aee4 commited on
Commit
799c2cd
·
verified ·
1 Parent(s): 0531179

Training in progress, step 23750, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f47ad190a414355ce7a8cbb0ca8b2b53dc983c9e2ce594629fefe3bd22d9b11e
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37158556609a44e85ed40d07e082fe57ac0eb6b1836d82f9653335228549cf45
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce1a81528a3c4d1a8adadf19d503af86b37fb929fa8c0e5e40e1f12849ae7406
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa06822a6230182e67102685ad10701b478d5eb0ddcb754e7b55cfaf1f2fa033
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:659b61bb16f28f03382e890ab91fc3883f76645106d565e032ad6e249ff51f3b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e574b667171facfb2e12b5774ec0434fb29a9bdc6e0722b72c08c43b493315be
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31c3d0db44789ce5bcdb90a4706fff078e3678a3e06a451eef823f94a1c0b804
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292b32c42d24880ac5a398551325fecfe5a97cd44bf158410f94ffe1e7fef02c
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": 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,
@@ -7716,6 +7716,88 @@
7716
  "eval_samples_per_second": 50.697,
7717
  "eval_steps_per_second": 12.674,
7718
  "step": 23500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7719
  }
7720
  ],
7721
  "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": 134.180790960452,
6
  "eval_steps": 250,
7
+ "global_step": 23750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
7716
  "eval_samples_per_second": 50.697,
7717
  "eval_steps_per_second": 12.674,
7718
  "step": 23500
7719
+ },
7720
+ {
7721
+ "epoch": 132.909604519774,
7722
+ "grad_norm": 2.931706428527832,
7723
+ "learning_rate": 1.220703125e-07,
7724
+ "loss": 0.2475,
7725
+ "step": 23525
7726
+ },
7727
+ {
7728
+ "epoch": 133.05084745762713,
7729
+ "grad_norm": 0.821354866027832,
7730
+ "learning_rate": 1.220703125e-07,
7731
+ "loss": 0.228,
7732
+ "step": 23550
7733
+ },
7734
+ {
7735
+ "epoch": 133.19209039548022,
7736
+ "grad_norm": 2.7116055488586426,
7737
+ "learning_rate": 1.220703125e-07,
7738
+ "loss": 0.2699,
7739
+ "step": 23575
7740
+ },
7741
+ {
7742
+ "epoch": 133.33333333333334,
7743
+ "grad_norm": 0.9110122919082642,
7744
+ "learning_rate": 1.220703125e-07,
7745
+ "loss": 0.2473,
7746
+ "step": 23600
7747
+ },
7748
+ {
7749
+ "epoch": 133.47457627118644,
7750
+ "grad_norm": 2.818114995956421,
7751
+ "learning_rate": 1.220703125e-07,
7752
+ "loss": 0.2757,
7753
+ "step": 23625
7754
+ },
7755
+ {
7756
+ "epoch": 133.61581920903956,
7757
+ "grad_norm": 1.1905447244644165,
7758
+ "learning_rate": 1.220703125e-07,
7759
+ "loss": 0.2811,
7760
+ "step": 23650
7761
+ },
7762
+ {
7763
+ "epoch": 133.75706214689265,
7764
+ "grad_norm": 0.5743904113769531,
7765
+ "learning_rate": 1.220703125e-07,
7766
+ "loss": 0.2437,
7767
+ "step": 23675
7768
+ },
7769
+ {
7770
+ "epoch": 133.89830508474577,
7771
+ "grad_norm": 2.0375077724456787,
7772
+ "learning_rate": 1.220703125e-07,
7773
+ "loss": 0.2541,
7774
+ "step": 23700
7775
+ },
7776
+ {
7777
+ "epoch": 134.03954802259886,
7778
+ "grad_norm": 1.4466464519500732,
7779
+ "learning_rate": 1.220703125e-07,
7780
+ "loss": 0.255,
7781
+ "step": 23725
7782
+ },
7783
+ {
7784
+ "epoch": 134.180790960452,
7785
+ "grad_norm": 0.809286892414093,
7786
+ "learning_rate": 1.220703125e-07,
7787
+ "loss": 0.25,
7788
+ "step": 23750
7789
+ },
7790
+ {
7791
+ "epoch": 134.180790960452,
7792
+ "eval_asd": 10.054365500863447,
7793
+ "eval_dice": 0.7921756239196641,
7794
+ "eval_hd95": 30.48199393706276,
7795
+ "eval_jaccard": 0.698016213575938,
7796
+ "eval_loss": 0.34629756212234497,
7797
+ "eval_runtime": 5.1267,
7798
+ "eval_samples_per_second": 50.715,
7799
+ "eval_steps_per_second": 12.679,
7800
+ "step": 23750
7801
  }
7802
  ],
7803
  "logging_steps": 25,