aee4 commited on
Commit
a538678
·
verified ·
1 Parent(s): cd1b029

Training in progress, step 23500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b84f91c11f3fbc32e6be265afc0530251c0fbdaf27ad4a85cdbce564dd4b3e74
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47ad190a414355ce7a8cbb0ca8b2b53dc983c9e2ce594629fefe3bd22d9b11e
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d86c3ac7a447f48bc83a6e28f8defe5c8257cfed5ce6757fb4ecc87565837e37
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1a81528a3c4d1a8adadf19d503af86b37fb929fa8c0e5e40e1f12849ae7406
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62eadb1900ba1f7762c55358e7560c216c5249390a3cc787e2545d54d16282a6
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659b61bb16f28f03382e890ab91fc3883f76645106d565e032ad6e249ff51f3b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69190bcd88d1643a9fa81ad731e2fe6e4ffb3c75222c8dca1d439dc160fab59b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c3d0db44789ce5bcdb90a4706fff078e3678a3e06a451eef823f94a1c0b804
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 18500,
3
  "best_metric": 0.7932397701166506,
4
  "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-18500",
5
- "epoch": 131.35593220338984,
6
  "eval_steps": 250,
7
- "global_step": 23250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -7634,6 +7634,88 @@
7634
  "eval_samples_per_second": 50.692,
7635
  "eval_steps_per_second": 12.673,
7636
  "step": 23250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7637
  }
7638
  ],
7639
  "logging_steps": 25,
 
2
  "best_global_step": 18500,
3
  "best_metric": 0.7932397701166506,
4
  "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-18500",
5
+ "epoch": 132.7683615819209,
6
  "eval_steps": 250,
7
+ "global_step": 23500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
7634
  "eval_samples_per_second": 50.692,
7635
  "eval_steps_per_second": 12.673,
7636
  "step": 23250
7637
+ },
7638
+ {
7639
+ "epoch": 131.49717514124293,
7640
+ "grad_norm": 2.158123254776001,
7641
+ "learning_rate": 1.220703125e-07,
7642
+ "loss": 0.2694,
7643
+ "step": 23275
7644
+ },
7645
+ {
7646
+ "epoch": 131.63841807909606,
7647
+ "grad_norm": 1.2811461687088013,
7648
+ "learning_rate": 1.220703125e-07,
7649
+ "loss": 0.2755,
7650
+ "step": 23300
7651
+ },
7652
+ {
7653
+ "epoch": 131.77966101694915,
7654
+ "grad_norm": 2.140599250793457,
7655
+ "learning_rate": 1.220703125e-07,
7656
+ "loss": 0.2564,
7657
+ "step": 23325
7658
+ },
7659
+ {
7660
+ "epoch": 131.92090395480227,
7661
+ "grad_norm": 1.0954556465148926,
7662
+ "learning_rate": 1.220703125e-07,
7663
+ "loss": 0.2539,
7664
+ "step": 23350
7665
+ },
7666
+ {
7667
+ "epoch": 132.06214689265536,
7668
+ "grad_norm": 2.0106749534606934,
7669
+ "learning_rate": 1.220703125e-07,
7670
+ "loss": 0.2488,
7671
+ "step": 23375
7672
+ },
7673
+ {
7674
+ "epoch": 132.20338983050848,
7675
+ "grad_norm": 1.4836710691452026,
7676
+ "learning_rate": 1.220703125e-07,
7677
+ "loss": 0.2364,
7678
+ "step": 23400
7679
+ },
7680
+ {
7681
+ "epoch": 132.34463276836158,
7682
+ "grad_norm": 1.3765805959701538,
7683
+ "learning_rate": 1.220703125e-07,
7684
+ "loss": 0.2852,
7685
+ "step": 23425
7686
+ },
7687
+ {
7688
+ "epoch": 132.4858757062147,
7689
+ "grad_norm": 1.5854461193084717,
7690
+ "learning_rate": 1.220703125e-07,
7691
+ "loss": 0.26,
7692
+ "step": 23450
7693
+ },
7694
+ {
7695
+ "epoch": 132.6271186440678,
7696
+ "grad_norm": 0.9916201829910278,
7697
+ "learning_rate": 1.220703125e-07,
7698
+ "loss": 0.2806,
7699
+ "step": 23475
7700
+ },
7701
+ {
7702
+ "epoch": 132.7683615819209,
7703
+ "grad_norm": 1.7302815914154053,
7704
+ "learning_rate": 1.220703125e-07,
7705
+ "loss": 0.2538,
7706
+ "step": 23500
7707
+ },
7708
+ {
7709
+ "epoch": 132.7683615819209,
7710
+ "eval_asd": 9.896800501852203,
7711
+ "eval_dice": 0.7925361522339586,
7712
+ "eval_hd95": 29.72504080935154,
7713
+ "eval_jaccard": 0.6988901576774726,
7714
+ "eval_loss": 0.3471981883049011,
7715
+ "eval_runtime": 5.1285,
7716
+ "eval_samples_per_second": 50.697,
7717
+ "eval_steps_per_second": 12.674,
7718
+ "step": 23500
7719
  }
7720
  ],
7721
  "logging_steps": 25,