/178 loss=0.1444
+epoch=19 step=20/178 loss=0.0389
+epoch=19 step=30/178 loss=0.0311
+epoch=19 step=40/178 loss=0.0229
+epoch=19 step=50/178 loss=0.0495
+epoch=19 step=60/178 loss=0.0241
+epoch=19 step=70/178 loss=0.0204
+epoch=19 step=80/178 loss=0.0132
+epoch=19 step=90/178 loss=0.0144
+epoch=19 step=100/178 loss=0.0351
+epoch=19 step=110/178 loss=0.0150
+epoch=19 step=120/178 loss=0.0136
+epoch=19 step=130/178 loss=0.0114
+epoch=19 step=140/178 loss=0.0307
+epoch=19 step=150/178 loss=0.0235
+epoch=19 step=160/178 loss=0.0266
+epoch=19 step=170/178 loss=0.0226
+epoch=19 train_loss=0.0339 train_contrastive=0.0307 train_regression=0.0185 val_loss=0.0823 val_contrastive=0.1161 val_regression=0.0242
+epoch=20 step=10/178 loss=0.0193
+epoch=20 step=20/178 loss=0.0095
+epoch=20 step=30/178 loss=0.0483
+epoch=20 step=40/178 loss=0.0244
+epoch=20 step=50/178 loss=0.0137
+epoch=20 step=60/178 loss=0.0257
+epoch=20 step=70/178 loss=0.0193
+epoch=20 step=80/178 loss=0.0230
+epoch=20 step=90/178 loss=0.0105
+epoch=20 step=100/178 loss=0.0095
+epoch=20 step=110/178 loss=0.0138
+epoch=20 step=120/178 loss=0.0157
+epoch=20 step=130/178 loss=0.0302
+epoch=20 step=140/178 loss=0.0197
+epoch=20 step=150/178 loss=0.0182
+epoch=20 step=160/178 loss=0.0132
+epoch=20 step=170/178 loss=0.0145
+epoch=20 train_loss=0.0265 train_contrastive=0.0208 train_regression=0.0161 val_loss=0.0714 val_contrastive=0.1058 val_regression=0.0185
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.0714 epoch=20
+epoch=21 step=10/178 loss=0.0139
+epoch=21 step=20/178 loss=0.0264
+epoch=21 step=30/178 loss=0.0155
+epoch=21 step=40/178 loss=0.0126
+epoch=21 step=50/178 loss=0.0167
+epoch=21 step=60/178 loss=0.0158
+epoch=21 step=70/178 loss=0.0263
+epoch=21 step=80/178 loss=0.0219
+epoch=21 step=90/178 loss=0.0095
+epoch=21 step=100/178 loss=0.0106
+epoch=21 step=110/178 loss=0.0133
+epoch=21 step=120/178 loss=0.0230
+epoch=21 step=130/178 loss=0.0190
+epoch=21 step=140/178 loss=0.0179
+epoch=21 step=150/178 loss=0.0655
+epoch=21 step=160/178 loss=0.0156
+epoch=21 step=170/178 loss=0.0218
+epoch=21 train_loss=0.0250 train_contrastive=0.0197 train_regression=0.0152 val_loss=0.0830 val_contrastive=0.1260 val_regression=0.0200
+epoch=22 step=10/178 loss=0.0155
+epoch=22 step=20/178 loss=0.0085
+epoch=22 step=30/178 loss=0.0282
+epoch=22 step=40/178 loss=0.1119
+epoch=22 step=50/178 loss=0.1646
+epoch=22 step=60/178 loss=0.0449
+epoch=22 step=70/178 loss=0.0413
+epoch=22 step=80/178 loss=0.0113
+epoch=22 step=90/178 loss=0.0349
+epoch=22 step=100/178 loss=0.0101
+epoch=22 step=110/178 loss=0.0176
+epoch=22 step=120/178 loss=0.0174
+epoch=22 step=130/178 loss=0.0282
+epoch=22 step=140/178 loss=0.0191
+epoch=22 step=150/178 loss=0.1568
+epoch=22 step=160/178 loss=0.0183
+epoch=22 step=170/178 loss=0.0098
+epoch=22 train_loss=0.0292 train_contrastive=0.0250 train_regression=0.0167 val_loss=0.1131 val_contrastive=0.1468 val_regression=0.0397
+epoch=23 step=10/178 loss=0.0210
+epoch=23 step=20/178 loss=0.1164
+epoch=23 step=30/178 loss=0.0417
+epoch=23 step=40/178 loss=0.0218
+epoch=23 step=50/178 loss=0.0281
+epoch=23 step=60/178 loss=0.0165
+epoch=23 step=70/178 loss=0.0300
+epoch=23 step=80/178 loss=0.0184
+epoch=23 step=90/178 loss=0.0243
+epoch=23 step=100/178 loss=0.0346
+epoch=23 step=110/178 loss=0.0236
+epoch=23 step=120/178 loss=0.0101
+epoch=23 step=130/178 loss=0.0250
+epoch=23 step=140/178 loss=0.0848
+epoch=23 step=150/178 loss=0.0119
+epoch=23 step=160/178 loss=0.0162
+epoch=23 step=170/178 loss=0.0183
+epoch=23 train_loss=0.0331 train_contrastive=0.0299 train_regression=0.0181 val_loss=0.0822 val_contrastive=0.1047 val_regression=0.0299
+epoch=24 step=10/178 loss=0.0104
+epoch=24 step=20/178 loss=0.0120
+epoch=24 step=30/178 loss=0.0136
+epoch=24 step=40/178 loss=0.0312
+epoch=24 step=50/178 loss=0.0408
+epoch=24 step=60/178 loss=0.0089
+epoch=24 step=70/178 loss=0.0482
+epoch=24 step=80/178 loss=0.0108
+epoch=24 step=90/178 loss=0.0277
+epoch=24 step=100/178 loss=0.0233
+epoch=24 step=110/178 loss=0.0096
+epoch=24 step=120/178 loss=0.0173
+epoch=24 step=130/178 loss=0.0133
+epoch=24 step=140/178 loss=0.0185
+epoch=24 step=150/178 loss=0.0785
+epoch=24 step=160/178 loss=0.0085
+epoch=24 step=170/178 loss=0.0135
+epoch=24 train_loss=0.0248 train_contrastive=0.0204 train_regression=0.0146 val_loss=0.0656 val_contrastive=0.0897 val_regression=0.0208
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.0656 epoch=24
+epoch=25 step=10/178 loss=0.0584
+epoch=25 step=20/178 loss=0.0210
+epoch=25 step=30/178 loss=0.0262
+epoch=25 step=40/178 loss=0.0131
+epoch=25 step=50/178 loss=0.0101
+epoch=25 step=60/178 loss=0.0118
+epoch=25 step=70/178 loss=0.0088
+epoch=25 step=80/178 loss=0.0302
+epoch=25 step=90/178 loss=0.0097
+epoch=25 step=100/178 loss=0.0139
+epoch=25 step=110/178 loss=0.0179
+epoch=25 step=120/178 loss=0.0115
+epoch=25 step=130/178 loss=0.0145
+epoch=25 step=140/178 loss=0.0094
+epoch=25 step=150/178 loss=0.0691
+epoch=25 step=160/178 loss=0.0241
+epoch=25 step=170/178 loss=0.0146
+epoch=25 train_loss=0.0223 train_contrastive=0.0164 train_regression=0.0141 val_loss=0.0731 val_contrastive=0.0819 val_regression=0.0321
+epoch=26 step=10/178 loss=0.0219
+epoch=26 step=20/178 loss=0.0182
+epoch=26 step=30/178 loss=0.0292
+epoch=26 step=40/178 loss=0.0098
+epoch=26 step=50/178 loss=0.0178
+epoch=26 step=60/178 loss=0.0193
+epoch=26 step=70/178 loss=0.0136
+epoch=26 step=80/178 loss=0.0861
+epoch=26 step=90/178 loss=0.0142
+epoch=26 step=100/178 loss=0.0609
+epoch=26 step=110/178 loss=0.0112
+epoch=26 step=120/178 loss=0.0128
+epoch=26 step=130/178 loss=0.0086
+epoch=26 step=140/178 loss=0.0153
+epoch=26 step=150/178 loss=0.0132
+epoch=26 step=160/178 loss=0.0122
+epoch=26 step=170/178 loss=0.0202
+epoch=26 train_loss=0.0222 train_contrastive=0.0155 train_regression=0.0145 val_loss=0.0523 val_contrastive=0.0605 val_regression=0.0221
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.0523 epoch=26
+epoch=27 step=10/178 loss=0.0105
+epoch=27 step=20/178 loss=0.0127
+epoch=27 step=30/178 loss=0.0164
+epoch=27 step=40/178 loss=0.0107
+epoch=27 step=50/178 loss=0.0278
+epoch=27 step=60/178 loss=0.0078
+epoch=27 step=70/178 loss=0.0099
+epoch=27 step=80/178 loss=0.0125
+epoch=27 step=90/178 loss=0.0746
+epoch=27 step=100/178 loss=0.0093
+epoch=27 step=110/178 loss=0.0098
+epoch=27 step=120/178 loss=0.0154
+epoch=27 step=130/178 loss=0.0126
+epoch=27 step=140/178 loss=0.0222
+epoch=27 step=150/178 loss=0.0210
+epoch=27 step=160/178 loss=0.0100
+epoch=27 step=170/178 loss=0.0106
+epoch=27 train_loss=0.0217 train_contrastive=0.0157 train_regression=0.0138 val_loss=0.0641 val_contrastive=0.0662 val_regression=0.0310
+epoch=28 step=10/178 loss=0.0179
+epoch=28 step=20/178 loss=0.0791
+epoch=28 step=30/178 loss=0.0265
+epoch=28 step=40/178 loss=0.0279
+epoch=28 step=50/178 loss=0.0477
+epoch=28 step=60/178 loss=0.0224
+epoch=28 step=70/178 loss=0.0390
+epoch=28 step=80/178 loss=0.0089
+epoch=28 step=90/178 loss=0.0652
+epoch=28 step=100/178 loss=0.0238
+epoch=28 step=110/178 loss=0.0205
+epoch=28 step=120/178 loss=0.0178
+epoch=28 step=130/178 loss=0.0061
+epoch=28 step=140/178 loss=0.0203
+epoch=28 step=150/178 loss=0.0136
+epoch=28 step=160/178 loss=0.0169
+epoch=28 step=170/178 loss=0.0182
+epoch=28 train_loss=0.0260 train_contrastive=0.0211 train_regression=0.0155 val_loss=0.0539 val_contrastive=0.0508 val_regression=0.0285
+epoch=29 step=10/178 loss=0.0192
+epoch=29 step=20/178 loss=0.0097
+epoch=29 step=30/178 loss=0.0564
+epoch=29 step=40/178 loss=0.0086
+epoch=29 step=50/178 loss=0.0194
+epoch=29 step=60/178 loss=0.0685
+epoch=29 step=70/178 loss=0.0150
+epoch=29 step=80/178 loss=0.0094
+epoch=29 step=90/178 loss=0.0187
+epoch=29 step=100/178 loss=0.0673
+epoch=29 step=110/178 loss=0.0209
+epoch=29 step=120/178 loss=0.0161
+epoch=29 step=130/178 loss=0.0096
+epoch=29 step=140/178 loss=0.0202
+epoch=29 step=150/178 loss=0.0352
+epoch=29 step=160/178 loss=0.0087
