aee4 commited on
Commit
2381ac5
·
verified ·
1 Parent(s): eccdd23

Training in progress, step 24000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37158556609a44e85ed40d07e082fe57ac0eb6b1836d82f9653335228549cf45
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45be0808ac296923114ee964ed5e05fdd3e3cda1c79a92769c337973c3a00e09
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa06822a6230182e67102685ad10701b478d5eb0ddcb754e7b55cfaf1f2fa033
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edcae5aa7a2555ed93a07140fc7e837a29f92821300ac4e0e503a440e38f21e1
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:e574b667171facfb2e12b5774ec0434fb29a9bdc6e0722b72c08c43b493315be
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b0e29fee27f3b2a77526bb3adf8684fc57f3e89a860e67c74c93ed58ea5638
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:292b32c42d24880ac5a398551325fecfe5a97cd44bf158410f94ffe1e7fef02c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5ffc48df38ef621253e24698e98be0059dedfa8e429144f256c3704e9596c1
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": 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,
@@ -7798,6 +7798,88 @@
7798
  "eval_samples_per_second": 50.715,
7799
  "eval_steps_per_second": 12.679,
7800
  "step": 23750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7801
  }
7802
  ],
7803
  "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": 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,
 
7798
  "eval_samples_per_second": 50.715,
7799
  "eval_steps_per_second": 12.679,
7800
  "step": 23750
7801
+ },
7802
+ {
7803
+ "epoch": 134.32203389830508,
7804
+ "grad_norm": 1.4156454801559448,
7805
+ "learning_rate": 1.220703125e-07,
7806
+ "loss": 0.2794,
7807
+ "step": 23775
7808
+ },
7809
+ {
7810
+ "epoch": 134.4632768361582,
7811
+ "grad_norm": 1.244895100593567,
7812
+ "learning_rate": 1.220703125e-07,
7813
+ "loss": 0.2778,
7814
+ "step": 23800
7815
+ },
7816
+ {
7817
+ "epoch": 134.6045197740113,
7818
+ "grad_norm": 1.0974403619766235,
7819
+ "learning_rate": 1.220703125e-07,
7820
+ "loss": 0.2346,
7821
+ "step": 23825
7822
+ },
7823
+ {
7824
+ "epoch": 134.74576271186442,
7825
+ "grad_norm": 1.4614615440368652,
7826
+ "learning_rate": 1.220703125e-07,
7827
+ "loss": 0.2303,
7828
+ "step": 23850
7829
+ },
7830
+ {
7831
+ "epoch": 134.8870056497175,
7832
+ "grad_norm": 1.3348093032836914,
7833
+ "learning_rate": 1.220703125e-07,
7834
+ "loss": 0.2759,
7835
+ "step": 23875
7836
+ },
7837
+ {
7838
+ "epoch": 135.02824858757063,
7839
+ "grad_norm": 1.647629976272583,
7840
+ "learning_rate": 1.220703125e-07,
7841
+ "loss": 0.2584,
7842
+ "step": 23900
7843
+ },
7844
+ {
7845
+ "epoch": 135.16949152542372,
7846
+ "grad_norm": 1.9197840690612793,
7847
+ "learning_rate": 1.220703125e-07,
7848
+ "loss": 0.2514,
7849
+ "step": 23925
7850
+ },
7851
+ {
7852
+ "epoch": 135.31073446327684,
7853
+ "grad_norm": 1.0577765703201294,
7854
+ "learning_rate": 1.220703125e-07,
7855
+ "loss": 0.2267,
7856
+ "step": 23950
7857
+ },
7858
+ {
7859
+ "epoch": 135.45197740112994,
7860
+ "grad_norm": 3.3588175773620605,
7861
+ "learning_rate": 1.220703125e-07,
7862
+ "loss": 0.2731,
7863
+ "step": 23975
7864
+ },
7865
+ {
7866
+ "epoch": 135.59322033898306,
7867
+ "grad_norm": 1.1587588787078857,
7868
+ "learning_rate": 1.220703125e-07,
7869
+ "loss": 0.239,
7870
+ "step": 24000
7871
+ },
7872
+ {
7873
+ "epoch": 135.59322033898306,
7874
+ "eval_asd": 9.814897614575308,
7875
+ "eval_dice": 0.7911056113323709,
7876
+ "eval_hd95": 29.909484129495365,
7877
+ "eval_jaccard": 0.6975650699222109,
7878
+ "eval_loss": 0.34924301505088806,
7879
+ "eval_runtime": 5.1199,
7880
+ "eval_samples_per_second": 50.783,
7881
+ "eval_steps_per_second": 12.696,
7882
+ "step": 24000
7883
  }
7884
  ],
7885
  "logging_steps": 25,