Training in progress, step 100
Browse files- all_results.json +5 -5
- pytorch_model.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +238 -398
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second": 23.
|
| 6 |
-
"train_steps_per_second": 2.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"train_loss": 0.2614198288559413,
|
| 4 |
+
"train_runtime": 441.6283,
|
| 5 |
+
"train_samples_per_second": 23.676,
|
| 6 |
+
"train_steps_per_second": 2.156
|
| 7 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343293293
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de7e09bd10f0d43a6ee5f1c5474102837fd704a0c5e66b40ce5c9774baff9c75
|
| 3 |
size 343293293
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second": 23.
|
| 6 |
-
"train_steps_per_second": 2.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"train_loss": 0.2614198288559413,
|
| 4 |
+
"train_runtime": 441.6283,
|
| 5 |
+
"train_samples_per_second": 23.676,
|
| 6 |
+
"train_steps_per_second": 2.156
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,827 +1,667 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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": 0.08,
|
| 12 |
-
"learning_rate": 9.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.17,
|
| 18 |
-
"learning_rate": 9.
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.25,
|
| 24 |
-
"learning_rate": 9.
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.34,
|
| 30 |
-
"learning_rate": 9.
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.42,
|
| 36 |
-
"learning_rate": 9.
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.5,
|
| 42 |
-
"learning_rate": 9.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.59,
|
| 48 |
-
"learning_rate": 9.
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.67,
|
| 54 |
-
"learning_rate": 9.
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.76,
|
| 60 |
-
"learning_rate": 9.
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.84,
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.84,
|
| 72 |
-
"eval_loss": 0.
|
| 73 |
-
"eval_runtime": 3.
|
| 74 |
-
"eval_samples_per_second":
|
| 75 |
-
"eval_steps_per_second":
|
| 76 |
"step": 100
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 0.92,
|
| 80 |
-
"learning_rate":
|
| 81 |
-
"loss": 0.
|
| 82 |
"step": 110
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 1.01,
|
| 86 |
-
"learning_rate": 8.
|
| 87 |
-
"loss": 0.
|
| 88 |
"step": 120
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 1.09,
|
| 92 |
-
"learning_rate": 8.
|
| 93 |
-
"loss": 0.
|
| 94 |
"step": 130
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 1.18,
|
| 98 |
-
"learning_rate": 8.
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 140
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 1.26,
|
| 104 |
-
"learning_rate": 8.
|
| 105 |
-
"loss": 0.
|
| 106 |
"step": 150
|
| 107 |
},
|
| 108 |
{
|
| 109 |
"epoch": 1.34,
|
| 110 |
-
"learning_rate": 8.
|
| 111 |
-
"loss": 0.
|
| 112 |
"step": 160
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"epoch": 1.43,
|
| 116 |
-
"learning_rate": 8.
|
| 117 |
-
"loss": 0.
|
| 118 |
"step": 170
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 1.51,
|
| 122 |
-
"learning_rate": 8.
|
| 123 |
-
"loss": 0.
|
| 124 |
"step": 180
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 1.6,
|
| 128 |
-
"learning_rate": 8.
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 190
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 1.68,
|
| 134 |
-
"learning_rate":
|
| 135 |
-
"loss": 0.
|
| 136 |
"step": 200
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 1.68,
|
| 140 |
-
"eval_loss": 0.
|
| 141 |
-
"eval_runtime":
|
| 142 |
-
"eval_samples_per_second":
|
| 143 |
-
"eval_steps_per_second":
|
| 144 |
"step": 200
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 1.76,
|
| 148 |
-
"learning_rate":
|
| 149 |
-
"loss": 0.
|
| 150 |
"step": 210
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 1.85,
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 220
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 1.93,
|
| 160 |
-
"learning_rate":
|
| 161 |
-
"loss": 0.
|
| 162 |
"step": 230
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 2.02,
|
| 166 |
-
"learning_rate": 7.
|
| 167 |
-
"loss": 0.
|
| 168 |
"step": 240
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 2.1,
|
| 172 |
-
"learning_rate": 7.
|
| 173 |
-
"loss": 0.
|
| 174 |
"step": 250
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 2.18,
|
| 178 |
-
"learning_rate": 7.
|
| 179 |
-
"loss": 0.
|
| 180 |
"step": 260
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 2.27,
|
| 184 |
-
"learning_rate": 7.
|
| 185 |
-
"loss": 0.
|
| 186 |
"step": 270
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 2.35,
|
| 190 |
-
"learning_rate": 7.
|
| 191 |
-
"loss": 0.
|
| 192 |
"step": 280
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 2.44,
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 290
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 2.52,
|
| 202 |
-
"learning_rate":
|
| 203 |
-
"loss": 0.
|
| 204 |
"step": 300
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 2.52,
|
| 208 |
-
"eval_loss": 0.
|
| 209 |
-
"eval_runtime":
|
| 210 |
-
"eval_samples_per_second":
|
| 211 |
-
"eval_steps_per_second":
|
| 212 |
"step": 300
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 2.61,
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 310
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 2.69,
|
| 222 |
-
"learning_rate":
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 320
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 2.77,
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 330
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 2.86,
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss": 0.
|
| 236 |
"step": 340
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 2.94,
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss": 0.
|
| 242 |
"step": 350
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 3.03,
|
| 246 |
-
"learning_rate": 6.
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 360
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 3.11,
|
| 252 |
-
"learning_rate": 6.
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 370
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 3.19,
|
| 258 |
-
"learning_rate": 6.
