Upload trainer_state.json
Browse files- trainer_state.json +609 -213
trainer_state.json
CHANGED
|
@@ -1,412 +1,808 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "Result/
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch": 0.
|
| 12 |
-
"learning_rate": 0.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate": 0.
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch":
|
| 24 |
-
"learning_rate": 0.
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch":
|
| 30 |
-
"learning_rate": 0.
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch":
|
| 36 |
-
"learning_rate": 0.
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"learning_rate": 0.
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"learning_rate": 0.
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch":
|
| 60 |
-
"learning_rate": 0.
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch":
|
| 66 |
-
"learning_rate": 0.
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
-
"learning_rate": 0.
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"learning_rate": 0.
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch":
|
| 84 |
-
"learning_rate": 0.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"learning_rate": 0.
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 140
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch":
|
| 96 |
-
"learning_rate": 0.
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 150
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch":
|
| 102 |
-
"learning_rate": 0.
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 160
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"learning_rate": 0.
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 170
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch":
|
| 114 |
-
"learning_rate": 0.
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 180
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch":
|
| 120 |
-
"learning_rate": 0.
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 190
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
-
"learning_rate": 0.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 200
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"eval_accuracy":
|
| 133 |
-
"eval_f1":
|
| 134 |
-
"eval_loss": 0.
|
| 135 |
-
"eval_precision":
|
| 136 |
-
"eval_recall":
|
| 137 |
-
"eval_runtime": 0.
|
| 138 |
-
"eval_samples_per_second":
|
| 139 |
-
"eval_steps_per_second":
|
| 140 |
"step": 200
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch":
|
| 144 |
-
"learning_rate": 0.
|
| 145 |
-
"loss": 0.
|
| 146 |
"step": 210
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch":
|
| 150 |
-
"learning_rate": 0.
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 220
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch":
|
| 156 |
-
"learning_rate": 0.
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 230
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch":
|
| 162 |
-
"learning_rate": 0.
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 240
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch":
|
| 168 |
-
"learning_rate": 0.
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 250
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"learning_rate": 0.
|
| 175 |
-
"loss": 0.
|
| 176 |
"step": 260
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch":
|
| 180 |
-
"learning_rate": 0.
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 270
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch":
|
| 186 |
-
"learning_rate": 0.
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 280
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch":
|
| 192 |
-
"learning_rate": 0.
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 290
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch":
|
| 198 |
-
"learning_rate": 0.
|
| 199 |
-
"loss": 0.
|
| 200 |
"step": 300
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch":
|
| 204 |
-
"learning_rate": 0.
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 310
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch":
|
| 210 |
-
"learning_rate": 0.
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 320
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch":
|
| 216 |
-
"learning_rate": 0.
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 330
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch":
|
| 222 |
-
"learning_rate": 0.
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 340
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch":
|
| 228 |
-
"learning_rate": 0.
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 350
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch":
|
| 234 |
-
"learning_rate": 0.
|
| 235 |
-
"loss": 0.
|
| 236 |
"step": 360
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch":
|
| 240 |
-
"learning_rate": 0.
|
| 241 |
-
"loss": 0.
|
| 242 |
"step": 370
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch":
|
| 246 |
-
"learning_rate": 0.
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 380
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch":
|
| 252 |
-
"learning_rate": 0.
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 390
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch":
|
| 258 |
-
"learning_rate": 0.
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 400
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch":
|
| 264 |
-
"eval_accuracy":
|
| 265 |
-
"eval_f1":
|
| 266 |
-
"eval_loss": 0.
|
| 267 |
-
"eval_precision":
|
| 268 |
-
"eval_recall":
|
| 269 |
-
"eval_runtime": 0.
|
| 270 |
-
"eval_samples_per_second":
|
| 271 |
-
"eval_steps_per_second":
|
| 272 |
"step": 400
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch": 19
|
| 276 |
-
"learning_rate": 0.
|
| 277 |
-
"loss": 0.
|
| 278 |
"step": 410
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch":
|
| 282 |
-
"learning_rate": 0.
|
| 283 |
-
"loss": 0.
|
| 284 |
"step": 420
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch":
|
| 288 |
-
"learning_rate": 0.
