aee4 commited on
Commit
7a81527
·
verified ·
1 Parent(s): 06cd979

Training in progress, step 26750, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8f6ec8a5bda1be88427a62fe74a6d496019a6218d4eb1e4f4a0ea20c7c0f5a6
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43bbf61c3e793f4ed9e2f675c2c59b01da88e155522a6e2096f9163dd148192e
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aede1b65ada6f785ae2d931b378919643fc0b7b618462f051e7e79bba5bfc226
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21468615aa437321441c9eb7bdf20990e74a01b44c6b98af2947e8f982e18e16
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ab4da90bdbaeecd3714bd9af7478458acb26bee1a399b28d9829deae167173d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:565b96c93e2c912750f612ea89d5f3e792e10e8ce187402e6ca2e983bbe4afe0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bd74a1ebc272cbefcf7394a7b79d8afa5be307b470a67c479fe9c8690d21115
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3ea3d3ff6643dab19278f76e31a57ef288173c81c6345ec1a31145e9355fbb6
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": 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,
@@ -8700,6 +8700,88 @@
8700
  "eval_samples_per_second": 51.397,
8701
  "eval_steps_per_second": 12.849,
8702
  "step": 26500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8703
  }
8704
  ],
8705
  "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": 151.12994350282486,
6
  "eval_steps": 250,
7
+ "global_step": 26750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
8700
  "eval_samples_per_second": 51.397,
8701
  "eval_steps_per_second": 12.849,
8702
  "step": 26500
8703
+ },
8704
+ {
8705
+ "epoch": 149.85875706214688,
8706
+ "grad_norm": 3.111588716506958,
8707
+ "learning_rate": 6.103515625e-08,
8708
+ "loss": 0.2487,
8709
+ "step": 26525
8710
+ },
8711
+ {
8712
+ "epoch": 150.0,
8713
+ "grad_norm": 1.7114454507827759,
8714
+ "learning_rate": 6.103515625e-08,
8715
+ "loss": 0.2449,
8716
+ "step": 26550
8717
+ },
8718
+ {
8719
+ "epoch": 150.14124293785312,
8720
+ "grad_norm": 1.8885021209716797,
8721
+ "learning_rate": 3.0517578125e-08,
8722
+ "loss": 0.2732,
8723
+ "step": 26575
8724
+ },
8725
+ {
8726
+ "epoch": 150.28248587570621,
8727
+ "grad_norm": 2.4494621753692627,
8728
+ "learning_rate": 3.0517578125e-08,
8729
+ "loss": 0.2499,
8730
+ "step": 26600
8731
+ },
8732
+ {
8733
+ "epoch": 150.42372881355934,
8734
+ "grad_norm": 2.8559539318084717,
8735
+ "learning_rate": 3.0517578125e-08,
8736
+ "loss": 0.2463,
8737
+ "step": 26625
8738
+ },
8739
+ {
8740
+ "epoch": 150.56497175141243,
8741
+ "grad_norm": 1.411656379699707,
8742
+ "learning_rate": 3.0517578125e-08,
8743
+ "loss": 0.2766,
8744
+ "step": 26650
8745
+ },
8746
+ {
8747
+ "epoch": 150.70621468926555,
8748
+ "grad_norm": 1.010740041732788,
8749
+ "learning_rate": 3.0517578125e-08,
8750
+ "loss": 0.2659,
8751
+ "step": 26675
8752
+ },
8753
+ {
8754
+ "epoch": 150.84745762711864,
8755
+ "grad_norm": 1.6802780628204346,
8756
+ "learning_rate": 3.0517578125e-08,
8757
+ "loss": 0.2438,
8758
+ "step": 26700
8759
+ },
8760
+ {
8761
+ "epoch": 150.98870056497177,
8762
+ "grad_norm": 1.5252970457077026,
8763
+ "learning_rate": 3.0517578125e-08,
8764
+ "loss": 0.2545,
8765
+ "step": 26725
8766
+ },
8767
+ {
8768
+ "epoch": 151.12994350282486,
8769
+ "grad_norm": 1.7808886766433716,
8770
+ "learning_rate": 3.0517578125e-08,
8771
+ "loss": 0.2389,
8772
+ "step": 26750
8773
+ },
8774
+ {
8775
+ "epoch": 151.12994350282486,
8776
+ "eval_asd": 10.155359979705905,
8777
+ "eval_dice": 0.7905615908117771,
8778
+ "eval_hd95": 30.977760141566918,
8779
+ "eval_jaccard": 0.6964458232464696,
8780
+ "eval_loss": 0.3477163016796112,
8781
+ "eval_runtime": 5.1102,
8782
+ "eval_samples_per_second": 50.879,
8783
+ "eval_steps_per_second": 12.72,
8784
+ "step": 26750
8785
  }
8786
  ],
8787
  "logging_steps": 25,