Training in progress, step 3000, 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 5323528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d9f1330624d49e1cfa068a1cfd37e35fba53b8c452104e1861364c4b2bcc193
|
| 3 |
size 5323528
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10707706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e1273154004834ff66e75e29f96e8a925d89006ab79c55eac7eeca115990223
|
| 3 |
size 10707706
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:635c549447e6d040590768c59571f091ceb0002258d8b337cb9e12c5e9806440
|
| 3 |
size 14244
|
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 sha256:66074cbfdf1af5e0486634010580a05d2b8863ee9a8c7ccf5e54b33878144bd6
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-
|
| 4 |
-
"epoch": 4.
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1707,13 +1707,353 @@
|
|
| 1707 |
"eval_samples_per_second": 89.035,
|
| 1708 |
"eval_steps_per_second": 11.177,
|
| 1709 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1710 |
}
|
| 1711 |
],
|
| 1712 |
"logging_steps": 10,
|
| 1713 |
"max_steps": 6130,
|
| 1714 |
"num_train_epochs": 10,
|
| 1715 |
"save_steps": 500,
|
| 1716 |
-
"total_flos":
|
| 1717 |
"trial_name": null,
|
| 1718 |
"trial_params": null
|
| 1719 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.4271390736103058,
|
| 3 |
+
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-3000",
|
| 4 |
+
"epoch": 4.893964110929853,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1707 |
"eval_samples_per_second": 89.035,
|
| 1708 |
"eval_steps_per_second": 11.177,
|
| 1709 |
"step": 2500
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 4.09,
|
| 1713 |
+
"learning_rate": 0.0006429840142095915,
|
| 1714 |
+
"loss": 0.4375,
|
| 1715 |
+
"step": 2510
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 4.11,
|
| 1719 |
+
"learning_rate": 0.0006412078152753108,
|
| 1720 |
+
"loss": 0.4485,
|
| 1721 |
+
"step": 2520
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 4.13,
|
| 1725 |
+
"learning_rate": 0.0006394316163410302,
|
| 1726 |
+
"loss": 0.4633,
|
| 1727 |
+
"step": 2530
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 4.14,
|
| 1731 |
+
"learning_rate": 0.0006376554174067496,
|
| 1732 |
+
"loss": 0.4457,
|
| 1733 |
+
"step": 2540
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 4.16,
|
| 1737 |
+
"learning_rate": 0.0006358792184724689,
|
| 1738 |
+
"loss": 0.4504,
|
| 1739 |
+
"step": 2550
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 4.18,
|
| 1743 |
+
"learning_rate": 0.0006341030195381882,
|
| 1744 |
+
"loss": 0.4719,
|
| 1745 |
+
"step": 2560
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 4.19,
|
| 1749 |
+
"learning_rate": 0.0006323268206039076,
|
| 1750 |
+
"loss": 0.4223,
|
| 1751 |
+
"step": 2570
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 4.21,
|
| 1755 |
+
"learning_rate": 0.0006305506216696269,
|
| 1756 |
+
"loss": 0.4481,
|
| 1757 |
+
"step": 2580
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 4.23,
|
| 1761 |
+
"learning_rate": 0.0006287744227353463,
|
| 1762 |
+
"loss": 0.4371,
|
| 1763 |
+
"step": 2590
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 4.24,
|
| 1767 |
+
"learning_rate": 0.0006269982238010657,
|
| 1768 |
+
"loss": 0.4284,
|
| 1769 |
+
"step": 2600
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 4.24,
|
| 1773 |
+
"eval_loss": 0.44260162115097046,
|
| 1774 |
+
"eval_runtime": 13.1231,
|
| 1775 |
+
"eval_samples_per_second": 89.232,
|
| 1776 |
+
"eval_steps_per_second": 11.202,
|
| 1777 |
+
"step": 2600
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 4.26,
|
| 1781 |
+
"learning_rate": 0.0006252220248667851,
|
| 1782 |
+
"loss": 0.4474,
|
| 1783 |
+
"step": 2610
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 4.27,
|
| 1787 |
+
"learning_rate": 0.0006234458259325044,
|
| 1788 |
+
"loss": 0.4725,
|
| 1789 |