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 430
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"epoch":
|
| 294 |
-
"learning_rate": 0.
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 440
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch":
|
| 300 |
-
"learning_rate": 0.
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 450
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch":
|
| 306 |
-
"learning_rate": 0.
|
| 307 |
-
"loss": 0.
|
| 308 |
"step": 460
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"epoch":
|
| 312 |
-
"learning_rate": 0.
|
| 313 |
-
"loss": 0.
|
| 314 |
"step": 470
|
| 315 |
},
|
| 316 |
{
|
| 317 |
-
"epoch":
|
| 318 |
-
"learning_rate": 0.
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 480
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch":
|
| 324 |
-
"learning_rate": 0.
|
| 325 |
-
"loss": 0.
|
| 326 |
"step": 490
|
| 327 |
},
|
| 328 |
{
|
| 329 |
-
"epoch":
|
| 330 |
-
"learning_rate": 0.
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 500
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch":
|
| 336 |
-
"learning_rate": 0.
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 510
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch":
|
| 342 |
-
"learning_rate": 0.
|
| 343 |
-
"loss": 0.
|
| 344 |
"step": 520
|
| 345 |
},
|
| 346 |
{
|
| 347 |
-
"epoch":
|
| 348 |
-
"learning_rate": 0.
|
| 349 |
-
"loss": 0.
|
| 350 |
"step": 530
|
| 351 |
},
|
| 352 |
{
|
| 353 |
-
"epoch":
|
| 354 |
-
"learning_rate": 0.
|
| 355 |
-
"loss": 0.
|
| 356 |
"step": 540
|
| 357 |
},
|
| 358 |
{
|
| 359 |
-
"epoch":
|
| 360 |
-
"learning_rate": 0.
|
| 361 |
-
"loss": 0.
|
| 362 |
"step": 550
|
| 363 |
},
|
| 364 |
{
|
| 365 |
-
"epoch":
|
| 366 |
-
"learning_rate": 0.
|
| 367 |
-
"loss": 0.
|
| 368 |
"step": 560
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"epoch":
|
| 372 |
-
"learning_rate": 0.
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 570
|
| 375 |
},
|
| 376 |
{
|
| 377 |
-
"epoch":
|
| 378 |
-
"learning_rate": 0.
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 580
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch":
|
| 384 |
-
"learning_rate": 0.
|
| 385 |
-
"loss": 0.
|
| 386 |
"step": 590
|
| 387 |
},
|
| 388 |
{
|
| 389 |
-
"epoch":
|
| 390 |
-
"learning_rate": 0.
|
| 391 |
-
"loss": 0.
|
| 392 |
"step": 600
|
| 393 |
},
|
| 394 |
{
|
| 395 |
-
"epoch":
|
| 396 |
-
"eval_accuracy":
|
| 397 |
-
"eval_f1":
|
| 398 |
-
"eval_loss": 0.
|
| 399 |
-
"eval_precision":
|
| 400 |
-
"eval_recall":
|
| 401 |
-
"eval_runtime": 0.
|
| 402 |
-
"eval_samples_per_second":
|
| 403 |
-
"eval_steps_per_second": 9.
