Training in progress, step 303, checkpoint
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 501168482
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:556d16bb6aae79c6f06e3f2b46b8e0433216e37e93f5a8a74d9897d77f66f311
|
3 |
size 501168482
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3254f9e31f58266c38d6de2c365eacf98b89fb35d937a352ff406f7e1ed6eac8
|
3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f1f81f7017fe3de5487899a5240e530892937427049e1d8f17c3160bd856c94
|
3 |
size 14512
|
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 sha256:0cd637ac2493efabb59c857ff309da18b7f1fa1c1f76d6f3f94628c5048f8d88
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 76,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1635,6 +1635,531 @@
|
|
1635 |
"eval_samples_per_second": 3.941,
|
1636 |
"eval_steps_per_second": 0.986,
|
1637 |
"step": 228
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1638 |
}
|
1639 |
],
|
1640 |
"logging_steps": 1,
|
@@ -1649,12 +2174,12 @@
|
|
1649 |
"should_evaluate": false,
|
1650 |
"should_log": false,
|
1651 |
"should_save": true,
|
1652 |
-
"should_training_stop":
|
1653 |
},
|
1654 |
"attributes": {}
|
1655 |
}
|
1656 |
},
|
1657 |
-
"total_flos":
|
1658 |
"train_batch_size": 2,
|
1659 |
"trial_name": null,
|
1660 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.09214627841557059,
|
5 |
"eval_steps": 76,
|
6 |
+
"global_step": 303,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1635 |
"eval_samples_per_second": 3.941,
|
1636 |
"eval_steps_per_second": 0.986,
|
1637 |
"step": 228
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 0.06964190678932564,
|
1641 |
+
"grad_norm": NaN,
|
1642 |
+
"learning_rate": 3.932929715102863e-05,
|
1643 |
+
"loss": 0.0,
|
1644 |
+
"step": 229
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.06994601991941002,
|
1648 |
+
"grad_norm": NaN,
|
1649 |
+
"learning_rate": 3.834691207696649e-05,
|
1650 |
+
"loss": 0.0,
|
1651 |
+
"step": 230
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 0.07025013304949441,
|
1655 |
+
"grad_norm": NaN,
|
1656 |
+
"learning_rate": 3.7374033224987084e-05,
|
1657 |
+
"loss": 0.0,
|
1658 |
+
"step": 231
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 0.0705542461795788,
|
1662 |
+
"grad_norm": NaN,
|
1663 |
+
"learning_rate": 3.6410810602214684e-05,
|
1664 |
+
"loss": 0.0,
|
1665 |
+
"step": 232
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 0.0708583593096632,
|
1669 |
+
"grad_norm": NaN,
|
1670 |
+
"learning_rate": 3.5457392726890236e-05,
|
1671 |
+
"loss": 0.0,
|
1672 |
+
"step": 233
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 0.07116247243974759,
|
1676 |
+
"grad_norm": NaN,
|
1677 |
+
"learning_rate": 3.45139266054715e-05,
|
1678 |
+
"loss": 0.0,
|
1679 |
+
"step": 234
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 0.07146658556983197,
|
1683 |
+
"grad_norm": NaN,
|
1684 |
+
"learning_rate": 3.3580557709966066e-05,
|
1685 |
+
"loss": 0.0,
|
1686 |
+
"step": 235
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 0.07177069869991637,
|
1690 |
+
"grad_norm": NaN,
|
1691 |
+
"learning_rate": 3.2657429955501394e-05,
|
1692 |
+
"loss": 0.0,
|
1693 |
+
"step": 236
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 0.07207481183000077,
|
1697 |
+
"grad_norm": NaN,
|
1698 |
+
"learning_rate": 3.174468567813461e-05,
|
1699 |
+
"loss": 0.0,
|
1700 |
+
"step": 237
