End of training
Browse files
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 21.
|
| 6 |
-
"eval_samples_per_second": 8.
|
| 7 |
-
"eval_steps_per_second": 8.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.17,
|
| 3 |
+
"eval_accuracy": 0.8601036269430051,
|
| 4 |
+
"eval_loss": 0.552123486995697,
|
| 5 |
+
"eval_runtime": 21.6981,
|
| 6 |
+
"eval_samples_per_second": 8.895,
|
| 7 |
+
"eval_steps_per_second": 8.895
|
| 8 |
}
|
runs/Dec04_05-15-34_ae41475a0cd8/events.out.tfevents.1701667485.ae41475a0cd8.4459.1
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08b741716acc007704d123cb9d514895c76c635b1147470178a59ec41446634d
|
| 3 |
+
size 734
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 21.
|
| 6 |
-
"eval_samples_per_second": 8.
|
| 7 |
-
"eval_steps_per_second": 8.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.17,
|
| 3 |
+
"eval_accuracy": 0.8601036269430051,
|
| 4 |
+
"eval_loss": 0.552123486995697,
|
| 5 |
+
"eval_runtime": 21.6981,
|
| 6 |
+
"eval_samples_per_second": 8.895,
|
| 7 |
+
"eval_steps_per_second": 8.895
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,901 +1,1072 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/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": 0.01,
|
| 13 |
-
"learning_rate": 3.
|
| 14 |
-
"loss": 2.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.01,
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 2.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.02,
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss": 2.
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 1.
|
| 32 |
-
"loss": 2.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 1.
|
| 38 |
-
"loss": 2.
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.04,
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 2.
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 2.
|
| 50 |
-
"loss": 2.
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 2.
|
| 56 |
-
"loss": 2.
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate":
|
| 62 |
-
"loss": 2.
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 3.
|
| 68 |
-
"loss": 2.
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate":
|
| 74 |
-
"loss": 2.
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate":
|
| 80 |
-
"loss": 2.
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 4.
|
| 86 |
-
"loss": 2.
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 4.
|
| 92 |
-
"loss": 2.
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate": 4.
|
| 98 |
-
"loss": 2.
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 0.
|
| 103 |
-
"learning_rate": 4.
|
| 104 |
-
"loss": 1.
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 0.
|
| 109 |
-
"learning_rate": 4.
|
| 110 |
-
"loss":
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch": 0.
|
| 115 |
-
"learning_rate": 4.
|
| 116 |
-
"loss": 2.
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch": 0.
|
| 121 |
-
"learning_rate": 4.
|
| 122 |
-
"loss": 1.
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0.
|
| 127 |
-
"learning_rate": 4.
|
| 128 |
-
"loss": 2.
|
| 129 |
"step": 200
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
-
"learning_rate": 4.
|
| 134 |
-
"loss":
|
| 135 |
"step": 210
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"learning_rate": 4.
|
| 140 |
-
"loss": 1.
|
| 141 |
"step": 220
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 0.
|
| 145 |
-
"learning_rate": 4.
|
| 146 |
-
"loss": 2.
|
| 147 |
"step": 230
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 0.
|
| 151 |
-
"learning_rate": 4.
|
| 152 |
-
"loss":
|
| 153 |
"step": 240
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 0.
|
| 157 |
-
"learning_rate": 4.
|
| 158 |
-
"loss":
|
| 159 |
"step": 250
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 0.
|
| 163 |
-
"learning_rate": 4.
|
| 164 |
-
"loss":
|
| 165 |
"step": 260
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch": 0.
|
| 169 |
-
"learning_rate": 4.
|
| 170 |
-
"loss": 1.
|
| 171 |
"step": 270
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"eval_accuracy": 0.
|
| 176 |
-
"eval_loss": 1.
|
| 177 |
-
"eval_runtime":
|
| 178 |
-
"eval_samples_per_second":
|
| 179 |
-
"eval_steps_per_second":
|
| 180 |
"step": 270
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 1.01,
|
| 184 |
-
"learning_rate": 4.