|
| 404 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 405 |
}
|
| 406 |
],
|
| 407 |
"max_steps": 2000,
|
| 408 |
-
"num_train_epochs":
|
| 409 |
-
"total_flos":
|
| 410 |
"trial_name": null,
|
| 411 |
"trial_params": null
|
| 412 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.11477231234312057,
|
| 3 |
+
"best_model_checkpoint": "Result/OffsetTwo_batch4_step2000_dropout01_data5\\checkpoint-600",
|
| 4 |
+
"epoch": 15.189873417721518,
|
| 5 |
+
"global_step": 1200,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.13,
|
| 12 |
+
"learning_rate": 0.00019910000000000001,
|
| 13 |
+
"loss": 0.7699,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.25,
|
| 18 |
+
"learning_rate": 0.00019810000000000002,
|
| 19 |
+
"loss": 0.6794,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.38,
|
| 24 |
+
"learning_rate": 0.00019710000000000002,
|
| 25 |
+
"loss": 0.6679,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.51,
|
| 30 |
+
"learning_rate": 0.00019610000000000002,
|
| 31 |
+
"loss": 0.6,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.63,
|
| 36 |
+
"learning_rate": 0.00019510000000000003,
|
| 37 |
+
"loss": 0.7582,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.76,
|
| 42 |
+
"learning_rate": 0.0001941,
|
| 43 |
+
"loss": 0.5271,
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.89,
|
| 48 |
+
"learning_rate": 0.0001931,
|
| 49 |
+
"loss": 0.3892,
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 1.01,
|
| 54 |
+
"learning_rate": 0.0001921,
|
| 55 |
+
"loss": 0.5038,
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 1.14,
|
| 60 |
+
"learning_rate": 0.0001911,
|
| 61 |
+
"loss": 0.9304,
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 1.27,
|
| 66 |
+
"learning_rate": 0.0001901,
|
| 67 |
+
"loss": 0.5224,
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 1.39,
|
| 72 |
+
"learning_rate": 0.00018910000000000002,
|
| 73 |
+
"loss": 0.2114,
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 1.52,
|
| 78 |
+
"learning_rate": 0.00018810000000000002,
|
| 79 |
+
"loss": 0.4839,
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 1.65,
|
| 84 |
+
"learning_rate": 0.00018710000000000002,
|
| 85 |
+
"loss": 0.4868,
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 1.77,
|
| 90 |
+
"learning_rate": 0.0001861,
|
| 91 |
+
"loss": 0.4647,
|
| 92 |
"step": 140
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 1.9,
|
| 96 |
+
"learning_rate": 0.0001851,
|
| 97 |
+
"loss": 0.6468,
|
| 98 |
"step": 150
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 2.03,
|
| 102 |
+
"learning_rate": 0.0001841,
|
| 103 |
+
"loss": 0.534,
|
| 104 |
"step": 160
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 2.15,
|
| 108 |
+
"learning_rate": 0.0001831,
|
| 109 |
+
"loss": 0.4389,
|
| 110 |
"step": 170
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 2.28,
|
| 114 |
+
"learning_rate": 0.0001821,
|
| 115 |
+
"loss": 0.7613,
|
| 116 |
"step": 180
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 2.41,
|
| 120 |
+
"learning_rate": 0.0001811,
|
| 121 |
+
"loss": 0.5378,
|
| 122 |
"step": 190
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 2.53,
|
| 126 |
+
"learning_rate": 0.00018010000000000001,
|
| 127 |
+
"loss": 0.4595,
|
| 128 |
"step": 200
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 2.53,
|
| 132 |
+
"eval_accuracy": 0.9318181818181818,
|
| 133 |
+
"eval_f1": 0.8646153846153846,
|
| 134 |
+
"eval_loss": 0.23132099211215973,
|
| 135 |
+
"eval_precision": 0.8903508771929824,
|
| 136 |
+
"eval_recall": 0.8436293436293436,
|
| 137 |
+
"eval_runtime": 0.574,
|
| 138 |
+
