ErrorAI commited on
Commit
61d4802
·
verified ·
1 Parent(s): 59e6f49

Training in progress, step 363, 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:c1190f8ea07552d2cf7b233831d176ca439c3608aadb29d6f2969f6b5f9f853a
3
  size 17425352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70cc9bfc54e5704a0456169a978825609ac71b7b1c9c38de547b1a30937e3ae5
3
  size 17425352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cbe0698af4298918ce8cfa5d500475d02ffc884ef48ada3d64849c596a2f39a
3
  size 10252116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0ffc6285cb67ef2253eac085c595861b394d0f4ef88ea3bf8478c9a9b37965
3
  size 10252116
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed10d462332dfdf5894804ba3ded0da179db213feaaae2c6345c62710844c539
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5aecdf1cddcfbe1387576f944dfa673d525856b11837f99ce53a5e262b12e4b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf75957cd974601020f5995f38dbafb5420a0acbd3c06be292250cfb4e7d1857
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ac5c649b3b07ad0898720745fd06763ece21dd621fd1e465e3bf3dd609d7456
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.7536231884057971,
5
  "eval_steps": 500,
6
- "global_step": 273,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1918,6 +1918,644 @@
1918
  "learning_rate": 1.4800129365390281e-05,
1919
  "loss": 2.1697,
1920
  "step": 273
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1921
  }
1922
  ],
1923
  "logging_steps": 1,
@@ -1932,12 +2570,12 @@
1932
  "should_evaluate": false,
1933
  "should_log": false,
1934
  "should_save": true,
1935
- "should_training_stop": false
1936
  },
1937
  "attributes": {}
1938
  }
1939
  },
1940
- "total_flos": 8560382123704320.0,
1941
  "train_batch_size": 4,
1942
  "trial_name": null,
1943
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0020703933747412,
5
  "eval_steps": 500,
6
+ "global_step": 363,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1918
  "learning_rate": 1.4800129365390281e-05,
1919
  "loss": 2.1697,
1920
  "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.756383712905452,
1924
+ "grad_norm": 0.6054173707962036,
1925
+ "learning_rate": 1.4489873172477409e-05,
1926
+ "loss": 1.6706,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.759144237405107,
1931
+ "grad_norm": 0.7372981905937195,
1932
+ "learning_rate": 1.4182351512311237e-05,
1933
+ "loss": 1.7511,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.7619047619047619,
1938
+ "grad_norm": 0.6251423954963684,
1939
+ "learning_rate": 1.3877588066250453e-05,
1940
+ "loss": 1.423,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.7646652864044169,
1945
+ "grad_norm": 0.6341333985328674,
1946
+ "learning_rate": 1.357560630325158e-05,
1947
+ "loss": 1.9509,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.7674258109040718,
1952
+ "grad_norm": 0.6252625584602356,
1953
+ "learning_rate": 1.3276429478061741e-05,
1954
+ "loss": 1.992,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.7701863354037267,
1959
+ "grad_norm": 0.6359195709228516,
1960
+ "learning_rate": 1.2980080629427904e-05,
1961
+ "loss": 1.9086,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.7729468599033816,
1966
+ "grad_norm": 0.8791253566741943,
1967
+ "learning_rate": 1.2686582578322631e-05,
1968
+ "loss": 1.8734,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.7757073844030365,
1973
+ "grad_norm": 0.6764018535614014,
1974
+ "learning_rate": 1.2395957926186803e-05,
1975
+ "loss": 1.83,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.7784679089026915,
1980
+ "grad_norm": 0.752800703048706,
1981
+ "learning_rate": 1.2108229053189097e-05,
1982
+ "loss": 1.7646,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.7812284334023465,
1987
+ "grad_norm": 0.7744107842445374,
1988
