End of training
Browse files- all_results.json +6 -6
- test_results.json +6 -6
- trainer_state.json +1300 -454
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": 39.02,
|
| 3 |
+
"eval_accuracy": 0.6342592592592593,
|
| 4 |
+
"eval_loss": 0.8682467341423035,
|
| 5 |
+
"eval_runtime": 165.9338,
|
| 6 |
+
"eval_samples_per_second": 1.302,
|
| 7 |
+
"eval_steps_per_second": 0.163
|
| 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": 39.02,
|
| 3 |
+
"eval_accuracy": 0.6342592592592593,
|
| 4 |
+
"eval_loss": 0.8682467341423035,
|
| 5 |
+
"eval_runtime": 165.9338,
|
| 6 |
+
"eval_samples_per_second": 1.302,
|
| 7 |
+
"eval_steps_per_second": 0.163
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,893 +1,1739 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "videomae-base-finetuned-subset-check10/checkpoint-
|
| 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":
|
| 46 |
-
"eval_samples_per_second": 1.
|
| 47 |
-
"eval_steps_per_second": 0.
|
| 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": 3.01,
|
| 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": 9.
|
| 155 |
-
"loss": 1.
|
| 156 |
"step": 200
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch": 3.
|
| 160 |
-
"learning_rate": 9.
|
| 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":
|
| 182 |
-
"loss": 1.
|
| 183 |
"step": 230
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 4.01,
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss": 1.
|
| 189 |
"step": 240
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch": 4.
|
| 193 |
-
"learning_rate":
|
| 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": 165.
|
| 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":
|
| 297 |
"step": 390
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch": 6.
|
| 301 |
-
"eval_accuracy": 0.
|
| 302 |
-
"eval_loss":
|
| 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":
|
| 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":
|
| 336 |
"step": 440
|
| 337 |
},
|
| 338 |
{
|
| 339 |
-
"epoch": 7.
|
| 340 |
-
"eval_accuracy": 0.
|
| 341 |
-
"eval_loss":
|
| 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": 8.01,
|
| 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": 0.
|
| 375 |
"step": 490
|
| 376 |
},
|
| 377 |
{
|
| 378 |
-
"epoch": 8.
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 500
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch": 8.
|
| 385 |
-
"eval_accuracy": 0.
|
| 386 |
-
"eval_loss": 0.
|
| 387 |
-
"eval_runtime": 165.
|
| 388 |
-
"eval_samples_per_second": 1.
|
| 389 |
"eval_steps_per_second": 0.169,
|
| 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":
|
| 402 |
"step": 520
|
| 403 |
},
|
| 404 |
{
|
| 405 |
-
"epoch": 9.
|
| 406 |
-
"learning_rate":
|
| 407 |
-
"loss":
|
| 408 |
"step": 530
|
| 409 |
},
|
| 410 |
{
|
| 411 |
-
"epoch": 9.
|
| 412 |
-
"learning_rate":
|
| 413 |
-
"loss": 0.
|
| 414 |
"step": 540
|
| 415 |
},
|
| 416 |
{
|
| 417 |
-
"epoch": 9.
|
| 418 |
-
"learning_rate":
|
| 419 |
-
"loss": 0.
|
| 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": 0.
|
| 441 |
"step": 570
|
| 442 |
},
|
| 443 |
{
|
| 444 |
-
"epoch": 10.
|
| 445 |
-
"learning_rate":
|
| 446 |
-
"loss": 0.
|
| 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": 0.
|
| 471 |
-
"eval_runtime":
|
| 472 |
-
"eval_samples_per_second": 1.
|
| 473 |
"eval_steps_per_second": 0.17,
|
| 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":
|
| 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": 0.
|
| 510 |
"step": 670
|
| 511 |
},
|
| 512 |
{
|
| 513 |
-
"epoch": 11.
|
| 514 |
-
"eval_accuracy": 0.
|
| 515 |
-
"eval_loss": 0.
|
| 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": 0.
|
| 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": 13.01,
|
| 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":
|
| 601 |
"eval_samples_per_second": 1.315,
|
| 602 |
"eval_steps_per_second": 0.17,
|
| 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":
|
| 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": 165.
|
| 685 |
-
"eval_samples_per_second": 1.
|
| 686 |
"eval_steps_per_second": 0.169,
|
| 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":
|
| 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": 0.
|
| 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":
|
| 768 |
-
"eval_runtime":
|
| 769 |
-
"eval_samples_per_second": 1.
|
| 770 |
"eval_steps_per_second": 0.17,
|
| 771 |
"step": 1008
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 18.0,
|
| 775 |
-
"learning_rate":
|
| 776 |
-
"loss": 0.
|
| 777 |
"step": 1010
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 18.01,
|
| 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":
|
| 800 |
-
"loss": 0.
|
| 801 |
"step": 1050
|
| 802 |
},
|
| 803 |
{
|
| 804 |
-
"epoch": 18.
|
| 805 |
-
"learning_rate": 5.
|
| 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 |
"eval_accuracy": 0.7188940092165899,
|
| 851 |
-
"eval_loss": 0.
|
| 852 |
-
"eval_runtime":
|
| 853 |
-
"eval_samples_per_second": 1.
|
| 854 |
-
"eval_steps_per_second": 0.
|
| 855 |
-
"step":
|
| 856 |
},
|
| 857 |
{
|
| 858 |
-
"epoch":
|
| 859 |
-
"
|
| 860 |
-
"
|
| 861 |
-
"
|
| 862 |
-
"train_runtime": 11661.5957,
|
| 863 |
-
"train_samples_per_second": 0.761,
|
| 864 |
-
"train_steps_per_second": 0.095
|
| 865 |
},
|
| 866 |
{
|
| 867 |
-
"epoch":
|
| 868 |
-
"
|
| 869 |
-
"
|
| 870 |
-
"
|
| 871 |
-
"eval_samples_per_second": 1.29,
|
| 872 |
-
"eval_steps_per_second": 0.161,
|
| 873 |
-
"step": 1110
|
| 874 |
},
|
| 875 |
{
|
| 876 |
-
"epoch":
|
| 877 |
-
"
|
| 878 |
-
"
|
| 879 |
-
"
|
| 880 |
-
|
| 881 |
-
|
| 882 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 883 |
}
|
| 884 |
],
|
| 885 |
"logging_steps": 10,
|
| 886 |
-
"max_steps":
|
| 887 |
"num_input_tokens_seen": 0,
|
| 888 |
"num_train_epochs": 9223372036854775807,
|
| 889 |
"save_steps": 500,
|
| 890 |
-
"total_flos":
|
| 891 |
"train_batch_size": 8,
|
| 892 |
"trial_name": null,
|
| 893 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.728110599078341,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-subset-check10/checkpoint-1960",
|
| 4 |
+
"epoch": 39.016216216216215,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2220,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 4.504504504504505e-07,
|
| 14 |
+
"loss": 1.5494,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 9.00900900900901e-07,
|
| 20 |
+
"loss": 1.5329,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 1.3513513513513515e-06,
|
| 26 |
+
"loss": 1.5277,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 1.801801801801802e-06,
|
| 32 |
+
"loss": 1.5543,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 2.2522522522522524e-06,
|
| 38 |
+
"loss": 1.5175,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"eval_accuracy": 0.2073732718894009,
|
| 44 |
+
"eval_loss": 1.6040809154510498,
|
| 45 |
+
"eval_runtime": 183.7832,
|
| 46 |
+
"eval_samples_per_second": 1.181,
|
| 47 |
+