"eval_samples_per_second": 76.655,
|
| 139 |
+
"eval_steps_per_second": 10.453,
|
| 140 |
"step": 200
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 2.66,
|
| 144 |
+
"learning_rate": 0.0001791,
|
| 145 |
+
"loss": 0.6753,
|
| 146 |
"step": 210
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 2.78,
|
| 150 |
+
"learning_rate": 0.0001781,
|
| 151 |
+
"loss": 0.6403,
|
| 152 |
"step": 220
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 2.91,
|
| 156 |
+
"learning_rate": 0.0001771,
|
| 157 |
+
"loss": 0.3846,
|
| 158 |
"step": 230
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 3.04,
|
| 162 |
+
"learning_rate": 0.0001761,
|
| 163 |
+
"loss": 0.436,
|
| 164 |
"step": 240
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 3.16,
|
| 168 |
+
"learning_rate": 0.0001751,
|
| 169 |
+
"loss": 0.5878,
|
| 170 |
"step": 250
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 3.29,
|
| 174 |
+
"learning_rate": 0.00017410000000000003,
|
| 175 |
+
"loss": 0.6039,
|
| 176 |
"step": 260
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 3.42,
|
| 180 |
+
"learning_rate": 0.0001731,
|
| 181 |
+
"loss": 0.3482,
|
| 182 |
"step": 270
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 3.54,
|
| 186 |
+
"learning_rate": 0.0001721,
|
| 187 |
+
"loss": 0.5476,
|
| 188 |
"step": 280
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 3.67,
|
| 192 |
+
"learning_rate": 0.0001711,
|
| 193 |
+
"loss": 0.8293,
|
| 194 |
"step": 290
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 3.8,
|
| 198 |
+
"learning_rate": 0.00017010000000000001,
|
| 199 |
+
"loss": 0.4146,
|
| 200 |
"step": 300
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 3.92,
|
| 204 |
+
"learning_rate": 0.00016910000000000002,
|
| 205 |
+
"loss": 0.2258,
|
| 206 |
"step": 310
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 4.05,
|
| 210 |
+
"learning_rate": 0.00016810000000000002,
|
| 211 |
+
"loss": 0.205,
|
| 212 |
"step": 320
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 4.18,
|
| 216 |
+
"learning_rate": 0.00016710000000000002,
|
| 217 |
+
"loss": 0.5747,
|
| 218 |
"step": 330
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 4.3,
|
| 222 |
+
"learning_rate": 0.0001661,
|
| 223 |
+
"loss": 0.4064,
|
| 224 |
"step": 340
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 4.43,
|
| 228 |
+
"learning_rate": 0.0001651,
|
| 229 |
+
"loss": 0.5639,
|
| 230 |
"step": 350
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 4.56,
|
| 234 |
+
"learning_rate": 0.0001642,
|
| 235 |
+
"loss": 0.3854,
|
| 236 |
"step": 360
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 4.68,
|
| 240 |
+
"learning_rate": 0.0001632,
|
| 241 |
+
"loss": 0.5548,
|
| 242 |
"step": 370
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 4.81,
|
| 246 |
+
"learning_rate": 0.0001622,
|
| 247 |
+
"loss": 0.5231,
|
| 248 |
"step": 380
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 4.94,
|
| 252 |
+
"learning_rate": 0.00016120000000000002,
|
| 253 |
+
"loss": 0.3772,
|
| 254 |
"step": 390
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 5.06,
|
| 258 |
+
"learning_rate": 0.00016020000000000002,
|
| 259 |
+
"loss": 0.5486,
|
| 260 |
"step": 400
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 5.06,
|
| 264 |
+
"eval_accuracy": 0.9545454545454546,
|
| 265 |
+
"eval_f1": 0.9035087719298245,
|
| 266 |
+
"eval_loss": 0.18894661962985992,
|
| 267 |
+
"eval_precision": 0.9743589743589743,
|
| 268 |
+
"eval_recall": 0.8571428571428572,
|
| 269 |
+
"eval_runtime": 0.521,
|
| 270 |
+
"eval_samples_per_second": 84.453,
|
| 271 |
+
"eval_steps_per_second": 11.516,
|
| 272 |
"step": 400
