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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78d2e42563ecfd65d97699a72f4be839c4815a628d9aafa31de38f84519e5ebf
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6cf00bdfb1404208c2471c83afcc106348ceb61f5610d2591e45fff9be83487
|
| 3 |
size 938825803
|
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 sha256:09745e8006c686b7ca1b3f3ce96dc9d5406d13f67ce84984ece76a3860e0757b
|
| 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 sha256:1a7a45fe9f879fdefbf9d22a9cd4381d35f0cc9247510e28a7632ac32b2c74e6
|
| 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": 84.315,
|
| 1881 |
"eval_steps_per_second": 21.079,
|
| 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": 0.2545454545454545,
|
| 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": 84.315,
|
| 1881 |
"eval_steps_per_second": 21.079,
|
| 1882 |
"step": 24000
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.2190909090909091,
|
| 1886 |
+
"grad_norm": 0.15911774337291718,
|
| 1887 |
+
"learning_rate": 0.0008872361524354357,
|
| 1888 |
+
"loss": 2.8208258056640627,
|
| 1889 |
+
"step": 24100
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.22,
|
| 1893 |
+
"grad_norm": 0.14365383982658386,
|
| 1894 |
+
"learning_rate": 0.0008863299746814158,
|
| 1895 |
+
"loss": 2.82010986328125,
|
| 1896 |
+
"step": 24200
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 0.22090909090909092,
|
| 1900 |
+
"grad_norm": 0.16335056722164154,
|
| 1901 |
+
"learning_rate": 0.0008854206371409452,
|
| 1902 |
+
"loss": 2.863214416503906,
|
| 1903 |
+
"step": 24300
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 0.22181818181818183,
|
| 1907 |
+
"grad_norm": 0.15806064009666443,
|
| 1908 |
+
"learning_rate": 0.0008845081472514806,
|
| 1909 |
+
"loss": 2.8272698974609374,
|
| 1910 |
+
"step": 24400
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 0.22272727272727272,
|
| 1914 |
+
"grad_norm": 0.1631830632686615,
|
| 1915 |
+
"learning_rate": 0.0008835925124762616,
|
| 1916 |
+
"loss": 2.8286688232421877,
|
| 1917 |
+
"step": 24500
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.22363636363636363,
|
| 1921 |
+
"grad_norm": 0.142561137676239,
|
| 1922 |
+
"learning_rate": 0.0008826737403042499,
|
| 1923 |
+
"loss": 2.823035888671875,
|
| 1924 |
+
"step": 24600
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 0.22454545454545455,
|
| 1928 |
+
"grad_norm": 0.17523014545440674,
|
| 1929 |
+
"learning_rate": 0.0008817518382500677,
|
| 1930 |
+
"loss": 2.830491027832031,
|
| 1931 |
+
"step": 24700
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 0.22545454545454546,
|
| 1935 |
+
"grad_norm": 0.15598313510417938,
|
| 1936 |
+
"learning_rate": 0.0008808268138539369,
|
| 1937 |
+
"loss": 2.8227529907226563,
|
| 1938 |
+
"step": 24800
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 0.22636363636363635,
|
| 1942 |
+
"grad_norm": 0.1439158320426941,
|
| 1943 |
+
"learning_rate": 0.0008798986746816162,
|
| 1944 |
+
"loss": 2.8210317993164065,
|
| 1945 |
+
"step": 24900
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.22727272727272727,
|
| 1949 |
+
"grad_norm": 0.14227908849716187,
|
| 1950 |
+
"learning_rate": 0.0008789674283243409,
|
| 1951 |
+
"loss": 2.8191732788085937,
|
| 1952 |
+
"step": 25000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.22727272727272727,
|
| 1956 |
+
"eval_loss": 3.1780831813812256,
|
| 1957 |
+
"eval_runtime": 6.8053,
|
| 1958 |
+
"eval_samples_per_second": 84.639,
|
| 1959 |
+
"eval_steps_per_second": 21.16,
|
| 1960 |
+
"step": 25000
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 0.22818181818181818,
|
| 1964 |
+
"grad_norm": 0.15105608105659485,
|
| 1965 |
+
"learning_rate": 0.0008780330823987592,
|
| 1966 |
+
"loss": 2.8317742919921876,
|
| 1967 |
+
"step": 25100
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 0.2290909090909091,
|
| 1971 |
+
"grad_norm": 0.16510829329490662,
|
| 1972 |
