error577 commited on
Commit
fe9f86e
·
verified ·
1 Parent(s): 739e873

Training in progress, step 300, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83bc9d32c440bb09b0e306b49ef66d95c54c199e5232e817229ddba46e25a087
3
  size 578859568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bbcf69b8eeb5cf9fd068e0ac17a52f2df71e8f11a6be6a22c8168f23eef03d9
3
  size 578859568
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:307bcb4f2a38b249970fda89b4d96744d49eb9460ddb7a85287c3abef80e335e
3
- size 294324372
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d6eff029a189244991acb874c7a5a97397aaf3b50735559ebb4a955f4b98f47
3
+ size 294324692
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c82ab9f2071d51a262a67414c9e0763e55a3b2ac7fdbba4135fff650dc8fe49
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ebec897dc147aad62d4d9cba9ec057687aa9ed3e810cfa1436fa460b983424
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d1f3538c1e3a5459eb655b11eb8bcebff4cdf068b69eab5cfd18947d9810e7a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698b407b737eae28d312187b0cfb0990e1352176888e7a2fdb41197b9abbc630
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7649185657501221,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-250",
4
- "epoch": 0.006949222034593227,
5
  "eval_steps": 50,
6
- "global_step": 250,
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": 11.517,
1806
  "eval_steps_per_second": 5.769,
1807
  "step": 250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1808
  }
1809
  ],
1810
  "logging_steps": 1,
@@ -1833,7 +2191,7 @@
1833
  "attributes": {}
1834
  }
1835
  },
1836
- "total_flos": 1.612399276720128e+16,
1837
  "train_batch_size": 2,
1838
  "trial_name": null,
1839
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7490311861038208,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-300",
4
+ "epoch": 0.008339066441511873,
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": 11.517,
1806
  "eval_steps_per_second": 5.769,
1807
  "step": 250
1808
+ },
1809
+ {
1810
+ "epoch": 0.0069770189227316,
1811
+ "grad_norm": 0.14372354745864868,
1812
+ "learning_rate": 0.0010256428432180956,
1813
+ "loss": 1.0122,
1814
+ "step": 251
1815
+ },
1816
+ {
1817
+ "epoch": 0.007004815810869973,
1818
+ "grad_norm": 0.11382071673870087,
1819
+ "learning_rate": 0.0010192330547876872,
1820
+ "loss": 0.8098,
1821
+ "step": 252
1822
+ },
1823
+ {
1824
+ "epoch": 0.007032612699008346,
1825
+ "grad_norm": 0.10247013717889786,
1826
+ "learning_rate": 0.0010128224757617274,
1827
+ "loss": 0.9305,
1828
+ "step": 253
1829
+ },
1830
+ {
1831
+ "epoch": 0.0070604095871467185,
1832
+ "grad_norm": 0.09587737172842026,
1833
+ "learning_rate": 0.0010064113696540112,
1834
+ "loss": 0.9049,
1835
+ "step": 254
1836
+ },
1837
+ {
1838
+ "epoch": 0.007088206475285092,
1839
+ "grad_norm": 0.0981241911649704,
1840
+ "learning_rate": 0.001,
1841
+ "loss": 0.7943,
1842
+ "step": 255
1843
+ },
1844
+ {
