aee4 commited on
Commit
d45bf34
·
verified ·
1 Parent(s): 0e225e5

Training in progress, step 10500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50984b2cd304ed41e9a26a244f0f38731c9300aa13e33bd56e86750befbe17e2
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23fc53d318ab66256c460bebf65a026268f2bd43b278527c77419ed17e7f62d8
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b21089b799194072b05ad6cc5be7cbe1491663cf9d055b584603c7a12119d935
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb20ff3768abd8e27be27c8c052375bb834a1e11b98b7cbe84cfda9da606e771
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32176cfb9726bdd1f5f70beed239110a8bacbb309021c31b449baeb50bb989aa
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de9b0286a7ff6d8e319cf8cd55365d4e61da2d79922461b32fb208d425c027c
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fd4bc03065e125b343158cbde0ceab4d48557902fe1c09cebf9fcdef2f58ac4
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0674e26b3ea83c7026bac8c58e207b898a2afb7f3fd370309d9bfe5e753db1a
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 10000,
3
  "best_metric": 0.8396956422654931,
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,
@@ -3411,6 +3411,89 @@
3411
  "eval_specificity": 0.9878321576512926,
3412
  "eval_steps_per_second": 26.436,
3413
  "step": 10250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3414
  }
3415
  ],
3416
  "logging_steps": 25,
@@ -3425,7 +3508,7 @@
3425
  "early_stopping_threshold": 0.0
3426
  },
3427
  "attributes": {
3428
- "early_stopping_patience_counter": 1
3429
  }
3430
  },
3431
  "TrainerControl": {
 
2
  "best_global_step": 10000,
3
  "best_metric": 0.8396956422654931,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-10000",
5
+ "epoch": 49.76303317535545,
6
  "eval_steps": 250,
7
+ "global_step": 10500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3411
  "eval_specificity": 0.9878321576512926,
3412
  "eval_steps_per_second": 26.436,
3413
  "step": 10250
3414
+ },
3415
+ {
3416
+ "epoch": 48.69668246445497,
3417
+ "grad_norm": 1.6236644983291626,
3418
+ "learning_rate": 5.654028436018957e-05,
3419
+ "loss": 0.2326,
3420
+ "step": 10275
3421
+ },
3422
+ {
3423
+ "epoch": 48.81516587677725,
3424
+ "grad_norm": 1.9124441146850586,
3425
+ "learning_rate": 5.5947867298578196e-05,
3426
+ "loss": 0.2217,
3427
+ "step": 10300
3428
+ },
3429
+ {
3430
+ "epoch": 48.93364928909953,
3431
+ "grad_norm": 5.480804443359375,
3432
+ "learning_rate": 5.535545023696682e-05,
3433
+ "loss": 0.2094,
3434
+ "step": 10325
3435
+ },
3436
+ {
3437
+ "epoch": 49.052132701421804,
3438
+ "grad_norm": 0.40421801805496216,
3439
+ "learning_rate": 5.4763033175355445e-05,
3440
+ "loss": 0.2283,
3441
+ "step": 10350
3442
+ },
3443
+ {
3444
+ "epoch": 49.170616113744074,
3445
+ "grad_norm": 1.2528854608535767,
3446
+ "learning_rate": 5.417061611374407e-05,
3447
+ "loss": 0.2497,
3448
+ "step": 10375
3449
+ },
3450
+ {
3451
+ "epoch": 49.28909952606635,
3452
+ "grad_norm": 1.6669247150421143,
3453
+ "learning_rate": 5.3578199052132695e-05,
3454
+ "loss": 0.2628,
3455
+ "step": 10400
3456
+ },
3457
+ {
3458
+ "epoch": 49.40758293838863,
3459
+ "grad_norm": 0.6224846839904785,
3460
+ "learning_rate": 5.298578199052132e-05,
3461
+ "loss": 0.2015,
3462
+ "step": 10425
3463
+ },
3464
+ {
3465
+ "epoch": 49.5260663507109,
3466
+ "grad_norm": 3.712109327316284,
3467
+ "learning_rate": 5.239336492890995e-05,
3468
+ "loss": 0.2291,
3469
+ "step": 10450
3470
+ },
3471
+ {
3472
+ "epoch": 49.644549763033176,
3473
+ "grad_norm": 2.576796531677246,
3474
+ "learning_rate": 5.180094786729857e-05,
3475
+ "loss": 0.2239,
3476
+ "step": 10475
3477
+ },
3478
+ {
3479
+ "epoch": 49.76303317535545,
3480
+ "grad_norm": 0.6758880019187927,
3481
+ "learning_rate": 5.12085308056872e-05,
3482
+ "loss": 0.2367,
3483
+ "step": 10500
3484
+ },
3485
+ {
3486
+ "epoch": 49.76303317535545,
3487
+ "eval_dice": 0.8338846019122825,
3488
+ "eval_iou": 0.7532402696643706,
3489
+ "eval_loss": 0.2920394539833069,
3490
+ "eval_precision": 0.8651331161821132,
3491
+ "eval_recall": 0.8412825252937629,
3492
+ "eval_runtime": 4.0151,
3493
+ "eval_samples_per_second": 104.606,
3494
+ "eval_specificity": 0.9880921379308268,
3495
+ "eval_steps_per_second": 26.151,
3496
+ "step": 10500
3497
  }
3498
  ],
3499
  "logging_steps": 25,
 
3508
  "early_stopping_threshold": 0.0
3509
  },
3510
  "attributes": {
3511
+ "early_stopping_patience_counter": 2
3512
  }
3513
  },
3514
  "TrainerControl": {