Nadav commited on
Commit
3e640b7
·
1 Parent(s): 6c68d02

Training in progress, step 85000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ddeabb9ead685c5e5b416b4a981e11a787d94773db5c89384835f8ea6b2e1c4
3
  size 893439185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472cad01c0a9f1ea8aaf84bdb45dfc7c4e1c36ba4b8820b938132e82c0227a88
3
  size 893439185
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98dacb4579cc2ad8d273f8bac5c3977b66490dafa2ef002d312807df6670d4cd
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9bb790cd1ed6619be446085ee0ce0f578bbf0f5bde03c7c17fa7ab47347b58
3
  size 449471589
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79b99893c9b02fa371856f47a0ec288962436c435769873b9db7532898348d23
3
  size 15523
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4db40485e0cc2ae2c7d4666298527a0e5fe43aae4d4d36410c256797b9d7b2
3
  size 15523
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56e8d48d0939e6a173efa67076df748028040c8480b0133ac53f27544c88363a
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73dcc385f3727cd90553fcdf4bbe518206c0aac0c3e0ac90d3a37a051bed3f6
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71d5e106c9d23676ccfa26cba844ba11ee123c667bd6da5c807ecc94bb13e886
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d6681857d812c4003058a73db89e98a889fba488550009396931874d6b944fb
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 6.805035726437564,
5
- "global_step": 80000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -1606,11 +1606,111 @@
1606
  "eval_samples_per_second": 29.995,
1607
  "eval_steps_per_second": 0.96,
1608
  "step": 80000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1609
  }
1610
  ],
1611
  "max_steps": 1000000,
1612
  "num_train_epochs": 86,
1613
- "total_flos": 3.680166814926219e+21,
1614
  "trial_name": null,
1615
  "trial_params": null
1616
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 7.2303504593399115,
5
+ "global_step": 85000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
1606
  "eval_samples_per_second": 29.995,
1607
  "eval_steps_per_second": 0.96,
1608
  "step": 80000
1609
+ },
1610
+ {
1611
+ "epoch": 6.85,
1612
+ "learning_rate": 9.999999999999999e-06,
1613
+ "loss": 0.4036,
1614
+ "step": 80500
1615
+ },
1616
+ {
1617
+ "epoch": 6.89,
1618
+ "learning_rate": 9.999999999999999e-06,
1619
+ "loss": 0.4035,
1620
+ "step": 81000
1621
+ },
1622
+ {
1623
+ "epoch": 6.89,
1624
+ "eval_loss": 0.3746860921382904,
1625
+ "eval_runtime": 15.7109,
1626
+ "eval_samples_per_second": 31.825,
1627
+ "eval_steps_per_second": 1.018,
1628
+ "step": 81000
1629
+ },
1630
+ {
1631
+ "epoch": 6.93,
1632
+ "learning_rate": 9.999999999999999e-06,
1633
+ "loss": 0.4037,
1634
+ "step": 81500
1635
+ },
1636
+ {
1637
+ "epoch": 6.98,
1638
+ "learning_rate": 9.999999999999999e-06,
1639
+ "loss": 0.4045,
1640
+ "step": 82000
1641
+ },
1642
+ {
1643
+ "epoch": 6.98,
1644
+ "eval_loss": 0.37363681197166443,
1645
+ "eval_runtime": 22.9088,
1646
+ "eval_samples_per_second": 21.826,
1647
+ "eval_steps_per_second": 0.698,
1648
+ "step": 82000
1649
+ },
1650
+ {
1651
+ "epoch": 7.02,
1652
+ "learning_rate": 9.999999999999999e-06,
1653
+ "loss": 0.4035,
1654
+ "step": 82500
1655
+ },
1656
+ {
1657
+ "epoch": 7.06,
1658
+ "learning_rate": 9.999999999999999e-06,
1659
+ "loss": 0.4031,
1660
+ "step": 83000
1661
+ },
1662
+ {
1663
+ "epoch": 7.06,
1664
+ "eval_loss": 0.37529370188713074,
1665
+ "eval_runtime": 14.7314,
1666
+ "eval_samples_per_second": 33.941,
1667
+ "eval_steps_per_second": 1.086,
1668
+ "step": 83000
1669
+ },
1670
+ {
1671
+ "epoch": 7.1,
1672
+ "learning_rate": 9.999999999999999e-06,
1673
+ "loss": 0.402,
1674
+ "step": 83500
1675
+ },
1676
+ {
1677
+ "epoch": 7.15,
1678
+ "learning_rate": 9.999999999999999e-06,
1679
+ "loss": 0.4042,
1680
+ "step": 84000
1681
+ },
1682
+ {
1683
+ "epoch": 7.15,
1684
+ "eval_loss": 0.37475818395614624,
1685
+ "eval_runtime": 15.8331,
1686
+ "eval_samples_per_second": 31.579,
1687
+ "eval_steps_per_second": 1.011,
1688
+ "step": 84000
1689
+ },
1690
+ {
1691
+ "epoch": 7.19,
1692
+ "learning_rate": 9.999999999999999e-06,
1693
+ "loss": 0.4032,
1694
+ "step": 84500
1695
+ },
1696
+ {
1697
+ "epoch": 7.23,
1698
+ "learning_rate": 9.999999999999999e-06,
1699
+ "loss": 0.4029,
1700
+ "step": 85000
1701
+ },
1702
+ {
1703
+ "epoch": 7.23,
1704
+ "eval_loss": 0.3748987317085266,
1705
+ "eval_runtime": 17.2956,
1706
+ "eval_samples_per_second": 28.909,
1707
+ "eval_steps_per_second": 0.925,
1708
+ "step": 85000
1709
  }
1710
  ],
1711
  "max_steps": 1000000,
1712
  "num_train_epochs": 86,
1713
+ "total_flos": 3.9101671434092717e+21,
1714
  "trial_name": null,
1715
  "trial_params": null
1716
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98dacb4579cc2ad8d273f8bac5c3977b66490dafa2ef002d312807df6670d4cd
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9bb790cd1ed6619be446085ee0ce0f578bbf0f5bde03c7c17fa7ab47347b58
3
  size 449471589