aee4 commited on
Commit
cf35682
·
verified ·
1 Parent(s): 085373b

Training in progress, step 33250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:569b0845513ba35035afcd1c85fdf6cce545eabc61984442708f6c3046d13901
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba70dbde6c94a91d8098dcb1a66d0bfa9ddacf631327428a1751ce2d5e48d1d4
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c1d79eadc04234555097396b6e10a144f8b65f1fbb5755e4e950bd03b5cff24
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d1f8bdbcec49f73d5c576147cad07e529a0abc16ae2ede799fb76d4a14530a
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:d247ff22ade11f4d41847cbcf6daa486f0e7160058ac0678bae8a18347fdb004
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61edaf3f0553716d17b4cdf3495e41392aa21b5dd0c62e00e348d712d5f5b71a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76e98dd682ab436ebd4aed99a8174d55c09f0150fc50922488b21188a506efe8
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1762c66216487a7c21482cf2930b9075aaac6fcaea890e5978ecb3816f2e82b9
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": 186.4406779661017,
6
  "eval_steps": 250,
7
- "global_step": 33000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -10832,6 +10832,88 @@
10832
  "eval_samples_per_second": 50.265,
10833
  "eval_steps_per_second": 12.566,
10834
  "step": 33000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10835
  }
10836
  ],
10837
  "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": 187.85310734463278,
6
  "eval_steps": 250,
7
+ "global_step": 33250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
10832
  "eval_samples_per_second": 50.265,
10833
  "eval_steps_per_second": 12.566,
10834
  "step": 33000
10835
+ },
10836
+ {
10837
+ "epoch": 186.5819209039548,
10838
+ "grad_norm": 1.8071727752685547,
10839
+ "learning_rate": 3.814697265625e-09,
10840
+ "loss": 0.2416,
10841
+ "step": 33025
10842
+ },
10843
+ {
10844
+ "epoch": 186.72316384180792,
10845
+ "grad_norm": 1.5756776332855225,
10846
+ "learning_rate": 3.814697265625e-09,
10847
+ "loss": 0.2665,
10848
+ "step": 33050
10849
+ },
10850
+ {
10851
+ "epoch": 186.864406779661,
10852
+ "grad_norm": 1.4147619009017944,
10853
+ "learning_rate": 3.814697265625e-09,
10854
+ "loss": 0.2675,
10855
+ "step": 33075
10856
+ },
10857
+ {
10858
+ "epoch": 187.00564971751413,
10859
+ "grad_norm": 1.9124417304992676,
10860
+ "learning_rate": 3.814697265625e-09,
10861
+ "loss": 0.2521,
10862
+ "step": 33100
10863
+ },
10864
+ {
10865
+ "epoch": 187.14689265536722,
10866
+ "grad_norm": 1.7862675189971924,
10867
+ "learning_rate": 3.814697265625e-09,
10868
+ "loss": 0.2724,
10869
+ "step": 33125
10870
+ },
10871
+ {
10872
+ "epoch": 187.28813559322035,
10873
+ "grad_norm": 1.217008113861084,
10874
+ "learning_rate": 3.814697265625e-09,
10875
+ "loss": 0.2377,
10876
+ "step": 33150
10877
+ },
10878
+ {
10879
+ "epoch": 187.42937853107344,
10880
+ "grad_norm": 1.4460328817367554,
10881
+ "learning_rate": 3.814697265625e-09,
10882
+ "loss": 0.2585,
10883
+ "step": 33175
10884
+ },
10885
+ {
10886
+ "epoch": 187.57062146892656,
10887
+ "grad_norm": 1.0221128463745117,
10888
+ "learning_rate": 3.814697265625e-09,
10889
+ "loss": 0.2776,
10890
+ "step": 33200
10891
+ },
10892
+ {
10893
+ "epoch": 187.71186440677965,
10894
+ "grad_norm": 0.7660859227180481,
10895
+ "learning_rate": 3.814697265625e-09,
10896
+ "loss": 0.2522,
10897
+ "step": 33225
10898
+ },
10899
+ {
10900
+ "epoch": 187.85310734463278,
10901
+ "grad_norm": 2.526947021484375,
10902
+ "learning_rate": 3.814697265625e-09,
10903
+ "loss": 0.2437,
10904
+ "step": 33250
10905
+ },
10906
+ {
10907
+ "epoch": 187.85310734463278,
10908
+ "eval_asd": 10.106282649079727,
10909
+ "eval_dice": 0.7923379997424416,
10910
+ "eval_hd95": 31.33355546015775,
10911
+ "eval_jaccard": 0.6983460617328477,
10912
+ "eval_loss": 0.3475651741027832,
10913
+ "eval_runtime": 5.2317,
10914
+ "eval_samples_per_second": 49.697,
10915
+ "eval_steps_per_second": 12.424,
10916
+ "step": 33250
10917
  }
10918
  ],
10919
  "logging_steps": 25,