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 380
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 3.28,
|
| 264 |
-
"learning_rate":
|
| 265 |
-
"loss": 0.
|
| 266 |
"step": 390
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 3.36,
|
| 270 |
-
"learning_rate":
|
| 271 |
-
"loss": 0.
|
| 272 |
"step": 400
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 3.36,
|
| 276 |
-
"eval_loss": 0.
|
| 277 |
-
"eval_runtime": 4.
|
| 278 |
-
"eval_samples_per_second":
|
| 279 |
-
"eval_steps_per_second":
|
| 280 |
"step": 400
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 3.45,
|
| 284 |
-
"learning_rate":
|
| 285 |
-
"loss": 0.
|
| 286 |
"step": 410
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 3.53,
|
| 290 |
-
"learning_rate":
|
| 291 |
-
"loss": 0.
|
| 292 |
"step": 420
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 3.61,
|
| 296 |
-
"learning_rate":
|
| 297 |
-
"loss": 0.
|
| 298 |
"step": 430
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 3.7,
|
| 302 |
-
"learning_rate":
|
| 303 |
-
"loss": 0.
|
| 304 |
"step": 440
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 3.78,
|
| 308 |
-
"learning_rate":
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 450
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 3.87,
|
| 314 |
-
"learning_rate":
|
| 315 |
-
"loss": 0.
|
| 316 |
"step": 460
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 3.95,
|
| 320 |
-
"learning_rate":
|
| 321 |
-
"loss": 0.
|
| 322 |
"step": 470
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 4.03,
|
| 326 |
-
"learning_rate":
|
| 327 |
-
"loss": 0.
|
| 328 |
"step": 480
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 4.12,
|
| 332 |
-
"learning_rate":
|
| 333 |
-
"loss": 0.
|
| 334 |
"step": 490
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 4.2,
|
| 338 |
-
"learning_rate":
|
| 339 |
-
"loss": 0.
|
| 340 |
"step": 500
|
| 341 |
},
|
| 342 |
{
|
| 343 |
"epoch": 4.2,
|
| 344 |
-
"eval_loss": 0.
|
| 345 |
-
"eval_runtime": 4.
|
| 346 |
-
"eval_samples_per_second":
|
| 347 |
-
"eval_steps_per_second":
|
| 348 |
"step": 500
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 4.29,
|
| 352 |
-
"learning_rate":
|
| 353 |
-
"loss": 0.
|
| 354 |
"step": 510
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 4.37,
|
| 358 |
-
"learning_rate":
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 520
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 4.45,
|
| 364 |
-
"learning_rate":
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 530
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 4.54,
|
| 370 |
-
"learning_rate":
|
| 371 |
-
"loss": 0.
|
| 372 |
"step": 540
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 4.62,
|
| 376 |
-
"learning_rate":
|
| 377 |
-
"loss": 0.
|
| 378 |
"step": 550
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 4.71,
|
| 382 |
-
"learning_rate":
|
| 383 |
-
"loss": 0.
|
| 384 |
"step": 560
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 4.79,
|
| 388 |
-
"learning_rate":
|
| 389 |
-
"loss": 0.
|
| 390 |
"step": 570
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 4.87,
|
| 394 |
-
"learning_rate":
|
| 395 |
-
"loss": 0.
|
| 396 |
"step": 580
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 4.96,
|
| 400 |
-
"learning_rate":
|
| 401 |
-
"loss": 0.
|
| 402 |
"step": 590
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 5.04,
|
| 406 |
-
"learning_rate":
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 600
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 5.04,
|
| 412 |
-
"eval_loss": 0.
|
| 413 |
-
"eval_runtime":
|
| 414 |
-
"eval_samples_per_second":
|
| 415 |
-
"eval_steps_per_second": 13.
|
| 416 |
"step": 600
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 5.13,
|
| 420 |
-
"learning_rate":
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 610
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 5.21,
|
| 426 |
-
"learning_rate":
|
| 427 |
-
"loss": 0.
|
| 428 |
"step": 620
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 5.29,
|
| 432 |
-
"learning_rate":
|
| 433 |
-
"loss": 0.
|
| 434 |
"step": 630
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 5.38,
|
| 438 |
-
"learning_rate":
|
| 439 |
-
"loss": 0.
|
| 440 |
"step": 640
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 5.46,
|
| 444 |
-
"learning_rate":
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 650
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 5.55,
|
| 450 |
-
"learning_rate":
|
| 451 |
-
"loss": 0.
|
| 452 |
"step": 660
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 5.63,
|
| 456 |
-
"learning_rate":
|
| 457 |
-
"loss": 0.
|
| 458 |
"step": 670
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 5.71,
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss": 0.
|
| 464 |
"step": 680
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 5.8,
|
| 468 |
-
"learning_rate":
|
| 469 |
-
"loss": 0.
|
| 470 |
"step": 690
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 5.88,
|
| 474 |
-
"learning_rate":
|
| 475 |
-
"loss": 0.
|
| 476 |
"step": 700
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 5.88,
|
| 480 |
-
"eval_loss": 0.
|
| 481 |
-
"eval_runtime":
|
| 482 |
-
"eval_samples_per_second":
|
| 483 |
-
"eval_steps_per_second":
|
| 484 |
"step": 700
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 5.97,
|
| 488 |
-
"learning_rate":
|
| 489 |
-
"loss": 0.
|
| 490 |
"step": 710
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 6.05,
|
| 494 |
-
"learning_rate":
|
| 495 |
-
"loss": 0.
|
| 496 |
"step": 720
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 6.13,
|
| 500 |
-
"learning_rate":
|
| 501 |
-
"loss": 0.
