aee4 commited on
Commit
77b45e2
·
verified ·
1 Parent(s): d9723d3

Training in progress, step 3250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f113d64db55a91ab198f098b06bf784788d931d91c83933dba8124a3ca598c4
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0365c3040a4917900306e2169895704160458cb2419e231accd9f56569c2af83
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0234d8eb4e48d04b3266627af4ff5e92b2e9d3ed1c50dd6c88e2e5a175e152ab
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5704c2ac816a3a42220b216f9799290ab4db44f799f2d3a5b32a8739a10f0b5
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a95215f64b02d62fb58ace326ad670f1d16eb1761f7fa3b3478d43d2b8d6108
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8553d3987609520495680f36a4682a760a418a930648ce46178a1399cde440b0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a8b1cfa877fe3d508a3d89f8aae273a75f356c5159310dad965dd08e42eed1f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1f84f7a369b1fd785fd1c8cd31399b408a52056ddc4a5c0edd1967702d9d61
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
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,
@@ -1004,6 +1004,89 @@
1004
  "eval_specificity": 0.9920376742907896,
1005
  "eval_steps_per_second": 26.264,
1006
  "step": 3000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1007
  }
1008
  ],
1009
  "logging_steps": 25,
@@ -1018,7 +1101,7 @@
1018
  "early_stopping_threshold": 0.0
1019
  },
1020
  "attributes": {
1021
- "early_stopping_patience_counter": 2
1022
  }
1023
  },
1024
  "TrainerControl": {
 
1
  {
2
+ "best_global_step": 3250,
3
+ "best_metric": 0.8044899088967555,
4
+ "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-3250",
5
+ "epoch": 15.402843601895734,
6
  "eval_steps": 250,
7
+ "global_step": 3250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1004
  "eval_specificity": 0.9920376742907896,
1005
  "eval_steps_per_second": 26.264,
1006
  "step": 3000
1007
+ },
1008
+ {
1009
+ "epoch": 14.336492890995261,
1010
+ "grad_norm": 1.1662991046905518,
1011
+ "learning_rate": 0.00022834123222748812,
1012
+ "loss": 0.3414,
1013
+ "step": 3025
1014
+ },
1015
+ {
1016
+ "epoch": 14.454976303317535,
1017
+ "grad_norm": 1.577745795249939,
1018
+ "learning_rate": 0.00022774881516587675,
1019
+ "loss": 0.3716,
1020
+ "step": 3050
1021
+ },
1022
+ {
1023
+ "epoch": 14.57345971563981,
1024
+ "grad_norm": 2.5545289516448975,
1025
+ "learning_rate": 0.00022715639810426538,
1026
+ "loss": 0.3249,
1027
+ "step": 3075
1028
+ },
1029
+ {
1030
+ "epoch": 14.691943127962086,
1031
+ "grad_norm": 9.015053749084473,
1032
+ "learning_rate": 0.000226563981042654,
1033
+ "loss": 0.3463,
1034
+ "step": 3100
1035
+ },
1036
+ {
1037
+ "epoch": 14.810426540284361,
1038
+ "grad_norm": 3.1575801372528076,
1039
+ "learning_rate": 0.00022597156398104264,
1040
+ "loss": 0.3909,
1041
+ "step": 3125
1042
+ },
1043
+ {
1044
+ "epoch": 14.928909952606634,
1045
+ "grad_norm": 0.4270494878292084,
1046
+ "learning_rate": 0.00022537914691943126,
1047
+ "loss": 0.3606,
1048
+ "step": 3150
1049
+ },
1050
+ {
1051
+ "epoch": 15.04739336492891,
1052
+ "grad_norm": 1.3492119312286377,
1053
+ "learning_rate": 0.0002247867298578199,
1054
+ "loss": 0.3179,
1055
+ "step": 3175
1056
+ },
1057
+ {
1058
+ "epoch": 15.165876777251185,
1059
+ "grad_norm": 3.429630756378174,
1060
+ "learning_rate": 0.0002241943127962085,
1061
+ "loss": 0.3811,
1062
+ "step": 3200
1063
+ },
1064
+ {
1065
+ "epoch": 15.28436018957346,
1066
+ "grad_norm": 1.0582832098007202,
1067
+ "learning_rate": 0.00022360189573459715,
1068
+ "loss": 0.3633,
1069
+ "step": 3225
1070
+ },
1071
+ {
1072
+ "epoch": 15.402843601895734,
1073
+ "grad_norm": 4.290567874908447,
1074
+ "learning_rate": 0.00022300947867298578,
1075
+ "loss": 0.315,
1076
+ "step": 3250
1077
+ },
1078
+ {
1079
+ "epoch": 15.402843601895734,
1080
+ "eval_dice": 0.8044899088967555,
1081
+ "eval_iou": 0.718718018315428,
1082
+ "eval_loss": 0.346737265586853,
1083
+ "eval_precision": 0.8566748822449157,
1084
+ "eval_recall": 0.8101183789212059,
1085
+ "eval_runtime": 3.9884,
1086
+ "eval_samples_per_second": 105.304,
1087
+ "eval_specificity": 0.989016693705865,
1088
+ "eval_steps_per_second": 26.326,
1089
+ "step": 3250
1090
  }
1091
  ],
1092
  "logging_steps": 25,
 
1101
  "early_stopping_threshold": 0.0
1102
  },
1103
  "attributes": {
1104
+ "early_stopping_patience_counter": 0
1105
  }
1106
  },
1107
  "TrainerControl": {