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 5.19,
|
| 276 |
+
"learning_rate": 0.00015920000000000002,
|
| 277 |
+
"loss": 0.5041,
|
| 278 |
"step": 410
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 5.32,
|
| 282 |
+
"learning_rate": 0.00015820000000000002,
|
| 283 |
+
"loss": 0.3767,
|
| 284 |
"step": 420
|
| 285 |
},
|
| 286 |
{
|
| 287 |
+
"epoch": 5.44,
|
| 288 |
+
"learning_rate": 0.00015720000000000003,
|
| 289 |
+
"loss": 0.1914,
|
| 290 |
"step": 430
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"epoch": 5.57,
|
| 294 |
+
"learning_rate": 0.0001562,
|
| 295 |
+
"loss": 0.4182,
|
| 296 |
"step": 440
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 5.7,
|
| 300 |
+
"learning_rate": 0.0001552,
|
| 301 |
+
"loss": 0.1872,
|
| 302 |
"step": 450
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 5.82,
|
| 306 |
+
"learning_rate": 0.0001542,
|
| 307 |
+
"loss": 0.3854,
|
| 308 |
"step": 460
|
| 309 |
},
|
| 310 |
{
|
| 311 |
+
"epoch": 5.95,
|
| 312 |
+
"learning_rate": 0.0001532,
|
| 313 |
+
"loss": 0.0307,
|
| 314 |
"step": 470
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 6.08,
|
| 318 |
+
"learning_rate": 0.0001522,
|
| 319 |
+
"loss": 0.0157,
|
| 320 |
"step": 480
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"epoch": 6.2,
|
| 324 |
+
"learning_rate": 0.00015120000000000002,
|
| 325 |
+
"loss": 0.2349,
|
| 326 |
"step": 490
|
| 327 |
},
|
| 328 |
{
|
| 329 |
+
"epoch": 6.33,
|
| 330 |
+
"learning_rate": 0.00015020000000000002,
|
| 331 |
+
"loss": 0.2716,
|
| 332 |
"step": 500
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 6.46,
|
| 336 |
+
"learning_rate": 0.0001492,
|
| 337 |
+
"loss": 0.2278,
|
| 338 |
"step": 510
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 6.58,
|
| 342 |
+
"learning_rate": 0.0001482,
|
| 343 |
+
"loss": 0.0078,
|
| 344 |
"step": 520
|
| 345 |
},
|
| 346 |
{
|
| 347 |
+
"epoch": 6.71,
|
| 348 |
+
"learning_rate": 0.0001472,
|
| 349 |
+
"loss": 0.0069,
|
| 350 |
"step": 530
|
| 351 |
},
|
| 352 |
{
|
| 353 |
+
"epoch": 6.84,
|
| 354 |
+
"learning_rate": 0.0001462,
|
| 355 |
+
"loss": 0.3477,
|
| 356 |
"step": 540
|
| 357 |
},
|
| 358 |
{
|
| 359 |
+
"epoch": 6.96,
|
| 360 |
+
"learning_rate": 0.0001452,
|
| 361 |
+
"loss": 0.0098,
|
| 362 |
"step": 550
|
| 363 |
},
|
| 364 |
{
|
| 365 |
+
"epoch": 7.09,
|
| 366 |
+
"learning_rate": 0.0001442,
|
| 367 |
+
"loss": 0.0061,
|
| 368 |
"step": 560
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"epoch": 7.22,
|
| 372 |
+
"learning_rate": 0.0001432,
|
| 373 |
+
"loss": 0.005,
|
| 374 |
"step": 570
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 7.34,
|
| 378 |
+
"learning_rate": 0.0001422,
|
| 379 |
+
"loss": 0.0047,
|
| 380 |
"step": 580
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 7.47,
|
| 384 |
+
"learning_rate": 0.0001412,
|
| 385 |
+
"loss": 0.0043,
|
| 386 |
"step": 590
|
| 387 |
},
|
| 388 |
{
|
| 389 |
+
"epoch": 7.59,
|
| 390 |
+
"learning_rate": 0.0001402,
|
| 391 |
+
"loss": 0.0045,
|
| 392 |
"step": 600
|
| 393 |
},
|
| 394 |
{
|
| 395 |
+
"epoch": 7.59,
|
| 396 |
+
"eval_accuracy": 0.9772727272727273,
|
| 397 |
+
"eval_f1": 0.9548717948717949,
|
| 398 |
+
"eval_loss": 0.11477231234312057,
|
| 399 |
+
"eval_precision": 0.986842105263158,
|
| 400 |
+
"eval_recall": 0.9285714285714286,
|
| 401 |
+
"eval_runtime": 0.622,
|
| 402 |
+
"eval_samples_per_second": 70.74,
|
| 403 |
+
"eval_steps_per_second": 9.646,
|
| 404 |
"step": 600
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 7.72,
|
| 408 |
+
"learning_rate": 0.0001392,
|
| 409 |
+
"loss": 0.0037,
|
| 410 |
+
"step": 610
