End of training
Browse files- all_results.json +6 -6
- test_results.json +6 -6
- trainer_state.json +459 -1725
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second": 1.
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.04,
|
| 3 |
+
"eval_accuracy": 0.6666666666666666,
|
| 4 |
+
"eval_loss": 0.6926783919334412,
|
| 5 |
+
"eval_runtime": 163.2396,
|
| 6 |
+
"eval_samples_per_second": 1.323,
|
| 7 |
+
"eval_steps_per_second": 0.165
|
| 8 |
}
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second": 1.
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.04,
|
| 3 |
+
"eval_accuracy": 0.6666666666666666,
|
| 4 |
+
"eval_loss": 0.6926783919334412,
|
| 5 |
+
"eval_runtime": 163.2396,
|
| 6 |
+
"eval_samples_per_second": 1.323,
|
| 7 |
+
"eval_steps_per_second": 0.165
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,2159 +1,893 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "videomae-base-finetuned-subset-check10/checkpoint-896",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss": 1.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 1.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss": 1.
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss": 1.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss": 1.
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"eval_accuracy": 0.
|
| 44 |
-
"eval_loss": 1.
|
| 45 |
-
"eval_runtime": 169.
|
| 46 |
-
"eval_samples_per_second": 1.
|
| 47 |
"eval_steps_per_second": 0.165,
|
| 48 |
"step": 56
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 1.0,
|
| 52 |
-
"learning_rate":
|
| 53 |
-
"loss": 1.
|
| 54 |
"step": 60
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 1.01,
|
| 58 |
-
"learning_rate":
|
| 59 |
-
"loss": 1.
|
| 60 |
"step": 70
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"epoch": 1.
|
| 64 |
-
"learning_rate":
|
| 65 |
-
"loss": 1.
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 1.
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 1.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 1.
|
| 76 |
-
"learning_rate":
|
| 77 |
-
"loss": 1.
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
-
"epoch": 1.
|
| 82 |
-
"learning_rate":
|
| 83 |
-
"loss": 1.
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
-
"epoch": 1.
|
| 88 |
-
"eval_accuracy": 0.
|
| 89 |
-
"eval_loss": 1.
|
| 90 |
-
"eval_runtime":
|
| 91 |
-
"eval_samples_per_second": 1.
|
| 92 |
-
"eval_steps_per_second": 0.
|
| 93 |
"step": 112
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 2.
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss": 1.
|
| 99 |
"step": 120
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 2.
|
| 103 |
-
"learning_rate":
|
| 104 |
-
"loss": 1.
|
| 105 |
"step": 130
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 2.
|
| 109 |
-
"learning_rate":
|
| 110 |
-
"loss": 1.
|
| 111 |
"step": 140
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch": 2.
|
| 115 |
-
"learning_rate":
|
| 116 |
-
"loss": 1.
|
| 117 |
"step": 150
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch": 2.
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 1.
|
| 123 |
"step": 160
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 2.
|
| 127 |
-
"eval_accuracy": 0.
|
| 128 |
-
"eval_loss": 1.
|
| 129 |
-
"eval_runtime":
|
| 130 |
-
"eval_samples_per_second": 1.
|
| 131 |
-
"eval_steps_per_second": 0.
|
| 132 |
"step": 168
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 3.0,
|
| 136 |
-
"learning_rate":
|
| 137 |
-
"loss": 1.
|
| 138 |
"step": 170
|
| 139 |
},
|
| 140 |
{
|
| 141 |
-
"epoch": 3.
|
| 142 |
-
"learning_rate":
|
| 143 |
-
"loss": 1.
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
-
"epoch": 3.
|
| 148 |
-
"learning_rate":
|
| 149 |
-
"loss": 1.
|
| 150 |
"step": 190
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch": 3.
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 1.
|
| 156 |
"step": 200
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch": 3.
|
| 160 |
-
"learning_rate":
|
| 161 |
-
"loss": 1.
|
| 162 |
"step": 210
|
| 163 |
},
|
| 164 |
{
|
| 165 |
-
"epoch": 3.
|
| 166 |
-
"learning_rate":
|
| 167 |
-
"loss": 1.
|
| 168 |
"step": 220
|
| 169 |
},
|
| 170 |
{
|
| 171 |
-
"epoch": 3.
|
| 172 |
-
"eval_accuracy": 0.
|
| 173 |
-
"eval_loss": 1.
|
| 174 |
-
"eval_runtime":
|
| 175 |
-
"eval_samples_per_second": 1.
|
| 176 |
-
"eval_steps_per_second": 0.
|
| 177 |
"step": 224
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 4.
|
| 181 |
-
"learning_rate": 8.
|
| 182 |
-
"loss": 1.
|
| 183 |
"step": 230
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 4.01,
|
| 187 |
-
"learning_rate": 8.
|
| 188 |
-
"loss": 1.
|
| 189 |
"step": 240
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch": 4.
|
| 193 |
-
"learning_rate": 8.
|
| 194 |
-
"loss": 1.
|
| 195 |
"step": 250
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 4.
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 1.
|
| 201 |
"step": 260
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch": 4.
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 1.
|
| 207 |
"step": 270
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch": 4.
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 1.
|
| 213 |
"step": 280
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch": 4.
|
| 217 |
-
"eval_accuracy": 0.
|
| 218 |
-
"eval_loss": 1.
|
| 219 |
-
"eval_runtime":
|
| 220 |
-
"eval_samples_per_second": 1.
|
| 221 |
-
"eval_steps_per_second": 0.
|
| 222 |
"step": 280
|
| 223 |
},
|
| 224 |
{
|
| 225 |
-
"epoch": 5.
|
| 226 |
-
"learning_rate":
|
| 227 |
-
"loss": 1.
|
| 228 |
"step": 290
|
| 229 |
},
|
| 230 |
{
|
| 231 |
-
"epoch": 5.
|
| 232 |
-
"learning_rate":
|
| 233 |
-
"loss": 1.
|
| 234 |
"step": 300
|
| 235 |
},
|
| 236 |
{
|
| 237 |
-
"epoch": 5.
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 1.
|
| 240 |
"step": 310
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch": 5.
|
| 244 |
-
"learning_rate":
|
| 245 |
-
"loss": 1.
|
| 246 |
"step": 320
|
| 247 |
},
|
| 248 |
{
|
| 249 |
-
"epoch": 5.
|
| 250 |
-
"learning_rate":
|
| 251 |
-
"loss": 1.
|
| 252 |
"step": 330
|
| 253 |
},
|
| 254 |
{
|
| 255 |
-
"epoch": 5.
|
| 256 |
-
"eval_accuracy": 0.
|
| 257 |
-
"eval_loss": 1.
|
| 258 |
-
"eval_runtime":
|
| 259 |
-
"eval_samples_per_second": 1.
|
| 260 |
-
"eval_steps_per_second": 0.
|
| 261 |
"step": 336
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 6.0,
|
| 265 |
-
"learning_rate":
|
| 266 |
-
"loss": 1.
|
| 267 |
"step": 340
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 6.01,
|
| 271 |
-
"learning_rate":
|
| 272 |
-
"loss": 1.
|
| 273 |
"step": 350
|
| 274 |
},
|
| 275 |
{
|
| 276 |
-
"epoch": 6.
|
| 277 |
-
"learning_rate":
|
| 278 |
-
"loss": 1.
|
| 279 |
"step": 360
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch": 6.
|
| 283 |
-
"learning_rate":
|
| 284 |
-
"loss": 1.
|
| 285 |
"step": 370
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch": 6.
|
| 289 |
-
"learning_rate":
|
| 290 |
-
"loss": 1.
|
| 291 |
"step": 380
|
| 292 |
},
|
| 293 |
{
|
| 294 |
-
"epoch": 6.
|
| 295 |
-
"learning_rate":
|
| 296 |
-
"loss": 1.
|
| 297 |
"step": 390
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch": 6.
|
| 301 |
-
"eval_accuracy": 0.
|
| 302 |
-
"eval_loss": 1.
|
| 303 |
-
"eval_runtime":
|
| 304 |
-
"eval_samples_per_second": 1.
|
| 305 |
-
"eval_steps_per_second": 0.
|
| 306 |
"step": 392
|
| 307 |
},
|
| 308 |
{
|
| 309 |
-
"epoch": 7.
|
| 310 |
-
"learning_rate":
|
| 311 |
-
"loss": 1.
|
| 312 |
"step": 400
|
| 313 |
},
|
| 314 |
{
|
| 315 |
-
"epoch": 7.
|
| 316 |
-
"learning_rate":
|
| 317 |
-
"loss": 1.
|
| 318 |
"step": 410
|
| 319 |
},
|
| 320 |
{
|
| 321 |
-
"epoch": 7.
|
| 322 |
-
"learning_rate":
|
| 323 |
-
"loss": 1.
|
| 324 |
"step": 420
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch": 7.
|
| 328 |
-
"learning_rate":
|
| 329 |
-
"loss": 1.
|
| 330 |
"step": 430
|
| 331 |
},
|
| 332 |
{
|
| 333 |
-
"epoch": 7.
|
| 334 |
-
"learning_rate":
|
| 335 |
-
"loss": 1.
|
| 336 |
"step": 440
|
| 337 |
},
|
| 338 |
{
|
| 339 |
-
"epoch": 7.
|
| 340 |
-
"eval_accuracy": 0.
|
| 341 |
-
"eval_loss": 1.
|
| 342 |
-
"eval_runtime":
|
| 343 |
-
"eval_samples_per_second": 1.
|
| 344 |
-
"eval_steps_per_second": 0.
|
| 345 |
"step": 448
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 8.0,
|
| 349 |
-
"learning_rate":
|
| 350 |
-
"loss": 1.
|
| 351 |
"step": 450
|
| 352 |
},
|
| 353 |
{
|
| 354 |
-
"epoch": 8.
|
| 355 |
-
"learning_rate":
|
| 356 |
-
"loss":
|
| 357 |
"step": 460
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"epoch": 8.
|
| 361 |
-
"learning_rate":
|
| 362 |
-
"loss": 1.
|
| 363 |
"step": 470
|
| 364 |
},
|
| 365 |
{
|
| 366 |
-
"epoch": 8.
|
| 367 |
-
"learning_rate":
|
| 368 |
-
"loss": 1.
|
| 369 |
"step": 480
|
| 370 |
},
|
| 371 |
{
|
| 372 |
-
"epoch": 8.
|
| 373 |
-
"learning_rate":
|
| 374 |
-
"loss":
|
| 375 |
"step": 490
|
| 376 |
},
|
| 377 |
{
|
| 378 |
-
"epoch": 8.
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss":
|
| 381 |
"step": 500
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch": 8.
|
| 385 |
-
"eval_accuracy": 0.
|
| 386 |
-
"eval_loss":
|
| 387 |
-
"eval_runtime":
|
| 388 |
-
"eval_samples_per_second": 1.
|
| 389 |
-
"eval_steps_per_second": 0.
|
| 390 |
"step": 504
|
| 391 |
},
|
| 392 |
{
|
| 393 |
-
"epoch": 9.
|
| 394 |
-
"learning_rate":
|
| 395 |
-
"loss": 0.
|
| 396 |
"step": 510
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 9.01,
|
| 400 |
-
"learning_rate":
|
| 401 |
-
"loss": 1.
|
| 402 |
"step": 520
|
| 403 |
},
|
| 404 |
{
|
| 405 |
-
"epoch": 9.
|
| 406 |
-
"learning_rate":
|
| 407 |
-
"loss": 1.
|
| 408 |
"step": 530
|
| 409 |
},
|
| 410 |
{
|
| 411 |
-
"epoch": 9.
|
| 412 |
-
"learning_rate":
|
| 413 |
-
"loss":
|
| 414 |
"step": 540
|
| 415 |
},
|
| 416 |
{
|
| 417 |
-
"epoch": 9.
|
| 418 |
-
"learning_rate":
|
| 419 |
-
"loss":
|
| 420 |
"step": 550
|
| 421 |
},
|
| 422 |
{
|
| 423 |
-
"epoch": 9.
|
| 424 |
-
"learning_rate":
|
| 425 |
-
"loss": 1.
|
| 426 |
"step": 560
|
| 427 |
},
|
| 428 |
{
|
| 429 |
-
"epoch": 9.
|
| 430 |
-
"eval_accuracy": 0.
|
| 431 |
-
"eval_loss": 1.
|
| 432 |
-
"eval_runtime":
|
| 433 |
-
"eval_samples_per_second": 1.
|
| 434 |
-
"eval_steps_per_second": 0.
|
| 435 |
"step": 560
|
| 436 |
},
|
| 437 |
{
|
| 438 |
-
"epoch": 10.
|
| 439 |
-
"learning_rate":
|
| 440 |
-
"loss":
|
| 441 |
"step": 570
|
| 442 |
},
|
| 443 |
{
|
| 444 |
-
"epoch": 10.
|
| 445 |
-
"learning_rate":
|
| 446 |
-
"loss": 1.
|
| 447 |
"step": 580
|
| 448 |
},
|
| 449 |
{
|
| 450 |
-
"epoch": 10.
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"loss":
|
| 453 |
"step": 590
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch": 10.
|
| 457 |
-
"learning_rate":
|
| 458 |
-
"loss": 0.
|
| 459 |
"step": 600
|
| 460 |
},
|
| 461 |
{
|
| 462 |
-
"epoch": 10.
|
| 463 |
-
"learning_rate":
|
| 464 |
-
"loss": 0.
|
| 465 |
"step": 610
|
| 466 |
},
|
| 467 |
{
|
| 468 |
-
"epoch": 10.
|
| 469 |
-
"eval_accuracy": 0.
|
| 470 |
-
"eval_loss":
|
| 471 |
-
"eval_runtime":
|
| 472 |
-
"eval_samples_per_second": 1.
|
| 473 |
-
"eval_steps_per_second": 0.
|
| 474 |
"step": 616
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 11.0,
|
| 478 |
-
"learning_rate":
|
| 479 |
-
"loss": 0.
|
| 480 |
"step": 620
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 11.01,
|
| 484 |
-
"learning_rate":
|
| 485 |
-
"loss": 0.
|
| 486 |
"step": 630
|
| 487 |
},
|
| 488 |
{
|
| 489 |
-
"epoch": 11.
|
| 490 |
-
"learning_rate":
|
| 491 |
-
"loss": 0.
|
| 492 |
"step": 640
|
| 493 |
},
|
| 494 |
{
|
| 495 |
-
"epoch": 11.
|
| 496 |
-
"learning_rate":
|
| 497 |
-
"loss": 0.
|
| 498 |
"step": 650
|
| 499 |
},
|
| 500 |
{
|
| 501 |
-
"epoch": 11.
|
| 502 |
-
"learning_rate":
|
| 503 |
-
"loss": 0.
|
| 504 |
"step": 660
|
| 505 |
},
|
| 506 |
{
|
| 507 |
-
"epoch": 11.
|
| 508 |
-
"learning_rate":
|
| 509 |
-
"loss":
|
| 510 |
"step": 670
|
| 511 |
},
|
| 512 |
{
|
| 513 |
-
"epoch": 11.
|
| 514 |
-
"eval_accuracy": 0.
|
| 515 |
-
"eval_loss":
|
| 516 |
-
"eval_runtime":
|
| 517 |
-
"eval_samples_per_second": 1.
|
| 518 |
-
"eval_steps_per_second": 0.
|
| 519 |
"step": 672
|
| 520 |
},
|
| 521 |
{
|
| 522 |
-
"epoch": 12.
|
| 523 |
-
"learning_rate":
|
| 524 |
-
"loss": 0.
|
| 525 |
"step": 680
|
| 526 |
},
|
| 527 |
{
|
| 528 |
-
"epoch": 12.
|
| 529 |
-
"learning_rate":
|
| 530 |
-
"loss": 0.
