aee4 commited on
Commit
405b237
·
verified ·
1 Parent(s): 0622125

Training in progress, step 5000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:944985c3b71e3b966d0d66130fb04814ae739ca0f4b0a9fd0c0e44b3fed90ae8
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d024b900eb502b7dc875d6e8464f828b626e15764cc8a6e43961b2a114fdd1e1
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2133f4c09ab73ff7e90f6c40bd95fc340766be776290e4ab3b3a255f0266a9f4
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff8c30c0830cdc9ee6a05f0e3d1f60181021c4fe8f3a7df4b8e2b448069744d
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:495527095ce64d42859bf28983716fbe3891476c1dd8d77f6b07b794fa6428e3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a5c11622183d87222d1ac6c441b6bba34fdcd36747c102761fbee73401f8dd3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4baece4e05e2bb2c080ed1776b5253130e3becf66a6e387f46f1e0da555c380
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a1d2f47383a399d7f2ff114d1b00076a3941fc1738f6e7a69d608ccee6c6e4
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 4750,
3
  "best_metric": 0.8153427180076909,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-4750",
5
- "epoch": 22.511848341232227,
6
  "eval_steps": 250,
7
- "global_step": 4750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1585,6 +1585,89 @@
1585
  "eval_specificity": 0.9882985359723886,
1586
  "eval_steps_per_second": 26.335,
1587
  "step": 4750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1588
  }
1589
  ],
1590
  "logging_steps": 25,
@@ -1599,7 +1682,7 @@
1599
  "early_stopping_threshold": 0.0
1600
  },
1601
  "attributes": {
1602
- "early_stopping_patience_counter": 0
1603
  }
1604
  },
1605
  "TrainerControl": {
 
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,
 
1585
  "eval_specificity": 0.9882985359723886,
1586
  "eval_steps_per_second": 26.335,
1587
  "step": 4750
1588
+ },
1589
+ {
1590
+ "epoch": 22.6303317535545,
1591
+ "grad_norm": 1.115892767906189,
1592
+ "learning_rate": 0.00018687203791469193,
1593
+ "loss": 0.2746,
1594
+ "step": 4775
1595
+ },
1596
+ {
1597
+ "epoch": 22.748815165876778,
1598
+ "grad_norm": 0.7727171778678894,
1599
+ "learning_rate": 0.00018627962085308056,
1600
+ "loss": 0.298,
1601
+ "step": 4800
1602
+ },
1603
+ {
1604
+ "epoch": 22.86729857819905,
1605
+ "grad_norm": 1.0133423805236816,
1606
+ "learning_rate": 0.00018568720379146916,
1607
+ "loss": 0.389,
1608
+ "step": 4825
1609
+ },
1610
+ {
1611
+ "epoch": 22.98578199052133,
1612
+ "grad_norm": 2.0958476066589355,
1613
+ "learning_rate": 0.00018509478672985781,
1614
+ "loss": 0.291,
1615
+ "step": 4850
1616
+ },
1617
+ {
1618
+ "epoch": 23.104265402843602,
1619
+ "grad_norm": 17.69247055053711,
1620
+ "learning_rate": 0.00018450236966824644,
1621
+ "loss": 0.2942,
1622
+ "step": 4875
1623
+ },
1624
+ {
1625
+ "epoch": 23.222748815165875,
1626
+ "grad_norm": 3.90667462348938,
1627
+ "learning_rate": 0.00018390995260663504,
1628
+ "loss": 0.3147,
1629
+ "step": 4900
1630
+ },
1631
+ {
1632
+ "epoch": 23.341232227488153,
1633
+ "grad_norm": 4.599174499511719,
1634
+ "learning_rate": 0.0001833175355450237,
1635
+ "loss": 0.3021,
1636
+ "step": 4925
1637
+ },
1638
+ {
1639
+ "epoch": 23.459715639810426,
1640
+ "grad_norm": 2.054778814315796,
1641
+ "learning_rate": 0.0001827251184834123,
1642
+ "loss": 0.2984,
1643
+ "step": 4950
1644
+ },
1645
+ {
1646
+ "epoch": 23.578199052132703,
1647
+ "grad_norm": 3.750981569290161,
1648
+ "learning_rate": 0.00018213270142180093,
1649
+ "loss": 0.2788,
1650
+ "step": 4975
1651
+ },
1652
+ {
1653
+ "epoch": 23.696682464454977,
1654
+ "grad_norm": 2.0988166332244873,
1655
+ "learning_rate": 0.00018154028436018956,
1656
+ "loss": 0.3256,
1657
+ "step": 5000
1658
+ },
1659
+ {
1660
+ "epoch": 23.696682464454977,
1661
+ "eval_dice": 0.813922998537341,
1662
+ "eval_iou": 0.7242266351140833,
1663
+ "eval_loss": 0.32353562116622925,
1664
+ "eval_precision": 0.8041277635735704,
1665
+ "eval_recall": 0.8715908318851824,
1666
+ "eval_runtime": 3.9695,
1667
+ "eval_samples_per_second": 105.807,
1668
+ "eval_specificity": 0.9810948954183578,
1669
+ "eval_steps_per_second": 26.452,
1670
+ "step": 5000
1671
  }
1672
  ],
1673
  "logging_steps": 25,
 
1682
  "early_stopping_threshold": 0.0
1683
  },
1684
  "attributes": {
1685
+ "early_stopping_patience_counter": 1
1686
  }
1687
  },
1688
  "TrainerControl": {