|
| 185 |
-
"loss": 1.
|
| 186 |
"step": 280
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 1.01,
|
| 190 |
-
"learning_rate": 4.
|
| 191 |
-
"loss": 1.
|
| 192 |
"step": 290
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 1.02,
|
| 196 |
-
"learning_rate": 4.
|
| 197 |
-
"loss":
|
| 198 |
"step": 300
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch": 1.
|
| 202 |
-
"learning_rate": 4.
|
| 203 |
-
"loss": 1.
|
| 204 |
"step": 310
|
| 205 |
},
|
| 206 |
{
|
| 207 |
-
"epoch": 1.
|
| 208 |
-
"learning_rate": 4.
|
| 209 |
-
"loss": 1.
|
| 210 |
"step": 320
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 1.04,
|
| 214 |
-
"learning_rate": 4.
|
| 215 |
-
"loss":
|
| 216 |
"step": 330
|
| 217 |
},
|
| 218 |
{
|
| 219 |
-
"epoch": 1.
|
| 220 |
-
"learning_rate": 4.
|
| 221 |
-
"loss": 1.
|
| 222 |
"step": 340
|
| 223 |
},
|
| 224 |
{
|
| 225 |
-
"epoch": 1.
|
| 226 |
-
"learning_rate": 4.
|
| 227 |
-
"loss": 1.
|
| 228 |
"step": 350
|
| 229 |
},
|
| 230 |
{
|
| 231 |
-
"epoch": 1.
|
| 232 |
-
"learning_rate": 4.
|
| 233 |
-
"loss": 1.
|
| 234 |
"step": 360
|
| 235 |
},
|
| 236 |
{
|
| 237 |
-
"epoch": 1.
|
| 238 |
-
"learning_rate": 4.
|
| 239 |
-
"loss": 1.
|
| 240 |
"step": 370
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch": 1.
|
| 244 |
-
"learning_rate":
|
| 245 |
-
"loss": 1.
|
| 246 |
"step": 380
|
| 247 |
},
|
| 248 |
{
|
| 249 |
-
"epoch": 1.
|
| 250 |
-
"learning_rate":
|
| 251 |
-
"loss": 1.
|
| 252 |
"step": 390
|
| 253 |
},
|
| 254 |
{
|
| 255 |
-
"epoch": 1.
|
| 256 |
-
"learning_rate":
|
| 257 |
-
"loss": 1.
|
| 258 |
"step": 400
|
| 259 |
},
|
| 260 |
{
|
| 261 |
-
"epoch": 1.
|
| 262 |
-
"learning_rate":
|
| 263 |
-
"loss": 1.
|
| 264 |
"step": 410
|
| 265 |
},
|
| 266 |
{
|
| 267 |
-
"epoch": 1.
|
| 268 |
-
"learning_rate":
|
| 269 |
-
"loss":
|
| 270 |
"step": 420
|
| 271 |
},
|
| 272 |
{
|
| 273 |
-
"epoch": 1.
|
| 274 |
-
"learning_rate":
|
| 275 |
-
"loss":
|
| 276 |
"step": 430
|
| 277 |
},
|
| 278 |
{
|
| 279 |
-
"epoch": 1.
|
| 280 |
-
"learning_rate":
|
| 281 |
-
"loss": 1.
|
| 282 |
"step": 440
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch": 1.
|
| 286 |
-
"learning_rate":
|
| 287 |
-
"loss": 1.
|
| 288 |
"step": 450
|
| 289 |
},
|
| 290 |
{
|
| 291 |
-
"epoch": 1.
|
| 292 |
-
"learning_rate": 3.
|
| 293 |
-
"loss": 1.
|
| 294 |
"step": 460
|
| 295 |
},
|
| 296 |
{
|
| 297 |
-
"epoch": 1.