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 0.07237892496008515,
|
1704 |
+
"grad_norm": NaN,
|
1705 |
+
"learning_rate": 3.0842465612905837e-05,
|
1706 |
+
"loss": 0.0,
|
1707 |
+
"step": 238
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 0.07268303809016954,
|
1711 |
+
"grad_norm": NaN,
|
1712 |
+
"learning_rate": 2.9950908872138584e-05,
|
1713 |
+
"loss": 0.0,
|
1714 |
+
"step": 239
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 0.07298715122025394,
|
1718 |
+
"grad_norm": NaN,
|
1719 |
+
"learning_rate": 2.9070152923989946e-05,
|
1720 |
+
"loss": 0.0,
|
1721 |
+
"step": 240
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 0.07329126435033832,
|
1725 |
+
"grad_norm": NaN,
|
1726 |
+
"learning_rate": 2.82003335712546e-05,
|
1727 |
+
"loss": 0.0,
|
1728 |
+
"step": 241
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 0.07359537748042272,
|
1732 |
+
"grad_norm": NaN,
|
1733 |
+
"learning_rate": 2.7341584930425657e-05,
|
1734 |
+
"loss": 0.0,
|
1735 |
+
"step": 242
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 0.07389949061050712,
|
1739 |
+
"grad_norm": NaN,
|
1740 |
+
"learning_rate": 2.6494039411015193e-05,
|
1741 |
+
"loss": 0.0,
|
1742 |
+
"step": 243
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 0.0742036037405915,
|
1746 |
+
"grad_norm": NaN,
|
1747 |
+
"learning_rate": 2.5657827695138372e-05,
|
1748 |
+
"loss": 0.0,
|
1749 |
+
"step": 244
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.0745077168706759,
|
1753 |
+
"grad_norm": NaN,
|
1754 |
+
"learning_rate": 2.4833078717363544e-05,
|
1755 |
+
"loss": 0.0,
|
1756 |
+
"step": 245
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 0.07481183000076028,
|
1760 |
+
"grad_norm": NaN,
|
1761 |
+
"learning_rate": 2.4019919644832023e-05,
|
1762 |
+
"loss": 0.0,
|
1763 |
+
"step": 246
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 0.07511594313084467,
|
1767 |
+
"grad_norm": NaN,
|
1768 |
+
"learning_rate": 2.3218475857650346e-05,
|
1769 |
+
"loss": 0.0,
|
1770 |
+
"step": 247
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 0.07542005626092907,
|
1774 |
+
"grad_norm": NaN,
|
1775 |
+
"learning_rate": 2.242887092955801e-05,
|
1776 |
+
"loss": 0.0,
|
1777 |
+
"step": 248
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 0.07572416939101345,
|
1781 |
+
"grad_norm": NaN,
|
1782 |
+
"learning_rate": 2.1651226608873877e-05,
|
1783 |
+
"loss": 0.0,
|
1784 |
+
"step": 249
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 0.07602828252109785,
|
1788 |
+
"grad_norm": NaN,
|
1789 |
+
"learning_rate": 2.0885662799723804e-05,
|
1790 |
+
"loss": 0.0,
|
1791 |
+
"step": 250
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 0.07633239565118224,
|
1795 |
+
"grad_norm": NaN,
|
1796 |
+
"learning_rate": 2.0132297543552757e-05,
|
1797 |
+
"loss": 0.0,
|
1798 |
+
"step": 251
|
1799 |
+
},
|
1800 |
+
{
|
1801 |
+
"epoch": 0.07663650878126663,
|
1802 |
+
"grad_norm": NaN,
|
1803 |
+
"learning_rate": 1.939124700092423e-05,
|
1804 |
+
"loss": 0.0,
|
1805 |
+
"step": 252
|
1806 |
+
},
|
1807 |
+
{
|
1808 |
+
"epoch": 0.07694062191135102,
|
1809 |
+
"grad_norm": NaN,
|
1810 |
+
"learning_rate": 1.866262543360958e-05,
|
1811 |
+
"loss": 0.0,
|
1812 |
+
"step": 253
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 0.07724473504143542,
|
1816 |
+
"grad_norm": NaN,
|
1817 |
+
"learning_rate": 1.7946545186970022e-05,
|
1818 |
+
"loss": 0.0,