+ "learning_rate": 1.1823418116502565e-05,
1989
+ "loss": 1.9604,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.7839889579020014,
1994
+ "grad_norm": 0.8803069591522217,
1995
+ "learning_rate": 1.1541547048598383e-05,
1996
+ "loss": 2.4493,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.7867494824016563,
2001
+ "grad_norm": 0.834362268447876,
2002
+ "learning_rate": 1.1262637555556903e-05,
2003
+ "loss": 2.0796,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.7895100069013112,
2008
+ "grad_norm": 1.0516443252563477,
2009
+ "learning_rate": 1.0986711115396058e-05,
2010
+ "loss": 2.3237,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.7922705314009661,
2015
+ "grad_norm": 0.7121506929397583,
2016
+ "learning_rate": 1.071378897641752e-05,
2017
+ "loss": 2.1616,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.7950310559006211,
2022
+ "grad_norm": 0.6001153588294983,
2023
+ "learning_rate": 1.044389215557034e-05,
2024
+ "loss": 1.7798,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.7977915804002761,
2029
+ "grad_norm": 0.8006875514984131,
2030
+ "learning_rate": 1.0177041436832507e-05,
2031
+ "loss": 2.3374,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.800552104899931,
2036
+ "grad_norm": 0.6787489652633667,
2037
+ "learning_rate": 9.913257369610473e-06,
2038
+ "loss": 2.1637,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.8033126293995859,
2043
+ "grad_norm": 0.8265159130096436,
2044
+ "learning_rate": 9.652560267156647e-06,
2045
+ "loss": 2.246,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.8060731538992408,
2050
+ "grad_norm": 1.0507712364196777,
2051
+ "learning_rate": 9.394970205005177e-06,
2052
+ "loss": 1.8864,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.8088336783988958,
2057
+ "grad_norm": 0.9701467752456665,
2058
+ "learning_rate": 9.140507019425981e-06,
2059
+ "loss": 2.4656,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.8115942028985508,
2064
+ "grad_norm": 0.9829404950141907,
2065
+ "learning_rate": 8.88919030589721e-06,
2066
+ "loss": 1.8753,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.8143547273982057,
2071
+ "grad_norm": 1.346711277961731,
2072
+ "learning_rate": 8.64103941759618e-06,
2073
+ "loss": 1.905,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.8171152518978606,
2078
+ "grad_norm": 1.1422017812728882,
2079
+ "learning_rate": 8.39607346390921e-06,
2080
+ "loss": 2.1189,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.8198757763975155,
2085
+ "grad_norm": 1.2060613632202148,
2086
+ "learning_rate": 8.15431130895991e-06,
2087
+ "loss": 1.5586,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.8226363008971704,
2092
+ "grad_norm": 1.0204120874404907,
2093
+ "learning_rate": 7.915771570156554e-06,
2094
+ "loss": 1.854,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.8253968253968254,
2099
+ "grad_norm": 1.0156620740890503,
2100
+ "learning_rate": 7.680472616758466e-06,
2101
+ "loss": 1.8096,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.8281573498964804,
2106
+ "grad_norm": 1.82632577419281,
2107
+ "learning_rate": 7.448432568461344e-06,
2108
+ "loss": 1.8969,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.8309178743961353,
2113
+ "grad_norm": 0.6277664303779602,
2114
+ "learning_rate": 7.219669294002002e-06,
2115
+ "loss": 2.484,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.8336783988957902,
2120
+ "grad_norm": 0.6709372401237488,
2121
+ "learning_rate": 6.9942004097823535e-06,
2122
+ "loss": 2.0705,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.8364389233954451,
2127
+ "grad_norm": 0.6607434153556824,
2128
+ "learning_rate": 6.7720432785127465e-06,
2129
+ "loss": 1.9909,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.8391994478951,
2134
+ "grad_norm": 0.5632132291793823,
2135