"eval_steps_per_second": 0.152,
|
| 48 |
"step": 56
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 1.0,
|
| 52 |
+
"learning_rate": 2.702702702702703e-06,
|
| 53 |
+
"loss": 1.4668,
|
| 54 |
"step": 60
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 1.01,
|
| 58 |
+
"learning_rate": 3.1531531531531532e-06,
|
| 59 |
+
"loss": 1.4494,
|
| 60 |
"step": 70
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"epoch": 1.01,
|
| 64 |
+
"learning_rate": 3.603603603603604e-06,
|
| 65 |
+
"loss": 1.5305,
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 1.02,
|
| 70 |
+
"learning_rate": 4.0540540540540545e-06,
|
| 71 |
+
"loss": 1.4669,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 1.02,
|
| 76 |
+
"learning_rate": 4.504504504504505e-06,
|
| 77 |
+
"loss": 1.4467,
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
+
"epoch": 1.02,
|
| 82 |
+
"learning_rate": 4.954954954954955e-06,
|
| 83 |
+
"loss": 1.4397,
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"epoch": 1.03,
|
| 88 |
+
"eval_accuracy": 0.3870967741935484,
|
| 89 |
+
"eval_loss": 1.4559013843536377,
|
| 90 |
+
"eval_runtime": 165.5917,
|
| 91 |
+
"eval_samples_per_second": 1.31,
|
| 92 |
+
"eval_steps_per_second": 0.169,
|
| 93 |
"step": 112
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 2.0,
|
| 97 |
+
"learning_rate": 5.405405405405406e-06,
|
| 98 |
+
"loss": 1.3919,
|
| 99 |
"step": 120
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 2.01,
|
| 103 |
+
"learning_rate": 5.855855855855856e-06,
|
| 104 |
+
"loss": 1.4257,
|
| 105 |
"step": 130
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 2.01,
|
| 109 |
+
"learning_rate": 6.3063063063063065e-06,
|
| 110 |
+
"loss": 1.402,
|
| 111 |
"step": 140
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 2.02,
|
| 115 |
+
"learning_rate": 6.7567567567567575e-06,
|
| 116 |
+
"loss": 1.3609,
|
| 117 |
"step": 150
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 2.02,
|
| 121 |
+
"learning_rate": 7.207207207207208e-06,
|
| 122 |
+
"loss": 1.464,
|
| 123 |
"step": 160
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 2.03,
|
| 127 |
+
"eval_accuracy": 0.39631336405529954,
|
| 128 |
+
"eval_loss": 1.3637099266052246,
|
| 129 |
+
"eval_runtime": 165.2932,
|
| 130 |
+
"eval_samples_per_second": 1.313,
|
| 131 |
+
"eval_steps_per_second": 0.169,
|
| 132 |
"step": 168
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 3.0,
|
| 136 |
+
"learning_rate": 7.657657657657658e-06,
|
| 137 |
+
"loss": 1.3384,
|
| 138 |
"step": 170
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 3.01,
|
| 142 |
+
"learning_rate": 8.108108108108109e-06,
|
| 143 |
+
"loss": 1.4317,
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 3.01,
|
| 148 |
+
"learning_rate": 8.55855855855856e-06,
|
| 149 |
+
"loss": 1.1669,
|
| 150 |
"step": 190
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 3.01,
|
| 154 |
+
"learning_rate": 9.00900900900901e-06,
|
| 155 |
+
"loss": 1.4449,
|
| 156 |
"step": 200
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 3.02,
|
| 160 |
+
"learning_rate": 9.45945945945946e-06,
|
| 161 |
+
"loss": 1.3429,
|
| 162 |
"step": 210
|
| 163 |
},
|
| 164 |
{
|
| 165 |
+
"epoch": 3.02,
|
| 166 |
+
"learning_rate": 9.90990990990991e-06,
|
| 167 |
+
"loss": 1.3404,
|
| 168 |
"step": 220
|
| 169 |
},
|
| 170 |
{
|
| 171 |
+
"epoch": 3.03,
|
| 172 |
+
"eval_accuracy": 0.4470046082949309,
|
| 173 |
+
"eval_loss": 1.2467495203018188,
|
| 174 |
+
"eval_runtime": 166.7691,
|
| 175 |
+
"eval_samples_per_second": 1.301,
|
| 176 |
+
"eval_steps_per_second": 0.168,
|
| 177 |
"step": 224
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 4.0,
|
| 181 |
+
"learning_rate": 9.95995995995996e-06,
|
| 182 |
+
"loss": 1.2682,
|
| 183 |
"step": 230
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 4.01,
|
| 187 |
+
"learning_rate": 9.90990990990991e-06,
|
| 188 |
+
"loss": 1.2307,
|
| 189 |
"step": 240
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 4.01,
|
| 193 |
+
"learning_rate": 9.85985985985986e-06,
|
| 194 |
+
"loss": 1.14,
|
| 195 |
"step": 250
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 4.02,
|
| 199 |
+
"learning_rate": 9.80980980980981e-06,
|
| 200 |
+
"loss": 1.091,
|
| 201 |
"step": 260
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 4.02,
|
| 205 |
+
"learning_rate": 9.75975975975976e-06,
|
| 206 |
+
"loss": 1.1822,
|
| 207 |
"step": 270
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 4.03,
|
| 211 |
+
"learning_rate": 9.70970970970971e-06,
|
| 212 |
+
"loss": 1.3284,
|
| 213 |
"step": 280
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 4.03,
|
| 217 |
+
"eval_accuracy": 0.3317972350230415,
|
| 218 |
+
"eval_loss": 1.3115123510360718,
|
| 219 |
+
"eval_runtime": 165.1237,
|
| 220 |
+
"eval_samples_per_second": 1.314,
|
| 221 |
+
"eval_steps_per_second": 0.17,
|
| 222 |
"step": 280
|
| 223 |
},
|
| 224 |
{
|
| 225 |
+
"epoch": 5.0,
|
| 226 |
+
"learning_rate": 9.65965965965966e-06,
|
| 227 |
+
"loss": 1.1944,
|
| 228 |
"step": 290
|
| 229 |
},
|
| 230 |
{
|
| 231 |
+
"epoch": 5.01,
|
| 232 |
+
"learning_rate": 9.60960960960961e-06,
|
| 233 |
+
"loss": 1.3055,
|
| 234 |
"step": 300
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 5.01,
|
| 238 |
+
"learning_rate": 9.55955955955956e-06,
|
| 239 |
+
"loss": 1.0722,
|
| 240 |
"step": 310
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 5.02,
|
| 244 |
+
"learning_rate": 9.50950950950951e-06,
|
| 245 |
+
"loss": 1.0467,
|
| 246 |
"step": 320
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 5.02,
|
| 250 |
+
"learning_rate": 9.45945945945946e-06,
|
| 251 |
+
"loss": 1.1598,
|
| 252 |
"step": 330
|
| 253 |
},
|
| 254 |
{
|
| 255 |
+
"epoch": 5.03,
|
| 256 |
+
"eval_accuracy": 0.4470046082949309,
|
| 257 |
+
"eval_loss": 1.2488903999328613,
|
| 258 |
+
"eval_runtime": 168.3906,
|
| 259 |
+
"eval_samples_per_second": 1.289,
|
| 260 |
+
"eval_steps_per_second": 0.166,
|
| 261 |
"step": 336
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 6.0,
|
| 265 |
+
"learning_rate": 9.40940940940941e-06,
|
| 266 |
+
"loss": 1.2285,
|
| 267 |
"step": 340
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 6.01,
|
| 271 |
+
"learning_rate": 9.35935935935936e-06,
|
| 272 |
+
"loss": 1.0002,
|
| 273 |
"step": 350
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 6.01,
|
| 277 |
+
"learning_rate": 9.30930930930931e-06,
|
| 278 |
+
"loss": 1.2506,
|
| 279 |
"step": 360
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 6.02,
|
| 283 |
+
"learning_rate": 9.25925925925926e-06,
|
| 284 |
+
"loss": 1.0963,
|
| 285 |
"step": 370
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 6.02,
|
| 289 |
+
"learning_rate": 9.20920920920921e-06,
|
| 290 |
+
"loss": 1.1495,
|
| 291 |
"step": 380
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 6.02,
|
| 295 |
+
"learning_rate": 9.15915915915916e-06,
|
| 296 |
+
"loss": 0.9615,
|
| 297 |
"step": 390
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 6.03,