|
| 502 |
"step": 730
|
| 503 |
},
|
| 504 |
{
|
| 505 |
"epoch": 6.22,
|
| 506 |
-
"learning_rate":
|
| 507 |
-
"loss": 0.
|
| 508 |
"step": 740
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 6.3,
|
| 512 |
-
"learning_rate":
|
| 513 |
-
"loss": 0.
|
| 514 |
"step": 750
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"epoch": 6.39,
|
| 518 |
-
"learning_rate":
|
| 519 |
-
"loss": 0.
|
| 520 |
"step": 760
|
| 521 |
},
|
| 522 |
{
|
| 523 |
"epoch": 6.47,
|
| 524 |
-
"learning_rate":
|
| 525 |
-
"loss": 0.
|
| 526 |
"step": 770
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"epoch": 6.55,
|
| 530 |
-
"learning_rate":
|
| 531 |
-
"loss": 0.
|
| 532 |
"step": 780
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 6.64,
|
| 536 |
-
"learning_rate":
|
| 537 |
-
"loss": 0.
|
| 538 |
"step": 790
|
| 539 |
},
|
| 540 |
{
|
| 541 |
"epoch": 6.72,
|
| 542 |
-
"learning_rate":
|
| 543 |
-
"loss": 0.
|
| 544 |
"step": 800
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"epoch": 6.72,
|
| 548 |
-
"eval_loss": 0.
|
| 549 |
-
"eval_runtime": 3.
|
| 550 |
-
"eval_samples_per_second":
|
| 551 |
-
"eval_steps_per_second": 13.
|
| 552 |
"step": 800
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 6.81,
|
| 556 |
-
"learning_rate":
|
| 557 |
-
"loss": 0.
|
| 558 |
"step": 810
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 6.89,
|
| 562 |
-
"learning_rate":
|
| 563 |
-
"loss": 0.
|
| 564 |
"step": 820
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 6.97,
|
| 568 |
-
"learning_rate":
|
| 569 |
-
"loss": 0.
|
| 570 |
"step": 830
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 7.06,
|
| 574 |
-
"learning_rate":
|
| 575 |
-
"loss": 0.
|
| 576 |
"step": 840
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 7.14,
|
| 580 |
-
"learning_rate":
|
| 581 |
-
"loss": 0.
|
| 582 |
"step": 850
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 7.23,
|
| 586 |
-
"learning_rate":
|
| 587 |
-
"loss": 0.
|
| 588 |
"step": 860
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 7.31,
|
| 592 |
-
"learning_rate":
|
| 593 |
-
"loss": 0.
|
| 594 |
"step": 870
|
| 595 |
},
|
| 596 |
{
|
| 597 |
"epoch": 7.39,
|
| 598 |
-
"learning_rate":
|
| 599 |
-
"loss": 0.
|
| 600 |
"step": 880
|
| 601 |
},
|
| 602 |
{
|
| 603 |
"epoch": 7.48,
|
| 604 |
-
"learning_rate":
|
| 605 |
-
"loss": 0.
|
| 606 |
"step": 890
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 7.56,
|
| 610 |
-
"learning_rate":
|
| 611 |
-
"loss": 0.
|
| 612 |
"step": 900
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 7.56,
|
| 616 |
-
"eval_loss": 0.
|
| 617 |
-
"eval_runtime":
|
| 618 |
-
"eval_samples_per_second":
|
| 619 |
-
"eval_steps_per_second":
|
| 620 |
"step": 900
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 7.65,
|
| 624 |
-
"learning_rate":
|
| 625 |
-
"loss": 0.
|
| 626 |
"step": 910
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 7.73,
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 920
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 7.82,
|
| 636 |
-
"learning_rate": 2.
|
| 637 |
-
"loss": 0.
|
| 638 |
"step": 930
|
| 639 |
},
|
| 640 |
{
|
| 641 |
"epoch": 7.9,
|
| 642 |
-
"learning_rate":
|
| 643 |
-
"loss": 0.
|
| 644 |
"step": 940
|
| 645 |
},
|
| 646 |
{
|
| 647 |
"epoch": 7.98,
|
| 648 |
-
"learning_rate": 2.
|
| 649 |
-
"loss": 0.
|
| 650 |
"step": 950
|
| 651 |
},
|
| 652 |
{
|
| 653 |
-
"epoch": 8.