+ "learning_rate": 6.553215007874985e-06,
2136
+ "loss": 1.9455,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.841959972394755,
2141
+ "grad_norm": 0.541318416595459,
2142
+ "learning_rate": 6.337732449204886e-06,
2143
+ "loss": 2.0353,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.84472049689441,
2148
+ "grad_norm": 0.7076634168624878,
2149
+ "learning_rate": 6.1256121961945915e-06,
2150
+ "loss": 1.7995,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.8474810213940649,
2155
+ "grad_norm": 0.6370120644569397,
2156
+ "learning_rate": 5.916870583614792e-06,
2157
+ "loss": 1.9695,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.8502415458937198,
2162
+ "grad_norm": 0.5746281147003174,
2163
+ "learning_rate": 5.711523686056769e-06,
2164
+ "loss": 2.2275,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.8530020703933747,
2169
+ "grad_norm": 0.6816925406455994,
2170
+ "learning_rate": 5.509587316694536e-06,
2171
+ "loss": 1.8413,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.8557625948930296,
2176
+ "grad_norm": 0.7342681288719177,
2177
+ "learning_rate": 5.311077026067196e-06,
2178
+ "loss": 2.1986,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.8585231193926847,
2183
+ "grad_norm": 0.6418979167938232,
2184
+ "learning_rate": 5.116008100881348e-06,
2185
+ "loss": 1.8917,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.8612836438923396,
2190
+ "grad_norm": 0.6395264863967896,
2191
+ "learning_rate": 4.924395562833933e-06,
2192
+ "loss": 1.9768,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.8640441683919945,
2197
+ "grad_norm": 0.6867514252662659,
2198
+ "learning_rate": 4.736254167455473e-06,
2199
+ "loss": 2.2776,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.8668046928916494,
2204
+ "grad_norm": 0.5997049808502197,
2205
+ "learning_rate": 4.5515984029737615e-06,
2206
+ "loss": 1.8973,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.8695652173913043,
2211
+ "grad_norm": 0.7374957799911499,
2212
+ "learning_rate": 4.370442489198179e-06,
2213
+ "loss": 1.8923,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.8723257418909592,
2218
+ "grad_norm": 0.809410035610199,
2219
+ "learning_rate": 4.1928003764246934e-06,
2220
+ "loss": 2.3245,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.8750862663906143,
2225
+ "grad_norm": 0.5919080972671509,
2226
+ "learning_rate": 4.018685744361539e-06,
2227
+ "loss": 1.9618,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.8778467908902692,
2232
+ "grad_norm": 0.6320842504501343,
2233
+ "learning_rate": 3.84811200107581e-06,
2234
+ "loss": 1.6811,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.8806073153899241,
2239
+ "grad_norm": 0.7248905301094055,
2240
+ "learning_rate": 3.6810922819609352e-06,
2241
+ "loss": 2.2784,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.883367839889579,
2246
+ "grad_norm": 0.5608075261116028,
2247
+ "learning_rate": 3.517639448725163e-06,
2248
+ "loss": 1.6641,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.8861283643892339,
2253
+ "grad_norm": 0.6745538711547852,
2254
+ "learning_rate": 3.3577660884011485e-06,
2255
+ "loss": 2.1938,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.8888888888888888,
2260
+ "grad_norm": 0.6236209273338318,
2261
+ "learning_rate": 3.2014845123765734e-06,
2262
+ "loss": 1.7981,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.8916494133885439,
2267
+ "grad_norm": 0.7572169303894043,
2268
+ "learning_rate": 3.0488067554461818e-06,
2269
+ "loss": 1.9801,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.8944099378881988,
2274
+ "grad_norm": 0.5115662217140198,
2275
+ "learning_rate": 2.8997445748849716e-06,
2276
+ "loss": 1.6648,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.8971704623878537,
2281
+ "grad_norm": 0.7543956637382507,
2282
