aee4 commited on
Commit
0444508
·
verified ·
1 Parent(s): 33990ba

Training in progress, step 11250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71ce19a78f58d884c93646478c6ecbc9cb44b7ff32863c4297c9fc81f4841635
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a641b7a9a54cb12d74f0d8c71d894f1ea406e346b81e127082a22fc580bbf89
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e946315d05268fc209bc43a49a84fe72fcd9114b5a0d3db4af420bdea7d396e9
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48214d1d06d5a4bfc33e66b0cffcab2b32738eb1dd1f6855c9ee5f5a2c008b77
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0591be5ab3c49004fb98678aba40d71597cb334b693aa1f9cf1270d955ae5462
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d83c3ee3c8e95e538ce7ad3336285b6895c62c33531f37b7797db24b42b5d5
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaece653e746cfa39f08eb4e0fb1883bc31a20cd4b6538cfa517136f09252df9
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c2593722988f7d3ea4df0e991519179efa8c03b45e0a2b8c7b092182b69cf0
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 10000,
3
  "best_metric": 0.8396956422654931,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-10000",
5
- "epoch": 52.132701421800945,
6
  "eval_steps": 250,
7
- "global_step": 11000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3660,6 +3660,89 @@
3660
  "eval_specificity": 0.9870270361022998,
3661
  "eval_steps_per_second": 26.311,
3662
  "step": 11000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3663
  }
3664
  ],
3665
  "logging_steps": 25,
@@ -3674,7 +3757,7 @@
3674
  "early_stopping_threshold": 0.0
3675
  },
3676
  "attributes": {
3677
- "early_stopping_patience_counter": 4
3678
  }
3679
  },
3680
  "TrainerControl": {
 
2
  "best_global_step": 10000,
3
  "best_metric": 0.8396956422654931,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-10000",
5
+ "epoch": 53.317535545023695,
6
  "eval_steps": 250,
7
+ "global_step": 11250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3660
  "eval_specificity": 0.9870270361022998,
3661
  "eval_steps_per_second": 26.311,
3662
  "step": 11000
3663
+ },
3664
+ {
3665
+ "epoch": 52.25118483412322,
3666
+ "grad_norm": 2.281587600708008,
3667
+ "learning_rate": 3.876777251184834e-05,
3668
+ "loss": 0.2345,
3669
+ "step": 11025
3670
+ },
3671
+ {
3672
+ "epoch": 52.3696682464455,
3673
+ "grad_norm": 1.6069631576538086,
3674
+ "learning_rate": 3.8175355450236966e-05,
3675
+ "loss": 0.2061,
3676
+ "step": 11050
3677
+ },
3678
+ {
3679
+ "epoch": 52.48815165876777,
3680
+ "grad_norm": 1.074258804321289,
3681
+ "learning_rate": 3.758293838862559e-05,
3682
+ "loss": 0.2242,
3683
+ "step": 11075
3684
+ },
3685
+ {
3686
+ "epoch": 52.60663507109005,
3687
+ "grad_norm": 4.207392692565918,
3688
+ "learning_rate": 3.6990521327014215e-05,
3689
+ "loss": 0.2245,
3690
+ "step": 11100
3691
+ },
3692
+ {
3693
+ "epoch": 52.725118483412324,
3694
+ "grad_norm": 1.9550474882125854,
3695
+ "learning_rate": 3.639810426540284e-05,
3696
+ "loss": 0.2412,
3697
+ "step": 11125
3698
+ },
3699
+ {
3700
+ "epoch": 52.843601895734594,
3701
+ "grad_norm": 0.8042076230049133,
3702
+ "learning_rate": 3.580568720379147e-05,
3703
+ "loss": 0.2266,
3704
+ "step": 11150
3705
+ },
3706
+ {
3707
+ "epoch": 52.96208530805687,
3708
+ "grad_norm": 0.9020439982414246,
3709
+ "learning_rate": 3.521327014218009e-05,
3710
+ "loss": 0.213,
3711
+ "step": 11175
3712
+ },
3713
+ {
3714
+ "epoch": 53.08056872037915,
3715
+ "grad_norm": 0.7768784761428833,
3716
+ "learning_rate": 3.4620853080568714e-05,
3717
+ "loss": 0.2275,
3718
+ "step": 11200
3719
+ },
3720
+ {
3721
+ "epoch": 53.199052132701425,
3722
+ "grad_norm": 1.9058053493499756,
3723
+ "learning_rate": 3.402843601895734e-05,
3724
+ "loss": 0.2189,
3725
+ "step": 11225
3726
+ },
3727
+ {
3728
+ "epoch": 53.317535545023695,
3729
+ "grad_norm": 0.5731157064437866,
3730
+ "learning_rate": 3.343601895734597e-05,
3731
+ "loss": 0.2108,
3732
+ "step": 11250
3733
+ },
3734
+ {
3735
+ "epoch": 53.317535545023695,
3736
+ "eval_dice": 0.8365840088238069,
3737
+ "eval_iou": 0.756966532800309,
3738
+ "eval_loss": 0.2835087776184082,
3739
+ "eval_precision": 0.866212605283929,
3740
+ "eval_recall": 0.8499078436050802,
3741
+ "eval_runtime": 3.9951,
3742
+ "eval_samples_per_second": 105.127,
3743
+ "eval_specificity": 0.9873055267108327,
3744
+ "eval_steps_per_second": 26.282,
3745
+ "step": 11250
3746
  }
3747
  ],
3748
  "logging_steps": 25,
 
3757
  "early_stopping_threshold": 0.0
3758
  },
3759
  "attributes": {
3760
+ "early_stopping_patience_counter": 5
3761
  }
3762
  },
3763
  "TrainerControl": {