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 7.85,
|
| 414 |
+
"learning_rate": 0.0001382,
|
| 415 |
+
"loss": 0.0042,
|
| 416 |
+
"step": 620
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 7.97,
|
| 420 |
+
"learning_rate": 0.00013720000000000003,
|
| 421 |
+
"loss": 0.3004,
|
| 422 |
+
"step": 630
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 8.1,
|
| 426 |
+
"learning_rate": 0.0001362,
|
| 427 |
+
"loss": 0.0332,
|
| 428 |
+
"step": 640
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 8.23,
|
| 432 |
+
"learning_rate": 0.0001352,
|
| 433 |
+
"loss": 0.0033,
|
| 434 |
+
"step": 650
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 8.35,
|
| 438 |
+
"learning_rate": 0.0001342,
|
| 439 |
+
"loss": 0.0033,
|
| 440 |
+
"step": 660
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 8.48,
|
| 444 |
+
"learning_rate": 0.0001332,
|
| 445 |
+
"loss": 0.0406,
|
| 446 |
+
"step": 670
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 8.61,
|
| 450 |
+
"learning_rate": 0.00013220000000000001,
|
| 451 |
+
"loss": 0.003,
|
| 452 |
+
"step": 680
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 8.73,
|
| 456 |
+
"learning_rate": 0.00013120000000000002,
|
| 457 |
+
"loss": 0.0043,
|
| 458 |
+
"step": 690
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 8.86,
|
| 462 |
+
"learning_rate": 0.00013020000000000002,
|
| 463 |
+
"loss": 0.0055,
|
| 464 |
+
"step": 700
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 8.99,
|
| 468 |
+
"learning_rate": 0.00012920000000000002,
|
| 469 |
+
"loss": 0.0029,
|
| 470 |
+
"step": 710
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 9.11,
|
| 474 |
+
"learning_rate": 0.0001282,
|
| 475 |
+
"loss": 0.0027,
|
| 476 |
+
"step": 720
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 9.24,
|
| 480 |
+
"learning_rate": 0.0001272,
|
| 481 |
+
"loss": 0.0027,
|
| 482 |
+
"step": 730
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 9.37,
|
| 486 |
+
"learning_rate": 0.0001262,
|
| 487 |
+
"loss": 0.0024,
|
| 488 |
+
"step": 740
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 9.49,
|
| 492 |
+
"learning_rate": 0.0001252,
|
| 493 |
+
"loss": 0.0922,
|
| 494 |
+
"step": 750
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 9.62,
|
| 498 |
+
"learning_rate": 0.0001242,
|
| 499 |
+
"loss": 0.0691,
|
| 500 |
+
"step": 760
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 9.75,
|
| 504 |
+
"learning_rate": 0.0001232,
|
| 505 |
+
"loss": 0.0023,
|
| 506 |
+
"step": 770
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 9.87,
|
| 510 |
+
"learning_rate": 0.00012220000000000002,
|
| 511 |
+
"loss": 0.0022,
|
| 512 |
+
"step": 780
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 10.0,
|
| 516 |
+
"learning_rate": 0.0001212,
|
| 517 |
+
"loss": 0.2026,
|
| 518 |
+
"step": 790
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 10.13,
|
| 522 |
+
"learning_rate": 0.00012020000000000001,
|
| 523 |
+
"loss": 0.0024,
|
| 524 |
+
"step": 800
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 10.13,
|
| 528 |
+
"eval_accuracy": 0.9545454545454546,
|
| 529 |
+
"eval_f1": 0.915057915057915,
|
| 530 |
+
"eval_loss": 0.31218913197517395,
|
| 531 |
+
"eval_precision": 0.915057915057915,
|
| 532 |
+
"eval_recall": 0.915057915057915,
|
| 533 |
+
"eval_runtime": 0.585,
|
| 534 |
+
"eval_samples_per_second": 75.214,
|
| 535 |
+
"eval_steps_per_second": 10.256,
|
| 536 |
+
"step": 800
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 10.25,
|
| 540 |
+
"learning_rate": 0.0001192,
|
| 541 |
+
"loss": 0.0021,
|
| 542 |
+
"step": 810
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 10.38,
