aee4 commited on
Commit
5e6b1d3
·
verified ·
1 Parent(s): 1af3bfd

Training in progress, step 30250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c7575f1d37a82f1b88b18a5fa08259b1018b7657e7f3cd90ea5d8235526589c
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9f3589bf3b08eaab110fa5ec074b7302e5e64661e701224cbbe9b89915e9356
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d801b93e0a2be0f31d8b1ba9f1fb6f8fbf73b706d02502a79391339bde8833ca
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aec28e0edf6fb22420b00afbccee10c6f14a4524e5e647628e4975ef35868f4
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:cbf4ac1dd2afcd7f7d208130ad7040b9f5a4ed189f5813c8e8d3e4602aa44fd1
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c9a08b995af490a0e42ca72e831f453b978e3b1063580da0ec20b8cef768c3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6edde6963616018107fed498b0b5f9935b10800764a6ca068b39f5f1364062ce
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8cf34afadc6cf9da8367181b86437bacbb0bb818365f7bf8c377cec5b190c9a
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": 169.4915254237288,
6
  "eval_steps": 250,
7
- "global_step": 30000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -9848,6 +9848,88 @@
9848
  "eval_samples_per_second": 51.109,
9849
  "eval_steps_per_second": 12.777,
9850
  "step": 30000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9851
  }
9852
  ],
9853
  "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": 170.90395480225988,
6
  "eval_steps": 250,
7
+ "global_step": 30250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
9848
  "eval_samples_per_second": 51.109,
9849
  "eval_steps_per_second": 12.777,
9850
  "step": 30000
9851
+ },
9852
+ {
9853
+ "epoch": 169.63276836158192,
9854
+ "grad_norm": 1.6769109964370728,
9855
+ "learning_rate": 1.52587890625e-08,
9856
+ "loss": 0.2697,
9857
+ "step": 30025
9858
+ },
9859
+ {
9860
+ "epoch": 169.77401129943502,
9861
+ "grad_norm": 1.0405176877975464,
9862
+ "learning_rate": 1.52587890625e-08,
9863
+ "loss": 0.2476,
9864
+ "step": 30050
9865
+ },
9866
+ {
9867
+ "epoch": 169.91525423728814,
9868
+ "grad_norm": 1.7500898838043213,
9869
+ "learning_rate": 1.52587890625e-08,
9870
+ "loss": 0.2323,
9871
+ "step": 30075
9872
+ },
9873
+ {
9874
+ "epoch": 170.05649717514123,
9875
+ "grad_norm": 1.4356002807617188,
9876
+ "learning_rate": 7.62939453125e-09,
9877
+ "loss": 0.2482,
9878
+ "step": 30100
9879
+ },
9880
+ {
9881
+ "epoch": 170.19774011299435,
9882
+ "grad_norm": 2.18666934967041,
9883
+ "learning_rate": 7.62939453125e-09,
9884
+ "loss": 0.2488,
9885
+ "step": 30125
9886
+ },
9887
+ {
9888
+ "epoch": 170.33898305084745,
9889
+ "grad_norm": 1.8500176668167114,
9890
+ "learning_rate": 7.62939453125e-09,
9891
+ "loss": 0.2762,
9892
+ "step": 30150
9893
+ },
9894
+ {
9895
+ "epoch": 170.48022598870057,
9896
+ "grad_norm": 2.1986944675445557,
9897
+ "learning_rate": 7.62939453125e-09,
9898
+ "loss": 0.2853,
9899
+ "step": 30175
9900
+ },
9901
+ {
9902
+ "epoch": 170.62146892655366,
9903
+ "grad_norm": 2.0215253829956055,
9904
+ "learning_rate": 7.62939453125e-09,
9905
+ "loss": 0.2654,
9906
+ "step": 30200
9907
+ },
9908
+ {
9909
+ "epoch": 170.76271186440678,
9910
+ "grad_norm": 4.401730060577393,
9911
+ "learning_rate": 7.62939453125e-09,
9912
+ "loss": 0.2238,
9913
+ "step": 30225
9914
+ },
9915
+ {
9916
+ "epoch": 170.90395480225988,
9917
+ "grad_norm": 1.3654005527496338,
9918
+ "learning_rate": 7.62939453125e-09,
9919
+ "loss": 0.26,
9920
+ "step": 30250
9921
+ },
9922
+ {
9923
+ "epoch": 170.90395480225988,
9924
+ "eval_asd": 10.04929366332852,
9925
+ "eval_dice": 0.7914709684226731,
9926
+ "eval_hd95": 30.787019540299703,
9927
+ "eval_jaccard": 0.6975064861497303,
9928
+ "eval_loss": 0.34925007820129395,
9929
+ "eval_runtime": 5.1249,
9930
+ "eval_samples_per_second": 50.732,
9931
+ "eval_steps_per_second": 12.683,
9932
+ "step": 30250
9933
  }
9934
  ],
9935
  "logging_steps": 25,