|
| 298 |
-
"learning_rate": 3.
|
| 299 |
-
"loss": 1.
|
| 300 |
"step": 470
|
| 301 |
},
|
| 302 |
{
|
| 303 |
-
"epoch": 1.
|
| 304 |
-
"learning_rate": 3.
|
| 305 |
-
"loss": 1.
|
| 306 |
"step": 480
|
| 307 |
},
|
| 308 |
{
|
| 309 |
-
"epoch": 1.
|
| 310 |
-
"learning_rate": 3.
|
| 311 |
-
"loss": 1.
|
| 312 |
"step": 490
|
| 313 |
},
|
| 314 |
{
|
| 315 |
-
"epoch": 1.
|
| 316 |
-
"learning_rate": 3.
|
| 317 |
-
"loss": 1.
|
| 318 |
"step": 500
|
| 319 |
},
|
| 320 |
{
|
| 321 |
-
"epoch": 1.
|
| 322 |
-
"learning_rate": 3.
|
| 323 |
-
"loss":
|
| 324 |
"step": 510
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch": 1.
|
| 328 |
-
"learning_rate": 3.
|
| 329 |
-
"loss":
|
| 330 |
"step": 520
|
| 331 |
},
|
| 332 |
{
|
| 333 |
-
"epoch": 1.
|
| 334 |
-
"learning_rate": 3.
|
| 335 |
-
"loss":
|
| 336 |
"step": 530
|
| 337 |
},
|
| 338 |
{
|
| 339 |
-
"epoch": 1.
|
| 340 |
-
"learning_rate": 3.
|
| 341 |
-
"loss": 1.
|
| 342 |
"step": 540
|
| 343 |
},
|
| 344 |
{
|
| 345 |
-
"epoch": 1.
|
| 346 |
-
"eval_accuracy": 0.
|
| 347 |
-
"eval_loss": 1.
|
| 348 |
-
"eval_runtime": 23.
|
| 349 |
-
"eval_samples_per_second": 8.
|
| 350 |
-
"eval_steps_per_second": 8.
|
| 351 |
"step": 540
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 2.01,
|
| 355 |
-
"learning_rate": 3.
|
| 356 |
-
"loss": 1.
|
| 357 |
"step": 550
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 2.01,
|
| 361 |
-
"learning_rate": 3.
|
| 362 |
-
"loss": 0.
|
| 363 |
"step": 560
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 2.02,
|
| 367 |
-
"learning_rate": 3.
|
| 368 |
-
"loss": 1.
|
| 369 |
"step": 570
|
| 370 |
},
|
| 371 |
{
|
| 372 |
-
"epoch": 2.
|
| 373 |
-
"learning_rate": 3.
|
| 374 |
-
"loss": 0.
|
| 375 |
"step": 580
|
| 376 |
},
|
| 377 |
{
|
| 378 |
-
"epoch": 2.
|
| 379 |
-
"learning_rate": 3.
|
| 380 |
-
"loss": 1.
|
| 381 |
"step": 590
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 2.04,
|
| 385 |
-
"learning_rate": 3.
|
| 386 |
-
"loss":
|
| 387 |
"step": 600
|
| 388 |
},
|
| 389 |
{
|
| 390 |
-
"epoch": 2.
|
| 391 |
-
"learning_rate": 3.
|
| 392 |
-
"loss": 1.
|
| 393 |
"step": 610
|
| 394 |
},
|
| 395 |
{
|
| 396 |
-
"epoch": 2.
|
| 397 |
-
"learning_rate": 3.
|
| 398 |
-
"loss":
|
| 399 |
"step": 620
|
| 400 |
},
|
| 401 |
{
|
| 402 |
-
"epoch": 2.
|
| 403 |
-
"learning_rate":
|
| 404 |
-
"loss": 0.
|
| 405 |
"step": 630
|
| 406 |
},
|
| 407 |
{
|
| 408 |
-
"epoch": 2.