|
| 531 |
"step": 690
|
| 532 |
},
|
| 533 |
{
|
| 534 |
-
"epoch": 12.
|
| 535 |
-
"learning_rate":
|
| 536 |
-
"loss": 0.
|
| 537 |
"step": 700
|
| 538 |
},
|
| 539 |
{
|
| 540 |
-
"epoch": 12.
|
| 541 |
-
"learning_rate":
|
| 542 |
-
"loss": 0.
|
| 543 |
"step": 710
|
| 544 |
},
|
| 545 |
{
|
| 546 |
-
"epoch": 12.
|
| 547 |
-
"learning_rate":
|
| 548 |
-
"loss": 0.
|
| 549 |
"step": 720
|
| 550 |
},
|
| 551 |
{
|
| 552 |
-
"epoch": 12.
|
| 553 |
-
"eval_accuracy": 0.
|
| 554 |
-
"eval_loss": 1.
|
| 555 |
-
"eval_runtime":
|
| 556 |
-
"eval_samples_per_second": 1.
|
| 557 |
-
"eval_steps_per_second": 0.
|
| 558 |
"step": 728
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 13.0,
|
| 562 |
-
"learning_rate":
|
| 563 |
-
"loss": 0.
|
| 564 |
"step": 730
|
| 565 |
},
|
| 566 |
{
|
| 567 |
-
"epoch": 13.
|
| 568 |
-
"learning_rate":
|
| 569 |
-
"loss": 0.
|
| 570 |
"step": 740
|
| 571 |
},
|
| 572 |
{
|
| 573 |
-
"epoch": 13.
|
| 574 |
-
"learning_rate":
|
| 575 |
-
"loss": 0.
|
| 576 |
"step": 750
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"epoch": 13.
|
| 580 |
-
"learning_rate":
|
| 581 |
-
"loss": 0.
|
| 582 |
"step": 760
|
| 583 |
},
|
| 584 |
{
|
| 585 |
-
"epoch": 13.
|
| 586 |
-
"learning_rate":
|
| 587 |
-
"loss": 0.
|
| 588 |
"step": 770
|
| 589 |
},
|
| 590 |
{
|
| 591 |
-
"epoch": 13.
|
| 592 |
-
"learning_rate":
|
| 593 |
-
"loss": 0.
|
| 594 |
"step": 780
|
| 595 |
},
|
| 596 |
{
|
| 597 |
-
"epoch": 13.
|
| 598 |
-
"eval_accuracy": 0.
|
| 599 |
-
"eval_loss": 0.
|
| 600 |
-
"eval_runtime": 164.
|
| 601 |
"eval_samples_per_second": 1.322,
|
| 602 |
"eval_steps_per_second": 0.171,
|
| 603 |
"step": 784
|
| 604 |
},
|
| 605 |
{
|
| 606 |
-
"epoch": 14.
|
| 607 |
-
"learning_rate":
|
| 608 |
-
"loss": 0.
|
| 609 |
"step": 790
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 14.01,
|
| 613 |
-
"learning_rate":
|
| 614 |
-
"loss": 0.
|
| 615 |
"step": 800
|
| 616 |
},
|
| 617 |
{
|
| 618 |
-
"epoch": 14.
|
| 619 |
-
"learning_rate":
|
| 620 |
-
"loss": 0.
|
| 621 |
"step": 810
|
| 622 |
},
|
| 623 |
{
|
| 624 |
-
"epoch": 14.
|
| 625 |
-
"learning_rate":
|
| 626 |
-
"loss": 0.
|
| 627 |
"step": 820
|
| 628 |
},
|
| 629 |
{
|
| 630 |
-
"epoch": 14.
|
| 631 |
-
"learning_rate":
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 830
|
| 634 |
},
|
| 635 |
{
|
| 636 |
-
"epoch": 14.
|
| 637 |
-
"learning_rate":
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 840
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch": 14.
|
| 643 |
-
"eval_accuracy": 0.
|
| 644 |
-
"eval_loss": 0.
|
| 645 |
-
"eval_runtime":
|
| 646 |
-
"eval_samples_per_second": 1.
|
| 647 |
-
"eval_steps_per_second": 0.
|
| 648 |
"step": 840
|
| 649 |
},
|
| 650 |
{
|
| 651 |
-
"epoch": 15.
|
| 652 |
-
"learning_rate":
|
| 653 |
-
"loss": 0.
|
| 654 |
"step": 850
|
| 655 |
},
|
| 656 |
{
|
| 657 |
-
"epoch": 15.
|
| 658 |
-
"learning_rate":
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 860
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"epoch": 15.
|
| 664 |
-
"learning_rate":
|
| 665 |
-
"loss": 0.
|
| 666 |
"step": 870
|
| 667 |
},
|
| 668 |
{
|
| 669 |
-
"epoch": 15.
|
| 670 |
-
"learning_rate":
|
| 671 |
-
"loss": 0.
|
| 672 |
"step": 880
|
| 673 |
},
|
| 674 |
{
|
| 675 |
-
"epoch": 15.
|
| 676 |
-
"learning_rate":
|
| 677 |
-
"loss": 0.
|
| 678 |
"step": 890
|
| 679 |
},
|
| 680 |
{
|
| 681 |
-
"epoch": 15.
|
| 682 |
-
"eval_accuracy": 0.
|
| 683 |
-
"eval_loss": 0.
|
| 684 |
-
"eval_runtime":
|
| 685 |
-
"eval_samples_per_second": 1.
|
| 686 |
-
"eval_steps_per_second": 0.
|
| 687 |
"step": 896
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 16.0,
|
| 691 |
-
"learning_rate":
|
| 692 |
-
"loss": 0.
|
| 693 |
"step": 900
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 16.01,
|
| 697 |
-
"learning_rate":
|
| 698 |
-
"loss": 0.
|
| 699 |
"step": 910
|
| 700 |
},
|
| 701 |
{
|
| 702 |
-
"epoch": 16.
|
| 703 |
-
"learning_rate":
|
| 704 |
-
"loss": 0.
|
| 705 |
"step": 920
|
| 706 |
},
|
| 707 |
{
|
| 708 |
-
"epoch": 16.
|
| 709 |
-
"learning_rate":
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 930
|
| 712 |
},
|
| 713 |
{
|
| 714 |
-
"epoch": 16.
|
| 715 |
-
"learning_rate":
|
| 716 |
-
"loss": 0.
|
| 717 |
"step": 940
|
| 718 |
},
|
| 719 |
{
|
| 720 |
-
"epoch": 16.
|
| 721 |
-
"learning_rate":
|
| 722 |
-
"loss": 0.
|
| 723 |
"step": 950
|
| 724 |
},
|
| 725 |
{
|
| 726 |
-
"epoch": 16.
|
| 727 |
-
"eval_accuracy": 0.
|
| 728 |
-
"eval_loss":
|
| 729 |
-
"eval_runtime":
|
| 730 |
-
"eval_samples_per_second": 1.
|
| 731 |
-
"eval_steps_per_second": 0.
|
| 732 |
"step": 952
|
| 733 |
},
|
| 734 |
{
|
| 735 |
-
"epoch": 17.
|
| 736 |
-
"learning_rate":
|
| 737 |
-
"loss": 0.
|
| 738 |
"step": 960
|
| 739 |
},
|
| 740 |
{
|
| 741 |
-
"epoch": 17.
|
| 742 |
-
"learning_rate":
|
| 743 |
-
"loss": 0.
|
| 744 |
"step": 970
|
| 745 |
},
|
| 746 |
{
|
| 747 |
-
"epoch": 17.
|
| 748 |
-
"learning_rate":
|
| 749 |
-
"loss": 0.
|
| 750 |
"step": 980
|
| 751 |
},
|
| 752 |
{
|
| 753 |
-
"epoch": 17.
|
| 754 |
-
"learning_rate":
|
| 755 |
-
"loss": 0.
|
| 756 |
"step": 990
|
| 757 |
},
|
| 758 |
{
|
| 759 |
-
"epoch": 17.
|
| 760 |
-
"learning_rate":
|
| 761 |
-
"loss": 0.
|
| 762 |
"step": 1000
|
| 763 |
},
|
| 764 |
{
|
| 765 |
-
"epoch": 17.
|
| 766 |
-
"eval_accuracy": 0.
|
| 767 |
-
"eval_loss": 0.
|
| 768 |
-
"eval_runtime":
|
| 769 |
-
"eval_samples_per_second": 1.
|
| 770 |
-
"eval_steps_per_second": 0.
|
| 771 |
"step": 1008
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 18.0,
|
| 775 |
-
"learning_rate":
|
| 776 |
-
"loss": 0.
|
| 777 |
"step": 1010
|
| 778 |
},
|
| 779 |
{
|
| 780 |
-
"epoch": 18.
|
| 781 |
-
"learning_rate":
|
| 782 |
-
"loss": 0.
|
| 783 |
"step": 1020
|
| 784 |
},
|
| 785 |
{
|
| 786 |
-
"epoch": 18.
|
| 787 |
-
"learning_rate":
|
| 788 |
-
"loss": 0.
|
| 789 |
"step": 1030
|
| 790 |
},
|
| 791 |
{
|
| 792 |
-
"epoch": 18.
|
| 793 |
-
"learning_rate":
|
| 794 |
-
"loss": 0.
|
| 795 |
"step": 1040
|
| 796 |
},
|
| 797 |
{
|
| 798 |
-
"epoch": 18.
|
| 799 |
-
"learning_rate": 6.
|
| 800 |
-
"loss": 0.
|
| 801 |
"step": 1050
|
| 802 |
},
|
| 803 |
{
|
| 804 |
-
"epoch": 18.
|
| 805 |
-
"learning_rate":
|
| 806 |
-
"loss": 0.
|
| 807 |
"step": 1060
|
| 808 |
},
|
| 809 |
{
|
| 810 |
-
"epoch": 18.
|
| 811 |
-
"eval_accuracy": 0.
|
| 812 |
-
"eval_loss": 0.
|
| 813 |
-
"eval_runtime":
|
| 814 |
-
"eval_samples_per_second": 1.
|
| 815 |
-
"eval_steps_per_second": 0.
|
| 816 |
"step": 1064
|
| 817 |
},
|
| 818 |
{
|
| 819 |
-
"epoch": 19.
|
| 820 |
-
"learning_rate":
|
| 821 |
-
"loss": 0.
|
| 822 |
"step": 1070
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 19.01,
|
| 826 |
-
"learning_rate":
|
| 827 |
-
"loss": 0.
|
| 828 |
"step": 1080
|
| 829 |
},
|
| 830 |
{
|
| 831 |
-
"epoch": 19.
|
| 832 |
-
"learning_rate":
|
| 833 |
-
"loss": 0.
|
| 834 |
"step": 1090
|
| 835 |
},
|
| 836 |
{
|
| 837 |
-
"epoch": 19.
|
| 838 |
-
"learning_rate":
|
| 839 |
-
"loss": 0.
|
| 840 |
"step": 1100
|
| 841 |
},
|
| 842 |
{
|
| 843 |
-
"epoch": 19.
|
| 844 |
-
"learning_rate":
|
| 845 |
-
"loss": 0.
|
| 846 |
"step": 1110
|
| 847 |
},
|
| 848 |
{
|
| 849 |
-
"epoch": 19.
|
| 850 |
-
"
|
| 851 |
-
"
|
| 852 |
-
"
|
| 853 |
-
|
| 854 |
-
|
| 855 |
-
"
|
| 856 |
-
"eval_accuracy": 0.6175115207373272,
|
| 857 |
-
"eval_loss": 0.9288573861122131,
|
| 858 |
-
"eval_runtime": 163.2915,
|
| 859 |
-
"eval_samples_per_second": 1.329,
|
| 860 |
-
"eval_steps_per_second": 0.171,
|
| 861 |
-
"step": 1120
|
| 862 |
-
},
|
| 863 |
-
{
|
| 864 |
-
"epoch": 20.0,
|
| 865 |
-
"learning_rate": 6.587905486583901e-06,
|
| 866 |
-
"loss": 0.7905,
|
| 867 |
-
"step": 1130
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 20.01,
|
| 871 |
-
"learning_rate": 6.547857428914698e-06,
|
| 872 |
-
"loss": 0.7592,
|
| 873 |
-
"step": 1140
|
| 874 |
-
},
|
| 875 |
-
{
|
| 876 |
-
"epoch": 20.01,
|
| 877 |
-
"learning_rate": 6.507809371245495e-06,
|
| 878 |
-
"loss": 0.7639,
|
| 879 |
-
"step": 1150
|
| 880 |
-
},
|
| 881 |
-
{
|
| 882 |
-
"epoch": 20.01,
|
| 883 |
-
"learning_rate": 6.4677613135762915e-06,
|
| 884 |
-
"loss": 0.7202,
|
| 885 |
-
"step": 1160
|
| 886 |
-
},
|
| 887 |
-
{
|
| 888 |
-
"epoch": 20.02,
|
| 889 |
-
"learning_rate": 6.427713255907089e-06,
|
| 890 |
-
"loss": 0.7443,
|
| 891 |
-
"step": 1170
|
| 892 |
-
},
|
| 893 |
-
{
|
| 894 |
-
"epoch": 20.02,
|
| 895 |
-
"eval_accuracy": 0.511520737327189,
|
| 896 |
-
"eval_loss": 1.2425593137741089,
|
| 897 |
-
"eval_runtime": 165.1561,
|
| 898 |
-
"eval_samples_per_second": 1.314,
|
| 899 |
-
"eval_steps_per_second": 0.17,
|
| 900 |
-
"step": 1176
|
| 901 |
-
},
|
| 902 |
-
{
|
| 903 |
-
"epoch": 21.0,
|
| 904 |
-
"learning_rate": 6.387665198237886e-06,
|
| 905 |
-
"loss": 0.7448,
|
| 906 |
-
"step": 1180
|
| 907 |
-
},
|
| 908 |
-
{
|
| 909 |
-
"epoch": 21.01,
|
| 910 |
-
"learning_rate": 6.347617140568683e-06,
|
| 911 |
-
"loss": 0.6349,
|
| 912 |
-
"step": 1190
|
| 913 |
-
},
|
| 914 |
-
{
|
| 915 |
-
"epoch": 21.01,
|
| 916 |
-
"learning_rate": 6.307569082899479e-06,
|
| 917 |
-
"loss": 0.672,
|
| 918 |
-
"step": 1200
|
| 919 |
-
},
|
| 920 |
-
{
|
| 921 |
-
"epoch": 21.01,
|
| 922 |
-
"learning_rate": 6.267521025230276e-06,
|
| 923 |
-
"loss": 0.5567,
|
| 924 |
-
"step": 1210
|
| 925 |
-
},
|
| 926 |
-
{
|
| 927 |
-
"epoch": 21.02,
|
| 928 |
-
"learning_rate": 6.227472967561074e-06,
|
| 929 |
-
"loss": 0.809,
|
| 930 |
-
"step": 1220
|
| 931 |
},
|
| 932 |
{
|
| 933 |
-
"epoch":
|
| 934 |
-
"
|
| 935 |
-
"
|
| 936 |
-
"
|
|
|
|
|
|
|
|
|
|
| 937 |
},
|
| 938 |
{
|
| 939 |
-
"epoch":
|
| 940 |
-
"eval_accuracy": 0.