+epoch=29 step=170/178 loss=0.0454
+epoch=29 train_loss=0.0242 train_contrastive=0.0192 train_regression=0.0147 val_loss=0.0510 val_contrastive=0.0574 val_regression=0.0223
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.0510 epoch=29
+epoch=30 step=10/178 loss=0.0309
+epoch=30 step=20/178 loss=0.0162
+epoch=30 step=30/178 loss=0.0440
+epoch=30 step=40/178 loss=0.0170
+epoch=30 step=50/178 loss=0.0089
+epoch=30 step=60/178 loss=0.0092
+epoch=30 step=70/178 loss=0.0166
+epoch=30 step=80/178 loss=0.0058
+epoch=30 step=90/178 loss=0.0099
+epoch=30 step=100/178 loss=0.0223
+epoch=30 step=110/178 loss=0.0146
+epoch=30 step=120/178 loss=0.0183
+epoch=30 step=130/178 loss=0.0139
+epoch=30 step=140/178 loss=0.0099
+epoch=30 step=150/178 loss=0.0082
+epoch=30 step=160/178 loss=0.0076
+epoch=30 step=170/178 loss=0.0218
+epoch=30 train_loss=0.0152 train_contrastive=0.0076 train_regression=0.0114 val_loss=0.0524 val_contrastive=0.0597 val_regression=0.0225
+epoch=31 step=10/178 loss=0.0296
+epoch=31 step=20/178 loss=0.0138
+epoch=31 step=30/178 loss=0.0081
+epoch=31 step=40/178 loss=0.0219
+epoch=31 step=50/178 loss=0.0157
+epoch=31 step=60/178 loss=0.0233
+epoch=31 step=70/178 loss=0.0127
+epoch=31 step=80/178 loss=0.0092
+epoch=31 step=90/178 loss=0.0081
+epoch=31 step=100/178 loss=0.0366
+epoch=31 step=110/178 loss=0.0093
+epoch=31 step=120/178 loss=0.0197
+epoch=31 step=130/178 loss=0.0062
+epoch=31 step=140/178 loss=0.0089
+epoch=31 step=150/178 loss=0.0114
+epoch=31 step=160/178 loss=0.0103
+epoch=31 step=170/178 loss=0.0115
+epoch=31 train_loss=0.0154 train_contrastive=0.0081 train_regression=0.0114 val_loss=0.0399 val_contrastive=0.0379 val_regression=0.0209
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.0399 epoch=31
+epoch=32 step=10/178 loss=0.0079
+epoch=32 step=20/178 loss=0.0129
+epoch=32 step=30/178 loss=0.0110
+epoch=32 step=40/178 loss=0.0090
+epoch=32 step=50/178 loss=0.0214
+epoch=32 step=60/178 loss=0.0071
+epoch=32 step=70/178 loss=0.0260
+epoch=32 step=80/178 loss=0.0061
+epoch=32 step=90/178 loss=0.0238
+epoch=32 step=100/178 loss=0.0324
+epoch=32 step=110/178 loss=0.0156
+epoch=32 step=120/178 loss=0.0158
+epoch=32 step=130/178 loss=0.0333
+epoch=32 step=140/178 loss=0.0133
+epoch=32 step=150/178 loss=0.0083
+epoch=32 step=160/178 loss=0.0092
+epoch=32 step=170/178 loss=0.0098
+epoch=32 train_loss=0.0202 train_contrastive=0.0150 train_regression=0.0127 val_loss=0.0338 val_contrastive=0.0324 val_regression=0.0176
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.0338 epoch=32
+epoch=33 step=10/178 loss=0.0087
+epoch=33 step=20/178 loss=0.0083
+epoch=33 step=30/178 loss=0.0135
+epoch=33 step=40/178 loss=0.0088
+epoch=33 step=50/178 loss=0.0095
+epoch=33 step=60/178 loss=0.0134
+epoch=33 step=70/178 loss=0.0324
+epoch=33 step=80/178 loss=0.0090
+epoch=33 step=90/178 loss=0.0475
+epoch=33 step=100/178 loss=0.0347
+epoch=33 step=110/178 loss=0.1372
+epoch=33 step=120/178 loss=0.0368
+epoch=33 step=130/178 loss=0.0313
+epoch=33 step=140/178 loss=0.0139
+epoch=33 step=150/178 loss=0.0287
+epoch=33 step=160/178 loss=0.0186
+epoch=33 step=170/178 loss=0.0266
+epoch=33 train_loss=0.0284 train_contrastive=0.0267 train_regression=0.0150 val_loss=0.0494 val_contrastive=0.0705 val_regression=0.0141
+epoch=34 step=10/178 loss=0.0104
+epoch=34 step=20/178 loss=0.0443
+epoch=34 step=30/178 loss=0.0232
+epoch=34 step=40/178 loss=0.0187
+epoch=34 step=50/178 loss=0.0240
+epoch=34 step=60/178 loss=0.0150
+epoch=34 step=70/178 loss=0.0344
+epoch=34 step=80/178 loss=0.0079
+epoch=34 step=90/178 loss=0.0318
+epoch=34 step=100/178 loss=0.0157
+epoch=34 step=110/178 loss=0.0270
+epoch=34 step=120/178 loss=0.1228
+epoch=34 step=130/178 loss=0.0594
+epoch=34 step=140/178 loss=0.0186
+epoch=34 step=150/178 loss=0.0153
+epoch=34 step=160/178 loss=0.0224
+epoch=34 step=170/178 loss=0.0337
+epoch=34 train_loss=0.0312 train_contrastive=0.0315 train_regression=0.0155 val_loss=0.0675 val_contrastive=0.1014 val_regression=0.0168
+epoch=35 step=10/178 loss=0.0089
+epoch=35 step=20/178 loss=0.0424
+epoch=35 step=30/178 loss=0.0181
+epoch=35 step=40/178 loss=0.0093
+epoch=35 step=50/178 loss=0.0156
+epoch=35 step=60/178 loss=0.0106
+epoch=35 step=70/178 loss=0.0181
+epoch=35 step=80/178 loss=0.0169
+epoch=35 step=90/178 loss=0.0065
+epoch=35 step=100/178 loss=0.0184
+epoch=35 step=110/178 loss=0.0173
+epoch=35 step=120/178 loss=0.0123
+epoch=35 step=130/178 loss=0.0103
+epoch=35 step=140/178 loss=0.0056
+epoch=35 step=150/178 loss=0.0049
+epoch=35 step=160/178 loss=0.0129
+epoch=35 step=170/178 loss=0.0432
+epoch=35 train_loss=0.0192 train_contrastive=0.0147 train_regression=0.0119 val_loss=0.0395 val_contrastive=0.0440 val_regression=0.0175
+epoch=36 step=10/178 loss=0.0077
+epoch=36 step=20/178 loss=0.0140
+epoch=36 step=30/178 loss=0.0286
+epoch=36 step=40/178 loss=0.0088
+epoch=36 step=50/178 loss=0.0058
+epoch=36 step=60/178 loss=0.0136
+epoch=36 step=70/178 loss=0.0063
+epoch=36 step=80/178 loss=0.0096
+epoch=36 step=90/178 loss=0.1326
+epoch=36 step=100/178 loss=0.0060
+epoch=36 step=110/178 loss=0.0108
+epoch=36 step=120/178 loss=0.0077
+epoch=36 step=130/178 loss=0.0297
+epoch=36 step=140/178 loss=0.0133
+epoch=36 step=150/178 loss=0.0072
+epoch=36 step=160/178 loss=0.0199
+epoch=36 step=170/178 loss=0.0123
+epoch=36 train_loss=0.0157 train_contrastive=0.0093 train_regression=0.0110 val_loss=0.0291 val_contrastive=0.0289 val_regression=0.0147
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.0291 epoch=36
+epoch=37 step=10/178 loss=0.0101
+epoch=37 step=20/178 loss=0.0075
+epoch=37 step=30/178 loss=0.0092
+epoch=37 step=40/178 loss=0.0115
+epoch=37 step=50/178 loss=0.0080
+epoch=37 step=60/178 loss=0.0170
+epoch=37 step=70/178 loss=0.0069
+epoch=37 step=80/178 loss=0.0173
+epoch=37 step=90/178 loss=0.0136
+epoch=37 step=100/178 loss=0.0049
+epoch=37 step=110/178 loss=0.0213
+epoch=37 step=120/178 loss=0.0232
+epoch=37 step=130/178 loss=0.0100
+epoch=37 step=140/178 loss=0.0221
+epoch=37 step=150/178 loss=0.0091
+epoch=37 step=160/178 loss=0.0128
+epoch=37 step=170/178 loss=0.0102
+epoch=37 train_loss=0.0167 train_contrastive=0.0107 train_regression=0.0113 val_loss=0.0644 val_contrastive=0.0828 val_regression=0.0230
+epoch=38 step=10/178 loss=0.0058
+epoch=38 step=20/178 loss=0.0117
+epoch=38 step=30/178 loss=0.0093
+epoch=38 step=40/178 loss=0.0091
+epoch=38 step=50/178 loss=0.0183
+epoch=38 step=60/178 loss=0.0124
+epoch=38 step=70/178 loss=0.0216
+epoch=38 step=80/178 loss=0.0218
+epoch=38 step=90/178 loss=0.0274
+epoch=38 step=100/178 loss=0.0203
+epoch=38 step=110/178 loss=0.0198
+epoch=38 step=120/178 loss=0.0423
+epoch=38 step=130/178 loss=0.0076
+epoch=38 step=140/178 loss=0.0134
+epoch=38 step=150/178 loss=0.0156
+epoch=38 step=160/178 loss=0.0078
+epoch=38 step=170/178 loss=0.0656
+epoch=38 train_loss=0.0227 train_contrastive=0.0199 train_regression=0.0127 val_loss=0.0569 val_contrastive=0.0610 val_regression=0.0264
+epoch=39 step=10/178 loss=0.0072
+epoch=39 step=20/178 loss=0.0073
+epoch=39 step=30/178 loss=0.0104
+epoch=39 step=40/178 loss=0.0167
+epoch=39 step=50/178 loss=0.0191
+epoch=39 step=60/178 loss=0.0100
+epoch=39 step=70/178 loss=0.0093
+epoch=39 step=80/178 loss=0.0085
+epoch=39 step=90/178 loss=0.0187
+epoch=39 step=100/178 loss=0.0065
+epoch=39 step=110/178 loss=0.0145
+epoch=39 step=120/178 loss=0.0078
+epoch=39 step=130/178 loss=0.0099
+epoch=39 step=140/178 loss=0.0114
+epoch=39 step=150/178 loss=0.0100
+epoch=39 step=160/178 loss=0.0396
+epoch=39 step=170/178 loss=0.0238
+epoch=39 train_loss=0.0167 train_contrastive=0.0114 train_regression=0.0111 val_loss=0.0450 val_contrastive=0.0555 val_regression=0.0173
+epoch=40 step=10/178 loss=0.0107
+epoch=40 step=20/178 loss=0.0095
+epoch=40 step=30/178 loss=0.0147
+epoch=40 step=40/178 loss=0.0053
+epoch=40 step=50/178 loss=0.0208
+epoch=40 step=60/178 loss=0.0106
+epoch=40 step=70/178 loss=0.0200
+epoch=40 step=80/178 loss=0.0075
+epoch=40 step=90/178 loss=0.0074
