error577 commited on
Commit
fb93847
·
verified ·
1 Parent(s): a0c152a

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:b81c89bf5a89dea220e294a4652d890349bf12553800a49024591d26ca2757a4
3
  size 323014168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628a3a2f90570264e045b0c66a72c37a82feda1da057e5fc7746cb522fe7b00b
3
  size 323014168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4536e6d49005fda0a95151faebf86801ba2e3b8da30b27d77d184347ee694363
3
- size 164464564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f6898c2c71088c4ef94a63a3c700b35c379e61100088540569424e9dffecf07
3
+ size 164465012
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:356dcfdc03c399d2e663c95cf1133f32813c707adc33ad61bc750dcc5222213f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3459ab28cb7371e035b392fdf49bc74d305172fd2f97aa43d33e13d80b0a5de7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:517cde929c0b918b0e53e0ffd764ecc43637194fb41b83640993bbae7c21d100
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f30fc7a303c581db8790c0d4f8638955c788c0b8516a8046c52d38b258639f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.39342138171195984,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-250",
4
- "epoch": 0.42435815828559303,
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": 2.941,
1806
  "eval_steps_per_second": 2.941,
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": 0
1823
  }
1824
  },
1825
  "TrainerControl": {
@@ -1833,7 +2191,7 @@
1833
  "attributes": {}
1834
  }
1835
  },
1836
- "total_flos": 1.6186741772569805e+17,
1837
  "train_batch_size": 1,
1838
  "trial_name": null,
1839
  "trial_params": null
 
1
  {
2
  "best_metric": 0.39342138171195984,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-250",
4
+ "epoch": 0.5092297899427116,
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": 2.941,
1806
  "eval_steps_per_second": 2.941,
1807
  "step": 250
1808
+ },
1809
+ {
1810
+ "epoch": 0.4260555909187354,
1811
+ "grad_norm": 0.3402771055698395,
1812
+ "learning_rate": 0.0002582310828261803,
1813
+ "loss": 0.955,
1814
+ "step": 251
1815
+ },
1816
+ {
1817
+ "epoch": 0.4277530235518778,
1818
+ "grad_norm": 0.2694092392921448,
1819
+ "learning_rate": 0.00025790097005079764,
1820
+ "loss": 0.7843,
1821
+ "step": 252
1822
+ },
1823
+ {
1824
+ "epoch": 0.42945045618502015,
1825
+ "grad_norm": 0.22484031319618225,
1826
+ "learning_rate": 0.00025756977071384455,
1827
+ "loss": 0.6626,
1828
+ "step": 253
1829
+ },
1830
+ {
1831
+ "epoch": 0.4311478888181625,
1832
+ "grad_norm": 0.25034627318382263,
1833
+ "learning_rate": 0.0002572374881504945,
1834
+ "loss": 0.8865,
1835
+ "step": 254
1836
+ },
1837
+ {
1838
+ "epoch": 0.4328453214513049,
1839
+ "grad_norm": 0.25369909405708313,
1840
+ "learning_rate": 0.00025690412570682946,
1841
+ "loss": 0.7099,
1842
+ "step": 255
1843
+ },
1844
+ {
1845
+ "epoch": 0.43454275408444726,
1846
+ "grad_norm": 0.22795934975147247,
1847
