Training in progress, step 28000, 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 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32cc85238f9b318459c5a80206968432f8685331234104eda2016524ba706b75
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e66d55b95606084af7dc0fbf657d700ecafd09b008231850874bdde638deda6
|
| 3 |
size 1082379659
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8553d3987609520495680f36a4682a760a418a930648ce46178a1399cde440b0
|
| 3 |
size 14645
|
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 sha256:71903ea651461945bbccce0e330f120093c2124a33f5b93ba51f8b9e386de7f9
|
| 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": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1880,6 +1880,318 @@
|
|
| 1880 |
"eval_samples_per_second": 35.576,
|
| 1881 |
"eval_steps_per_second": 8.894,
|
| 1882 |
"step": 24000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1883 |
}
|
| 1884 |
],
|
| 1885 |
"logging_steps": 100,
|
|
@@ -1899,7 +2211,7 @@
|
|
| 1899 |
"attributes": {}
|
| 1900 |
}
|
| 1901 |
},
|
| 1902 |
-
"total_flos":
|
| 1903 |
"train_batch_size": 22,
|
| 1904 |
"trial_name": null,
|
| 1905 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.36363636363636365,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 28000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1880 |
"eval_samples_per_second": 35.576,
|
| 1881 |
"eval_steps_per_second": 8.894,
|
| 1882 |
"step": 24000
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.312987012987013,
|
| 1886 |
+
"grad_norm": 0.21797960996627808,
|
| 1887 |
+
"learning_rate": 0.0008935749824785922,
|
| 1888 |
+
"loss": 2.8992,
|
| 1889 |
+
"step": 24100
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.3142857142857143,
|
| 1893 |
+
"grad_norm": 0.19554930925369263,
|
| 1894 |
+
"learning_rate": 0.0008926841258872131,
|
| 1895 |
+
"loss": 2.8771,
|
| 1896 |
+
"step": 24200
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 0.3155844155844156,
|
| 1900 |
+
"grad_norm": 0.18446357548236847,
|
| 1901 |
+
"learning_rate": 0.0008917900042572283,
|
| 1902 |
+
"loss": 2.8753,
|
| 1903 |
+
"step": 24300
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 0.3168831168831169,
|
| 1907 |
+
"grad_norm": 0.18406012654304504,
|
| 1908 |
+
"learning_rate": 0.0008908926250229633,
|
| 1909 |
+
"loss": 2.8819,
|
| 1910 |
+
"step": 24400
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 0.3181818181818182,
|
| 1914 |
+
"grad_norm": 0.21075041592121124,
|
| 1915 |
+
"learning_rate": 0.0008899919956458296,
|
| 1916 |
+
"loss": 2.8796,
|
| 1917 |
+
"step": 24500
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.3194805194805195,
|
| 1921 |
+
"grad_norm": 0.20150282979011536,
|
| 1922 |
+
"learning_rate": 0.0008890881236142624,
|
| 1923 |
+
"loss": 2.8611,
|
| 1924 |
+
"step": 24600
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 0.3207792207792208,
|
| 1928 |
+
"grad_norm": 0.43753939867019653,
|
| 1929 |
+
"learning_rate": 0.0008881810164436588,
|
| 1930 |
+
"loss": 2.8587,
|
| 1931 |
+
"step": 24700
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 0.3220779220779221,
|
| 1935 |
+
"grad_norm": 0.1800195425748825,
|
| 1936 |
+
"learning_rate": 0.0008872706816763148,
|
| 1937 |
+
"loss": 2.8797,
|
| 1938 |
+
"step": 24800
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 0.3233766233766234,
|
| 1942 |
+
"grad_norm": 0.2071843296289444,
|
| 1943 |
+
"learning_rate": 0.0008863571268813628,
|
| 1944 |
+
"loss": 2.8697,
|
| 1945 |
+
"step": 24900
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.3246753246753247,
|
| 1949 |
+
"grad_norm": 0.19320254027843475,
|
| 1950 |
+
"learning_rate": 0.0008854403596547088,
|
| 1951 |
+
"loss": 2.8938,
|
| 1952 |
+
"step": 25000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.3246753246753247,
|
| 1956 |
+
"eval_loss": 3.232848882675171,
|
| 1957 |
+
"eval_runtime": 15.6644,
|
| 1958 |
+
"eval_samples_per_second": 36.771,
|
| 1959 |
+
"eval_steps_per_second": 9.193,
|
| 1960 |
+