+epoch=40 step=100/178 loss=0.0132
+epoch=40 step=110/178 loss=0.0130
+epoch=40 step=120/178 loss=0.0175
+epoch=40 step=130/178 loss=0.0055
+epoch=40 step=140/178 loss=0.0062
+epoch=40 step=150/178 loss=0.0103
+epoch=40 step=160/178 loss=0.0119
+epoch=40 step=170/178 loss=0.0102
+epoch=40 train_loss=0.0138 train_contrastive=0.0071 train_regression=0.0103 val_loss=0.0353 val_contrastive=0.0416 val_regression=0.0145
+epoch=41 step=10/178 loss=0.0077
+epoch=41 step=20/178 loss=0.0121
+epoch=41 step=30/178 loss=0.0085
+epoch=41 step=40/178 loss=0.0120
+epoch=41 step=50/178 loss=0.0112
+epoch=41 step=60/178 loss=0.0083
+epoch=41 step=70/178 loss=0.0654
+epoch=41 step=80/178 loss=0.0195
+epoch=41 step=90/178 loss=0.0073
+epoch=41 step=100/178 loss=0.0069
+epoch=41 step=110/178 loss=0.0061
+epoch=41 step=120/178 loss=0.0104
+epoch=41 step=130/178 loss=0.0182
+epoch=41 step=140/178 loss=0.0235
+epoch=41 step=150/178 loss=0.0092
+epoch=41 step=160/178 loss=0.0160
+epoch=41 step=170/178 loss=0.0107
+epoch=41 train_loss=0.0144 train_contrastive=0.0080 train_regression=0.0104 val_loss=0.0660 val_contrastive=0.0787 val_regression=0.0266
+epoch=42 step=10/178 loss=0.0056
+epoch=42 step=20/178 loss=0.0069
+epoch=42 step=30/178 loss=0.0078
+epoch=42 step=40/178 loss=0.0123
+epoch=42 step=50/178 loss=0.0067
+epoch=42 step=60/178 loss=0.0059
+epoch=42 step=70/178 loss=0.0116
+epoch=42 step=80/178 loss=0.0082
+epoch=42 step=90/178 loss=0.0295
+epoch=42 step=100/178 loss=0.0131
+epoch=42 step=110/178 loss=0.0079
+epoch=42 step=120/178 loss=0.0082
+epoch=42 step=130/178 loss=0.0088
+epoch=42 step=140/178 loss=0.0097
+epoch=42 step=150/178 loss=0.0122
+epoch=42 step=160/178 loss=0.0110
+epoch=42 step=170/178 loss=0.0687
+epoch=42 train_loss=0.0129 train_contrastive=0.0058 train_regression=0.0100 val_loss=0.0615 val_contrastive=0.0633 val_regression=0.0299
+epoch=43 step=10/178 loss=0.0094
+epoch=43 step=20/178 loss=0.0108
+epoch=43 step=30/178 loss=0.0382
+epoch=43 step=40/178 loss=0.0757
+epoch=43 step=50/178 loss=0.0077
+epoch=43 step=60/178 loss=0.1205
+epoch=43 step=70/178 loss=0.0145
+epoch=43 step=80/178 loss=0.0123
+epoch=43 step=90/178 loss=0.0069
+epoch=43 step=100/178 loss=0.0127
+epoch=43 step=110/178 loss=0.0141
+epoch=43 step=120/178 loss=0.0061
+epoch=43 step=130/178 loss=0.0188
+epoch=43 step=140/178 loss=0.0667
+epoch=43 step=150/178 loss=0.0096
+epoch=43 step=160/178 loss=0.0199
+epoch=43 step=170/178 loss=0.0467
+epoch=43 train_loss=0.0210 train_contrastive=0.0178 train_regression=0.0122 val_loss=0.0582 val_contrastive=0.0758 val_regression=0.0203
+epoch=44 step=10/178 loss=0.0062
+epoch=44 step=20/178 loss=0.0137
+epoch=44 step=30/178 loss=0.0316
+epoch=44 step=40/178 loss=0.0065
+epoch=44 step=50/178 loss=0.0175
+epoch=44 step=60/178 loss=0.0255
+epoch=44 step=70/178 loss=0.0447
+epoch=44 step=80/178 loss=0.0117
+epoch=44 step=90/178 loss=0.0055
+epoch=44 step=100/178 loss=0.0206
+epoch=44 step=110/178 loss=0.0075
+epoch=44 step=120/178 loss=0.0128
+epoch=44 step=130/178 loss=0.0109
+epoch=44 step=140/178 loss=0.0061
+epoch=44 step=150/178 loss=0.0360
+epoch=44 step=160/178 loss=0.0103
+epoch=44 step=170/178 loss=0.0097
+epoch=44 train_loss=0.0154 train_contrastive=0.0093 train_regression=0.0108 val_loss=0.0502 val_contrastive=0.0561 val_regression=0.0221
+epoch=45 step=10/178 loss=0.0292
+epoch=45 step=20/178 loss=0.0070
+epoch=45 step=30/178 loss=0.0064
+epoch=45 step=40/178 loss=0.0086
+epoch=45 step=50/178 loss=0.0124
+epoch=45 step=60/178 loss=0.0158
+epoch=45 step=70/178 loss=0.0089
+epoch=45 step=80/178 loss=0.0279
+epoch=45 step=90/178 loss=0.0138
+epoch=45 step=100/178 loss=0.0081
+epoch=45 step=110/178 loss=0.0125
+epoch=45 step=120/178 loss=0.0142
+epoch=45 step=130/178 loss=0.0409
+epoch=45 step=140/178 loss=0.0170
+epoch=45 step=150/178 loss=0.0077
+epoch=45 step=160/178 loss=0.0724
+epoch=45 step=170/178 loss=0.0376
+epoch=45 train_loss=0.0278 train_contrastive=0.0287 train_regression=0.0134 val_loss=0.0512 val_contrastive=0.0659 val_regression=0.0183
+epoch=46 step=10/178 loss=0.0164
+epoch=46 step=20/178 loss=0.0145
+epoch=46 step=30/178 loss=0.0066
+epoch=46 step=40/178 loss=0.0080
+epoch=46 step=50/178 loss=0.0120
+epoch=46 step=60/178 loss=0.0206
+epoch=46 step=70/178 loss=0.0114
+epoch=46 step=80/178 loss=0.0082
+epoch=46 step=90/178 loss=0.0072
+epoch=46 step=100/178 loss=0.0247
+epoch=46 step=110/178 loss=0.0085
+epoch=46 step=120/178 loss=0.0069
+epoch=46 step=130/178 loss=0.1036
+epoch=46 step=140/178 loss=0.0903
+epoch=46 step=150/178 loss=0.0131
+epoch=46 step=160/178 loss=0.0054
+epoch=46 step=170/178 loss=0.0164
+epoch=46 train_loss=0.0198 train_contrastive=0.0155 train_regression=0.0121 val_loss=0.0603 val_contrastive=0.0763 val_regression=0.0221
+epoch=47 step=10/178 loss=0.0200
+epoch=47 step=20/178 loss=0.0122
+epoch=47 step=30/178 loss=0.0071
+epoch=47 step=40/178 loss=0.0099
+epoch=47 step=50/178 loss=0.0096
+epoch=47 step=60/178 loss=0.0069
+epoch=47 step=70/178 loss=0.0078
+epoch=47 step=80/178 loss=0.0209
+epoch=47 step=90/178 loss=0.0051
+epoch=47 step=100/178 loss=0.0098
+epoch=47 step=110/178 loss=0.0507
+epoch=47 step=120/178 loss=0.0418
+epoch=47 step=130/178 loss=0.0098
+epoch=47 step=140/178 loss=0.0433
+epoch=47 step=150/178 loss=0.0088
+epoch=47 step=160/178 loss=0.0123
+epoch=47 step=170/178 loss=0.0089
+epoch=47 train_loss=0.0167 train_contrastive=0.0121 train_regression=0.0107 val_loss=0.0346 val_contrastive=0.0323 val_regression=0.0185
+epoch=48 step=10/178 loss=0.0247
+epoch=48 step=20/178 loss=0.0443
+epoch=48 step=30/178 loss=0.0060
+epoch=48 step=40/178 loss=0.0162
+epoch=48 step=50/178 loss=0.0070
+epoch=48 step=60/178 loss=0.0084
+epoch=48 step=70/178 loss=0.0079
+epoch=48 step=80/178 loss=0.0122
+epoch=48 step=90/178 loss=0.0316
+epoch=48 step=100/178 loss=0.0266
+epoch=48 step=110/178 loss=0.0066
+epoch=48 step=120/178 loss=0.0142
+epoch=48 step=130/178 loss=0.0072
+epoch=48 step=140/178 loss=0.0075
+epoch=48 step=150/178 loss=0.0085
+epoch=48 step=160/178 loss=0.0060
+epoch=48 step=170/178 loss=0.0049
+epoch=48 train_loss=0.0134 train_contrastive=0.0076 train_regression=0.0096 val_loss=0.0240 val_contrastive=0.0249 val_regression=0.0116
+saved_best runs/foundation/remap_pet_layer4_cw05_best.pt val_loss=0.0240 epoch=48
+epoch=49 step=10/178 loss=0.0096
+epoch=49 step=20/178 loss=0.0210
+epoch=49 step=30/178 loss=0.0188
+epoch=49 step=40/178 loss=0.0072
+epoch=49 step=50/178 loss=0.0055
+epoch=49 step=60/178 loss=0.0160
+epoch=49 step=70/178 loss=0.0071
+epoch=49 step=80/178 loss=0.0088
+epoch=49 step=90/178 loss=0.0134
+epoch=49 step=100/178 loss=0.0073
+epoch=49 step=110/178 loss=0.0100
+epoch=49 step=120/178 loss=0.0274
+epoch=49 step=130/178 loss=0.0202
+epoch=49 step=140/178 loss=0.0074
+epoch=49 step=150/178 loss=0.0069
+epoch=49 step=160/178 loss=0.0066
+epoch=49 step=170/178 loss=0.0054
+epoch=49 train_loss=0.0110 train_contrastive=0.0036 train_regression=0.0092 val_loss=0.0295 val_contrastive=0.0317 val_regression=0.0136
+epoch=50 step=10/178 loss=0.0045
+epoch=50 step=20/178 loss=0.0050
+epoch=50 step=30/178 loss=0.0057
+epoch=50 step=40/178 loss=0.0080
+epoch=50 step=50/178 loss=0.0055
+epoch=50 step=60/178 loss=0.0046
+epoch=50 step=70/178 loss=0.0113
+epoch=50 step=80/178 loss=0.0100
+epoch=50 step=90/178 loss=0.0084
+epoch=50 step=100/178 loss=0.0065
+epoch=50 step=110/178 loss=0.0151
+epoch=50 step=120/178 loss=0.0091
+epoch=50 step=130/178 loss=0.0070
+epoch=50 step=140/178 loss=0.0047
+epoch=50 step=150/178 loss=0.0106
+epoch=50 step=160/178 loss=0.0061
+epoch=50 step=170/178 loss=0.0418
+epoch=50 train_loss=0.0146 train_contrastive=0.0103 train_regression=0.0094 val_loss=0.1107 val_contrastive=0.1536 val_regression=0.0340
+saved runs/foundation/remap_pet_layer4_cw05.pt

logs/swinunetr_lastblock_regalign.log ADDED Viewed

	@@ -0,0 +1,1104 @@

+<frozen importlib._bootstrap_external>:1325: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead.