1845
+ "epoch": 0.007116003363423465,
1846
+ "grad_norm": 0.10372012108564377,
1847
+ "learning_rate": 0.0009935886303459888,
1848
+ "loss": 0.8079,
1849
+ "step": 256
1850
+ },
1851
+ {
1852
+ "epoch": 0.007143800251561838,
1853
+ "grad_norm": 0.0910145714879036,
1854
+ "learning_rate": 0.0009871775242382727,
1855
+ "loss": 0.7809,
1856
+ "step": 257
1857
+ },
1858
+ {
1859
+ "epoch": 0.007171597139700211,
1860
+ "grad_norm": 0.09489095211029053,
1861
+ "learning_rate": 0.0009807669452123128,
1862
+ "loss": 0.7955,
1863
+ "step": 258
1864
+ },
1865
+ {
1866
+ "epoch": 0.0071993940278385835,
1867
+ "grad_norm": 0.09354311227798462,
1868
+ "learning_rate": 0.0009743571567819046,
1869
+ "loss": 0.8035,
1870
+ "step": 259
1871
+ },
1872
+ {
1873
+ "epoch": 0.007227190915976956,
1874
+ "grad_norm": 0.09070082753896713,
1875
+ "learning_rate": 0.0009679484224283449,
1876
+ "loss": 0.7908,
1877
+ "step": 260
1878
+ },
1879
+ {
1880
+ "epoch": 0.007254987804115329,
1881
+ "grad_norm": 0.1037682518362999,
1882
+ "learning_rate": 0.0009615410055896016,
1883
+ "loss": 0.7739,
1884
+ "step": 261
1885
+ },
1886
+ {
1887
+ "epoch": 0.007282784692253702,
1888
+ "grad_norm": 0.09658119082450867,
1889
+ "learning_rate": 0.0009551351696494854,
1890
+ "loss": 0.8614,
1891
+ "step": 262
1892
+ },
1893
+ {
1894
+ "epoch": 0.007310581580392075,
1895
+ "grad_norm": 0.10361933708190918,
1896
+ "learning_rate": 0.0009487311779268209,
1897
+ "loss": 0.9021,
1898
+ "step": 263
1899
+ },
1900
+ {
1901
+ "epoch": 0.007338378468530448,
1902
+ "grad_norm": 0.08979956805706024,
1903
+ "learning_rate": 0.0009423292936646257,
1904
+ "loss": 0.7559,
1905
+ "step": 264
1906
+ },
1907
+ {
1908
+ "epoch": 0.007366175356668821,
1909
+ "grad_norm": 0.09771803766489029,
1910
+ "learning_rate": 0.0009359297800192872,
1911
+ "loss": 0.7717,
1912
+ "step": 265
1913
+ },
1914
+ {
1915
+ "epoch": 0.007393972244807194,
1916
+ "grad_norm": 0.10628974437713623,
1917
+ "learning_rate": 0.0009295329000497459,
1918
+ "loss": 0.8083,
1919
+ "step": 266
1920
+ },
1921
+ {
1922
+ "epoch": 0.007421769132945567,
1923
+ "grad_norm": 0.10804276913404465,
1924
+ "learning_rate": 0.0009231389167066836,
1925
+ "loss": 0.8077,
1926
+ "step": 267
1927
+ },
1928
+ {
1929
+ "epoch": 0.00744956602108394,
1930
+ "grad_norm": 0.13234536349773407,
1931
+ "learning_rate": 0.0009167480928217108,
1932
+ "loss": 0.8623,
1933
+ "step": 268
1934
+ },
1935
+ {
1936
+ "epoch": 0.0074773629092223124,
1937
+ "grad_norm": 0.10681891441345215,
1938
+ "learning_rate": 0.0009103606910965666,
1939
+ "loss": 0.7624,
1940
+ "step": 269
1941
+ },
1942
+ {
1943
+ "epoch": 0.007505159797360685,
1944
+ "grad_norm": 0.11654768884181976,
1945
+ "learning_rate": 0.0009039769740923182,
1946
+ "loss": 0.8082,
1947
+ "step": 270
1948
+ },
1949
+ {
1950
+ "epoch": 0.007532956685499058,
1951
+ "grad_norm": 0.1005023717880249,
1952
+ "learning_rate": 0.0008975972042185687,
1953
+ "loss": 0.7448,
