Commit
•
8de7203
1
Parent(s):
01dcb61
Training in progress, step 3000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +363 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Feb09_05-15-33_2f481ea0b382/1675919822.3009498/events.out.tfevents.1675919822.2f481ea0b382.229.1 +3 -0
- runs/Feb09_05-15-33_2f481ea0b382/events.out.tfevents.1675919822.2f481ea0b382.229.0 +3 -0
- runs/Feb09_05-19-49_2f481ea0b382/1675920014.2635813/events.out.tfevents.1675920014.2f481ea0b382.229.3 +3 -0
- runs/Feb09_05-19-49_2f481ea0b382/1675920384.8822913/events.out.tfevents.1675920384.2f481ea0b382.229.5 +3 -0
- runs/Feb09_05-19-49_2f481ea0b382/events.out.tfevents.1675920014.2f481ea0b382.229.2 +3 -0
- runs/Feb09_05-19-49_2f481ea0b382/events.out.tfevents.1675920384.2f481ea0b382.229.4 +3 -0
- training_args.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 4115013
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8fab46afba02b9664ca3eb5d4fc9d6f6e2f8b5882d6ad6a6f5bda047e6e1fbd
|
| 3 |
size 4115013
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:347082fb15486e1ce22829a5a9a17790976d005235f55b77b736bf422a4e49ef
|
| 3 |
size 2329702453
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b47b76e58d40ed6257704d7bde822b19860484ca61d1450fb6ff42df326b971d
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e2936137cf5142f34c072a19508ea41ce0d6a55cae7261f6c7cb486aa65afbe
|
| 3 |
size 627
|
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 +1806,371 @@
|
|
| 1806 |
"eval_samples_per_second": 0.241,
|
| 1807 |
"eval_steps_per_second": 0.241,
|
| 1808 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1809 |
}
|
| 1810 |
],
|
| 1811 |
"max_steps": 3542,
|
| 1812 |
"num_train_epochs": 7,
|
| 1813 |
-
"total_flos":
|
| 1814 |
"trial_name": null,
|
| 1815 |
"trial_params": null
|
| 1816 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.927135988164221,
|
| 5 |
+
"global_step": 3000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1806 |
"eval_samples_per_second": 0.241,
|
| 1807 |
"eval_steps_per_second": 0.241,
|
| 1808 |
"step": 2500
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 4.96,
|
| 1812 |
+
"learning_rate": 0.00014947856315179606,
|
| 1813 |
+
"loss": 0.1688,
|
| 1814 |
+
"step": 2510
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 4.98,
|
| 1818 |
+
"learning_rate": 0.00014803012746234068,
|
| 1819 |
+
"loss": 0.1385,
|
| 1820 |
+
"step": 2520
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 5.0,
|
| 1824 |
+
"learning_rate": 0.0001465816917728853,
|
| 1825 |
+
"loss": 0.1592,
|
| 1826 |
+
"step": 2530
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 5.02,
|
| 1830 |
+
"learning_rate": 0.0001451332560834299,
|
| 1831 |
+
"loss": 0.1014,
|
| 1832 |
+
"step": 2540
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 5.04,
|
| 1836 |
+
"learning_rate": 0.0001436848203939745,
|
| 1837 |
+
"loss": 0.0796,
|
| 1838 |
+
"step": 2550
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 5.06,
|
| 1842 |
+
"learning_rate": 0.00014223638470451912,
|
| 1843 |
+
"loss": 0.0981,
|
| 1844 |
+
"step": 2560
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 5.08,
|
| 1848 |
+
"learning_rate": 0.00014078794901506374,
|
| 1849 |
+
"loss": 0.093,
|
| 1850 |
+
"step": 2570
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 5.1,
|
| 1854 |
+
"learning_rate": 0.00013933951332560835,
|
| 1855 |
+
"loss": 0.1599,
|
| 1856 |
+
"step": 2580
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 5.12,
|
| 1860 |
+
"learning_rate": 0.00013789107763615297,
|
| 1861 |
+
"loss": 0.1223,
|
| 1862 |
+
"step": 2590
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 5.14,
|
| 1866 |
+
"learning_rate": 0.00013644264194669756,
|