+
"step": 2620
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 4.29,
|
| 1793 |
+
"learning_rate": 0.0006216696269982238,
|
| 1794 |
+
"loss": 0.4319,
|
| 1795 |
+
"step": 2630
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 4.31,
|
| 1799 |
+
"learning_rate": 0.0006198934280639432,
|
| 1800 |
+
"loss": 0.4502,
|
| 1801 |
+
"step": 2640
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 4.32,
|
| 1805 |
+
"learning_rate": 0.0006181172291296625,
|
| 1806 |
+
"loss": 0.4378,
|
| 1807 |
+
"step": 2650
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 4.34,
|
| 1811 |
+
"learning_rate": 0.0006163410301953819,
|
| 1812 |
+
"loss": 0.4333,
|
| 1813 |
+
"step": 2660
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 4.36,
|
| 1817 |
+
"learning_rate": 0.0006145648312611012,
|
| 1818 |
+
"loss": 0.4206,
|
| 1819 |
+
"step": 2670
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 4.37,
|
| 1823 |
+
"learning_rate": 0.0006127886323268205,
|
| 1824 |
+
"loss": 0.4314,
|
| 1825 |
+
"step": 2680
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 4.39,
|
| 1829 |
+
"learning_rate": 0.00061101243339254,
|
| 1830 |
+
"loss": 0.4083,
|
| 1831 |
+
"step": 2690
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 4.4,
|
| 1835 |
+
"learning_rate": 0.0006092362344582594,
|
| 1836 |
+
"loss": 0.4416,
|
| 1837 |
+
"step": 2700
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 4.4,
|
| 1841 |
+
"eval_loss": 0.4252881109714508,
|
| 1842 |
+
"eval_runtime": 13.1357,
|
| 1843 |
+
"eval_samples_per_second": 89.146,
|
| 1844 |
+
"eval_steps_per_second": 11.191,
|
| 1845 |
+
"step": 2700
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 4.42,
|
| 1849 |
+
"learning_rate": 0.0006074600355239787,
|
| 1850 |
+
"loss": 0.452,
|
| 1851 |
+
"step": 2710
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 4.44,
|
| 1855 |
+
"learning_rate": 0.0006056838365896981,
|
| 1856 |
+
"loss": 0.4075,
|
| 1857 |
+
"step": 2720
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 4.45,
|
| 1861 |
+
"learning_rate": 0.0006039076376554175,
|
| 1862 |
+
"loss": 0.466,
|
| 1863 |
+
"step": 2730
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 4.47,
|
| 1867 |
+
"learning_rate": 0.0006021314387211368,
|
| 1868 |
+
"loss": 0.4219,
|
| 1869 |
+
"step": 2740
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 4.49,
|
| 1873 |
+
"learning_rate": 0.0006003552397868562,
|
| 1874 |
+
"loss": 0.4391,
|
| 1875 |
+
"step": 2750
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 4.5,
|
| 1879 |
+
"learning_rate": 0.0005985790408525756,
|
| 1880 |
+
"loss": 0.4952,
|
| 1881 |
+
"step": 2760
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 4.52,
|
| 1885 |
+
"learning_rate": 0.0005968028419182949,
|
| 1886 |
+
"loss": 0.4594,
|
| 1887 |
+
"step": 2770
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 4.54,
|
| 1891 |
+
"learning_rate": 0.0005950266429840142,
|
| 1892 |
+
"loss": 0.4501,
|
| 1893 |
+
"step": 2780
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 4.55,
|
| 1897 |
+
"learning_rate": 0.0005932504440497336,
|
| 1898 |
+
"loss": 0.4474,
|
| 1899 |
+
"step": 2790
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 4.57,
|
| 1903 |
+
"learning_rate": 0.0005914742451154529,
|
| 1904 |
+
"loss": 0.4335,
|
| 1905 |
+
"step": 2800
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 4.57,
|
| 1909 |
+
"eval_loss": 0.43218302726745605,
|
| 1910 |
+
"eval_runtime": 12.9197,
|
| 1911 |
+
"eval_samples_per_second": 90.637,
|
| 1912 |
+
"eval_steps_per_second": 11.378,
|
| 1913 |
+
"step": 2800
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 4.58,
|
| 1917 |
+
"learning_rate": 0.0005896980461811723,
|
| 1918 |
+
"loss": 0.4498,
|
| 1919 |
+
"step": 2810
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 4.6,
|
| 1923 |
+
"learning_rate": 0.0005879218472468917,
|
| 1924 |
+
