aee4 commited on
Commit
fb02e0c
·
verified ·
1 Parent(s): dfe8dc5

Training in progress, step 27250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebd89c6515f18c5f63bfaab313b5017e213492f818edb1de4edd785f2308d612
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2979ef3cf00c936313a7a929cd81352822ce62b97ac05abaf0f3c1bf12febeee
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:494905543427b1fa540386956bc968768b710fa14dc18a947bdd54579b67c5e6
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c118766de402bfe3e62206a87f39c6d46fe3ee0a0bb740392a806a10d2bcb8d6
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:088021e9e30df3e99b533f5c532c8118858d471144b44926ee497e1c10a672f3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ffe34d77c5cee36911714512c5937860963bc471f0847054916c4e38e6e7621
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a80232965dc895fccdec14fe8ecf064705219528c2a7e76afac9a65e7aff2cab
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b784d21d353cb1ab7af74bca30ff375492629f7fd3b8564b00c00b73c05a05
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": 152.54237288135593,
6
  "eval_steps": 250,
7
- "global_step": 27000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -8864,6 +8864,88 @@
8864
  "eval_samples_per_second": 50.995,
8865
  "eval_steps_per_second": 12.749,
8866
  "step": 27000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8867
  }
8868
  ],
8869
  "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": 153.954802259887,
6
  "eval_steps": 250,
7
+ "global_step": 27250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
8864
  "eval_samples_per_second": 50.995,
8865
  "eval_steps_per_second": 12.749,
8866
  "step": 27000
8867
+ },
8868
+ {
8869
+ "epoch": 152.68361581920905,
8870
+ "grad_norm": 1.1066265106201172,
8871
+ "learning_rate": 3.0517578125e-08,
8872
+ "loss": 0.2369,
8873
+ "step": 27025
8874
+ },
8875
+ {
8876
+ "epoch": 152.82485875706215,
8877
+ "grad_norm": 1.3614978790283203,
8878
+ "learning_rate": 3.0517578125e-08,
8879
+ "loss": 0.2877,
8880
+ "step": 27050
8881
+ },
8882
+ {
8883
+ "epoch": 152.96610169491527,
8884
+ "grad_norm": 3.7374267578125,
8885
+ "learning_rate": 3.0517578125e-08,
8886
+ "loss": 0.2714,
8887
+ "step": 27075
8888
+ },
8889
+ {
8890
+ "epoch": 153.10734463276836,
8891
+ "grad_norm": 1.7165569067001343,
8892
+ "learning_rate": 3.0517578125e-08,
8893
+ "loss": 0.2867,
8894
+ "step": 27100
8895
+ },
8896
+ {
8897
+ "epoch": 153.24858757062148,
8898
+ "grad_norm": 1.8597270250320435,
8899
+ "learning_rate": 3.0517578125e-08,
8900
+ "loss": 0.2535,
8901
+ "step": 27125
8902
+ },
8903
+ {
8904
+ "epoch": 153.38983050847457,
8905
+ "grad_norm": 1.1545196771621704,
8906
+ "learning_rate": 3.0517578125e-08,
8907
+ "loss": 0.27,
8908
+ "step": 27150
8909
+ },
8910
+ {
8911
+ "epoch": 153.5310734463277,
8912
+ "grad_norm": 1.381099820137024,
8913
+ "learning_rate": 3.0517578125e-08,
8914
+ "loss": 0.2577,
8915
+ "step": 27175
8916
+ },
8917
+ {
8918
+ "epoch": 153.6723163841808,
8919
+ "grad_norm": 1.01311457157135,
8920
+ "learning_rate": 3.0517578125e-08,
8921
+ "loss": 0.249,
8922
+ "step": 27200
8923
+ },
8924
+ {
8925
+ "epoch": 153.8135593220339,
8926
+ "grad_norm": 1.8920495510101318,
8927
+ "learning_rate": 3.0517578125e-08,
8928
+ "loss": 0.2715,
8929
+ "step": 27225
8930
+ },
8931
+ {
8932
+ "epoch": 153.954802259887,
8933
+ "grad_norm": 1.1804313659667969,
8934
+ "learning_rate": 3.0517578125e-08,
8935
+ "loss": 0.2507,
8936
+ "step": 27250
8937
+ },
8938
+ {
8939
+ "epoch": 153.954802259887,
8940
+ "eval_asd": 10.039854843023694,
8941
+ "eval_dice": 0.7910890326099744,
8942
+ "eval_hd95": 30.538841540906553,
8943
+ "eval_jaccard": 0.6970893202787153,
8944
+ "eval_loss": 0.3497607111930847,
8945
+ "eval_runtime": 5.097,
8946
+ "eval_samples_per_second": 51.011,
8947
+ "eval_steps_per_second": 12.753,
8948
+ "step": 27250
8949
  }
8950
  ],
8951
  "logging_steps": 25,