|
| 301 |
+
"eval_accuracy": 0.4009216589861751,
|
| 302 |
+
"eval_loss": 1.3057225942611694,
|
| 303 |
+
"eval_runtime": 165.4477,
|
| 304 |
+
"eval_samples_per_second": 1.312,
|
| 305 |
+
"eval_steps_per_second": 0.169,
|
| 306 |
"step": 392
|
| 307 |
},
|
| 308 |
{
|
| 309 |
+
"epoch": 7.0,
|
| 310 |
+
"learning_rate": 9.10910910910911e-06,
|
| 311 |
+
"loss": 1.0211,
|
| 312 |
"step": 400
|
| 313 |
},
|
| 314 |
{
|
| 315 |
+
"epoch": 7.01,
|
| 316 |
+
"learning_rate": 9.05905905905906e-06,
|
| 317 |
+
"loss": 1.0622,
|
| 318 |
"step": 410
|
| 319 |
},
|
| 320 |
{
|
| 321 |
+
"epoch": 7.01,
|
| 322 |
+
"learning_rate": 9.00900900900901e-06,
|
| 323 |
+
"loss": 1.1759,
|
| 324 |
"step": 420
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 7.02,
|
| 328 |
+
"learning_rate": 8.95895895895896e-06,
|
| 329 |
+
"loss": 1.0414,
|
| 330 |
"step": 430
|
| 331 |
},
|
| 332 |
{
|
| 333 |
+
"epoch": 7.02,
|
| 334 |
+
"learning_rate": 8.90890890890891e-06,
|
| 335 |
+
"loss": 0.9357,
|
| 336 |
"step": 440
|
| 337 |
},
|
| 338 |
{
|
| 339 |
+
"epoch": 7.03,
|
| 340 |
+
"eval_accuracy": 0.6497695852534562,
|
| 341 |
+
"eval_loss": 0.9200783967971802,
|
| 342 |
+
"eval_runtime": 165.3979,
|
| 343 |
+
"eval_samples_per_second": 1.312,
|
| 344 |
+
"eval_steps_per_second": 0.169,
|
| 345 |
"step": 448
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 8.0,
|
| 349 |
+
"learning_rate": 8.85885885885886e-06,
|
| 350 |
+
"loss": 1.2506,
|
| 351 |
"step": 450
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 8.01,
|
| 355 |
+
"learning_rate": 8.80880880880881e-06,
|
| 356 |
+
"loss": 1.0342,
|
| 357 |
"step": 460
|
| 358 |
},
|
| 359 |
{
|
| 360 |
+
"epoch": 8.01,
|
| 361 |
+
"learning_rate": 8.75875875875876e-06,
|
| 362 |
+
"loss": 1.0815,
|
| 363 |
"step": 470
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 8.01,
|
| 367 |
+
"learning_rate": 8.70870870870871e-06,
|
| 368 |
+
"loss": 1.0373,
|
| 369 |
"step": 480
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 8.02,
|
| 373 |
+
"learning_rate": 8.65865865865866e-06,
|
| 374 |
+
"loss": 0.9051,
|
| 375 |
"step": 490
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 8.02,
|
| 379 |
+
"learning_rate": 8.60860860860861e-06,
|
| 380 |
+
"loss": 0.9785,
|
| 381 |
"step": 500
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 8.03,
|
| 385 |
+
"eval_accuracy": 0.6774193548387096,
|
| 386 |
+
"eval_loss": 0.8629115223884583,
|
| 387 |
+
"eval_runtime": 165.2531,
|
| 388 |
+
"eval_samples_per_second": 1.313,
|
| 389 |
"eval_steps_per_second": 0.169,
|
| 390 |
"step": 504
|
| 391 |
},
|
| 392 |
{
|
| 393 |
+
"epoch": 9.0,
|
| 394 |
+
"learning_rate": 8.55855855855856e-06,
|
| 395 |
+
"loss": 0.9915,
|
| 396 |
"step": 510
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 9.01,
|
| 400 |
+
"learning_rate": 8.50850850850851e-06,
|
| 401 |
+
"loss": 0.9176,
|
| 402 |
"step": 520
|
| 403 |
},
|
| 404 |
{
|
| 405 |
+
"epoch": 9.01,
|
| 406 |
+
"learning_rate": 8.45845845845846e-06,
|
| 407 |
+
"loss": 1.1561,
|
| 408 |
"step": 530
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 9.02,
|
| 412 |
+
"learning_rate": 8.408408408408409e-06,
|
| 413 |
+
"loss": 0.8966,
|
| 414 |
"step": 540
|
| 415 |
},
|
| 416 |
{
|
| 417 |
+
"epoch": 9.02,
|
| 418 |
+
"learning_rate": 8.358358358358359e-06,
|
| 419 |
+
"loss": 0.894,
|
| 420 |
"step": 550
|
| 421 |
},
|
| 422 |
{
|
| 423 |
+
"epoch": 9.03,
|
| 424 |
+
"learning_rate": 8.308308308308309e-06,
|
| 425 |
+
"loss": 1.0862,
|
| 426 |
"step": 560
|
| 427 |
},
|
| 428 |
{
|
| 429 |
+
"epoch": 9.03,
|
| 430 |
+
"eval_accuracy": 0.5069124423963134,
|
| 431 |
+
"eval_loss": 1.0976766347885132,
|
| 432 |
+
"eval_runtime": 165.1522,
|
| 433 |
+
"eval_samples_per_second": 1.314,
|
| 434 |
+
"eval_steps_per_second": 0.17,
|
| 435 |
"step": 560
|
| 436 |
},
|
| 437 |
{
|
| 438 |
+
"epoch": 10.0,
|
| 439 |
+
"learning_rate": 8.258258258258259e-06,
|
| 440 |
+
"loss": 0.7806,
|
| 441 |
"step": 570
|
| 442 |
},
|
| 443 |
{
|
| 444 |
+
"epoch": 10.01,
|
| 445 |
+
"learning_rate": 8.208208208208209e-06,
|
| 446 |
+
"loss": 0.9904,
|
| 447 |
"step": 580
|
| 448 |
},
|
| 449 |
{
|
| 450 |
+
"epoch": 10.01,
|
| 451 |
+
"learning_rate": 8.158158158158159e-06,
|
| 452 |
+
"loss": 0.9099,
|
| 453 |
"step": 590
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 10.02,
|
| 457 |
+
"learning_rate": 8.108108108108109e-06,
|
| 458 |
+
"loss": 0.9169,
|
| 459 |
"step": 600
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 10.02,
|
| 463 |
+
"learning_rate": 8.058058058058059e-06,
|
| 464 |
+
"loss": 0.9315,
|
| 465 |
"step": 610
|
| 466 |
},
|
| 467 |
{
|
| 468 |
+
"epoch": 10.03,
|
| 469 |
+
"eval_accuracy": 0.7096774193548387,
|
| 470 |
+
"eval_loss": 0.7867635488510132,
|
| 471 |
+
"eval_runtime": 165.0158,
|
| 472 |
+
"eval_samples_per_second": 1.315,
|
| 473 |
"eval_steps_per_second": 0.17,
|
| 474 |
"step": 616
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 11.0,
|
| 478 |
+
"learning_rate": 8.00800800800801e-06,
|
| 479 |
+
"loss": 0.7636,
|
| 480 |
"step": 620
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 11.01,
|
| 484 |
+
"learning_rate": 7.95795795795796e-06,
|
| 485 |
+
"loss": 0.9198,
|
| 486 |
"step": 630
|
| 487 |
},
|
| 488 |
{
|
| 489 |
+
"epoch": 11.01,
|
| 490 |
+
"learning_rate": 7.90790790790791e-06,
|
| 491 |
+
"loss": 1.0816,
|
| 492 |
"step": 640
|
| 493 |
},
|
| 494 |
{
|
| 495 |
+
"epoch": 11.02,
|
| 496 |
+
"learning_rate": 7.85785785785786e-06,
|
| 497 |
+
"loss": 0.8409,
|
| 498 |
"step": 650
|
| 499 |
},
|
| 500 |
{
|
| 501 |
+
"epoch": 11.02,
|
| 502 |
+
"learning_rate": 7.807807807807808e-06,
|
| 503 |
+
"loss": 0.7348,
|
| 504 |
"step": 660
|
| 505 |
},
|
| 506 |
{
|
| 507 |
+
"epoch": 11.02,
|
| 508 |
+
"learning_rate": 7.757757757757758e-06,
|
| 509 |
+
"loss": 0.9404,
|
| 510 |
"step": 670
|
| 511 |
},
|
| 512 |
{
|
| 513 |
+
"epoch": 11.03,
|
| 514 |
+
"eval_accuracy": 0.6728110599078341,
|
| 515 |
+
"eval_loss": 0.8170290589332581,
|
| 516 |
+
"eval_runtime": 165.2251,
|
| 517 |
+
"eval_samples_per_second": 1.313,
|
| 518 |
+
"eval_steps_per_second": 0.169,
|
| 519 |
"step": 672
|
| 520 |
},
|
| 521 |
{
|
| 522 |
+
"epoch": 12.0,
|
| 523 |
+
"learning_rate": 7.707707707707708e-06,
|
| 524 |
+
"loss": 0.8669,
|
| 525 |
"step": 680
|
| 526 |
},
|
| 527 |
{
|
| 528 |
+
"epoch": 12.01,
|
| 529 |
+
"learning_rate": 7.657657657657658e-06,
|
| 530 |
+
"loss": 0.7773,
|
| 531 |
"step": 690
|
| 532 |
},
|
| 533 |
{
|
| 534 |
+
"epoch": 12.01,
|
| 535 |
+
"learning_rate": 7.607607607607608e-06,
|
| 536 |
+
"loss": 0.7599,
|
| 537 |
"step": 700
|
| 538 |
},
|
| 539 |
{
|
| 540 |
+
"epoch": 12.02,
|
| 541 |
+
"learning_rate": 7.557557557557558e-06,
|
| 542 |
+
"loss": 0.9216,
|
| 543 |
"step": 710
|
| 544 |
},
|
| 545 |
{
|
| 546 |
+
"epoch": 12.02,
|
| 547 |
+
"learning_rate": 7.507507507507507e-06,
|
| 548 |
+
"loss": 0.939,
|
| 549 |
"step": 720
|
| 550 |
},
|
| 551 |
{
|
| 552 |
+
"epoch": 12.03,
|
| 553 |
