aee4 commited on
Commit
89db4de
·
verified ·
1 Parent(s): 672b4df

Training in progress, step 4750, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a751c3cc0a7f58e3f4fc3d2ee42631d2fb5004351623e060d28d580726ff6f6
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944985c3b71e3b966d0d66130fb04814ae739ca0f4b0a9fd0c0e44b3fed90ae8
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7cacb770fdb93d494b02e007140b259bf1b0382e77a5486337d5c041a42b809
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2133f4c09ab73ff7e90f6c40bd95fc340766be776290e4ab3b3a255f0266a9f4
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50dd579ef1d2d932c3d7726ef0f6ec72d0e25b023ae2fd8b67112ac75e1041b9
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495527095ce64d42859bf28983716fbe3891476c1dd8d77f6b07b794fa6428e3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cd033f826b365cf29330cc7ea586055479d07ab26ca8ab63bb5ef3f22b0f394
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4baece4e05e2bb2c080ed1776b5253130e3becf66a6e387f46f1e0da555c380
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 4000,
3
- "best_metric": 0.8133356678481004,
4
- "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-4000",
5
- "epoch": 21.327014218009477,
6
  "eval_steps": 250,
7
- "global_step": 4500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1502,6 +1502,89 @@
1502
  "eval_specificity": 0.9921307390670687,
1503
  "eval_steps_per_second": 26.206,
1504
  "step": 4500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1505
  }
1506
  ],
1507
  "logging_steps": 25,
@@ -1516,7 +1599,7 @@
1516
  "early_stopping_threshold": 0.0
1517
  },
1518
  "attributes": {
1519
- "early_stopping_patience_counter": 2
1520
  }
1521
  },
1522
  "TrainerControl": {
 
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": 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,
 
1502
  "eval_specificity": 0.9921307390670687,
1503
  "eval_steps_per_second": 26.206,
1504
  "step": 4500
1505
+ },
1506
+ {
1507
+ "epoch": 21.445497630331754,
1508
+ "grad_norm": 2.472405195236206,
1509
+ "learning_rate": 0.00019279620853080568,
1510
+ "loss": 0.2955,
1511
+ "step": 4525
1512
+ },
1513
+ {
1514
+ "epoch": 21.563981042654028,
1515
+ "grad_norm": 1.8272291421890259,
1516
+ "learning_rate": 0.0001922037914691943,
1517
+ "loss": 0.2996,
1518
+ "step": 4550
1519
+ },
1520
+ {
1521
+ "epoch": 21.682464454976305,
1522
+ "grad_norm": 1.9406638145446777,
1523
+ "learning_rate": 0.0001916113744075829,
1524
+ "loss": 0.3282,
1525
+ "step": 4575
1526
+ },
1527
+ {
1528
+ "epoch": 21.80094786729858,
1529
+ "grad_norm": 2.1419270038604736,
1530
+ "learning_rate": 0.00019101895734597153,
1531
+ "loss": 0.2759,
1532
+ "step": 4600
1533
+ },
1534
+ {
1535
+ "epoch": 21.919431279620852,
1536
+ "grad_norm": 1.2849805355072021,
1537
+ "learning_rate": 0.0001904265402843602,
1538
+ "loss": 0.2996,
1539
+ "step": 4625
1540
+ },
1541
+ {
1542
+ "epoch": 22.03791469194313,
1543
+ "grad_norm": 2.132885456085205,
1544
+ "learning_rate": 0.0001898341232227488,
1545
+ "loss": 0.3123,
1546
+ "step": 4650
1547
+ },
1548
+ {
1549
+ "epoch": 22.156398104265403,
1550
+ "grad_norm": 2.010129451751709,
1551
+ "learning_rate": 0.00018924170616113742,
1552
+ "loss": 0.3282,
1553
+ "step": 4675
1554
+ },
1555
+ {
1556
+ "epoch": 22.274881516587676,
1557
+ "grad_norm": 3.260033130645752,
1558
+ "learning_rate": 0.00018864928909952605,
1559
+ "loss": 0.3061,
1560
+ "step": 4700
1561
+ },
1562
+ {
1563
+ "epoch": 22.393364928909953,
1564
+ "grad_norm": 2.2977731227874756,
1565
+ "learning_rate": 0.00018805687203791467,
1566
+ "loss": 0.3108,
1567
+ "step": 4725
1568
+ },
1569
+ {
1570
+ "epoch": 22.511848341232227,
1571
+ "grad_norm": 9.876200675964355,
1572
+ "learning_rate": 0.0001874644549763033,
1573
+ "loss": 0.2496,
1574
+ "step": 4750
1575
+ },
1576
+ {
1577
+ "epoch": 22.511848341232227,
1578
+ "eval_dice": 0.8153427180076909,
1579
+ "eval_iou": 0.7304762053879992,
1580
+ "eval_loss": 0.3227435052394867,
1581
+ "eval_precision": 0.8555616175874826,
1582
+ "eval_recall": 0.8223609828975341,
1583
+ "eval_runtime": 3.9871,
1584
+ "eval_samples_per_second": 105.338,
1585
+ "eval_specificity": 0.9882985359723886,
1586
+ "eval_steps_per_second": 26.335,
1587
+ "step": 4750
1588
  }
1589
  ],
1590
  "logging_steps": 25,
 
1599
  "early_stopping_threshold": 0.0
1600
  },
1601
  "attributes": {
1602
+ "early_stopping_patience_counter": 0
1603
  }
1604
  },
1605
  "TrainerControl": {