Training in progress, step 100000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +2 -2
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +2 -2
- last-checkpoint/rng_state_6.pth +2 -2
- last-checkpoint/rng_state_7.pth +2 -2
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +203 -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 202194449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9a3fc6351d09bd039d306f53b05fa03590011ea2849b43bd52529e0bd8514b9
|
3 |
size 202194449
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61dde823420dc7042c5bb2d699d112697bdd3010f540547619caa8b07f20d030
|
3 |
size 102501541
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:330f3cda58bd3cda7fe4052bcd097fef510e7fce1d130c443ec32e1f5486a104
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db9a8646bfa77c67b79c4b30fed86fd905de2821912180ec33d06ceff7f9e882
|
3 |
size 14503
|
last-checkpoint/rng_state_2.pth
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:dcf4e8fe75afcd199d62b4b9a4e3758f2eaf0ffa4730fdb2d98d4bb191801698
|
3 |
+
size 14439
|
last-checkpoint/rng_state_3.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 sha256:80c9489f4e58dc887e83e88882e5e1382e1ee3173dcbda417ffbbdcb858a9d65
|
3 |
size 14503
|
last-checkpoint/rng_state_4.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:cf0f5ebb927172859f9f7bd6df79a9456d1222e97acfe9ef9113e346912ff663
|
3 |
size 14503
|
last-checkpoint/rng_state_5.pth
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 sha256:1dae2826d240394f23ebead2538e7f8ab9151433f5d76c787e8de37065711b2b
|
3 |
+
size 14567
|
last-checkpoint/rng_state_6.pth
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 sha256:0d1a3d037a53cd82051029fcc53619c43fd8479867f8522cbd8ad58f9ba5a632
|
3 |
+
size 14503
|
last-checkpoint/rng_state_7.pth
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 sha256:2c028788cc8743c6a98b2e0f67f4bc6d1434318ea95a0cdb39b9728727ca1342
|
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 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7786e0d240c1817a80f936fe537093f6b0f81238abcccea2c0e618f1ac9e9438
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1806,11 +1806,211 @@
|
|
1806 |
"eval_samples_per_second": 1955.578,
|
1807 |
"eval_steps_per_second": 31.289,
|
1808 |
"step": 90000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1809 |
}
|
1810 |
],
|
1811 |
"max_steps": 500000,
|
1812 |
"num_train_epochs": 16,
|
1813 |
-
"total_flos":
|
1814 |
"trial_name": null,
|
1815 |
"trial_params": null
|
1816 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.063819357210699,
|
5 |
+
"global_step": 100000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1806 |
"eval_samples_per_second": 1955.578,
|
1807 |
"eval_steps_per_second": 31.289,
|
1808 |
"step": 90000
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 2.77,
|
1812 |
+
"learning_rate": 0.00028660537773622294,
|
1813 |
+
"loss": 0.3803,
|
1814 |
+
"step": 90500
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 2.79,
|
1818 |
+
"learning_rate": 0.00028640336867499143,
|
1819 |
+
"loss": 0.3796,
|
1820 |
+
"step": 91000
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 2.79,
|
1824 |
+
"eval_loss": 0.7904797196388245,
|
1825 |
+
"eval_runtime": 0.5244,
|
1826 |
+
"eval_samples_per_second": 1906.796,
|
1827 |
+
"eval_steps_per_second": 30.509,
|
1828 |
+
"step": 91000
|
1829 |
+
},
|
1830 |
+
{
|
1831 |
+
"epoch": 2.8,
|
1832 |
+
"learning_rate": 0.0002861999226075728,
|
1833 |
+
"loss": 0.3798,
|
1834 |
+
"step": 91500
|
1835 |
+
},
|
1836 |
+
{
|
1837 |
+
"epoch": 2.82,
|
1838 |
+
"learning_rate": 0.0002859950417588206,
|
1839 |
+
"loss": 0.3792,
|
1840 |
+
"step": 92000
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 2.82,
|
1844 |
+
"eval_loss": 0.7905736565589905,
|
1845 |
+
"eval_runtime": 0.5306,
|
1846 |
+
"eval_samples_per_second": 1884.737,
|
1847 |
+
"eval_steps_per_second": 30.156,
|
1848 |
+
"step": 92000
|
1849 |
+
},
|
1850 |
+
{
|
1851 |
+
"epoch": 2.83,
|
1852 |
+
"learning_rate": 0.00028578872836927904,
|
1853 |
+
"loss": 0.3788,
|
1854 |
+
"step": 92500
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 2.85,
|
1858 |
+
"learning_rate": 0.0002855809846951582,
|
1859 |
+
"loss": 0.3789,
|
1860 |
+
"step": 93000
|
1861 |
+
},
|
1862 |
+
{
|
1863 |
+
"epoch": 2.85,
|
1864 |
+
"eval_loss": 0.7809098958969116,
|
1865 |
+
"eval_runtime": 0.5414,
|
1866 |
+
"eval_samples_per_second": 1847.16,
|
1867 |
+