|
1819 |
+
"step": 254
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 0.0775488481715198,
|
1823 |
+
"grad_norm": NaN,
|
1824 |
+
"learning_rate": 1.7243116672634262e-05,
|
1825 |
+
"loss": 0.0,
|
1826 |
+
"step": 255
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 0.0778529613016042,
|
1830 |
+
"grad_norm": NaN,
|
1831 |
+
"learning_rate": 1.6552448351474304e-05,
|
1832 |
+
"loss": 0.0,
|
1833 |
+
"step": 256
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 0.0781570744316886,
|
1837 |
+
"grad_norm": NaN,
|
1838 |
+
"learning_rate": 1.587464671688187e-05,
|
1839 |
+
"loss": 0.0,
|
1840 |
+
"step": 257
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 0.07846118756177298,
|
1844 |
+
"grad_norm": NaN,
|
1845 |
+
"learning_rate": 1.520981627834851e-05,
|
1846 |
+
"loss": 0.0,
|
1847 |
+
"step": 258
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"epoch": 0.07876530069185737,
|
1851 |
+
"grad_norm": NaN,
|
1852 |
+
"learning_rate": 1.4558059545351143e-05,
|
1853 |
+
"loss": 0.0,
|
1854 |
+
"step": 259
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.07906941382194176,
|
1858 |
+
"grad_norm": NaN,
|
1859 |
+
"learning_rate": 1.3919477011546423e-05,
|
1860 |
+
"loss": 0.0,
|
1861 |
+
"step": 260
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 0.07937352695202615,
|
1865 |
+
"grad_norm": NaN,
|
1866 |
+
"learning_rate": 1.3294167139275593e-05,
|
1867 |
+
"loss": 0.0,
|
1868 |
+
"step": 261
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 0.07967764008211055,
|
1872 |
+
"grad_norm": NaN,
|
1873 |
+
"learning_rate": 1.2682226344382796e-05,
|
1874 |
+
"loss": 0.0,
|
1875 |
+
"step": 262
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 0.07998175321219493,
|
1879 |
+
"grad_norm": NaN,
|
1880 |
+
"learning_rate": 1.208374898134883e-05,
|
1881 |
+
"loss": 0.0,
|
1882 |
+
"step": 263
|
1883 |
+
},
|
1884 |
+
{
|
1885 |
+
"epoch": 0.08028586634227933,
|
1886 |
+
"grad_norm": NaN,
|
1887 |
+
"learning_rate": 1.1498827328742623e-05,
|
1888 |
+
"loss": 0.0,
|
1889 |
+
"step": 264
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 0.08058997947236372,
|
1893 |
+
"grad_norm": NaN,
|
1894 |
+
"learning_rate": 1.0927551574992967e-05,
|
1895 |
+
"loss": 0.0,
|
1896 |
+
"step": 265
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 0.0808940926024481,
|
1900 |
+
"grad_norm": NaN,
|
1901 |
+
"learning_rate": 1.0370009804482483e-05,
|
1902 |
+
"loss": 0.0,
|
1903 |
+
"step": 266
|
1904 |
+
},
|
1905 |
+
{
|
1906 |
+
"epoch": 0.0811982057325325,
|
1907 |
+
"grad_norm": NaN,
|
1908 |
+
"learning_rate": 9.82628798396592e-06,
|
1909 |
+
"loss": 0.0,
|
1910 |
+
"step": 267
|
1911 |
+
},
|
1912 |
+
{
|
1913 |
+
"epoch": 0.0815023188626169,
|
1914 |
+
"grad_norm": NaN,
|
1915 |
+
"learning_rate": 9.296469949315156e-06,
|
1916 |
+
"loss": 0.0,
|
1917 |
+
"step": 268
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 0.08180643199270128,
|
1921 |
+
"grad_norm": NaN,
|
1922 |
+
"learning_rate": 8.780637392592495e-06,
|
1923 |
+
"loss": 0.0,
|
1924 |
+
"step": 269
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 0.08211054512278568,
|
1928 |
+
"grad_norm": NaN,
|
1929 |
+
"learning_rate": 8.278869849454718e-06,
|
1930 |
+
"loss": 0.0,
|
1931 |
+
"step": 270
|
1932 |
+
},
|
1933 |
+
{
|
1934 |
+
"epoch": 0.08241465825287007,
|
1935 |
+
"grad_norm": NaN,
|
1936 |
+
"learning_rate": 7.791244686889588e-06,
