aee4 commited on
Commit
a0b5e60
·
verified ·
1 Parent(s): e86d446

Training in progress, step 3500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0365c3040a4917900306e2169895704160458cb2419e231accd9f56569c2af83
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3953b3d9bcd852baf802d2f69c20cb7d6738900ff0a609a38eb45e1518c6cac
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5704c2ac816a3a42220b216f9799290ab4db44f799f2d3a5b32a8739a10f0b5
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b224c0133ddda2f3899646aa4de2cb38a511744d00aacc15bdb9d30555ffd2fc
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8553d3987609520495680f36a4682a760a418a930648ce46178a1399cde440b0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad51b10e839112e76a728f9dcce3122120c8a10612b9b186c929a95fd591904
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e1f84f7a369b1fd785fd1c8cd31399b408a52056ddc4a5c0edd1967702d9d61
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a6ac893777df14d810aa33fba8a8466c2a2c5a1c037c84ea7a8e3e6b4d761b
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
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,
@@ -1087,6 +1087,89 @@
1087
  "eval_specificity": 0.989016693705865,
1088
  "eval_steps_per_second": 26.326,
1089
  "step": 3250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1090
  }
1091
  ],
1092
  "logging_steps": 25,
 
1
  {
2
+ "best_global_step": 3500,
3
+ "best_metric": 0.8116266608952536,
4
+ "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-3500",
5
+ "epoch": 16.587677725118482,
6
  "eval_steps": 250,
7
+ "global_step": 3500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1087
  "eval_specificity": 0.989016693705865,
1088
  "eval_steps_per_second": 26.326,
1089
  "step": 3250
1090
+ },
1091
+ {
1092
+ "epoch": 15.52132701421801,
1093
+ "grad_norm": 2.170355796813965,
1094
+ "learning_rate": 0.00022241706161137438,
1095
+ "loss": 0.3529,
1096
+ "step": 3275
1097
+ },
1098
+ {
1099
+ "epoch": 15.639810426540285,
1100
+ "grad_norm": 2.05668568611145,
1101
+ "learning_rate": 0.00022182464454976303,
1102
+ "loss": 0.2975,
1103
+ "step": 3300
1104
+ },
1105
+ {
1106
+ "epoch": 15.75829383886256,
1107
+ "grad_norm": 1.8362689018249512,
1108
+ "learning_rate": 0.00022123222748815163,
1109
+ "loss": 0.3534,
1110
+ "step": 3325
1111
+ },
1112
+ {
1113
+ "epoch": 15.876777251184834,
1114
+ "grad_norm": 1.6324963569641113,
1115
+ "learning_rate": 0.00022063981042654026,
1116
+ "loss": 0.3369,
1117
+ "step": 3350
1118
+ },
1119
+ {
1120
+ "epoch": 15.995260663507109,
1121
+ "grad_norm": 0.6811165809631348,
1122
+ "learning_rate": 0.00022004739336492892,
1123
+ "loss": 0.3685,
1124
+ "step": 3375
1125
+ },
1126
+ {
1127
+ "epoch": 16.113744075829384,
1128
+ "grad_norm": 0.734277069568634,
1129
+ "learning_rate": 0.00021945497630331752,
1130
+ "loss": 0.3385,
1131
+ "step": 3400
1132
+ },
1133
+ {
1134
+ "epoch": 16.232227488151658,
1135
+ "grad_norm": 0.8578847050666809,
1136
+ "learning_rate": 0.00021886255924170615,
1137
+ "loss": 0.3064,
1138
+ "step": 3425
1139
+ },
1140
+ {
1141
+ "epoch": 16.350710900473935,
1142
+ "grad_norm": 1.7155730724334717,
1143
+ "learning_rate": 0.00021827014218009475,
1144
+ "loss": 0.3416,
1145
+ "step": 3450
1146
+ },
1147
+ {
1148
+ "epoch": 16.46919431279621,
1149
+ "grad_norm": 3.927844285964966,
1150
+ "learning_rate": 0.0002176777251184834,
1151
+ "loss": 0.3546,
1152
+ "step": 3475
1153
+ },
1154
+ {
1155
+ "epoch": 16.587677725118482,
1156
+ "grad_norm": 3.0497796535491943,
1157
+ "learning_rate": 0.00021708530805687203,
1158
+ "loss": 0.3798,
1159
+ "step": 3500
1160
+ },
1161
+ {
1162
+ "epoch": 16.587677725118482,
1163
+ "eval_dice": 0.8116266608952536,
1164
+ "eval_iou": 0.7224499948883196,
1165
+ "eval_loss": 0.3336605727672577,
1166
+ "eval_precision": 0.8230311671567544,
1167
+ "eval_recall": 0.8480512286139866,
1168
+ "eval_runtime": 3.9698,
1169
+ "eval_samples_per_second": 105.799,
1170
+ "eval_specificity": 0.984850914069978,
1171
+ "eval_steps_per_second": 26.45,
1172
+ "step": 3500
1173
  }
1174
  ],
1175
  "logging_steps": 25,