stefania-radu
commited on
Commit
•
4bf20bf
1
Parent(s):
4a8a79d
Training in progress, step 240000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893441530
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11144856c02c8e972a36fb5b42d4223035071c4a917ea79c06d582d2b9be6085
|
3 |
size 893441530
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ad81878847ff45e1880bc9e193537b6a982e87fb64a13bbf06eba84c2c3ee6f
|
3 |
size 454197066
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14180
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20be28e08eeb080e0d87de2c1d006e31a433ae3d529b46a69dfe770492fd995c
|
3 |
size 14180
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c781a803fdb01dba917962146262a56eb080213a823923503263cf460fa3ac80
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1708,11 +1708,85 @@
|
|
1708 |
"eval_samples_per_second": 106.178,
|
1709 |
"eval_steps_per_second": 13.272,
|
1710 |
"step": 230000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1711 |
}
|
1712 |
],
|
1713 |
"max_steps": 1000000,
|
1714 |
"num_train_epochs": 9223372036854775807,
|
1715 |
-
"total_flos": 2.
|
1716 |
"trial_name": null,
|
1717 |
"trial_params": null
|
1718 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.24,
|
5 |
+
"global_step": 240000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1708 |
"eval_samples_per_second": 106.178,
|
1709 |
"eval_steps_per_second": 13.272,
|
1710 |
"step": 230000
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.23,
|
1714 |
+
"learning_rate": 1.798940649585048e-05,
|
1715 |
+
"loss": 0.3703,
|
1716 |
+
"step": 231000
|
1717 |
+
},
|
1718 |
+
{
|
1719 |
+
"epoch": 0.23,
|
1720 |
+
"learning_rate": 1.7981234828858012e-05,
|
1721 |
+
"loss": 0.3696,
|
1722 |
+
"step": 232000
|
1723 |
+
},
|
1724 |
+
{
|
1725 |
+
"epoch": 0.23,
|
1726 |
+
"learning_rate": 1.7973023724659226e-05,
|
1727 |
+
"loss": 0.3696,
|
1728 |
+
"step": 233000
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 0.23,
|
1732 |
+
"learning_rate": 1.7964773273049443e-05,
|
1733 |
+
"loss": 0.3696,
|
1734 |
+
"step": 234000
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 0.23,
|
1738 |
+
"learning_rate": 1.795648356425428e-05,
|
1739 |
+
"loss": 0.3689,
|
1740 |
+
"step": 235000
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 0.23,
|
1744 |
+
"eval_runtime": 3392.6969,
|
1745 |
+
"eval_samples_per_second": 100.113,
|
1746 |
+
"eval_steps_per_second": 12.514,
|
1747 |
+
"step": 235000
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 0.24,
|
1751 |
+
"learning_rate": 1.7948154688928657e-05,
|
1752 |
+
"loss": 0.3691,
|
1753 |
+
"step": 236000
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 0.24,
|
1757 |
+
"learning_rate": 1.793978673815583e-05,
|
1758 |
+
"loss": 0.368,
|
1759 |
+
"step": 237000
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.24,
|
1763 |
+
"learning_rate": 1.7931379803446365e-05,
|
1764 |
+
"loss": 0.3662,
|
1765 |
+
"step": 238000
|
1766 |
+
},
|
1767 |
+
{
|
1768 |
+
"epoch": 0.24,
|
1769 |
+
"learning_rate": 1.792293397673715e-05,
|
1770 |
+
"loss": 0.3634,
|
1771 |
+
"step": 239000
|
1772 |
+
},
|
1773 |
+
{
|
1774 |
+
"epoch": 0.24,
|
1775 |
+
"learning_rate": 1.791444935039039e-05,
|
1776 |
+
"loss": 0.365,
|
1777 |
+
"step": 240000
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 0.24,
|
1781 |
+
"eval_runtime": 3401.6269,
|
1782 |
+
"eval_samples_per_second": 99.85,
|
1783 |
+
"eval_steps_per_second": 12.481,
|
1784 |
+
"step": 240000
|
1785 |
}
|
1786 |
],
|
1787 |
"max_steps": 1000000,
|
1788 |
"num_train_epochs": 9223372036854775807,
|
1789 |
+
"total_flos": 2.125106441575465e+21,
|
1790 |
"trial_name": null,
|
1791 |
"trial_params": null
|
1792 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ad81878847ff45e1880bc9e193537b6a982e87fb64a13bbf06eba84c2c3ee6f
|
3 |
size 454197066
|