Training in progress, step 2340, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2384234968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e25481045a998d4e040b2d3114349e4f2ea96e62e32a39f2adeb51d25de7a48
|
| 3 |
size 2384234968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4768663315
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ffcde3cd0ac7235d16ff44cbb1d360ca8c7288c11306fb4a4310cba5b85f523
|
| 3 |
size 4768663315
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74b6236cf0b98164ed85bb41f9abc6098fd976f945ac9580a1a26ceb2561076b
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1808,6 +1808,312 @@
|
|
| 1808 |
"mean_token_accuracy": 0.8290239717811346,
|
| 1809 |
"num_tokens": 16371712.0,
|
| 1810 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1811 |
}
|
| 1812 |
],
|
| 1813 |
"logging_steps": 10,
|
|
@@ -1822,12 +2128,12 @@
|
|
| 1822 |
"should_evaluate": false,
|
| 1823 |
"should_log": false,
|
| 1824 |
"should_save": true,
|
| 1825 |
-
"should_training_stop":
|
| 1826 |
},
|
| 1827 |
"attributes": {}
|
| 1828 |
}
|
| 1829 |
},
|
| 1830 |
-
"total_flos":
|
| 1831 |
"train_batch_size": 2,
|
| 1832 |
"trial_name": null,
|
| 1833 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 2340,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1808 |
"mean_token_accuracy": 0.8290239717811346,
|
| 1809 |
"num_tokens": 16371712.0,
|
| 1810 |
"step": 2000
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.577478344562079,
|
| 1814 |
+
"grad_norm": 1.7604620456695557,
|
| 1815 |
+
"learning_rate": 1.5716999050332385e-06,
|
| 1816 |
+
"loss": 0.1638,
|
| 1817 |
+
"mean_token_accuracy": 0.7912915859371423,
|
| 1818 |
+
"num_tokens": 16453632.0,
|
| 1819 |
+
"step": 2010
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 2.5903111966634587,
|
| 1823 |
+
"grad_norm": 0.9279603958129883,
|
| 1824 |
+
"learning_rate": 1.5242165242165245e-06,
|
| 1825 |
+
"loss": 0.1439,
|
| 1826 |
+
"mean_token_accuracy": 0.8103840544819831,
|
| 1827 |
+
"num_tokens": 16535552.0,
|
| 1828 |
+
"step": 2020
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 2.603144048764838,
|
| 1832 |
+
"grad_norm": 1.5552164316177368,
|
| 1833 |
+
"learning_rate": 1.4767331433998102e-06,
|
| 1834 |
+
"loss": 0.1597,
|
| 1835 |
+
"mean_token_accuracy": 0.8110934458673,
|
| 1836 |
+
"num_tokens": 16617472.0,
|
| 1837 |
+
"step": 2030
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.6159769008662175,
|
| 1841 |
+
"grad_norm": 1.2231167554855347,
|
| 1842 |
+
"learning_rate": 1.429249762583096e-06,
|
| 1843 |
+
"loss": 0.16,
|
| 1844 |
+
"mean_token_accuracy": 0.7961350310593843,
|
| 1845 |
+
"num_tokens": 16699392.0,
|
| 1846 |
+
"step": 2040
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 2.628809752967597,
|
| 1850 |
+
"grad_norm": 1.4283727407455444,
|
| 1851 |
+
"learning_rate": 1.3817663817663818e-06,
|
| 1852 |
+
"loss": 0.1861,
|
| 1853 |
+
"mean_token_accuracy": 0.7857387486845255,
|
| 1854 |
+
"num_tokens": 16781312.0,
|
| 1855 |
+
"step": 2050
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 2.6416426050689767,
|
| 1859 |
+
"grad_norm": 1.2813409566879272,
|
| 1860 |
+
"learning_rate": 1.3342830009496678e-06,
|
| 1861 |