"loss": 0.4228,
|
| 1925 |
+
"step": 2820
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 4.62,
|
| 1929 |
+
"learning_rate": 0.0005861456483126111,
|
| 1930 |
+
"loss": 0.4399,
|
| 1931 |
+
"step": 2830
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 4.63,
|
| 1935 |
+
"learning_rate": 0.0005843694493783304,
|
| 1936 |
+
"loss": 0.4561,
|
| 1937 |
+
"step": 2840
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 4.65,
|
| 1941 |
+
"learning_rate": 0.0005825932504440498,
|
| 1942 |
+
"loss": 0.4394,
|
| 1943 |
+
"step": 2850
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 4.67,
|
| 1947 |
+
"learning_rate": 0.0005808170515097692,
|
| 1948 |
+
"loss": 0.4641,
|
| 1949 |
+
"step": 2860
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 4.68,
|
| 1953 |
+
"learning_rate": 0.0005790408525754885,
|
| 1954 |
+
"loss": 0.4162,
|
| 1955 |
+
"step": 2870
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 4.7,
|
| 1959 |
+
"learning_rate": 0.0005772646536412079,
|
| 1960 |
+
"loss": 0.4456,
|
| 1961 |
+
"step": 2880
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 4.71,
|
| 1965 |
+
"learning_rate": 0.0005754884547069273,
|
| 1966 |
+
"loss": 0.4588,
|
| 1967 |
+
"step": 2890
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 4.73,
|
| 1971 |
+
"learning_rate": 0.0005737122557726465,
|
| 1972 |
+
"loss": 0.4316,
|
| 1973 |
+
"step": 2900
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 4.73,
|
| 1977 |
+
"eval_loss": 0.428786039352417,
|
| 1978 |
+
"eval_runtime": 12.9621,
|
| 1979 |
+
"eval_samples_per_second": 90.341,
|
| 1980 |
+
"eval_steps_per_second": 11.341,
|
| 1981 |
+
"step": 2900
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 4.75,
|
| 1985 |
+
"learning_rate": 0.0005719360568383659,
|
| 1986 |
+
"loss": 0.4255,
|
| 1987 |
+
"step": 2910
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 4.76,
|
| 1991 |
+
"learning_rate": 0.0005701598579040853,
|
| 1992 |
+
"loss": 0.4353,
|
| 1993 |
+
"step": 2920
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 4.78,
|
| 1997 |
+
"learning_rate": 0.0005683836589698046,
|
| 1998 |
+
"loss": 0.4517,
|
| 1999 |
+
"step": 2930
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 4.8,
|
| 2003 |
+
"learning_rate": 0.000566607460035524,
|
| 2004 |
+
"loss": 0.4747,
|
| 2005 |
+
"step": 2940
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 4.81,
|
| 2009 |
+
"learning_rate": 0.0005648312611012434,
|
| 2010 |
+
"loss": 0.4213,
|
| 2011 |
+
"step": 2950
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 4.83,
|
| 2015 |
+
"learning_rate": 0.0005630550621669627,
|
| 2016 |
+
"loss": 0.437,
|
| 2017 |
+
"step": 2960
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 4.85,
|
| 2021 |
+
"learning_rate": 0.0005612788632326821,
|
| 2022 |
+
"loss": 0.4278,
|
| 2023 |
+
"step": 2970
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 4.86,
|
| 2027 |
+
"learning_rate": 0.0005595026642984015,
|
| 2028 |
+
"loss": 0.428,
|
| 2029 |
+
"step": 2980
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 4.88,
|
| 2033 |
+
"learning_rate": 0.0005577264653641208,
|
| 2034 |
+
"loss": 0.4256,
|
| 2035 |
+
"step": 2990
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 4.89,
|
| 2039 |
+
"learning_rate": 0.0005559502664298401,
|
| 2040 |
+
"loss": 0.4509,
|
| 2041 |
+
"step": 3000
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 4.89,
|
| 2045 |
+
"eval_loss": 0.4271390736103058,
|
| 2046 |
+
"eval_runtime": 12.8651,
|
| 2047 |
+
"eval_samples_per_second": 91.022,
|
| 2048 |
+
"eval_steps_per_second": 11.426,
|
| 2049 |
+
"step": 3000
|
| 2050 |
}
|
| 2051 |
],
|
| 2052 |
"logging_steps": 10,
|
| 2053 |
"max_steps": 6130,
|
| 2054 |
"num_train_epochs": 10,
|
| 2055 |
"save_steps": 500,
|
| 2056 |
+
"total_flos": 5664599237689344.0,
|
| 2057 |
"trial_name": null,
|
| 2058 |
"trial_params": null
|
| 2059 |
}
|