aee4 commited on
Commit
eeb72f9
·
verified ·
1 Parent(s): d82f117

Training in progress, step 26250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4ac2b9ea578ac0723f1a9983297e88345d1579d31d7e3dbe2fe0019776cef07
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e6914ff34e2c37a902a8e27c913bad86310f11a886aa152ef32cafb8b8e2d6
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c3751246c4a1c4469b4eb9b3174f156f89f9257e952209cef0bd735d8cc7d8a
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9249bc48e2b9137137bdc43dfb3dfed1b12e6f28de5a1f99f5b0aa5e3bdc7eb5
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:ac8215c8453acfecf490d2d32032f34662d53d1e714d3718318dce3dc33fa786
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d83da7d3ddea445ede9f960a7e389d8b0bd2e1fc4596e4e0241ad4877d08952c
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec07fd001272c4b628af25c7623521ac00c253c73b25f0502822730523b0b41b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d80b1c7aca49008ea603c6dae7f034292ad375dd4c090f11cfd3b8da55232e72
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": 146.89265536723164,
6
  "eval_steps": 250,
7
- "global_step": 26000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -8536,6 +8536,88 @@
8536
  "eval_samples_per_second": 50.786,
8537
  "eval_steps_per_second": 12.696,
8538
  "step": 26000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8539
  }
8540
  ],
8541
  "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": 148.3050847457627,
6
  "eval_steps": 250,
7
+ "global_step": 26250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
8536
  "eval_samples_per_second": 50.786,
8537
  "eval_steps_per_second": 12.696,
8538
  "step": 26000
8539
+ },
8540
+ {
8541
+ "epoch": 147.03389830508473,
8542
+ "grad_norm": 2.2682864665985107,
8543
+ "learning_rate": 6.103515625e-08,
8544
+ "loss": 0.2651,
8545
+ "step": 26025
8546
+ },
8547
+ {
8548
+ "epoch": 147.17514124293785,
8549
+ "grad_norm": 0.9155160188674927,
8550
+ "learning_rate": 6.103515625e-08,
8551
+ "loss": 0.2691,
8552
+ "step": 26050
8553
+ },
8554
+ {
8555
+ "epoch": 147.31638418079095,
8556
+ "grad_norm": 1.977743148803711,
8557
+ "learning_rate": 6.103515625e-08,
8558
+ "loss": 0.254,
8559
+ "step": 26075
8560
+ },
8561
+ {
8562
+ "epoch": 147.45762711864407,
8563
+ "grad_norm": 1.5487498044967651,
8564
+ "learning_rate": 6.103515625e-08,
8565
+ "loss": 0.2606,
8566
+ "step": 26100
8567
+ },
8568
+ {
8569
+ "epoch": 147.59887005649716,
8570
+ "grad_norm": 1.0697898864746094,
8571
+ "learning_rate": 6.103515625e-08,
8572
+ "loss": 0.2685,
8573
+ "step": 26125
8574
+ },
8575
+ {
8576
+ "epoch": 147.74011299435028,
8577
+ "grad_norm": 3.3261802196502686,
8578
+ "learning_rate": 6.103515625e-08,
8579
+ "loss": 0.2838,
8580
+ "step": 26150
8581
+ },
8582
+ {
8583
+ "epoch": 147.88135593220338,
8584
+ "grad_norm": 1.4471898078918457,
8585
+ "learning_rate": 6.103515625e-08,
8586
+ "loss": 0.2265,
8587
+ "step": 26175
8588
+ },
8589
+ {
8590
+ "epoch": 148.0225988700565,
8591
+ "grad_norm": 1.982006549835205,
8592
+ "learning_rate": 6.103515625e-08,
8593
+ "loss": 0.2615,
8594
+ "step": 26200
8595
+ },
8596
+ {
8597
+ "epoch": 148.1638418079096,
8598
+ "grad_norm": 1.6246839761734009,
8599
+ "learning_rate": 6.103515625e-08,
8600
+ "loss": 0.2482,
8601
+ "step": 26225
8602
+ },
8603
+ {
8604
+ "epoch": 148.3050847457627,
8605
+ "grad_norm": 1.6307405233383179,
8606
+ "learning_rate": 6.103515625e-08,
8607
+ "loss": 0.2837,
8608
+ "step": 26250
8609
+ },
8610
+ {
8611
+ "epoch": 148.3050847457627,
8612
+ "eval_asd": 10.046845573962226,
8613
+ "eval_dice": 0.7918568407114337,
8614
+ "eval_hd95": 30.332257894684698,
8615
+ "eval_jaccard": 0.6977271203919192,
8616
+ "eval_loss": 0.35064437985420227,
8617
+ "eval_runtime": 5.0737,
8618
+ "eval_samples_per_second": 51.245,
8619
+ "eval_steps_per_second": 12.811,
8620
+ "step": 26250
8621
  }
8622
  ],
8623
  "logging_steps": 25,