+
"loss": 0.1599,
|
| 1862 |
+
"mean_token_accuracy": 0.7960371825844049,
|
| 1863 |
+
"num_tokens": 16863232.0,
|
| 1864 |
+
"step": 2060
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.6544754571703564,
|
| 1868 |
+
"grad_norm": 1.814128041267395,
|
| 1869 |
+
"learning_rate": 1.2867996201329535e-06,
|
| 1870 |
+
"loss": 0.1769,
|
| 1871 |
+
"mean_token_accuracy": 0.7898116439580918,
|
| 1872 |
+
"num_tokens": 16945152.0,
|
| 1873 |
+
"step": 2070
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 2.6673083092717356,
|
| 1877 |
+
"grad_norm": 1.8410574197769165,
|
| 1878 |
+
"learning_rate": 1.2393162393162394e-06,
|
| 1879 |
+
"loss": 0.1609,
|
| 1880 |
+
"mean_token_accuracy": 0.8141511753201485,
|
| 1881 |
+
"num_tokens": 17027072.0,
|
| 1882 |
+
"step": 2080
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 2.680141161373115,
|
| 1886 |
+
"grad_norm": 1.4829483032226562,
|
| 1887 |
+
"learning_rate": 1.1918328584995251e-06,
|
| 1888 |
+
"loss": 0.1742,
|
| 1889 |
+
"mean_token_accuracy": 0.7898361060768366,
|
| 1890 |
+
"num_tokens": 17108992.0,
|
| 1891 |
+
"step": 2090
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 2.692974013474495,
|
| 1895 |
+
"grad_norm": 1.1964958906173706,
|
| 1896 |
+
"learning_rate": 1.144349477682811e-06,
|
| 1897 |
+
"loss": 0.1827,
|
| 1898 |
+
"mean_token_accuracy": 0.7777886476367712,
|
| 1899 |
+
"num_tokens": 17190912.0,
|
| 1900 |
+
"step": 2100
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.705806865575874,
|
| 1904 |
+
"grad_norm": 1.4900107383728027,
|
| 1905 |
+
"learning_rate": 1.096866096866097e-06,
|
| 1906 |
+
"loss": 0.1289,
|
| 1907 |
+
"mean_token_accuracy": 0.8270180996507406,
|
| 1908 |
+
"num_tokens": 17272832.0,
|
| 1909 |
+
"step": 2110
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 2.7186397176772537,
|
| 1913 |
+
"grad_norm": 1.7298692464828491,
|
| 1914 |
+
"learning_rate": 1.0493827160493827e-06,
|
| 1915 |
+
"loss": 0.1671,
|
| 1916 |
+
"mean_token_accuracy": 0.787377692013979,
|
| 1917 |
+
"num_tokens": 17354752.0,
|
| 1918 |
+
"step": 2120
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 2.7314725697786333,
|
| 1922 |
+
"grad_norm": 1.5013244152069092,
|
| 1923 |
+
"learning_rate": 1.0018993352326686e-06,
|
| 1924 |
+
"loss": 0.1639,
|
| 1925 |
+
"mean_token_accuracy": 0.7969789639115333,
|
| 1926 |
+
"num_tokens": 17436672.0,
|
| 1927 |
+
"step": 2130
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 2.744305421880013,
|
| 1931 |
+
"grad_norm": 1.1740142107009888,
|
| 1932 |
+
"learning_rate": 9.544159544159546e-07,
|
| 1933 |
+
"loss": 0.1611,
|
| 1934 |
+
"mean_token_accuracy": 0.794043542444706,
|
| 1935 |
+
"num_tokens": 17518592.0,
|
| 1936 |
+
"step": 2140
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 2.7571382739813926,
|
| 1940 |
+
"grad_norm": 1.4351530075073242,
|
| 1941 |
+
"learning_rate": 9.069325735992403e-07,
|
| 1942 |
+
"loss": 0.1642,
|
| 1943 |
+
"mean_token_accuracy": 0.8051247522234917,
|
| 1944 |
+
"num_tokens": 17600512.0,
|
| 1945 |
+
"step": 2150
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 2.7699711260827717,
|
| 1949 |
+
"grad_norm": 1.5310108661651611,
|
| 1950 |
+