|
| 941 |
-
"eval_loss":
|
| 942 |
-
"eval_runtime":
|
| 943 |
"eval_samples_per_second": 1.312,
|
| 944 |
-
"eval_steps_per_second": 0.169,
|
| 945 |
-
"step": 1232
|
| 946 |
-
},
|
| 947 |
-
{
|
| 948 |
-
"epoch": 22.0,
|
| 949 |
-
"learning_rate": 6.147376852222667e-06,
|
| 950 |
-
"loss": 0.5671,
|
| 951 |
-
"step": 1240
|
| 952 |
-
},
|
| 953 |
-
{
|
| 954 |
-
"epoch": 22.01,
|
| 955 |
-
"learning_rate": 6.107328794553464e-06,
|
| 956 |
-
"loss": 0.6794,
|
| 957 |
-
"step": 1250
|
| 958 |
-
},
|
| 959 |
-
{
|
| 960 |
-
"epoch": 22.01,
|
| 961 |
-
"learning_rate": 6.067280736884261e-06,
|
| 962 |
-
"loss": 0.7263,
|
| 963 |
-
"step": 1260
|
| 964 |
-
},
|
| 965 |
-
{
|
| 966 |
-
"epoch": 22.01,
|
| 967 |
-
"learning_rate": 6.027232679215058e-06,
|
| 968 |
-
"loss": 0.6543,
|
| 969 |
-
"step": 1270
|
| 970 |
-
},
|
| 971 |
-
{
|
| 972 |
-
"epoch": 22.02,
|
| 973 |
-
"learning_rate": 5.987184621545855e-06,
|
| 974 |
-
"loss": 0.7503,
|
| 975 |
-
"step": 1280
|
| 976 |
-
},
|
| 977 |
-
{
|
| 978 |
-
"epoch": 22.02,
|
| 979 |
-
"eval_accuracy": 0.4792626728110599,
|
| 980 |
-
"eval_loss": 1.4511420726776123,
|
| 981 |
-
"eval_runtime": 163.4694,
|
| 982 |
-
"eval_samples_per_second": 1.327,
|
| 983 |
-
"eval_steps_per_second": 0.171,
|
| 984 |
-
"step": 1288
|
| 985 |
-
},
|
| 986 |
-
{
|
| 987 |
-
"epoch": 23.0,
|
| 988 |
-
"learning_rate": 5.947136563876652e-06,
|
| 989 |
-
"loss": 0.7247,
|
| 990 |
-
"step": 1290
|
| 991 |
-
},
|
| 992 |
-
{
|
| 993 |
-
"epoch": 23.0,
|
| 994 |
-
"learning_rate": 5.907088506207449e-06,
|
| 995 |
-
"loss": 0.6522,
|
| 996 |
-
"step": 1300
|
| 997 |
-
},
|
| 998 |
-
{
|
| 999 |
-
"epoch": 23.01,
|
| 1000 |
-
"learning_rate": 5.867040448538246e-06,
|
| 1001 |
-
"loss": 0.6363,
|
| 1002 |
-
"step": 1310
|
| 1003 |
-
},
|
| 1004 |
-
{
|
| 1005 |
-
"epoch": 23.01,
|
| 1006 |
-
"learning_rate": 5.826992390869043e-06,
|
| 1007 |
-
"loss": 0.7127,
|
| 1008 |
-
"step": 1320
|
| 1009 |
-
},
|
| 1010 |
-
{
|
| 1011 |
-
"epoch": 23.02,
|
| 1012 |
-
"learning_rate": 5.78694433319984e-06,
|
| 1013 |
-
"loss": 0.5885,
|
| 1014 |
-
"step": 1330
|
| 1015 |
-
},
|
| 1016 |
-
{
|
| 1017 |
-
"epoch": 23.02,
|
| 1018 |
-
"learning_rate": 5.746896275530637e-06,
|
| 1019 |
-
"loss": 0.6529,
|
| 1020 |
-
"step": 1340
|
| 1021 |
-
},
|
| 1022 |
-
{
|
| 1023 |
-
"epoch": 23.02,
|
| 1024 |
-
"eval_accuracy": 0.6866359447004609,
|
| 1025 |
-
"eval_loss": 0.9009619951248169,
|
| 1026 |
-
"eval_runtime": 171.0268,
|
| 1027 |
-
"eval_samples_per_second": 1.269,
|
| 1028 |
"eval_steps_per_second": 0.164,
|
| 1029 |
-
"step":
|
| 1030 |
-
},
|
| 1031 |
-
{
|
| 1032 |
-
"epoch": 24.0,
|
| 1033 |
-
"learning_rate": 5.706848217861433e-06,
|
| 1034 |
-
"loss": 0.5402,
|
| 1035 |
-
"step": 1350
|
| 1036 |
-
},
|
| 1037 |
-
{
|
| 1038 |
-
"epoch": 24.01,
|
| 1039 |
-
"learning_rate": 5.666800160192231e-06,
|
| 1040 |
-
"loss": 0.6978,
|
| 1041 |
-
"step": 1360
|
| 1042 |
-
},
|
| 1043 |
-
{
|
| 1044 |
-
"epoch": 24.01,
|
| 1045 |
-
"learning_rate": 5.626752102523028e-06,
|
| 1046 |
-
"loss": 0.6435,
|
| 1047 |
-
"step": 1370
|
| 1048 |
-
},
|
| 1049 |
-
{
|
| 1050 |
-
"epoch": 24.01,
|
| 1051 |
-
"learning_rate": 5.5867040448538245e-06,
|
| 1052 |
-
"loss": 0.6665,
|
| 1053 |
-
"step": 1380
|
| 1054 |
-
},
|
| 1055 |
-
{
|
| 1056 |
-
"epoch": 24.02,
|
| 1057 |
-
"learning_rate": 5.546655987184621e-06,
|
| 1058 |
-
"loss": 0.805,
|
| 1059 |
-
"step": 1390
|
| 1060 |
-
},
|
| 1061 |
-
{
|
| 1062 |
-
"epoch": 24.02,
|
| 1063 |
-
"learning_rate": 5.506607929515418e-06,
|
| 1064 |
-
"loss": 0.6001,
|
| 1065 |
-
"step": 1400
|
| 1066 |
-
},
|
| 1067 |
-
{
|
| 1068 |
-
"epoch": 24.02,
|
| 1069 |
-
"eval_accuracy": 0.6129032258064516,
|
| 1070 |
-
"eval_loss": 0.9717797040939331,
|
| 1071 |
-
"eval_runtime": 163.6301,
|
| 1072 |
-
"eval_samples_per_second": 1.326,
|
| 1073 |
-
"eval_steps_per_second": 0.171,
|
| 1074 |
-
"step": 1400
|
| 1075 |
-
},
|
| 1076 |
-
{
|
| 1077 |
-
"epoch": 25.0,
|
| 1078 |
-
"learning_rate": 5.466559871846216e-06,
|
| 1079 |
-
"loss": 0.6452,
|
| 1080 |
-
"step": 1410
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
-
"epoch":
|
| 1084 |
-
"
|
| 1085 |
-
"
|
| 1086 |
-
"
|
| 1087 |
-
|
| 1088 |
-
|
| 1089 |
-
"
|
| 1090 |
-
"learning_rate": 5.386463756507809e-06,
|
| 1091 |
-
"loss": 0.7066,
|
| 1092 |
-
"step": 1430
|
| 1093 |
-
},
|
| 1094 |
-
{
|
| 1095 |
-
"epoch": 25.01,
|
| 1096 |
-
"learning_rate": 5.346415698838606e-06,
|
| 1097 |
-
"loss": 0.543,
|
| 1098 |
-
"step": 1440
|
| 1099 |
-
},
|
| 1100 |
-
{
|
| 1101 |
-
"epoch": 25.02,
|
| 1102 |
-
"learning_rate": 5.306367641169404e-06,
|
| 1103 |
-
"loss": 0.55,
|
| 1104 |
-
"step": 1450
|
| 1105 |
-
},
|
| 1106 |
-
{
|
| 1107 |
-
"epoch": 25.02,
|
| 1108 |
-
"eval_accuracy": 0.4377880184331797,
|
| 1109 |
-
"eval_loss": 1.3723992109298706,
|
| 1110 |
-
"eval_runtime": 164.6177,
|
| 1111 |
-
"eval_samples_per_second": 1.318,
|
| 1112 |
-
"eval_steps_per_second": 0.17,
|
| 1113 |
-
"step": 1456
|
| 1114 |
-
},
|
| 1115 |
-
{
|
| 1116 |
-
"epoch": 26.0,
|
| 1117 |
-
"learning_rate": 5.2663195835002e-06,
|
| 1118 |
-
"loss": 0.6087,
|
| 1119 |
-
"step": 1460
|
| 1120 |
-
},
|
| 1121 |
-
{
|
| 1122 |
-
"epoch": 26.01,
|
| 1123 |
-
"learning_rate": 5.226271525830998e-06,
|
| 1124 |
-
"loss": 0.6169,
|
| 1125 |
-
"step": 1470
|
| 1126 |
-
},
|
| 1127 |
-
{
|
| 1128 |
-
"epoch": 26.01,
|
| 1129 |
-
"learning_rate": 5.186223468161795e-06,
|
| 1130 |
-
"loss": 0.9426,
|
| 1131 |
-
"step": 1480
|
| 1132 |
-
},
|
| 1133 |
-
{
|
| 1134 |
-
"epoch": 26.01,
|
| 1135 |
-
"learning_rate": 5.146175410492592e-06,
|
| 1136 |
-
"loss": 0.4587,
|
| 1137 |
-
"step": 1490
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 26.02,
|
| 1141 |
-
"learning_rate": 5.106127352823389e-06,
|
| 1142 |
-
"loss": 0.6725,
|
| 1143 |
-
"step": 1500
|
| 1144 |
-
},
|
| 1145 |
-
{
|
| 1146 |
-
"epoch": 26.02,
|
| 1147 |
-
"learning_rate": 5.066079295154186e-06,
|
| 1148 |
-
"loss": 0.7328,
|
| 1149 |
-
"step": 1510
|
| 1150 |
-
},
|
| 1151 |
-
{
|
| 1152 |
-
"epoch": 26.02,
|
| 1153 |
-
"eval_accuracy": 0.4930875576036866,
|
| 1154 |
-
"eval_loss": 1.2508519887924194,
|
| 1155 |
-
"eval_runtime": 165.1191,
|
| 1156 |
-
"eval_samples_per_second": 1.314,
|
| 1157 |
-
"eval_steps_per_second": 0.17,
|
| 1158 |
-
"step": 1512
|
| 1159 |
-
},
|
| 1160 |
-
{
|
| 1161 |
-
"epoch": 27.0,
|
| 1162 |
-
"learning_rate": 5.026031237484983e-06,
|
| 1163 |
-
"loss": 0.4386,
|
| 1164 |
-
"step": 1520
|
| 1165 |
-
},
|
| 1166 |
-
{
|
| 1167 |
-
"epoch": 27.01,
|
| 1168 |
-
"learning_rate": 4.985983179815779e-06,
|
| 1169 |
-
"loss": 0.5087,
|
| 1170 |
-
"step": 1530
|
| 1171 |
-
},
|
| 1172 |
-
{
|
| 1173 |
-
"epoch": 27.01,
|
| 1174 |
-
"learning_rate": 4.945935122146576e-06,
|
| 1175 |
-
"loss": 0.8035,
|
| 1176 |
-
"step": 1540
|
| 1177 |
-
},
|
| 1178 |
-
{
|
| 1179 |
-
"epoch": 27.01,
|
| 1180 |
-
"learning_rate": 4.905887064477373e-06,
|
| 1181 |
-
"loss": 0.6609,
|
| 1182 |
-
"step": 1550
|
| 1183 |
-
},
|
| 1184 |
-
{
|
| 1185 |
-
"epoch": 27.02,
|
| 1186 |
-
"learning_rate": 4.86583900680817e-06,
|
| 1187 |
-
"loss": 0.5754,
|
| 1188 |
-
"step": 1560
|
| 1189 |
-
},
|
| 1190 |
-
{
|
| 1191 |
-
"epoch": 27.02,
|
| 1192 |
-
"eval_accuracy": 0.663594470046083,
|
| 1193 |
-
"eval_loss": 0.9112865924835205,
|
| 1194 |
-
"eval_runtime": 163.6522,
|
| 1195 |
-
"eval_samples_per_second": 1.326,
|
| 1196 |
-
"eval_steps_per_second": 0.171,
|
| 1197 |
-
"step": 1568
|
| 1198 |
-
},
|
| 1199 |
-
{
|
| 1200 |
-
"epoch": 28.0,
|
| 1201 |
-
"learning_rate": 4.825790949138967e-06,
|
| 1202 |
-
"loss": 0.7097,
|
| 1203 |
-
"step": 1570
|
| 1204 |
-
},
|
| 1205 |
-
{
|
| 1206 |
-
"epoch": 28.0,
|
| 1207 |
-
"learning_rate": 4.785742891469764e-06,
|
| 1208 |
-
"loss": 0.5724,
|
| 1209 |
-
"step": 1580
|
| 1210 |
-
},
|
| 1211 |
-
{
|
| 1212 |
-
"epoch": 28.01,
|
| 1213 |
-
"learning_rate": 4.745694833800561e-06,
|
| 1214 |
-
"loss": 0.666,
|
| 1215 |
-
"step": 1590
|
| 1216 |
-
},
|
| 1217 |
-
{
|
| 1218 |
-
"epoch": 28.01,
|
| 1219 |
-
"learning_rate": 4.705646776131358e-06,
|
| 1220 |
-
"loss": 0.7482,
|
| 1221 |
-
"step": 1600
|
| 1222 |
-
},
|
| 1223 |
-
{
|
| 1224 |
-
"epoch": 28.02,
|
| 1225 |
-
"learning_rate": 4.665598718462155e-06,
|
| 1226 |
-
"loss": 0.7556,
|
| 1227 |
-
"step": 1610
|
| 1228 |
-
},
|
| 1229 |
-
{
|
| 1230 |
-
"epoch": 28.02,
|
| 1231 |
-
"learning_rate": 4.625550660792952e-06,
|
| 1232 |
-
"loss": 0.6717,
|
| 1233 |
-
"step": 1620
|
| 1234 |
-
},
|
| 1235 |
-
{
|
| 1236 |
-
"epoch": 28.02,
|
| 1237 |
-
"eval_accuracy": 0.5345622119815668,
|
| 1238 |
-
"eval_loss": 1.0872467756271362,
|
| 1239 |
-
"eval_runtime": 163.65,
|
| 1240 |
-
"eval_samples_per_second": 1.326,
|
| 1241 |
-
"eval_steps_per_second": 0.171,
|
| 1242 |
-
"step": 1624
|
| 1243 |
-
},
|
| 1244 |
-
{
|
| 1245 |
-
"epoch": 29.0,
|
| 1246 |
-
"learning_rate": 4.585502603123749e-06,
|
| 1247 |
-
"loss": 0.7058,
|
| 1248 |
-
"step": 1630
|
| 1249 |
-
},
|
| 1250 |
-
{
|
| 1251 |
-
"epoch": 29.01,
|
| 1252 |
-
"learning_rate": 4.5454545454545455e-06,
|
| 1253 |
-
"loss": 0.6564,
|
| 1254 |
-
"step": 1640
|
| 1255 |
-
},
|
| 1256 |
-
{
|
| 1257 |
-
"epoch": 29.01,
|
| 1258 |
-
"learning_rate": 4.505406487785342e-06,
|
| 1259 |
-
"loss": 0.5864,
|
| 1260 |
-
"step": 1650
|
| 1261 |
-
},
|
| 1262 |
-
{
|
| 1263 |
-
"epoch": 29.01,
|
| 1264 |
-
"learning_rate": 4.46535843011614e-06,
|
| 1265 |
-
"loss": 0.751,
|
| 1266 |
-
"step": 1660
|
| 1267 |
-
},
|
| 1268 |
-
{
|
| 1269 |
-
"epoch": 29.02,
|
| 1270 |
-
"learning_rate": 4.425310372446937e-06,
|
| 1271 |
-
"loss": 0.6114,
|
| 1272 |
-
"step": 1670
|
| 1273 |
-
},
|
| 1274 |
-
{
|
| 1275 |
-
"epoch": 29.02,
|
| 1276 |
-
"learning_rate": 4.3852623147777334e-06,
|
| 1277 |
-
"loss": 0.8697,
|
| 1278 |
-
"step": 1680
|
| 1279 |
-
},
|
| 1280 |
-
{
|
| 1281 |
-
"epoch": 29.02,
|
| 1282 |
-
"eval_accuracy": 0.663594470046083,
|
| 1283 |
-
"eval_loss": 0.8410985469818115,
|
| 1284 |
-
"eval_runtime": 163.2869,
|
| 1285 |
-
"eval_samples_per_second": 1.329,
|
| 1286 |
-
"eval_steps_per_second": 0.171,
|
| 1287 |
-
"step": 1680
|
| 1288 |
-
},
|
| 1289 |
-
{
|
| 1290 |
-