+
"learning_rate": 0.0008770956445468713,
|
| 1973 |
+
"loss": 2.8396697998046876,
|
| 1974 |
+
"step": 25200
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 0.23,
|
| 1978 |
+
"grad_norm": 0.13736529648303986,
|
| 1979 |
+
"learning_rate": 0.0008761551224359657,
|
| 1980 |
+
"loss": 2.859419860839844,
|
| 1981 |
+
"step": 25300
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 0.2309090909090909,
|
| 1985 |
+
"grad_norm": 0.17783844470977783,
|
| 1986 |
+
"learning_rate": 0.0008752115237585567,
|
| 1987 |
+
"loss": 2.813878173828125,
|
| 1988 |
+
"step": 25400
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 0.2318181818181818,
|
| 1992 |
+
"grad_norm": 0.15228304266929626,
|
| 1993 |
+
"learning_rate": 0.0008742648562323228,
|
| 1994 |
+
"loss": 2.7972647094726564,
|
| 1995 |
+
"step": 25500
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 0.23272727272727273,
|
| 1999 |
+
"grad_norm": 0.17638841271400452,
|
| 2000 |
+
"learning_rate": 0.0008733151276000417,
|
| 2001 |
+
"loss": 2.84191650390625,
|
| 2002 |
+
"step": 25600
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 0.23363636363636364,
|
| 2006 |
+
"grad_norm": 0.15283086895942688,
|
| 2007 |
+
"learning_rate": 0.0008723623456295282,
|
| 2008 |
+
"loss": 2.8249298095703126,
|
| 2009 |
+
"step": 25700
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 0.23454545454545456,
|
| 2013 |
+
"grad_norm": 0.15044672787189484,
|
| 2014 |
+
"learning_rate": 0.0008714065181135701,
|
| 2015 |
+
"loss": 2.8220599365234373,
|
| 2016 |
+
"step": 25800
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 0.23545454545454544,
|
| 2020 |
+
"grad_norm": 0.149523064494133,
|
| 2021 |
+
"learning_rate": 0.0008704476528698649,
|
| 2022 |
+
"loss": 2.7989315795898437,
|
| 2023 |
+
"step": 25900
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 0.23636363636363636,
|
| 2027 |
+
"grad_norm": 0.15856775641441345,
|
| 2028 |
+
"learning_rate": 0.0008694857577409556,
|
| 2029 |
+
"loss": 2.7933050537109376,
|
| 2030 |
+
"step": 26000
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.23636363636363636,
|
| 2034 |
+
"eval_loss": 3.1705970764160156,
|
| 2035 |
+
"eval_runtime": 6.8357,
|
| 2036 |
+
"eval_samples_per_second": 84.264,
|
| 2037 |
+
"eval_steps_per_second": 21.066,
|
| 2038 |
+
"step": 26000
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 0.23727272727272727,
|
| 2042 |
+
"grad_norm": 0.15482839941978455,
|
| 2043 |
+
"learning_rate": 0.0008685208405941662,
|
| 2044 |
+
"loss": 2.8198681640625,
|
| 2045 |
+
"step": 26100
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 0.2381818181818182,
|
| 2049 |
+
"grad_norm": 0.14043229818344116,
|
| 2050 |
+
"learning_rate": 0.0008675529093215384,
|
| 2051 |
+
"loss": 2.8507424926757814,
|
| 2052 |
+
"step": 26200
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 0.2390909090909091,
|
| 2056 |
+
"grad_norm": 0.13602057099342346,
|
| 2057 |
+
"learning_rate": 0.0008665819718397658,
|
| 2058 |
+
"loss": 2.841172180175781,
|
| 2059 |
+
"step": 26300
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 0.24,
|
| 2063 |
+
"grad_norm": 0.1507735699415207,
|
| 2064 |
+
"learning_rate": 0.0008656080360901299,
|
| 2065 |
+
"loss": 2.8332550048828127,
|
| 2066 |
+
"step": 26400
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.2409090909090909,
|
| 2070 |
+
"grad_norm": 0.14570394158363342,
|
| 2071 |
+
"learning_rate": 0.0008646311100384352,
|
| 2072 |
+
"loss": 2.815726013183594,
|
| 2073 |
+
"step": 26500
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.24181818181818182,
|
| 2077 |
+
"grad_norm": 0.15119144320487976,
|
| 2078 |
+
"learning_rate": 0.0008636512016749436,
|
| 2079 |
+
"loss": 2.7973052978515627,
|
| 2080 |
+
"step": 26600
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 0.24272727272727274,
|
| 2084 |
+
"grad_norm": 0.1478470116853714,
|
| 2085 |
+
"learning_rate": 0.0008626683190143092,
|
| 2086 |
+
"loss": 2.8057537841796876,