+device=cuda backbone=swinunetr encoder_scope=last_block contrastive_weight=0.2 regression_weight=1.0 train=710 val=152
+epoch=1 step=10/355 loss=1.1069
+epoch=1 step=20/355 loss=0.6074
+epoch=1 step=30/355 loss=0.5072
+epoch=1 step=40/355 loss=0.3560
+epoch=1 step=50/355 loss=0.4034
+epoch=1 step=60/355 loss=0.3922
+epoch=1 step=70/355 loss=0.3531
+epoch=1 step=80/355 loss=0.2256
+epoch=1 step=90/355 loss=0.2329
+epoch=1 step=100/355 loss=0.2520
+epoch=1 step=110/355 loss=0.2988
+epoch=1 step=120/355 loss=0.3001
+epoch=1 step=130/355 loss=0.2480
+epoch=1 step=140/355 loss=0.1784
+epoch=1 step=150/355 loss=0.1998
+epoch=1 step=160/355 loss=0.1697
+epoch=1 step=170/355 loss=0.1913
+epoch=1 step=180/355 loss=0.2466
+epoch=1 step=190/355 loss=0.1757
+epoch=1 step=200/355 loss=0.1539
+epoch=1 step=210/355 loss=0.1845
+epoch=1 step=220/355 loss=0.2060
+epoch=1 step=230/355 loss=0.1592
+epoch=1 step=240/355 loss=0.2081
+epoch=1 step=250/355 loss=0.1442
+epoch=1 step=260/355 loss=0.1730
+epoch=1 step=270/355 loss=0.1605
+epoch=1 step=280/355 loss=0.1567
+epoch=1 step=290/355 loss=0.1684
+epoch=1 step=300/355 loss=0.1703
+epoch=1 step=310/355 loss=0.1606
+epoch=1 step=320/355 loss=0.1664
+epoch=1 step=330/355 loss=0.1521
+epoch=1 step=340/355 loss=0.1600
+epoch=1 step=350/355 loss=0.1679
+epoch=1 train_loss=0.2976 train_contrastive=0.6806 train_regression=0.1615 val_loss=0.1666 val_contrastive=0.6618 val_regression=0.0343
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.1666 epoch=1
+epoch=2 step=10/355 loss=0.1201
+epoch=2 step=20/355 loss=0.1426
+epoch=2 step=30/355 loss=0.1637
+epoch=2 step=40/355 loss=0.1314
+epoch=2 step=50/355 loss=0.1293
+epoch=2 step=60/355 loss=0.1513
+epoch=2 step=70/355 loss=0.1999
+epoch=2 step=80/355 loss=0.1675
+epoch=2 step=90/355 loss=0.1509
+epoch=2 step=100/355 loss=0.1351
+epoch=2 step=110/355 loss=0.1320
+epoch=2 step=120/355 loss=0.1584
+epoch=2 step=130/355 loss=0.1277
+epoch=2 step=140/355 loss=0.1055
+epoch=2 step=150/355 loss=0.1372
+epoch=2 step=160/355 loss=0.1542
+epoch=2 step=170/355 loss=0.1622
+epoch=2 step=180/355 loss=0.1710
+epoch=2 step=190/355 loss=0.1295
+epoch=2 step=200/355 loss=0.1532
+epoch=2 step=210/355 loss=0.1235
+epoch=2 step=220/355 loss=0.1723
+epoch=2 step=230/355 loss=0.1530
+epoch=2 step=240/355 loss=0.1834
+epoch=2 step=250/355 loss=0.1455
+epoch=2 step=260/355 loss=0.1555
+epoch=2 step=270/355 loss=0.1509
+epoch=2 step=280/355 loss=0.1156
+epoch=2 step=290/355 loss=0.1028
+epoch=2 step=300/355 loss=0.1192
+epoch=2 step=310/355 loss=0.1833
+epoch=2 step=320/355 loss=0.1811
+epoch=2 step=330/355 loss=0.1504
+epoch=2 step=340/355 loss=0.0972
+epoch=2 step=350/355 loss=0.1537
+epoch=2 train_loss=0.1502 train_contrastive=0.6218 train_regression=0.0259 val_loss=0.1443 val_contrastive=0.5818 val_regression=0.0279
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.1443 epoch=2
+epoch=3 step=10/355 loss=0.0756
+epoch=3 step=20/355 loss=0.1556
+epoch=3 step=30/355 loss=0.1650
+epoch=3 step=40/355 loss=0.1478
+epoch=3 step=50/355 loss=0.1460
+epoch=3 step=60/355 loss=0.1730
+epoch=3 step=70/355 loss=0.1682
+epoch=3 step=80/355 loss=0.1441
+epoch=3 step=90/355 loss=0.1256
+epoch=3 step=100/355 loss=0.1194
+epoch=3 step=110/355 loss=0.1434
+epoch=3 step=120/355 loss=0.0848
+epoch=3 step=130/355 loss=0.1294
+epoch=3 step=140/355 loss=0.1141
+epoch=3 step=150/355 loss=0.1462
+epoch=3 step=160/355 loss=0.1269
+epoch=3 step=170/355 loss=0.1618
+epoch=3 step=180/355 loss=0.0888
+epoch=3 step=190/355 loss=0.1062
+epoch=3 step=200/355 loss=0.1244
+epoch=3 step=210/355 loss=0.0640
+epoch=3 step=220/355 loss=0.1358
+epoch=3 step=230/355 loss=0.1089
+epoch=3 step=240/355 loss=0.2132
+epoch=3 step=250/355 loss=0.1753
+epoch=3 step=260/355 loss=0.1112
+epoch=3 step=270/355 loss=0.0832
+epoch=3 step=280/355 loss=0.1612
+epoch=3 step=290/355 loss=0.1260
+epoch=3 step=300/355 loss=0.1138
+epoch=3 step=310/355 loss=0.1017
+epoch=3 step=320/355 loss=0.0609
+epoch=3 step=330/355 loss=0.0969
+epoch=3 step=340/355 loss=0.1968
+epoch=3 step=350/355 loss=0.1358
+epoch=3 train_loss=0.1251 train_contrastive=0.5024 train_regression=0.0246 val_loss=0.1238 val_contrastive=0.4818 val_regression=0.0274
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.1238 epoch=3
+epoch=4 step=10/355 loss=0.2226
+epoch=4 step=20/355 loss=0.1519
+epoch=4 step=30/355 loss=0.0572
+epoch=4 step=40/355 loss=0.0659
+epoch=4 step=50/355 loss=0.0266
+epoch=4 step=60/355 loss=0.0296
+epoch=4 step=70/355 loss=0.1017
+epoch=4 step=80/355 loss=0.1792
+epoch=4 step=90/355 loss=0.1139
+epoch=4 step=100/355 loss=0.0503
+epoch=4 step=110/355 loss=0.1249
+epoch=4 step=120/355 loss=0.1805
+epoch=4 step=130/355 loss=0.1419
+epoch=4 step=140/355 loss=0.0675
+epoch=4 step=150/355 loss=0.0740
+epoch=4 step=160/355 loss=0.1440
+epoch=4 step=170/355 loss=0.1489
+epoch=4 step=180/355 loss=0.1204
+epoch=4 step=190/355 loss=0.0396
+epoch=4 step=200/355 loss=0.1116
+epoch=4 step=210/355 loss=0.0660
+epoch=4 step=220/355 loss=0.1535
+epoch=4 step=230/355 loss=0.0848
+epoch=4 step=240/355 loss=0.1218
+epoch=4 step=250/355 loss=0.0978
+epoch=4 step=260/355 loss=0.1312
+epoch=4 step=270/355 loss=0.1208
+epoch=4 step=280/355 loss=0.0543
+epoch=4 step=290/355 loss=0.0540
+epoch=4 step=300/355 loss=0.0874
+epoch=4 step=310/355 loss=0.0197
+epoch=4 step=320/355 loss=0.0442
+epoch=4 step=330/355 loss=0.0769
+epoch=4 step=340/355 loss=0.0568
+epoch=4 step=350/355 loss=0.0607
+epoch=4 train_loss=0.1042 train_contrastive=0.4049 train_regression=0.0232 val_loss=0.1102 val_contrastive=0.4191 val_regression=0.0264
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.1102 epoch=4
+epoch=5 step=10/355 loss=0.1289
+epoch=5 step=20/355 loss=0.1300
+epoch=5 step=30/355 loss=0.1277
+epoch=5 step=40/355 loss=0.0166
+epoch=5 step=50/355 loss=0.1741
+epoch=5 step=60/355 loss=0.0852
+epoch=5 step=70/355 loss=0.0828
+epoch=5 step=80/355 loss=0.0458
+epoch=5 step=90/355 loss=0.0587
+epoch=5 step=100/355 loss=0.0297
+epoch=5 step=110/355 loss=0.1327
+epoch=5 step=120/355 loss=0.0478
+epoch=5 step=130/355 loss=0.0410
+epoch=5 step=140/355 loss=0.1366
+epoch=5 step=150/355 loss=0.0672
+epoch=5 step=160/355 loss=0.0286
+epoch=5 step=170/355 loss=0.0843
+epoch=5 step=180/355 loss=0.0153
+epoch=5 step=190/355 loss=0.1472
+epoch=5 step=200/355 loss=0.0483
+epoch=5 step=210/355 loss=0.1249
+epoch=5 step=220/355 loss=0.1257
+epoch=5 step=230/355 loss=0.1092
+epoch=5 step=240/355 loss=0.1159
+epoch=5 step=250/355 loss=0.0285
+epoch=5 step=260/355 loss=0.0124
+epoch=5 step=270/355 loss=0.0599
+epoch=5 step=280/355 loss=0.1575
+epoch=5 step=290/355 loss=0.0881
+epoch=5 step=300/355 loss=0.0767
+epoch=5 step=310/355 loss=0.0392
+epoch=5 step=320/355 loss=0.0472
+epoch=5 step=330/355 loss=0.1577
+epoch=5 step=340/355 loss=0.0612
+epoch=5 step=350/355 loss=0.0249
+epoch=5 train_loss=0.0895 train_contrastive=0.3337 train_regression=0.0227 val_loss=0.1075 val_contrastive=0.4112 val_regression=0.0252
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.1075 epoch=5
+epoch=6 step=10/355 loss=0.0297
+epoch=6 step=20/355 loss=0.0939
+epoch=6 step=30/355 loss=0.1159
+epoch=6 step=40/355 loss=0.0510
+epoch=6 step=50/355 loss=0.0090
+epoch=6 step=60/355 loss=0.0310
+epoch=6 step=70/355 loss=0.0433
+epoch=6 step=80/355 loss=0.1097
+epoch=6 step=90/355 loss=0.1530
+epoch=6 step=100/355 loss=0.0607
+epoch=6 step=110/355 loss=0.1108
+epoch=6 step=120/355 loss=0.1407
+epoch=6 step=130/355 loss=0.0260
+epoch=6 step=140/355 loss=0.0455
+epoch=6 step=150/355 loss=0.0555
+epoch=6 step=160/355 loss=0.1619
+epoch=6 step=170/355 loss=0.0568
+epoch=6 step=180/355 loss=0.1763
+epoch=6 step=190/355 loss=0.1102
+epoch=6 step=200/355 loss=0.0314
+epoch=6 step=210/355 loss=0.1213
+epoch=6 step=220/355 loss=0.0205
+epoch=6 step=230/355 loss=0.0164
+epoch=6 step=240/355 loss=0.0211
+epoch=6 step=250/355 loss=0.0922
+epoch=6 step=260/355 loss=0.0762
+epoch=6 step=270/355 loss=0.1094
+epoch=6 step=280/355 loss=0.2845
+epoch=6 step=290/355 loss=0.0890
+epoch=6 step=300/355 loss=0.0515
+epoch=6 step=310/355 loss=0.0971
+epoch=6 step=320/355 loss=0.1341
+epoch=6 step=330/355 loss=0.1651
+epoch=6 step=340/355 loss=0.0389
+epoch=6 step=350/355 loss=0.0359
+epoch=6 train_loss=0.0808 train_contrastive=0.2968 train_regression=0.0214 val_loss=0.0991 val_contrastive=0.3775 val_regression=0.0236