"epoch": 30.0,
|
| 1291 |
-
"learning_rate": 4.34521425710853e-06,
|
| 1292 |
-
"loss": 0.5641,
|
| 1293 |
-
"step": 1690
|
| 1294 |
-
},
|
| 1295 |
-
{
|
| 1296 |
-
"epoch": 30.01,
|
| 1297 |
-
"learning_rate": 4.305166199439327e-06,
|
| 1298 |
-
"loss": 0.6042,
|
| 1299 |
-
"step": 1700
|
| 1300 |
-
},
|
| 1301 |
-
{
|
| 1302 |
-
"epoch": 30.01,
|
| 1303 |
-
"learning_rate": 4.2651181417701246e-06,
|
| 1304 |
-
"loss": 0.6321,
|
| 1305 |
-
"step": 1710
|
| 1306 |
-
},
|
| 1307 |
-
{
|
| 1308 |
-
"epoch": 30.01,
|
| 1309 |
-
"learning_rate": 4.225070084100921e-06,
|
| 1310 |
-
"loss": 0.5942,
|
| 1311 |
-
"step": 1720
|
| 1312 |
-
},
|
| 1313 |
-
{
|
| 1314 |
-
"epoch": 30.02,
|
| 1315 |
-
"learning_rate": 4.185022026431718e-06,
|
| 1316 |
-
"loss": 0.4557,
|
| 1317 |
-
"step": 1730
|
| 1318 |
-
},
|
| 1319 |
-
{
|
| 1320 |
-
"epoch": 30.02,
|
| 1321 |
-
"eval_accuracy": 0.5852534562211982,
|
| 1322 |
-
"eval_loss": 1.0334526300430298,
|
| 1323 |
-
"eval_runtime": 164.4022,
|
| 1324 |
-
"eval_samples_per_second": 1.32,
|
| 1325 |
-
"eval_steps_per_second": 0.17,
|
| 1326 |
-
"step": 1736
|
| 1327 |
-
},
|
| 1328 |
-
{
|
| 1329 |
-
"epoch": 31.0,
|
| 1330 |
-
"learning_rate": 4.144973968762515e-06,
|
| 1331 |
-
"loss": 0.5802,
|
| 1332 |
-
"step": 1740
|
| 1333 |
-
},
|
| 1334 |
-
{
|
| 1335 |
-
"epoch": 31.01,
|
| 1336 |
-
"learning_rate": 4.1049259110933125e-06,
|
| 1337 |
-
"loss": 0.8083,
|
| 1338 |
-
"step": 1750
|
| 1339 |
-
},
|
| 1340 |
-
{
|
| 1341 |
-
"epoch": 31.01,
|
| 1342 |
-
"learning_rate": 4.064877853424109e-06,
|
| 1343 |
-
"loss": 0.5083,
|
| 1344 |
-
"step": 1760
|
| 1345 |
-
},
|
| 1346 |
-
{
|
| 1347 |
-
"epoch": 31.01,
|
| 1348 |
-
"learning_rate": 4.024829795754906e-06,
|
| 1349 |
-
"loss": 0.782,
|
| 1350 |
-
"step": 1770
|
| 1351 |
-
},
|
| 1352 |
-
{
|
| 1353 |
-
"epoch": 31.02,
|
| 1354 |
-
"learning_rate": 3.984781738085703e-06,
|
| 1355 |
-
"loss": 0.6633,
|
| 1356 |
-
"step": 1780
|
| 1357 |
-
},
|
| 1358 |
-
{
|
| 1359 |
-
"epoch": 31.02,
|
| 1360 |
-
"learning_rate": 3.9447336804165e-06,
|
| 1361 |
-
"loss": 0.4873,
|
| 1362 |
-
"step": 1790
|
| 1363 |
-
},
|
| 1364 |
-
{
|
| 1365 |
-
"epoch": 31.02,
|
| 1366 |
-
"eval_accuracy": 0.5299539170506913,
|
| 1367 |
-
"eval_loss": 1.154846429824829,
|
| 1368 |
-
"eval_runtime": 164.5771,
|
| 1369 |
-
"eval_samples_per_second": 1.319,
|
| 1370 |
-
"eval_steps_per_second": 0.17,
|
| 1371 |
-
"step": 1792
|
| 1372 |
-
},
|
| 1373 |
-
{
|
| 1374 |
-
"epoch": 32.0,
|
| 1375 |
-
"learning_rate": 3.904685622747297e-06,
|
| 1376 |
-
"loss": 0.569,
|
| 1377 |
-
"step": 1800
|
| 1378 |
-
},
|
| 1379 |
-
{
|
| 1380 |
-
"epoch": 32.01,
|
| 1381 |
-
"learning_rate": 3.864637565078094e-06,
|
| 1382 |
-
"loss": 0.5574,
|
| 1383 |
-
"step": 1810
|
| 1384 |
-
},
|
| 1385 |
-
{
|
| 1386 |
-
"epoch": 32.01,
|
| 1387 |
-
"learning_rate": 3.8245895074088915e-06,
|
| 1388 |
-
"loss": 0.5999,
|
| 1389 |
-
"step": 1820
|
| 1390 |
-
},
|
| 1391 |
-
{
|
| 1392 |
-
"epoch": 32.01,
|
| 1393 |
-
"learning_rate": 3.7845414497396883e-06,
|
| 1394 |
-
"loss": 0.6882,
|
| 1395 |
-
"step": 1830
|
| 1396 |
-
},
|
| 1397 |
-
{
|
| 1398 |
-
"epoch": 32.02,
|
| 1399 |
-
"learning_rate": 3.744493392070485e-06,
|
| 1400 |
-
"loss": 0.7812,
|
| 1401 |
-
"step": 1840
|
| 1402 |
-
},
|
| 1403 |
-
{
|
| 1404 |
-
"epoch": 32.02,
|
| 1405 |
-
"eval_accuracy": 0.5990783410138248,
|
| 1406 |
-
"eval_loss": 1.036067247390747,
|
| 1407 |
-
"eval_runtime": 165.0007,
|
| 1408 |
-
"eval_samples_per_second": 1.315,
|
| 1409 |
-
"eval_steps_per_second": 0.17,
|
| 1410 |
-
"step": 1848
|
| 1411 |
-
},
|
| 1412 |
-
{
|
| 1413 |
-
"epoch": 33.0,
|
| 1414 |
-
"learning_rate": 3.7044453344012823e-06,
|
| 1415 |
-
"loss": 0.6552,
|
| 1416 |
-
"step": 1850
|
| 1417 |
-
},
|
| 1418 |
-
{
|
| 1419 |
-
"epoch": 33.0,
|
| 1420 |
-
"learning_rate": 3.664397276732079e-06,
|
| 1421 |
-
"loss": 0.724,
|
| 1422 |
-
"step": 1860
|
| 1423 |
-
},
|
| 1424 |
-
{
|
| 1425 |
-
"epoch": 33.01,
|
| 1426 |
-
"learning_rate": 3.6243492190628758e-06,
|
| 1427 |
-
"loss": 0.6444,
|
| 1428 |
-
"step": 1870
|
| 1429 |
-
},
|
| 1430 |
-
{
|
| 1431 |
-
"epoch": 33.01,
|
| 1432 |
-
"learning_rate": 3.584301161393673e-06,
|
| 1433 |
-
"loss": 0.5467,
|
| 1434 |
-
"step": 1880
|
| 1435 |
-
},
|
| 1436 |
-
{
|
| 1437 |
-
"epoch": 33.02,
|
| 1438 |
-
"learning_rate": 3.5442531037244697e-06,
|
| 1439 |
-
"loss": 0.4304,
|
| 1440 |
-
"step": 1890
|
| 1441 |
-
},
|
| 1442 |
-
{
|
| 1443 |
-
"epoch": 33.02,
|
| 1444 |
-
"learning_rate": 3.504205046055267e-06,
|
| 1445 |
-
"loss": 0.5975,
|
| 1446 |
-
"step": 1900
|
| 1447 |
-
},
|
| 1448 |
-
{
|
| 1449 |
-
"epoch": 33.02,
|
| 1450 |
-
"eval_accuracy": 0.5253456221198156,
|
| 1451 |
-
"eval_loss": 1.2160247564315796,
|
| 1452 |
-
"eval_runtime": 164.1864,
|
| 1453 |
-
"eval_samples_per_second": 1.322,
|
| 1454 |
-
"eval_steps_per_second": 0.171,
|
| 1455 |
-
"step": 1904
|
| 1456 |
-
},
|
| 1457 |
-
{
|
| 1458 |
-
"epoch": 34.0,
|
| 1459 |
-
"learning_rate": 3.4641569883860637e-06,
|
| 1460 |
-
"loss": 0.5616,
|
| 1461 |
-
"step": 1910
|
| 1462 |
-
},
|
| 1463 |
-
{
|
| 1464 |
-
"epoch": 34.01,
|
| 1465 |
-
"learning_rate": 3.424108930716861e-06,
|
| 1466 |
-
"loss": 0.5305,
|
| 1467 |
-
"step": 1920
|
| 1468 |
-
},
|
| 1469 |
-
{
|
| 1470 |
-
"epoch": 34.01,
|
| 1471 |
-
"learning_rate": 3.3840608730476576e-06,
|
| 1472 |
-
"loss": 0.5134,
|
| 1473 |
-
"step": 1930
|
| 1474 |
-
},
|
| 1475 |
-
{
|
| 1476 |
-
"epoch": 34.01,
|
| 1477 |
-
"learning_rate": 3.3440128153784544e-06,
|
| 1478 |
-
"loss": 0.5199,
|
| 1479 |
-
"step": 1940
|
| 1480 |
-
},
|
| 1481 |
-
{
|
| 1482 |
-
"epoch": 34.02,
|
| 1483 |
-
"learning_rate": 3.3039647577092516e-06,
|
| 1484 |
-
"loss": 0.5365,
|
| 1485 |
-
"step": 1950
|
| 1486 |
-
},
|
| 1487 |
-
{
|
| 1488 |
-
"epoch": 34.02,
|
| 1489 |
-
"learning_rate": 3.2639167000400484e-06,
|
| 1490 |
-
"loss": 0.6439,
|
| 1491 |
-
"step": 1960
|
| 1492 |
-
},
|
| 1493 |
-
{
|
| 1494 |
-
"epoch": 34.02,
|
| 1495 |
-
"eval_accuracy": 0.576036866359447,
|
| 1496 |
-
"eval_loss": 1.0630296468734741,
|
| 1497 |
-
"eval_runtime": 164.642,
|
| 1498 |
-
"eval_samples_per_second": 1.318,
|
| 1499 |
-
"eval_steps_per_second": 0.17,
|
| 1500 |
-
"step": 1960
|
| 1501 |
-
},
|
| 1502 |
-
{
|
| 1503 |
-
"epoch": 35.0,
|
| 1504 |
-
"learning_rate": 3.2238686423708456e-06,
|
| 1505 |
-
"loss": 0.4724,
|
| 1506 |
-
"step": 1970
|
| 1507 |
-
},
|
| 1508 |
-
{
|
| 1509 |
-
"epoch": 35.01,
|
| 1510 |
-
"learning_rate": 3.1838205847016423e-06,
|
| 1511 |
-
"loss": 0.5804,
|
| 1512 |
-
"step": 1980
|
| 1513 |
-
},
|
| 1514 |
-
{
|
| 1515 |
-
"epoch": 35.01,
|
| 1516 |
-
"learning_rate": 3.143772527032439e-06,
|
| 1517 |
-
"loss": 0.607,
|
| 1518 |
-
"step": 1990
|
| 1519 |
-
},
|
| 1520 |
-
{
|
| 1521 |
-
"epoch": 35.01,
|
| 1522 |
-
"learning_rate": 3.1037244693632363e-06,
|
| 1523 |
-
"loss": 0.64,
|
| 1524 |
-
"step": 2000
|
| 1525 |
-
},
|
| 1526 |
-
{
|
| 1527 |
-
"epoch": 35.02,
|
| 1528 |
-
"learning_rate": 3.063676411694033e-06,
|
| 1529 |
-
"loss": 0.597,
|
| 1530 |
-
"step": 2010
|
| 1531 |
-
},
|
| 1532 |
-
{
|
| 1533 |
-
"epoch": 35.02,
|
| 1534 |
-
"eval_accuracy": 0.6082949308755761,
|
| 1535 |
-
"eval_loss": 1.0567601919174194,
|
| 1536 |
-
"eval_runtime": 163.9076,
|
| 1537 |
-
"eval_samples_per_second": 1.324,
|
| 1538 |
-
"eval_steps_per_second": 0.171,
|
| 1539 |
-
"step": 2016
|
| 1540 |
-
},
|
| 1541 |
-
{
|
| 1542 |
-
"epoch": 36.0,
|
| 1543 |
-
"learning_rate": 3.0236283540248302e-06,
|
| 1544 |
-
"loss": 0.5915,
|
| 1545 |
-
"step": 2020
|
| 1546 |
-
},
|
| 1547 |
-
{
|
| 1548 |
-
"epoch": 36.01,
|
| 1549 |
-
"learning_rate": 2.983580296355627e-06,
|
| 1550 |
-
"loss": 0.6774,
|
| 1551 |
-
"step": 2030
|
| 1552 |
-
},
|
| 1553 |
-
{
|
| 1554 |
-
"epoch": 36.01,
|
| 1555 |
-
"learning_rate": 2.943532238686424e-06,
|
| 1556 |
-
"loss": 0.4855,
|
| 1557 |
-
"step": 2040
|
| 1558 |
-
},
|
| 1559 |
-
{
|
| 1560 |
-
"epoch": 36.01,
|
| 1561 |
-
"learning_rate": 2.903484181017221e-06,
|
| 1562 |
-
"loss": 0.6448,
|
| 1563 |
-
"step": 2050
|
| 1564 |
-
},
|
| 1565 |
-
{
|
| 1566 |
-
"epoch": 36.02,
|
| 1567 |
-
"learning_rate": 2.8634361233480177e-06,
|
| 1568 |
-
"loss": 0.6921,
|
| 1569 |
-
"step": 2060
|
| 1570 |
-
},
|
| 1571 |
-
{
|
| 1572 |
-
"epoch": 36.02,
|
| 1573 |
-
"learning_rate": 2.823388065678815e-06,
|
| 1574 |
-
"loss": 0.5641,
|
| 1575 |
-
"step": 2070
|
| 1576 |
-
},
|
| 1577 |
-
{
|
| 1578 |
-
"epoch": 36.02,
|
| 1579 |
-
"eval_accuracy": 0.6682027649769585,
|
| 1580 |
-
"eval_loss": 0.950232982635498,
|
| 1581 |
-
"eval_runtime": 163.9254,
|
| 1582 |
-
"eval_samples_per_second": 1.324,
|
| 1583 |
-
"eval_steps_per_second": 0.171,
|
| 1584 |
-
"step": 2072
|
| 1585 |
-
},
|
| 1586 |
-
{
|
| 1587 |
-
"epoch": 37.0,
|
| 1588 |
-
"learning_rate": 2.7833400080096117e-06,
|
| 1589 |
-
"loss": 0.4284,
|
| 1590 |
-
"step": 2080
|
| 1591 |
-
},
|
| 1592 |
-
{
|
| 1593 |
-
"epoch": 37.01,
|
| 1594 |
-
"learning_rate": 2.743291950340409e-06,
|
| 1595 |
-
"loss": 0.4562,
|
| 1596 |
-
"step": 2090
|
| 1597 |
-
},
|
| 1598 |
-
{
|
| 1599 |
-
"epoch": 37.01,
|
| 1600 |
-
"learning_rate": 2.7032438926712056e-06,
|
| 1601 |
-
"loss": 0.3981,
|
| 1602 |
-
"step": 2100
|
| 1603 |
-
},
|
| 1604 |
-
{
|
| 1605 |
-
"epoch": 37.01,
|
| 1606 |
-
"learning_rate": 2.663195835002003e-06,
|
| 1607 |
-
"loss": 0.675,
|
| 1608 |
-
"step": 2110
|
| 1609 |
-
},
|
| 1610 |
-
{
|
| 1611 |
-
"epoch": 37.02,
|
| 1612 |
-
"learning_rate": 2.6231477773327996e-06,
|
| 1613 |
-
"loss": 0.4992,
|
| 1614 |
-
"step": 2120
|
| 1615 |
-
},
|
| 1616 |
-
{
|
| 1617 |
-
"epoch": 37.02,
|
| 1618 |
-
"eval_accuracy": 0.5898617511520737,
|
| 1619 |
-
"eval_loss": 1.0643178224563599,
|
| 1620 |
-
"eval_runtime": 163.7021,
|
| 1621 |
-
"eval_samples_per_second": 1.326,
|
| 1622 |
-
"eval_steps_per_second": 0.171,
|
| 1623 |
-
"step": 2128
|
| 1624 |
-
},
|
| 1625 |
-
{
|
| 1626 |
-
"epoch": 38.0,
|
| 1627 |
-
"learning_rate": 2.5830997196635963e-06,
|
| 1628 |
-
"loss": 0.5807,
|
| 1629 |
-
"step": 2130
|
| 1630 |
-
},
|
| 1631 |
-
{
|
| 1632 |
-
"epoch": 38.0,
|
| 1633 |
-
"learning_rate": 2.5430516619943935e-06,
|
