aee4 commited on
Commit
76fc9b8
·
verified ·
1 Parent(s): df83514

Training in progress, step 2250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dc695bc7e06a188130c43df20cd69f55f527286242c7e31f6e150326c532bf0
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c21a2153ca2536f7f184f080fcb93b655ef15a2770d72f3e216fe138928e310
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bcc42f03b3d331f3fc008e58a2985ff35d71d86222ddcc3387f4583890c98c7
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9814fa0e34b0fcd2f75a427ad34a3d9f02f65ff7814f2a27bc9f0e593990e7
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9445552595536daf5bd8731be4eabb308bd26e76a3f4f0c20c4aa55fcf9ea202
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed3753ab7977739b8eda494dd72defae5750f7283141b11a8f562160ba4c1a23
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0330c8706523b766ef326ed4a6f8de06caf04f1a920b2766e16d88cfcd58addf
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aaaa87e94728981919310f585c21490b3b273e11e95d6808d2045d1da16d210
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 2000,
3
- "best_metric": 0.7854634956037094,
4
- "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-2000",
5
- "epoch": 9.47867298578199,
6
  "eval_steps": 250,
7
- "global_step": 2000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -672,6 +672,89 @@
672
  "eval_specificity": 0.9869023999827429,
673
  "eval_steps_per_second": 26.318,
674
  "step": 2000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
675
  }
676
  ],
677
  "logging_steps": 25,
 
1
  {
2
+ "best_global_step": 2250,
3
+ "best_metric": 0.7871868770789375,
4
+ "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-2250",
5
+ "epoch": 10.663507109004739,
6
  "eval_steps": 250,
7
+ "global_step": 2250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
672
  "eval_specificity": 0.9869023999827429,
673
  "eval_steps_per_second": 26.318,
674
  "step": 2000
675
+ },
676
+ {
677
+ "epoch": 9.597156398104266,
678
+ "grad_norm": 1.5289881229400635,
679
+ "learning_rate": 0.0002520379146919431,
680
+ "loss": 0.3731,
681
+ "step": 2025
682
+ },
683
+ {
684
+ "epoch": 9.71563981042654,
685
+ "grad_norm": 1.1199995279312134,
686
+ "learning_rate": 0.00025144549763033173,
687
+ "loss": 0.3517,
688
+ "step": 2050
689
+ },
690
+ {
691
+ "epoch": 9.834123222748815,
692
+ "grad_norm": 3.4922306537628174,
693
+ "learning_rate": 0.00025085308056872036,
694
+ "loss": 0.4081,
695
+ "step": 2075
696
+ },
697
+ {
698
+ "epoch": 9.95260663507109,
699
+ "grad_norm": 1.3827158212661743,
700
+ "learning_rate": 0.000250260663507109,
701
+ "loss": 0.3698,
702
+ "step": 2100
703
+ },
704
+ {
705
+ "epoch": 10.071090047393366,
706
+ "grad_norm": 1.1517351865768433,
707
+ "learning_rate": 0.0002496682464454976,
708
+ "loss": 0.4486,
709
+ "step": 2125
710
+ },
711
+ {
712
+ "epoch": 10.189573459715639,
713
+ "grad_norm": 0.9759774804115295,
714
+ "learning_rate": 0.00024907582938388625,
715
+ "loss": 0.374,
716
+ "step": 2150
717
+ },
718
+ {
719
+ "epoch": 10.308056872037914,
720
+ "grad_norm": 0.7033727765083313,
721
+ "learning_rate": 0.0002484834123222749,
722
+ "loss": 0.3686,
723
+ "step": 2175
724
+ },
725
+ {
726
+ "epoch": 10.42654028436019,
727
+ "grad_norm": 3.277723789215088,
728
+ "learning_rate": 0.00024789099526066345,
729
+ "loss": 0.3787,
730
+ "step": 2200
731
+ },
732
+ {
733
+ "epoch": 10.545023696682465,
734
+ "grad_norm": 5.341111660003662,
735
+ "learning_rate": 0.00024729857819905213,
736
+ "loss": 0.3529,
737
+ "step": 2225
738
+ },
739
+ {
740
+ "epoch": 10.663507109004739,
741
+ "grad_norm": 1.1771985292434692,
742
+ "learning_rate": 0.00024670616113744076,
743
+ "loss": 0.3208,
744
+ "step": 2250
745
+ },
746
+ {
747
+ "epoch": 10.663507109004739,
748
+ "eval_dice": 0.7871868770789375,
749
+ "eval_iou": 0.6950669575440851,
750
+ "eval_loss": 0.37345126271247864,
751
+ "eval_precision": 0.8321049954798452,
752
+ "eval_recall": 0.8071492722472687,
753
+ "eval_runtime": 3.9824,
754
+ "eval_samples_per_second": 105.464,
755
+ "eval_specificity": 0.9868751729738183,
756
+ "eval_steps_per_second": 26.366,
757
+ "step": 2250
758
  }
759
  ],
760
  "logging_steps": 25,