| 1867 |
+
"loss": 0.1,
|
| 1868 |
+
"step": 2600
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 5.14,
|
| 1872 |
+
"eval_loss": 0.9408878087997437,
|
| 1873 |
+
"eval_rouge1": 0.12507936507936507,
|
| 1874 |
+
"eval_rouge2": 0.08333333333333333,
|
| 1875 |
+
"eval_rougeL": 0.12396825396825398,
|
| 1876 |
+
"eval_rougeLsum": 0.13111111111111112,
|
| 1877 |
+
"eval_runtime": 96.2103,
|
| 1878 |
+
"eval_samples_per_second": 0.208,
|
| 1879 |
+
"eval_steps_per_second": 0.208,
|
| 1880 |
+
"step": 2600
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 5.16,
|
| 1884 |
+
"learning_rate": 0.00013499420625724218,
|
| 1885 |
+
"loss": 0.1284,
|
| 1886 |
+
"step": 2610
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 5.18,
|
| 1890 |
+
"learning_rate": 0.0001335457705677868,
|
| 1891 |
+
"loss": 0.1523,
|
| 1892 |
+
"step": 2620
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 5.2,
|
| 1896 |
+
"learning_rate": 0.00013209733487833138,
|
| 1897 |
+
"loss": 0.1051,
|
| 1898 |
+
"step": 2630
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 5.22,
|
| 1902 |
+
"learning_rate": 0.00013064889918887603,
|
| 1903 |
+
"loss": 0.1216,
|
| 1904 |
+
"step": 2640
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 5.24,
|
| 1908 |
+
"learning_rate": 0.00012920046349942064,
|
| 1909 |
+
"loss": 0.1219,
|
| 1910 |
+
"step": 2650
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 5.26,
|
| 1914 |
+
"learning_rate": 0.00012775202780996523,
|
| 1915 |
+
"loss": 0.1482,
|
| 1916 |
+
"step": 2660
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 5.28,
|
| 1920 |
+
"learning_rate": 0.00012630359212050985,
|
| 1921 |
+
"loss": 0.1076,
|
| 1922 |
+
"step": 2670
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 5.3,
|
| 1926 |
+
"learning_rate": 0.00012485515643105447,
|
| 1927 |
+
"loss": 0.121,
|
| 1928 |
+
"step": 2680
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 5.32,
|
| 1932 |
+
"learning_rate": 0.00012340672074159908,
|
| 1933 |
+
"loss": 0.1448,
|
| 1934 |
+
"step": 2690
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 5.34,
|
| 1938 |
+
"learning_rate": 0.0001219582850521437,
|
| 1939 |
+
"loss": 0.1683,
|
| 1940 |
+
"step": 2700
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 5.34,
|
| 1944 |
+
"eval_loss": 0.9422550201416016,
|
| 1945 |
+
"eval_rouge1": 0.13818181818181818,
|
| 1946 |
+
"eval_rouge2": 0.0951010101010101,
|
| 1947 |
+
"eval_rougeL": 0.13713286713286715,
|
| 1948 |
+
"eval_rougeLsum": 0.14174825174825176,
|
| 1949 |
+
"eval_runtime": 96.365,
|
| 1950 |
+
"eval_samples_per_second": 0.208,
|
| 1951 |
+
"eval_steps_per_second": 0.208,
|
| 1952 |
+
"step": 2700
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 5.36,
|
| 1956 |
+
"learning_rate": 0.0001205098493626883,
|
| 1957 |
+
"loss": 0.103,
|
| 1958 |
+
"step": 2710
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 5.37,
|
| 1962 |
+
"learning_rate": 0.0001190614136732329,
|
| 1963 |
+
"loss": 0.1434,
|
| 1964 |
+
"step": 2720
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 5.39,
|
| 1968 |
+
"learning_rate": 0.00011761297798377752,
|
| 1969 |
+
"loss": 0.1419,
|
| 1970 |
+
"step": 2730
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 5.41,
|
| 1974 |
+
"learning_rate": 0.00011616454229432214,
|
| 1975 |
+
"loss": 0.1145,
|
| 1976 |
+
"step": 2740
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 5.43,
|
| 1980 |
+
"learning_rate": 0.00011471610660486674,
|
| 1981 |
+
"loss": 0.1302,
|
| 1982 |
+
"step": 2750
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 5.45,
|
| 1986 |
+
"learning_rate": 0.00011326767091541136,
|
| 1987 |
+
"loss": 0.0718,
|
| 1988 |
+
"step": 2760