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0991 epoch=6
+epoch=7 step=10/355 loss=0.0580
+epoch=7 step=20/355 loss=0.0564
+epoch=7 step=30/355 loss=0.0543
+epoch=7 step=40/355 loss=0.0845
+epoch=7 step=50/355 loss=0.0198
+epoch=7 step=60/355 loss=0.0228
+epoch=7 step=70/355 loss=0.0230
+epoch=7 step=80/355 loss=0.0242
+epoch=7 step=90/355 loss=0.1043
+epoch=7 step=100/355 loss=0.0723
+epoch=7 step=110/355 loss=0.0302
+epoch=7 step=120/355 loss=0.0230
+epoch=7 step=130/355 loss=0.0134
+epoch=7 step=140/355 loss=0.0429
+epoch=7 step=150/355 loss=0.0513
+epoch=7 step=160/355 loss=0.1304
+epoch=7 step=170/355 loss=0.1681
+epoch=7 step=180/355 loss=0.0262
+epoch=7 step=190/355 loss=0.1571
+epoch=7 step=200/355 loss=0.1138
+epoch=7 step=210/355 loss=0.0669
+epoch=7 step=220/355 loss=0.0224
+epoch=7 step=230/355 loss=0.1203
+epoch=7 step=240/355 loss=0.0660
+epoch=7 step=250/355 loss=0.0880
+epoch=7 step=260/355 loss=0.0613
+epoch=7 step=270/355 loss=0.0237
+epoch=7 step=280/355 loss=0.0876
+epoch=7 step=290/355 loss=0.1541
+epoch=7 step=300/355 loss=0.0580
+epoch=7 step=310/355 loss=0.0478
+epoch=7 step=320/355 loss=0.0278
+epoch=7 step=330/355 loss=0.0805
+epoch=7 step=340/355 loss=0.0908
+epoch=7 step=350/355 loss=0.0438
+epoch=7 train_loss=0.0773 train_contrastive=0.2779 train_regression=0.0218 val_loss=0.0891 val_contrastive=0.3306 val_regression=0.0230
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0891 epoch=7
+epoch=8 step=10/355 loss=0.0975
+epoch=8 step=20/355 loss=0.1328
+epoch=8 step=30/355 loss=0.0880
+epoch=8 step=40/355 loss=0.0931
+epoch=8 step=50/355 loss=0.0173
+epoch=8 step=60/355 loss=0.0546
+epoch=8 step=70/355 loss=0.0268
+epoch=8 step=80/355 loss=0.0958
+epoch=8 step=90/355 loss=0.0148
+epoch=8 step=100/355 loss=0.0236
+epoch=8 step=110/355 loss=0.1397
+epoch=8 step=120/355 loss=0.0163
+epoch=8 step=130/355 loss=0.0699
+epoch=8 step=140/355 loss=0.0799
+epoch=8 step=150/355 loss=0.0710
+epoch=8 step=160/355 loss=0.0229
+epoch=8 step=170/355 loss=0.0545
+epoch=8 step=180/355 loss=0.0890
+epoch=8 step=190/355 loss=0.0602
+epoch=8 step=200/355 loss=0.0638
+epoch=8 step=210/355 loss=0.0668
+epoch=8 step=220/355 loss=0.0922
+epoch=8 step=230/355 loss=0.0381
+epoch=8 step=240/355 loss=0.0968
+epoch=8 step=250/355 loss=0.1152
+epoch=8 step=260/355 loss=0.0158
+epoch=8 step=270/355 loss=0.0310
+epoch=8 step=280/355 loss=0.0915
+epoch=8 step=290/355 loss=0.0736
+epoch=8 step=300/355 loss=0.0211
+epoch=8 step=310/355 loss=0.0390
+epoch=8 step=320/355 loss=0.0862
+epoch=8 step=330/355 loss=0.1238
+epoch=8 step=340/355 loss=0.1668
+epoch=8 step=350/355 loss=0.0226
+epoch=8 train_loss=0.0651 train_contrastive=0.2198 train_regression=0.0211 val_loss=0.0882 val_contrastive=0.3138 val_regression=0.0255
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0882 epoch=8
+epoch=9 step=10/355 loss=0.0504
+epoch=9 step=20/355 loss=0.0318
+epoch=9 step=30/355 loss=0.1925
+epoch=9 step=40/355 loss=0.0393
+epoch=9 step=50/355 loss=0.1443
+epoch=9 step=60/355 loss=0.1004
+epoch=9 step=70/355 loss=0.1113
+epoch=9 step=80/355 loss=0.0635
+epoch=9 step=90/355 loss=0.1825
+epoch=9 step=100/355 loss=0.0692
+epoch=9 step=110/355 loss=0.0855
+epoch=9 step=120/355 loss=0.0640
+epoch=9 step=130/355 loss=0.0412
+epoch=9 step=140/355 loss=0.1410
+epoch=9 step=150/355 loss=0.1467
+epoch=9 step=160/355 loss=0.0191
+epoch=9 step=170/355 loss=0.1184
+epoch=9 step=180/355 loss=0.0357
+epoch=9 step=190/355 loss=0.0405
+epoch=9 step=200/355 loss=0.0185
+epoch=9 step=210/355 loss=0.1548
+epoch=9 step=220/355 loss=0.0438
+epoch=9 step=230/355 loss=0.1084
+epoch=9 step=240/355 loss=0.0163
+epoch=9 step=250/355 loss=0.0528
+epoch=9 step=260/355 loss=0.0718
+epoch=9 step=270/355 loss=0.0862
+epoch=9 step=280/355 loss=0.0194
+epoch=9 step=290/355 loss=0.0143
+epoch=9 step=300/355 loss=0.1725
+epoch=9 step=310/355 loss=0.0700
+epoch=9 step=320/355 loss=0.1177
+epoch=9 step=330/355 loss=0.1201
+epoch=9 step=340/355 loss=0.1391
+epoch=9 step=350/355 loss=0.0441
+epoch=9 train_loss=0.0658 train_contrastive=0.2279 train_regression=0.0202 val_loss=0.0816 val_contrastive=0.3027 val_regression=0.0211
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0816 epoch=9
+epoch=10 step=10/355 loss=0.0285
+epoch=10 step=20/355 loss=0.0331
+epoch=10 step=30/355 loss=0.0291
+epoch=10 step=40/355 loss=0.0473
+epoch=10 step=50/355 loss=0.1534
+epoch=10 step=60/355 loss=0.0184
+epoch=10 step=70/355 loss=0.0337
+epoch=10 step=80/355 loss=0.0164
+epoch=10 step=90/355 loss=0.0162
+epoch=10 step=100/355 loss=0.1085
+epoch=10 step=110/355 loss=0.0883
+epoch=10 step=120/355 loss=0.0838
+epoch=10 step=130/355 loss=0.0794
+epoch=10 step=140/355 loss=0.0085
+epoch=10 step=150/355 loss=0.0205
+epoch=10 step=160/355 loss=0.0550
+epoch=10 step=170/355 loss=0.0347
+epoch=10 step=180/355 loss=0.0179
+epoch=10 step=190/355 loss=0.0224
+epoch=10 step=200/355 loss=0.0898
+epoch=10 step=210/355 loss=0.2458
+epoch=10 step=220/355 loss=0.0631
+epoch=10 step=230/355 loss=0.0099
+epoch=10 step=240/355 loss=0.0394
+epoch=10 step=250/355 loss=0.0201
+epoch=10 step=260/355 loss=0.0932
+epoch=10 step=270/355 loss=0.0291
+epoch=10 step=280/355 loss=0.0879
+epoch=10 step=290/355 loss=0.0220
+epoch=10 step=300/355 loss=0.0371
+epoch=10 step=310/355 loss=0.0354
+epoch=10 step=320/355 loss=0.0502
+epoch=10 step=330/355 loss=0.0516
+epoch=10 step=340/355 loss=0.0299
+epoch=10 step=350/355 loss=0.0114
+epoch=10 train_loss=0.0552 train_contrastive=0.1776 train_regression=0.0197 val_loss=0.0811 val_contrastive=0.2857 val_regression=0.0240
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0811 epoch=10
+epoch=11 step=10/355 loss=0.1327
+epoch=11 step=20/355 loss=0.0190
+epoch=11 step=30/355 loss=0.0135
+epoch=11 step=40/355 loss=0.0700
+epoch=11 step=50/355 loss=0.0245
+epoch=11 step=60/355 loss=0.0194
+epoch=11 step=70/355 loss=0.0203
+epoch=11 step=80/355 loss=0.0551
+epoch=11 step=90/355 loss=0.0105
+epoch=11 step=100/355 loss=0.0213
+epoch=11 step=110/355 loss=0.0448
+epoch=11 step=120/355 loss=0.0806
+epoch=11 step=130/355 loss=0.0293
+epoch=11 step=140/355 loss=0.0155
+epoch=11 step=150/355 loss=0.0878
+epoch=11 step=160/355 loss=0.0274
+epoch=11 step=170/355 loss=0.1195
+epoch=11 step=180/355 loss=0.0213
+epoch=11 step=190/355 loss=0.0431
+epoch=11 step=200/355 loss=0.0543
+epoch=11 step=210/355 loss=0.0652
+epoch=11 step=220/355 loss=0.0154
+epoch=11 step=230/355 loss=0.0152
+epoch=11 step=240/355 loss=0.0745
+epoch=11 step=250/355 loss=0.1440
+epoch=11 step=260/355 loss=0.0293
+epoch=11 step=270/355 loss=0.0641
+epoch=11 step=280/355 loss=0.0119
+epoch=11 step=290/355 loss=0.0102
+epoch=11 step=300/355 loss=0.0445
+epoch=11 step=310/355 loss=0.0839
+epoch=11 step=320/355 loss=0.0694
+epoch=11 step=330/355 loss=0.0495
+epoch=11 step=340/355 loss=0.0514
+epoch=11 step=350/355 loss=0.0469
+epoch=11 train_loss=0.0553 train_contrastive=0.1771 train_regression=0.0199 val_loss=0.0714 val_contrastive=0.2585 val_regression=0.0197
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0714 epoch=11
+epoch=12 step=10/355 loss=0.0307
+epoch=12 step=20/355 loss=0.0126
+epoch=12 step=30/355 loss=0.0121
+epoch=12 step=40/355 loss=0.0346
+epoch=12 step=50/355 loss=0.0279
+epoch=12 step=60/355 loss=0.0195
+epoch=12 step=70/355 loss=0.0191
+epoch=12 step=80/355 loss=0.0839
+epoch=12 step=90/355 loss=0.0103
+epoch=12 step=100/355 loss=0.0623
+epoch=12 step=110/355 loss=0.0156
+epoch=12 step=120/355 loss=0.0298
+epoch=12 step=130/355 loss=0.0507
+epoch=12 step=140/355 loss=0.0933
+epoch=12 step=150/355 loss=0.0285
+epoch=12 step=160/355 loss=0.0379
+epoch=12 step=170/355 loss=0.0865
+epoch=12 step=180/355 loss=0.0929
+epoch=12 step=190/355 loss=0.0181
+epoch=12 step=200/355 loss=0.1380
+epoch=12 step=210/355 loss=0.0302
+epoch=12 step=220/355 loss=0.0084
+epoch=12 step=230/355 loss=0.1085
+epoch=12 step=240/355 loss=0.0923
+epoch=12 step=250/355 loss=0.0198
+epoch=12 step=260/355 loss=0.0531
+epoch=12 step=270/355 loss=0.0100
+epoch=12 step=280/355 loss=0.0124
+epoch=12 step=290/355 loss=0.0198
+epoch=12 step=300/355 loss=0.0296
+epoch=12 step=310/355 loss=0.0221
+epoch=12 step=320/355 loss=0.0818
+epoch=12 step=330/355 loss=0.0382
+epoch=12 step=340/355 loss=0.0727
+epoch=12 step=350/355 loss=0.0139
+epoch=12 train_loss=0.0546 train_contrastive=0.1801 train_regression=0.0186 val_loss=0.0745 val_contrastive=0.2710 val_regression=0.0203