|
| 654 |
-
"
|
| 655 |
-
"
|
| 656 |
-
"
|
| 657 |
-
|
| 658 |
-
|
| 659 |
-
"
|
| 660 |
-
"learning_rate": 1.8487394957983196e-05,
|
| 661 |
-
"loss": 0.1549,
|
| 662 |
-
"step": 970
|
| 663 |
-
},
|
| 664 |
-
{
|
| 665 |
-
"epoch": 8.24,
|
| 666 |
-
"learning_rate": 1.7647058823529414e-05,
|
| 667 |
-
"loss": 0.1538,
|
| 668 |
-
"step": 980
|
| 669 |
-
},
|
| 670 |
-
{
|
| 671 |
-
"epoch": 8.32,
|
| 672 |
-
"learning_rate": 1.6806722689075634e-05,
|
| 673 |
-
"loss": 0.1546,
|
| 674 |
-
"step": 990
|
| 675 |
-
},
|
| 676 |
-
{
|
| 677 |
-
"epoch": 8.4,
|
| 678 |
-
"learning_rate": 1.5966386554621848e-05,
|
| 679 |
-
"loss": 0.1553,
|
| 680 |
-
"step": 1000
|
| 681 |
-
},
|
| 682 |
-
{
|
| 683 |
-
"epoch": 8.4,
|
| 684 |
-
"eval_loss": 0.28088859500924873,
|
| 685 |
-
"eval_runtime": 4.3025,
|
| 686 |
-
"eval_samples_per_second": 99.477,
|
| 687 |
-
"eval_steps_per_second": 12.551,
|
| 688 |
-
"step": 1000
|
| 689 |
-
},
|
| 690 |
-
{
|
| 691 |
-
"epoch": 8.49,
|
| 692 |
-
"learning_rate": 1.5126050420168067e-05,
|
| 693 |
-
"loss": 0.1498,
|
| 694 |
-
"step": 1010
|
| 695 |
-
},
|
| 696 |
-
{
|
| 697 |
-
"epoch": 8.57,
|
| 698 |
-
"learning_rate": 1.4285714285714285e-05,
|
| 699 |
-
"loss": 0.1527,
|
| 700 |
-
"step": 1020
|
| 701 |
-
},
|
| 702 |
-
{
|
| 703 |
-
"epoch": 8.66,
|
| 704 |
-
"learning_rate": 1.3445378151260504e-05,
|
| 705 |
-
"loss": 0.155,
|
| 706 |
-
"step": 1030
|
| 707 |
-
},
|
| 708 |
-
{
|
| 709 |
-
"epoch": 8.74,
|
| 710 |
-
"learning_rate": 1.2605042016806723e-05,
|
| 711 |
-
"loss": 0.1501,
|
| 712 |
-
"step": 1040
|
| 713 |
-
},
|
| 714 |
-
{
|
| 715 |
-
"epoch": 8.82,
|
| 716 |
-
"learning_rate": 1.1764705882352942e-05,
|
| 717 |
-
"loss": 0.155,
|
| 718 |
-
"step": 1050
|
| 719 |
-
},
|
| 720 |
-
{
|
| 721 |
-
"epoch": 8.91,
|
| 722 |
-
"learning_rate": 1.092436974789916e-05,
|
| 723 |
-
"loss": 0.1482,
|
| 724 |
-
"step": 1060
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 8.99,
|
| 728 |
-
"learning_rate": 1.008403361344538e-05,
|
| 729 |
-
"loss": 0.1473,
|
| 730 |
-
"step": 1070
|
| 731 |
-
},
|
| 732 |
-
{
|
| 733 |
-
"epoch": 9.08,
|
| 734 |
-
"learning_rate": 9.243697478991598e-06,
|
| 735 |
-
"loss": 0.1467,
|
| 736 |
-
"step": 1080
|
| 737 |
-
},
|
| 738 |
-
{
|
| 739 |
-
"epoch": 9.16,
|
| 740 |
-
"learning_rate": 8.403361344537817e-06,
|
| 741 |
-
"loss": 0.1494,
|
| 742 |
-
"step": 1090
|
| 743 |
-
},
|
| 744 |
-
{
|
| 745 |
-
"epoch": 9.24,
|
| 746 |
-
"learning_rate": 7.563025210084033e-06,
|
| 747 |
-
"loss": 0.1519,
|
| 748 |
-
"step": 1100
|
| 749 |
-
},
|
| 750 |
-
{
|
| 751 |
-
"epoch": 9.24,
|
| 752 |
-
"eval_loss": 0.28304105524189127,
|
| 753 |
-
"eval_runtime": 4.1728,
|
| 754 |
-
"eval_samples_per_second": 102.568,
|
| 755 |
-
"eval_steps_per_second": 12.941,
|
| 756 |
-
"step": 1100
|
| 757 |
-
},
|
| 758 |
-
{
|
| 759 |
-
"epoch": 9.33,
|
| 760 |
-
"learning_rate": 6.722689075630252e-06,
|
| 761 |
-
"loss": 0.1539,
|
| 762 |
-
"step": 1110
|
| 763 |
-
},
|
| 764 |
-
{
|
| 765 |
-
"epoch": 9.41,
|
| 766 |
-
"learning_rate": 5.882352941176471e-06,
|
| 767 |
-
"loss": 0.1517,
|
| 768 |
-
"step": 1120
|
| 769 |
-
},
|
| 770 |
-
{
|
| 771 |
-
"epoch": 9.5,
|
| 772 |
-
"learning_rate": 5.04201680672269e-06,
|
| 773 |
-
"loss": 0.1488,
|
| 774 |
-
"step": 1130
|
| 775 |
-
},
|
| 776 |
-
{
|
| 777 |
-
"epoch": 9.58,
|
| 778 |
-
"learning_rate": 4.2016806722689085e-06,
|
| 779 |
-
"loss": 0.1528,
|
| 780 |
-
"step": 1140
|
| 781 |
-
},
|
| 782 |
-
{
|
| 783 |
-
"epoch": 9.66,
|
| 784 |
-
"learning_rate": 3.361344537815126e-06,
|
| 785 |
-
"loss": 0.1478,
|
| 786 |
-
"step": 1150
|
| 787 |
-
},
|
| 788 |
-
{
|
| 789 |
-
"epoch": 9.75,
|
| 790 |
-
"learning_rate": 2.521008403361345e-06,
|
| 791 |
-
"loss": 0.1478,
|
| 792 |
-
"step": 1160
|
| 793 |
-
},
|
| 794 |
-
{
|
| 795 |
-
"epoch": 9.83,
|
| 796 |
-
"learning_rate": 1.680672268907563e-06,
|
| 797 |
-
"loss": 0.1503,
|
| 798 |
-
"step": 1170
|
| 799 |
-
},
|
| 800 |
-
{
|
| 801 |
-
"epoch": 9.92,
|
| 802 |
-
"learning_rate": 8.403361344537815e-07,
|
| 803 |
-
"loss": 0.1458,
|
| 804 |
-
"step": 1180
|
| 805 |
-
},
|
| 806 |
-
{
|
| 807 |
-
"epoch": 10.0,
|
| 808 |
-
"learning_rate": 0.0,
|
| 809 |
-
"loss": 0.1551,
|
| 810 |
-
"step": 1190
|
| 811 |
-
},
|
| 812 |
-
{
|
| 813 |
-
"epoch": 10.0,
|
| 814 |
-
"step": 1190,
|
| 815 |
-
"total_flos": 1.012892924966953e+18,
|
| 816 |
-
"train_loss": 0.22901465462035492,
|
| 817 |
-
"train_runtime": 549.9161,
|
| 818 |
-
"train_samples_per_second": 23.767,
|
| 819 |
-
"train_steps_per_second": 2.164
|
| 820 |
}
|
| 821 |
],
|
| 822 |
-