|
| 409 |
-
"learning_rate":
|
| 410 |
-
"loss": 1.
|
| 411 |
"step": 640
|
| 412 |
},
|
| 413 |
{
|
| 414 |
-
"epoch": 2.
|
| 415 |
-
"learning_rate":
|
| 416 |
-
"loss": 1.
|
| 417 |
"step": 650
|
| 418 |
},
|
| 419 |
{
|
| 420 |
-
"epoch": 2.
|
| 421 |
-
"learning_rate":
|
| 422 |
-
"loss": 0.
|
| 423 |
"step": 660
|
| 424 |
},
|
| 425 |
{
|
| 426 |
-
"epoch": 2.
|
| 427 |
-
"learning_rate":
|
| 428 |
-
"loss":
|
| 429 |
"step": 670
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch": 2.
|
| 433 |
-
"learning_rate":
|
| 434 |
-
"loss": 0.
|
| 435 |
"step": 680
|
| 436 |
},
|
| 437 |
{
|
| 438 |
-
"epoch": 2.
|
| 439 |
-
"learning_rate":
|
| 440 |
-
"loss": 0.
|
| 441 |
"step": 690
|
| 442 |
},
|
| 443 |
{
|
| 444 |
-
"epoch": 2.
|
| 445 |
-
"learning_rate":
|
| 446 |
-
"loss":
|
| 447 |
"step": 700
|
| 448 |
},
|
| 449 |
{
|
| 450 |
-
"epoch": 2.
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 710
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch": 2.
|
| 457 |
-
"learning_rate":
|
| 458 |
-
"loss": 0.
|
| 459 |
"step": 720
|
| 460 |
},
|
| 461 |
{
|
| 462 |
-
"epoch": 2.
|
| 463 |
-
"learning_rate":
|
| 464 |
-
"loss": 0.
|
| 465 |
"step": 730
|
| 466 |
},
|
| 467 |
{
|
| 468 |
-
"epoch": 2.
|
| 469 |
-
"learning_rate":
|
| 470 |
-
"loss": 1.
|
| 471 |
"step": 740
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch": 2.
|
| 475 |
-
"learning_rate": 2.
|
| 476 |
-
"loss": 0.
|
| 477 |
"step": 750
|
| 478 |
},
|
| 479 |
{
|
| 480 |
-
"epoch": 2.
|
| 481 |
-
"learning_rate": 2.
|
| 482 |
-
"loss":
|
| 483 |
"step": 760
|
| 484 |
},
|
| 485 |
{
|
| 486 |
-
"epoch": 2.
|
| 487 |
-
"learning_rate": 2.
|
| 488 |
-
"loss": 0.
|
| 489 |
"step": 770
|
| 490 |
},
|
| 491 |
{
|
| 492 |
-
"epoch": 2.
|
| 493 |
-
"learning_rate": 2.
|
| 494 |
-
"loss": 1.
|
| 495 |
"step": 780
|
| 496 |
},
|
| 497 |
{
|
| 498 |
-
"epoch": 2.
|
| 499 |
-
"learning_rate": 2.
|
| 500 |
-
"loss": 0.
|
| 501 |
"step": 790
|
| 502 |
},
|
| 503 |
{
|
| 504 |
-
"epoch": 2.
|
| 505 |
-
"learning_rate": 2.
|
| 506 |
-
"loss": 0.
|
| 507 |
"step": 800
|
| 508 |
},
|
| 509 |
{
|
| 510 |
-
"epoch": 2.
|
| 511 |
-
"learning_rate": 2.
|
| 512 |
-
"loss": 0.
|
| 513 |
"step": 810
|
| 514 |
},
|
| 515 |
{
|
| 516 |
-
"epoch": 2.
|
| 517 |
-
"eval_accuracy": 0.
|
| 518 |
-
"eval_loss":
|
| 519 |
-
"eval_runtime": 23.
|
| 520 |
-
"eval_samples_per_second": 8.