+ "learning_rate": 0.0002565696867398053,
1848
+ "loss": 0.7818,
1849
+ "step": 256
1850
+ },
1851
+ {
1852
+ "epoch": 0.43624018671758963,
1853
+ "grad_norm": 0.2158069759607315,
1854
+ "learning_rate": 0.00025623417461721884,
1855
+ "loss": 0.6434,
1856
+ "step": 257
1857
+ },
1858
+ {
1859
+ "epoch": 0.437937619350732,
1860
+ "grad_norm": 0.2332068681716919,
1861
+ "learning_rate": 0.00025589759271767344,
1862
+ "loss": 0.8126,
1863
+ "step": 258
1864
+ },
1865
+ {
1866
+ "epoch": 0.43963505198387437,
1867
+ "grad_norm": 0.21993213891983032,
1868
+ "learning_rate": 0.00025555994443054504,
1869
+ "loss": 0.6689,
1870
+ "step": 259
1871
+ },
1872
+ {
1873
+ "epoch": 0.44133248461701674,
1874
+ "grad_norm": 0.26037323474884033,
1875
+ "learning_rate": 0.0002552212331559482,
1876
+ "loss": 0.992,
1877
+ "step": 260
1878
+ },
1879
+ {
1880
+ "epoch": 0.4430299172501591,
1881
+ "grad_norm": 0.2357717603445053,
1882
+ "learning_rate": 0.00025488146230470156,
1883
+ "loss": 0.7212,
1884
+ "step": 261
1885
+ },
1886
+ {
1887
+ "epoch": 0.4447273498833015,
1888
+ "grad_norm": 0.22752051055431366,
1889
+ "learning_rate": 0.00025454063529829405,
1890
+ "loss": 0.7759,
1891
+ "step": 262
1892
+ },
1893
+ {
1894
+ "epoch": 0.44642478251644385,
1895
+ "grad_norm": 0.20641978085041046,
1896
+ "learning_rate": 0.0002541987555688496,
1897
+ "loss": 0.6029,
1898
+ "step": 263
1899
+ },
1900
+ {
1901
+ "epoch": 0.4481222151495863,
1902
+ "grad_norm": 1.728589415550232,
1903
+ "learning_rate": 0.0002538558265590934,
1904
+ "loss": 0.8527,
1905
+ "step": 264
1906
+ },
1907
+ {
1908
+ "epoch": 0.44981964778272865,
1909
+ "grad_norm": 0.3176920711994171,
1910
+ "learning_rate": 0.0002535118517223168,
1911
+ "loss": 1.0045,
1912
+ "step": 265
1913
+ },
1914
+ {
1915
+ "epoch": 0.451517080415871,
1916
+ "grad_norm": 0.22813205420970917,
1917
+ "learning_rate": 0.00025316683452234254,
1918
+ "loss": 0.5755,
1919
+ "step": 266
1920
+ },
1921
+ {
1922
+ "epoch": 0.4532145130490134,
1923
+ "grad_norm": 0.27417638897895813,
1924
+ "learning_rate": 0.00025282077843349,
1925
+ "loss": 0.6442,
1926
+ "step": 267
1927
+ },
1928
+ {
1929
+ "epoch": 0.45491194568215576,
1930
+ "grad_norm": 0.23180553317070007,
1931
+ "learning_rate": 0.00025247368694054017,
1932
+ "loss": 0.3961,
1933
+ "step": 268
1934
+ },
1935
+ {
1936
+ "epoch": 0.45660937831529813,
1937
+ "grad_norm": 0.21716707944869995,
1938
+ "learning_rate": 0.0002521255635387005,
1939
+ "loss": 0.5498,
1940
+ "step": 269
1941
+ },
1942
+ {
1943
+ "epoch": 0.4583068109484405,
1944
+ "grad_norm": 0.1608789563179016,
1945
+ "learning_rate": 0.0002517764117335698,
1946
+ "loss": 0.3229,
1947
+ "step": 270
1948
+ },
1949
+ {
1950
+ "epoch": 0.4600042435815829,
1951
+ "grad_norm": 0.06968680769205093,
1952
+ "learning_rate": 0.00025142623504110286,
1953
+ "loss": 0.0545,
1954
+ "step": 271
1955
+ },
1956
+ {
1957
+ "epoch": 0.46170167621472524,
1958
+ "grad_norm": 0.17753787338733673,
1959
