aee4 commited on
Commit
18eb2ea
·
verified ·
1 Parent(s): 44972eb

Training in progress, step 29000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d02b64f5e6137683920d2c91ccb3d457eb034056c1baec06409aeeabbcb7831d
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cba105a991310824863a02c859bf0f6c43c9900432452a1880b1f2a5df4cf7f
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9b82d08ea98d74131529d3a8155d403942dcdb5193964e8c8b27e9a122fb8b3
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3043e28073acc6653129beb7a2747c02a4be7fac4c0be6cc39c006bab6ec7af
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77c116b3aebc1918c5e63c1859ba10ae16f47a5bd62cf4dbe771cb0153ca14a3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6566cfc6ffb2d4f489ca5e3b763009366a4a2a0b093dd01514fc2d531cbb3e0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b55f7f713843019ad2c6781f234450280135b1cb3a52a6a761977c88a3061c2f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71c815fd12f57f1d9b333b50556ec7142747cfb81779db9ed759d6ec3ef571f8
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 18500,
3
  "best_metric": 0.7932397701166506,
4
  "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-18500",
5
- "epoch": 162.42937853107344,
6
  "eval_steps": 250,
7
- "global_step": 28750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -9438,6 +9438,88 @@
9438
  "eval_samples_per_second": 51.13,
9439
  "eval_steps_per_second": 12.782,
9440
  "step": 28750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9441
  }
9442
  ],
9443
  "logging_steps": 25,
 
2
  "best_global_step": 18500,
3
  "best_metric": 0.7932397701166506,
4
  "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-18500",
5
+ "epoch": 163.8418079096045,
6
  "eval_steps": 250,
7
+ "global_step": 29000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
9438
  "eval_samples_per_second": 51.13,
9439
  "eval_steps_per_second": 12.782,
9440
  "step": 28750
9441
+ },
9442
+ {
9443
+ "epoch": 162.57062146892656,
9444
+ "grad_norm": 0.7945625185966492,
9445
+ "learning_rate": 1.52587890625e-08,
9446
+ "loss": 0.2667,
9447
+ "step": 28775
9448
+ },
9449
+ {
9450
+ "epoch": 162.71186440677965,
9451
+ "grad_norm": 1.0799317359924316,
9452
+ "learning_rate": 1.52587890625e-08,
9453
+ "loss": 0.2652,
9454
+ "step": 28800
9455
+ },
9456
+ {
9457
+ "epoch": 162.85310734463278,
9458
+ "grad_norm": 1.4340652227401733,
9459
+ "learning_rate": 1.52587890625e-08,
9460
+ "loss": 0.265,
9461
+ "step": 28825
9462
+ },
9463
+ {
9464
+ "epoch": 162.99435028248587,
9465
+ "grad_norm": 1.1508347988128662,
9466
+ "learning_rate": 1.52587890625e-08,
9467
+ "loss": 0.2533,
9468
+ "step": 28850
9469
+ },
9470
+ {
9471
+ "epoch": 163.135593220339,
9472
+ "grad_norm": 1.4746330976486206,
9473
+ "learning_rate": 1.52587890625e-08,
9474
+ "loss": 0.2557,
9475
+ "step": 28875
9476
+ },
9477
+ {
9478
+ "epoch": 163.27683615819208,
9479
+ "grad_norm": 2.0886967182159424,
9480
+ "learning_rate": 1.52587890625e-08,
9481
+ "loss": 0.2608,
9482
+ "step": 28900
9483
+ },
9484
+ {
9485
+ "epoch": 163.4180790960452,
9486
+ "grad_norm": 1.8162198066711426,
9487
+ "learning_rate": 1.52587890625e-08,
9488
+ "loss": 0.244,
9489
+ "step": 28925
9490
+ },
9491
+ {
9492
+ "epoch": 163.5593220338983,
9493
+ "grad_norm": 1.4550220966339111,
9494
+ "learning_rate": 1.52587890625e-08,
9495
+ "loss": 0.268,
9496
+ "step": 28950
9497
+ },
9498
+ {
9499
+ "epoch": 163.70056497175142,
9500
+ "grad_norm": 1.8503577709197998,
9501
+ "learning_rate": 1.52587890625e-08,
9502
+ "loss": 0.2518,
9503
+ "step": 28975
9504
+ },
9505
+ {
9506
+ "epoch": 163.8418079096045,
9507
+ "grad_norm": 1.09251868724823,
9508
+ "learning_rate": 1.52587890625e-08,
9509
+ "loss": 0.2609,
9510
+ "step": 29000
9511
+ },
9512
+ {
9513
+ "epoch": 163.8418079096045,
9514
+ "eval_asd": 10.070173957171534,
9515
+ "eval_dice": 0.7912016210187272,
9516
+ "eval_hd95": 30.75775920619105,
9517
+ "eval_jaccard": 0.697150315825311,
9518
+ "eval_loss": 0.3487544357776642,
9519
+ "eval_runtime": 5.1358,
9520
+ "eval_samples_per_second": 50.625,
9521
+ "eval_steps_per_second": 12.656,
9522
+ "step": 29000
9523
  }
9524
  ],
9525
  "logging_steps": 25,