"step": 25000
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 0.32597402597402597,
|
| 1964 |
+
"grad_norm": 0.21449397504329681,
|
| 1965 |
+
"learning_rate": 0.000884520387618969,
|
| 1966 |
+
"loss": 2.8374,
|
| 1967 |
+
"step": 25100
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 0.32727272727272727,
|
| 1971 |
+
"grad_norm": 0.2025729864835739,
|
| 1972 |
+
"learning_rate": 0.0008835972184234066,
|
| 1973 |
+
"loss": 2.845,
|
| 1974 |
+
"step": 25200
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 0.32857142857142857,
|
| 1978 |
+
"grad_norm": 0.22090762853622437,
|
| 1979 |
+
"learning_rate": 0.000882670859743868,
|
| 1980 |
+
"loss": 2.8518,
|
| 1981 |
+
"step": 25300
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 0.32987012987012987,
|
| 1985 |
+
"grad_norm": 0.20626656711101532,
|
| 1986 |
+
"learning_rate": 0.0008817413192827191,
|
| 1987 |
+
"loss": 2.8299,
|
| 1988 |
+
"step": 25400
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 0.33116883116883117,
|
| 1992 |
+
"grad_norm": 0.18527238070964813,
|
| 1993 |
+
"learning_rate": 0.0008808086047687813,
|
| 1994 |
+
"loss": 2.8532,
|
| 1995 |
+
"step": 25500
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 0.33246753246753247,
|
| 1999 |
+
"grad_norm": 0.20959258079528809,
|
| 2000 |
+
"learning_rate": 0.0008798727239572676,
|
| 2001 |
+
"loss": 2.8656,
|
| 2002 |
+
"step": 25600
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 0.33376623376623377,
|
| 2006 |
+
"grad_norm": 0.2122378945350647,
|
| 2007 |
+
"learning_rate": 0.000878933684629717,
|
| 2008 |
+
"loss": 2.8532,
|
| 2009 |
+
"step": 25700
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 0.33506493506493507,
|
| 2013 |
+
"grad_norm": 0.18408456444740295,
|
| 2014 |
+
"learning_rate": 0.0008779914945939311,
|
| 2015 |
+
"loss": 2.8639,
|
| 2016 |
+
"step": 25800
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 0.33636363636363636,
|
| 2020 |
+
"grad_norm": 0.20426695048809052,
|
| 2021 |
+
"learning_rate": 0.0008770461616839082,
|
| 2022 |
+
"loss": 2.865,
|
| 2023 |
+
"step": 25900
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 0.33766233766233766,
|
| 2027 |
+
"grad_norm": 0.1808163821697235,
|
| 2028 |
+
"learning_rate": 0.0008760976937597787,
|
| 2029 |
+
"loss": 2.8481,
|
| 2030 |
+
"step": 26000
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.33766233766233766,
|
| 2034 |
+
"eval_loss": 3.214432716369629,
|
| 2035 |
+
"eval_runtime": 15.0454,
|
| 2036 |
+
"eval_samples_per_second": 38.284,
|
| 2037 |
+
"eval_steps_per_second": 9.571,
|
| 2038 |
+
"step": 26000
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 0.33896103896103896,
|
| 2042 |
+
"grad_norm": 0.20782601833343506,
|
| 2043 |
+
"learning_rate": 0.0008751460987077398,
|
| 2044 |
+
"loss": 2.8405,
|
| 2045 |
+
"step": 26100
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 0.34025974025974026,
|
| 2049 |
+
"grad_norm": 0.2266394942998886,
|
| 2050 |
+
"learning_rate": 0.0008741913844399896,
|
| 2051 |
+
"loss": 2.8304,
|
| 2052 |
+
"step": 26200
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 0.34155844155844156,
|
| 2056 |
+
"grad_norm": 0.215355783700943,
|
| 2057 |
+
"learning_rate": 0.0008732335588946612,
|
| 2058 |
+
"loss": 2.8749,
|
| 2059 |
+
"step": 26300
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 0.34285714285714286,
|
| 2063 |
+
"grad_norm": 0.17590366303920746,
|
| 2064 |
+
"learning_rate": 0.0008722726300357573,
|
| 2065 |
+
"loss": 2.8542,
|
| 2066 |
+
"step": 26400
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.34415584415584416,
|
| 2070 |
+
"grad_norm": 0.19376814365386963,
|
| 2071 |
+
"learning_rate": 0.0008713086058530832,
|
| 2072 |
+
"loss": 2.8636,
|
| 2073 |
+
"step": 26500
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.34545454545454546,
|
| 2077 |
+
"grad_norm": 0.19086168706417084,
|
| 2078 |
+
"learning_rate": 0.0008703414943621817,
|
| 2079 |
+
"loss": 2.8752,
|
| 2080 |
+
"step": 26600