1954
+ "step": 271
1955
+ },
1956
+ {
1957
+ "epoch": 0.007560753573637431,
1958
+ "grad_norm": 0.10492710024118423,
1959
+ "learning_rate": 0.0008912216437226692,
1960
+ "loss": 0.8734,
1961
+ "step": 272
1962
+ },
1963
+ {
1964
+ "epoch": 0.0075885504617758046,
1965
+ "grad_norm": 0.10636113584041595,
1966
+ "learning_rate": 0.0008848505546789408,
1967
+ "loss": 0.7397,
1968
+ "step": 273
1969
+ },
1970
+ {
1971
+ "epoch": 0.007616347349914177,
1972
+ "grad_norm": 0.0918545350432396,
1973
+ "learning_rate": 0.0008784841989778997,
1974
+ "loss": 0.6861,
1975
+ "step": 274
1976
+ },
1977
+ {
1978
+ "epoch": 0.00764414423805255,
1979
+ "grad_norm": 0.10185957700014114,
1980
+ "learning_rate": 0.0008721228383154939,
1981
+ "loss": 0.7906,
1982
+ "step": 275
1983
+ },
1984
+ {
1985
+ "epoch": 0.007671941126190923,
1986
+ "grad_norm": 0.09865249693393707,
1987
+ "learning_rate": 0.0008657667341823448,
1988
+ "loss": 0.6877,
1989
+ "step": 276
1990
+ },
1991
+ {
1992
+ "epoch": 0.007699738014329296,
1993
+ "grad_norm": 0.10265160351991653,
1994
+ "learning_rate": 0.0008594161478529974,
1995
+ "loss": 0.7361,
1996
+ "step": 277
1997
+ },
1998
+ {
1999
+ "epoch": 0.007727534902467669,
2000
+ "grad_norm": 0.10760695487260818,
2001
+ "learning_rate": 0.0008530713403751821,
2002
+ "loss": 0.6973,
2003
+ "step": 278
2004
+ },
2005
+ {
2006
+ "epoch": 0.007755331790606041,
2007
+ "grad_norm": 0.1106325089931488,
2008
+ "learning_rate": 0.000846732572559084,
2009
+ "loss": 0.7736,
2010
+ "step": 279
2011
+ },
2012
+ {
2013
+ "epoch": 0.007783128678744414,
2014
+ "grad_norm": 0.11260738223791122,
2015
+ "learning_rate": 0.000840400104966621,
2016
+ "loss": 0.7567,
2017
+ "step": 280
2018
+ },
2019
+ {
2020
+ "epoch": 0.007810925566882787,
2021
+ "grad_norm": 0.10231205821037292,
2022
+ "learning_rate": 0.0008340741979007324,
2023
+ "loss": 0.7018,
2024
+ "step": 281
2025
+ },
2026
+ {
2027
+ "epoch": 0.00783872245502116,
2028
+ "grad_norm": 0.10939161479473114,
2029
+ "learning_rate": 0.0008277551113946811,
2030
+ "loss": 0.5913,
2031
+ "step": 282
2032
+ },
2033
+ {
2034
+ "epoch": 0.007866519343159533,
2035
+ "grad_norm": 0.10841213166713715,
2036
+ "learning_rate": 0.0008214431052013634,
2037
+ "loss": 0.7421,
2038
+ "step": 283
2039
+ },
2040
+ {
2041
+ "epoch": 0.007894316231297906,
2042
+ "grad_norm": 0.11439742892980576,
2043
+ "learning_rate": 0.0008151384387826313,
2044
+ "loss": 0.7312,
2045
+ "step": 284
2046
+ },
2047
+ {
2048
+ "epoch": 0.007922113119436278,
2049
+ "grad_norm": 0.11929941177368164,
2050
+ "learning_rate": 0.0008088413712986279,
2051
+ "loss": 0.7529,
2052
+ "step": 285
2053
+ },
2054
+ {
2055
+ "epoch": 0.007949910007574652,
2056
+ "grad_norm": 0.11869197338819504,
2057
+ "learning_rate": 0.0008025521615971329,
2058
+ "loss": 0.6848,
2059
+ "step": 286
2060
+ },
2061
+ {
2062
+ "epoch": 0.007977706895713026,
2063
+ "grad_norm": 0.10041101276874542,
2064