| 1634 |
-
"loss": 0.5385,
|
| 1635 |
-
"step": 2140
|
| 1636 |
-
},
|
| 1637 |
-
{
|
| 1638 |
-
"epoch": 38.01,
|
| 1639 |
-
"learning_rate": 2.5030036043251903e-06,
|
| 1640 |
-
"loss": 0.5467,
|
| 1641 |
-
"step": 2150
|
| 1642 |
-
},
|
| 1643 |
-
{
|
| 1644 |
-
"epoch": 38.01,
|
| 1645 |
-
"learning_rate": 2.4629555466559875e-06,
|
| 1646 |
-
"loss": 0.5206,
|
| 1647 |
-
"step": 2160
|
| 1648 |
-
},
|
| 1649 |
-
{
|
| 1650 |
-
"epoch": 38.02,
|
| 1651 |
-
"learning_rate": 2.4229074889867843e-06,
|
| 1652 |
-
"loss": 0.648,
|
| 1653 |
-
"step": 2170
|
| 1654 |
-
},
|
| 1655 |
-
{
|
| 1656 |
-
"epoch": 38.02,
|
| 1657 |
-
"learning_rate": 2.3828594313175814e-06,
|
| 1658 |
-
"loss": 0.4136,
|
| 1659 |
-
"step": 2180
|
| 1660 |
-
},
|
| 1661 |
-
{
|
| 1662 |
-
"epoch": 38.02,
|
| 1663 |
-
"eval_accuracy": 0.6082949308755761,
|
| 1664 |
-
"eval_loss": 0.9271302223205566,
|
| 1665 |
-
"eval_runtime": 163.5799,
|
| 1666 |
-
"eval_samples_per_second": 1.327,
|
| 1667 |
-
"eval_steps_per_second": 0.171,
|
| 1668 |
-
"step": 2184
|
| 1669 |
-
},
|
| 1670 |
-
{
|
| 1671 |
-
"epoch": 39.0,
|
| 1672 |
-
"learning_rate": 2.342811373648378e-06,
|
| 1673 |
-
"loss": 0.6367,
|
| 1674 |
-
"step": 2190
|
| 1675 |
-
},
|
| 1676 |
-
{
|
| 1677 |
-
"epoch": 39.01,
|
| 1678 |
-
"learning_rate": 2.302763315979175e-06,
|
| 1679 |
-
"loss": 0.4054,
|
| 1680 |
-
"step": 2200
|
| 1681 |
-
},
|
| 1682 |
-
{
|
| 1683 |
-
"epoch": 39.01,
|
| 1684 |
-
"learning_rate": 2.262715258309972e-06,
|
| 1685 |
-
"loss": 0.6031,
|
| 1686 |
-
"step": 2210
|
| 1687 |
-
},
|
| 1688 |
-
{
|
| 1689 |
-
"epoch": 39.01,
|
| 1690 |
-
"learning_rate": 2.222667200640769e-06,
|
| 1691 |
-
"loss": 0.6353,
|
| 1692 |
-
"step": 2220
|
| 1693 |
-
},
|
| 1694 |
-
{
|
| 1695 |
-
"epoch": 39.02,
|
| 1696 |
-
"learning_rate": 2.182619142971566e-06,
|
| 1697 |
-
"loss": 0.7539,
|
| 1698 |
-
"step": 2230
|
| 1699 |
-
},
|
| 1700 |
-
{
|
| 1701 |
-
"epoch": 39.02,
|
| 1702 |
-
"learning_rate": 2.142571085302363e-06,
|
| 1703 |
-
"loss": 0.5194,
|
| 1704 |
-
"step": 2240
|
| 1705 |
-
},
|
| 1706 |
-
{
|
| 1707 |
-
"epoch": 39.02,
|
| 1708 |
-
"eval_accuracy": 0.576036866359447,
|
| 1709 |
-
"eval_loss": 1.0672531127929688,
|
| 1710 |
-
"eval_runtime": 166.7593,
|
| 1711 |
-
"eval_samples_per_second": 1.301,
|
| 1712 |
-
"eval_steps_per_second": 0.168,
|
| 1713 |
-
"step": 2240
|
| 1714 |
-
},
|
| 1715 |
-
{
|
| 1716 |
-
"epoch": 40.0,
|
| 1717 |
-
"learning_rate": 2.1025230276331596e-06,
|
| 1718 |
-
"loss": 0.5378,
|
| 1719 |
-
"step": 2250
|
| 1720 |
-
},
|
| 1721 |
-
{
|
| 1722 |
-
"epoch": 40.01,
|
| 1723 |
-
"learning_rate": 2.062474969963957e-06,
|
| 1724 |
-
"loss": 0.548,
|
| 1725 |
-
"step": 2260
|
| 1726 |
-
},
|
| 1727 |
-
{
|
| 1728 |
-
"epoch": 40.01,
|
| 1729 |
-
"learning_rate": 2.0224269122947536e-06,
|
| 1730 |
-
"loss": 0.4956,
|
| 1731 |
-
"step": 2270
|
| 1732 |
-
},
|
| 1733 |
-
{
|
| 1734 |
-
"epoch": 40.01,
|
| 1735 |
-
"learning_rate": 1.982378854625551e-06,
|
| 1736 |
-
"loss": 0.5747,
|
| 1737 |
-
"step": 2280
|
| 1738 |
-
},
|
| 1739 |
-
{
|
| 1740 |
-
"epoch": 40.02,
|
| 1741 |
-
"learning_rate": 1.942330796956348e-06,
|
| 1742 |
-
"loss": 0.7653,
|
| 1743 |
-
"step": 2290
|
| 1744 |
-
},
|
| 1745 |
-
{
|
| 1746 |
-
"epoch": 40.02,
|
| 1747 |
-
"eval_accuracy": 0.6267281105990783,
|
| 1748 |
-
"eval_loss": 0.9899203181266785,
|
| 1749 |
-
"eval_runtime": 163.3473,
|
| 1750 |
-
"eval_samples_per_second": 1.328,
|
| 1751 |
-
"eval_steps_per_second": 0.171,
|
| 1752 |
-
"step": 2296
|
| 1753 |
-
},
|
| 1754 |
-
{
|
| 1755 |
-
"epoch": 41.0,
|
| 1756 |
-
"learning_rate": 1.902282739287145e-06,
|
| 1757 |
-
"loss": 0.6948,
|
| 1758 |
-
"step": 2300
|
| 1759 |
-
},
|
| 1760 |
-
{
|
| 1761 |
-
"epoch": 41.01,
|
| 1762 |
-
"learning_rate": 1.8622346816179417e-06,
|
| 1763 |
-
"loss": 0.4703,
|
| 1764 |
-
"step": 2310
|
| 1765 |
-
},
|
| 1766 |
-
{
|
| 1767 |
-
"epoch": 41.01,
|
| 1768 |
-
"learning_rate": 1.8221866239487387e-06,
|
| 1769 |
-
"loss": 0.5782,
|
| 1770 |
-
"step": 2320
|
| 1771 |
-
},
|
| 1772 |
-
{
|
| 1773 |
-
"epoch": 41.01,
|
| 1774 |
-
"learning_rate": 1.7821385662795357e-06,
|
| 1775 |
-
"loss": 0.4866,
|
| 1776 |
-
"step": 2330
|
| 1777 |
-
},
|
| 1778 |
-
{
|
| 1779 |
-
"epoch": 41.02,
|
| 1780 |
-
"learning_rate": 1.7420905086103327e-06,
|
| 1781 |
-
"loss": 0.5591,
|
| 1782 |
-
"step": 2340
|
| 1783 |
-
},
|
| 1784 |
-
{
|
| 1785 |
-
"epoch": 41.02,
|
| 1786 |
-
"learning_rate": 1.7020424509411296e-06,
|
| 1787 |
-
"loss": 0.6247,
|
| 1788 |
-
"step": 2350
|
| 1789 |
-
},
|
| 1790 |
-
{
|
| 1791 |
-
"epoch": 41.02,
|
| 1792 |
-
"eval_accuracy": 0.631336405529954,
|
| 1793 |
-
"eval_loss": 1.0216394662857056,
|
| 1794 |
-
"eval_runtime": 164.836,
|
| 1795 |
-
"eval_samples_per_second": 1.316,
|
| 1796 |
-
"eval_steps_per_second": 0.17,
|
| 1797 |
-
"step": 2352
|
| 1798 |
-
},
|
| 1799 |
-
{
|
| 1800 |
-
"epoch": 42.0,
|
| 1801 |
-
"learning_rate": 1.6619943932719266e-06,
|
| 1802 |
-
"loss": 0.4712,
|
| 1803 |
-
"step": 2360
|
| 1804 |
-
},
|
| 1805 |
-
{
|
| 1806 |
-
"epoch": 42.01,
|
| 1807 |
-
"learning_rate": 1.6219463356027234e-06,
|
| 1808 |
-
"loss": 0.4287,
|
| 1809 |
-
"step": 2370
|
| 1810 |
-
},
|
| 1811 |
-
{
|
| 1812 |
-
"epoch": 42.01,
|
| 1813 |
-
"learning_rate": 1.5818982779335204e-06,
|
| 1814 |
-
"loss": 0.5673,
|
| 1815 |
-
"step": 2380
|
| 1816 |
-
},
|
| 1817 |
-
{
|
| 1818 |
-
"epoch": 42.01,
|
| 1819 |
-
"learning_rate": 1.5418502202643173e-06,
|
| 1820 |
-
"loss": 0.4914,
|
| 1821 |
-
"step": 2390
|
| 1822 |
-
},
|
| 1823 |
-
{
|
| 1824 |
-
"epoch": 42.02,
|
| 1825 |
-
"learning_rate": 1.5018021625951143e-06,
|
| 1826 |
-
"loss": 0.6901,
|
| 1827 |
-
"step": 2400
|
| 1828 |
-
},
|
| 1829 |
-
{
|
| 1830 |
-
"epoch": 42.02,
|
| 1831 |
-
"eval_accuracy": 0.5576036866359447,
|
| 1832 |
-
"eval_loss": 1.1336352825164795,
|
| 1833 |
-
"eval_runtime": 163.2895,
|
| 1834 |
-
"eval_samples_per_second": 1.329,
|
| 1835 |
-
"eval_steps_per_second": 0.171,
|
| 1836 |
-
"step": 2408
|
| 1837 |
-
},
|
| 1838 |
-
{
|
| 1839 |
-
"epoch": 43.0,
|
| 1840 |
-
"learning_rate": 1.4617541049259113e-06,
|
| 1841 |
-
"loss": 0.4876,
|
| 1842 |
-
"step": 2410
|
| 1843 |
-
},
|
| 1844 |
-
{
|
| 1845 |
-
"epoch": 43.0,
|
| 1846 |
-
"learning_rate": 1.4217060472567083e-06,
|
| 1847 |
-
"loss": 0.4494,
|
| 1848 |
-
"step": 2420
|
| 1849 |
-
},
|
| 1850 |
-
{
|
| 1851 |
-
"epoch": 43.01,
|
| 1852 |
-
"learning_rate": 1.3816579895875052e-06,
|
| 1853 |
-
"loss": 0.5611,
|
| 1854 |
-
"step": 2430
|
| 1855 |
-
},
|
| 1856 |
-
{
|
| 1857 |
-
"epoch": 43.01,
|
| 1858 |
-
"learning_rate": 1.341609931918302e-06,
|
| 1859 |
-
"loss": 0.7779,
|
| 1860 |
-
"step": 2440
|
| 1861 |
-
},
|
| 1862 |
-
{
|
| 1863 |
-
"epoch": 43.02,
|
| 1864 |
-
"learning_rate": 1.301561874249099e-06,
|
| 1865 |
-
"loss": 0.4958,
|
| 1866 |
-
"step": 2450
|
| 1867 |
-
},
|
| 1868 |
-
{
|
| 1869 |
-
"epoch": 43.02,
|
| 1870 |
-
"learning_rate": 1.261513816579896e-06,
|
| 1871 |
-
"loss": 0.4731,
|
| 1872 |
-
"step": 2460
|
| 1873 |
-
},
|
| 1874 |
-
{
|
| 1875 |
-
"epoch": 43.02,
|
| 1876 |
-
"eval_accuracy": 0.5944700460829493,
|
| 1877 |
-
"eval_loss": 1.1247893571853638,
|
| 1878 |
-
"eval_runtime": 169.0052,
|
| 1879 |
-
"eval_samples_per_second": 1.284,
|
| 1880 |
-
"eval_steps_per_second": 0.166,
|
| 1881 |
-
"step": 2464
|
| 1882 |
-
},
|
| 1883 |
-
{
|
| 1884 |
-
"epoch": 44.0,
|
| 1885 |
-
"learning_rate": 1.221465758910693e-06,
|
| 1886 |
-
"loss": 0.3636,
|
| 1887 |
-
"step": 2470
|
| 1888 |
-
},
|
| 1889 |
-
{
|
| 1890 |
-
"epoch": 44.01,
|
| 1891 |
-
"learning_rate": 1.18141770124149e-06,
|
| 1892 |
-
"loss": 0.4359,
|
| 1893 |
-
"step": 2480
|
| 1894 |
-
},
|
| 1895 |
-
{
|
| 1896 |
-
"epoch": 44.01,
|
| 1897 |
-
"learning_rate": 1.1413696435722869e-06,
|
| 1898 |
-
"loss": 0.5232,
|
| 1899 |
-
"step": 2490
|
| 1900 |
-
},
|
| 1901 |
-
{
|
| 1902 |
-
"epoch": 44.01,
|
| 1903 |
-
"learning_rate": 1.1013215859030837e-06,
|
| 1904 |
-
"loss": 0.3694,
|
| 1905 |
-
"step": 2500
|
| 1906 |
-
},
|
| 1907 |
-
{
|
| 1908 |
-
"epoch": 44.02,
|
| 1909 |
-
"learning_rate": 1.0612735282338806e-06,
|
| 1910 |
-
"loss": 0.6064,
|
| 1911 |
-
"step": 2510
|
| 1912 |
-
},
|
| 1913 |
-
{
|
| 1914 |
-
"epoch": 44.02,
|
| 1915 |
-
"learning_rate": 1.0212254705646776e-06,
|
| 1916 |
-
"loss": 0.4623,
|
| 1917 |
-
"step": 2520
|
| 1918 |
-
},
|
| 1919 |
-
{
|
| 1920 |
-
"epoch": 44.02,
|
| 1921 |
-
"eval_accuracy": 0.6359447004608295,
|
| 1922 |
-
"eval_loss": 1.010471224784851,
|
| 1923 |
-
"eval_runtime": 162.4614,
|
| 1924 |
-
"eval_samples_per_second": 1.336,
|
| 1925 |
-
"eval_steps_per_second": 0.172,
|
| 1926 |
-
"step": 2520
|
| 1927 |
-
},
|
| 1928 |
-
{
|
| 1929 |
-
"epoch": 45.0,
|
| 1930 |
-
"learning_rate": 9.811774128954748e-07,
|
| 1931 |
-
"loss": 0.4463,
|
| 1932 |
-
"step": 2530
|
| 1933 |
-
},
|
| 1934 |
-
{
|
| 1935 |
-
"epoch": 45.01,
|
| 1936 |
-
"learning_rate": 9.411293552262717e-07,
|
| 1937 |
-
"loss": 0.5154,
|
| 1938 |
-
"step": 2540
|
| 1939 |
-
},
|
| 1940 |
-
{
|
| 1941 |
-
"epoch": 45.01,
|
| 1942 |
-
"learning_rate": 9.010812975570686e-07,
|
| 1943 |
-
"loss": 0.5859,
|
| 1944 |
-
"step": 2550
|
| 1945 |
-
},
|
| 1946 |
-
{
|
| 1947 |
-
"epoch": 45.01,
|
| 1948 |
-
"learning_rate": 8.610332398878655e-07,
|
| 1949 |
-
"loss": 0.6416,
|
| 1950 |
-
"step": 2560
|
| 1951 |
-
},
|
| 1952 |
-
{
|
| 1953 |
-
"epoch": 45.02,
|
| 1954 |
-
"learning_rate": 8.209851822186625e-07,
|
| 1955 |
-
"loss": 0.5236,
|
| 1956 |
-
"step": 2570
|
| 1957 |
-
},
|
| 1958 |
-
{
|
| 1959 |
-
"epoch": 45.02,
|
| 1960 |
-
"eval_accuracy": 0.5622119815668203,
|
| 1961 |
-
"eval_loss": 1.2222412824630737,
|
| 1962 |
-
"eval_runtime": 166.434,
|
| 1963 |
-
"eval_samples_per_second": 1.304,
|
| 1964 |
-
"eval_steps_per_second": 0.168,
|
| 1965 |
-
"step": 2576
|
| 1966 |
-
},
|
| 1967 |
-
{
|
| 1968 |
-
"epoch": 46.0,
|
| 1969 |
-
"learning_rate": 7.809371245494595e-07,
|
| 1970 |
-
"loss": 0.4967,
|
| 1971 |
-
"step": 2580
|
| 1972 |
-
},
|
| 1973 |
-
{
|
| 1974 |
-
"epoch": 46.01,
|
| 1975 |
-
"learning_rate": 7.408890668802563e-07,
|
| 1976 |
-
"loss": 0.4661,
|
| 1977 |
-
"step": 2590