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 5.47,
|
| 1992 |
+
"learning_rate": 0.00011181923522595596,
|
| 1993 |
+
"loss": 0.1166,
|
| 1994 |
+
"step": 2770
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 5.49,
|
| 1998 |
+
"learning_rate": 0.0001103707995365006,
|
| 1999 |
+
"loss": 0.1265,
|
| 2000 |
+
"step": 2780
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 5.51,
|
| 2004 |
+
"learning_rate": 0.0001089223638470452,
|
| 2005 |
+
"loss": 0.0972,
|
| 2006 |
+
"step": 2790
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 5.53,
|
| 2010 |
+
"learning_rate": 0.0001074739281575898,
|
| 2011 |
+
"loss": 0.1395,
|
| 2012 |
+
"step": 2800
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 5.53,
|
| 2016 |
+
"eval_loss": 0.9336325526237488,
|
| 2017 |
+
"eval_rouge1": 0.16115384615384615,
|
| 2018 |
+
"eval_rouge2": 0.12329545454545454,
|
| 2019 |
+
"eval_rougeL": 0.15999999999999998,
|
| 2020 |
+
"eval_rougeLsum": 0.16307692307692306,
|
| 2021 |
+
"eval_runtime": 93.5346,
|
| 2022 |
+
"eval_samples_per_second": 0.214,
|
| 2023 |
+
"eval_steps_per_second": 0.214,
|
| 2024 |
+
"step": 2800
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 5.55,
|
| 2028 |
+
"learning_rate": 0.00010602549246813442,
|
| 2029 |
+
"loss": 0.0808,
|
| 2030 |
+
"step": 2810
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 5.57,
|
| 2034 |
+
"learning_rate": 0.00010457705677867903,
|
| 2035 |
+
"loss": 0.1205,
|
| 2036 |
+
"step": 2820
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 5.59,
|
| 2040 |
+
"learning_rate": 0.00010312862108922364,
|
| 2041 |
+
"loss": 0.119,
|
| 2042 |
+
"step": 2830
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 5.61,
|
| 2046 |
+
"learning_rate": 0.00010168018539976825,
|
| 2047 |
+
"loss": 0.1357,
|
| 2048 |
+
"step": 2840
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 5.63,
|
| 2052 |
+
"learning_rate": 0.00010023174971031286,
|
| 2053 |
+
"loss": 0.1144,
|
| 2054 |
+
"step": 2850
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 5.65,
|
| 2058 |
+
"learning_rate": 9.878331402085749e-05,
|
| 2059 |
+
"loss": 0.138,
|
| 2060 |
+
"step": 2860
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 5.67,
|
| 2064 |
+
"learning_rate": 9.733487833140209e-05,
|
| 2065 |
+
"loss": 0.0998,
|
| 2066 |
+
"step": 2870
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 5.69,
|
| 2070 |
+
"learning_rate": 9.588644264194669e-05,
|
| 2071 |
+
"loss": 0.1437,
|
| 2072 |
+
"step": 2880
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 5.71,
|
| 2076 |
+
"learning_rate": 9.443800695249131e-05,
|
| 2077 |
+
"loss": 0.1053,
|
| 2078 |
+
"step": 2890
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 5.73,
|
| 2082 |
+
"learning_rate": 9.298957126303593e-05,
|
| 2083 |
+
"loss": 0.1067,
|
| 2084 |
+
"step": 2900
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 5.73,
|
| 2088 |
+
"eval_loss": 0.9290033578872681,
|
| 2089 |
+
"eval_rouge1": 0.2234265734265734,
|
| 2090 |
+
"eval_rouge2": 0.13156565656565655,
|
| 2091 |
+
"eval_rougeL": 0.21744755244755246,
|
| 2092 |
+
"eval_rougeLsum": 0.2169230769230769,
|
| 2093 |
+
"eval_runtime": 91.8958,
|
| 2094 |
+
"eval_samples_per_second": 0.218,
|
| 2095 |
+
"eval_steps_per_second": 0.218,
|
| 2096 |
+
"step": 2900
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 5.75,
|
| 2100 |
+
"learning_rate": 9.154113557358054e-05,
|
| 2101 |
+
"loss": 0.1225,
|
| 2102 |
+
"step": 2910
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 5.77,
|
| 2106 |
+
"learning_rate": 9.009269988412515e-05,
|
| 2107 |
+
"loss": 0.0867,
|
| 2108 |
+
"step": 2920
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 5.79,
|
| 2112 |
+
"learning_rate": 8.864426419466975e-05,
