Training in progress, step 300, checkpoint
Browse files
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 sha256:50b7ed4bc6445e0f3a4b14a59436c85a68429db8277b8233a48f4f160b757d41
|
| 3 |
+
size 71078228
|
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 sha256:7c3ff73738c2ced9f71ca0e08c0b96b8e63fefb6a5254da60b6833f49da2a93b
|
| 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 sha256:14703588fc9c4c07c4dd895844b6404acd8f3d2be2c0e15a4873dacb9d6a3541
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": NaN,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1805,6 +1805,364 @@
|
|
| 1805 |
"eval_samples_per_second": 55.808,
|
| 1806 |
"eval_steps_per_second": 13.954,
|
| 1807 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1808 |
}
|
| 1809 |
],
|
| 1810 |
"logging_steps": 1,
|
|
@@ -1819,7 +2177,7 @@
|
|
| 1819 |
"early_stopping_threshold": 0.0
|
| 1820 |
},
|
| 1821 |
"attributes": {
|
| 1822 |
-
"early_stopping_patience_counter":
|
| 1823 |
}
|
| 1824 |
},
|
| 1825 |
"TrainerControl": {
|
|
@@ -1828,12 +2186,12 @@
|
|
| 1828 |
"should_evaluate": false,
|
| 1829 |
"should_log": false,
|
| 1830 |
"should_save": true,
|
| 1831 |
-
"should_training_stop":
|
| 1832 |
},
|
| 1833 |
"attributes": {}
|
| 1834 |
}
|
| 1835 |
},
|
| 1836 |
-
"total_flos": 2.
|
| 1837 |
"train_batch_size": 8,
|
| 1838 |
"trial_name": null,
|
| 1839 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": NaN,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.05394470667565745,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1805 |
"eval_samples_per_second": 55.808,
|
| 1806 |
"eval_steps_per_second": 13.954,
|
| 1807 |
"step": 250
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.0451337379186334,
|
| 1811 |
+
"grad_norm": NaN,
|
| 1812 |
+
"learning_rate": 5.128214216090478e-05,
|
| 1813 |
+
"loss": 0.0,
|
| 1814 |
+
"step": 251
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 0.04531355360755226,
|
| 1818 |
+
"grad_norm": NaN,
|
| 1819 |
+
"learning_rate": 5.0961652739384356e-05,
|
| 1820 |
+
"loss": 0.0,
|
| 1821 |
+
"step": 252
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.04549336929647112,
|
| 1825 |
+
"grad_norm": NaN,
|
| 1826 |
+
"learning_rate": 5.064112378808637e-05,
|
| 1827 |
+
"loss": 0.0,
|
| 1828 |
+
"step": 253
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 0.04567318498538998,
|
| 1832 |
+
"grad_norm": NaN,
|
| 1833 |
+
"learning_rate": 5.0320568482700556e-05,
|
| 1834 |
+
"loss": 0.0,
|
| 1835 |
+
"step": 254
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 0.045853000674308836,
|
| 1839 |
+
"grad_norm": NaN,
|
| 1840 |
+
"learning_rate": 5e-05,
|
| 1841 |
+
"loss": 0.0,
|
| 1842 |
+
"step": 255
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 0.04603281636322769,
|
| 1846 |
+
"grad_norm": NaN,
|
| 1847 |
+
"learning_rate": 4.967943151729945e-05,
|
| 1848 |
+
"loss": 0.0,
|
| 1849 |
+
"step": 256
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.04621263205214655,
|
| 1853 |
+
"grad_norm": NaN,
|
| 1854 |
+
"learning_rate": 4.935887621191364e-05,
|
| 1855 |
+
"loss": 0.0,
|
| 1856 |
+
"step": 257
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 0.04639244774106541,
|
| 1860 |
+
"grad_norm": NaN,
|
| 1861 |
+
"learning_rate": 4.903834726061565e-05,
