DuongTrongChi
commited on
Commit
•
6670c4e
1
Parent(s):
073be20
Training in progress, step 289, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100198584
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5ba6698fd44d93d0d95a7529def37a9cede5e4d09940a0ab3a40fd14872cf1f
|
3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4758eb51404ba0b3f4b0b36fcf9c00f2cdf4fdf570c90bf394f1816ab1cc5a08
|
3 |
+
size 50675604
|
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 sha256:7e7a65992fdf54fe4538029cd8ec72e942bb69b362a7899f495d5668d43ce184
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1638,6 +1638,398 @@
|
|
1638 |
"learning_rate": 1.5445205479452056e-05,
|
1639 |
"loss": 1.1876,
|
1640 |
"step": 233
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1641 |
}
|
1642 |
],
|
1643 |
"logging_steps": 1,
|
@@ -1657,7 +2049,7 @@
|
|
1657 |
"attributes": {}
|
1658 |
}
|
1659 |
},
|
1660 |
-
"total_flos":
|
1661 |
"train_batch_size": 4,
|
1662 |
"trial_name": null,
|
1663 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4222445438772715,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 289,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1638 |
"learning_rate": 1.5445205479452056e-05,
|
1639 |
"loss": 1.1876,
|
1640 |
"step": 233
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.3418865856999361,
|
1644 |
+
"grad_norm": 0.09288407117128372,
|
1645 |
+
"learning_rate": 1.541095890410959e-05,
|
1646 |
+
"loss": 1.2163,
|
1647 |
+
"step": 234
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.34334763948497854,
|
1651 |
+
"grad_norm": 0.09983450174331665,
|
1652 |
+
"learning_rate": 1.5376712328767125e-05,
|
1653 |
+
"loss": 1.2118,
|
1654 |
+
"step": 235
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.344808693270021,
|
1658 |
+
"grad_norm": 0.10181832313537598,
|
1659 |
+
"learning_rate": 1.5342465753424658e-05,
|
1660 |
+
"loss": 1.2189,
|
1661 |
+
"step": 236
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.34626974705506347,
|
1665 |
+
"grad_norm": 0.10253550857305527,
|
1666 |
+
"learning_rate": 1.5308219178082195e-05,
|
1667 |
+
"loss": 1.2415,
|
1668 |
+
"step": 237
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.34773080084010594,
|
1672 |
+
"grad_norm": 0.09938843548297882,
|
1673 |
+
"learning_rate": 1.5273972602739728e-05,
|
1674 |
+
"loss": 1.2391,
|
1675 |
+
"step": 238
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.3491918546251484,
|
1679 |
+
"grad_norm": 0.09904040396213531,
|
1680 |
+
"learning_rate": 1.523972602739726e-05,
|
1681 |
+
"loss": 1.147,
|
1682 |
+
"step": 239
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.35065290841019087,
|
1686 |
+
"grad_norm": 0.1011345386505127,
|
1687 |
+
"learning_rate": 1.5205479452054797e-05,
|
1688 |
+
"loss": 1.2801,
|
1689 |
+
"step": 240
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.35211396219523333,
|
1693 |
+
"grad_norm": 0.10546337813138962,
|
1694 |
+
"learning_rate": 1.517123287671233e-05,
|
1695 |
+
"loss": 1.2179,
|
1696 |
+
"step": 241
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.3535750159802758,
|
1700 |
+
"grad_norm": 0.09379958361387253,
|
1701 |
+
"learning_rate": 1.5136986301369865e-05,
|
1702 |
+
"loss": 1.2078,
|
1703 |
+
"step": 242
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.35503606976531826,
|
1707 |
+
"grad_norm": 0.09210502356290817,
|
1708 |
+
"learning_rate": 1.5102739726027398e-05,
|
1709 |
+
"loss": 1.2126,
|
1710 |
+
"step": 243
