aee4 commited on
Commit
aff3b54
·
verified ·
1 Parent(s): 4d92a12

Training in progress, step 33500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba70dbde6c94a91d8098dcb1a66d0bfa9ddacf631327428a1751ce2d5e48d1d4
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33317f8b3bcc0884e431f75d7d95f295d6ed9d99ac138eafe40f094aa3ed96e2
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4d1f8bdbcec49f73d5c576147cad07e529a0abc16ae2ede799fb76d4a14530a
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb8b94839ea92eea72d58b9177fc10963dcec9c9bfee9ff88ae84baa5b98e8f
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61edaf3f0553716d17b4cdf3495e41392aa21b5dd0c62e00e348d712d5f5b71a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6ff8000ec111d3b11183c888b407fb0542a3ae586c890685c5db05d18bbf8f
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1762c66216487a7c21482cf2930b9075aaac6fcaea890e5978ecb3816f2e82b9
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c5a0461a93c6723b2cdd523b84e1561a17487ef64ce11c1147a67e7b07bd5ec
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": 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,
@@ -10914,6 +10914,88 @@
10914
  "eval_samples_per_second": 49.697,
10915
  "eval_steps_per_second": 12.424,
10916
  "step": 33250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10917
  }
10918
  ],
10919
  "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": 189.26553672316385,
6
  "eval_steps": 250,
7
+ "global_step": 33500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
10914
  "eval_samples_per_second": 49.697,
10915
  "eval_steps_per_second": 12.424,
10916
  "step": 33250
10917
+ },
10918
+ {
10919
+ "epoch": 187.99435028248587,
10920
+ "grad_norm": 2.2486283779144287,
10921
+ "learning_rate": 3.814697265625e-09,
10922
+ "loss": 0.2749,
10923
+ "step": 33275
10924
+ },
10925
+ {
10926
+ "epoch": 188.135593220339,
10927
+ "grad_norm": 2.660114049911499,
10928
+ "learning_rate": 3.814697265625e-09,
10929
+ "loss": 0.2553,
10930
+ "step": 33300
10931
+ },
10932
+ {
10933
+ "epoch": 188.27683615819208,
10934
+ "grad_norm": 1.6325404644012451,
10935
+ "learning_rate": 3.814697265625e-09,
10936
+ "loss": 0.2356,
10937
+ "step": 33325
10938
+ },
10939
+ {
10940
+ "epoch": 188.4180790960452,
10941
+ "grad_norm": 0.7675624489784241,
10942
+ "learning_rate": 3.814697265625e-09,
10943
+ "loss": 0.2816,
10944
+ "step": 33350
10945
+ },
10946
+ {
10947
+ "epoch": 188.5593220338983,
10948
+ "grad_norm": 1.7626734972000122,
10949
+ "learning_rate": 3.814697265625e-09,
10950
+ "loss": 0.2587,
10951
+ "step": 33375
10952
+ },
10953
+ {
10954
+ "epoch": 188.70056497175142,
10955
+ "grad_norm": 1.2840185165405273,
10956
+ "learning_rate": 3.814697265625e-09,
10957
+ "loss": 0.2583,
10958
+ "step": 33400
10959
+ },
10960
+ {
10961
+ "epoch": 188.8418079096045,
10962
+ "grad_norm": 1.2463464736938477,
10963
+ "learning_rate": 3.814697265625e-09,
10964
+ "loss": 0.283,
10965
+ "step": 33425
10966
+ },
10967
+ {
10968
+ "epoch": 188.98305084745763,
10969
+ "grad_norm": 3.476984977722168,
10970
+ "learning_rate": 3.814697265625e-09,
10971
+ "loss": 0.2712,
10972
+ "step": 33450
10973
+ },
10974
+ {
10975
+ "epoch": 189.12429378531073,
10976
+ "grad_norm": 1.2410030364990234,
10977
+ "learning_rate": 3.814697265625e-09,
10978
+ "loss": 0.251,
10979
+ "step": 33475
10980
+ },
10981
+ {
10982
+ "epoch": 189.26553672316385,
10983
+ "grad_norm": 1.291839361190796,
10984
+ "learning_rate": 3.814697265625e-09,
10985
+ "loss": 0.2417,
10986
+ "step": 33500
10987
+ },
10988
+ {
10989
+ "epoch": 189.26553672316385,
10990
+ "eval_asd": 10.027402664953854,
10991
+ "eval_dice": 0.7905529727046201,
10992
+ "eval_hd95": 30.962968725248125,
10993
+ "eval_jaccard": 0.6966103134954164,
10994
+ "eval_loss": 0.3497767746448517,
10995
+ "eval_runtime": 5.1239,
10996
+ "eval_samples_per_second": 50.743,
10997
+ "eval_steps_per_second": 12.686,
10998
+ "step": 33500
10999
  }
11000
  ],
11001
  "logging_steps": 25,