|
| 1862 |
+
"loss": 0.0,
|
| 1863 |
+
"step": 258
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.046572263429984266,
|
| 1867 |
+
"grad_norm": NaN,
|
| 1868 |
+
"learning_rate": 4.871785783909523e-05,
|
| 1869 |
+
"loss": 0.8791,
|
| 1870 |
+
"step": 259
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 0.046752079118903125,
|
| 1874 |
+
"grad_norm": NaN,
|
| 1875 |
+
"learning_rate": 4.839742112141724e-05,
|
| 1876 |
+
"loss": 2.2549,
|
| 1877 |
+
"step": 260
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 0.046931894807821985,
|
| 1881 |
+
"grad_norm": NaN,
|
| 1882 |
+
"learning_rate": 4.807705027948008e-05,
|
| 1883 |
+
"loss": 0.0,
|
| 1884 |
+
"step": 261
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 0.047111710496740844,
|
| 1888 |
+
"grad_norm": NaN,
|
| 1889 |
+
"learning_rate": 4.775675848247427e-05,
|
| 1890 |
+
"loss": 0.0,
|
| 1891 |
+
"step": 262
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.047291526185659696,
|
| 1895 |
+
"grad_norm": NaN,
|
| 1896 |
+
"learning_rate": 4.743655889634105e-05,
|
| 1897 |
+
"loss": 0.0,
|
| 1898 |
+
"step": 263
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.047471341874578556,
|
| 1902 |
+
"grad_norm": NaN,
|
| 1903 |
+
"learning_rate": 4.711646468323129e-05,
|
| 1904 |
+
"loss": 0.0,
|
| 1905 |
+
"step": 264
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.047651157563497415,
|
| 1909 |
+
"grad_norm": NaN,
|
| 1910 |
+
"learning_rate": 4.679648900096436e-05,
|
| 1911 |
+
"loss": 0.0,
|
| 1912 |
+
"step": 265
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 0.047830973252416274,
|
| 1916 |
+
"grad_norm": NaN,
|
| 1917 |
+
"learning_rate": 4.64766450024873e-05,
|
| 1918 |
+
"loss": 0.0,
|
| 1919 |
+
"step": 266
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.048010788941335134,
|
| 1923 |
+
"grad_norm": NaN,
|
| 1924 |
+
"learning_rate": 4.6156945835334184e-05,
|
| 1925 |
+
"loss": 0.0,
|
| 1926 |
+
"step": 267
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 0.04819060463025399,
|
| 1930 |
+
"grad_norm": NaN,
|
| 1931 |
+
"learning_rate": 4.583740464108554e-05,
|
| 1932 |
+
"loss": 0.0,
|
| 1933 |
+
"step": 268
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.048370420319172845,
|
| 1937 |
+
"grad_norm": NaN,
|
| 1938 |
+
"learning_rate": 4.551803455482833e-05,
|
| 1939 |
+
"loss": 0.0,
|
| 1940 |
+
"step": 269
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.048550236008091704,
|
| 1944 |
+
"grad_norm": NaN,
|
| 1945 |
+
"learning_rate": 4.5198848704615914e-05,
|
| 1946 |
+
"loss": 0.0,
|
| 1947 |
+
"step": 270
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.048730051697010564,
|
| 1951 |
+
"grad_norm": NaN,
|
| 1952 |
+
"learning_rate": 4.487986021092844e-05,
|
| 1953 |
+
"loss": 0.0,
|
| 1954 |
+
"step": 271
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.04890986738592942,
|
| 1958 |
+
"grad_norm": NaN,
|
| 1959 |
+
"learning_rate": 4.4561082186133464e-05,
|
| 1960 |
+
"loss": 0.0,
|
| 1961 |
+
"step": 272
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.04908968307484828,
|
| 1965 |
+
"grad_norm": NaN,
|
| 1966 |
+
"learning_rate": 4.424252773394704e-05,
|
| 1967 |
+
"loss": 0.0,
|
| 1968 |
+
"step": 273
