Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +355 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,355 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7473598700243704,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 460,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016246953696181964,
|
| 13 |
+
"grad_norm": 0.11087504774332047,
|
| 14 |
+
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 1.2851,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03249390739236393,
|
| 20 |
+
"grad_norm": 0.14227746427059174,
|
| 21 |
+
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 1.1866,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.048740861088545896,
|
| 27 |
+
"grad_norm": 0.15468546748161316,
|
| 28 |
+
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 1.3344,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06498781478472786,
|
| 34 |
+
"grad_norm": 0.1867746114730835,
|
| 35 |
+
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 1.4973,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08123476848090982,
|
| 41 |
+
"grad_norm": 0.6773258447647095,
|
| 42 |
+
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 1.7041,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09748172217709179,
|
| 48 |
+
"grad_norm": 0.09346572309732437,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 1.239,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11372867587327376,
|
| 55 |
+
"grad_norm": 0.11293257027864456,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 1.1884,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.12997562956945571,
|
| 62 |
+
"grad_norm": 0.1317419856786728,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 1.3503,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1462225832656377,
|
| 69 |
+
"grad_norm": 0.20818021893501282,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 1.505,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16246953696181965,
|
| 76 |
+
"grad_norm": 0.5995267629623413,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 1.7264,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.17871649065800163,
|
| 83 |
+
"grad_norm": 0.10515395551919937,
|
| 84 |
+
"learning_rate": 0.0002,
|
| 85 |
+
"loss": 1.1812,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.19496344435418358,
|
| 90 |
+
"grad_norm": 0.11150451004505157,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 1.287,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.21121039805036557,
|
| 97 |
+
"grad_norm": 0.1395130306482315,
|
| 98 |
+
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 1.2411,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.22745735174654752,
|
| 104 |
+
"grad_norm": 0.15016046166419983,
|
| 105 |
+
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 1.4182,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2437043054427295,
|
| 111 |
+
"grad_norm": 0.4636495113372803,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 1.7269,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.25995125913891143,
|
| 118 |
+
"grad_norm": 0.0939592495560646,
|
| 119 |
+
"learning_rate": 0.0002,
|
| 120 |
+
"loss": 1.2139,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.27619821283509344,
|
| 125 |
+
"grad_norm": 0.09509933739900589,
|
| 126 |
+
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 1.1963,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2924451665312754,
|
| 132 |
+
"grad_norm": 0.1235380694270134,
|
| 133 |
+
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 1.2873,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.30869212022745735,
|
| 139 |
+
"grad_norm": 0.1839320808649063,
|
| 140 |
+
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 1.455,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3249390739236393,
|
| 146 |
+
"grad_norm": 0.481478750705719,
|
| 147 |
+
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 1.7412,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3411860276198213,
|
| 153 |
+
"grad_norm": 0.08681885898113251,
|
| 154 |
+
"learning_rate": 0.0002,
|
| 155 |
+
"loss": 1.2474,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.35743298131600326,
|
| 160 |
+
"grad_norm": 0.09558644890785217,
|
| 161 |
+
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 1.2158,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3736799350121852,
|
| 167 |
+
"grad_norm": 0.12771648168563843,
|
| 168 |
+
"learning_rate": 0.0002,
|
| 169 |
+
"loss": 1.3005,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.38992688870836717,
|
| 174 |
+
"grad_norm": 0.17630507051944733,
|
| 175 |
+
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 1.4772,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4061738424045491,