|
| 546 |
+
"learning_rate": 0.0001182,
|
| 547 |
+
"loss": 0.0021,
|
| 548 |
+
"step": 820
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 10.51,
|
| 552 |
+
"learning_rate": 0.0001172,
|
| 553 |
+
"loss": 0.002,
|
| 554 |
+
"step": 830
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 10.63,
|
| 558 |
+
"learning_rate": 0.00011619999999999999,
|
| 559 |
+
"loss": 0.002,
|
| 560 |
+
"step": 840
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 10.76,
|
| 564 |
+
"learning_rate": 0.0001152,
|
| 565 |
+
"loss": 0.0019,
|
| 566 |
+
"step": 850
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 10.89,
|
| 570 |
+
"learning_rate": 0.0001142,
|
| 571 |
+
"loss": 0.0018,
|
| 572 |
+
"step": 860
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 11.01,
|
| 576 |
+
"learning_rate": 0.0001132,
|
| 577 |
+
"loss": 0.0018,
|
| 578 |
+
"step": 870
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 11.14,
|
| 582 |
+
"learning_rate": 0.00011220000000000002,
|
| 583 |
+
"loss": 0.0017,
|
| 584 |
+
"step": 880
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 11.27,
|
| 588 |
+
"learning_rate": 0.00011120000000000002,
|
| 589 |
+
"loss": 0.0017,
|
| 590 |
+
"step": 890
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 11.39,
|
| 594 |
+
"learning_rate": 0.00011020000000000001,
|
| 595 |
+
"loss": 0.0017,
|
| 596 |
+
"step": 900
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 11.52,
|
| 600 |
+
"learning_rate": 0.00010920000000000001,
|
| 601 |
+
"loss": 0.0016,
|
| 602 |
+
"step": 910
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 11.65,
|
| 606 |
+
"learning_rate": 0.00010820000000000001,
|
| 607 |
+
"loss": 0.0016,
|
| 608 |
+
"step": 920
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 11.77,
|
| 612 |
+
"learning_rate": 0.00010720000000000002,
|
| 613 |
+
"loss": 0.0016,
|
| 614 |
+
"step": 930
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 11.9,
|
| 618 |
+
"learning_rate": 0.0001062,
|
| 619 |
+
"loss": 0.0016,
|
| 620 |
+
"step": 940
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 12.03,
|
| 624 |
+
"learning_rate": 0.00010520000000000001,
|
| 625 |
+
"loss": 0.0015,
|
| 626 |
+
"step": 950
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 12.15,
|
| 630 |
+
"learning_rate": 0.00010420000000000001,
|
| 631 |
+
"loss": 0.0015,
|
| 632 |
+
"step": 960
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 12.28,
|
| 636 |
+
"learning_rate": 0.0001032,
|
| 637 |
+
"loss": 0.0014,
|
| 638 |
+
"step": 970
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 12.41,
|
| 642 |
+
"learning_rate": 0.0001022,
|
| 643 |
+
"loss": 0.0014,
|
| 644 |
+
"step": 980
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 12.53,
|
| 648 |
+
"learning_rate": 0.00010120000000000001,
|
| 649 |
+
"loss": 0.0014,
|
| 650 |
+
"step": 990
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 12.66,
|
| 654 |
+
"learning_rate": 0.00010020000000000001,
|
| 655 |
+
"loss": 0.0014,
|
| 656 |
+
"step": 1000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 12.66,
|
| 660 |
+
"eval_accuracy": 0.9545454545454546,
|
| 661 |
+
"eval_f1": 0.915057915057915,
|
| 662 |
+
"eval_loss": 0.32846134901046753,
|
| 663 |
+
"eval_precision": 0.915057915057915,
|
| 664 |
+
"eval_recall": 0.915057915057915,
|
| 665 |
+
"eval_runtime": 0.572,
|
| 666 |
+
"eval_samples_per_second": 76.923,
|
| 667 |
+
"eval_steps_per_second": 10.49,
|
| 668 |
+
"step": 1000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 12.78,
|
| 672 |
+
"learning_rate": 9.92e-05,
|
| 673 |
+
"loss": 0.0014,
|
| 674 |
+
"step": 1010
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 12.91,