|
1937 |
+
"loss": 0.0,
|
1938 |
+
"step": 271
|
1939 |
+
},
|
1940 |
+
{
|
1941 |
+
"epoch": 0.08271877138295446,
|
1942 |
+
"grad_norm": NaN,
|
1943 |
+
"learning_rate": 7.317837091286706e-06,
|
1944 |
+
"loss": 0.0,
|
1945 |
+
"step": 272
|
1946 |
+
},
|
1947 |
+
{
|
1948 |
+
"epoch": 0.08302288451303885,
|
1949 |
+
"grad_norm": NaN,
|
1950 |
+
"learning_rate": 6.858720056844614e-06,
|
1951 |
+
"loss": 0.0,
|
1952 |
+
"step": 273
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 0.08332699764312324,
|
1956 |
+
"grad_norm": NaN,
|
1957 |
+
"learning_rate": 6.413964374315851e-06,
|
1958 |
+
"loss": 0.0,
|
1959 |
+
"step": 274
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 0.08363111077320763,
|
1963 |
+
"grad_norm": NaN,
|
1964 |
+
"learning_rate": 5.983638620091858e-06,
|
1965 |
+
"loss": 0.0,
|
1966 |
+
"step": 275
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 0.08393522390329203,
|
1970 |
+
"grad_norm": NaN,
|
1971 |
+
"learning_rate": 5.567809145629244e-06,
|
1972 |
+
"loss": 0.0,
|
1973 |
+
"step": 276
|
1974 |
+
},
|
1975 |
+
{
|
1976 |
+
"epoch": 0.08423933703337641,
|
1977 |
+
"grad_norm": NaN,
|
1978 |
+
"learning_rate": 5.1665400672190725e-06,
|
1979 |
+
"loss": 0.0,
|
1980 |
+
"step": 277
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 0.0845434501634608,
|
1984 |
+
"grad_norm": NaN,
|
1985 |
+
"learning_rate": 4.7798932561009865e-06,
|
1986 |
+
"loss": 0.0,
|
1987 |
+
"step": 278
|
1988 |
+
},
|
1989 |
+
{
|
1990 |
+
"epoch": 0.0848475632935452,
|
1991 |
+
"grad_norm": NaN,
|
1992 |
+
"learning_rate": 4.407928328923194e-06,
|
1993 |
+
"loss": 0.0,
|
1994 |
+
"step": 279
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 0.08515167642362959,
|
1998 |
+
"grad_norm": NaN,
|
1999 |
+
"learning_rate": 4.050702638550275e-06,
|
2000 |
+
"loss": 0.0,
|
2001 |
+
"step": 280
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 0.08545578955371398,
|
2005 |
+
"grad_norm": NaN,
|
2006 |
+
"learning_rate": 3.7082712652200867e-06,
|
2007 |
+
"loss": 0.0,
|
2008 |
+
"step": 281
|
2009 |
+
},
|
2010 |
+
{
|
2011 |
+
"epoch": 0.08575990268379838,
|
2012 |
+
"grad_norm": NaN,
|
2013 |
+
"learning_rate": 3.380687008050909e-06,
|
2014 |
+
"loss": 0.0,
|
2015 |
+
"step": 282
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 0.08606401581388276,
|
2019 |
+
"grad_norm": NaN,
|
2020 |
+
"learning_rate": 3.068000376900515e-06,
|
2021 |
+
"loss": 0.0,
|
2022 |
+
"step": 283
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 0.08636812894396716,
|
2026 |
+
"grad_norm": NaN,
|
2027 |
+
"learning_rate": 2.770259584577972e-06,
|
2028 |
+
"loss": 0.0,
|
2029 |
+
"step": 284
|
2030 |
+
},
|
2031 |
+
{
|
2032 |
+
"epoch": 0.08667224207405155,
|
2033 |
+
"grad_norm": NaN,
|
2034 |
+
"learning_rate": 2.4875105394098654e-06,
|
2035 |
+
"loss": 0.0,
|
2036 |
+
"step": 285
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"epoch": 0.08697635520413594,
|
2040 |
+
"grad_norm": NaN,
|
2041 |
+
"learning_rate": 2.219796838161681e-06,
|
2042 |
+
"loss": 0.0,
|
2043 |
+
"step": 286
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 0.08728046833422033,
|
2047 |
+
"grad_norm": NaN,
|
2048 |
+
"learning_rate": 1.967159759315751e-06,
|
2049 |
+
"loss": 0.0,
|
2050 |
+
"step": 287
|
2051 |
+
},
|
2052 |
+
{
|
2053 |
+
"epoch": 0.08758458146430473,
|
2054 |
+
"grad_norm": NaN,
|
2055 |
+
"learning_rate": 1.7296382567064672e-06,