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.3564971235503607,
|
1714 |
+
"grad_norm": 0.0911347046494484,
|
1715 |
+
"learning_rate": 1.5068493150684933e-05,
|
1716 |
+
"loss": 1.2353,
|
1717 |
+
"step": 244
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.35795817733540314,
|
1721 |
+
"grad_norm": 0.10343588888645172,
|
1722 |
+
"learning_rate": 1.5034246575342466e-05,
|
1723 |
+
"loss": 1.2063,
|
1724 |
+
"step": 245
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.3594192311204456,
|
1728 |
+
"grad_norm": 0.10774116218090057,
|
1729 |
+
"learning_rate": 1.5000000000000002e-05,
|
1730 |
+
"loss": 1.1895,
|
1731 |
+
"step": 246
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.36088028490548807,
|
1735 |
+
"grad_norm": 0.09309092164039612,
|
1736 |
+
"learning_rate": 1.4965753424657537e-05,
|
1737 |
+
"loss": 1.2661,
|
1738 |
+
"step": 247
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.36234133869053053,
|
1742 |
+
"grad_norm": 0.09687670320272446,
|
1743 |
+
"learning_rate": 1.493150684931507e-05,
|
1744 |
+
"loss": 1.2154,
|
1745 |
+
"step": 248
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.363802392475573,
|
1749 |
+
"grad_norm": 0.09125279635190964,
|
1750 |
+
"learning_rate": 1.4897260273972605e-05,
|
1751 |
+
"loss": 1.2367,
|
1752 |
+
"step": 249
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.36526344626061547,
|
1756 |
+
"grad_norm": 0.11119771748781204,
|
1757 |
+
"learning_rate": 1.4863013698630138e-05,
|
1758 |
+
"loss": 1.1032,
|
1759 |
+
"step": 250
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.36672450004565793,
|
1763 |
+
"grad_norm": 0.11136704683303833,
|
1764 |
+
"learning_rate": 1.4828767123287672e-05,
|
1765 |
+
"loss": 1.1679,
|
1766 |
+
"step": 251
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 0.3681855538307004,
|
1770 |
+
"grad_norm": 0.11276744306087494,
|
1771 |
+
"learning_rate": 1.4794520547945205e-05,
|
1772 |
+
"loss": 1.1268,
|
1773 |
+
"step": 252
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.36964660761574286,
|
1777 |
+
"grad_norm": 0.10903234779834747,
|
1778 |
+
"learning_rate": 1.4760273972602742e-05,
|
1779 |
+
"loss": 1.1681,
|
1780 |
+
"step": 253
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 0.3711076614007853,
|
1784 |
+
"grad_norm": 0.09586647897958755,
|
1785 |
+
"learning_rate": 1.4726027397260275e-05,
|
1786 |
+
"loss": 1.2486,
|
1787 |
+
"step": 254
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 0.3725687151858278,
|
1791 |
+
"grad_norm": 0.09748208522796631,
|
1792 |
+
"learning_rate": 1.469178082191781e-05,
|
1793 |
+
"loss": 1.3186,
|
1794 |
+
"step": 255
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.37402976897087026,
|
1798 |
+
"grad_norm": 0.10351759195327759,
|
1799 |
+
"learning_rate": 1.4657534246575344e-05,
|
1800 |
+
"loss": 1.1344,
|
1801 |
+
"step": 256
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.3754908227559127,
|
1805 |
+
"grad_norm": 0.11112543940544128,
|
1806 |
+
"learning_rate": 1.4623287671232877e-05,
|
1807 |
+
"loss": 1.2433,
|
1808 |
+
"step": 257
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.3769518765409552,
|
1812 |
+
"grad_norm": 0.09291627258062363,
|
1813 |
+
"learning_rate": 1.4589041095890412e-05,
|
1814 |
+
"loss": 1.1717,
|
1815 |
+
"step": 258
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.3784129303259976,
|
1819 |
+
"grad_norm": 0.11696401238441467,
|
1820 |
+
"learning_rate": 1.4554794520547945e-05,