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 0.34675324675324676,
|
| 2084 |
+
"grad_norm": 0.19386428594589233,
|
| 2085 |
+
"learning_rate": 0.0008693713036042643,
|
| 2086 |
+
"loss": 2.8595,
|
| 2087 |
+
"step": 26700
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 0.34805194805194806,
|
| 2091 |
+
"grad_norm": 0.20364010334014893,
|
| 2092 |
+
"learning_rate": 0.0008683980416461465,
|
| 2093 |
+
"loss": 2.8322,
|
| 2094 |
+
"step": 26800
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.34935064935064936,
|
| 2098 |
+
"grad_norm": 0.20115472376346588,
|
| 2099 |
+
"learning_rate": 0.0008674217165801797,
|
| 2100 |
+
"loss": 2.8271,
|
| 2101 |
+
"step": 26900
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.35064935064935066,
|
| 2105 |
+
"grad_norm": 0.19452853500843048,
|
| 2106 |
+
"learning_rate": 0.0008664423365241833,
|
| 2107 |
+
"loss": 2.8445,
|
| 2108 |
+
"step": 27000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.35064935064935066,
|
| 2112 |
+
"eval_loss": 3.206655263900757,
|
| 2113 |
+
"eval_runtime": 14.9037,
|
| 2114 |
+
"eval_samples_per_second": 38.648,
|
| 2115 |
+
"eval_steps_per_second": 9.662,
|
| 2116 |
+
"step": 27000
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.35194805194805195,
|
| 2120 |
+
"grad_norm": 0.29245325922966003,
|
| 2121 |
+
"learning_rate": 0.0008654599096213792,
|
| 2122 |
+
"loss": 2.8584,
|
| 2123 |
+
"step": 27100
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.35324675324675325,
|
| 2127 |
+
"grad_norm": 0.1941668838262558,
|
| 2128 |
+
"learning_rate": 0.0008644744440403214,
|
| 2129 |
+
"loss": 2.8146,
|
| 2130 |
+
"step": 27200
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.35454545454545455,
|
| 2134 |
+
"grad_norm": 0.20218811929225922,
|
| 2135 |
+
"learning_rate": 0.0008634859479748306,
|
| 2136 |
+
"loss": 2.8623,
|
| 2137 |
+
"step": 27300
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.35584415584415585,
|
| 2141 |
+
"grad_norm": 0.19882351160049438,
|
| 2142 |
+
"learning_rate": 0.0008624944296439246,
|
| 2143 |
+
"loss": 2.8491,
|
| 2144 |
+
"step": 27400
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.35714285714285715,
|
| 2148 |
+
"grad_norm": 0.19472059607505798,
|
| 2149 |
+
"learning_rate": 0.0008614998972917503,
|
| 2150 |
+
"loss": 2.8372,
|
| 2151 |
+
"step": 27500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.35844155844155845,
|
| 2155 |
+
"grad_norm": 0.20453399419784546,
|
| 2156 |
+
"learning_rate": 0.000860502359187515,
|
| 2157 |
+
"loss": 2.8228,
|
| 2158 |
+
"step": 27600
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.35974025974025975,
|
| 2162 |
+
"grad_norm": 0.20085613429546356,
|
| 2163 |
+
"learning_rate": 0.0008595018236254182,
|
| 2164 |
+
"loss": 2.8416,
|
| 2165 |
+
"step": 27700
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.36103896103896105,
|
| 2169 |
+
"grad_norm": 0.1953079253435135,
|
| 2170 |
+
"learning_rate": 0.0008584982989245822,
|
| 2171 |
+
"loss": 2.844,
|
| 2172 |
+
"step": 27800
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.36233766233766235,
|
| 2176 |
+
"grad_norm": 0.18861424922943115,
|
| 2177 |
+
"learning_rate": 0.0008574917934289829,
|
| 2178 |
+
"loss": 2.8586,
|
| 2179 |
+
"step": 27900
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.36363636363636365,
|
| 2183 |
+
"grad_norm": 0.2032879889011383,
|
| 2184 |
+
"learning_rate": 0.0008564823155073804,
|
| 2185 |
+
"loss": 2.8676,
|
| 2186 |
+
"step": 28000
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.36363636363636365,
|
| 2190 |
+
"eval_loss": 3.213535785675049,
|
| 2191 |
+
"eval_runtime": 15.9519,
|
| 2192 |
+
"eval_samples_per_second": 36.109,
|
| 2193 |
+
"eval_steps_per_second": 9.027,
|
| 2194 |
+
"step": 28000
|
| 2195 |
}
|
| 2196 |
],
|
| 2197 |
"logging_steps": 100,
|
|
|
|
| 2211 |
"attributes": {}
|
| 2212 |
}
|
| 2213 |
},
|
| 2214 |
+
"total_flos": 8.3354078674944e+17,
|
| 2215 |
"train_batch_size": 22,
|
| 2216 |
"trial_name": null,
|
| 2217 |
"trial_params": null
|