|
| 521 |
-
"eval_steps_per_second": 8.
|
| 522 |
"step": 810
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 3.01,
|
| 526 |
-
"learning_rate": 2.
|
| 527 |
-
"loss": 0.
|
| 528 |
"step": 820
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 3.01,
|
| 532 |
-
"learning_rate": 2.
|
| 533 |
-
"loss": 0.
|
| 534 |
"step": 830
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 3.02,
|
| 538 |
-
"learning_rate": 2.
|
| 539 |
-
"loss": 0.
|
| 540 |
"step": 840
|
| 541 |
},
|
| 542 |
{
|
| 543 |
-
"epoch": 3.
|
| 544 |
-
"learning_rate": 2.
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 850
|
| 547 |
},
|
| 548 |
{
|
| 549 |
-
"epoch": 3.
|
| 550 |
-
"learning_rate": 2.
|
| 551 |
-
"loss": 0.
|
| 552 |
"step": 860
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 3.04,
|
| 556 |
-
"learning_rate":
|
| 557 |
-
"loss": 0.
|
| 558 |
"step": 870
|
| 559 |
},
|
| 560 |
{
|
| 561 |
-
"epoch": 3.
|
| 562 |
-
"learning_rate":
|
| 563 |
-
"loss": 0.
|
| 564 |
"step": 880
|
| 565 |
},
|
| 566 |
{
|
| 567 |
-
"epoch": 3.
|
| 568 |
-
"learning_rate":
|
| 569 |
-
"loss":
|
| 570 |
"step": 890
|
| 571 |
},
|
| 572 |
{
|
| 573 |
-
"epoch": 3.
|
| 574 |
-
"learning_rate":
|
| 575 |
-
"loss": 0.
|
| 576 |
"step": 900
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"epoch": 3.
|
| 580 |
-
"learning_rate":
|
| 581 |
-
"loss": 0.
|
| 582 |
"step": 910
|
| 583 |
},
|
| 584 |
{
|
| 585 |
-
"epoch": 3.
|
| 586 |
-
"learning_rate":
|
| 587 |
-
"loss": 0.
|
| 588 |
"step": 920
|
| 589 |
},
|
| 590 |
{
|
| 591 |
-
"epoch": 3.
|
| 592 |
-
"learning_rate":
|
| 593 |
-
"loss": 0.
|
| 594 |
"step": 930
|
| 595 |
},
|
| 596 |
{
|
| 597 |
-
"epoch": 3.
|
| 598 |
-
"learning_rate":
|
| 599 |
-
"loss": 0.
|
| 600 |
"step": 940
|
| 601 |
},
|
| 602 |
{
|
| 603 |
-
"epoch": 3.
|
| 604 |
-
"learning_rate":
|
| 605 |
-
"loss": 0.
|
| 606 |
"step": 950
|
| 607 |
},
|
| 608 |
{
|
| 609 |
-
"epoch": 3.
|
| 610 |
-
"learning_rate":
|
| 611 |
-
"loss": 0.
|
| 612 |
"step": 960
|
| 613 |
},
|
| 614 |
{
|
| 615 |
-
"epoch": 3.
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 970
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch": 3.
|
| 622 |
-
"learning_rate":
|
| 623 |
-
"loss": 0.
|
| 624 |
"step": 980
|
| 625 |
},
|
| 626 |
{
|
| 627 |
-
"epoch": 3.
|
| 628 |
-
"learning_rate":
|
| 629 |
-
"loss": 0.
|
| 630 |
"step": 990
|
| 631 |
},
|
| 632 |
{
|
| 633 |
-
"epoch": 3.
|
| 634 |
-
"learning_rate":
|
| 635 |
-
"loss": 0.
|
| 636 |
"step": 1000
|
| 637 |
},
|
| 638 |
{
|
| 639 |
-
"epoch": 3.
|
| 640 |
-
"learning_rate":
|
| 641 |
-
"loss": 0.