"max_steps":
|
| 823 |
-
"num_train_epochs":
|
| 824 |
-
"total_flos":
|
| 825 |
"trial_name": null,
|
| 826 |
"trial_params": null
|
| 827 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"global_step": 952,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 9.894957983193278e-05,
|
| 13 |
+
"loss": 0.5818,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.17,
|
| 18 |
+
"learning_rate": 9.789915966386555e-05,
|
| 19 |
+
"loss": 0.4739,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.25,
|
| 24 |
+
"learning_rate": 9.684873949579833e-05,
|
| 25 |
+
"loss": 0.4468,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.34,
|
| 30 |
+
"learning_rate": 9.579831932773111e-05,
|
| 31 |
+
"loss": 0.4327,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.42,
|
| 36 |
+
"learning_rate": 9.474789915966387e-05,
|
| 37 |
+
"loss": 0.4303,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.5,
|
| 42 |
+
"learning_rate": 9.369747899159664e-05,
|
| 43 |
+
"loss": 0.4184,
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.59,
|
| 48 |
+
"learning_rate": 9.264705882352942e-05,
|
| 49 |
+
"loss": 0.4001,
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.67,
|
| 54 |
+
"learning_rate": 9.159663865546218e-05,
|
| 55 |
+
"loss": 0.3856,
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.76,
|
| 60 |
+
"learning_rate": 9.054621848739496e-05,
|
| 61 |
+
"loss": 0.3843,
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.84,
|
| 66 |
+
"learning_rate": 8.949579831932774e-05,
|
| 67 |
+
"loss": 0.3751,
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.84,
|
| 72 |
+
"eval_loss": 0.3845197769571269,
|
| 73 |
+
"eval_runtime": 3.5352,
|
| 74 |
+
"eval_samples_per_second": 121.067,
|
| 75 |
+
"eval_steps_per_second": 15.275,
|
| 76 |
"step": 100
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 0.92,
|
| 80 |
+
"learning_rate": 8.84453781512605e-05,
|
| 81 |
+
"loss": 0.3852,
|
| 82 |
"step": 110
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 1.01,
|
| 86 |
+
"learning_rate": 8.739495798319329e-05,
|
| 87 |
+
"loss": 0.3678,
|
| 88 |
"step": 120
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 1.09,
|
| 92 |
+
"learning_rate": 8.634453781512606e-05,
|
| 93 |
+
"loss": 0.3489,
|
| 94 |
"step": 130
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 1.18,
|
| 98 |
+
"learning_rate": 8.529411764705883e-05,
|
| 99 |
+
"loss": 0.3346,
|
| 100 |
"step": 140
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 1.26,
|
| 104 |
+
"learning_rate": 8.42436974789916e-05,
|
| 105 |
+
"loss": 0.3417,
|
| 106 |
"step": 150
|
| 107 |
},
|
| 108 |
{
|
| 109 |
"epoch": 1.34,
|
| 110 |
+
"learning_rate": 8.319327731092437e-05,
|
| 111 |
+
"loss": 0.334,
|
| 112 |
"step": 160
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"epoch": 1.43,
|
| 116 |
+
"learning_rate": 8.214285714285714e-05,
|
| 117 |
+
"loss": 0.3318,
|
| 118 |
"step": 170
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 1.51,
|
| 122 |
+
"learning_rate": 8.109243697478992e-05,
|
| 123 |
+
"loss": 0.32,
|
| 124 |
"step": 180
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 1.6,
|
| 128 |
+
"learning_rate": 8.00420168067227e-05,
|
| 129 |
+
"loss": 0.3125,
|
| 130 |
"step": 190
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 1.68,
|
| 134 |
+
"learning_rate": 7.899159663865546e-05,
|
| 135 |
+
"loss": 0.3237,
|
| 136 |
"step": 200
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 1.68,
|
| 140 |
+
"eval_loss": 0.32147175100431824,
|
| 141 |
+
"eval_runtime": 4.3808,
|
| 142 |
+
"eval_samples_per_second": 97.7,
|
| 143 |
+
"eval_steps_per_second": 12.327,
|
| 144 |
"step": 200
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 1.76,
|
| 148 |
+
"learning_rate": 7.794117647058824e-05,
|
| 149 |
+
"loss": 0.3103,
|
| 150 |
"step": 210
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 1.85,
|
| 154 |
+
"learning_rate": 7.689075630252102e-05,
|
| 155 |
+
"loss": 0.3079,
|
| 156 |
"step": 220
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 1.93,
|
| 160 |
+
"learning_rate": 7.584033613445379e-05,
|
| 161 |
+
"loss": 0.3046,
|
| 162 |
"step": 230
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 2.02,
|
| 166 |
+
"learning_rate": 7.478991596638657e-05,
|
| 167 |
+
"loss": 0.3002,
|
| 168 |
"step": 240
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 2.1,
|
| 172 |
+
"learning_rate": 7.373949579831933e-05,
|
| 173 |
+
"loss": 0.2845,
|
| 174 |
"step": 250
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 2.18,
|
| 178 |
+
"learning_rate": 7.26890756302521e-05,
|
| 179 |
+