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.04926949876376714,
|
| 1972 |
+
"grad_norm": NaN,
|
| 1973 |
+
"learning_rate": 4.392420994889498e-05,
|
| 1974 |
+
"loss": 0.0,
|
| 1975 |
+
"step": 274
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.049449314452685994,
|
| 1979 |
+
"grad_norm": NaN,
|
| 1980 |
+
"learning_rate": 4.3606141915774693e-05,
|
| 1981 |
+
"loss": 0.0,
|
| 1982 |
+
"step": 275
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 0.04962913014160485,
|
| 1986 |
+
"grad_norm": NaN,
|
| 1987 |
+
"learning_rate": 4.328833670911724e-05,
|
| 1988 |
+
"loss": 0.0,
|
| 1989 |
+
"step": 276
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.04980894583052371,
|
| 1993 |
+
"grad_norm": NaN,
|
| 1994 |
+
"learning_rate": 4.297080739264987e-05,
|
| 1995 |
+
"loss": 0.0,
|
| 1996 |
+
"step": 277
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.04998876151944257,
|
| 2000 |
+
"grad_norm": NaN,
|
| 2001 |
+
"learning_rate": 4.265356701875911e-05,
|
| 2002 |
+
"loss": 0.0,
|
| 2003 |
+
"step": 278
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.05016857720836143,
|
| 2007 |
+
"grad_norm": NaN,
|
| 2008 |
+
"learning_rate": 4.23366286279542e-05,
|
| 2009 |
+
"loss": 0.0,
|
| 2010 |
+
"step": 279
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.05034839289728029,
|
| 2014 |
+
"grad_norm": NaN,
|
| 2015 |
+
"learning_rate": 4.2020005248331054e-05,
|
| 2016 |
+
"loss": 0.0,
|
| 2017 |
+
"step": 280
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.05052820858619914,
|
| 2021 |
+
"grad_norm": NaN,
|
| 2022 |
+
"learning_rate": 4.1703709895036625e-05,
|
| 2023 |
+
"loss": 0.0,
|
| 2024 |
+
"step": 281
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 0.050708024275118,
|
| 2028 |
+
"grad_norm": NaN,
|
| 2029 |
+
"learning_rate": 4.138775556973406e-05,
|
| 2030 |
+
"loss": 0.0,
|
| 2031 |
+
"step": 282
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 0.05088783996403686,
|
| 2035 |
+
"grad_norm": NaN,
|
| 2036 |
+
"learning_rate": 4.107215526006817e-05,
|
| 2037 |
+
"loss": 0.0,
|
| 2038 |
+
"step": 283
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 0.05106765565295572,
|
| 2042 |
+
"grad_norm": NaN,
|
| 2043 |
+
"learning_rate": 4.0756921939131565e-05,
|
| 2044 |
+
"loss": 0.0,
|
| 2045 |
+
"step": 284
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 0.05124747134187458,
|
| 2049 |
+
"grad_norm": NaN,
|
| 2050 |
+
"learning_rate": 4.04420685649314e-05,
|
| 2051 |
+
"loss": 0.0,
|
| 2052 |
+
"step": 285
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 0.05142728703079344,
|
| 2056 |
+
"grad_norm": NaN,
|
| 2057 |
+
"learning_rate": 4.012760807985665e-05,
|
| 2058 |
+
"loss": 0.0,
|
| 2059 |
+
"step": 286
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 0.05160710271971229,
|
| 2063 |
+
"grad_norm": NaN,
|
| 2064 |
+
"learning_rate": 3.981355341014623e-05,
|
| 2065 |
+
"loss": 0.0,
|
| 2066 |
+
"step": 287
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.05178691840863115,
|
| 2070 |
+
"grad_norm": NaN,
|
| 2071 |
+
"learning_rate": 3.9499917465357534e-05,
|
| 2072 |
+
"loss": 0.0,
|
| 2073 |
+
"step": 288
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.05196673409755001,
|
| 2077 |
+
"grad_norm": NaN,
|
| 2078 |
+
"learning_rate": 3.9186713137835826e-05,