|
1821 |
+
"loss": 1.1889,
|
1822 |
+
"step": 259
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 0.37987398411104006,
|
1826 |
+
"grad_norm": 0.09728217869997025,
|
1827 |
+
"learning_rate": 1.4520547945205482e-05,
|
1828 |
+
"loss": 1.1756,
|
1829 |
+
"step": 260
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 0.38133503789608253,
|
1833 |
+
"grad_norm": 0.10936015099287033,
|
1834 |
+
"learning_rate": 1.4486301369863015e-05,
|
1835 |
+
"loss": 1.1526,
|
1836 |
+
"step": 261
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 0.382796091681125,
|
1840 |
+
"grad_norm": 0.09887027740478516,
|
1841 |
+
"learning_rate": 1.445205479452055e-05,
|
1842 |
+
"loss": 1.1556,
|
1843 |
+
"step": 262
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 0.38425714546616746,
|
1847 |
+
"grad_norm": 0.09080694615840912,
|
1848 |
+
"learning_rate": 1.4417808219178084e-05,
|
1849 |
+
"loss": 1.1592,
|
1850 |
+
"step": 263
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 0.3857181992512099,
|
1854 |
+
"grad_norm": 0.09273724257946014,
|
1855 |
+
"learning_rate": 1.4383561643835617e-05,
|
1856 |
+
"loss": 1.1994,
|
1857 |
+
"step": 264
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.3871792530362524,
|
1861 |
+
"grad_norm": 0.10300930589437485,
|
1862 |
+
"learning_rate": 1.4349315068493152e-05,
|
1863 |
+
"loss": 1.2292,
|
1864 |
+
"step": 265
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 0.38864030682129486,
|
1868 |
+
"grad_norm": 0.10504985600709915,
|
1869 |
+
"learning_rate": 1.4315068493150685e-05,
|
1870 |
+
"loss": 1.1623,
|
1871 |
+
"step": 266
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 0.3901013606063373,
|
1875 |
+
"grad_norm": 0.10123489052057266,
|
1876 |
+
"learning_rate": 1.4280821917808221e-05,
|
1877 |
+
"loss": 1.1435,
|
1878 |
+
"step": 267
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 0.3915624143913798,
|
1882 |
+
"grad_norm": 0.09777438640594482,
|
1883 |
+
"learning_rate": 1.4246575342465754e-05,
|
1884 |
+
"loss": 1.2014,
|
1885 |
+
"step": 268
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 0.39302346817642225,
|
1889 |
+
"grad_norm": 0.10096925497055054,
|
1890 |
+
"learning_rate": 1.421232876712329e-05,
|
1891 |
+
"loss": 1.243,
|
1892 |
+
"step": 269
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 0.3944845219614647,
|
1896 |
+
"grad_norm": 0.11357256770133972,
|
1897 |
+
"learning_rate": 1.4178082191780822e-05,
|
1898 |
+
"loss": 1.1434,
|
1899 |
+
"step": 270
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.3959455757465072,
|
1903 |
+
"grad_norm": 0.09454260766506195,
|
1904 |
+
"learning_rate": 1.4143835616438357e-05,
|
1905 |
+
"loss": 1.257,
|
1906 |
+
"step": 271
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 0.39740662953154965,
|
1910 |
+
"grad_norm": 0.0995330736041069,
|
1911 |
+
"learning_rate": 1.4109589041095892e-05,
|
1912 |
+
"loss": 1.2173,
|
1913 |
+
"step": 272
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 0.3988676833165921,
|
1917 |
+
"grad_norm": 0.09766160696744919,
|
1918 |
+
"learning_rate": 1.4075342465753425e-05,
|
1919 |
+
"loss": 1.1523,
|
1920 |
+
"step": 273
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 0.4003287371016346,
|
1924 |
+
"grad_norm": 0.09799221158027649,
|
1925 |
+
"learning_rate": 1.4041095890410961e-05,
|
1926 |
+
"loss": 1.2785,
|
1927 |
+
"step": 274
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 0.401789790886677,
|
1931 |
+