+
"eval_accuracy": 0.663594470046083,
|
| 554 |
+
"eval_loss": 0.9246166348457336,
|
| 555 |
+
"eval_runtime": 165.7726,
|
| 556 |
+
"eval_samples_per_second": 1.309,
|
| 557 |
+
"eval_steps_per_second": 0.169,
|
| 558 |
"step": 728
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 13.0,
|
| 562 |
+
"learning_rate": 7.457457457457457e-06,
|
| 563 |
+
"loss": 0.9703,
|
| 564 |
"step": 730
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 13.01,
|
| 568 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 569 |
+
"loss": 0.6688,
|
| 570 |
"step": 740
|
| 571 |
},
|
| 572 |
{
|
| 573 |
+
"epoch": 13.01,
|
| 574 |
+
"learning_rate": 7.3573573573573575e-06,
|
| 575 |
+
"loss": 0.9097,
|
| 576 |
"step": 750
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 13.01,
|
| 580 |
+
"learning_rate": 7.307307307307308e-06,
|
| 581 |
+
"loss": 0.9963,
|
| 582 |
"step": 760
|
| 583 |
},
|
| 584 |
{
|
| 585 |
+
"epoch": 13.02,
|
| 586 |
+
"learning_rate": 7.257257257257258e-06,
|
| 587 |
+
"loss": 0.8594,
|
| 588 |
"step": 770
|
| 589 |
},
|
| 590 |
{
|
| 591 |
+
"epoch": 13.02,
|
| 592 |
+
"learning_rate": 7.207207207207208e-06,
|
| 593 |
+
"loss": 0.8205,
|
| 594 |
"step": 780
|
| 595 |
},
|
| 596 |
{
|
| 597 |
+
"epoch": 13.03,
|
| 598 |
+
"eval_accuracy": 0.6866359447004609,
|
| 599 |
+
"eval_loss": 0.8420272469520569,
|
| 600 |
+
"eval_runtime": 165.0282,
|
| 601 |
"eval_samples_per_second": 1.315,
|
| 602 |
"eval_steps_per_second": 0.17,
|
| 603 |
"step": 784
|
| 604 |
},
|
| 605 |
{
|
| 606 |
+
"epoch": 14.0,
|
| 607 |
+
"learning_rate": 7.157157157157158e-06,
|
| 608 |
+
"loss": 0.8206,
|
| 609 |
"step": 790
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 14.01,
|
| 613 |
+
"learning_rate": 7.107107107107107e-06,
|
| 614 |
+
"loss": 0.8183,
|
| 615 |
"step": 800
|
| 616 |
},
|
| 617 |
{
|
| 618 |
+
"epoch": 14.01,
|
| 619 |
+
"learning_rate": 7.057057057057057e-06,
|
| 620 |
+
"loss": 0.7596,
|
| 621 |
"step": 810
|
| 622 |
},
|
| 623 |
{
|
| 624 |
+
"epoch": 14.02,
|
| 625 |
+
"learning_rate": 7.007007007007007e-06,
|
| 626 |
+
"loss": 0.799,
|
| 627 |
"step": 820
|
| 628 |
},
|
| 629 |
{
|
| 630 |
+
"epoch": 14.02,
|
| 631 |
+
"learning_rate": 6.956956956956957e-06,
|
| 632 |
+
"loss": 0.7377,
|
| 633 |
"step": 830
|
| 634 |
},
|
| 635 |
{
|
| 636 |
+
"epoch": 14.03,
|
| 637 |
+
"learning_rate": 6.906906906906907e-06,
|
| 638 |
+
"loss": 0.6719,
|
| 639 |
"step": 840
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 14.03,
|
| 643 |
+
"eval_accuracy": 0.5898617511520737,
|
| 644 |
+
"eval_loss": 1.07249116897583,
|
| 645 |
+
"eval_runtime": 164.1063,
|
| 646 |
+
"eval_samples_per_second": 1.322,
|
| 647 |
+
"eval_steps_per_second": 0.171,
|
| 648 |
"step": 840
|
| 649 |
},
|
| 650 |
{
|
| 651 |
+
"epoch": 15.0,
|
| 652 |
+
"learning_rate": 6.856856856856857e-06,
|
| 653 |
+
"loss": 0.6874,
|
| 654 |
"step": 850
|
| 655 |
},
|
| 656 |
{
|
| 657 |
+
"epoch": 15.01,
|
| 658 |
+
"learning_rate": 6.8068068068068075e-06,
|
| 659 |
+
"loss": 0.8207,
|
| 660 |
"step": 860
|
| 661 |
},
|
| 662 |
{
|
| 663 |
+
"epoch": 15.01,
|
| 664 |
+
"learning_rate": 6.7567567567567575e-06,
|
| 665 |
+
"loss": 0.7454,
|
| 666 |
"step": 870
|
| 667 |
},
|
| 668 |
{
|
| 669 |
+
"epoch": 15.02,
|
| 670 |
+
"learning_rate": 6.706706706706707e-06,
|
| 671 |
+
"loss": 0.7188,
|
| 672 |
"step": 880
|
| 673 |
},
|
| 674 |
{
|
| 675 |
+
"epoch": 15.02,
|
| 676 |
+
"learning_rate": 6.656656656656657e-06,
|
| 677 |
+
"loss": 0.8308,
|
| 678 |
"step": 890
|
| 679 |
},
|
| 680 |
{
|
| 681 |
+
"epoch": 15.03,
|
| 682 |
+
"eval_accuracy": 0.6912442396313364,
|
| 683 |
+
"eval_loss": 0.8682537078857422,
|
| 684 |
+
"eval_runtime": 165.7327,
|
| 685 |
+
"eval_samples_per_second": 1.309,
|
| 686 |
"eval_steps_per_second": 0.169,
|
| 687 |
"step": 896
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 16.0,
|
| 691 |
+
"learning_rate": 6.606606606606607e-06,
|
| 692 |
+
"loss": 0.891,
|
| 693 |
"step": 900
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 16.01,
|
| 697 |
+
"learning_rate": 6.556556556556557e-06,
|
| 698 |
+
"loss": 0.7597,
|
| 699 |
"step": 910
|
| 700 |
},
|
| 701 |
{
|
| 702 |
+
"epoch": 16.01,
|
| 703 |
+
"learning_rate": 6.506506506506507e-06,
|
| 704 |
+
"loss": 0.8318,
|
| 705 |
"step": 920
|
| 706 |
},
|
| 707 |
{
|
| 708 |
+
"epoch": 16.02,
|
| 709 |
+
"learning_rate": 6.456456456456457e-06,
|
| 710 |
+
"loss": 0.7681,
|
| 711 |
"step": 930
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 16.02,
|
| 715 |
+
"learning_rate": 6.406406406406407e-06,
|
| 716 |
+
"loss": 1.0094,
|
| 717 |
"step": 940
|
| 718 |
},
|
| 719 |
{
|
| 720 |
+
"epoch": 16.02,
|
| 721 |
+
"learning_rate": 6.356356356356357e-06,
|
| 722 |
+
"loss": 0.7554,
|
| 723 |
"step": 950
|
| 724 |
},
|
| 725 |
{
|
| 726 |
+
"epoch": 16.03,
|
| 727 |
+
"eval_accuracy": 0.5990783410138248,
|
| 728 |
+
"eval_loss": 0.9684067368507385,
|
| 729 |
+
"eval_runtime": 164.5634,
|
| 730 |
+
"eval_samples_per_second": 1.319,
|
| 731 |
+
"eval_steps_per_second": 0.17,
|
| 732 |
"step": 952
|
| 733 |
},
|
| 734 |
{
|
| 735 |
+
"epoch": 17.0,
|
| 736 |
+
"learning_rate": 6.3063063063063065e-06,
|
| 737 |
+
"loss": 0.9087,
|
| 738 |
"step": 960
|
| 739 |
},
|
| 740 |
{
|
| 741 |
+
"epoch": 17.01,
|
| 742 |
+
"learning_rate": 6.2562562562562565e-06,
|
| 743 |
+
"loss": 0.7401,
|
| 744 |
"step": 970
|
| 745 |
},
|
| 746 |
{
|
| 747 |
+
"epoch": 17.01,
|
| 748 |
+
"learning_rate": 6.206206206206207e-06,
|
| 749 |
+
"loss": 0.7611,
|
| 750 |
"step": 980
|
| 751 |
},
|
| 752 |
{
|
| 753 |
+
"epoch": 17.02,
|
| 754 |
+
"learning_rate": 6.156156156156157e-06,
|
| 755 |
+
"loss": 0.6347,
|
| 756 |
"step": 990
|
| 757 |
},
|
| 758 |
{
|
| 759 |
+
"epoch": 17.02,
|
| 760 |
+
"learning_rate": 6.106106106106107e-06,
|
| 761 |
+
"loss": 0.6962,
|
| 762 |
"step": 1000
|
| 763 |
},
|
| 764 |
{
|
| 765 |
+
"epoch": 17.03,
|
| 766 |
+
"eval_accuracy": 0.5483870967741935,
|
| 767 |
+
"eval_loss": 1.1106446981430054,
|
| 768 |
+
"eval_runtime": 165.0022,
|
| 769 |
+
"eval_samples_per_second": 1.315,
|
| 770 |
"eval_steps_per_second": 0.17,
|
| 771 |
"step": 1008
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 18.0,
|
| 775 |
+
"learning_rate": 6.056056056056057e-06,
|
| 776 |
+
"loss": 0.6861,
|
| 777 |
"step": 1010
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 18.01,
|
| 781 |
+
"learning_rate": 6.006006006006007e-06,
|
| 782 |
+
"loss": 0.7999,
|
| 783 |
"step": 1020
|
| 784 |
},
|
| 785 |
{
|
| 786 |
+
"epoch": 18.01,
|
| 787 |
+
"learning_rate": 5.955955955955957e-06,
|
| 788 |
+
"loss": 0.7412,
|
| 789 |
"step": 1030
|
| 790 |
},
|
| 791 |
{
|
| 792 |
+
"epoch": 18.01,
|
| 793 |
+
"learning_rate": 5.905905905905906e-06,
|
| 794 |
+
"loss": 0.8145,
|
| 795 |
"step": 1040
|
| 796 |
},
|
| 797 |
{
|
| 798 |
+
"epoch": 18.02,
|
| 799 |
+
"learning_rate": 5.855855855855856e-06,
|
| 800 |
+
"loss": 0.6653,
|
| 801 |
"step": 1050
|
| 802 |
},
|
| 803 |
{
|
| 804 |
+
"epoch": 18.02,
