Training in progress, step 70000
Browse files- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +2 -2
- last-checkpoint/trainer_state.json +303 -3
- pytorch_model.bin +1 -1
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 sha256:3eb55ec1aacbfeebe119e515b71d01fac6a80c1dc916333ed52358ff9464626e
|
| 3 |
+
size 100172997
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e319b3e22d458ba27ff2a2eb8537fae27cd2f8bcba6cd5bc802fb4266dab1c01
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b63f7cf635c5cd7e0a6a99be90b9c9040bc4b142713e70d6ed808fdd72cc930
|
| 3 |
size 14503
|
last-checkpoint/scheduler.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 sha256:5cce12b461956f7f82f9c60078f067ba7f5af96b281245752bc9e8d8eb78bb3a
|
| 3 |
+
size 246899880
|
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,
|
|
@@ -1806,11 +1806,311 @@
|
|
| 1806 |
"learning_rate": 0.0003716756671558975,
|
| 1807 |
"loss": 3.3157,
|
| 1808 |
"step": 60000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1809 |
}
|
| 1810 |
],
|
| 1811 |
"max_steps": 500000,
|
| 1812 |
"num_train_epochs": 3,
|
| 1813 |
-
"total_flos":
|
| 1814 |
"trial_name": null,
|
| 1815 |
"trial_params": null
|
| 1816 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.30081650193382037,
|
| 5 |
+
"global_step": 70000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1806 |
"learning_rate": 0.0003716756671558975,
|
| 1807 |
"loss": 3.3157,
|
| 1808 |
"step": 60000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.26,
|
| 1812 |
+
"learning_rate": 0.0003735891933646703,
|
| 1813 |
+
"loss": 3.2991,
|
| 1814 |
+
"step": 60200
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 0.26,
|
| 1818 |
+
"learning_rate": 0.00037550528852259106,
|
| 1819 |
+
"loss": 3.2628,
|
| 1820 |
+
"step": 60400
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 0.26,
|
| 1824 |
+
"learning_rate": 0.00037742391900952516,
|
| 1825 |
+
"loss": 3.2928,
|
| 1826 |
+
"step": 60600
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.26,
|
| 1830 |
+
"learning_rate": 0.0003793450511608526,
|
| 1831 |
+
"loss": 3.2828,
|
| 1832 |
+
"step": 60800
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 0.26,
|
| 1836 |
+
"learning_rate": 0.00038126865126805905,
|
| 1837 |
+
"loss": 3.2863,
|
| 1838 |
+
"step": 61000
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 0.26,
|
| 1842 |
+
"learning_rate": 0.0003831946855793267,
|
| 1843 |
+
"loss": 3.2951,
|
| 1844 |
+
"step": 61200
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.26,
|
| 1848 |
+
"learning_rate": 0.00038512312030012676,
|
| 1849 |
+
"loss": 3.2583,
|
| 1850 |
+
"step": 61400
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.26,
|
| 1854 |
+
"learning_rate": 0.0003870539215938128,
|
| 1855 |
+
"loss": 3.2872,
|
| 1856 |
+
"step": 61600
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 0.27,
|
| 1860 |
+
"learning_rate": 0.00038898705558221367,
|
| 1861 |
+
"loss": 3.2748,
|
| 1862 |
+
"step": 61800
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 0.27,
|
| 1866 |
+
"learning_rate": 0.00039092248834622883,
|
| 1867 |
+
"loss": 3.3026,
|
| 1868 |
+
"step": 62000
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 0.27,
|
| 1872 |
+
"learning_rate": 0.00039286018592642224,
|
| 1873 |
+
"loss": 3.2734,
|
| 1874 |
+
"step": 62200
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 0.27,
|
| 1878 |
+
"learning_rate": 0.00039480011432362007,