"loss": 0.2738,
|
| 180 |
"step": 260
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 2.27,
|
| 184 |
+
"learning_rate": 7.163865546218488e-05,
|
| 185 |
+
"loss": 0.2752,
|
| 186 |
"step": 270
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 2.35,
|
| 190 |
+
"learning_rate": 7.058823529411765e-05,
|
| 191 |
+
"loss": 0.2737,
|
| 192 |
"step": 280
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 2.44,
|
| 196 |
+
"learning_rate": 6.953781512605042e-05,
|
| 197 |
+
"loss": 0.2757,
|
| 198 |
"step": 290
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 2.52,
|
| 202 |
+
"learning_rate": 6.84873949579832e-05,
|
| 203 |
+
"loss": 0.2812,
|
| 204 |
"step": 300
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 2.52,
|
| 208 |
+
"eval_loss": 0.30918010934225554,
|
| 209 |
+
"eval_runtime": 4.0582,
|
| 210 |
+
"eval_samples_per_second": 105.466,
|
| 211 |
+
"eval_steps_per_second": 13.306,
|
| 212 |
"step": 300
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 2.61,
|
| 216 |
+
"learning_rate": 6.743697478991598e-05,
|
| 217 |
+
"loss": 0.2727,
|
| 218 |
"step": 310
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 2.69,
|
| 222 |
+
"learning_rate": 6.638655462184874e-05,
|
| 223 |
+
"loss": 0.27,
|
| 224 |
"step": 320
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 2.77,
|
| 228 |
+
"learning_rate": 6.533613445378152e-05,
|
| 229 |
+
"loss": 0.2669,
|
| 230 |
"step": 330
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 2.86,
|
| 234 |
+
"learning_rate": 6.428571428571429e-05,
|
| 235 |
+
"loss": 0.2613,
|
| 236 |
"step": 340
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 2.94,
|
| 240 |
+
"learning_rate": 6.323529411764705e-05,
|
| 241 |
+
"loss": 0.2671,
|
| 242 |
"step": 350
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 3.03,
|
| 246 |
+
"learning_rate": 6.218487394957983e-05,
|
| 247 |
+
"loss": 0.2649,
|
| 248 |
"step": 360
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 3.11,
|
| 252 |
+
"learning_rate": 6.113445378151261e-05,
|
| 253 |
+
"loss": 0.249,
|
| 254 |
"step": 370
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 3.19,
|
| 258 |
+
"learning_rate": 6.008403361344538e-05,
|
| 259 |
+
"loss": 0.2442,
|
| 260 |
"step": 380
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 3.28,
|
| 264 |
+
"learning_rate": 5.9033613445378156e-05,
|
| 265 |
+
"loss": 0.2476,
|
| 266 |
"step": 390
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 3.36,
|
| 270 |
+
"learning_rate": 5.7983193277310935e-05,
|
| 271 |
+
"loss": 0.2441,
|
| 272 |
"step": 400
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 3.36,
|
| 276 |
+
"eval_loss": 0.29600601734145254,
|
| 277 |
+
"eval_runtime": 4.0145,
|
| 278 |
+
"eval_samples_per_second": 106.614,
|
| 279 |
+
"eval_steps_per_second": 13.451,
|
| 280 |
"step": 400
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 3.45,
|
| 284 |
+
"learning_rate": 5.69327731092437e-05,
|
| 285 |
+
"loss": 0.2413,
|
| 286 |
"step": 410
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 3.53,
|
| 290 |
+
"learning_rate": 5.588235294117647e-05,
|
| 291 |
+
"loss": 0.252,
|
| 292 |
"step": 420
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 3.61,
|
| 296 |
+
"learning_rate": 5.483193277310925e-05,
|
| 297 |
+
"loss": 0.2421,
|
| 298 |
"step": 430
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 3.7,
|
| 302 |
+
"learning_rate": 5.378151260504202e-05,
|
| 303 |
+
"loss": 0.2556,
|
| 304 |
"step": 440
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 3.78,
|
| 308 |
+
"learning_rate": 5.2731092436974796e-05,
|
| 309 |
+
"loss": 0.2351,
|
| 310 |
"step": 450
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 3.87,
|
| 314 |
+
"learning_rate": 5.168067226890757e-05,
|
| 315 |
+
"loss": 0.2447,
|
| 316 |
"step": 460
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 3.95,
|
| 320 |
+
"learning_rate": 5.0630252100840334e-05,
|
| 321 |
+
"loss": 0.2365,
|
| 322 |
"step": 470
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 4.03,
|
| 326 |
+
"learning_rate": 4.957983193277311e-05,
|
| 327 |
+
"loss": 0.2312,
|
| 328 |
"step": 480
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 4.12,
|
| 332 |
+
"learning_rate": 4.8529411764705885e-05,
|
| 333 |
+
"loss": 0.2276,
|
| 334 |
"step": 490
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 4.2,
|
| 338 |
+
"learning_rate": 4.747899159663866e-05,
|
| 339 |
+
"loss": 0.2268,
|
| 340 |
"step": 500
|
| 341 |
},
|
| 342 |
{
|
| 343 |
"epoch": 4.2,
|
| 344 |
+
"eval_loss": 0.28844825865122026,
|
| 345 |
+
"eval_runtime": 4.1301,
|
| 346 |