|
| 2087 |
+
"step": 26700
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 0.24363636363636362,
|
| 2091 |
+
"grad_norm": 0.17405441403388977,
|
| 2092 |
+
"learning_rate": 0.0008616824700955132,
|
| 2093 |
+
"loss": 2.8201614379882813,
|
| 2094 |
+
"step": 26800
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.24454545454545454,
|
| 2098 |
+
"grad_norm": 0.1828102022409439,
|
| 2099 |
+
"learning_rate": 0.0008606936629817973,
|
| 2100 |
+
"loss": 2.817716064453125,
|
| 2101 |
+
"step": 26900
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.24545454545454545,
|
| 2105 |
+
"grad_norm": 0.1402510702610016,
|
| 2106 |
+
"learning_rate": 0.0008597019057605986,
|
| 2107 |
+
"loss": 2.8126416015625,
|
| 2108 |
+
"step": 27000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.24545454545454545,
|
| 2112 |
+
"eval_loss": 3.1654067039489746,
|
| 2113 |
+
"eval_runtime": 6.8224,
|
| 2114 |
+
"eval_samples_per_second": 84.428,
|
| 2115 |
+
"eval_steps_per_second": 21.107,
|
| 2116 |
+
"step": 27000
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.24636363636363637,
|
| 2120 |
+
"grad_norm": 0.15282770991325378,
|
| 2121 |
+
"learning_rate": 0.000858707206543483,
|
| 2122 |
+
"loss": 2.814878234863281,
|
| 2123 |
+
"step": 27100
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.24727272727272728,
|
| 2127 |
+
"grad_norm": 0.1374608278274536,
|
| 2128 |
+
"learning_rate": 0.0008577095734660788,
|
| 2129 |
+
"loss": 2.8010260009765626,
|
| 2130 |
+
"step": 27200
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.24818181818181817,
|
| 2134 |
+
"grad_norm": 0.14548851549625397,
|
| 2135 |
+
"learning_rate": 0.0008567090146880105,
|
| 2136 |
+
"loss": 2.828005676269531,
|
| 2137 |
+
"step": 27300
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.24909090909090909,
|
| 2141 |
+
"grad_norm": 0.1567397266626358,
|
| 2142 |
+
"learning_rate": 0.0008557055383928316,
|
| 2143 |
+
"loss": 2.78892578125,
|
| 2144 |
+
"step": 27400
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.25,
|
| 2148 |
+
"grad_norm": 0.17172624170780182,
|
| 2149 |
+
"learning_rate": 0.0008546991527879581,
|
| 2150 |
+
"loss": 2.8362548828125,
|
| 2151 |
+
"step": 27500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.2509090909090909,
|
| 2155 |
+
"grad_norm": 0.1834629327058792,
|
| 2156 |
+
"learning_rate": 0.000853689866104601,
|
| 2157 |
+
"loss": 2.799326171875,
|
| 2158 |
+
"step": 27600
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.25181818181818183,
|
| 2162 |
+
"grad_norm": 0.14964266121387482,
|
| 2163 |
+
"learning_rate": 0.0008526776865976997,
|
| 2164 |
+
"loss": 2.7806500244140624,
|
| 2165 |
+
"step": 27700
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.25272727272727274,
|
| 2169 |
+
"grad_norm": 0.1613718867301941,
|
| 2170 |
+
"learning_rate": 0.0008516626225458535,
|
| 2171 |
+
"loss": 2.8114141845703124,
|
| 2172 |
+
"step": 27800
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.25363636363636366,
|
| 2176 |
+
"grad_norm": 0.15746520459651947,
|
| 2177 |
+
"learning_rate": 0.0008506446822512541,
|
| 2178 |
+
"loss": 2.7960455322265627,
|
| 2179 |
+
"step": 27900
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.2545454545454545,
|
| 2183 |
+
"grad_norm": 0.14515548944473267,
|
| 2184 |
+
"learning_rate": 0.0008496238740396188,
|
| 2185 |
+
"loss": 2.848003234863281,
|
| 2186 |
+
"step": 28000
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.2545454545454545,
|
| 2190 |
+
"eval_loss": 3.1647140979766846,
|
| 2191 |
+
"eval_runtime": 6.7942,
|
| 2192 |
+
"eval_samples_per_second": 84.778,
|
| 2193 |
+
"eval_steps_per_second": 21.195,
|
| 2194 |
+
"step": 28000
|
| 2195 |
}
|
| 2196 |
],
|
| 2197 |
"logging_steps": 100,
|
|
|
|
| 2211 |
"attributes": {}
|
| 2212 |
}
|
| 2213 |
},
|
| 2214 |
+
"total_flos": 6.97608267890688e+17,
|
| 2215 |
"train_batch_size": 22,
|
| 2216 |
"trial_name": null,
|
| 2217 |
"trial_params": null
|