|
2056 |
+
"loss": 0.0,
|
2057 |
+
"step": 288
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 0.08788869459438911,
|
2061 |
+
"grad_norm": NaN,
|
2062 |
+
"learning_rate": 1.5072689535141072e-06,
|
2063 |
+
"loss": 0.0,
|
2064 |
+
"step": 289
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 0.08819280772447351,
|
2068 |
+
"grad_norm": NaN,
|
2069 |
+
"learning_rate": 1.3000861366179062e-06,
|
2070 |
+
"loss": 0.0,
|
2071 |
+
"step": 290
|
2072 |
+
},
|
2073 |
+
{
|
2074 |
+
"epoch": 0.08849692085455789,
|
2075 |
+
"grad_norm": NaN,
|
2076 |
+
"learning_rate": 1.1081217513094212e-06,
|
2077 |
+
"loss": 0.0,
|
2078 |
+
"step": 291
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 0.08880103398464229,
|
2082 |
+
"grad_norm": NaN,
|
2083 |
+
"learning_rate": 9.314053963669245e-07,
|
2084 |
+
"loss": 0.0,
|
2085 |
+
"step": 292
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 0.08910514711472668,
|
2089 |
+
"grad_norm": NaN,
|
2090 |
+
"learning_rate": 7.699643194915784e-07,
|
2091 |
+
"loss": 0.0,
|
2092 |
+
"step": 293
|
2093 |
+
},
|
2094 |
+
{
|
2095 |
+
"epoch": 0.08940926024481106,
|
2096 |
+
"grad_norm": NaN,
|
2097 |
+
"learning_rate": 6.238234131061616e-07,
|
2098 |
+
"loss": 0.0,
|
2099 |
+
"step": 294
|
2100 |
+
},
|
2101 |
+
{
|
2102 |
+
"epoch": 0.08971337337489546,
|
2103 |
+
"grad_norm": NaN,
|
2104 |
+
"learning_rate": 4.93005210516928e-07,
|
2105 |
+
"loss": 0.0,
|
2106 |
+
"step": 295
|
2107 |
+
},
|
2108 |
+
{
|
2109 |
+
"epoch": 0.09001748650497986,
|
2110 |
+
"grad_norm": NaN,
|
2111 |
+
"learning_rate": 3.775298824391982e-07,
|
2112 |
+
"loss": 0.0,
|
2113 |
+
"step": 296
|
2114 |
+
},
|
2115 |
+
{
|
2116 |
+
"epoch": 0.09032159963506424,
|
2117 |
+
"grad_norm": NaN,
|
2118 |
+
"learning_rate": 2.774152338873126e-07,
|
2119 |
+
"loss": 0.0,
|
2120 |
+
"step": 297
|
2121 |
+
},
|
2122 |
+
{
|
2123 |
+
"epoch": 0.09062571276514864,
|
2124 |
+
"grad_norm": NaN,
|
2125 |
+
"learning_rate": 1.9267670142926187e-07,
|
2126 |
+
"loss": 0.0,
|
2127 |
+
"step": 298
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 0.09092982589523303,
|
2131 |
+
"grad_norm": NaN,
|
2132 |
+
"learning_rate": 1.2332735080651248e-07,
|
2133 |
+
"loss": 0.0,
|
2134 |
+
"step": 299
|
2135 |
+
},
|
2136 |
+
{
|
2137 |
+
"epoch": 0.09123393902531741,
|
2138 |
+
"grad_norm": NaN,
|
2139 |
+
"learning_rate": 6.9377874919474e-08,
|
2140 |
+
"loss": 0.0,
|
2141 |
+
"step": 300
|
2142 |
+
},
|
2143 |
+
{
|
2144 |
+
"epoch": 0.09153805215540181,
|
2145 |
+
"grad_norm": NaN,
|
2146 |
+
"learning_rate": 3.0836592178717926e-08,
|
2147 |
+
"loss": 0.0,
|
2148 |
+
"step": 301
|
2149 |
+
},
|
2150 |
+
{
|
2151 |
+
"epoch": 0.09184216528548621,
|
2152 |
+
"grad_norm": NaN,
|
2153 |
+
"learning_rate": 7.709445222403577e-09,
|
2154 |
+
"loss": 0.0,
|
2155 |
+
"step": 302
|
2156 |
+
},
|
2157 |
+
{
|
2158 |
+
"epoch": 0.09214627841557059,
|
2159 |
+
"grad_norm": NaN,
|
2160 |
+
"learning_rate": 0.0,
|
2161 |
+
"loss": 0.0,
|
2162 |
+
"step": 303
|
2163 |
}
|
2164 |
],
|
2165 |
"logging_steps": 1,
|
|
|
2174 |
"should_evaluate": false,
|
2175 |
"should_log": false,
|
2176 |
"should_save": true,
|
2177 |
+
"should_training_stop": true
|
2178 |
},
|
2179 |
"attributes": {}
|
2180 |
}
|
2181 |
},
|
2182 |
+
"total_flos": 2.06572946950665e+18,
|
2183 |
"train_batch_size": 2,
|
2184 |
"trial_name": null,
|
2185 |
"trial_params": null
|