aee4 commited on
Commit
9a44d69
·
verified ·
1 Parent(s): dd7f3f3

Training in progress, step 4000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ced94accc727ca2bc0d23ca961e82c43c5de36e879ce638916898aa4df3a701
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4e56efbdb73ebae7919aad782f36af02abac5694c4468dd2da4a602ebd6611
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30ec6a2af856ba1d33ab4a167f2b2cb91fd64b46c5e910d1d0198a7d330dc771
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225a8d346848ce8df251ff085834186d2030fafdcb8afdc78ee7c06ee0894016
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:428aed83766f09a6a2d9ccfb86972eeda646225b3b0cd6accec4a90e4f900161
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63aab5945fa6a4f19ef11eca5b6add2fab56216a2af2a42b2f4db10b37425e8e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e1f39b5505482f9af92307fe34a11bae8a1ec2b43a86b1f36923bb70d565321
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb4399e6711cba70be49f1b0d117e1d07819f402683df91af196744b25c2d3a
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
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": 17.77251184834123,
6
  "eval_steps": 250,
7
- "global_step": 3750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1253,6 +1253,89 @@
1253
  "eval_specificity": 0.9890864062817681,
1254
  "eval_steps_per_second": 26.402,
1255
  "step": 3750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1256
  }
1257
  ],
1258
  "logging_steps": 25,
@@ -1267,7 +1350,7 @@
1267
  "early_stopping_threshold": 0.0
1268
  },
1269
  "attributes": {
1270
- "early_stopping_patience_counter": 1
1271
  }
1272
  },
1273
  "TrainerControl": {
 
1
  {
2
+ "best_global_step": 4000,
3
+ "best_metric": 0.8133356678481004,
4
+ "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-4000",
5
+ "epoch": 18.95734597156398,
6
  "eval_steps": 250,
7
+ "global_step": 4000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1253
  "eval_specificity": 0.9890864062817681,
1254
  "eval_steps_per_second": 26.402,
1255
  "step": 3750
1256
+ },
1257
+ {
1258
+ "epoch": 17.89099526066351,
1259
+ "grad_norm": 5.142725467681885,
1260
+ "learning_rate": 0.00021056872037914689,
1261
+ "loss": 0.3185,
1262
+ "step": 3775
1263
+ },
1264
+ {
1265
+ "epoch": 18.009478672985782,
1266
+ "grad_norm": 2.5820343494415283,
1267
+ "learning_rate": 0.00020997630331753554,
1268
+ "loss": 0.3293,
1269
+ "step": 3800
1270
+ },
1271
+ {
1272
+ "epoch": 18.127962085308056,
1273
+ "grad_norm": 1.0522630214691162,
1274
+ "learning_rate": 0.00020938388625592414,
1275
+ "loss": 0.3492,
1276
+ "step": 3825
1277
+ },
1278
+ {
1279
+ "epoch": 18.246445497630333,
1280
+ "grad_norm": 1.011150598526001,
1281
+ "learning_rate": 0.00020879146919431277,
1282
+ "loss": 0.3011,
1283
+ "step": 3850
1284
+ },
1285
+ {
1286
+ "epoch": 18.364928909952607,
1287
+ "grad_norm": 0.7069483995437622,
1288
+ "learning_rate": 0.00020819905213270143,
1289
+ "loss": 0.3495,
1290
+ "step": 3875
1291
+ },
1292
+ {
1293
+ "epoch": 18.48341232227488,
1294
+ "grad_norm": 1.3292298316955566,
1295
+ "learning_rate": 0.00020760663507109003,
1296
+ "loss": 0.3583,
1297
+ "step": 3900
1298
+ },
1299
+ {
1300
+ "epoch": 18.601895734597157,
1301
+ "grad_norm": 1.4981029033660889,
1302
+ "learning_rate": 0.00020701421800947865,
1303
+ "loss": 0.3264,
1304
+ "step": 3925
1305
+ },
1306
+ {
1307
+ "epoch": 18.72037914691943,
1308
+ "grad_norm": 3.668264150619507,
1309
+ "learning_rate": 0.00020642180094786726,
1310
+ "loss": 0.2897,
1311
+ "step": 3950
1312
+ },
1313
+ {
1314
+ "epoch": 18.838862559241708,
1315
+ "grad_norm": 2.195600986480713,
1316
+ "learning_rate": 0.0002058293838862559,
1317
+ "loss": 0.311,
1318
+ "step": 3975
1319
+ },
1320
+ {
1321
+ "epoch": 18.95734597156398,
1322
+ "grad_norm": 0.9898369908332825,
1323
+ "learning_rate": 0.00020523696682464454,
1324
+ "loss": 0.3678,
1325
+ "step": 4000
1326
+ },
1327
+ {
1328
+ "epoch": 18.95734597156398,
1329
+ "eval_dice": 0.8133356678481004,
1330
+ "eval_iou": 0.7271215896545176,
1331
+ "eval_loss": 0.32779061794281006,
1332
+ "eval_precision": 0.8281005236038452,
1333
+ "eval_recall": 0.8525780734871894,
1334
+ "eval_runtime": 3.9799,
1335
+ "eval_samples_per_second": 105.53,
1336
+ "eval_specificity": 0.9846235508040047,
1337
+ "eval_steps_per_second": 26.383,
1338
+ "step": 4000
1339
  }
1340
  ],
1341
  "logging_steps": 25,
 
1350
  "early_stopping_threshold": 0.0
1351
  },
1352
  "attributes": {
1353
+ "early_stopping_patience_counter": 0
1354
  }
1355
  },
1356
  "TrainerControl": {