"learning_rate": 8.594491927825262e-07,
|
| 1951 |
+
"loss": 0.1683,
|
| 1952 |
+
"mean_token_accuracy": 0.8000000014901161,
|
| 1953 |
+
"num_tokens": 17682432.0,
|
| 1954 |
+
"step": 2160
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 2.7828039781841514,
|
| 1958 |
+
"grad_norm": 1.3762239217758179,
|
| 1959 |
+
"learning_rate": 8.11965811965812e-07,
|
| 1960 |
+
"loss": 0.1641,
|
| 1961 |
+
"mean_token_accuracy": 0.7894324846565723,
|
| 1962 |
+
"num_tokens": 17764352.0,
|
| 1963 |
+
"step": 2170
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.795636830285531,
|
| 1967 |
+
"grad_norm": 1.4585622549057007,
|
| 1968 |
+
"learning_rate": 7.644824311490979e-07,
|
| 1969 |
+
"loss": 0.1591,
|
| 1970 |
+
"mean_token_accuracy": 0.7889432465657592,
|
| 1971 |
+
"num_tokens": 17846272.0,
|
| 1972 |
+
"step": 2180
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 2.8084696823869106,
|
| 1976 |
+
"grad_norm": 1.2188738584518433,
|
| 1977 |
+
"learning_rate": 7.169990503323837e-07,
|
| 1978 |
+
"loss": 0.1447,
|
| 1979 |
+
"mean_token_accuracy": 0.8227128185331821,
|
| 1980 |
+
"num_tokens": 17928192.0,
|
| 1981 |
+
"step": 2190
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 2.8213025344882903,
|
| 1985 |
+
"grad_norm": 1.2576043605804443,
|
| 1986 |
+
"learning_rate": 6.695156695156696e-07,
|
| 1987 |
+
"loss": 0.1439,
|
| 1988 |
+
"mean_token_accuracy": 0.8094300415366888,
|
| 1989 |
+
"num_tokens": 18010112.0,
|
| 1990 |
+
"step": 2200
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 2.8341353865896695,
|
| 1994 |
+
"grad_norm": 1.0408450365066528,
|
| 1995 |
+
"learning_rate": 6.220322886989554e-07,
|
| 1996 |
+
"loss": 0.2027,
|
| 1997 |
+
"mean_token_accuracy": 0.7656066533178091,
|
| 1998 |
+
"num_tokens": 18092032.0,
|
| 1999 |
+
"step": 2210
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 2.846968238691049,
|
| 2003 |
+
"grad_norm": 1.3711516857147217,
|
| 2004 |
+
"learning_rate": 5.745489078822413e-07,
|
| 2005 |
+
"loss": 0.1703,
|
| 2006 |
+
"mean_token_accuracy": 0.7800391372293234,
|
| 2007 |
+
"num_tokens": 18173952.0,
|
| 2008 |
+
"step": 2220
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 2.8598010907924287,
|
| 2012 |
+
"grad_norm": 1.3574531078338623,
|
| 2013 |
+
"learning_rate": 5.270655270655271e-07,
|
| 2014 |
+
"loss": 0.1682,
|
| 2015 |
+
"mean_token_accuracy": 0.7911692764610052,
|
| 2016 |
+
"num_tokens": 18255872.0,
|
| 2017 |
+
"step": 2230
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 2.872633942893808,
|
| 2021 |
+
"grad_norm": 1.412182331085205,
|
| 2022 |
+
"learning_rate": 4.795821462488129e-07,
|
| 2023 |
+
"loss": 0.1805,
|
| 2024 |
+
"mean_token_accuracy": 0.788820942863822,
|
| 2025 |
+
"num_tokens": 18337792.0,
|
| 2026 |
+
"step": 2240
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.8854667949951875,
|
| 2030 |
+
"grad_norm": 1.5910438299179077,
|
| 2031 |
+
"learning_rate": 4.320987654320988e-07,
|
| 2032 |
+
"loss": 0.1588,
|
| 2033 |
+
"mean_token_accuracy": 0.8040606647729873,
|
| 2034 |
+
"num_tokens": 18419712.0,
|
| 2035 |
+
"step": 2250
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 2.898299647096567,
|
| 2039 |
+
"grad_norm": 1.3554024696350098,
|
