aee4 commited on
Commit
9aa0649
·
verified ·
1 Parent(s): ab95468

Training in progress, step 24250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45be0808ac296923114ee964ed5e05fdd3e3cda1c79a92769c337973c3a00e09
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516b4950a0910b09897c2bee934ef5677ede9660fbb3d7aa4531f1565e29aba2
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edcae5aa7a2555ed93a07140fc7e837a29f92821300ac4e0e503a440e38f21e1
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9d53651052a2e357639baff2c17ef8a874197f54c3f3cf3967d6b6d00f6182
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:d9b0e29fee27f3b2a77526bb3adf8684fc57f3e89a860e67c74c93ed58ea5638
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9cc832d3aebb5441f9a5ff0cb6a2bcda1ed4a32851e02d6ead313e452149ec5
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd5ffc48df38ef621253e24698e98be0059dedfa8e429144f256c3704e9596c1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c6c483385c2ba8561145493abe4d27a741a82518e4dadcc1e335cc34efad16
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": 135.59322033898306,
6
  "eval_steps": 250,
7
- "global_step": 24000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -7880,6 +7880,88 @@
7880
  "eval_samples_per_second": 50.783,
7881
  "eval_steps_per_second": 12.696,
7882
  "step": 24000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7883
  }
7884
  ],
7885
  "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": 137.00564971751413,
6
  "eval_steps": 250,
7
+ "global_step": 24250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
7880
  "eval_samples_per_second": 50.783,
7881
  "eval_steps_per_second": 12.696,
7882
  "step": 24000
7883
+ },
7884
+ {
7885
+ "epoch": 135.73446327683615,
7886
+ "grad_norm": 2.201047897338867,
7887
+ "learning_rate": 1.220703125e-07,
7888
+ "loss": 0.2826,
7889
+ "step": 24025
7890
+ },
7891
+ {
7892
+ "epoch": 135.87570621468927,
7893
+ "grad_norm": 1.3103464841842651,
7894
+ "learning_rate": 1.220703125e-07,
7895
+ "loss": 0.295,
7896
+ "step": 24050
7897
+ },
7898
+ {
7899
+ "epoch": 136.01694915254237,
7900
+ "grad_norm": 0.9736390113830566,
7901
+ "learning_rate": 1.220703125e-07,
7902
+ "loss": 0.2445,
7903
+ "step": 24075
7904
+ },
7905
+ {
7906
+ "epoch": 136.1581920903955,
7907
+ "grad_norm": 3.0514163970947266,
7908
+ "learning_rate": 1.220703125e-07,
7909
+ "loss": 0.2547,
7910
+ "step": 24100
7911
+ },
7912
+ {
7913
+ "epoch": 136.29943502824858,
7914
+ "grad_norm": 2.604400873184204,
7915
+ "learning_rate": 1.220703125e-07,
7916
+ "loss": 0.2585,
7917
+ "step": 24125
7918
+ },
7919
+ {
7920
+ "epoch": 136.4406779661017,
7921
+ "grad_norm": 1.1696339845657349,
7922
+ "learning_rate": 1.220703125e-07,
7923
+ "loss": 0.2639,
7924
+ "step": 24150
7925
+ },
7926
+ {
7927
+ "epoch": 136.5819209039548,
7928
+ "grad_norm": 1.660635232925415,
7929
+ "learning_rate": 1.220703125e-07,
7930
+ "loss": 0.2693,
7931
+ "step": 24175
7932
+ },
7933
+ {
7934
+ "epoch": 136.72316384180792,
7935
+ "grad_norm": 1.271910548210144,
7936
+ "learning_rate": 1.220703125e-07,
7937
+ "loss": 0.275,
7938
+ "step": 24200
7939
+ },
7940
+ {
7941
+ "epoch": 136.864406779661,
7942
+ "grad_norm": 0.9756634831428528,
7943
+ "learning_rate": 1.220703125e-07,
7944
+ "loss": 0.252,
7945
+ "step": 24225
7946
+ },
7947
+ {
7948
+ "epoch": 137.00564971751413,
7949
+ "grad_norm": 1.1731343269348145,
7950
+ "learning_rate": 1.220703125e-07,
7951
+ "loss": 0.2695,
7952
+ "step": 24250
7953
+ },
7954
+ {
7955
+ "epoch": 137.00564971751413,
7956
+ "eval_asd": 10.315812274868911,
7957
+ "eval_dice": 0.7921660767176506,
7958
+ "eval_hd95": 31.329149052302693,
7959
+ "eval_jaccard": 0.6976254494817659,
7960
+ "eval_loss": 0.3447021543979645,
7961
+ "eval_runtime": 5.1243,
7962
+ "eval_samples_per_second": 50.739,
7963
+ "eval_steps_per_second": 12.685,
7964
+ "step": 24250
7965
  }
7966
  ],
7967
  "logging_steps": 25,