aee4 commited on
Commit
09efa95
·
verified ·
1 Parent(s): 0d6d57a

Training in progress, step 3000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1535381112734493074a2a8a5c0c53d00c343e8ac9d9c8b9a210510c41f4fb3a
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f113d64db55a91ab198f098b06bf784788d931d91c83933dba8124a3ca598c4
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56625fa7f98d61a651b17dbfe466d67465c902eff3c704254f481eb8c6de6e56
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0234d8eb4e48d04b3266627af4ff5e92b2e9d3ed1c50dd6c88e2e5a175e152ab
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a804dd9b4962bc1e7c8e5b51c83ce95f04ab0a366340b47fc4849e7d4ecffd6d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a95215f64b02d62fb58ace326ad670f1d16eb1761f7fa3b3478d43d2b8d6108
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03b62609dfdc390c0309f694d3b2203ee09ee9a0f90c9f0a09e6fb3c2ce8c439
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a8b1cfa877fe3d508a3d89f8aae273a75f356c5159310dad965dd08e42eed1f
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 2500,
3
  "best_metric": 0.7978012695406858,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-2500",
5
- "epoch": 13.033175355450236,
6
  "eval_steps": 250,
7
- "global_step": 2750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -921,6 +921,89 @@
921
  "eval_specificity": 0.9814133020651598,
922
  "eval_steps_per_second": 26.414,
923
  "step": 2750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
924
  }
925
  ],
926
  "logging_steps": 25,
@@ -935,7 +1018,7 @@
935
  "early_stopping_threshold": 0.0
936
  },
937
  "attributes": {
938
- "early_stopping_patience_counter": 1
939
  }
940
  },
941
  "TrainerControl": {
 
2
  "best_global_step": 2500,
3
  "best_metric": 0.7978012695406858,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-2500",
5
+ "epoch": 14.218009478672986,
6
  "eval_steps": 250,
7
+ "global_step": 3000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
921
  "eval_specificity": 0.9814133020651598,
922
  "eval_steps_per_second": 26.414,
923
  "step": 2750
924
+ },
925
+ {
926
+ "epoch": 13.151658767772512,
927
+ "grad_norm": 2.0801682472229004,
928
+ "learning_rate": 0.00023426540284360187,
929
+ "loss": 0.3068,
930
+ "step": 2775
931
+ },
932
+ {
933
+ "epoch": 13.270142180094787,
934
+ "grad_norm": 5.534780979156494,
935
+ "learning_rate": 0.0002336729857819905,
936
+ "loss": 0.3268,
937
+ "step": 2800
938
+ },
939
+ {
940
+ "epoch": 13.388625592417062,
941
+ "grad_norm": 1.5055299997329712,
942
+ "learning_rate": 0.00023308056872037912,
943
+ "loss": 0.3724,
944
+ "step": 2825
945
+ },
946
+ {
947
+ "epoch": 13.507109004739336,
948
+ "grad_norm": 4.12996768951416,
949
+ "learning_rate": 0.00023248815165876775,
950
+ "loss": 0.3282,
951
+ "step": 2850
952
+ },
953
+ {
954
+ "epoch": 13.625592417061611,
955
+ "grad_norm": 0.9329816102981567,
956
+ "learning_rate": 0.00023189573459715638,
957
+ "loss": 0.3427,
958
+ "step": 2875
959
+ },
960
+ {
961
+ "epoch": 13.744075829383887,
962
+ "grad_norm": 0.39483118057250977,
963
+ "learning_rate": 0.000231303317535545,
964
+ "loss": 0.3431,
965
+ "step": 2900
966
+ },
967
+ {
968
+ "epoch": 13.862559241706162,
969
+ "grad_norm": 3.6165993213653564,
970
+ "learning_rate": 0.00023071090047393364,
971
+ "loss": 0.3675,
972
+ "step": 2925
973
+ },
974
+ {
975
+ "epoch": 13.981042654028435,
976
+ "grad_norm": 2.748633861541748,
977
+ "learning_rate": 0.00023011848341232224,
978
+ "loss": 0.4157,
979
+ "step": 2950
980
+ },
981
+ {
982
+ "epoch": 14.09952606635071,
983
+ "grad_norm": 1.0624897480010986,
984
+ "learning_rate": 0.0002295260663507109,
985
+ "loss": 0.3904,
986
+ "step": 2975
987
+ },
988
+ {
989
+ "epoch": 14.218009478672986,
990
+ "grad_norm": 3.1612582206726074,
991
+ "learning_rate": 0.00022893364928909952,
992
+ "loss": 0.3618,
993
+ "step": 3000
994
+ },
995
+ {
996
+ "epoch": 14.218009478672986,
997
+ "eval_dice": 0.778690010691854,
998
+ "eval_iou": 0.6846281801358097,
999
+ "eval_loss": 0.38707780838012695,
1000
+ "eval_precision": 0.8852834625312765,
1001
+ "eval_recall": 0.7412936980795883,
1002
+ "eval_runtime": 3.9978,
1003
+ "eval_samples_per_second": 105.057,
1004
+ "eval_specificity": 0.9920376742907896,
1005
+ "eval_steps_per_second": 26.264,
1006
+ "step": 3000
1007
  }
1008
  ],
1009
  "logging_steps": 25,
 
1018
  "early_stopping_threshold": 0.0
1019
  },
1020
  "attributes": {
1021
+ "early_stopping_patience_counter": 2
1022
  }
1023
  },
1024
  "TrainerControl": {