|
| 805 |
+
"learning_rate": 5.805805805805806e-06,
|
| 806 |
+
"loss": 0.7995,
|
| 807 |
"step": 1060
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 18.03,
|
| 811 |
+
"eval_accuracy": 0.6497695852534562,
|
| 812 |
+
"eval_loss": 0.9750950336456299,
|
| 813 |
+
"eval_runtime": 163.7137,
|
| 814 |
+
"eval_samples_per_second": 1.325,
|
| 815 |
+
"eval_steps_per_second": 0.171,
|
| 816 |
"step": 1064
|
| 817 |
},
|
| 818 |
{
|
| 819 |
+
"epoch": 19.0,
|
| 820 |
+
"learning_rate": 5.755755755755756e-06,
|
| 821 |
+
"loss": 0.6923,
|
| 822 |
"step": 1070
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 19.01,
|
| 826 |
+
"learning_rate": 5.7057057057057065e-06,
|
| 827 |
+
"loss": 0.7874,
|
| 828 |
"step": 1080
|
| 829 |
},
|
| 830 |
{
|
| 831 |
+
"epoch": 19.01,
|
| 832 |
+
"learning_rate": 5.6556556556556565e-06,
|
| 833 |
+
"loss": 0.728,
|
| 834 |
"step": 1090
|
| 835 |
},
|
| 836 |
{
|
| 837 |
+
"epoch": 19.02,
|
| 838 |
+
"learning_rate": 5.605605605605607e-06,
|
| 839 |
+
"loss": 0.6329,
|
| 840 |
"step": 1100
|
| 841 |
},
|
| 842 |
{
|
| 843 |
+
"epoch": 19.02,
|
| 844 |
+
"learning_rate": 5.555555555555557e-06,
|
| 845 |
+
"loss": 0.8939,
|
| 846 |
"step": 1110
|
| 847 |
},
|
| 848 |
{
|
| 849 |
+
"epoch": 19.03,
|
| 850 |
+
"learning_rate": 5.505505505505506e-06,
|
| 851 |
+
"loss": 0.8298,
|
| 852 |
+
"step": 1120
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 19.03,
|
| 856 |
+
"eval_accuracy": 0.5299539170506913,
|
| 857 |
+
"eval_loss": 1.0630956888198853,
|
| 858 |
+
"eval_runtime": 165.0711,
|
| 859 |
+
"eval_samples_per_second": 1.315,
|
| 860 |
+
"eval_steps_per_second": 0.17,
|
| 861 |
+
"step": 1120
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 20.0,
|
| 865 |
+
"learning_rate": 5.455455455455456e-06,
|
| 866 |
+
"loss": 0.7025,
|
| 867 |
+
"step": 1130
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 20.01,
|
| 871 |
+
"learning_rate": 5.405405405405406e-06,
|
| 872 |
+
"loss": 0.6251,
|
| 873 |
+
"step": 1140
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 20.01,
|
| 877 |
+
"learning_rate": 5.355355355355356e-06,
|
| 878 |
+
"loss": 0.7818,
|
| 879 |
+
"step": 1150
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 20.02,
|
| 883 |
+
"learning_rate": 5.305305305305306e-06,
|
| 884 |
+
"loss": 0.8259,
|
| 885 |
+
"step": 1160
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 20.02,
|
| 889 |
+
"learning_rate": 5.255255255255256e-06,
|
| 890 |
+
"loss": 0.6607,
|
| 891 |
+
"step": 1170
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 20.03,
|
| 895 |
+
"eval_accuracy": 0.6175115207373272,
|
| 896 |
+
"eval_loss": 0.9457883834838867,
|
| 897 |
+
"eval_runtime": 164.6389,
|
| 898 |
+
"eval_samples_per_second": 1.318,
|
| 899 |
+
"eval_steps_per_second": 0.17,
|
| 900 |
+
"step": 1176
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 21.0,
|
| 904 |
+
"learning_rate": 5.205205205205206e-06,
|
| 905 |
+
"loss": 0.6344,
|
| 906 |
+
"step": 1180
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 21.01,
|
| 910 |
+
"learning_rate": 5.155155155155156e-06,
|
| 911 |
+
"loss": 0.637,
|
| 912 |
+
"step": 1190
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 21.01,
|
| 916 |
+
"learning_rate": 5.105105105105106e-06,
|
| 917 |
+
"loss": 0.858,
|
| 918 |
+
"step": 1200
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 21.02,
|
| 922 |
+
"learning_rate": 5.055055055055056e-06,
|
| 923 |
+
"loss": 0.6934,
|
| 924 |
+
"step": 1210
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 21.02,
|
| 928 |
+
"learning_rate": 5.005005005005006e-06,
|
| 929 |
+
"loss": 0.5714,
|
| 930 |
+
"step": 1220
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 21.02,
|
| 934 |
+
"learning_rate": 4.954954954954955e-06,
|
| 935 |
+
"loss": 0.688,
|
| 936 |
+
"step": 1230
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 21.03,
|
| 940 |
+
"eval_accuracy": 0.6036866359447005,
|
| 941 |
+
"eval_loss": 1.029563546180725,
|
| 942 |
+
"eval_runtime": 163.856,
|
| 943 |
+
"eval_samples_per_second": 1.324,
|
| 944 |
+
"eval_steps_per_second": 0.171,
|
| 945 |
+
"step": 1232
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 22.0,
|
| 949 |
+
"learning_rate": 4.904904904904905e-06,
|
| 950 |
+
"loss": 0.5114,
|
| 951 |
+
"step": 1240
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 22.01,
|
| 955 |
+
"learning_rate": 4.854854854854855e-06,
|
| 956 |
+
"loss": 0.6638,
|
| 957 |
+
"step": 1250
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 22.01,
|
| 961 |
+
"learning_rate": 4.804804804804805e-06,
|
| 962 |
+
"loss": 0.7833,
|
| 963 |
+
"step": 1260
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 22.02,
|
| 967 |
+
"learning_rate": 4.754754754754755e-06,
|
| 968 |
+
"loss": 0.7556,
|
| 969 |
+
"step": 1270
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 22.02,
|
| 973 |
+
"learning_rate": 4.704704704704705e-06,
|
| 974 |
+
"loss": 0.5835,
|
| 975 |
+
"step": 1280
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 22.03,
|
| 979 |
+
"eval_accuracy": 0.6774193548387096,
|
| 980 |
+
"eval_loss": 0.8947747349739075,
|
| 981 |
+
"eval_runtime": 163.875,
|
| 982 |
+
"eval_samples_per_second": 1.324,
|
| 983 |
+
"eval_steps_per_second": 0.171,
|
| 984 |
+
"step": 1288
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 23.0,
|
| 988 |
+
"learning_rate": 4.654654654654655e-06,
|
| 989 |
+
"loss": 0.7209,
|
| 990 |
+
"step": 1290
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 23.01,
|
| 994 |
+
"learning_rate": 4.604604604604605e-06,
|
| 995 |
+
"loss": 0.6087,
|
| 996 |
+
"step": 1300
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 23.01,
|
| 1000 |
+
"learning_rate": 4.554554554554555e-06,
|
| 1001 |
+
"loss": 0.6529,
|
| 1002 |
+
"step": 1310
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 23.01,
|
| 1006 |
+
"learning_rate": 4.504504504504505e-06,
|
| 1007 |
+
"loss": 0.7221,
|
| 1008 |
+
"step": 1320
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 23.02,
|
| 1012 |
+
"learning_rate": 4.454454454454455e-06,
|
| 1013 |
+
"loss": 0.6167,
|
| 1014 |
+
"step": 1330
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 23.02,
|
| 1018 |
+
"learning_rate": 4.404404404404405e-06,
|
| 1019 |
+
"loss": 0.6987,
|
| 1020 |
+
"step": 1340
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 23.03,
|
| 1024 |
"eval_accuracy": 0.7188940092165899,
|
| 1025 |
+
"eval_loss": 0.7882533669471741,
|
| 1026 |
+
"eval_runtime": 163.4201,
|
| 1027 |
+
"eval_samples_per_second": 1.328,
|
| 1028 |
+
"eval_steps_per_second": 0.171,
|
| 1029 |
+
"step": 1344
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
+
"epoch": 24.0,
|
| 1033 |
+
"learning_rate": 4.354354354354355e-06,
|
| 1034 |
+
"loss": 0.7234,
|
| 1035 |
+
"step": 1350
|
|
|
|
|
|
|
|
|
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
+
"epoch": 24.01,
|
| 1039 |
+
"learning_rate": 4.304304304304305e-06,
|
| 1040 |
+
"loss": 0.808,
|
| 1041 |
+
"step": 1360
|
|
|
|
|
|
|
|
|