|
| 678 |
+
"learning_rate": 9.82e-05,
|
| 679 |
+
"loss": 0.0013,
|
| 680 |
+
"step": 1020
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 13.04,
|
| 684 |
+
"learning_rate": 9.72e-05,
|
| 685 |
+
"loss": 0.0013,
|
| 686 |
+
"step": 1030
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 13.16,
|
| 690 |
+
"learning_rate": 9.620000000000001e-05,
|
| 691 |
+
"loss": 0.0013,
|
| 692 |
+
"step": 1040
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 13.29,
|
| 696 |
+
"learning_rate": 9.52e-05,
|
| 697 |
+
"loss": 0.0013,
|
| 698 |
+
"step": 1050
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 13.42,
|
| 702 |
+
"learning_rate": 9.42e-05,
|
| 703 |
+
"loss": 0.0012,
|
| 704 |
+
"step": 1060
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 13.54,
|
| 708 |
+
"learning_rate": 9.320000000000002e-05,
|
| 709 |
+
"loss": 0.0012,
|
| 710 |
+
"step": 1070
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 13.67,
|
| 714 |
+
"learning_rate": 9.22e-05,
|
| 715 |
+
"loss": 0.0012,
|
| 716 |
+
"step": 1080
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 13.8,
|
| 720 |
+
"learning_rate": 9.120000000000001e-05,
|
| 721 |
+
"loss": 0.0012,
|
| 722 |
+
"step": 1090
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 13.92,
|
| 726 |
+
"learning_rate": 9.020000000000001e-05,
|
| 727 |
+
"loss": 0.0012,
|
| 728 |
+
"step": 1100
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 14.05,
|
| 732 |
+
"learning_rate": 8.92e-05,
|
| 733 |
+
"loss": 0.0012,
|
| 734 |
+
"step": 1110
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 14.18,
|
| 738 |
+
"learning_rate": 8.82e-05,
|
| 739 |
+
"loss": 0.0011,
|
| 740 |
+
"step": 1120
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 14.3,
|
| 744 |
+
"learning_rate": 8.72e-05,
|
| 745 |
+
"loss": 0.0011,
|
| 746 |
+
"step": 1130
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 14.43,
|
| 750 |
+
"learning_rate": 8.620000000000001e-05,
|
| 751 |
+
"loss": 0.0011,
|
| 752 |
+
"step": 1140
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 14.56,
|
| 756 |
+
"learning_rate": 8.52e-05,
|
| 757 |
+
"loss": 0.0011,
|
| 758 |
+
"step": 1150
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 14.68,
|
| 762 |
+
"learning_rate": 8.42e-05,
|
| 763 |
+
"loss": 0.0011,
|
| 764 |
+
"step": 1160
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 14.81,
|
| 768 |
+
"learning_rate": 8.32e-05,
|
| 769 |
+
"loss": 0.0011,
|
| 770 |
+
"step": 1170
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 14.94,
|
| 774 |
+
"learning_rate": 8.22e-05,
|
| 775 |
+
"loss": 0.0011,
|
| 776 |
+
"step": 1180
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 15.06,
|
| 780 |
+
"learning_rate": 8.120000000000001e-05,
|
| 781 |
+
"loss": 0.001,
|
| 782 |
+
"step": 1190
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 15.19,
|
| 786 |
+
"learning_rate": 8.020000000000001e-05,
|
| 787 |
+
"loss": 0.001,
|
| 788 |
+
"step": 1200
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 15.19,
|
| 792 |
+
"eval_accuracy": 0.9545454545454546,
|
| 793 |
+
"eval_f1": 0.915057915057915,
|
| 794 |
+
"eval_loss": 0.3429644703865051,
|
| 795 |
+
"eval_precision": 0.915057915057915,
|
| 796 |
+
"eval_recall": 0.915057915057915,
|
| 797 |
+
"eval_runtime": 0.592,
|
| 798 |
+
"eval_samples_per_second": 74.325,
|
| 799 |
+
"eval_steps_per_second": 10.135,
|
| 800 |
+
"step": 1200
|
| 801 |
}
|
| 802 |
],
|
| 803 |
"max_steps": 2000,
|
| 804 |
+
"num_train_epochs": 26,
|
| 805 |
+
"total_flos": 3.6847441061738496e+17,
|
| 806 |
"trial_name": null,
|
| 807 |
"trial_params": null
|
| 808 |
}
|