|
| 1978 |
-
},
|
| 1979 |
-
{
|
| 1980 |
-
"epoch": 46.01,
|
| 1981 |
-
"learning_rate": 7.008410092110533e-07,
|
| 1982 |
-
"loss": 0.6802,
|
| 1983 |
-
"step": 2600
|
| 1984 |
-
},
|
| 1985 |
-
{
|
| 1986 |
-
"epoch": 46.01,
|
| 1987 |
-
"learning_rate": 6.607929515418503e-07,
|
| 1988 |
-
"loss": 0.3791,
|
| 1989 |
-
"step": 2610
|
| 1990 |
-
},
|
| 1991 |
-
{
|
| 1992 |
-
"epoch": 46.02,
|
| 1993 |
-
"learning_rate": 6.207448938726472e-07,
|
| 1994 |
-
"loss": 0.688,
|
| 1995 |
-
"step": 2620
|
| 1996 |
-
},
|
| 1997 |
-
{
|
| 1998 |
-
"epoch": 46.02,
|
| 1999 |
-
"learning_rate": 5.806968362034441e-07,
|
| 2000 |
-
"loss": 0.4865,
|
| 2001 |
-
"step": 2630
|
| 2002 |
-
},
|
| 2003 |
-
{
|
| 2004 |
-
"epoch": 46.02,
|
| 2005 |
-
"eval_accuracy": 0.5668202764976958,
|
| 2006 |
-
"eval_loss": 1.1389591693878174,
|
| 2007 |
-
"eval_runtime": 164.5648,
|
| 2008 |
-
"eval_samples_per_second": 1.319,
|
| 2009 |
-
"eval_steps_per_second": 0.17,
|
| 2010 |
-
"step": 2632
|
| 2011 |
-
},
|
| 2012 |
-
{
|
| 2013 |
-
"epoch": 47.0,
|
| 2014 |
-
"learning_rate": 5.406487785342411e-07,
|
| 2015 |
-
"loss": 0.5445,
|
| 2016 |
-
"step": 2640
|
| 2017 |
-
},
|
| 2018 |
-
{
|
| 2019 |
-
"epoch": 47.01,
|
| 2020 |
-
"learning_rate": 5.006007208650381e-07,
|
| 2021 |
-
"loss": 0.445,
|
| 2022 |
-
"step": 2650
|
| 2023 |
-
},
|
| 2024 |
-
{
|
| 2025 |
-
"epoch": 47.01,
|
| 2026 |
-
"learning_rate": 4.605526631958351e-07,
|
| 2027 |
-
"loss": 0.4754,
|
| 2028 |
-
"step": 2660
|
| 2029 |
-
},
|
| 2030 |
-
{
|
| 2031 |
-
"epoch": 47.01,
|
| 2032 |
-
"learning_rate": 4.20504605526632e-07,
|
| 2033 |
-
"loss": 0.5643,
|
| 2034 |
-
"step": 2670
|
| 2035 |
-
},
|
| 2036 |
-
{
|
| 2037 |
-
"epoch": 47.02,
|
| 2038 |
-
"learning_rate": 3.80456547857429e-07,
|
| 2039 |
-
"loss": 0.6178,
|
| 2040 |
-
"step": 2680
|
| 2041 |
-
},
|
| 2042 |
-
{
|
| 2043 |
-
"epoch": 47.02,
|
| 2044 |
-
"eval_accuracy": 0.5806451612903226,
|
| 2045 |
-
"eval_loss": 1.118094801902771,
|
| 2046 |
-
"eval_runtime": 163.1432,
|
| 2047 |
-
"eval_samples_per_second": 1.33,
|
| 2048 |
-
"eval_steps_per_second": 0.172,
|
| 2049 |
-
"step": 2688
|
| 2050 |
-
},
|
| 2051 |
-
{
|
| 2052 |
-
"epoch": 48.0,
|
| 2053 |
-
"learning_rate": 3.404084901882259e-07,
|
| 2054 |
-
"loss": 0.4701,
|
| 2055 |
-
"step": 2690
|
| 2056 |
-
},
|
| 2057 |
-
{
|
| 2058 |
-
"epoch": 48.0,
|
| 2059 |
-
"learning_rate": 3.0036043251902283e-07,
|
| 2060 |
-
"loss": 0.3917,
|
| 2061 |
-
"step": 2700
|
| 2062 |
-
},
|
| 2063 |
-
{
|
| 2064 |
-
"epoch": 48.01,
|
| 2065 |
-
"learning_rate": 2.603123748498198e-07,
|
| 2066 |
-
"loss": 0.5181,
|
| 2067 |
-
"step": 2710
|
| 2068 |
-
},
|
| 2069 |
-
{
|
| 2070 |
-
"epoch": 48.01,
|
| 2071 |
-
"learning_rate": 2.2026431718061676e-07,
|
| 2072 |
-
"loss": 0.5627,
|
| 2073 |
-
"step": 2720
|
| 2074 |
-
},
|
| 2075 |
-
{
|
| 2076 |
-
"epoch": 48.02,
|
| 2077 |
-
"learning_rate": 1.802162595114137e-07,
|
| 2078 |
-
"loss": 0.449,
|
| 2079 |
-
"step": 2730
|
| 2080 |
-
},
|
| 2081 |
-
{
|
| 2082 |
-
"epoch": 48.02,
|
| 2083 |
-
"learning_rate": 1.4016820184221066e-07,
|
| 2084 |
-
"loss": 0.6068,
|
| 2085 |
-
"step": 2740
|
| 2086 |
-
},
|
| 2087 |
-
{
|
| 2088 |
-
"epoch": 48.02,
|
| 2089 |
-
"eval_accuracy": 0.6036866359447005,
|
| 2090 |
-
"eval_loss": 1.0918972492218018,
|
| 2091 |
-
"eval_runtime": 166.7399,
|
| 2092 |
-
"eval_samples_per_second": 1.301,
|
| 2093 |
-
"eval_steps_per_second": 0.168,
|
| 2094 |
-
"step": 2744
|
| 2095 |
-
},
|
| 2096 |
-
{
|
| 2097 |
-
"epoch": 49.0,
|
| 2098 |
-
"learning_rate": 1.0012014417300762e-07,
|
| 2099 |
-
"loss": 0.4975,
|
| 2100 |
-
"step": 2750
|
| 2101 |
-
},
|
| 2102 |
-
{
|
| 2103 |
-
"epoch": 49.01,
|
| 2104 |
-
"learning_rate": 6.007208650380457e-08,
|
| 2105 |
-
"loss": 0.4256,
|
| 2106 |
-
"step": 2760
|
| 2107 |
-
},
|
| 2108 |
-
{
|
| 2109 |
-
"epoch": 49.01,
|
| 2110 |
-
"learning_rate": 2.0024028834601525e-08,
|
| 2111 |
-
"loss": 0.4835,
|
| 2112 |
-
"step": 2770
|
| 2113 |
-
},
|
| 2114 |
-
{
|
| 2115 |
-
"epoch": 49.01,
|
| 2116 |
-
"eval_accuracy": 0.5852534562211982,
|
| 2117 |
-
"eval_loss": 1.0932610034942627,
|
| 2118 |
-
"eval_runtime": 164.2231,
|
| 2119 |
-
"eval_samples_per_second": 1.321,
|
| 2120 |
-
"eval_steps_per_second": 0.17,
|
| 2121 |
-
"step": 2775
|
| 2122 |
-
},
|
| 2123 |
-
{
|
| 2124 |
-
"epoch": 49.01,
|
| 2125 |
-
"step": 2775,
|
| 2126 |
-
"total_flos": 2.7602315185605673e+19,
|
| 2127 |
-
"train_loss": 0.8102743840432381,
|
| 2128 |
-
"train_runtime": 28793.9081,
|
| 2129 |
-
"train_samples_per_second": 0.771,
|
| 2130 |
-
"train_steps_per_second": 0.096
|
| 2131 |
-
},
|
| 2132 |
-
{
|
| 2133 |
-
"epoch": 49.01,
|
| 2134 |
-
"eval_accuracy": 0.6805555555555556,
|
| 2135 |
-
"eval_loss": 0.7703173160552979,
|
| 2136 |
-
"eval_runtime": 171.6337,
|
| 2137 |
-
"eval_samples_per_second": 1.258,
|
| 2138 |
-
"eval_steps_per_second": 0.157,
|
| 2139 |
-
"step": 2775
|
| 2140 |
-
},
|
| 2141 |
-
{
|
| 2142 |
-
"epoch": 49.01,
|
| 2143 |
-
"eval_accuracy": 0.6805555555555556,
|
| 2144 |
-
"eval_loss": 0.7703171968460083,
|
| 2145 |
-
"eval_runtime": 162.7205,
|
| 2146 |
-
"eval_samples_per_second": 1.327,
|
| 2147 |
-
"eval_steps_per_second": 0.166,
|
| 2148 |
-
"step": 2775
|
| 2149 |
}
|
| 2150 |
],
|
| 2151 |
"logging_steps": 10,
|
| 2152 |
-
"max_steps":
|
| 2153 |
"num_input_tokens_seen": 0,
|
| 2154 |
"num_train_epochs": 9223372036854775807,
|
| 2155 |
"save_steps": 500,
|
| 2156 |
-
"total_flos":
|
| 2157 |
"train_batch_size": 8,
|
| 2158 |
"trial_name": null,
|
| 2159 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7419354838709677,
|
| 3 |
"best_model_checkpoint": "videomae-base-finetuned-subset-check10/checkpoint-896",
|
| 4 |
+
"epoch": 19.041441441441442,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1110,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 9.00900900900901e-07,
|
| 14 |
+
"loss": 1.6695,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 1.801801801801802e-06,
|
| 20 |
+
"loss": 1.6945,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 2.702702702702703e-06,
|
| 26 |
+
"loss": 1.6484,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.04,
|
| 31 |
+
"learning_rate": 3.603603603603604e-06,
|
| 32 |
+
"loss": 1.6661,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.05,
|
| 37 |
+
"learning_rate": 4.504504504504505e-06,
|
| 38 |
+
"loss": 1.6348,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.05,
|
| 43 |
+
"eval_accuracy": 0.511520737327189,
|
| 44 |
+
"eval_loss": 1.544296383857727,
|
| 45 |
+
"eval_runtime": 169.659,
|
| 46 |
+
"eval_samples_per_second": 1.279,
|
| 47 |
"eval_steps_per_second": 0.165,
|
| 48 |
"step": 56
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 1.0,
|
| 52 |
+
"learning_rate": 5.405405405405406e-06,
|
| 53 |
+
"loss": 1.5964,
|
| 54 |
"step": 60
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 1.01,
|
| 58 |
+
"learning_rate": 6.3063063063063065e-06,
|
| 59 |
+
"loss": 1.6218,
|
| 60 |
"step": 70
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"epoch": 1.02,
|
| 64 |
+
"learning_rate": 7.207207207207208e-06,
|
| 65 |
+
"loss": 1.6405,
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 1.03,
|
| 70 |
+
"learning_rate": 8.108108108108109e-06,
|
| 71 |
+
"loss": 1.6203,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 1.04,
|
| 76 |
+
"learning_rate": 9.00900900900901e-06,
|
| 77 |
+
"loss": 1.6147,
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
+
"epoch": 1.05,
|
| 82 |
+
"learning_rate": 9.90990990990991e-06,
|
| 83 |
+
"loss": 1.6015,
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"epoch": 1.05,
|
| 88 |
+
"eval_accuracy": 0.4792626728110599,
|
| 89 |
+
"eval_loss": 1.529832124710083,
|
| 90 |
+
"eval_runtime": 163.2712,
|
| 91 |
+
"eval_samples_per_second": 1.329,
|
| 92 |
+
"eval_steps_per_second": 0.171,
|
| 93 |
"step": 112
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 2.01,
|
| 97 |
+
"learning_rate": 9.90990990990991e-06,
|
| 98 |
+
"loss": 1.5899,
|
| 99 |
"step": 120
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 2.02,
|
| 103 |
+
"learning_rate": 9.80980980980981e-06,
|
| 104 |
+
"loss": 1.6095,
|
| 105 |
"step": 130
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 2.03,
|
| 109 |
+
"learning_rate": 9.70970970970971e-06,
|
| 110 |
+
"loss": 1.613,
|
| 111 |
"step": 140
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 2.03,
|
| 115 |
+
"learning_rate": 9.60960960960961e-06,
|
| 116 |
+
"loss": 1.5829,
|
| 117 |
"step": 150
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 2.04,
|
| 121 |
+
"learning_rate": 9.50950950950951e-06,
|
| 122 |
+
"loss": 1.5683,
|
| 123 |
"step": 160
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 2.05,
|
| 127 |
+
"eval_accuracy": 0.3271889400921659,
|
| 128 |
+
"eval_loss": 1.5288971662521362,
|
| 129 |
+
"eval_runtime": 162.8221,
|
| 130 |
+
"eval_samples_per_second": 1.333,
|
| 131 |
+
"eval_steps_per_second": 0.172,
|
| 132 |
"step": 168
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 3.0,
|
| 136 |
+
"learning_rate": 9.40940940940941e-06,
|
| 137 |
+
"loss": 1.5958,
|
| 138 |
"step": 170
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 3.01,
|
| 142 |
+
"learning_rate": 9.30930930930931e-06,
|
| 143 |
+
"loss": 1.5487,
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 3.02,
|
| 148 |
+
"learning_rate": 9.20920920920921e-06,
|
| 149 |
+
"loss": 1.5407,
|
| 150 |
"step": 190
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 3.03,
|
| 154 |
+
"learning_rate": 9.10910910910911e-06,
|
| 155 |
+
"loss": 1.5352,
|
| 156 |
"step": 200
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 3.04,
|
| 160 |
+
"learning_rate": 9.00900900900901e-06,
|
| 161 |
+
"loss": 1.4537,
|
| 162 |
"step": 210
|
| 163 |
},
|
| 164 |
{
|
| 165 |
+
"epoch": 3.05,
|
| 166 |
+
"learning_rate": 8.90890890890891e-06,
|
| 167 |
+
"loss": 1.512,
|
| 168 |
"step": 220
|
| 169 |
},
|
| 170 |
{
|
| 171 |
+
"epoch": 3.05,
|
| 172 |
+
"eval_accuracy": 0.631336405529954,
|
| 173 |
+
"eval_loss": 1.302922248840332,
|
| 174 |
+
"eval_runtime": 162.9796,
|
| 175 |
+
"eval_samples_per_second": 1.331,
|
| 176 |
+