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
+
"epoch": 24.01,
|
| 1045 |
+
"learning_rate": 4.254254254254255e-06,
|
| 1046 |
+
"loss": 0.6323,
|
| 1047 |
+
"step": 1370
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 24.02,
|
| 1051 |
+
"learning_rate": 4.204204204204204e-06,
|
| 1052 |
+
"loss": 0.5463,
|
| 1053 |
+
"step": 1380
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 24.02,
|
| 1057 |
+
"learning_rate": 4.154154154154154e-06,
|
| 1058 |
+
"loss": 0.7978,
|
| 1059 |
+
"step": 1390
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 24.03,
|
| 1063 |
+
"learning_rate": 4.1041041041041045e-06,
|
| 1064 |
+
"loss": 0.4979,
|
| 1065 |
+
"step": 1400
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 24.03,
|
| 1069 |
+
"eval_accuracy": 0.7188940092165899,
|
| 1070 |
+
"eval_loss": 0.7089133262634277,
|
| 1071 |
+
"eval_runtime": 164.3791,
|
| 1072 |
+
"eval_samples_per_second": 1.32,
|
| 1073 |
+
"eval_steps_per_second": 0.17,
|
| 1074 |
+
"step": 1400
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 25.0,
|
| 1078 |
+
"learning_rate": 4.0540540540540545e-06,
|
| 1079 |
+
"loss": 0.4685,
|
| 1080 |
+
"step": 1410
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 25.01,
|
| 1084 |
+
"learning_rate": 4.004004004004005e-06,
|
| 1085 |
+
"loss": 0.665,
|
| 1086 |
+
"step": 1420
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 25.01,
|
| 1090 |
+
"learning_rate": 3.953953953953955e-06,
|
| 1091 |
+
"loss": 0.6872,
|
| 1092 |
+
"step": 1430
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 25.02,
|
| 1096 |
+
"learning_rate": 3.903903903903904e-06,
|
| 1097 |
+
"loss": 0.5854,
|
| 1098 |
+
"step": 1440
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 25.02,
|
| 1102 |
+
"learning_rate": 3.853853853853854e-06,
|
| 1103 |
+
"loss": 0.6163,
|
| 1104 |
+
"step": 1450
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 25.03,
|
| 1108 |
+
"eval_accuracy": 0.7235023041474654,
|
| 1109 |
+
"eval_loss": 0.7633541226387024,
|
| 1110 |
+
"eval_runtime": 163.5735,
|
| 1111 |
+
"eval_samples_per_second": 1.327,
|
| 1112 |
+
"eval_steps_per_second": 0.171,
|
| 1113 |
+
"step": 1456
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 26.0,
|
| 1117 |
+
"learning_rate": 3.803803803803804e-06,
|
| 1118 |
+
"loss": 0.7065,
|
| 1119 |
+
"step": 1460
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 26.01,
|
| 1123 |
+
"learning_rate": 3.7537537537537537e-06,
|
| 1124 |
+
"loss": 0.6684,
|
| 1125 |
+
"step": 1470
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 26.01,
|
| 1129 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 1130 |
+
"loss": 0.786,
|
| 1131 |
+
"step": 1480
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 26.02,
|
| 1135 |
+
"learning_rate": 3.653653653653654e-06,
|
| 1136 |
+
"loss": 0.437,
|
| 1137 |
+
"step": 1490
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 26.02,
|
| 1141 |
+
"learning_rate": 3.603603603603604e-06,
|
| 1142 |
+
"loss": 0.6708,
|
| 1143 |
+
"step": 1500
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 26.02,
|
| 1147 |
+
"learning_rate": 3.5535535535535535e-06,
|
| 1148 |
+
"loss": 0.6754,
|
| 1149 |
+
"step": 1510
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 26.03,
|
| 1153 |
+
"eval_accuracy": 0.6359447004608295,
|
| 1154 |
+
"eval_loss": 0.9443588852882385,
|
| 1155 |
+
"eval_runtime": 163.9867,
|
| 1156 |
+
"eval_samples_per_second": 1.323,
|
| 1157 |
+
"eval_steps_per_second": 0.171,
|
| 1158 |
+
"step": 1512
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 27.0,
|
| 1162 |
+
"learning_rate": 3.5035035035035036e-06,
|
| 1163 |
+
"loss": 0.7284,
|
| 1164 |
+
"step": 1520
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 27.01,
|
| 1168 |
+
"learning_rate": 3.4534534534534537e-06,
|
| 1169 |
+
"loss": 0.5413,
|
| 1170 |
+
"step": 1530
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 27.01,
|
| 1174 |
+
"learning_rate": 3.4034034034034037e-06,
|
| 1175 |
+
"loss": 0.6884,
|
| 1176 |
+
"step": 1540
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 27.02,
|
| 1180 |
+
"learning_rate": 3.3533533533533534e-06,
|
| 1181 |
+
"loss": 0.5541,
|
| 1182 |
+
"step": 1550
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 27.02,
|
| 1186 |
+
"learning_rate": 3.3033033033033035e-06,
|
| 1187 |
+
"loss": 0.6673,
|
| 1188 |
+
"step": 1560
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 27.03,
|
| 1192 |
+
"eval_accuracy": 0.6543778801843319,
|
| 1193 |
+
"eval_loss": 0.8390823602676392,
|
| 1194 |
+
"eval_runtime": 164.572,
|
| 1195 |
+
"eval_samples_per_second": 1.319,
|
| 1196 |
+
"eval_steps_per_second": 0.17,
|
| 1197 |
+
"step": 1568
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 28.0,
|
| 1201 |
+
"learning_rate": 3.2532532532532535e-06,
|
| 1202 |
+
"loss": 0.6895,
|
| 1203 |
+
"step": 1570
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 28.01,
|
| 1207 |
+
"learning_rate": 3.2032032032032036e-06,
|
| 1208 |
+
"loss": 0.553,
|
| 1209 |
+
"step": 1580
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 28.01,
|
| 1213 |
+
"learning_rate": 3.1531531531531532e-06,
|
| 1214 |
+
"loss": 0.4311,
|
| 1215 |
+
"step": 1590
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 28.01,
|
| 1219 |
+
"learning_rate": 3.1031031031031033e-06,
|
| 1220 |
+
"loss": 0.6969,
|
| 1221 |
+
"step": 1600
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 28.02,
|
| 1225 |
+
"learning_rate": 3.0530530530530534e-06,
|
| 1226 |
+
"loss": 0.7507,
|
| 1227 |
+
"step": 1610
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 28.02,
|
| 1231 |
+
"learning_rate": 3.0030030030030034e-06,
|
| 1232 |
+
"loss": 0.4924,
|
| 1233 |
+
"step": 1620
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 28.03,
|
| 1237 |
+
"eval_accuracy": 0.6682027649769585,
|
| 1238 |
+
"eval_loss": 0.8288503885269165,
|
| 1239 |
+
"eval_runtime": 164.6437,
|
| 1240 |
+
"eval_samples_per_second": 1.318,
|
| 1241 |
+
"eval_steps_per_second": 0.17,
|
| 1242 |
+
"step": 1624
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 29.0,
|
| 1246 |
+
"learning_rate": 2.952952952952953e-06,
|
| 1247 |
+
"loss": 0.7695,
|
| 1248 |
+
"step": 1630
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 29.01,
|
| 1252 |
+
"learning_rate": 2.902902902902903e-06,
|
| 1253 |
+
"loss": 0.5981,
|
| 1254 |
+
"step": 1640
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 29.01,
|
| 1258 |
+
"learning_rate": 2.8528528528528532e-06,
|
| 1259 |
+
"loss": 0.613,
|
| 1260 |
+
"step": 1650
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 29.02,
|
| 1264 |
+
"learning_rate": 2.8028028028028033e-06,
|
| 1265 |
+
"loss": 0.5841,
|
| 1266 |
+
"step": 1660
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 29.02,
|
| 1270 |
+
"learning_rate": 2.752752752752753e-06,
|
| 1271 |
+
"loss": 0.7704,
|
| 1272 |
+
"step": 1670
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 29.03,
|
| 1276 |
+
"learning_rate": 2.702702702702703e-06,
|
| 1277 |
+
"loss": 0.6438,
