aee4 commited on
Commit
0802acc
·
verified ·
1 Parent(s): ee8efe9

Training in progress, step 10750, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23fc53d318ab66256c460bebf65a026268f2bd43b278527c77419ed17e7f62d8
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c4592ce34800539e9cffd4925c38523f8b0a53030f34a1bf40e4de91fe9339d
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb20ff3768abd8e27be27c8c052375bb834a1e11b98b7cbe84cfda9da606e771
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aecaeae8908ef5ba2202370537cb1effd26ae7a0c01e3c72b25091a8c766265
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2de9b0286a7ff6d8e319cf8cd55365d4e61da2d79922461b32fb208d425c027c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1da75bced15d0c0ad08ac6f92e20da81e67fff47141ca76354909981931d2e09
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0674e26b3ea83c7026bac8c58e207b898a2afb7f3fd370309d9bfe5e753db1a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9084cee024bb8c815a21896260b435cbb1aab1a6ab0ff0fc1c5a4b90752d25ff
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": 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,
@@ -3494,6 +3494,89 @@
3494
  "eval_specificity": 0.9880921379308268,
3495
  "eval_steps_per_second": 26.151,
3496
  "step": 10500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3497
  }
3498
  ],
3499
  "logging_steps": 25,
@@ -3508,7 +3591,7 @@
3508
  "early_stopping_threshold": 0.0
3509
  },
3510
  "attributes": {
3511
- "early_stopping_patience_counter": 2
3512
  }
3513
  },
3514
  "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": 50.9478672985782,
6
  "eval_steps": 250,
7
+ "global_step": 10750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3494
  "eval_specificity": 0.9880921379308268,
3495
  "eval_steps_per_second": 26.151,
3496
  "step": 10500
3497
+ },
3498
+ {
3499
+ "epoch": 49.88151658767772,
3500
+ "grad_norm": 0.40841296315193176,
3501
+ "learning_rate": 5.061611374407582e-05,
3502
+ "loss": 0.1979,
3503
+ "step": 10525
3504
+ },
3505
+ {
3506
+ "epoch": 50.0,
3507
+ "grad_norm": 1.612800121307373,
3508
+ "learning_rate": 5.002369668246446e-05,
3509
+ "loss": 0.2527,
3510
+ "step": 10550
3511
+ },
3512
+ {
3513
+ "epoch": 50.11848341232228,
3514
+ "grad_norm": 1.4746556282043457,
3515
+ "learning_rate": 4.943127962085308e-05,
3516
+ "loss": 0.2262,
3517
+ "step": 10575
3518
+ },
3519
+ {
3520
+ "epoch": 50.23696682464455,
3521
+ "grad_norm": 6.130502700805664,
3522
+ "learning_rate": 4.88388625592417e-05,
3523
+ "loss": 0.2203,
3524
+ "step": 10600
3525
+ },
3526
+ {
3527
+ "epoch": 50.355450236966824,
3528
+ "grad_norm": 1.6463886499404907,
3529
+ "learning_rate": 4.824644549763033e-05,
3530
+ "loss": 0.2098,
3531
+ "step": 10625
3532
+ },
3533
+ {
3534
+ "epoch": 50.4739336492891,
3535
+ "grad_norm": 3.873288869857788,
3536
+ "learning_rate": 4.765402843601895e-05,
3537
+ "loss": 0.2242,
3538
+ "step": 10650
3539
+ },
3540
+ {
3541
+ "epoch": 50.59241706161137,
3542
+ "grad_norm": 1.2585475444793701,
3543
+ "learning_rate": 4.7061611374407584e-05,
3544
+ "loss": 0.2519,
3545
+ "step": 10675
3546
+ },
3547
+ {
3548
+ "epoch": 50.71090047393365,
3549
+ "grad_norm": 0.7723769545555115,
3550
+ "learning_rate": 4.6469194312796205e-05,
3551
+ "loss": 0.2035,
3552
+ "step": 10700
3553
+ },
3554
+ {
3555
+ "epoch": 50.829383886255926,
3556
+ "grad_norm": 2.0607786178588867,
3557
+ "learning_rate": 4.587677725118483e-05,
3558
+ "loss": 0.2569,
3559
+ "step": 10725
3560
+ },
3561
+ {
3562
+ "epoch": 50.9478672985782,
3563
+ "grad_norm": 0.849461555480957,
3564
+ "learning_rate": 4.5284360189573455e-05,
3565
+ "loss": 0.2387,
3566
+ "step": 10750
3567
+ },
3568
+ {
3569
+ "epoch": 50.9478672985782,
3570
+ "eval_dice": 0.8365962699233992,
3571
+ "eval_iou": 0.7557875999378797,
3572
+ "eval_loss": 0.28302592039108276,
3573
+ "eval_precision": 0.8513715790476627,
3574
+ "eval_recall": 0.8580040627385193,
3575
+ "eval_runtime": 4.0052,
3576
+ "eval_samples_per_second": 104.863,
3577
+ "eval_specificity": 0.9857683519200869,
3578
+ "eval_steps_per_second": 26.216,
3579
+ "step": 10750
3580
  }
3581
  ],
3582
  "logging_steps": 25,
 
3591
  "early_stopping_threshold": 0.0
3592
  },
3593
  "attributes": {
3594
+ "early_stopping_patience_counter": 3
3595
  }
3596
  },
3597
  "TrainerControl": {