+ "learning_rate": 2.7543094495427913e-06,
2283
+ "loss": 1.8281,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.8999309868875086,
2288
+ "grad_norm": 0.5938908457756042,
2289
+ "learning_rate": 2.612512578960391e-06,
2290
+ "loss": 1.9528,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.9026915113871635,
2295
+ "grad_norm": 0.6712254881858826,
2296
+ "learning_rate": 2.474364882507002e-06,
2297
+ "loss": 2.0534,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.9054520358868184,
2302
+ "grad_norm": 0.5828601121902466,
2303
+ "learning_rate": 2.339876998539442e-06,
2304
+ "loss": 1.7284,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.9082125603864735,
2309
+ "grad_norm": 0.8522250056266785,
2310
+ "learning_rate": 2.2090592835828814e-06,
2311
+ "loss": 2.1892,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.9109730848861284,
2316
+ "grad_norm": 0.9318490028381348,
2317
+ "learning_rate": 2.081921811533366e-06,
2318
+ "loss": 2.1246,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.9137336093857833,
2323
+ "grad_norm": 0.7124171257019043,
2324
+ "learning_rate": 1.9584743728819686e-06,
2325
+ "loss": 1.8016,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.9164941338854382,
2330
+ "grad_norm": 0.9738188982009888,
2331
+ "learning_rate": 1.83872647396095e-06,
2332
+ "loss": 2.3653,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 0.9192546583850931,
2337
+ "grad_norm": 0.7715499401092529,
2338
+ "learning_rate": 1.7226873362116257e-06,
2339
+ "loss": 2.4177,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 0.9220151828847482,
2344
+ "grad_norm": 0.7315263748168945,
2345
+ "learning_rate": 1.6103658954742918e-06,
2346
+ "loss": 1.8725,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 0.9247757073844031,
2351
+ "grad_norm": 0.7532916069030762,
2352
+ "learning_rate": 1.5017708013000786e-06,
2353
+ "loss": 2.2835,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 0.927536231884058,
2358
+ "grad_norm": 0.7594407796859741,
2359
+ "learning_rate": 1.396910416284891e-06,
2360
+ "loss": 2.0195,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 0.9302967563837129,
2365
+ "grad_norm": 0.9144908785820007,
2366
+ "learning_rate": 1.2957928154254172e-06,
2367
+ "loss": 2.2633,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 0.9330572808833678,
2372
+ "grad_norm": 0.7762795090675354,
2373
+ "learning_rate": 1.1984257854973147e-06,
2374
+ "loss": 2.1501,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 0.9358178053830227,
2379
+ "grad_norm": 1.0061681270599365,
2380
+ "learning_rate": 1.1048168244555513e-06,
2381
+ "loss": 2.2689,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 0.9385783298826778,
2386
+ "grad_norm": 0.7763106822967529,
2387
+ "learning_rate": 1.0149731408569951e-06,
2388
+ "loss": 1.7844,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 0.9413388543823327,
2393
+ "grad_norm": 0.7826094031333923,
2394
+ "learning_rate": 9.289016533053696e-07,
2395
+ "loss": 1.741,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 0.9440993788819876,
2400
+ "grad_norm": 1.0212883949279785,
2401
+ "learning_rate": 8.46608989918396e-07,
2402
+ "loss": 1.9246,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 0.9468599033816425,
2407
+ "grad_norm": 0.7793722748756409,
2408
+ "learning_rate": 7.681014878174187e-07,
2409
+ "loss": 1.6821,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 0.9496204278812974,
2414
+ "grad_norm": 0.7322463989257812,
2415
+ "learning_rate": 6.933851926394175e-07,
2416
+ "loss": 1.7588,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 0.9523809523809523,
2421
+ "grad_norm": 0.850485622882843,
2422
+ "learning_rate": 6.224658580713971e-07,
2423
+ "loss": 1.9027,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 0.9551414768806074,
2428