|
| 642 |
"step": 1010
|
| 643 |
},
|
| 644 |
{
|
| 645 |
-
"epoch": 3.
|
| 646 |
-
"learning_rate":
|
| 647 |
-
"loss":
|
| 648 |
"step": 1020
|
| 649 |
},
|
| 650 |
{
|
| 651 |
-
"epoch": 3.
|
| 652 |
-
"learning_rate":
|
| 653 |
-
"loss": 0.
|
| 654 |
"step": 1030
|
| 655 |
},
|
| 656 |
{
|
| 657 |
-
"epoch": 3.
|
| 658 |
-
"learning_rate": 1.
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 1040
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"epoch": 3.
|
| 664 |
-
"learning_rate": 1.
|
| 665 |
-
"loss": 0.
|
| 666 |
"step": 1050
|
| 667 |
},
|
| 668 |
{
|
| 669 |
-
"epoch": 3.
|
| 670 |
-
"learning_rate": 1.
|
| 671 |
-
"loss": 0.
|
| 672 |
"step": 1060
|
| 673 |
},
|
| 674 |
{
|
| 675 |
-
"epoch": 3.
|
| 676 |
-
"learning_rate": 1.
|
| 677 |
-
"loss": 0.
|
| 678 |
"step": 1070
|
| 679 |
},
|
| 680 |
{
|
| 681 |
-
"epoch": 3.
|
| 682 |
-
"learning_rate": 1.
|
| 683 |
-
"loss": 0.
|
| 684 |
"step": 1080
|
| 685 |
},
|
| 686 |
{
|
| 687 |
-
"epoch": 3.
|
| 688 |
-
"eval_accuracy": 0.
|
| 689 |
-
"eval_loss": 0.
|
| 690 |
-
"eval_runtime":
|
| 691 |
-
"eval_samples_per_second":
|
| 692 |
-
"eval_steps_per_second":
|
| 693 |
"step": 1080
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 4.01,
|
| 697 |
-
"learning_rate": 1.
|
| 698 |
-
"loss": 0.
|
| 699 |
"step": 1090
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 4.01,
|
| 703 |
-
"learning_rate": 1.
|
| 704 |
-
"loss": 0.
|
| 705 |
"step": 1100
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 4.02,
|
| 709 |
-
"learning_rate":
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 1110
|
| 712 |
},
|
| 713 |
{
|
| 714 |
-
"epoch": 4.
|
| 715 |
-
"learning_rate":
|
| 716 |
-
"loss": 0.
|
| 717 |
"step": 1120
|
| 718 |
},
|
| 719 |
{
|
| 720 |
-
"epoch": 4.
|
| 721 |
-
"learning_rate":
|
| 722 |
-
"loss": 0.
|
| 723 |
"step": 1130
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 4.04,
|
| 727 |
-
"learning_rate":
|
| 728 |
-
"loss": 0.
|
| 729 |
"step": 1140
|
| 730 |
},
|
| 731 |
{
|
| 732 |
-
"epoch": 4.
|
| 733 |
-
"learning_rate":
|
| 734 |
-
"loss": 0.
|
| 735 |
"step": 1150
|
| 736 |
},
|
| 737 |
{
|
| 738 |
-
"epoch": 4.
|
| 739 |
-
"learning_rate":
|
| 740 |
-
"loss": 0.
|
| 741 |
"step": 1160
|
| 742 |
},
|
| 743 |
{
|
| 744 |
-
"epoch": 4.
|
| 745 |
-
"learning_rate":
|
| 746 |
-
"loss": 0.
|
| 747 |
"step": 1170
|
| 748 |
},
|
| 749 |
{
|
| 750 |
-
"epoch": 4.
|
| 751 |
-
"learning_rate":
|
| 752 |
-
"loss": 0.
|
| 753 |
"step": 1180
|
| 754 |
},
|
| 755 |
{
|
| 756 |
-
"epoch": 4.
