aee4 commited on
Commit
f1ef109
·
verified ·
1 Parent(s): f12e177

Training in progress, step 26500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3e6914ff34e2c37a902a8e27c913bad86310f11a886aa152ef32cafb8b8e2d6
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f6ec8a5bda1be88427a62fe74a6d496019a6218d4eb1e4f4a0ea20c7c0f5a6
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9249bc48e2b9137137bdc43dfb3dfed1b12e6f28de5a1f99f5b0aa5e3bdc7eb5
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aede1b65ada6f785ae2d931b378919643fc0b7b618462f051e7e79bba5bfc226
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:d83da7d3ddea445ede9f960a7e389d8b0bd2e1fc4596e4e0241ad4877d08952c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab4da90bdbaeecd3714bd9af7478458acb26bee1a399b28d9829deae167173d
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d80b1c7aca49008ea603c6dae7f034292ad375dd4c090f11cfd3b8da55232e72
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bd74a1ebc272cbefcf7394a7b79d8afa5be307b470a67c479fe9c8690d21115
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": 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,
@@ -8618,6 +8618,88 @@
8618
  "eval_samples_per_second": 51.245,
8619
  "eval_steps_per_second": 12.811,
8620
  "step": 26250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8621
  }
8622
  ],
8623
  "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": 149.71751412429379,
6
  "eval_steps": 250,
7
+ "global_step": 26500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
8618
  "eval_samples_per_second": 51.245,
8619
  "eval_steps_per_second": 12.811,
8620
  "step": 26250
8621
+ },
8622
+ {
8623
+ "epoch": 148.4463276836158,
8624
+ "grad_norm": 2.058320999145508,
8625
+ "learning_rate": 6.103515625e-08,
8626
+ "loss": 0.2468,
8627
+ "step": 26275
8628
+ },
8629
+ {
8630
+ "epoch": 148.58757062146893,
8631
+ "grad_norm": 2.8546700477600098,
8632
+ "learning_rate": 6.103515625e-08,
8633
+ "loss": 0.2424,
8634
+ "step": 26300
8635
+ },
8636
+ {
8637
+ "epoch": 148.72881355932202,
8638
+ "grad_norm": 2.4922406673431396,
8639
+ "learning_rate": 6.103515625e-08,
8640
+ "loss": 0.2968,
8641
+ "step": 26325
8642
+ },
8643
+ {
8644
+ "epoch": 148.87005649717514,
8645
+ "grad_norm": 2.245364189147949,
8646
+ "learning_rate": 6.103515625e-08,
8647
+ "loss": 0.2491,
8648
+ "step": 26350
8649
+ },
8650
+ {
8651
+ "epoch": 149.01129943502823,
8652
+ "grad_norm": 1.9189472198486328,
8653
+ "learning_rate": 6.103515625e-08,
8654
+ "loss": 0.2661,
8655
+ "step": 26375
8656
+ },
8657
+ {
8658
+ "epoch": 149.15254237288136,
8659
+ "grad_norm": 1.3316715955734253,
8660
+ "learning_rate": 6.103515625e-08,
8661
+ "loss": 0.2599,
8662
+ "step": 26400
8663
+ },
8664
+ {
8665
+ "epoch": 149.29378531073445,
8666
+ "grad_norm": 1.9115773439407349,
8667
+ "learning_rate": 6.103515625e-08,
8668
+ "loss": 0.2704,
8669
+ "step": 26425
8670
+ },
8671
+ {
8672
+ "epoch": 149.43502824858757,
8673
+ "grad_norm": 1.132863998413086,
8674
+ "learning_rate": 6.103515625e-08,
8675
+ "loss": 0.2607,
8676
+ "step": 26450
8677
+ },
8678
+ {
8679
+ "epoch": 149.57627118644066,
8680
+ "grad_norm": 1.9513949155807495,
8681
+ "learning_rate": 6.103515625e-08,
8682
+ "loss": 0.2491,
8683
+ "step": 26475
8684
+ },
8685
+ {
8686
+ "epoch": 149.71751412429379,
8687
+ "grad_norm": 0.8847301602363586,
8688
+ "learning_rate": 6.103515625e-08,
8689
+ "loss": 0.2669,
8690
+ "step": 26500
8691
+ },
8692
+ {
8693
+ "epoch": 149.71751412429379,
8694
+ "eval_asd": 9.799609928630428,
8695
+ "eval_dice": 0.7912810863809179,
8696
+ "eval_hd95": 29.836209593963627,
8697
+ "eval_jaccard": 0.6976270906442142,
8698
+ "eval_loss": 0.3478092849254608,
8699
+ "eval_runtime": 5.0586,
8700
+ "eval_samples_per_second": 51.397,
8701
+ "eval_steps_per_second": 12.849,
8702
+ "step": 26500
8703
  }
8704
  ],
8705
  "logging_steps": 25,