+ "learning_rate": 0.0007962710682029245,
2065
+ "loss": 0.5243,
2066
+ "step": 287
2067
+ },
2068
+ {
2069
+ "epoch": 0.008005503783851398,
2070
+ "grad_norm": 0.11425133794546127,
2071
+ "learning_rate": 0.0007899983493071507,
2072
+ "loss": 0.6441,
2073
+ "step": 288
2074
+ },
2075
+ {
2076
+ "epoch": 0.008033300671989771,
2077
+ "grad_norm": 0.10552135854959488,
2078
+ "learning_rate": 0.0007837342627567166,
2079
+ "loss": 0.5675,
2080
+ "step": 289
2081
+ },
2082
+ {
2083
+ "epoch": 0.008061097560128143,
2084
+ "grad_norm": 0.12019749730825424,
2085
+ "learning_rate": 0.0007774790660436857,
2086
+ "loss": 0.7536,
2087
+ "step": 290
2088
+ },
2089
+ {
2090
+ "epoch": 0.008088894448266517,
2091
+ "grad_norm": 0.11838424205780029,
2092
+ "learning_rate": 0.0007712330162946947,
2093
+ "loss": 0.6558,
2094
+ "step": 291
2095
+ },
2096
+ {
2097
+ "epoch": 0.008116691336404889,
2098
+ "grad_norm": 0.11879291385412216,
2099
+ "learning_rate": 0.0007649963702603848,
2100
+ "loss": 0.6071,
2101
+ "step": 292
2102
+ },
2103
+ {
2104
+ "epoch": 0.008144488224543263,
2105
+ "grad_norm": 0.1303434818983078,
2106
+ "learning_rate": 0.0007587693843048475,
2107
+ "loss": 0.5558,
2108
+ "step": 293
2109
+ },
2110
+ {
2111
+ "epoch": 0.008172285112681634,
2112
+ "grad_norm": 0.1721266806125641,
2113
+ "learning_rate": 0.0007525523143950859,
2114
+ "loss": 0.6311,
2115
+ "step": 294
2116
+ },
2117
+ {
2118
+ "epoch": 0.008200082000820008,
2119
+ "grad_norm": 0.13676951825618744,
2120
+ "learning_rate": 0.0007463454160904928,
2121
+ "loss": 0.5886,
2122
+ "step": 295
2123
+ },
2124
+ {
2125
+ "epoch": 0.008227878888958382,
2126
+ "grad_norm": 0.16192977130413055,
2127
+ "learning_rate": 0.0007401489445323472,
2128
+ "loss": 0.746,
2129
+ "step": 296
2130
+ },
2131
+ {
2132
+ "epoch": 0.008255675777096754,
2133
+ "grad_norm": 0.12178271263837814,
2134
+ "learning_rate": 0.000733963154433325,
2135
+ "loss": 0.544,
2136
+ "step": 297
2137
+ },
2138
+ {
2139
+ "epoch": 0.008283472665235127,
2140
+ "grad_norm": 0.1465931534767151,
2141
+ "learning_rate": 0.0007277883000670289,
2142
+ "loss": 0.4949,
2143
+ "step": 298
2144
+ },
2145
+ {
2146
+ "epoch": 0.0083112695533735,
2147
+ "grad_norm": 0.15438374876976013,
2148
+ "learning_rate": 0.0007216246352575369,
2149
+ "loss": 0.6408,
2150
+ "step": 299
2151
+ },
2152
+ {
2153
+ "epoch": 0.008339066441511873,
2154
+ "grad_norm": 0.2604023814201355,
2155
+ "learning_rate": 0.0007154724133689676,
2156
+ "loss": 0.7431,
2157
+ "step": 300
2158
+ },
2159
+ {
2160
+ "epoch": 0.008339066441511873,
2161
+ "eval_loss": 0.7490311861038208,
2162
+ "eval_runtime": 50.0501,
2163
+ "eval_samples_per_second": 11.528,
2164
+ "eval_steps_per_second": 5.774,
2165
+ "step": 300
2166
  }
2167
  ],
2168
  "logging_steps": 1,
 
2191
  "attributes": {}
2192
  }
2193
  },
2194
+ "total_flos": 1.9262509085097984e+16,
2195
  "train_batch_size": 2,
2196
  "trial_name": null,
2197
  "trial_params": null