|
| 1278 |
+
"step": 1680
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 29.03,
|
| 1282 |
+
"eval_accuracy": 0.6129032258064516,
|
| 1283 |
+
"eval_loss": 0.9605286121368408,
|
| 1284 |
+
"eval_runtime": 164.5062,
|
| 1285 |
+
"eval_samples_per_second": 1.319,
|
| 1286 |
+
"eval_steps_per_second": 0.17,
|
| 1287 |
+
"step": 1680
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 30.0,
|
| 1291 |
+
"learning_rate": 2.652652652652653e-06,
|
| 1292 |
+
"loss": 0.583,
|
| 1293 |
+
"step": 1690
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 30.01,
|
| 1297 |
+
"learning_rate": 2.602602602602603e-06,
|
| 1298 |
+
"loss": 0.7539,
|
| 1299 |
+
"step": 1700
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 30.01,
|
| 1303 |
+
"learning_rate": 2.552552552552553e-06,
|
| 1304 |
+
"loss": 0.5418,
|
| 1305 |
+
"step": 1710
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 30.02,
|
| 1309 |
+
"learning_rate": 2.502502502502503e-06,
|
| 1310 |
+
"loss": 0.6689,
|
| 1311 |
+
"step": 1720
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 30.02,
|
| 1315 |
+
"learning_rate": 2.4524524524524525e-06,
|
| 1316 |
+
"loss": 0.5714,
|
| 1317 |
+
"step": 1730
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 30.03,
|
| 1321 |
+
"eval_accuracy": 0.6451612903225806,
|
| 1322 |
+
"eval_loss": 0.8838080763816833,
|
| 1323 |
+
"eval_runtime": 163.4686,
|
| 1324 |
+
"eval_samples_per_second": 1.327,
|
| 1325 |
+
"eval_steps_per_second": 0.171,
|
| 1326 |
+
"step": 1736
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 31.0,
|
| 1330 |
+
"learning_rate": 2.4024024024024026e-06,
|
| 1331 |
+
"loss": 0.4737,
|
| 1332 |
+
"step": 1740
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 31.01,
|
| 1336 |
+
"learning_rate": 2.3523523523523527e-06,
|
| 1337 |
+
"loss": 0.6563,
|
| 1338 |
+
"step": 1750
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 31.01,
|
| 1342 |
+
"learning_rate": 2.3023023023023023e-06,
|
| 1343 |
+
"loss": 0.4469,
|
| 1344 |
+
"step": 1760
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 31.02,
|
| 1348 |
+
"learning_rate": 2.2522522522522524e-06,
|
| 1349 |
+
"loss": 0.5655,
|
| 1350 |
+
"step": 1770
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 31.02,
|
| 1354 |
+
"learning_rate": 2.2022022022022024e-06,
|
| 1355 |
+
"loss": 0.5421,
|
| 1356 |
+
"step": 1780
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 31.02,
|
| 1360 |
+
"learning_rate": 2.1521521521521525e-06,
|
| 1361 |
+
"loss": 0.6726,
|
| 1362 |
+
"step": 1790
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 31.03,
|
| 1366 |
+
"eval_accuracy": 0.6589861751152074,
|
| 1367 |
+
"eval_loss": 0.8412278890609741,
|
| 1368 |
+
"eval_runtime": 164.9282,
|
| 1369 |
+
"eval_samples_per_second": 1.316,
|
| 1370 |
+
"eval_steps_per_second": 0.17,
|
| 1371 |
+
"step": 1792
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 32.0,
|
| 1375 |
+
"learning_rate": 2.102102102102102e-06,
|
| 1376 |
+
"loss": 0.7254,
|
| 1377 |
+
"step": 1800
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 32.01,
|
| 1381 |
+
"learning_rate": 2.0520520520520522e-06,
|
| 1382 |
+
"loss": 0.5397,
|
| 1383 |
+
"step": 1810
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 32.01,
|
| 1387 |
+
"learning_rate": 2.0020020020020023e-06,
|
| 1388 |
+
"loss": 0.596,
|
| 1389 |
+
"step": 1820
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 32.02,
|
| 1393 |
+
"learning_rate": 1.951951951951952e-06,
|
| 1394 |
+
"loss": 0.5603,
|
| 1395 |
+
"step": 1830
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 32.02,
|
| 1399 |
+
"learning_rate": 1.901901901901902e-06,
|
| 1400 |
+
"loss": 0.5027,
|
| 1401 |
+
"step": 1840
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 32.03,
|
| 1405 |
+
"eval_accuracy": 0.6728110599078341,
|
| 1406 |
+
"eval_loss": 0.8439391255378723,
|
| 1407 |
+
"eval_runtime": 168.1229,
|
| 1408 |
+
"eval_samples_per_second": 1.291,
|
| 1409 |
+
"eval_steps_per_second": 0.167,
|
| 1410 |
+
"step": 1848
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 33.0,
|
| 1414 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 1415 |
+
"loss": 0.6769,
|
| 1416 |
+
"step": 1850
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 33.01,
|
| 1420 |
+
"learning_rate": 1.801801801801802e-06,
|
| 1421 |
+
"loss": 0.565,
|
| 1422 |
+
"step": 1860
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 33.01,
|
| 1426 |
+
"learning_rate": 1.7517517517517518e-06,
|
| 1427 |
+
"loss": 0.556,
|
| 1428 |
+
"step": 1870
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 33.01,
|
| 1432 |
+
"learning_rate": 1.7017017017017019e-06,
|
| 1433 |
+
"loss": 0.4187,
|
| 1434 |
+
"step": 1880
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 33.02,
|
| 1438 |
+
"learning_rate": 1.6516516516516517e-06,
|
| 1439 |
+
"loss": 0.4718,
|
| 1440 |
+
"step": 1890
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 33.02,
|
| 1444 |
+
"learning_rate": 1.6016016016016018e-06,
|
| 1445 |
+
"loss": 0.4649,
|
| 1446 |
+
"step": 1900
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 33.03,
|
| 1450 |
+
"eval_accuracy": 0.6267281105990783,
|
| 1451 |
+
"eval_loss": 0.9524617791175842,
|
| 1452 |
+
"eval_runtime": 169.6407,
|
| 1453 |
+
"eval_samples_per_second": 1.279,
|
| 1454 |
+
"eval_steps_per_second": 0.165,
|
| 1455 |
+
"step": 1904
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 34.0,
|
| 1459 |
+
"learning_rate": 1.5515515515515517e-06,
|
| 1460 |
+
"loss": 0.4505,
|
| 1461 |
+
"step": 1910
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 34.01,
|
| 1465 |
+
"learning_rate": 1.5015015015015017e-06,
|
| 1466 |
+
"loss": 0.5412,
|
| 1467 |
+
"step": 1920
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 34.01,
|
| 1471 |
+
"learning_rate": 1.4514514514514516e-06,
|
| 1472 |
+
"loss": 0.5931,
|
| 1473 |
+
"step": 1930
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 34.02,
|
| 1477 |
+
"learning_rate": 1.4014014014014016e-06,
|
| 1478 |
+
"loss": 0.4183,
|
| 1479 |
+
"step": 1940
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 34.02,
|
| 1483 |
+
"learning_rate": 1.3513513513513515e-06,
|
| 1484 |
+
"loss": 0.6046,
|
| 1485 |
+
"step": 1950
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 34.03,
|
| 1489 |
+
"learning_rate": 1.3013013013013016e-06,
|
| 1490 |
+
"loss": 0.6625,
|
| 1491 |
+
"step": 1960
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 34.03,
|
| 1495 |
+
"eval_accuracy": 0.728110599078341,
|
| 1496 |
+
"eval_loss": 0.7850246429443359,
|
| 1497 |
+
"eval_runtime": 164.4991,
|
| 1498 |
+
"eval_samples_per_second": 1.319,
|
| 1499 |
+
"eval_steps_per_second": 0.17,
|
| 1500 |
+
"step": 1960
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 35.0,
|
| 1504 |
+
"learning_rate": 1.2512512512512514e-06,
|
| 1505 |
+
"loss": 0.5967,
|
| 1506 |
+
"step": 1970
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 35.01,
|
| 1510 |
+
"learning_rate": 1.2012012012012013e-06,
|
| 1511 |
+