|
| 2079 |
+
"loss": 0.0,
|
| 2080 |
+
"step": 289
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 0.05214654978646887,
|
| 2084 |
+
"grad_norm": NaN,
|
| 2085 |
+
"learning_rate": 3.887395330218429e-05,
|
| 2086 |
+
"loss": 0.0,
|
| 2087 |
+
"step": 290
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 0.05232636547538773,
|
| 2091 |
+
"grad_norm": NaN,
|
| 2092 |
+
"learning_rate": 3.856165081473474e-05,
|
| 2093 |
+
"loss": 0.0,
|
| 2094 |
+
"step": 291
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.05250618116430659,
|
| 2098 |
+
"grad_norm": NaN,
|
| 2099 |
+
"learning_rate": 3.8249818513019244e-05,
|
| 2100 |
+
"loss": 0.0,
|
| 2101 |
+
"step": 292
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.05268599685322544,
|
| 2105 |
+
"grad_norm": NaN,
|
| 2106 |
+
"learning_rate": 3.793846921524237e-05,
|
| 2107 |
+
"loss": 0.0,
|
| 2108 |
+
"step": 293
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.0528658125421443,
|
| 2112 |
+
"grad_norm": NaN,
|
| 2113 |
+
"learning_rate": 3.762761571975429e-05,
|
| 2114 |
+
"loss": 0.0,
|
| 2115 |
+
"step": 294
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 0.05304562823106316,
|
| 2119 |
+
"grad_norm": NaN,
|
| 2120 |
+
"learning_rate": 3.731727080452464e-05,
|
| 2121 |
+
"loss": 0.0,
|
| 2122 |
+
"step": 295
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 0.05322544391998202,
|
| 2126 |
+
"grad_norm": NaN,
|
| 2127 |
+
"learning_rate": 3.7007447226617366e-05,
|
| 2128 |
+
"loss": 0.0,
|
| 2129 |
+
"step": 296
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 0.05340525960890088,
|
| 2133 |
+
"grad_norm": NaN,
|
| 2134 |
+
"learning_rate": 3.6698157721666246e-05,
|
| 2135 |
+
"loss": 0.0,
|
| 2136 |
+
"step": 297
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 0.05358507529781974,
|
| 2140 |
+
"grad_norm": NaN,
|
| 2141 |
+
"learning_rate": 3.638941500335145e-05,
|
| 2142 |
+
"loss": 0.0,
|
| 2143 |
+
"step": 298
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 0.053764890986738596,
|
| 2147 |
+
"grad_norm": NaN,
|
| 2148 |
+
"learning_rate": 3.608123176287685e-05,
|
| 2149 |
+
"loss": 0.0,
|
| 2150 |
+
"step": 299
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 0.05394470667565745,
|
| 2154 |
+
"grad_norm": NaN,
|
| 2155 |
+
"learning_rate": 3.5773620668448384e-05,
|
| 2156 |
+
"loss": 0.0,
|
| 2157 |
+
"step": 300
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 0.05394470667565745,
|
| 2161 |
+
"eval_loss": NaN,
|
| 2162 |
+
"eval_runtime": 168.1974,
|
| 2163 |
+
"eval_samples_per_second": 55.691,
|
| 2164 |
+
"eval_steps_per_second": 13.924,
|
| 2165 |
+
"step": 300
|
| 2166 |
}
|
| 2167 |
],
|
| 2168 |
"logging_steps": 1,
|
|
|
|
| 2177 |
"early_stopping_threshold": 0.0
|
| 2178 |
},
|
| 2179 |
"attributes": {
|
| 2180 |
+
"early_stopping_patience_counter": 5
|
| 2181 |
}
|
| 2182 |
},
|
| 2183 |
"TrainerControl": {
|
|
|
|
| 2186 |
"should_evaluate": false,
|
| 2187 |
"should_log": false,
|
| 2188 |
"should_save": true,
|
| 2189 |
+
"should_training_stop": true
|
| 2190 |
},
|
| 2191 |
"attributes": {}
|
| 2192 |
}
|
| 2193 |
},
|
| 2194 |
+
"total_flos": 2.4041078390784e+16,
|
| 2195 |
"train_batch_size": 8,
|
| 2196 |
"trial_name": null,
|
| 2197 |
"trial_params": null
|