"eval_steps_per_second": 0.172,
|
| 177 |
"step": 224
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 4.01,
|
| 181 |
+
"learning_rate": 8.80880880880881e-06,
|
| 182 |
+
"loss": 1.4831,
|
| 183 |
"step": 230
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 4.01,
|
| 187 |
+
"learning_rate": 8.70870870870871e-06,
|
| 188 |
+
"loss": 1.3654,
|
| 189 |
"step": 240
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 4.02,
|
| 193 |
+
"learning_rate": 8.60860860860861e-06,
|
| 194 |
+
"loss": 1.3439,
|
| 195 |
"step": 250
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 4.03,
|
| 199 |
+
"learning_rate": 8.50850850850851e-06,
|
| 200 |
+
"loss": 1.2985,
|
| 201 |
"step": 260
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 4.04,
|
| 205 |
+
"learning_rate": 8.408408408408409e-06,
|
| 206 |
+
"loss": 1.2316,
|
| 207 |
"step": 270
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 4.05,
|
| 211 |
+
"learning_rate": 8.308308308308309e-06,
|
| 212 |
+
"loss": 1.2309,
|
| 213 |
"step": 280
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 4.05,
|
| 217 |
+
"eval_accuracy": 0.5207373271889401,
|
| 218 |
+
"eval_loss": 1.21807861328125,
|
| 219 |
+
"eval_runtime": 162.5548,
|
| 220 |
+
"eval_samples_per_second": 1.335,
|
| 221 |
+
"eval_steps_per_second": 0.172,
|
| 222 |
"step": 280
|
| 223 |
},
|
| 224 |
{
|
| 225 |
+
"epoch": 5.01,
|
| 226 |
+
"learning_rate": 8.208208208208209e-06,
|
| 227 |
+
"loss": 1.3147,
|
| 228 |
"step": 290
|
| 229 |
},
|
| 230 |
{
|
| 231 |
+
"epoch": 5.02,
|
| 232 |
+
"learning_rate": 8.108108108108109e-06,
|
| 233 |
+
"loss": 1.2977,
|
| 234 |
"step": 300
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 5.03,
|
| 238 |
+
"learning_rate": 8.00800800800801e-06,
|
| 239 |
+
"loss": 1.2603,
|
| 240 |
"step": 310
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 5.04,
|
| 244 |
+
"learning_rate": 7.90790790790791e-06,
|
| 245 |
+
"loss": 1.1538,
|
| 246 |
"step": 320
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 5.05,
|
| 250 |
+
"learning_rate": 7.807807807807808e-06,
|
| 251 |
+
"loss": 1.1949,
|
| 252 |
"step": 330
|
| 253 |
},
|
| 254 |
{
|
| 255 |
+
"epoch": 5.05,
|
| 256 |
+
"eval_accuracy": 0.6589861751152074,
|
| 257 |
+
"eval_loss": 1.0441014766693115,
|
| 258 |
+
"eval_runtime": 161.7405,
|
| 259 |
+
"eval_samples_per_second": 1.342,
|
| 260 |
+
"eval_steps_per_second": 0.173,
|
| 261 |
"step": 336
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 6.0,
|
| 265 |
+
"learning_rate": 7.707707707707708e-06,
|
| 266 |
+
"loss": 1.2623,
|
| 267 |
"step": 340
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 6.01,
|
| 271 |
+
"learning_rate": 7.607607607607608e-06,
|
| 272 |
+
"loss": 1.1608,
|
| 273 |
"step": 350
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 6.02,
|
| 277 |
+
"learning_rate": 7.507507507507507e-06,
|
| 278 |
+
"loss": 1.1801,
|
| 279 |
"step": 360
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 6.03,
|
| 283 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 284 |
+
"loss": 1.0873,
|
| 285 |
"step": 370
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 6.04,
|
| 289 |
+
"learning_rate": 7.307307307307308e-06,
|
| 290 |
+
"loss": 1.0739,
|
| 291 |
"step": 380
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 6.05,
|
| 295 |
+
"learning_rate": 7.207207207207208e-06,
|
| 296 |
+
"loss": 1.0987,
|
| 297 |
"step": 390
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 6.05,
|
| 301 |
+
"eval_accuracy": 0.6129032258064516,
|
| 302 |
+
"eval_loss": 1.004054307937622,
|
| 303 |
+
"eval_runtime": 161.9536,
|
| 304 |
+
"eval_samples_per_second": 1.34,
|
| 305 |
+
"eval_steps_per_second": 0.173,
|
| 306 |
"step": 392
|
| 307 |
},
|
| 308 |
{
|
| 309 |
+
"epoch": 7.01,
|
| 310 |
+
"learning_rate": 7.107107107107107e-06,
|
| 311 |
+
"loss": 1.142,
|
| 312 |
"step": 400
|
| 313 |
},
|
| 314 |
{
|
| 315 |
+
"epoch": 7.02,
|
| 316 |
+
"learning_rate": 7.007007007007007e-06,
|
| 317 |
+
"loss": 1.0111,
|
| 318 |
"step": 410
|
| 319 |
},
|
| 320 |
{
|
| 321 |
+
"epoch": 7.03,
|
| 322 |
+
"learning_rate": 6.906906906906907e-06,
|
| 323 |
+
"loss": 1.0603,
|
| 324 |
"step": 420
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 7.03,
|
| 328 |
+
"learning_rate": 6.8068068068068075e-06,
|
| 329 |
+
"loss": 1.185,
|
| 330 |
"step": 430
|
| 331 |
},
|
| 332 |
{
|
| 333 |
+
"epoch": 7.04,
|
| 334 |
+
"learning_rate": 6.706706706706707e-06,
|
| 335 |
+
"loss": 1.148,
|
| 336 |
"step": 440
|
| 337 |
},
|
| 338 |
{
|
| 339 |
+
"epoch": 7.05,
|
| 340 |
+
"eval_accuracy": 0.6175115207373272,
|
| 341 |
+
"eval_loss": 1.0258899927139282,
|
| 342 |
+
"eval_runtime": 163.4987,
|
| 343 |
+
"eval_samples_per_second": 1.327,
|
| 344 |
+
"eval_steps_per_second": 0.171,
|
| 345 |
"step": 448
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 8.0,
|
| 349 |
+
"learning_rate": 6.606606606606607e-06,
|
| 350 |
+
"loss": 1.1361,
|
| 351 |
"step": 450
|
| 352 |
},
|
| 353 |
{
|
| 354 |
+
"epoch": 8.01,
|
| 355 |
+
"learning_rate": 6.506506506506507e-06,
|
| 356 |
+
"loss": 0.9612,
|
| 357 |
"step": 460
|
| 358 |
},
|
| 359 |
{
|
| 360 |
+
"epoch": 8.02,
|
| 361 |
+
"learning_rate": 6.406406406406407e-06,
|
| 362 |
+
"loss": 1.0823,
|
| 363 |
"step": 470
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 8.03,
|
| 367 |
+
"learning_rate": 6.3063063063063065e-06,
|
| 368 |
+
"loss": 1.21,
|
| 369 |
"step": 480
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 8.04,
|
| 373 |
+
"learning_rate": 6.206206206206207e-06,
|
| 374 |
+
"loss": 0.9171,
|
| 375 |
"step": 490
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 8.05,
|
| 379 |
+
"learning_rate": 6.106106106106107e-06,
|
| 380 |
+
"loss": 0.9958,
|
| 381 |
"step": 500
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 8.05,
|
| 385 |
+
"eval_accuracy": 0.6728110599078341,
|
| 386 |
+
"eval_loss": 0.9507986307144165,
|
| 387 |
+
"eval_runtime": 161.9408,
|
| 388 |
+
"eval_samples_per_second": 1.34,
|
| 389 |
+
"eval_steps_per_second": 0.173,
|
| 390 |
"step": 504
|
| 391 |
},
|
| 392 |
{
|
| 393 |
+
"epoch": 9.01,
|
| 394 |
+
"learning_rate": 6.006006006006007e-06,
|
| 395 |
+
"loss": 0.9985,
|
| 396 |
"step": 510
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 9.01,
|
| 400 |
+
"learning_rate": 5.905905905905906e-06,
|
| 401 |
+
"loss": 1.1594,
|
| 402 |
"step": 520
|
| 403 |
},
|
| 404 |
{
|
| 405 |
+
"epoch": 9.02,
|
| 406 |
+
"learning_rate": 5.805805805805806e-06,
|
| 407 |
+
"loss": 1.0034,
|
| 408 |
"step": 530
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 9.03,
|
| 412 |
+
"learning_rate": 5.7057057057057065e-06,
|
| 413 |
+
"loss": 0.9761,
|
| 414 |
"step": 540
|
| 415 |
},
|
| 416 |
{
|
| 417 |
+
"epoch": 9.04,
|
| 418 |
+
"learning_rate": 5.605605605605607e-06,
|
| 419 |
+
"loss": 0.8942,
|
| 420 |
"step": 550
|
| 421 |
},
|
| 422 |
{
|
| 423 |
+
"epoch": 9.05,
|
| 424 |
+
"learning_rate": 5.505505505505506e-06,
|
| 425 |
+
"loss": 1.0856,
|
| 426 |
"step": 560
|
| 427 |
},
|
| 428 |
{
|
| 429 |
+
"epoch": 9.05,
|
| 430 |
+
"eval_accuracy": 0.5944700460829493,
|
| 431 |
+
"eval_loss": 1.0041232109069824,
|
| 432 |
+
"eval_runtime": 162.8782,
|
| 433 |
+
"eval_samples_per_second": 1.332,
|
| 434 |
+
"eval_steps_per_second": 0.172,
|
| 435 |
"step": 560
|
| 436 |
},
|
| 437 |
{
|
| 438 |
+
"epoch": 10.01,
|
| 439 |
+
"learning_rate": 5.405405405405406e-06,
|
| 440 |
+
"loss": 0.972,
|
| 441 |
"step": 570
|
| 442 |
},
|
| 443 |
{
|
| 444 |
+
"epoch": 10.02,
|
| 445 |
+
"learning_rate": 5.305305305305306e-06,
|
| 446 |
+
"loss": 1.0112,
|
| 447 |
"step": 580
|
| 448 |
},
|
| 449 |
{
|
| 450 |
+
"epoch": 10.03,
|
| 451 |
+
"learning_rate": 5.205205205205206e-06,
|
| 452 |
+
"loss": 0.9801,
|
| 453 |
"step": 590
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 10.04,
|
| 457 |
+
"learning_rate": 5.105105105105106e-06,
|
| 458 |
+
"loss": 0.8615,
|
| 459 |
"step": 600
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 10.05,
|
| 463 |
+
"learning_rate": 5.005005005005006e-06,
|
| 464 |
+
"loss": 0.8809,
|
| 465 |
"step": 610
|
| 466 |
},
|
| 467 |
{
|
| 468 |
+
"epoch": 10.05,
|
| 469 |
+
"eval_accuracy": 0.6359447004608295,
|
| 470 |
+
"eval_loss": 0.9638356566429138,
|
| 471 |
+
"eval_runtime": 161.5478,
|
| 472 |
+
"eval_samples_per_second": 1.343,
|
| 473 |
+
"eval_steps_per_second": 0.173,
|
| 474 |
"step": 616
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 11.0,
|
| 478 |
+
"learning_rate": 4.904904904904905e-06,
|
| 479 |
+
"loss": 0.8911,
|
| 480 |
"step": 620
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 11.01,
|
| 484 |
+
"learning_rate": 4.804804804804805e-06,
|
| 485 |
+
"loss": 0.8545,
|
| 486 |
"step": 630
|
| 487 |
},
|
| 488 |
{
|
| 489 |
+
"epoch": 11.02,
|
| 490 |
+
"learning_rate": 4.704704704704705e-06,
|
| 491 |
+
"loss": 0.8887,
|
| 492 |
"step": 640
|
| 493 |
},
|
| 494 |
{
|
| 495 |
+
"epoch": 11.03,
|
| 496 |
+
"learning_rate": 4.604604604604605e-06,
|
| 497 |
+
"loss": 0.8687,
|
| 498 |
"step": 650
|
| 499 |
},
|
| 500 |
{
|
| 501 |
+
"epoch": 11.04,
|
| 502 |
+
"learning_rate": 4.504504504504505e-06,
|
| 503 |
+
"loss": 0.8959,
|
| 504 |
"step": 660
|
| 505 |
},
|
| 506 |
{
|
| 507 |
+
"epoch": 11.05,
|
| 508 |
+
"learning_rate": 4.404404404404405e-06,
|
| 509 |
+
"loss": 0.9185,
|
| 510 |
"step": 670
|
| 511 |
},
|
| 512 |
{
|
| 513 |
+
"epoch": 11.05,
|
| 514 |
+
"eval_accuracy": 0.6820276497695853,
|
| 515 |
+
"eval_loss": 0.9248147010803223,
|
| 516 |
+
"eval_runtime": 161.5706,
|
| 517 |
+
"eval_samples_per_second": 1.343,
|
| 518 |
+
"eval_steps_per_second": 0.173,
|
| 519 |
"step": 672
|
| 520 |
},
|
| 521 |
{
|
| 522 |
+
"epoch": 12.01,
|
| 523 |
+
"learning_rate": 4.304304304304305e-06,
|
| 524 |
+
"loss": 0.9707,
|
| 525 |
"step": 680
|
| 526 |
},
|
| 527 |
{
|
| 528 |
+
"epoch": 12.02,
|
| 529 |
+
"learning_rate": 4.204204204204204e-06,
|
| 530 |
+
"loss": 0.7837,
|
| 531 |
"step": 690
|
| 532 |
},
|
| 533 |
{
|
| 534 |
+
"epoch": 12.03,
|
| 535 |
+
"learning_rate": 4.1041041041041045e-06,
|
| 536 |
+
"loss": 0.9325,
|
| 537 |
"step": 700
|
| 538 |
},
|
| 539 |
{
|
| 540 |
+
"epoch": 12.03,
|
| 541 |
+