"eval_steps_per_second": 29.555,
|
1868 |
+
"step": 93000
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 2.86,
|
1872 |
+
"learning_rate": 0.00028537181300830963,
|
1873 |
+
"loss": 0.3782,
|
1874 |
+
"step": 93500
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 2.88,
|
1878 |
+
"learning_rate": 0.0002851612155962014,
|
1879 |
+
"loss": 0.3784,
|
1880 |
+
"step": 94000
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 2.88,
|
1884 |
+
"eval_loss": 0.7892218232154846,
|
1885 |
+
"eval_runtime": 0.516,
|
1886 |
+
"eval_samples_per_second": 1938.108,
|
1887 |
+
"eval_steps_per_second": 31.01,
|
1888 |
+
"step": 94000
|
1889 |
+
},
|
1890 |
+
{
|
1891 |
+
"epoch": 2.9,
|
1892 |
+
"learning_rate": 0.0002849491947618932,
|
1893 |
+
"loss": 0.3778,
|
1894 |
+
"step": 94500
|
1895 |
+
},
|
1896 |
+
{
|
1897 |
+
"epoch": 2.91,
|
1898 |
+
"learning_rate": 0.0002847357528240107,
|
1899 |
+
"loss": 0.3775,
|
1900 |
+
"step": 95000
|
1901 |
+
},
|
1902 |
+
{
|
1903 |
+
"epoch": 2.91,
|
1904 |
+
"eval_loss": 0.7847021818161011,
|
1905 |
+
"eval_runtime": 0.5181,
|
1906 |
+
"eval_samples_per_second": 1930.051,
|
1907 |
+
"eval_steps_per_second": 30.881,
|
1908 |
+
"step": 95000
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 2.93,
|
1912 |
+
"learning_rate": 0.0002845208921167208,
|
1913 |
+
"loss": 0.3773,
|
1914 |
+
"step": 95500
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 2.94,
|
1918 |
+
"learning_rate": 0.00028430461498970584,
|
1919 |
+
"loss": 0.3768,
|
1920 |
+
"step": 96000
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 2.94,
|
1924 |
+
"eval_loss": 0.78525710105896,
|
1925 |
+
"eval_runtime": 0.5373,
|
1926 |
+
"eval_samples_per_second": 1861.031,
|
1927 |
+
"eval_steps_per_second": 29.776,
|
1928 |
+
"step": 96000
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 2.96,
|
1932 |
+
"learning_rate": 0.00028408692380813775,
|
1933 |
+
"loss": 0.3768,
|
1934 |
+
"step": 96500
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 2.97,
|
1938 |
+
"learning_rate": 0.00028386782095265247,
|
1939 |
+
"loss": 0.3769,
|
1940 |
+
"step": 97000
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 2.97,
|
1944 |
+
"eval_loss": 0.7837897539138794,
|
1945 |
+
"eval_runtime": 0.5288,
|
1946 |
+
"eval_samples_per_second": 1891.025,
|
1947 |
+
"eval_steps_per_second": 30.256,
|
1948 |
+
"step": 97000
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 2.99,
|
1952 |
+
"learning_rate": 0.0002836473088193237,
|
1953 |
+
"loss": 0.3761,
|
1954 |
+
"step": 97500
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 3.0,
|
1958 |
+
"learning_rate": 0.00028342538981963677,
|
1959 |
+
"loss": 0.3797,
|
1960 |
+
"step": 98000
|
1961 |
+
},
|
1962 |
+
{
|
1963 |
+
"epoch": 3.0,
|
1964 |
+
"eval_loss": 0.7850324511528015,
|
1965 |
+
"eval_runtime": 0.5376,
|
1966 |
+
"eval_samples_per_second": 1860.245,
|
1967 |
+
"eval_steps_per_second": 29.764,
|
1968 |
+
"step": 98000
|
1969 |
+
},
|
1970 |
+
{
|
1971 |
+
"epoch": 3.02,
|
1972 |
+
"learning_rate": 0.0002832020663804624,
|
1973 |
+
"loss": 0.3752,
|
1974 |
+
"step": 98500
|
1975 |
+
},
|
1976 |
+
{
|
1977 |
+
"epoch": 3.03,
|
1978 |
+
"learning_rate": 0.00028297734094402986,
|
1979 |
+
"loss": 0.3747,
|
1980 |
+
"step": 99000
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 3.03,
|
1984 |
+
"eval_loss": 0.780020534992218,
|
1985 |
+
"eval_runtime": 0.5281,
|
1986 |
+
"eval_samples_per_second": 1893.464,
|
1987 |
+
"eval_steps_per_second": 30.295,
|
1988 |
+
"step": 99000
|
1989 |
+
},
|
1990 |
+
{
|
1991 |
+
"epoch": 3.05,
|
1992 |
+
"learning_rate": 0.0002827512159679005,
|
1993 |
+
"loss": 0.375,
|
1994 |
+
"step": 99500
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 3.06,
|
1998 |
+
"learning_rate": 0.00028252369392494086,
|
1999 |
+
"loss": 0.3746,
|
2000 |
+
"step": 100000
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 3.06,
|
2004 |
+
"eval_loss": 0.7855916619300842,
|
2005 |
+
"eval_runtime": 0.5271,
|
2006 |
+
"eval_samples_per_second": 1897.09,
|
2007 |
+
"eval_steps_per_second": 30.353,
|
2008 |
+
"step": 100000
|
2009 |
}
|
2010 |
],
|
2011 |
"max_steps": 500000,
|
2012 |
"num_train_epochs": 16,
|
2013 |
+
"total_flos": 3.1948474238890725e+21,
|
2014 |
"trial_name": null,
|
2015 |
"trial_params": null
|
2016 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61dde823420dc7042c5bb2d699d112697bdd3010f540547619caa8b07f20d030
|
3 |
size 102501541
|