aee4 commited on
Commit
725c214
·
verified ·
1 Parent(s): eff0747

Training in progress, step 10250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2ed21ae35e3800e155600064f0537e7d53a82ceff85c753854caddcfd967cc5
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6817da3a2afda2a49f3362236445c2b6d48e8f72cebd0c0dcc17c2a8481e99a3
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9ac24dc7542c921cbb9dc421392b94c58297151767adc33b6767e7667e9a11d
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae508cd764330c9e88498b2ab64e821a42849ad7085661c062c8b3b7b3a022dc
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:a6dbb90f03320796635b26281f9a3921d95277c32e6673e792faf729c478a88b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32176cfb9726bdd1f5f70beed239110a8bacbb309021c31b449baeb50bb989aa
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23335f3b21225accd4782ef3c4a924d72aff54feef3d38251342660850309f15
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fd4bc03065e125b343158cbde0ceab4d48557902fe1c09cebf9fcdef2f58ac4
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 10000,
3
  "best_metric": 0.8403776925789292,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-10000",
5
- "epoch": 47.39336492890995,
6
  "eval_steps": 250,
7
- "global_step": 10000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3328,6 +3328,89 @@
3328
  "eval_specificity": 0.9828701914870307,
3329
  "eval_steps_per_second": 26.108,
3330
  "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3331
  }
3332
  ],
3333
  "logging_steps": 25,
@@ -3342,7 +3425,7 @@
3342
  "early_stopping_threshold": 0.0
3343
  },
3344
  "attributes": {
3345
- "early_stopping_patience_counter": 0
3346
  }
3347
  },
3348
  "TrainerControl": {
 
2
  "best_global_step": 10000,
3
  "best_metric": 0.8403776925789292,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-10000",
5
+ "epoch": 48.5781990521327,
6
  "eval_steps": 250,
7
+ "global_step": 10250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3328
  "eval_specificity": 0.9828701914870307,
3329
  "eval_steps_per_second": 26.108,
3330
  "step": 10000
3331
+ },
3332
+ {
3333
+ "epoch": 47.51184834123223,
3334
+ "grad_norm": 3.944502830505371,
3335
+ "learning_rate": 6.246445497630331e-05,
3336
+ "loss": 0.2098,
3337
+ "step": 10025
3338
+ },
3339
+ {
3340
+ "epoch": 47.6303317535545,
3341
+ "grad_norm": 1.6057257652282715,
3342
+ "learning_rate": 6.187203791469194e-05,
3343
+ "loss": 0.2423,
3344
+ "step": 10050
3345
+ },
3346
+ {
3347
+ "epoch": 47.74881516587678,
3348
+ "grad_norm": 5.08576774597168,
3349
+ "learning_rate": 6.127962085308057e-05,
3350
+ "loss": 0.2812,
3351
+ "step": 10075
3352
+ },
3353
+ {
3354
+ "epoch": 47.867298578199055,
3355
+ "grad_norm": 1.5568195581436157,
3356
+ "learning_rate": 6.0687203791469184e-05,
3357
+ "loss": 0.2452,
3358
+ "step": 10100
3359
+ },
3360
+ {
3361
+ "epoch": 47.985781990521325,
3362
+ "grad_norm": 1.5616092681884766,
3363
+ "learning_rate": 6.009478672985782e-05,
3364
+ "loss": 0.2199,
3365
+ "step": 10125
3366
+ },
3367
+ {
3368
+ "epoch": 48.1042654028436,
3369
+ "grad_norm": 1.298160433769226,
3370
+ "learning_rate": 5.950236966824644e-05,
3371
+ "loss": 0.2279,
3372
+ "step": 10150
3373
+ },
3374
+ {
3375
+ "epoch": 48.22274881516588,
3376
+ "grad_norm": 1.4128798246383667,
3377
+ "learning_rate": 5.890995260663507e-05,
3378
+ "loss": 0.2401,
3379
+ "step": 10175
3380
+ },
3381
+ {
3382
+ "epoch": 48.34123222748815,
3383
+ "grad_norm": 3.664189338684082,
3384
+ "learning_rate": 5.831753554502369e-05,
3385
+ "loss": 0.2571,
3386
+ "step": 10200
3387
+ },
3388
+ {
3389
+ "epoch": 48.459715639810426,
3390
+ "grad_norm": 1.5395433902740479,
3391
+ "learning_rate": 5.772511848341231e-05,
3392
+ "loss": 0.2176,
3393
+ "step": 10225
3394
+ },
3395
+ {
3396
+ "epoch": 48.5781990521327,
3397
+ "grad_norm": 0.6564604043960571,
3398
+ "learning_rate": 5.7132701421800946e-05,
3399
+ "loss": 0.2248,
3400
+ "step": 10250
3401
+ },
3402
+ {
3403
+ "epoch": 48.5781990521327,
3404
+ "eval_dice": 0.8362172984011872,
3405
+ "eval_iou": 0.7532469173349392,
3406
+ "eval_loss": 0.27925926446914673,
3407
+ "eval_precision": 0.8612305662284476,
3408
+ "eval_recall": 0.8482660596049372,
3409
+ "eval_runtime": 4.0119,
3410
+ "eval_samples_per_second": 104.69,
3411
+ "eval_specificity": 0.9858453922646354,
3412
+ "eval_steps_per_second": 26.172,
3413
+ "step": 10250
3414
  }
3415
  ],
3416
  "logging_steps": 25,
 
3425
  "early_stopping_threshold": 0.0
3426
  },
3427
  "attributes": {
3428
+ "early_stopping_patience_counter": 1
3429
  }
3430
  },
3431
  "TrainerControl": {