+
"eval_samples_per_second": 103.629,
|
| 347 |
+
"eval_steps_per_second": 13.075,
|
| 348 |
"step": 500
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 4.29,
|
| 352 |
+
"learning_rate": 4.642857142857143e-05,
|
| 353 |
+
"loss": 0.2269,
|
| 354 |
"step": 510
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 4.37,
|
| 358 |
+
"learning_rate": 4.53781512605042e-05,
|
| 359 |
+
"loss": 0.2307,
|
| 360 |
"step": 520
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 4.45,
|
| 364 |
+
"learning_rate": 4.4327731092436974e-05,
|
| 365 |
+
"loss": 0.2209,
|
| 366 |
"step": 530
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 4.54,
|
| 370 |
+
"learning_rate": 4.327731092436975e-05,
|
| 371 |
+
"loss": 0.2231,
|
| 372 |
"step": 540
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 4.62,
|
| 376 |
+
"learning_rate": 4.2226890756302525e-05,
|
| 377 |
+
"loss": 0.2276,
|
| 378 |
"step": 550
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 4.71,
|
| 382 |
+
"learning_rate": 4.11764705882353e-05,
|
| 383 |
+
"loss": 0.2215,
|
| 384 |
"step": 560
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 4.79,
|
| 388 |
+
"learning_rate": 4.012605042016807e-05,
|
| 389 |
+
"loss": 0.2159,
|
| 390 |
"step": 570
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 4.87,
|
| 394 |
+
"learning_rate": 3.907563025210084e-05,
|
| 395 |
+
"loss": 0.2256,
|
| 396 |
"step": 580
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 4.96,
|
| 400 |
+
"learning_rate": 3.8025210084033614e-05,
|
| 401 |
+
"loss": 0.2209,
|
| 402 |
"step": 590
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 5.04,
|
| 406 |
+
"learning_rate": 3.697478991596639e-05,
|
| 407 |
+
"loss": 0.2236,
|
| 408 |
"step": 600
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 5.04,
|
| 412 |
+
"eval_loss": 0.28733093379126323,
|
| 413 |
+
"eval_runtime": 4.0382,
|
| 414 |
+
"eval_samples_per_second": 105.987,
|
| 415 |
+
"eval_steps_per_second": 13.372,
|
| 416 |
"step": 600
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 5.13,
|
| 420 |
+
"learning_rate": 3.592436974789916e-05,
|
| 421 |
+
"loss": 0.2134,
|
| 422 |
"step": 610
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 5.21,
|
| 426 |
+
"learning_rate": 3.487394957983193e-05,
|
| 427 |
+
"loss": 0.2092,
|
| 428 |
"step": 620
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 5.29,
|
| 432 |
+
"learning_rate": 3.382352941176471e-05,
|
| 433 |
+
"loss": 0.2103,
|
| 434 |
"step": 630
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 5.38,
|
| 438 |
+
"learning_rate": 3.277310924369748e-05,
|
| 439 |
+
"loss": 0.2131,
|
| 440 |
"step": 640
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 5.46,
|
| 444 |
+
"learning_rate": 3.1722689075630254e-05,
|
| 445 |
+
"loss": 0.2091,
|
| 446 |
"step": 650
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 5.55,
|
| 450 |
+
"learning_rate": 3.0672268907563026e-05,
|
| 451 |
+
"loss": 0.2128,
|
| 452 |
"step": 660
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 5.63,
|
| 456 |
+
"learning_rate": 2.96218487394958e-05,
|
| 457 |
+
"loss": 0.2085,
|
| 458 |
"step": 670
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 5.71,
|
| 462 |
+
"learning_rate": 2.857142857142857e-05,
|
| 463 |
+
"loss": 0.207,
|
| 464 |
"step": 680
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 5.8,
|
| 468 |
+
"learning_rate": 2.7521008403361346e-05,
|
| 469 |
+
"loss": 0.2003,
|
| 470 |
"step": 690
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 5.88,
|
| 474 |
+
"learning_rate": 2.647058823529412e-05,
|
| 475 |
+
"loss": 0.2027,
|
| 476 |
"step": 700
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 5.88,
|
| 480 |
+
"eval_loss": 0.2859314660902927,
|
| 481 |
+
"eval_runtime": 4.3959,
|
| 482 |
+
"eval_samples_per_second": 97.363,
|
| 483 |
+
"eval_steps_per_second": 12.284,
|
| 484 |
"step": 700
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 5.97,
|
| 488 |
+
"learning_rate": 2.542016806722689e-05,
|
| 489 |
+
"loss": 0.2073,
|
| 490 |
"step": 710
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 6.05,
|
| 494 |
+
"learning_rate": 2.4369747899159663e-05,
|
| 495 |
+
"loss": 0.2119,
|
| 496 |
"step": 720
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 6.13,
|
| 500 |
+
"learning_rate": 2.331932773109244e-05,
|
| 501 |
+
"loss": 0.1967,
|
| 502 |
"step": 730
|
| 503 |
},
|
| 504 |
{
|
| 505 |
"epoch": 6.22,
|
| 506 |
+
"learning_rate": 2.226890756302521e-05,
|
| 507 |
+
"loss": 0.199,
|
| 508 |
"step": 740
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 6.3,
|
| 512 |
+