"learning_rate": 4.004004004004005e-06,
|
| 542 |
+
"loss": 0.8425,
|
| 543 |
"step": 710
|
| 544 |
},
|
| 545 |
{
|
| 546 |
+
"epoch": 12.04,
|
| 547 |
+
"learning_rate": 3.903903903903904e-06,
|
| 548 |
+
"loss": 0.9136,
|
| 549 |
"step": 720
|
| 550 |
},
|
| 551 |
{
|
| 552 |
+
"epoch": 12.05,
|
| 553 |
+
"eval_accuracy": 0.6728110599078341,
|
| 554 |
+
"eval_loss": 1.0136313438415527,
|
| 555 |
+
"eval_runtime": 162.7529,
|
| 556 |
+
"eval_samples_per_second": 1.333,
|
| 557 |
+
"eval_steps_per_second": 0.172,
|
| 558 |
"step": 728
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 13.0,
|
| 562 |
+
"learning_rate": 3.803803803803804e-06,
|
| 563 |
+
"loss": 0.9652,
|
| 564 |
"step": 730
|
| 565 |
},
|
| 566 |
{
|
| 567 |
+
"epoch": 13.01,
|
| 568 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 569 |
+
"loss": 0.8421,
|
| 570 |
"step": 740
|
| 571 |
},
|
| 572 |
{
|
| 573 |
+
"epoch": 13.02,
|
| 574 |
+
"learning_rate": 3.603603603603604e-06,
|
| 575 |
+
"loss": 0.9862,
|
| 576 |
"step": 750
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 13.03,
|
| 580 |
+
"learning_rate": 3.5035035035035036e-06,
|
| 581 |
+
"loss": 0.9638,
|
| 582 |
"step": 760
|
| 583 |
},
|
| 584 |
{
|
| 585 |
+
"epoch": 13.04,
|
| 586 |
+
"learning_rate": 3.4034034034034037e-06,
|
| 587 |
+
"loss": 0.8826,
|
| 588 |
"step": 770
|
| 589 |
},
|
| 590 |
{
|
| 591 |
+
"epoch": 13.05,
|
| 592 |
+
"learning_rate": 3.3033033033033035e-06,
|
| 593 |
+
"loss": 0.8537,
|
| 594 |
"step": 780
|
| 595 |
},
|
| 596 |
{
|
| 597 |
+
"epoch": 13.05,
|
| 598 |
+
"eval_accuracy": 0.7188940092165899,
|
| 599 |
+
"eval_loss": 0.8515194058418274,
|
| 600 |
+
"eval_runtime": 164.1283,
|
| 601 |
"eval_samples_per_second": 1.322,
|
| 602 |
"eval_steps_per_second": 0.171,
|
| 603 |
"step": 784
|
| 604 |
},
|
| 605 |
{
|
| 606 |
+
"epoch": 14.01,
|
| 607 |
+
"learning_rate": 3.2032032032032036e-06,
|
| 608 |
+
"loss": 0.9158,
|
| 609 |
"step": 790
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 14.01,
|
| 613 |
+
"learning_rate": 3.1031031031031033e-06,
|
| 614 |
+
"loss": 0.8456,
|
| 615 |
"step": 800
|
| 616 |
},
|
| 617 |
{
|
| 618 |
+
"epoch": 14.02,
|
| 619 |
+
"learning_rate": 3.0030030030030034e-06,
|
| 620 |
+
"loss": 0.8235,
|
| 621 |
"step": 810
|
| 622 |
},
|
| 623 |
{
|
| 624 |
+
"epoch": 14.03,
|
| 625 |
+
"learning_rate": 2.902902902902903e-06,
|
| 626 |
+
"loss": 0.7452,
|
| 627 |
"step": 820
|
| 628 |
},
|
| 629 |
{
|
| 630 |
+
"epoch": 14.04,
|
| 631 |
+
"learning_rate": 2.8028028028028033e-06,
|
| 632 |
+
"loss": 0.8251,
|
| 633 |
"step": 830
|
| 634 |
},
|
| 635 |
{
|
| 636 |
+
"epoch": 14.05,
|
| 637 |
+
"learning_rate": 2.702702702702703e-06,
|
| 638 |
+
"loss": 0.7921,
|
| 639 |
"step": 840
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 14.05,
|
| 643 |
+
"eval_accuracy": 0.7004608294930875,
|
| 644 |
+
"eval_loss": 0.8222436308860779,
|
| 645 |
+
"eval_runtime": 161.8478,
|
| 646 |
+
"eval_samples_per_second": 1.341,
|
| 647 |
+
"eval_steps_per_second": 0.173,
|
| 648 |
"step": 840
|
| 649 |
},
|
| 650 |
{
|
| 651 |
+
"epoch": 15.01,
|
| 652 |
+
"learning_rate": 2.602602602602603e-06,
|
| 653 |
+
"loss": 0.9356,
|
| 654 |
"step": 850
|
| 655 |
},
|
| 656 |
{
|
| 657 |
+
"epoch": 15.02,
|
| 658 |
+
"learning_rate": 2.502502502502503e-06,
|
| 659 |
+
"loss": 0.8556,
|
| 660 |
"step": 860
|
| 661 |
},
|
| 662 |
{
|
| 663 |
+
"epoch": 15.03,
|
| 664 |
+
"learning_rate": 2.4024024024024026e-06,
|
| 665 |
+
"loss": 0.7946,
|
| 666 |
"step": 870
|
| 667 |
},
|
| 668 |
{
|
| 669 |
+
"epoch": 15.04,
|
| 670 |
+
"learning_rate": 2.3023023023023023e-06,
|
| 671 |
+
"loss": 0.7411,
|
| 672 |
"step": 880
|
| 673 |
},
|
| 674 |
{
|
| 675 |
+
"epoch": 15.05,
|
| 676 |
+
"learning_rate": 2.2022022022022024e-06,
|
| 677 |
+
"loss": 0.7313,
|
| 678 |
"step": 890
|
| 679 |
},
|
| 680 |
{
|
| 681 |
+
"epoch": 15.05,
|
| 682 |
+
"eval_accuracy": 0.7419354838709677,
|
| 683 |
+
"eval_loss": 0.7512253522872925,
|
| 684 |
+
"eval_runtime": 161.7824,
|
| 685 |
+
"eval_samples_per_second": 1.341,
|
| 686 |
+
"eval_steps_per_second": 0.173,
|
| 687 |
"step": 896
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 16.0,
|
| 691 |
+
"learning_rate": 2.102102102102102e-06,
|
| 692 |
+
"loss": 0.8169,
|
| 693 |
"step": 900
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 16.01,
|
| 697 |
+
"learning_rate": 2.0020020020020023e-06,
|
| 698 |
+
"loss": 0.7236,
|
| 699 |
"step": 910
|
| 700 |
},
|
| 701 |
{
|
| 702 |
+
"epoch": 16.02,
|
| 703 |
+
"learning_rate": 1.901901901901902e-06,
|
| 704 |
+
"loss": 0.8335,
|
| 705 |
"step": 920
|
| 706 |
},
|
| 707 |
{
|
| 708 |
+
"epoch": 16.03,
|
| 709 |
+
"learning_rate": 1.801801801801802e-06,
|
| 710 |
+
"loss": 0.8666,
|
| 711 |
"step": 930
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 16.04,
|
| 715 |
+
"learning_rate": 1.7017017017017019e-06,
|
| 716 |
+
"loss": 0.8429,
|
| 717 |
"step": 940
|
| 718 |
},
|
| 719 |
{
|
| 720 |
+
"epoch": 16.05,
|
| 721 |
+
"learning_rate": 1.6016016016016018e-06,
|
| 722 |
+
"loss": 0.5998,
|
| 723 |
"step": 950
|
| 724 |
},
|
| 725 |
{
|
| 726 |
+
"epoch": 16.05,
|
| 727 |
+
"eval_accuracy": 0.6129032258064516,
|
| 728 |
+
"eval_loss": 0.9409515857696533,
|
| 729 |
+
"eval_runtime": 161.5869,
|
| 730 |
+
"eval_samples_per_second": 1.343,
|
| 731 |
+
"eval_steps_per_second": 0.173,
|
| 732 |
"step": 952
|
| 733 |
},
|
| 734 |
{
|
| 735 |
+
"epoch": 17.01,
|
| 736 |
+
"learning_rate": 1.5015015015015017e-06,
|
| 737 |
+
"loss": 0.8206,
|
| 738 |
"step": 960
|
| 739 |
},
|
| 740 |
{
|
| 741 |
+
"epoch": 17.02,
|
| 742 |
+
"learning_rate": 1.4014014014014016e-06,
|
| 743 |
+
"loss": 0.7474,
|
| 744 |
"step": 970
|
| 745 |
},
|
| 746 |
{
|
| 747 |
+
"epoch": 17.03,
|
| 748 |
+
"learning_rate": 1.3013013013013016e-06,
|
| 749 |
+
"loss": 0.7778,
|
| 750 |
"step": 980
|
| 751 |
},
|
| 752 |
{
|
| 753 |
+
"epoch": 17.03,
|
| 754 |
+
"learning_rate": 1.2012012012012013e-06,
|
| 755 |
+
"loss": 0.7003,
|
| 756 |
"step": 990
|
| 757 |
},
|
| 758 |
{
|
| 759 |
+
"epoch": 17.04,
|
| 760 |
+
"learning_rate": 1.1011011011011012e-06,
|
| 761 |
+
"loss": 0.8093,
|
| 762 |
"step": 1000
|
| 763 |
},
|
| 764 |
{
|
| 765 |
+
"epoch": 17.05,
|
| 766 |
+
"eval_accuracy": 0.7050691244239631,
|
| 767 |
+
"eval_loss": 0.8144727349281311,
|
| 768 |
+
"eval_runtime": 161.5502,
|
| 769 |
+
"eval_samples_per_second": 1.343,
|
| 770 |
+
"eval_steps_per_second": 0.173,
|
| 771 |
"step": 1008
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 18.0,
|
| 775 |
+
"learning_rate": 1.0010010010010011e-06,
|
| 776 |
+
"loss": 0.8227,
|
| 777 |
"step": 1010
|
| 778 |
},
|
| 779 |
{
|
| 780 |
+
"epoch": 18.01,
|
| 781 |
+
"learning_rate": 9.00900900900901e-07,
|
| 782 |
+
"loss": 0.8949,
|
| 783 |
"step": 1020
|
| 784 |
},
|
| 785 |
{
|
| 786 |
+
"epoch": 18.02,
|
| 787 |
+
"learning_rate": 8.008008008008009e-07,
|
| 788 |
+
"loss": 0.6573,
|
| 789 |
"step": 1030
|
| 790 |
},
|
| 791 |
{
|
| 792 |
+
"epoch": 18.03,
|
| 793 |
+
"learning_rate": 7.007007007007008e-07,
|
| 794 |
+
"loss": 0.8836,
|
| 795 |
"step": 1040
|
| 796 |
},
|
| 797 |
{
|
| 798 |
+
"epoch": 18.04,
|
| 799 |
+
"learning_rate": 6.006006006006006e-07,
|
| 800 |
+
"loss": 0.7605,
|
| 801 |
"step": 1050
|
| 802 |
},
|
| 803 |
{
|
| 804 |
+
"epoch": 18.05,
|
| 805 |
+
"learning_rate": 5.005005005005006e-07,
|
| 806 |
+
"loss": 0.604,
|
| 807 |
"step": 1060
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 18.05,
|
| 811 |
+
"eval_accuracy": 0.6820276497695853,
|
| 812 |
+
"eval_loss": 0.9013708233833313,
|
| 813 |
+
"eval_runtime": 162.7504,
|
| 814 |
+
"eval_samples_per_second": 1.333,
|
| 815 |
+
"eval_steps_per_second": 0.172,
|
| 816 |
"step": 1064
|
| 817 |
},
|
| 818 |
{
|
| 819 |
+
"epoch": 19.01,
|
| 820 |
+
"learning_rate": 4.0040040040040045e-07,
|
| 821 |
+
"loss": 0.7955,
|
| 822 |
"step": 1070
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 19.01,
|
| 826 |
+
"learning_rate": 3.003003003003003e-07,
|
| 827 |
+
"loss": 0.9212,
|
| 828 |
"step": 1080
|
| 829 |
},
|
| 830 |
{
|
| 831 |
+
"epoch": 19.02,
|
| 832 |
+
"learning_rate": 2.0020020020020022e-07,
|
| 833 |
+
"loss": 0.9198,
|
| 834 |
"step": 1090
|
| 835 |
},
|
| 836 |
{
|
| 837 |
+
"epoch": 19.03,
|
| 838 |
+
"learning_rate": 1.0010010010010011e-07,
|
| 839 |
+
"loss": 0.5744,
|
| 840 |
"step": 1100
|
| 841 |
},
|
| 842 |
{
|
| 843 |
+
"epoch": 19.04,
|
| 844 |
+
"learning_rate": 0.0,
|
| 845 |
+
"loss": 0.7066,
|
| 846 |
"step": 1110
|
| 847 |
},
|
| 848 |
{
|
| 849 |
+
"epoch": 19.04,
|
| 850 |
+
"eval_accuracy": 0.6682027649769585,
|
| 851 |
+
"eval_loss": 0.893532931804657,
|
| 852 |
+
"eval_runtime": 167.9329,
|
| 853 |
+
"eval_samples_per_second": 1.292,
|
| 854 |
+
"eval_steps_per_second": 0.167,
|
| 855 |
+
"step": 1110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 19.04,
|
| 859 |
+
"step": 1110,
|
| 860 |
+
"total_flos": 1.1041673732998595e+19,
|
| 861 |
+
"train_loss": 1.0829452497465117,
|
| 862 |
+
"train_runtime": 11433.1912,
|
| 863 |
+
"train_samples_per_second": 0.777,
|
| 864 |
+
"train_steps_per_second": 0.097
|
| 865 |
},
|
| 866 |
{
|
| 867 |
+
"epoch": 19.04,
|
| 868 |
+
"eval_accuracy": 0.6666666666666666,
|
| 869 |
+
"eval_loss": 0.6926783919334412,
|
| 870 |
+
"eval_runtime": 164.6443,
|
| 871 |
"eval_samples_per_second": 1.312,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 872 |
"eval_steps_per_second": 0.164,
|
| 873 |
+
"step": 1110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 19.04,
|
| 877 |
+
"eval_accuracy": 0.6666666666666666,
|
| 878 |
+
"eval_loss": 0.6926783919334412,
|
| 879 |
+
"eval_runtime": 163.2396,
|
| 880 |
+
"eval_samples_per_second": 1.323,
|
| 881 |
+
"eval_steps_per_second": 0.165,
|
| 882 |
+
"step": 1110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 883 |
}
|
| 884 |
],
|
| 885 |
"logging_steps": 10,
|
| 886 |
+
"max_steps": 1110,
|
| 887 |
"num_input_tokens_seen": 0,
|
| 888 |
"num_train_epochs": 9223372036854775807,
|
| 889 |
"save_steps": 500,
|
| 890 |
+
"total_flos": 1.1041673732998595e+19,
|
| 891 |
"train_batch_size": 8,
|
| 892 |
"trial_name": null,
|
| 893 |
"trial_params": null
|