+ "learning_rate": 0.0002510750369875752,
1960
+ "loss": 0.3944,
1961
+ "step": 272
1962
+ },
1963
+ {
1964
+ "epoch": 0.4633991088478676,
1965
+ "grad_norm": 0.1846492886543274,
1966
+ "learning_rate": 0.0002507228211095471,
1967
+ "loss": 0.4219,
1968
+ "step": 273
1969
+ },
1970
+ {
1971
+ "epoch": 0.46509654148101,
1972
+ "grad_norm": 0.12200163304805756,
1973
+ "learning_rate": 0.0002503695909538287,
1974
+ "loss": 0.1832,
1975
+ "step": 274
1976
+ },
1977
+ {
1978
+ "epoch": 0.46679397411415235,
1979
+ "grad_norm": 0.08617426455020905,
1980
+ "learning_rate": 0.00025001535007744373,
1981
+ "loss": 0.0833,
1982
+ "step": 275
1983
+ },
1984
+ {
1985
+ "epoch": 0.4684914067472947,
1986
+ "grad_norm": 0.10826346278190613,
1987
+ "learning_rate": 0.0002496601020475938,
1988
+ "loss": 0.1379,
1989
+ "step": 276
1990
+ },
1991
+ {
1992
+ "epoch": 0.4701888393804371,
1993
+ "grad_norm": 0.09130895137786865,
1994
+ "learning_rate": 0.00024930385044162276,
1995
+ "loss": 0.0909,
1996
+ "step": 277
1997
+ },
1998
+ {
1999
+ "epoch": 0.47188627201357947,
2000
+ "grad_norm": 0.01284122746437788,
2001
+ "learning_rate": 0.0002489465988469802,
2002
+ "loss": 0.0011,
2003
+ "step": 278
2004
+ },
2005
+ {
2006
+ "epoch": 0.47358370464672184,
2007
+ "grad_norm": 0.03364328294992447,
2008
+ "learning_rate": 0.0002485883508611858,
2009
+ "loss": 0.0151,
2010
+ "step": 279
2011
+ },
2012
+ {
2013
+ "epoch": 0.4752811372798642,
2014
+ "grad_norm": 0.005700011737644672,
2015
+ "learning_rate": 0.00024822911009179276,
2016
+ "loss": 0.0004,
2017
+ "step": 280
2018
+ },
2019
+ {
2020
+ "epoch": 0.4769785699130066,
2021
+ "grad_norm": 0.026785628870129585,
2022
+ "learning_rate": 0.0002478688801563516,
2023
+ "loss": 0.0022,
2024
+ "step": 281
2025
+ },
2026
+ {
2027
+ "epoch": 0.47867600254614895,
2028
+ "grad_norm": 0.014533424749970436,
2029
+ "learning_rate": 0.00024750766468237387,
2030
+ "loss": 0.0009,
2031
+ "step": 282
2032
+ },
2033
+ {
2034
+ "epoch": 0.4803734351792913,
2035
+ "grad_norm": 0.02565724588930607,
2036
+ "learning_rate": 0.0002471454673072953,
2037
+ "loss": 0.0015,
2038
+ "step": 283
2039
+ },
2040
+ {
2041
+ "epoch": 0.4820708678124337,
2042
+ "grad_norm": 0.01476586889475584,
2043
+ "learning_rate": 0.0002467822916784394,
2044
+ "loss": 0.0007,
2045
+ "step": 284
2046
+ },
2047
+ {
2048
+ "epoch": 0.48376830044557606,
2049
+ "grad_norm": 0.0030139784794300795,
2050
+ "learning_rate": 0.0002464181414529809,
2051
+ "loss": 0.0001,
2052
+ "step": 285
2053
+ },
2054
+ {
2055
+ "epoch": 0.48546573307871843,
2056
+ "grad_norm": 0.013711950741708279,
2057
+ "learning_rate": 0.00024605302029790836,
2058
+ "loss": 0.0002,
2059
+ "step": 286
2060
+ },
2061
+ {
2062
+ "epoch": 0.4871631657118608,
2063
+ "grad_norm": 0.0045742918737232685,
2064
+ "learning_rate": 0.00024568693188998776,
2065
+ "loss": 0.0002,
2066
+ "step": 287
2067
+ },
2068
+ {
2069
+ "epoch": 0.48886059834500317,
2070
+ "grad_norm": 0.01617550477385521,