+epoch=13 step=10/355 loss=0.0365
+epoch=13 step=20/355 loss=0.1185
+epoch=13 step=30/355 loss=0.0259
+epoch=13 step=40/355 loss=0.0345
+epoch=13 step=50/355 loss=0.0115
+epoch=13 step=60/355 loss=0.0198
+epoch=13 step=70/355 loss=0.0726
+epoch=13 step=80/355 loss=0.0130
+epoch=13 step=90/355 loss=0.0184
+epoch=13 step=100/355 loss=0.0658
+epoch=13 step=110/355 loss=0.0169
+epoch=13 step=120/355 loss=0.0124
+epoch=13 step=130/355 loss=0.1149
+epoch=13 step=140/355 loss=0.0529
+epoch=13 step=150/355 loss=0.0819
+epoch=13 step=160/355 loss=0.0073
+epoch=13 step=170/355 loss=0.1408
+epoch=13 step=180/355 loss=0.1002
+epoch=13 step=190/355 loss=0.2123
+epoch=13 step=200/355 loss=0.0163
+epoch=13 step=210/355 loss=0.0314
+epoch=13 step=220/355 loss=0.1336
+epoch=13 step=230/355 loss=0.1272
+epoch=13 step=240/355 loss=0.1114
+epoch=13 step=250/355 loss=0.0123
+epoch=13 step=260/355 loss=0.0525
+epoch=13 step=270/355 loss=0.0331
+epoch=13 step=280/355 loss=0.0377
+epoch=13 step=290/355 loss=0.0124
+epoch=13 step=300/355 loss=0.0153
+epoch=13 step=310/355 loss=0.0118
+epoch=13 step=320/355 loss=0.0369
+epoch=13 step=330/355 loss=0.0110
+epoch=13 step=340/355 loss=0.0217
+epoch=13 step=350/355 loss=0.0099
+epoch=13 train_loss=0.0494 train_contrastive=0.1533 train_regression=0.0187 val_loss=0.0765 val_contrastive=0.2862 val_regression=0.0192
+epoch=14 step=10/355 loss=0.0398
+epoch=14 step=20/355 loss=0.0192
+epoch=14 step=30/355 loss=0.0344
+epoch=14 step=40/355 loss=0.1070
+epoch=14 step=50/355 loss=0.0321
+epoch=14 step=60/355 loss=0.0198
+epoch=14 step=70/355 loss=0.0487
+epoch=14 step=80/355 loss=0.0338
+epoch=14 step=90/355 loss=0.0194
+epoch=14 step=100/355 loss=0.0215
+epoch=14 step=110/355 loss=0.1157
+epoch=14 step=120/355 loss=0.0087
+epoch=14 step=130/355 loss=0.0235
+epoch=14 step=140/355 loss=0.0453
+epoch=14 step=150/355 loss=0.0080
+epoch=14 step=160/355 loss=0.0665
+epoch=14 step=170/355 loss=0.0628
+epoch=14 step=180/355 loss=0.0968
+epoch=14 step=190/355 loss=0.0279
+epoch=14 step=200/355 loss=0.0086
+epoch=14 step=210/355 loss=0.0083
+epoch=14 step=220/355 loss=0.1803
+epoch=14 step=230/355 loss=0.0870
+epoch=14 step=240/355 loss=0.0585
+epoch=14 step=250/355 loss=0.0390
+epoch=14 step=260/355 loss=0.0190
+epoch=14 step=270/355 loss=0.0444
+epoch=14 step=280/355 loss=0.0631
+epoch=14 step=290/355 loss=0.0417
+epoch=14 step=300/355 loss=0.1080
+epoch=14 step=310/355 loss=0.0232
+epoch=14 step=320/355 loss=0.1206
+epoch=14 step=330/355 loss=0.3081
+epoch=14 step=340/355 loss=0.0126
+epoch=14 step=350/355 loss=0.0137
+epoch=14 train_loss=0.0482 train_contrastive=0.1515 train_regression=0.0179 val_loss=0.0690 val_contrastive=0.2505 val_regression=0.0189
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0690 epoch=14
+epoch=15 step=10/355 loss=0.0130
+epoch=15 step=20/355 loss=0.0142
+epoch=15 step=30/355 loss=0.1207
+epoch=15 step=40/355 loss=0.1007
+epoch=15 step=50/355 loss=0.0960
+epoch=15 step=60/355 loss=0.1786
+epoch=15 step=70/355 loss=0.0798
+epoch=15 step=80/355 loss=0.0640
+epoch=15 step=90/355 loss=0.0830
+epoch=15 step=100/355 loss=0.0149
+epoch=15 step=110/355 loss=0.0160
+epoch=15 step=120/355 loss=0.0126
+epoch=15 step=130/355 loss=0.0160
+epoch=15 step=140/355 loss=0.1814
+epoch=15 step=150/355 loss=0.0111
+epoch=15 step=160/355 loss=0.0805
+epoch=15 step=170/355 loss=0.0325
+epoch=15 step=180/355 loss=0.0297
+epoch=15 step=190/355 loss=0.0223
+epoch=15 step=200/355 loss=0.0305
+epoch=15 step=210/355 loss=0.1906
+epoch=15 step=220/355 loss=0.0191
+epoch=15 step=230/355 loss=0.0142
+epoch=15 step=240/355 loss=0.0119
+epoch=15 step=250/355 loss=0.0228
+epoch=15 step=260/355 loss=0.0237
+epoch=15 step=270/355 loss=0.1363
+epoch=15 step=280/355 loss=0.0222
+epoch=15 step=290/355 loss=0.0084
+epoch=15 step=300/355 loss=0.0448
+epoch=15 step=310/355 loss=0.0070
+epoch=15 step=320/355 loss=0.0405
+epoch=15 step=330/355 loss=0.0220
+epoch=15 step=340/355 loss=0.0209
+epoch=15 step=350/355 loss=0.0711
+epoch=15 train_loss=0.0413 train_contrastive=0.1207 train_regression=0.0172 val_loss=0.0651 val_contrastive=0.2320 val_regression=0.0187
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0651 epoch=15
+epoch=16 step=10/355 loss=0.0171
+epoch=16 step=20/355 loss=0.0884
+epoch=16 step=30/355 loss=0.0446
+epoch=16 step=40/355 loss=0.0099
+epoch=16 step=50/355 loss=0.0310
+epoch=16 step=60/355 loss=0.0116
+epoch=16 step=70/355 loss=0.0950
+epoch=16 step=80/355 loss=0.0232
+epoch=16 step=90/355 loss=0.1521
+epoch=16 step=100/355 loss=0.0330
+epoch=16 step=110/355 loss=0.0985
+epoch=16 step=120/355 loss=0.0762
+epoch=16 step=130/355 loss=0.0208
+epoch=16 step=140/355 loss=0.1021
+epoch=16 step=150/355 loss=0.0174
+epoch=16 step=160/355 loss=0.1521
+epoch=16 step=170/355 loss=0.0244
+epoch=16 step=180/355 loss=0.0183
+epoch=16 step=190/355 loss=0.0067
+epoch=16 step=200/355 loss=0.0174
+epoch=16 step=210/355 loss=0.0080
+epoch=16 step=220/355 loss=0.0149
+epoch=16 step=230/355 loss=0.1719
+epoch=16 step=240/355 loss=0.0111
+epoch=16 step=250/355 loss=0.0579
+epoch=16 step=260/355 loss=0.0135
+epoch=16 step=270/355 loss=0.0101
+epoch=16 step=280/355 loss=0.0756
+epoch=16 step=290/355 loss=0.0250
+epoch=16 step=300/355 loss=0.1045
+epoch=16 step=310/355 loss=0.0174
+epoch=16 step=320/355 loss=0.0219
+epoch=16 step=330/355 loss=0.0094
+epoch=16 step=340/355 loss=0.0369
+epoch=16 step=350/355 loss=0.0077
+epoch=16 train_loss=0.0410 train_contrastive=0.1172 train_regression=0.0175 val_loss=0.0640 val_contrastive=0.2123 val_regression=0.0215
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0640 epoch=16
+epoch=17 step=10/355 loss=0.0208
+epoch=17 step=20/355 loss=0.0082
+epoch=17 step=30/355 loss=0.0569
+epoch=17 step=40/355 loss=0.0525
+epoch=17 step=50/355 loss=0.0063
+epoch=17 step=60/355 loss=0.0138
+epoch=17 step=70/355 loss=0.0180
+epoch=17 step=80/355 loss=0.2074
+epoch=17 step=90/355 loss=0.0134
+epoch=17 step=100/355 loss=0.0084
+epoch=17 step=110/355 loss=0.0117
+epoch=17 step=120/355 loss=0.0245
+epoch=17 step=130/355 loss=0.0116
+epoch=17 step=140/355 loss=0.0682
+epoch=17 step=150/355 loss=0.1451
+epoch=17 step=160/355 loss=0.0183
+epoch=17 step=170/355 loss=0.0326
+epoch=17 step=180/355 loss=0.0323
+epoch=17 step=190/355 loss=0.0134
+epoch=17 step=200/355 loss=0.0217
+epoch=17 step=210/355 loss=0.0174
+epoch=17 step=220/355 loss=0.0120
+epoch=17 step=230/355 loss=0.0386
+epoch=17 step=240/355 loss=0.0294
+epoch=17 step=250/355 loss=0.0171
+epoch=17 step=260/355 loss=0.1438
+epoch=17 step=270/355 loss=0.0126
+epoch=17 step=280/355 loss=0.0089
+epoch=17 step=290/355 loss=0.0404
+epoch=17 step=300/355 loss=0.0295
+epoch=17 step=310/355 loss=0.0636
+epoch=17 step=320/355 loss=0.0095
+epoch=17 step=330/355 loss=0.0839
+epoch=17 step=340/355 loss=0.0366
+epoch=17 step=350/355 loss=0.0249
+epoch=17 train_loss=0.0387 train_contrastive=0.1125 train_regression=0.0162 val_loss=0.0895 val_contrastive=0.3071 val_regression=0.0281
+epoch=18 step=10/355 loss=0.0384
+epoch=18 step=20/355 loss=0.0283
+epoch=18 step=30/355 loss=0.0152
+epoch=18 step=40/355 loss=0.0265
+epoch=18 step=50/355 loss=0.0223
+epoch=18 step=60/355 loss=0.0523
+epoch=18 step=70/355 loss=0.0114
+epoch=18 step=80/355 loss=0.0400
+epoch=18 step=90/355 loss=0.0207
+epoch=18 step=100/355 loss=0.0621
+epoch=18 step=110/355 loss=0.0927
+epoch=18 step=120/355 loss=0.0197
+epoch=18 step=130/355 loss=0.0114
+epoch=18 step=140/355 loss=0.0453
+epoch=18 step=150/355 loss=0.0172
+epoch=18 step=160/355 loss=0.0136
+epoch=18 step=170/355 loss=0.0150
+epoch=18 step=180/355 loss=0.0110
+epoch=18 step=190/355 loss=0.0185
+epoch=18 step=200/355 loss=0.0601
+epoch=18 step=210/355 loss=0.0179
+epoch=18 step=220/355 loss=0.1171
+epoch=18 step=230/355 loss=0.1470
+epoch=18 step=240/355 loss=0.0441
+epoch=18 step=250/355 loss=0.0102
+epoch=18 step=260/355 loss=0.1161
+epoch=18 step=270/355 loss=0.0477
+epoch=18 step=280/355 loss=0.0923
+epoch=18 step=290/355 loss=0.0362
+epoch=18 step=300/355 loss=0.0926
+epoch=18 step=310/355 loss=0.0647
+epoch=18 step=320/355 loss=0.0121
+epoch=18 step=330/355 loss=0.0090
+epoch=18 step=340/355 loss=0.0088
+epoch=18 step=350/355 loss=0.0126
+epoch=18 train_loss=0.0382 train_contrastive=0.1080 train_regression=0.0166 val_loss=0.0594 val_contrastive=0.2031 val_regression=0.0188
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0594 epoch=18