|
| 757 |
-
"learning_rate":
|
| 758 |
-
"loss": 0.
|
| 759 |
"step": 1190
|
| 760 |
},
|
| 761 |
{
|
| 762 |
-
"epoch": 4.
|
| 763 |
-
"learning_rate":
|
| 764 |
-
"loss": 0.
|
| 765 |
"step": 1200
|
| 766 |
},
|
| 767 |
{
|
| 768 |
-
"epoch": 4.
|
| 769 |
-
"learning_rate":
|
| 770 |
-
"loss": 0.
|
| 771 |
"step": 1210
|
| 772 |
},
|
| 773 |
{
|
| 774 |
-
"epoch": 4.
|
| 775 |
-
"learning_rate":
|
| 776 |
-
"loss": 0.
|
| 777 |
"step": 1220
|
| 778 |
},
|
| 779 |
{
|
| 780 |
-
"epoch": 4.
|
| 781 |
-
"learning_rate":
|
| 782 |
-
"loss": 0.
|
| 783 |
"step": 1230
|
| 784 |
},
|
| 785 |
{
|
| 786 |
-
"epoch": 4.
|
| 787 |
-
"learning_rate":
|
| 788 |
-
"loss": 0.
|
| 789 |
"step": 1240
|
| 790 |
},
|
| 791 |
{
|
| 792 |
-
"epoch": 4.
|
| 793 |
-
"learning_rate":
|
| 794 |
-
"loss": 1.
|
| 795 |
"step": 1250
|
| 796 |
},
|
| 797 |
{
|
| 798 |
-
"epoch": 4.
|
| 799 |
-
"learning_rate":
|
| 800 |
-
"loss": 0.
|
| 801 |
"step": 1260
|
| 802 |
},
|
| 803 |
{
|
| 804 |
-
"epoch": 4.
|
| 805 |
-
"learning_rate":
|
| 806 |
-
"loss": 0.
|
| 807 |
"step": 1270
|
| 808 |
},
|
| 809 |
{
|
| 810 |
-
"epoch": 4.
|
| 811 |
-
"learning_rate":
|
| 812 |
-
"loss": 0.
|
| 813 |
"step": 1280
|
| 814 |
},
|
| 815 |
{
|
| 816 |
-
"epoch": 4.
|
| 817 |
-
"learning_rate":
|
| 818 |
-
"loss": 0.
|
| 819 |
"step": 1290
|
| 820 |
},
|
| 821 |
{
|
| 822 |
-
"epoch": 4.
|
| 823 |
-
"learning_rate":
|
| 824 |
-
"loss":
|
| 825 |
"step": 1300
|
| 826 |
},
|
| 827 |
{
|
| 828 |
-
"epoch": 4.
|
| 829 |
-
"learning_rate": 1.
|
| 830 |
-
"loss": 0.
|
| 831 |
"step": 1310
|
| 832 |
},
|
| 833 |
{
|
| 834 |
-
"epoch": 4.
|
| 835 |
-
"learning_rate": 1.
|
| 836 |
-
"loss": 0.
|
| 837 |
"step": 1320
|
| 838 |
},
|
| 839 |
{
|
| 840 |
-
"epoch": 4.
|
| 841 |
-
"learning_rate":
|
| 842 |
-
"loss": 0.
|
| 843 |
"step": 1330
|
| 844 |
},
|
| 845 |
{
|
| 846 |
-
"epoch": 4.
|
| 847 |
-
"learning_rate":
|
| 848 |
-
"loss": 0.
|
| 849 |
"step": 1340
|
| 850 |
},
|
| 851 |
{
|
| 852 |
-
"epoch": 4.
|
| 853 |
-
"learning_rate":
|
| 854 |
-
"loss": 0.
|
| 855 |
"step": 1350
|
| 856 |
},
|
| 857 |
{
|
| 858 |
-
"epoch": 4.
|
| 859 |
-
"eval_accuracy": 0.