| 2040 |
+
"learning_rate": 3.846153846153847e-07,
|
| 2041 |
+
"loss": 0.1601,
|
| 2042 |
+
"mean_token_accuracy": 0.801565557718277,
|
| 2043 |
+
"num_tokens": 18501632.0,
|
| 2044 |
+
"step": 2260
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 2.911132499197947,
|
| 2048 |
+
"grad_norm": 1.2987529039382935,
|
| 2049 |
+
"learning_rate": 3.371320037986705e-07,
|
| 2050 |
+
"loss": 0.1377,
|
| 2051 |
+
"mean_token_accuracy": 0.8144080229103565,
|
| 2052 |
+
"num_tokens": 18583552.0,
|
| 2053 |
+
"step": 2270
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 2.9239653512993264,
|
| 2057 |
+
"grad_norm": 1.268310308456421,
|
| 2058 |
+
"learning_rate": 2.8964862298195633e-07,
|
| 2059 |
+
"loss": 0.1426,
|
| 2060 |
+
"mean_token_accuracy": 0.8171110570430755,
|
| 2061 |
+
"num_tokens": 18665472.0,
|
| 2062 |
+
"step": 2280
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 2.9367982034007056,
|
| 2066 |
+
"grad_norm": 1.5489550828933716,
|
| 2067 |
+
"learning_rate": 2.4216524216524215e-07,
|
| 2068 |
+
"loss": 0.1686,
|
| 2069 |
+
"mean_token_accuracy": 0.8061276923865079,
|
| 2070 |
+
"num_tokens": 18747392.0,
|
| 2071 |
+
"step": 2290
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 2.9496310555020853,
|
| 2075 |
+
"grad_norm": 1.5315167903900146,
|
| 2076 |
+
"learning_rate": 1.9468186134852803e-07,
|
| 2077 |
+
"loss": 0.1734,
|
| 2078 |
+
"mean_token_accuracy": 0.8045376718044281,
|
| 2079 |
+
"num_tokens": 18829312.0,
|
| 2080 |
+
"step": 2300
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 2.962463907603465,
|
| 2084 |
+
"grad_norm": 1.887633204460144,
|
| 2085 |
+
"learning_rate": 1.4719848053181388e-07,
|
| 2086 |
+
"loss": 0.1881,
|
| 2087 |
+
"mean_token_accuracy": 0.7852617412805557,
|
| 2088 |
+
"num_tokens": 18911232.0,
|
| 2089 |
+
"step": 2310
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.9752967597048445,
|
| 2093 |
+
"grad_norm": 1.3356051445007324,
|
| 2094 |
+
"learning_rate": 9.971509971509972e-08,
|
| 2095 |
+
"loss": 0.1747,
|
| 2096 |
+
"mean_token_accuracy": 0.7836839504539966,
|
| 2097 |
+
"num_tokens": 18993152.0,
|
| 2098 |
+
"step": 2320
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 2.988129611806224,
|
| 2102 |
+
"grad_norm": 1.3567869663238525,
|
| 2103 |
+
"learning_rate": 5.223171889838557e-08,
|
| 2104 |
+
"loss": 0.1577,
|
| 2105 |
+
"mean_token_accuracy": 0.8161815080791712,
|
| 2106 |
+
"num_tokens": 19075072.0,
|
| 2107 |
+
"step": 2330
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 3.0,
|
| 2111 |
+
"grad_norm": 3.3493268489837646,
|
| 2112 |
+
"learning_rate": 4.7483380816714155e-09,
|
| 2113 |
+
"loss": 0.1777,
|
| 2114 |
+
"mean_token_accuracy": 0.7969138461190302,
|
| 2115 |
+
"num_tokens": 19150848.0,
|
| 2116 |
+
"step": 2340
|
| 2117 |
}
|
| 2118 |
],
|
| 2119 |
"logging_steps": 10,
|
|
|
|
| 2128 |
"should_evaluate": false,
|
| 2129 |
"should_log": false,
|
| 2130 |
"should_save": true,
|
| 2131 |
+
"should_training_stop": true
|
| 2132 |
},
|
| 2133 |
"attributes": {}
|
| 2134 |
}
|
| 2135 |
},
|
| 2136 |
+
"total_flos": 5.061195179281613e+16,
|
| 2137 |
"train_batch_size": 2,
|
| 2138 |
"trial_name": null,
|
| 2139 |
"trial_params": null
|