+epoch=19 step=10/355 loss=0.0807
+epoch=19 step=20/355 loss=0.0325
+epoch=19 step=30/355 loss=0.0372
+epoch=19 step=40/355 loss=0.0225
+epoch=19 step=50/355 loss=0.0230
+epoch=19 step=60/355 loss=0.0082
+epoch=19 step=70/355 loss=0.0076
+epoch=19 step=80/355 loss=0.0078
+epoch=19 step=90/355 loss=0.0148
+epoch=19 step=100/355 loss=0.0146
+epoch=19 step=110/355 loss=0.0109
+epoch=19 step=120/355 loss=0.1222
+epoch=19 step=130/355 loss=0.0434
+epoch=19 step=140/355 loss=0.0179
+epoch=19 step=150/355 loss=0.0034
+epoch=19 step=160/355 loss=0.0095
+epoch=19 step=170/355 loss=0.0273
+epoch=19 step=180/355 loss=0.1564
+epoch=19 step=190/355 loss=0.0318
+epoch=19 step=200/355 loss=0.0185
+epoch=19 step=210/355 loss=0.0122
+epoch=19 step=220/355 loss=0.0533
+epoch=19 step=230/355 loss=0.0239
+epoch=19 step=240/355 loss=0.0116
+epoch=19 step=250/355 loss=0.0108
+epoch=19 step=260/355 loss=0.0123
+epoch=19 step=270/355 loss=0.0098
+epoch=19 step=280/355 loss=0.0121
+epoch=19 step=290/355 loss=0.0074
+epoch=19 step=300/355 loss=0.0124
+epoch=19 step=310/355 loss=0.0105
+epoch=19 step=320/355 loss=0.0138
+epoch=19 step=330/355 loss=0.0102
+epoch=19 step=340/355 loss=0.0136
+epoch=19 step=350/355 loss=0.0146
+epoch=19 train_loss=0.0342 train_contrastive=0.0923 train_regression=0.0158 val_loss=0.0586 val_contrastive=0.1964 val_regression=0.0193
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0586 epoch=19
+epoch=20 step=10/355 loss=0.0251
+epoch=20 step=20/355 loss=0.0154
+epoch=20 step=30/355 loss=0.0076
+epoch=20 step=40/355 loss=0.0123
+epoch=20 step=50/355 loss=0.0152
+epoch=20 step=60/355 loss=0.0140
+epoch=20 step=70/355 loss=0.0443
+epoch=20 step=80/355 loss=0.0094
+epoch=20 step=90/355 loss=0.0378
+epoch=20 step=100/355 loss=0.0135
+epoch=20 step=110/355 loss=0.0208
+epoch=20 step=120/355 loss=0.0233
+epoch=20 step=130/355 loss=0.0074
+epoch=20 step=140/355 loss=0.0203
+epoch=20 step=150/355 loss=0.0130
+epoch=20 step=160/355 loss=0.0087
+epoch=20 step=170/355 loss=0.0337
+epoch=20 step=180/355 loss=0.0126
+epoch=20 step=190/355 loss=0.0125
+epoch=20 step=200/355 loss=0.0210
+epoch=20 step=210/355 loss=0.0363
+epoch=20 step=220/355 loss=0.0239
+epoch=20 step=230/355 loss=0.0685
+epoch=20 step=240/355 loss=0.0123
+epoch=20 step=250/355 loss=0.0079
+epoch=20 step=260/355 loss=0.0080
+epoch=20 step=270/355 loss=0.0257
+epoch=20 step=280/355 loss=0.0138
+epoch=20 step=290/355 loss=0.1434
+epoch=20 step=300/355 loss=0.3127
+epoch=20 step=310/355 loss=0.0221
+epoch=20 step=320/355 loss=0.0150
+epoch=20 step=330/355 loss=0.0078
+epoch=20 step=340/355 loss=0.0088
+epoch=20 step=350/355 loss=0.0324
+epoch=20 train_loss=0.0353 train_contrastive=0.0980 train_regression=0.0157 val_loss=0.0558 val_contrastive=0.1934 val_regression=0.0171
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0558 epoch=20
+epoch=21 step=10/355 loss=0.0317
+epoch=21 step=20/355 loss=0.0153
+epoch=21 step=30/355 loss=0.0075
+epoch=21 step=40/355 loss=0.0103
+epoch=21 step=50/355 loss=0.0189
+epoch=21 step=60/355 loss=0.0263
+epoch=21 step=70/355 loss=0.0097
+epoch=21 step=80/355 loss=0.0095
+epoch=21 step=90/355 loss=0.1421
+epoch=21 step=100/355 loss=0.0147
+epoch=21 step=110/355 loss=0.0131
+epoch=21 step=120/355 loss=0.0152
+epoch=21 step=130/355 loss=0.0097
+epoch=21 step=140/355 loss=0.0092
+epoch=21 step=150/355 loss=0.0092
+epoch=21 step=160/355 loss=0.0148
+epoch=21 step=170/355 loss=0.0240
+epoch=21 step=180/355 loss=0.0280
+epoch=21 step=190/355 loss=0.0194
+epoch=21 step=200/355 loss=0.0228
+epoch=21 step=210/355 loss=0.0096
+epoch=21 step=220/355 loss=0.0739
+epoch=21 step=230/355 loss=0.0167
+epoch=21 step=240/355 loss=0.0133
+epoch=21 step=250/355 loss=0.0165
+epoch=21 step=260/355 loss=0.0242
+epoch=21 step=270/355 loss=0.0717
+epoch=21 step=280/355 loss=0.0107
+epoch=21 step=290/355 loss=0.0099
+epoch=21 step=300/355 loss=0.0259
+epoch=21 step=310/355 loss=0.0197
+epoch=21 step=320/355 loss=0.1824
+epoch=21 step=330/355 loss=0.0104
+epoch=21 step=340/355 loss=0.0542
+epoch=21 step=350/355 loss=0.0479
+epoch=21 train_loss=0.0334 train_contrastive=0.0888 train_regression=0.0156 val_loss=0.0603 val_contrastive=0.2070 val_regression=0.0189
+epoch=22 step=10/355 loss=0.0158
+epoch=22 step=20/355 loss=0.0088
+epoch=22 step=30/355 loss=0.0215
+epoch=22 step=40/355 loss=0.0427
+epoch=22 step=50/355 loss=0.0161
+epoch=22 step=60/355 loss=0.0278
+epoch=22 step=70/355 loss=0.0156
+epoch=22 step=80/355 loss=0.0251
+epoch=22 step=90/355 loss=0.1779
+epoch=22 step=100/355 loss=0.2876
+epoch=22 step=110/355 loss=0.0114
+epoch=22 step=120/355 loss=0.0140
+epoch=22 step=130/355 loss=0.0238
+epoch=22 step=140/355 loss=0.0383
+epoch=22 step=150/355 loss=0.0089
+epoch=22 step=160/355 loss=0.0338
+epoch=22 step=170/355 loss=0.0186
+epoch=22 step=180/355 loss=0.0616
+epoch=22 step=190/355 loss=0.0147
+epoch=22 step=200/355 loss=0.0561
+epoch=22 step=210/355 loss=0.0222
+epoch=22 step=220/355 loss=0.0068
+epoch=22 step=230/355 loss=0.0356
+epoch=22 step=240/355 loss=0.0088
+epoch=22 step=250/355 loss=0.0395
+epoch=22 step=260/355 loss=0.0300
+epoch=22 step=270/355 loss=0.1299
+epoch=22 step=280/355 loss=0.0123
+epoch=22 step=290/355 loss=0.0079
+epoch=22 step=300/355 loss=0.1033
+epoch=22 step=310/355 loss=0.0056
+epoch=22 step=320/355 loss=0.0170
+epoch=22 step=330/355 loss=0.0116
+epoch=22 step=340/355 loss=0.0071
+epoch=22 step=350/355 loss=0.0605
+epoch=22 train_loss=0.0310 train_contrastive=0.0790 train_regression=0.0152 val_loss=0.0559 val_contrastive=0.1925 val_regression=0.0174
+epoch=23 step=10/355 loss=0.0115
+epoch=23 step=20/355 loss=0.0153
+epoch=23 step=30/355 loss=0.1094
+epoch=23 step=40/355 loss=0.0176
+epoch=23 step=50/355 loss=0.0090
+epoch=23 step=60/355 loss=0.0470
+epoch=23 step=70/355 loss=0.0097
+epoch=23 step=80/355 loss=0.0078
+epoch=23 step=90/355 loss=0.0300
+epoch=23 step=100/355 loss=0.0196
+epoch=23 step=110/355 loss=0.0134
+epoch=23 step=120/355 loss=0.0163
+epoch=23 step=130/355 loss=0.0126
+epoch=23 step=140/355 loss=0.0115
+epoch=23 step=150/355 loss=0.0207
+epoch=23 step=160/355 loss=0.0278
+epoch=23 step=170/355 loss=0.0127
+epoch=23 step=180/355 loss=0.0172
+epoch=23 step=190/355 loss=0.1244
+epoch=23 step=200/355 loss=0.0338
+epoch=23 step=210/355 loss=0.1443
+epoch=23 step=220/355 loss=0.0066
+epoch=23 step=230/355 loss=0.0206
+epoch=23 step=240/355 loss=0.0191
+epoch=23 step=250/355 loss=0.0215
+epoch=23 step=260/355 loss=0.0267
+epoch=23 step=270/355 loss=0.2547
+epoch=23 step=280/355 loss=0.0199
+epoch=23 step=290/355 loss=0.0221
+epoch=23 step=300/355 loss=0.0228
+epoch=23 step=310/355 loss=0.0932
+epoch=23 step=320/355 loss=0.1008
+epoch=23 step=330/355 loss=0.0228
+epoch=23 step=340/355 loss=0.0371
+epoch=23 step=350/355 loss=0.0190
+epoch=23 train_loss=0.0315 train_contrastive=0.0795 train_regression=0.0156 val_loss=0.0516 val_contrastive=0.1697 val_regression=0.0177
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0516 epoch=23
+epoch=24 step=10/355 loss=0.1221
+epoch=24 step=20/355 loss=0.0357
+epoch=24 step=30/355 loss=0.0187
+epoch=24 step=40/355 loss=0.1738
+epoch=24 step=50/355 loss=0.0194
+epoch=24 step=60/355 loss=0.0774
+epoch=24 step=70/355 loss=0.0092
+epoch=24 step=80/355 loss=0.0089
+epoch=24 step=90/355 loss=0.0298
+epoch=24 step=100/355 loss=0.0258
+epoch=24 step=110/355 loss=0.0315
+epoch=24 step=120/355 loss=0.0131
+epoch=24 step=130/355 loss=0.0114
+epoch=24 step=140/355 loss=0.0495
+epoch=24 step=150/355 loss=0.0135
+epoch=24 step=160/355 loss=0.0960
+epoch=24 step=170/355 loss=0.0193
+epoch=24 step=180/355 loss=0.0141
+epoch=24 step=190/355 loss=0.0357
+epoch=24 step=200/355 loss=0.0066
+epoch=24 step=210/355 loss=0.0080
+epoch=24 step=220/355 loss=0.0479
+epoch=24 step=230/355 loss=0.1366
+epoch=24 step=240/355 loss=0.0122
+epoch=24 step=250/355 loss=0.0050
+epoch=24 step=260/355 loss=0.0108
+epoch=24 step=270/355 loss=0.0176
+epoch=24 step=280/355 loss=0.0153
+epoch=24 step=290/355 loss=0.0269
+epoch=24 step=300/355 loss=0.0351
+epoch=24 step=310/355 loss=0.0243
+epoch=24 step=320/355 loss=0.0278
+epoch=24 step=330/355 loss=0.0094
+epoch=24 step=340/355 loss=0.0114
+epoch=24 step=350/355 loss=0.0255
+epoch=24 train_loss=0.0313 train_contrastive=0.0847 train_regression=0.0144 val_loss=0.0507 val_contrastive=0.1610 val_regression=0.0185
