aee4 commited on
Commit
288a57f
·
verified ·
1 Parent(s): 0eddce0

Training in progress, step 32250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd1b5cc696418ac14ca64fc4b743dfea3996f53dbd50fce25070bef97ddfe055
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:920fb38cbb24c1414bb159951cf0010f3fb3dc85a545c2f2ff8459e374ae6b4d
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:219aa61074ab6dfbc836c295f51a0e6cb95dae1709cfd32a24c1e61c291708db
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e55769aa6e8eec6e9651f4828d9efc4fadb2120a7c1b92e7bcffd51678deb4a
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84be82a0aac1de5442bd7a3a1b9d3ae51c65d62a5d1ec9a9db736ff1cbd20626
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28351f3cc9f021eaa81d3137a6d67b229a50f084154e81e9f478f37a6fc4612b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28af6884a741203d787c22aa07f9ef7af89a0ec502079ab322ed3c93de38fc98
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183e011caa9d729b44b0c7e0826d62d7c6cf1ad519e39b529ac9a43f5691684e
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": 180.7909604519774,
6
  "eval_steps": 250,
7
- "global_step": 32000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -10504,6 +10504,88 @@
10504
  "eval_samples_per_second": 51.112,
10505
  "eval_steps_per_second": 12.778,
10506
  "step": 32000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10507
  }
10508
  ],
10509
  "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": 182.20338983050848,
6
  "eval_steps": 250,
7
+ "global_step": 32250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
10504
  "eval_samples_per_second": 51.112,
10505
  "eval_steps_per_second": 12.778,
10506
  "step": 32000
10507
+ },
10508
+ {
10509
+ "epoch": 180.9322033898305,
10510
+ "grad_norm": 0.8895372748374939,
10511
+ "learning_rate": 3.814697265625e-09,
10512
+ "loss": 0.2628,
10513
+ "step": 32025
10514
+ },
10515
+ {
10516
+ "epoch": 181.07344632768363,
10517
+ "grad_norm": 1.2311677932739258,
10518
+ "learning_rate": 3.814697265625e-09,
10519
+ "loss": 0.2562,
10520
+ "step": 32050
10521
+ },
10522
+ {
10523
+ "epoch": 181.21468926553672,
10524
+ "grad_norm": 2.450664758682251,
10525
+ "learning_rate": 3.814697265625e-09,
10526
+ "loss": 0.2469,
10527
+ "step": 32075
10528
+ },
10529
+ {
10530
+ "epoch": 181.35593220338984,
10531
+ "grad_norm": 2.7843716144561768,
10532
+ "learning_rate": 3.814697265625e-09,
10533
+ "loss": 0.254,
10534
+ "step": 32100
10535
+ },
10536
+ {
10537
+ "epoch": 181.49717514124293,
10538
+ "grad_norm": 1.5901066064834595,
10539
+ "learning_rate": 3.814697265625e-09,
10540
+ "loss": 0.2811,
10541
+ "step": 32125
10542
+ },
10543
+ {
10544
+ "epoch": 181.63841807909606,
10545
+ "grad_norm": 1.877365231513977,
10546
+ "learning_rate": 3.814697265625e-09,
10547
+ "loss": 0.2705,
10548
+ "step": 32150
10549
+ },
10550
+ {
10551
+ "epoch": 181.77966101694915,
10552
+ "grad_norm": 1.953351378440857,
10553
+ "learning_rate": 3.814697265625e-09,
10554
+ "loss": 0.2564,
10555
+ "step": 32175
10556
+ },
10557
+ {
10558
+ "epoch": 181.92090395480227,
10559
+ "grad_norm": 1.4703274965286255,
10560
+ "learning_rate": 3.814697265625e-09,
10561
+ "loss": 0.2584,
10562
+ "step": 32200
10563
+ },
10564
+ {
10565
+ "epoch": 182.06214689265536,
10566
+ "grad_norm": 1.59602952003479,
10567
+ "learning_rate": 3.814697265625e-09,
10568
+ "loss": 0.2485,
10569
+ "step": 32225
10570
+ },
10571
+ {
10572
+ "epoch": 182.20338983050848,
10573
+ "grad_norm": 1.576170802116394,
10574
+ "learning_rate": 3.814697265625e-09,
10575
+ "loss": 0.2744,
10576
+ "step": 32250
10577
+ },
10578
+ {
10579
+ "epoch": 182.20338983050848,
10580
+ "eval_asd": 10.129164039983765,
10581
+ "eval_dice": 0.791251187707582,
10582
+ "eval_hd95": 30.823732280619815,
10583
+ "eval_jaccard": 0.697155757807823,
10584
+ "eval_loss": 0.3506031334400177,
10585
+ "eval_runtime": 5.1104,
10586
+ "eval_samples_per_second": 50.877,
10587
+ "eval_steps_per_second": 12.719,
10588
+ "step": 32250
10589
  }
10590
  ],
10591
  "logging_steps": 25,