|
| 1879 |
+
"loss": 3.2849,
|
| 1880 |
+
"step": 62400
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 0.27,
|
| 1884 |
+
"learning_rate": 0.00039674223949950514,
|
| 1885 |
+
"loss": 3.2889,
|
| 1886 |
+
"step": 62600
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.27,
|
| 1890 |
+
"learning_rate": 0.0003986865273772159,
|
| 1891 |
+
"loss": 3.2938,
|
| 1892 |
+
"step": 62800
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.27,
|
| 1896 |
+
"learning_rate": 0.00040063294384194367,
|
| 1897 |
+
"loss": 3.2755,
|
| 1898 |
+
"step": 63000
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.27,
|
| 1902 |
+
"learning_rate": 0.0004025814547415307,
|
| 1903 |
+
"loss": 3.2774,
|
| 1904 |
+
"step": 63200
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 0.27,
|
| 1908 |
+
"learning_rate": 0.00040453202588707036,
|
| 1909 |
+
"loss": 3.2819,
|
| 1910 |
+
"step": 63400
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 0.27,
|
| 1914 |
+
"learning_rate": 0.0004064846230535067,
|
| 1915 |
+
"loss": 3.2867,
|
| 1916 |
+
"step": 63600
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 0.27,
|
| 1920 |
+
"learning_rate": 0.00040843921198023417,
|
| 1921 |
+
"loss": 3.2856,
|
| 1922 |
+
"step": 63800
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.28,
|
| 1926 |
+
"learning_rate": 0.0004103957583717001,
|
| 1927 |
+
"loss": 3.2932,
|
| 1928 |
+
"step": 64000
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.28,
|
| 1932 |
+
"learning_rate": 0.0004123542278980058,
|
| 1933 |
+
"loss": 3.272,
|
| 1934 |
+
"step": 64200
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.28,
|
| 1938 |
+
"learning_rate": 0.00041431458619550874,
|
| 1939 |
+
"loss": 3.2697,
|
| 1940 |
+
"step": 64400
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.28,
|
| 1944 |
+
"learning_rate": 0.00041627679886742527,
|
| 1945 |
+
"loss": 3.276,
|
| 1946 |
+
"step": 64600
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 0.28,
|
| 1950 |
+
"learning_rate": 0.0004182408314844355,
|
| 1951 |
+
"loss": 3.2732,
|
| 1952 |
+
"step": 64800
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.28,
|
| 1956 |
+
"learning_rate": 0.00042020664958528574,
|
| 1957 |
+
"loss": 3.2535,
|
| 1958 |
+
"step": 65000
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 0.28,
|
| 1962 |
+
"learning_rate": 0.0004221742186773941,
|
| 1963 |
+
"loss": 3.2791,
|
| 1964 |
+
"step": 65200
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 0.28,
|
| 1968 |
+
"learning_rate": 0.0004241435042374555,
|
| 1969 |
+
"loss": 3.2718,
|
| 1970 |
+
"step": 65400
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.28,
|
| 1974 |
+
"learning_rate": 0.0004261144717120477,
|
| 1975 |
+
"loss": 3.2672,
|
| 1976 |
+
"step": 65600
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.28,
|
| 1980 |
+
"learning_rate": 0.00042808708651823654,
|
| 1981 |
+
"loss": 3.2555,
|
| 1982 |
+
"step": 65800
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 0.28,
|
| 1986 |
+
"learning_rate": 0.00043006131404418424,
|
| 1987 |
+
"loss": 3.2717,
|
| 1988 |
+
"step": 66000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 0.28,
|
| 1992 |
+
"learning_rate": 0.00043203711964975595,
|
| 1993 |
+
"loss": 3.2497,
|
| 1994 |
+
"step": 66200
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 0.29,
|
| 1998 |
+
"learning_rate": 0.00043401446866712684,
|
| 1999 |
+
"loss": 3.2525,