"grad_norm": 0.11043940484523773,
|
1932 |
+
"learning_rate": 1.4006849315068494e-05,
|
1933 |
+
"loss": 1.1715,
|
1934 |
+
"step": 275
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 0.40325084467171946,
|
1938 |
+
"grad_norm": 0.09611232578754425,
|
1939 |
+
"learning_rate": 1.3972602739726029e-05,
|
1940 |
+
"loss": 1.1689,
|
1941 |
+
"step": 276
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.4047118984567619,
|
1945 |
+
"grad_norm": 0.0990489274263382,
|
1946 |
+
"learning_rate": 1.3938356164383562e-05,
|
1947 |
+
"loss": 1.2633,
|
1948 |
+
"step": 277
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 0.4061729522418044,
|
1952 |
+
"grad_norm": 0.09898124635219574,
|
1953 |
+
"learning_rate": 1.3904109589041097e-05,
|
1954 |
+
"loss": 1.2649,
|
1955 |
+
"step": 278
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 0.40763400602684685,
|
1959 |
+
"grad_norm": 0.10052936524152756,
|
1960 |
+
"learning_rate": 1.3869863013698633e-05,
|
1961 |
+
"loss": 1.1938,
|
1962 |
+
"step": 279
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 0.4090950598118893,
|
1966 |
+
"grad_norm": 0.10725940018892288,
|
1967 |
+
"learning_rate": 1.3835616438356164e-05,
|
1968 |
+
"loss": 1.2371,
|
1969 |
+
"step": 280
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 0.4105561135969318,
|
1973 |
+
"grad_norm": 0.10019299387931824,
|
1974 |
+
"learning_rate": 1.3801369863013701e-05,
|
1975 |
+
"loss": 1.2738,
|
1976 |
+
"step": 281
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 0.41201716738197425,
|
1980 |
+
"grad_norm": 0.10612376034259796,
|
1981 |
+
"learning_rate": 1.3767123287671234e-05,
|
1982 |
+
"loss": 1.1666,
|
1983 |
+
"step": 282
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.4134782211670167,
|
1987 |
+
"grad_norm": 0.1012573391199112,
|
1988 |
+
"learning_rate": 1.3732876712328769e-05,
|
1989 |
+
"loss": 1.2489,
|
1990 |
+
"step": 283
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 0.4149392749520592,
|
1994 |
+
"grad_norm": 0.10012490302324295,
|
1995 |
+
"learning_rate": 1.3698630136986302e-05,
|
1996 |
+
"loss": 1.2934,
|
1997 |
+
"step": 284
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 0.41640032873710164,
|
2001 |
+
"grad_norm": 0.09684241563081741,
|
2002 |
+
"learning_rate": 1.3664383561643836e-05,
|
2003 |
+
"loss": 1.2547,
|
2004 |
+
"step": 285
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 0.4178613825221441,
|
2008 |
+
"grad_norm": 0.10791518539190292,
|
2009 |
+
"learning_rate": 1.363013698630137e-05,
|
2010 |
+
"loss": 1.2118,
|
2011 |
+
"step": 286
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 0.4193224363071866,
|
2015 |
+
"grad_norm": 0.10714226961135864,
|
2016 |
+
"learning_rate": 1.3595890410958906e-05,
|
2017 |
+
"loss": 1.218,
|
2018 |
+
"step": 287
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 0.42078349009222904,
|
2022 |
+
"grad_norm": 0.10130172967910767,
|
2023 |
+
"learning_rate": 1.356164383561644e-05,
|
2024 |
+
"loss": 1.2244,
|
2025 |
+
"step": 288
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.4222445438772715,
|
2029 |
+
"grad_norm": 0.0985652357339859,
|
2030 |
+
"learning_rate": 1.3527397260273974e-05,
|
2031 |
+
"loss": 1.2228,
|
2032 |
+
"step": 289
|
2033 |
}
|
2034 |
],
|
2035 |
"logging_steps": 1,
|
|
|
2049 |
"attributes": {}
|
2050 |
}
|
2051 |
},
|
2052 |
+
"total_flos": 3.2530992653758464e+17,
|
2053 |
"train_batch_size": 4,
|
2054 |
"trial_name": null,
|
2055 |
"trial_params": null
|