|
| 2113 |
+
"loss": 0.1325,
|
| 2114 |
+
"step": 2930
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 5.81,
|
| 2118 |
+
"learning_rate": 8.719582850521438e-05,
|
| 2119 |
+
"loss": 0.118,
|
| 2120 |
+
"step": 2940
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 5.83,
|
| 2124 |
+
"learning_rate": 8.574739281575898e-05,
|
| 2125 |
+
"loss": 0.112,
|
| 2126 |
+
"step": 2950
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 5.85,
|
| 2130 |
+
"learning_rate": 8.429895712630359e-05,
|
| 2131 |
+
"loss": 0.1326,
|
| 2132 |
+
"step": 2960
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 5.87,
|
| 2136 |
+
"learning_rate": 8.28505214368482e-05,
|
| 2137 |
+
"loss": 0.1506,
|
| 2138 |
+
"step": 2970
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 5.89,
|
| 2142 |
+
"learning_rate": 8.140208574739282e-05,
|
| 2143 |
+
"loss": 0.1499,
|
| 2144 |
+
"step": 2980
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 5.91,
|
| 2148 |
+
"learning_rate": 7.995365005793744e-05,
|
| 2149 |
+
"loss": 0.1092,
|
| 2150 |
+
"step": 2990
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 5.93,
|
| 2154 |
+
"learning_rate": 7.850521436848204e-05,
|
| 2155 |
+
"loss": 0.1104,
|
| 2156 |
+
"step": 3000
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 5.93,
|
| 2160 |
+
"eval_loss": 0.9244877696037292,
|
| 2161 |
+
"eval_rouge1": 0.2,
|
| 2162 |
+
"eval_rouge2": 0.1,
|
| 2163 |
+
"eval_rougeL": 0.19153846153846155,
|
| 2164 |
+
"eval_rougeLsum": 0.19153846153846155,
|
| 2165 |
+
"eval_runtime": 93.7022,
|
| 2166 |
+
"eval_samples_per_second": 0.213,
|
| 2167 |
+
"eval_steps_per_second": 0.213,
|
| 2168 |
+
"step": 3000
|
| 2169 |
}
|
| 2170 |
],
|
| 2171 |
"max_steps": 3542,
|
| 2172 |
"num_train_epochs": 7,
|
| 2173 |
+
"total_flos": 7.297038322401485e+16,
|
| 2174 |
"trial_name": null,
|
| 2175 |
"trial_params": null
|
| 2176 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c84070d0e82c96b5d90688a9eaac039d70060ac2fb04ad15294fe621d1085031
|
| 3 |
size 3643
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:347082fb15486e1ce22829a5a9a17790976d005235f55b77b736bf422a4e49ef
|
| 3 |
size 2329702453
|
runs/Feb09_05-15-33_2f481ea0b382/1675919822.3009498/events.out.tfevents.1675919822.2f481ea0b382.229.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2158c55d9c18b09babe3afd3628b7b9db9948dd64adc03d98aaeaf3fdedb19cc
|
| 3 |
+
size 5963
|
runs/Feb09_05-15-33_2f481ea0b382/events.out.tfevents.1675919822.2f481ea0b382.229.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39ea82e021df455d0b872a29b4241fd128157b9e12cd0e02049765435e647026
|
| 3 |
+
size 4373
|
runs/Feb09_05-19-49_2f481ea0b382/1675920014.2635813/events.out.tfevents.1675920014.2f481ea0b382.229.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9885aa1ad8d035a7245932173d30a177b54c4bea111ff4b8f24a0a39bb518372
|
| 3 |
+
size 5952
|
runs/Feb09_05-19-49_2f481ea0b382/1675920384.8822913/events.out.tfevents.1675920384.2f481ea0b382.229.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3cd46406fd5fcf0df98c5506929a6c5fdac00b065adf380344345fde71eb856
|
| 3 |
+
size 5952
|
runs/Feb09_05-19-49_2f481ea0b382/events.out.tfevents.1675920014.2f481ea0b382.229.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0666918e3bf6e4588614adc4681a6884f490b1b1ffe5fc3e674bc8d620aca324
|
| 3 |
+
size 4991
|
runs/Feb09_05-19-49_2f481ea0b382/events.out.tfevents.1675920384.2f481ea0b382.229.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fdd1cd3228b9e1861b5bb9722e297776fac3573f23a401d1935533fabc65f3f
|
| 3 |
+
size 14426
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c84070d0e82c96b5d90688a9eaac039d70060ac2fb04ad15294fe621d1085031
|
| 3 |
size 3643
|