|
| 2000 |
+
"step": 66400
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 0.29,
|
| 2004 |
+
"learning_rate": 0.000435993326401392,
|
| 2005 |
+
"loss": 3.2523,
|
| 2006 |
+
"step": 66600
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 0.29,
|
| 2010 |
+
"learning_rate": 0.0004379736581311737,
|
| 2011 |
+
"loss": 3.2431,
|
| 2012 |
+
"step": 66800
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.29,
|
| 2016 |
+
"learning_rate": 0.00043995542910923167,
|
| 2017 |
+
"loss": 3.2571,
|
| 2018 |
+
"step": 67000
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.29,
|
| 2022 |
+
"learning_rate": 0.0004419386045630716,
|
| 2023 |
+
"loss": 3.2445,
|
| 2024 |
+
"step": 67200
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 0.29,
|
| 2028 |
+
"learning_rate": 0.0004439231496955571,
|
| 2029 |
+
"loss": 3.2508,
|
| 2030 |
+
"step": 67400
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.29,
|
| 2034 |
+
"learning_rate": 0.00044590902968551834,
|
| 2035 |
+
"loss": 3.2435,
|
| 2036 |
+
"step": 67600
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 0.29,
|
| 2040 |
+
"learning_rate": 0.00044789620968836404,
|
| 2041 |
+
"loss": 3.2436,
|
| 2042 |
+
"step": 67800
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 0.29,
|
| 2046 |
+
"learning_rate": 0.0004498846548366927,
|
| 2047 |
+
"loss": 3.2533,
|
| 2048 |
+
"step": 68000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 0.29,
|
| 2052 |
+
"learning_rate": 0.0004518743302409047,
|
| 2053 |
+
"loss": 3.2523,
|
| 2054 |
+
"step": 68200
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.29,
|
| 2058 |
+
"learning_rate": 0.00045386520098981335,
|
| 2059 |
+
"loss": 3.2284,
|
| 2060 |
+
"step": 68400
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.29,
|
| 2064 |
+
"learning_rate": 0.0004558572321512592,
|
| 2065 |
+
"loss": 3.2285,
|
| 2066 |
+
"step": 68600
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.3,
|
| 2070 |
+
"learning_rate": 0.00045785038877272114,
|
| 2071 |
+
"loss": 3.2395,
|
| 2072 |
+
"step": 68800
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 0.3,
|
| 2076 |
+
"learning_rate": 0.00045984463588193104,
|
| 2077 |
+
"loss": 3.2592,
|
| 2078 |
+
"step": 69000
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 0.3,
|
| 2082 |
+
"learning_rate": 0.00046183993848748675,
|
| 2083 |
+
"loss": 3.2478,
|
| 2084 |
+
"step": 69200
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 0.3,
|
| 2088 |
+
"learning_rate": 0.0004638362615794662,
|
| 2089 |
+
"loss": 3.2303,
|
| 2090 |
+
"step": 69400
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 0.3,
|
| 2094 |
+
"learning_rate": 0.00046583357013004194,
|
| 2095 |
+
"loss": 3.242,
|
| 2096 |
+
"step": 69600
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.3,
|
| 2100 |
+
"learning_rate": 0.00046783182909409496,
|
| 2101 |
+
"loss": 3.2582,
|
| 2102 |
+
"step": 69800
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.3,
|
| 2106 |
+
"learning_rate": 0.00046983100340983056,
|
| 2107 |
+
"loss": 3.2461,
|
| 2108 |
+
"step": 70000
|
| 2109 |
}
|
| 2110 |
],
|
| 2111 |
"max_steps": 500000,
|
| 2112 |
"num_train_epochs": 3,
|
| 2113 |
+
"total_flos": 1.1156809875456e+17,
|
| 2114 |
"trial_name": null,
|
| 2115 |
"trial_params": null
|
| 2116 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e319b3e22d458ba27ff2a2eb8537fae27cd2f8bcba6cd5bc802fb4266dab1c01
|
| 3 |
size 146774203
|