"loss": 0.5503,
|
| 1512 |
+
"step": 1980
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 35.01,
|
| 1516 |
+
"learning_rate": 1.1511511511511512e-06,
|
| 1517 |
+
"loss": 0.5159,
|
| 1518 |
+
"step": 1990
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 35.02,
|
| 1522 |
+
"learning_rate": 1.1011011011011012e-06,
|
| 1523 |
+
"loss": 0.4377,
|
| 1524 |
+
"step": 2000
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 35.02,
|
| 1528 |
+
"learning_rate": 1.051051051051051e-06,
|
| 1529 |
+
"loss": 0.5793,
|
| 1530 |
+
"step": 2010
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 35.03,
|
| 1534 |
+
"eval_accuracy": 0.6728110599078341,
|
| 1535 |
+
"eval_loss": 0.8481199741363525,
|
| 1536 |
+
"eval_runtime": 164.3359,
|
| 1537 |
+
"eval_samples_per_second": 1.32,
|
| 1538 |
+
"eval_steps_per_second": 0.17,
|
| 1539 |
+
"step": 2016
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 36.0,
|
| 1543 |
+
"learning_rate": 1.0010010010010011e-06,
|
| 1544 |
+
"loss": 0.7009,
|
| 1545 |
+
"step": 2020
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 36.01,
|
| 1549 |
+
"learning_rate": 9.50950950950951e-07,
|
| 1550 |
+
"loss": 0.5902,
|
| 1551 |
+
"step": 2030
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 36.01,
|
| 1555 |
+
"learning_rate": 9.00900900900901e-07,
|
| 1556 |
+
"loss": 0.5366,
|
| 1557 |
+
"step": 2040
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 36.02,
|
| 1561 |
+
"learning_rate": 8.508508508508509e-07,
|
| 1562 |
+
"loss": 0.5119,
|
| 1563 |
+
"step": 2050
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 36.02,
|
| 1567 |
+
"learning_rate": 8.008008008008009e-07,
|
| 1568 |
+
"loss": 0.4946,
|
| 1569 |
+
"step": 2060
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 36.02,
|
| 1573 |
+
"learning_rate": 7.507507507507509e-07,
|
| 1574 |
+
"loss": 0.6411,
|
| 1575 |
+
"step": 2070
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 36.03,
|
| 1579 |
+
"eval_accuracy": 0.6589861751152074,
|
| 1580 |
+
"eval_loss": 0.8842198252677917,
|
| 1581 |
+
"eval_runtime": 164.6218,
|
| 1582 |
+
"eval_samples_per_second": 1.318,
|
| 1583 |
+
"eval_steps_per_second": 0.17,
|
| 1584 |
+
"step": 2072
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 37.0,
|
| 1588 |
+
"learning_rate": 7.007007007007008e-07,
|
| 1589 |
+
"loss": 0.5172,
|
| 1590 |
+
"step": 2080
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 37.01,
|
| 1594 |
+
"learning_rate": 6.506506506506508e-07,
|
| 1595 |
+
"loss": 0.3986,
|
| 1596 |
+
"step": 2090
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 37.01,
|
| 1600 |
+
"learning_rate": 6.006006006006006e-07,
|
| 1601 |
+
"loss": 0.4807,
|
| 1602 |
+
"step": 2100
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 37.02,
|
| 1606 |
+
"learning_rate": 5.505505505505506e-07,
|
| 1607 |
+
"loss": 0.4681,
|
| 1608 |
+
"step": 2110
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 37.02,
|
| 1612 |
+
"learning_rate": 5.005005005005006e-07,
|
| 1613 |
+
"loss": 0.6592,
|
| 1614 |
+
"step": 2120
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 37.03,
|
| 1618 |
+
"eval_accuracy": 0.6912442396313364,
|
| 1619 |
+
"eval_loss": 0.802787184715271,
|
| 1620 |
+
"eval_runtime": 163.9059,
|
| 1621 |
+
"eval_samples_per_second": 1.324,
|
| 1622 |
+
"eval_steps_per_second": 0.171,
|
| 1623 |
+
"step": 2128
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 38.0,
|
| 1627 |
+
"learning_rate": 4.504504504504505e-07,
|
| 1628 |
+
"loss": 0.5769,
|
| 1629 |
+
"step": 2130
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 38.01,
|
| 1633 |
+
"learning_rate": 4.0040040040040045e-07,
|
| 1634 |
+
"loss": 0.6323,
|
| 1635 |
+
"step": 2140
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 38.01,
|
| 1639 |
+
"learning_rate": 3.503503503503504e-07,
|
| 1640 |
+
"loss": 0.5319,
|
| 1641 |
+
"step": 2150
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 38.01,
|
| 1645 |
+
"learning_rate": 3.003003003003003e-07,
|
| 1646 |
+
"loss": 0.6306,
|
| 1647 |
+
"step": 2160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 38.02,
|
| 1651 |
+
"learning_rate": 2.502502502502503e-07,
|
| 1652 |
+
"loss": 0.6192,
|
| 1653 |
+
"step": 2170
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 38.02,
|
| 1657 |
+
"learning_rate": 2.0020020020020022e-07,
|
| 1658 |
+
"loss": 0.5524,
|
| 1659 |
+
"step": 2180
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 38.03,
|
| 1663 |
+
"eval_accuracy": 0.6866359447004609,
|
| 1664 |
+
"eval_loss": 0.821592390537262,
|
| 1665 |
+
"eval_runtime": 165.1926,
|
| 1666 |
+
"eval_samples_per_second": 1.314,
|
| 1667 |
+
"eval_steps_per_second": 0.169,
|
| 1668 |
+
"step": 2184
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 39.0,
|
| 1672 |
+
"learning_rate": 1.5015015015015016e-07,
|
| 1673 |
+
"loss": 0.5701,
|
| 1674 |
+
"step": 2190
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 39.01,
|
| 1678 |
+
"learning_rate": 1.0010010010010011e-07,
|
| 1679 |
+
"loss": 0.5891,
|
| 1680 |
+
"step": 2200
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 39.01,
|
| 1684 |
+
"learning_rate": 5.0050050050050056e-08,
|
| 1685 |
+
"loss": 0.5807,
|
| 1686 |
+
"step": 2210
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 39.02,
|
| 1690 |
+
"learning_rate": 0.0,
|
| 1691 |
+
"loss": 0.5697,
|
| 1692 |
+
"step": 2220
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 39.02,
|
| 1696 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1697 |
+
"eval_loss": 0.833946943283081,
|
| 1698 |
+
"eval_runtime": 164.2083,
|
| 1699 |
+
"eval_samples_per_second": 1.321,
|
| 1700 |
+
"eval_steps_per_second": 0.171,
|
| 1701 |
+
"step": 2220
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 39.02,
|
| 1705 |
+
"step": 2220,
|
| 1706 |
+
"total_flos": 2.208334746599719e+19,
|
| 1707 |
+
"train_loss": 0.8170982454274152,
|
| 1708 |
+
"train_runtime": 23121.8467,
|
| 1709 |
+
"train_samples_per_second": 0.768,
|
| 1710 |
+
"train_steps_per_second": 0.096
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 39.02,
|
| 1714 |
+
"eval_accuracy": 0.6342592592592593,
|
| 1715 |
+
"eval_loss": 0.8682467341423035,
|
| 1716 |
+
"eval_runtime": 165.599,
|
| 1717 |
+
"eval_samples_per_second": 1.304,
|
| 1718 |
+
"eval_steps_per_second": 0.163,
|
| 1719 |
+
"step": 2220
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 39.02,
|
| 1723 |
+
"eval_accuracy": 0.6342592592592593,
|
| 1724 |
+
"eval_loss": 0.8682467341423035,
|
| 1725 |
+
"eval_runtime": 165.9338,
|
| 1726 |
+
"eval_samples_per_second": 1.302,
|
| 1727 |
+
"eval_steps_per_second": 0.163,
|
| 1728 |
+
"step": 2220
|
| 1729 |
}
|
| 1730 |
],
|
| 1731 |
"logging_steps": 10,
|
| 1732 |
+
"max_steps": 2220,
|
| 1733 |
"num_input_tokens_seen": 0,
|
| 1734 |
"num_train_epochs": 9223372036854775807,
|
| 1735 |
"save_steps": 500,
|
| 1736 |
+
"total_flos": 2.208334746599719e+19,
|
| 1737 |
"train_batch_size": 8,
|
| 1738 |
"trial_name": null,
|
| 1739 |
"trial_params": null
|