aee4 commited on
Commit
175960d
·
verified ·
1 Parent(s): ff86e2c

Training in progress, step 5250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d024b900eb502b7dc875d6e8464f828b626e15764cc8a6e43961b2a114fdd1e1
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7323f45ff43cf356785cf9627f8712678b5d01b728329f915fd95cf369b72866
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ff8c30c0830cdc9ee6a05f0e3d1f60181021c4fe8f3a7df4b8e2b448069744d
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a6af2a7a7d255ce06fa071073bfa125bcc2012a236efbedf9c25a4cad7a436c
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a5c11622183d87222d1ac6c441b6bba34fdcd36747c102761fbee73401f8dd3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771529242bdb07b1cb665e7e57920e3e30f761a3d29ac1dacd1d5590d33d1212
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29a1d2f47383a399d7f2ff114d1b00076a3941fc1738f6e7a69d608ccee6c6e4
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e46fc3c904c9104b39e5e3ca12f6d474dd9364ac3f027b09eeb25e4ccfed4f
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 4750,
3
- "best_metric": 0.8153427180076909,
4
- "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-4750",
5
- "epoch": 23.696682464454977,
6
  "eval_steps": 250,
7
- "global_step": 5000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1668,6 +1668,89 @@
1668
  "eval_specificity": 0.9810948954183578,
1669
  "eval_steps_per_second": 26.452,
1670
  "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1671
  }
1672
  ],
1673
  "logging_steps": 25,
@@ -1682,7 +1765,7 @@
1682
  "early_stopping_threshold": 0.0
1683
  },
1684
  "attributes": {
1685
- "early_stopping_patience_counter": 1
1686
  }
1687
  },
1688
  "TrainerControl": {
 
1
  {
2
+ "best_global_step": 5250,
3
+ "best_metric": 0.8170367604268931,
4
+ "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-5250",
5
+ "epoch": 24.881516587677726,
6
  "eval_steps": 250,
7
+ "global_step": 5250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1668
  "eval_specificity": 0.9810948954183578,
1669
  "eval_steps_per_second": 26.452,
1670
  "step": 5000
1671
+ },
1672
+ {
1673
+ "epoch": 23.81516587677725,
1674
+ "grad_norm": 3.221370220184326,
1675
+ "learning_rate": 0.00018094786729857818,
1676
+ "loss": 0.3261,
1677
+ "step": 5025
1678
+ },
1679
+ {
1680
+ "epoch": 23.933649289099527,
1681
+ "grad_norm": 3.098498582839966,
1682
+ "learning_rate": 0.0001803554502369668,
1683
+ "loss": 0.3135,
1684
+ "step": 5050
1685
+ },
1686
+ {
1687
+ "epoch": 24.0521327014218,
1688
+ "grad_norm": 0.5403777360916138,
1689
+ "learning_rate": 0.00017976303317535541,
1690
+ "loss": 0.3064,
1691
+ "step": 5075
1692
+ },
1693
+ {
1694
+ "epoch": 24.170616113744074,
1695
+ "grad_norm": 17.22354507446289,
1696
+ "learning_rate": 0.00017917061611374407,
1697
+ "loss": 0.3279,
1698
+ "step": 5100
1699
+ },
1700
+ {
1701
+ "epoch": 24.28909952606635,
1702
+ "grad_norm": 0.8308712244033813,
1703
+ "learning_rate": 0.0001785781990521327,
1704
+ "loss": 0.3275,
1705
+ "step": 5125
1706
+ },
1707
+ {
1708
+ "epoch": 24.407582938388625,
1709
+ "grad_norm": 1.2310388088226318,
1710
+ "learning_rate": 0.0001779857819905213,
1711
+ "loss": 0.2319,
1712
+ "step": 5150
1713
+ },
1714
+ {
1715
+ "epoch": 24.5260663507109,
1716
+ "grad_norm": 1.4885170459747314,
1717
+ "learning_rate": 0.00017739336492890995,
1718
+ "loss": 0.2883,
1719
+ "step": 5175
1720
+ },
1721
+ {
1722
+ "epoch": 24.644549763033176,
1723
+ "grad_norm": 1.2367713451385498,
1724
+ "learning_rate": 0.00017680094786729855,
1725
+ "loss": 0.3569,
1726
+ "step": 5200
1727
+ },
1728
+ {
1729
+ "epoch": 24.76303317535545,
1730
+ "grad_norm": 1.162682294845581,
1731
+ "learning_rate": 0.00017620853080568718,
1732
+ "loss": 0.3139,
1733
+ "step": 5225
1734
+ },
1735
+ {
1736
+ "epoch": 24.881516587677726,
1737
+ "grad_norm": 6.823002338409424,
1738
+ "learning_rate": 0.00017561611374407584,
1739
+ "loss": 0.3007,
1740
+ "step": 5250
1741
+ },
1742
+ {
1743
+ "epoch": 24.881516587677726,
1744
+ "eval_dice": 0.8170367604268931,
1745
+ "eval_iou": 0.7314210943879321,
1746
+ "eval_loss": 0.31642186641693115,
1747
+ "eval_precision": 0.8368024358349674,
1748
+ "eval_recall": 0.8498774823292035,
1749
+ "eval_runtime": 3.9744,
1750
+ "eval_samples_per_second": 105.676,
1751
+ "eval_specificity": 0.9833768002184645,
1752
+ "eval_steps_per_second": 26.419,
1753
+ "step": 5250
1754
  }
1755
  ],
1756
  "logging_steps": 25,
 
1765
  "early_stopping_threshold": 0.0
1766
  },
1767
  "attributes": {
1768
+ "early_stopping_patience_counter": 0
1769
  }
1770
  },
1771
  "TrainerControl": {