+ "grad_norm": 0.9016429781913757,
2429
+ "learning_rate": 5.55348945407369e-07,
2430
+ "loss": 1.9853,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 0.9579020013802623,
2435
+ "grad_norm": 0.9636366963386536,
2436
+ "learning_rate": 4.920396231277713e-07,
2437
+ "loss": 1.6812,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 0.9606625258799172,
2442
+ "grad_norm": 0.7816176414489746,
2443
+ "learning_rate": 4.3254276650143144e-07,
2444
+ "loss": 1.7355,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 0.9634230503795721,
2449
+ "grad_norm": 1.2527109384536743,
2450
+ "learning_rate": 3.7686295721018893e-07,
2451
+ "loss": 2.1681,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 0.966183574879227,
2456
+ "grad_norm": 2.706392288208008,
2457
+ "learning_rate": 3.2500448299603305e-07,
2458
+ "loss": 2.2018,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 0.968944099378882,
2463
+ "grad_norm": 0.5852137804031372,
2464
+ "learning_rate": 2.769713373309168e-07,
2465
+ "loss": 2.2764,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 0.971704623878537,
2470
+ "grad_norm": 0.5416120290756226,
2471
+ "learning_rate": 2.3276721910926448e-07,
2472
+ "loss": 2.1675,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 0.9744651483781919,
2477
+ "grad_norm": 0.5589115619659424,
2478
+ "learning_rate": 1.923955323630877e-07,
2479
+ "loss": 2.0924,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 0.9772256728778468,
2484
+ "grad_norm": 0.582391619682312,
2485
+ "learning_rate": 1.5585938599989025e-07,
2486
+ "loss": 1.9631,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 0.9799861973775017,
2491
+ "grad_norm": 0.6033303141593933,
2492
+ "learning_rate": 1.231615935632313e-07,
2493
+ "loss": 1.5731,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 0.9827467218771566,
2498
+ "grad_norm": 0.7292796969413757,
2499
+ "learning_rate": 9.430467301607682e-08,
2500
+ "loss": 2.1532,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 0.9855072463768116,
2505
+ "grad_norm": 0.768563449382782,
2506
+ "learning_rate": 6.929084654688222e-08,
2507
+ "loss": 2.1209,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 0.9882677708764666,
2512
+ "grad_norm": 0.7994271516799927,
2513
+ "learning_rate": 4.8122040398496105e-08,
2514
+ "loss": 2.1563,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 0.9910282953761215,
2519
+ "grad_norm": 0.800473690032959,
2520
+ "learning_rate": 3.0799884719795444e-08,
2521
+ "loss": 2.2567,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 0.9937888198757764,
2526
+ "grad_norm": 0.6938081383705139,
2527
+ "learning_rate": 1.7325713440180524e-08,
2528
+ "loss": 1.8412,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 0.9965493443754313,
2533
+ "grad_norm": 1.0545095205307007,
2534
+ "learning_rate": 7.700564166834844e-09,
2535
+ "loss": 2.372,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.9993098688750862,
2540
+ "grad_norm": 0.8724227547645569,
2541
+ "learning_rate": 1.9251781048168493e-09,
2542
+ "loss": 1.7168,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 0.9993098688750862,
2547
+ "eval_loss": 2.0619454383850098,
2548
+ "eval_runtime": 5.2483,
2549
+ "eval_samples_per_second": 58.114,
2550
+ "eval_steps_per_second": 14.671,
2551
+ "step": 362
2552
+ },
2553
+ {
2554
+ "epoch": 1.0020703933747412,
2555
+ "grad_norm": 2.523097276687622,
2556
+ "learning_rate": 0.0,
2557
+ "loss": 4.4299,
2558
+ "step": 363
2559
  }
2560
  ],
2561
  "logging_steps": 1,
 
2570
  "should_evaluate": false,
2571
  "should_log": false,
2572
  "should_save": true,
2573
+ "should_training_stop": true
2574
  },
2575
  "attributes": {}
2576
  }
2577
  },
2578
+ "total_flos": 1.138052632608768e+16,
2579
  "train_batch_size": 4,
2580
  "trial_name": null,
2581
  "trial_params": null