"learning_rate": 2.1218487394957983e-05,
|
| 513 |
+
"loss": 0.2012,
|
| 514 |
"step": 750
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"epoch": 6.39,
|
| 518 |
+
"learning_rate": 2.016806722689076e-05,
|
| 519 |
+
"loss": 0.195,
|
| 520 |
"step": 760
|
| 521 |
},
|
| 522 |
{
|
| 523 |
"epoch": 6.47,
|
| 524 |
+
"learning_rate": 1.9117647058823528e-05,
|
| 525 |
+
"loss": 0.1952,
|
| 526 |
"step": 770
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"epoch": 6.55,
|
| 530 |
+
"learning_rate": 1.8067226890756303e-05,
|
| 531 |
+
"loss": 0.1985,
|
| 532 |
"step": 780
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 6.64,
|
| 536 |
+
"learning_rate": 1.7016806722689076e-05,
|
| 537 |
+
"loss": 0.1947,
|
| 538 |
"step": 790
|
| 539 |
},
|
| 540 |
{
|
| 541 |
"epoch": 6.72,
|
| 542 |
+
"learning_rate": 1.5966386554621848e-05,
|
| 543 |
+
"loss": 0.2024,
|
| 544 |
"step": 800
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"epoch": 6.72,
|
| 548 |
+
"eval_loss": 0.2877343659552041,
|
| 549 |
+
"eval_runtime": 3.8576,
|
| 550 |
+
"eval_samples_per_second": 110.95,
|
| 551 |
+
"eval_steps_per_second": 13.998,
|
| 552 |
"step": 800
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 6.81,
|
| 556 |
+
"learning_rate": 1.4915966386554622e-05,
|
| 557 |
+
"loss": 0.2005,
|
| 558 |
"step": 810
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 6.89,
|
| 562 |
+
"learning_rate": 1.3865546218487396e-05,
|
| 563 |
+
"loss": 0.1978,
|
| 564 |
"step": 820
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 6.97,
|
| 568 |
+
"learning_rate": 1.2815126050420168e-05,
|
| 569 |
+
"loss": 0.1956,
|
| 570 |
"step": 830
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 7.06,
|
| 574 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 575 |
+
"loss": 0.2002,
|
| 576 |
"step": 840
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 7.14,
|
| 580 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 581 |
+
"loss": 0.1944,
|
| 582 |
"step": 850
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 7.23,
|
| 586 |
+
"learning_rate": 9.663865546218488e-06,
|
| 587 |
+
"loss": 0.1948,
|
| 588 |
"step": 860
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 7.31,
|
| 592 |
+
"learning_rate": 8.61344537815126e-06,
|
| 593 |
+
"loss": 0.1934,
|
| 594 |
"step": 870
|
| 595 |
},
|
| 596 |
{
|
| 597 |
"epoch": 7.39,
|
| 598 |
+
"learning_rate": 7.563025210084033e-06,
|
| 599 |
+
"loss": 0.1954,
|
| 600 |
"step": 880
|
| 601 |
},
|
| 602 |
{
|
| 603 |
"epoch": 7.48,
|
| 604 |
+
"learning_rate": 6.512605042016807e-06,
|
| 605 |
+
"loss": 0.1972,
|
| 606 |
"step": 890
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 7.56,
|
| 610 |
+
"learning_rate": 5.46218487394958e-06,
|
| 611 |
+
"loss": 0.1952,
|
| 612 |
"step": 900
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 7.56,
|
| 616 |
+
"eval_loss": 0.28674467348030147,
|
| 617 |
+
"eval_runtime": 3.9339,
|
| 618 |
+
"eval_samples_per_second": 108.799,
|
| 619 |
+
"eval_steps_per_second": 13.727,
|
| 620 |
"step": 900
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 7.65,
|
| 624 |
+
"learning_rate": 4.411764705882353e-06,
|
| 625 |
+
"loss": 0.197,
|
| 626 |
"step": 910
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 7.73,
|
| 630 |
+
"learning_rate": 3.361344537815126e-06,
|
| 631 |
+
"loss": 0.1899,
|
| 632 |
"step": 920
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 7.82,
|
| 636 |
+
"learning_rate": 2.3109243697478996e-06,
|
| 637 |
+
"loss": 0.192,
|
| 638 |
"step": 930
|
| 639 |
},
|
| 640 |
{
|
| 641 |
"epoch": 7.9,
|
| 642 |
+
"learning_rate": 1.2605042016806724e-06,
|
| 643 |
+
"loss": 0.1943,
|
| 644 |
"step": 940
|
| 645 |
},
|
| 646 |
{
|
| 647 |
"epoch": 7.98,
|
| 648 |
+
"learning_rate": 2.1008403361344538e-07,
|
| 649 |
+
"loss": 0.1908,
|
| 650 |
"step": 950
|
| 651 |
},
|
| 652 |
{
|
| 653 |
+
"epoch": 8.0,
|
| 654 |
+
"step": 952,
|
| 655 |
+
"total_flos": 8.103143399735624e+17,
|
| 656 |
+
"train_loss": 0.2614198288559413,
|
| 657 |
+
"train_runtime": 441.6283,
|
| 658 |
+
"train_samples_per_second": 23.676,
|
| 659 |
+
"train_steps_per_second": 2.156
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 660 |
}
|
| 661 |
],
|
| 662 |
+
"max_steps": 952,
|
| 663 |
+
"num_train_epochs": 8,
|
| 664 |
+
"total_flos": 8.103143399735624e+17,
|
| 665 |
"trial_name": null,
|
| 666 |
"trial_params": null
|
| 667 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3387
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f549d21220738e5a0893f155ee14d7e13de0dbbb52c3371aa9961f37c34d0bb5
|
| 3 |
size 3387
|