aee4 commited on
Commit
ad87a85
·
verified ·
1 Parent(s): 0d88e48

Training in progress, step 5500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7323f45ff43cf356785cf9627f8712678b5d01b728329f915fd95cf369b72866
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c0fdbd6717bf7dbad9274d0c6deeb40ebddec7d4147fb72d5709a18eff92b3
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a6af2a7a7d255ce06fa071073bfa125bcc2012a236efbedf9c25a4cad7a436c
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc29d47560ff0059a3e5a75c554f21edf2cb792aaa8c28939230ed97da615d5d
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:771529242bdb07b1cb665e7e57920e3e30f761a3d29ac1dacd1d5590d33d1212
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66e48699b199955664d97c152eda4d498658e8c242bfacea1b8e34bd9e4220b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8e46fc3c904c9104b39e5e3ca12f6d474dd9364ac3f027b09eeb25e4ccfed4f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a9a3e504dfa9cccf0a4a1c3859a599158e0a975f613d034dfa1401733bd56fa
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
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,
@@ -1751,6 +1751,89 @@
1751
  "eval_specificity": 0.9833768002184645,
1752
  "eval_steps_per_second": 26.419,
1753
  "step": 5250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1754
  }
1755
  ],
1756
  "logging_steps": 25,
@@ -1765,7 +1848,7 @@
1765
  "early_stopping_threshold": 0.0
1766
  },
1767
  "attributes": {
1768
- "early_stopping_patience_counter": 0
1769
  }
1770
  },
1771
  "TrainerControl": {
 
2
  "best_global_step": 5250,
3
  "best_metric": 0.8170367604268931,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-5250",
5
+ "epoch": 26.066350710900473,
6
  "eval_steps": 250,
7
+ "global_step": 5500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1751
  "eval_specificity": 0.9833768002184645,
1752
  "eval_steps_per_second": 26.419,
1753
  "step": 5250
1754
+ },
1755
+ {
1756
+ "epoch": 25.0,
1757
+ "grad_norm": 1.2732200622558594,
1758
+ "learning_rate": 0.00017502369668246444,
1759
+ "loss": 0.3074,
1760
+ "step": 5275
1761
+ },
1762
+ {
1763
+ "epoch": 25.118483412322274,
1764
+ "grad_norm": 2.8807833194732666,
1765
+ "learning_rate": 0.00017443127962085307,
1766
+ "loss": 0.3222,
1767
+ "step": 5300
1768
+ },
1769
+ {
1770
+ "epoch": 25.23696682464455,
1771
+ "grad_norm": 2.276731252670288,
1772
+ "learning_rate": 0.00017383886255924167,
1773
+ "loss": 0.3098,
1774
+ "step": 5325
1775
+ },
1776
+ {
1777
+ "epoch": 25.355450236966824,
1778
+ "grad_norm": 1.050060749053955,
1779
+ "learning_rate": 0.00017324644549763032,
1780
+ "loss": 0.3092,
1781
+ "step": 5350
1782
+ },
1783
+ {
1784
+ "epoch": 25.4739336492891,
1785
+ "grad_norm": 1.1748206615447998,
1786
+ "learning_rate": 0.00017265402843601895,
1787
+ "loss": 0.3106,
1788
+ "step": 5375
1789
+ },
1790
+ {
1791
+ "epoch": 25.592417061611375,
1792
+ "grad_norm": 2.645148754119873,
1793
+ "learning_rate": 0.00017206161137440755,
1794
+ "loss": 0.2969,
1795
+ "step": 5400
1796
+ },
1797
+ {
1798
+ "epoch": 25.71090047393365,
1799
+ "grad_norm": 2.3750476837158203,
1800
+ "learning_rate": 0.0001714691943127962,
1801
+ "loss": 0.3196,
1802
+ "step": 5425
1803
+ },
1804
+ {
1805
+ "epoch": 25.829383886255926,
1806
+ "grad_norm": 2.618100166320801,
1807
+ "learning_rate": 0.0001708767772511848,
1808
+ "loss": 0.2565,
1809
+ "step": 5450
1810
+ },
1811
+ {
1812
+ "epoch": 25.9478672985782,
1813
+ "grad_norm": 4.953620910644531,
1814
+ "learning_rate": 0.00017028436018957344,
1815
+ "loss": 0.3091,
1816
+ "step": 5475
1817
+ },
1818
+ {
1819
+ "epoch": 26.066350710900473,
1820
+ "grad_norm": 11.964319229125977,
1821
+ "learning_rate": 0.0001696919431279621,
1822
+ "loss": 0.3147,
1823
+ "step": 5500
1824
+ },
1825
+ {
1826
+ "epoch": 26.066350710900473,
1827
+ "eval_dice": 0.8163914954138223,
1828
+ "eval_iou": 0.7295507337663005,
1829
+ "eval_loss": 0.31315475702285767,
1830
+ "eval_precision": 0.8429735780254375,
1831
+ "eval_recall": 0.8377491769214714,
1832
+ "eval_runtime": 4.0706,
1833
+ "eval_samples_per_second": 103.179,
1834
+ "eval_specificity": 0.9866618177517321,
1835
+ "eval_steps_per_second": 25.795,
1836
+ "step": 5500
1837
  }
1838
  ],
1839
  "logging_steps": 25,
 
1848
  "early_stopping_threshold": 0.0
1849
  },
1850
  "attributes": {
1851
+ "early_stopping_patience_counter": 1
1852
  }
1853
  },
1854
  "TrainerControl": {