|
| 181 |
+
"grad_norm": 0.44942063093185425,
|
| 182 |
+
"learning_rate": 0.0002,
|
| 183 |
+
"loss": 1.6645,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.42242079610073113,
|
| 188 |
+
"grad_norm": 0.09558656066656113,
|
| 189 |
+
"learning_rate": 0.0002,
|
| 190 |
+
"loss": 1.1758,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4386677497969131,
|
| 195 |
+
"grad_norm": 0.09703896939754486,
|
| 196 |
+
"learning_rate": 0.0002,
|
| 197 |
+
"loss": 1.2423,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.45491470349309504,
|
| 202 |
+
"grad_norm": 0.12717948853969574,
|
| 203 |
+
"learning_rate": 0.0002,
|
| 204 |
+
"loss": 1.3671,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.471161657189277,
|
| 209 |
+
"grad_norm": 0.1827155202627182,
|
| 210 |
+
"learning_rate": 0.0002,
|
| 211 |
+
"loss": 1.5173,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.487408610885459,
|
| 216 |
+
"grad_norm": 0.4099660813808441,
|
| 217 |
+
"learning_rate": 0.0002,
|
| 218 |
+
"loss": 1.6514,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.503655564581641,
|
| 223 |
+
"grad_norm": 0.12756651639938354,
|
| 224 |
+
"learning_rate": 0.0002,
|
| 225 |
+
"loss": 1.1952,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5199025182778229,
|
| 230 |
+
"grad_norm": 0.09647507965564728,
|
| 231 |
+
"learning_rate": 0.0002,
|
| 232 |
+
"loss": 1.1511,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5361494719740049,
|
| 237 |
+
"grad_norm": 0.12492221593856812,
|
| 238 |
+
"learning_rate": 0.0002,
|
| 239 |
+
"loss": 1.1778,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5523964256701869,
|
| 244 |
+
"grad_norm": 0.18637599050998688,
|
| 245 |
+
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 1.4947,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5686433793663688,
|
| 251 |
+
"grad_norm": 0.5491933226585388,
|
| 252 |
+
"learning_rate": 0.0002,
|
| 253 |
+
"loss": 1.6702,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5848903330625508,
|
| 258 |
+
"grad_norm": 0.091646708548069,
|
| 259 |
+
"learning_rate": 0.0002,
|
| 260 |
+
"loss": 1.1607,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6011372867587328,
|
| 265 |
+
"grad_norm": 0.10480837523937225,
|
| 266 |
+
"learning_rate": 0.0002,
|
| 267 |
+
"loss": 1.2112,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6173842404549147,
|
| 272 |
+
"grad_norm": 0.12856683135032654,
|
| 273 |
+
"learning_rate": 0.0002,
|
| 274 |
+
"loss": 1.2448,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6336311941510967,
|
| 279 |
+
"grad_norm": 0.221836119890213,
|
| 280 |
+
"learning_rate": 0.0002,
|
| 281 |
+
"loss": 1.471,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6498781478472786,
|
| 286 |
+
"grad_norm": 0.442389577627182,
|
| 287 |
+
"learning_rate": 0.0002,
|
| 288 |
+
"loss": 1.7765,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6661251015434606,
|
| 293 |
+
"grad_norm": 0.08752889186143875,
|
| 294 |
+
"learning_rate": 0.0002,
|
| 295 |
+
"loss": 1.2821,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6823720552396426,
|
| 300 |
+
"grad_norm": 0.10227832943201065,
|
| 301 |
+
"learning_rate": 0.0002,
|
| 302 |
+
"loss": 1.1901,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6986190089358245,
|
| 307 |
+
"grad_norm": 0.12081281840801239,
|
| 308 |
+
"learning_rate": 0.0002,
|
| 309 |
+
"loss": 1.302,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7148659626320065,
|
| 314 |
+
"grad_norm": 0.1923910230398178,
|
| 315 |
+
"learning_rate": 0.0002,
|
| 316 |
+
"loss": 1.5397,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7311129163281884,
|
| 321 |
+
"grad_norm": 0.5226483941078186,
|
| 322 |
+
"learning_rate": 0.0002,
|
| 323 |
+
"loss": 1.6591,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7473598700243704,
|
| 328 |
+
"grad_norm": 0.09780491888523102,
|
| 329 |
+
"learning_rate": 0.0002,
|
| 330 |
+
"loss": 1.1514,
|
| 331 |
+
"step": 460
|
| 332 |
+
}
|
| 333 |
+
],
|
| 334 |
+
"logging_steps": 10,
|
| 335 |
+
"max_steps": 500,
|
| 336 |
+
"num_input_tokens_seen": 0,
|
| 337 |
+
"num_train_epochs": 1,
|
| 338 |
+
"save_steps": 10,
|
| 339 |
+
"stateful_callbacks": {
|
| 340 |
+
"TrainerControl": {
|
| 341 |
+
"args": {
|
| 342 |
+
"should_epoch_stop": false,
|
| 343 |
+
"should_evaluate": false,
|
| 344 |
+
"should_log": false,
|
| 345 |
+
"should_save": true,
|
| 346 |
+
"should_training_stop": false
|
| 347 |
+
},
|
| 348 |
+
"attributes": {}
|
| 349 |
+
}
|
| 350 |
+
},
|
| 351 |
+
"total_flos": 1.0671426142086758e+17,
|
| 352 |
+
"train_batch_size": 4,
|
| 353 |
+
"trial_name": null,
|
| 354 |
+
"trial_params": null
|
| 355 |
+
}
|