2071
+ "learning_rate": 0.00024531987991572543,
2072
+ "loss": 0.0008,
2073
+ "step": 288
2074
+ },
2075
+ {
2076
+ "epoch": 0.49055803097814554,
2077
+ "grad_norm": 0.0015017741825431585,
2078
+ "learning_rate": 0.00024495186807133056,
2079
+ "loss": 0.0001,
2080
+ "step": 289
2081
+ },
2082
+ {
2083
+ "epoch": 0.4922554636112879,
2084
+ "grad_norm": 0.04141293093562126,
2085
+ "learning_rate": 0.00024458290006267833,
2086
+ "loss": 0.0021,
2087
+ "step": 290
2088
+ },
2089
+ {
2090
+ "epoch": 0.4939528962444303,
2091
+ "grad_norm": 0.03005625680088997,
2092
+ "learning_rate": 0.0002442129796052726,
2093
+ "loss": 0.0015,
2094
+ "step": 291
2095
+ },
2096
+ {
2097
+ "epoch": 0.49565032887757265,
2098
+ "grad_norm": 0.0004941977094858885,
2099
+ "learning_rate": 0.00024384211042420822,
2100
+ "loss": 0.0,
2101
+ "step": 292
2102
+ },
2103
+ {
2104
+ "epoch": 0.497347761510715,
2105
+ "grad_norm": 0.0018400073749944568,
2106
+ "learning_rate": 0.00024347029625413364,
2107
+ "loss": 0.0001,
2108
+ "step": 293
2109
+ },
2110
+ {
2111
+ "epoch": 0.4990451941438574,
2112
+ "grad_norm": 0.023964567109942436,
2113
+ "learning_rate": 0.00024309754083921354,
2114
+ "loss": 0.0008,
2115
+ "step": 294
2116
+ },
2117
+ {
2118
+ "epoch": 0.5007426267769998,
2119
+ "grad_norm": 0.00808011181652546,
2120
+ "learning_rate": 0.00024272384793309077,
2121
+ "loss": 0.0003,
2122
+ "step": 295
2123
+ },
2124
+ {
2125
+ "epoch": 0.5024400594101421,
2126
+ "grad_norm": 0.026506319642066956,
2127
+ "learning_rate": 0.0002423492212988487,
2128
+ "loss": 0.0011,
2129
+ "step": 296
2130
+ },
2131
+ {
2132
+ "epoch": 0.5041374920432845,
2133
+ "grad_norm": 0.0033183887135237455,
2134
+ "learning_rate": 0.0002419736647089735,
2135
+ "loss": 0.0001,
2136
+ "step": 297
2137
+ },
2138
+ {
2139
+ "epoch": 0.5058349246764269,
2140
+ "grad_norm": 0.0012288711732253432,
2141
+ "learning_rate": 0.00024159718194531572,
2142
+ "loss": 0.0001,
2143
+ "step": 298
2144
+ },
2145
+ {
2146
+ "epoch": 0.5075323573095692,
2147
+ "grad_norm": 0.001825229381211102,
2148
+ "learning_rate": 0.00024121977679905266,
2149
+ "loss": 0.0001,
2150
+ "step": 299
2151
+ },
2152
+ {
2153
+ "epoch": 0.5092297899427116,
2154
+ "grad_norm": 0.0013848728267475963,
2155
+ "learning_rate": 0.00024084145307064997,
2156
+ "loss": 0.0001,
2157
+ "step": 300
2158
+ },
2159
+ {
2160
+ "epoch": 0.5092297899427116,
2161
+ "eval_loss": 0.408105731010437,
2162
+ "eval_runtime": 65.5854,
2163
+ "eval_samples_per_second": 2.943,
2164
+ "eval_steps_per_second": 2.943,
2165
+ "step": 300
2166
  }
2167
  ],
2168
  "logging_steps": 1,
 
2177
  "early_stopping_threshold": 0.0
2178
  },
2179
  "attributes": {
2180
+ "early_stopping_patience_counter": 1
2181
  }
2182
  },
2183
  "TrainerControl": {
 
2191
  "attributes": {}
2192
  }
2193
  },
2194
+ "total_flos": 1.9420575090868224e+17,
2195
  "train_batch_size": 1,
2196
  "trial_name": null,
2197
  "trial_params": null