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0507 epoch=24
+epoch=25 step=10/355 loss=0.0169
+epoch=25 step=20/355 loss=0.0277
+epoch=25 step=30/355 loss=0.0128
+epoch=25 step=40/355 loss=0.0525
+epoch=25 step=50/355 loss=0.0347
+epoch=25 step=60/355 loss=0.0098
+epoch=25 step=70/355 loss=0.0126
+epoch=25 step=80/355 loss=0.0084
+epoch=25 step=90/355 loss=0.0149
+epoch=25 step=100/355 loss=0.0088
+epoch=25 step=110/355 loss=0.0113
+epoch=25 step=120/355 loss=0.0414
+epoch=25 step=130/355 loss=0.0161
+epoch=25 step=140/355 loss=0.0190
+epoch=25 step=150/355 loss=0.0423
+epoch=25 step=160/355 loss=0.0078
+epoch=25 step=170/355 loss=0.0085
+epoch=25 step=180/355 loss=0.1778
+epoch=25 step=190/355 loss=0.0266
+epoch=25 step=200/355 loss=0.0155
+epoch=25 step=210/355 loss=0.0128
+epoch=25 step=220/355 loss=0.0150
+epoch=25 step=230/355 loss=0.0673
+epoch=25 step=240/355 loss=0.0138
+epoch=25 step=250/355 loss=0.0063
+epoch=25 step=260/355 loss=0.0252
+epoch=25 step=270/355 loss=0.0191
+epoch=25 step=280/355 loss=0.0120
+epoch=25 step=290/355 loss=0.0176
+epoch=25 step=300/355 loss=0.1955
+epoch=25 step=310/355 loss=0.0093
+epoch=25 step=320/355 loss=0.0154
+epoch=25 step=330/355 loss=0.0215
+epoch=25 step=340/355 loss=0.0169
+epoch=25 step=350/355 loss=0.0070
+epoch=25 train_loss=0.0272 train_contrastive=0.0630 train_regression=0.0146 val_loss=0.0492 val_contrastive=0.1688 val_regression=0.0154
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0492 epoch=25
+epoch=26 step=10/355 loss=0.0115
+epoch=26 step=20/355 loss=0.0121
+epoch=26 step=30/355 loss=0.0936
+epoch=26 step=40/355 loss=0.0099
+epoch=26 step=50/355 loss=0.0097
+epoch=26 step=60/355 loss=0.0139
+epoch=26 step=70/355 loss=0.0119
+epoch=26 step=80/355 loss=0.0197
+epoch=26 step=90/355 loss=0.0076
+epoch=26 step=100/355 loss=0.0095
+epoch=26 step=110/355 loss=0.1351
+epoch=26 step=120/355 loss=0.0165
+epoch=26 step=130/355 loss=0.1532
+epoch=26 step=140/355 loss=0.0134
+epoch=26 step=150/355 loss=0.0059
+epoch=26 step=160/355 loss=0.0161
+epoch=26 step=170/355 loss=0.0209
+epoch=26 step=180/355 loss=0.0079
+epoch=26 step=190/355 loss=0.0156
+epoch=26 step=200/355 loss=0.0654
+epoch=26 step=210/355 loss=0.0548
+epoch=26 step=220/355 loss=0.0134
+epoch=26 step=230/355 loss=0.0077
+epoch=26 step=240/355 loss=0.0269
+epoch=26 step=250/355 loss=0.0077
+epoch=26 step=260/355 loss=0.0160
+epoch=26 step=270/355 loss=0.0143
+epoch=26 step=280/355 loss=0.0082
+epoch=26 step=290/355 loss=0.0070
+epoch=26 step=300/355 loss=0.0112
+epoch=26 step=310/355 loss=0.0203
+epoch=26 step=320/355 loss=0.0089
+epoch=26 step=330/355 loss=0.0073
+epoch=26 step=340/355 loss=0.0087
+epoch=26 step=350/355 loss=0.0182
+epoch=26 train_loss=0.0278 train_contrastive=0.0691 train_regression=0.0140 val_loss=0.0486 val_contrastive=0.1581 val_regression=0.0170
+saved_best runs/foundation/swinunetr_lastblock_regalign_best.pt val_loss=0.0486 epoch=26
+epoch=27 step=10/355 loss=0.0176
+epoch=27 step=20/355 loss=0.0053
+epoch=27 step=30/355 loss=0.0234
+epoch=27 step=40/355 loss=0.0062
+epoch=27 step=50/355 loss=0.0516
+epoch=27 step=60/355 loss=0.0094
+epoch=27 step=70/355 loss=0.0190
+epoch=27 step=80/355 loss=0.0649
+epoch=27 step=90/355 loss=0.0292
+epoch=27 step=100/355 loss=0.0137
+epoch=27 step=110/355 loss=0.0197
+epoch=27 step=120/355 loss=0.0684
+epoch=27 step=130/355 loss=0.0096
+epoch=27 step=140/355 loss=0.0238
+epoch=27 step=150/355 loss=0.0205
+epoch=27 step=160/355 loss=0.0078
+epoch=27 step=170/355 loss=0.0123
+epoch=27 step=180/355 loss=0.0176
+epoch=27 step=190/355 loss=0.0094
+epoch=27 step=200/355 loss=0.0720
+epoch=27 step=210/355 loss=0.0177
+epoch=27 step=220/355 loss=0.0242
+epoch=27 step=230/355 loss=0.0962
+epoch=27 step=240/355 loss=0.0206
+epoch=27 step=250/355 loss=0.0212
+epoch=27 step=260/355 loss=0.0153
+epoch=27 step=270/355 loss=0.0151
+epoch=27 step=280/355 loss=0.0226
+epoch=27 step=290/355 loss=0.0068
+epoch=27 step=300/355 loss=0.0496
+epoch=27 step=310/355 loss=0.0062
+epoch=27 step=320/355 loss=0.0379
+epoch=27 step=330/355 loss=0.0084
+epoch=27 step=340/355 loss=0.0084
+epoch=27 step=350/355 loss=0.0261
+epoch=27 train_loss=0.0308 train_contrastive=0.0803 train_regression=0.0148 val_loss=0.0614 val_contrastive=0.2201 val_regression=0.0173
+epoch=28 step=10/355 loss=0.0056
+epoch=28 step=20/355 loss=0.0403
+epoch=28 step=30/355 loss=0.0194
+epoch=28 step=40/355 loss=0.0075
+epoch=28 step=50/355 loss=0.0224
+epoch=28 step=60/355 loss=0.0049
+epoch=28 step=70/355 loss=0.0104
+epoch=28 step=80/355 loss=0.0167
+epoch=28 step=90/355 loss=0.0131
+epoch=28 step=100/355 loss=0.1004
+epoch=28 step=110/355 loss=0.0150
+epoch=28 step=120/355 loss=0.0072
+epoch=28 step=130/355 loss=0.0075
+epoch=28 step=140/355 loss=0.1016
+epoch=28 step=150/355 loss=0.0154
+epoch=28 step=160/355 loss=0.0251
+epoch=28 step=170/355 loss=0.0063
+epoch=28 step=180/355 loss=0.0230
+epoch=28 step=190/355 loss=0.0222
+epoch=28 step=200/355 loss=0.0121
+epoch=28 step=210/355 loss=0.0274
+epoch=28 step=220/355 loss=0.0233
+epoch=28 step=230/355 loss=0.0259
+epoch=28 step=240/355 loss=0.0073
+epoch=28 step=250/355 loss=0.0345
+epoch=28 step=260/355 loss=0.1606
+epoch=28 step=270/355 loss=0.0165
+epoch=28 step=280/355 loss=0.0077
+epoch=28 step=290/355 loss=0.0068
+epoch=28 step=300/355 loss=0.1575
+epoch=28 step=310/355 loss=0.0060
+epoch=28 step=320/355 loss=0.0172
+epoch=28 step=330/355 loss=0.0153
+epoch=28 step=340/355 loss=0.1610
+epoch=28 step=350/355 loss=0.0141
+epoch=28 train_loss=0.0253 train_contrastive=0.0602 train_regression=0.0133 val_loss=0.0536 val_contrastive=0.1895 val_regression=0.0157
+epoch=29 step=10/355 loss=0.0054
+epoch=29 step=20/355 loss=0.0048
+epoch=29 step=30/355 loss=0.0113
+epoch=29 step=40/355 loss=0.0120
+epoch=29 step=50/355 loss=0.0390
+epoch=29 step=60/355 loss=0.0410
+epoch=29 step=70/355 loss=0.0395
+epoch=29 step=80/355 loss=0.0252
+epoch=29 step=90/355 loss=0.0444
+epoch=29 step=100/355 loss=0.0322
+epoch=29 step=110/355 loss=0.0231
+epoch=29 step=120/355 loss=0.0175
+epoch=29 step=130/355 loss=0.0171
+epoch=29 step=140/355 loss=0.0463
+epoch=29 step=150/355 loss=0.0169
+epoch=29 step=160/355 loss=0.0136
+epoch=29 step=170/355 loss=0.0059
+epoch=29 step=180/355 loss=0.0367
+epoch=29 step=190/355 loss=0.0144
+epoch=29 step=200/355 loss=0.0103
+epoch=29 step=210/355 loss=0.0130
+epoch=29 step=220/355 loss=0.0175
+epoch=29 step=230/355 loss=0.0273
+epoch=29 step=240/355 loss=0.0173
+epoch=29 step=250/355 loss=0.0174
+epoch=29 step=260/355 loss=0.0220
+epoch=29 step=270/355 loss=0.0228
+epoch=29 step=280/355 loss=0.0089
+epoch=29 step=290/355 loss=0.1051
+epoch=29 step=300/355 loss=0.0711
+epoch=29 step=310/355 loss=0.0370
+epoch=29 step=320/355 loss=0.0120
+epoch=29 step=330/355 loss=0.0104
+epoch=29 step=340/355 loss=0.0141
+epoch=29 step=350/355 loss=0.0108
+epoch=29 train_loss=0.0301 train_contrastive=0.0793 train_regression=0.0143 val_loss=0.0518 val_contrastive=0.1752 val_regression=0.0168
+epoch=30 step=10/355 loss=0.0140
+epoch=30 step=20/355 loss=0.0432
+epoch=30 step=30/355 loss=0.0094
+epoch=30 step=40/355 loss=0.0085
+epoch=30 step=50/355 loss=0.0081
+epoch=30 step=60/355 loss=0.1876
+epoch=30 step=70/355 loss=0.0114
+epoch=30 step=80/355 loss=0.0145
+epoch=30 step=90/355 loss=0.0184
+epoch=30 step=100/355 loss=0.0134
+epoch=30 step=110/355 loss=0.0059
+epoch=30 step=120/355 loss=0.0085
+epoch=30 step=130/355 loss=0.0220
+epoch=30 step=140/355 loss=0.0225
+epoch=30 step=150/355 loss=0.0136
+epoch=30 step=160/355 loss=0.0046
+epoch=30 step=170/355 loss=0.0083
+epoch=30 step=180/355 loss=0.0498
+epoch=30 step=190/355 loss=0.0079
+epoch=30 step=200/355 loss=0.0159
+epoch=30 step=210/355 loss=0.0620
+epoch=30 step=220/355 loss=0.0354
+epoch=30 step=230/355 loss=0.0055
+epoch=30 step=240/355 loss=0.0293
+epoch=30 step=250/355 loss=0.0511
+epoch=30 step=260/355 loss=0.0076
+epoch=30 step=270/355 loss=0.0188
+epoch=30 step=280/355 loss=0.0115
+epoch=30 step=290/355 loss=0.0094
+epoch=30 step=300/355 loss=0.0206
+epoch=30 step=310/355 loss=0.0084
+epoch=30 step=320/355 loss=0.0221
+epoch=30 step=330/355 loss=0.0152
+epoch=30 step=340/355 loss=0.0056
+epoch=30 step=350/355 loss=0.0091
+epoch=30 train_loss=0.0269 train_contrastive=0.0663 train_regression=0.0136 val_loss=0.0522 val_contrastive=0.1791 val_regression=0.0164
+saved runs/foundation/swinunetr_lastblock_regalign.pt