|
| 860 |
-
"eval_loss": 0.
|
| 861 |
-
"eval_runtime":
|
| 862 |
-
"eval_samples_per_second":
|
| 863 |
-
"eval_steps_per_second":
|
| 864 |
"step": 1350
|
| 865 |
},
|
| 866 |
{
|
| 867 |
-
"epoch":
|
| 868 |
-
"
|
| 869 |
-
"
|
| 870 |
-
"
|
| 871 |
-
"train_runtime": 414.0045,
|
| 872 |
-
"train_samples_per_second": 3.261,
|
| 873 |
-
"train_steps_per_second": 3.261
|
| 874 |
},
|
| 875 |
{
|
| 876 |
-
"epoch":
|
| 877 |
-
"
|
| 878 |
-
"
|
| 879 |
-
"
|
| 880 |
-
"eval_samples_per_second": 8.961,
|
| 881 |
-
"eval_steps_per_second": 8.961,
|
| 882 |
-
"step": 1350
|
| 883 |
},
|
| 884 |
{
|
| 885 |
-
"epoch":
|
| 886 |
-
"
|
| 887 |
-
"
|
| 888 |
-
"
|
| 889 |
-
|
| 890 |
-
|
| 891 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 892 |
}
|
| 893 |
],
|
| 894 |
"logging_steps": 10,
|
| 895 |
-
"max_steps":
|
| 896 |
"num_train_epochs": 9223372036854775807,
|
| 897 |
"save_steps": 500,
|
| 898 |
-
"total_flos":
|
| 899 |
"trial_name": null,
|
| 900 |
"trial_params": null
|
| 901 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8695652173913043,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-1620",
|
| 4 |
+
"epoch": 5.166666666666667,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1620,
|
| 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": 3.0864197530864196e-06,
|
| 14 |
+
"loss": 2.1068,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 6.172839506172839e-06,
|
| 20 |
+
"loss": 2.274,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 9.259259259259259e-06,
|
| 26 |
+
"loss": 2.2436,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 32 |
+
"loss": 2.2524,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.03,
|
| 37 |
+
"learning_rate": 1.54320987654321e-05,
|
| 38 |
+
"loss": 2.1734,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.04,
|
| 43 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 44 |
+
"loss": 2.3132,
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.04,
|
| 49 |
+
"learning_rate": 2.1604938271604937e-05,
|
| 50 |
+
"loss": 2.1998,
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 56 |
+
"loss": 2.0898,
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.06,
|
| 61 |
+
"learning_rate": 2.777777777777778e-05,
|
| 62 |
+
"loss": 2.148,
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.06,
|
| 67 |
+
"learning_rate": 3.08641975308642e-05,
|
| 68 |
+
"loss": 2.1234,
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.07,
|
| 73 |
+
"learning_rate": 3.395061728395062e-05,
|
| 74 |
+
"loss": 2.2654,
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.07,
|
| 79 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 80 |
+
"loss": 2.0256,
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.08,
|
| 85 |
+
"learning_rate": 4.012345679012346e-05,
|
| 86 |
+
"loss": 2.2243,
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.09,
|
| 91 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 92 |
+
"loss": 2.095,
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 4.62962962962963e-05,
|
| 98 |
+
"loss": 2.0638,
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.1,
|
| 103 |
+
"learning_rate": 4.938271604938271e-05,
|
| 104 |
+
"loss": 1.7901,
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.1,
|
| 109 |
+
"learning_rate": 4.972565157750343e-05,
|
| 110 |
+
"loss": 2.0289,
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.11,
|
| 115 |
+
"learning_rate": 4.938271604938271e-05,
|
| 116 |
+
"loss": 2.1525,
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.12,
|
| 121 |
+
"learning_rate": 4.9039780521262005e-05,
|
| 122 |
+
"loss": 1.8115,
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.12,
|
| 127 |
+
"learning_rate": 4.86968449931413e-05,
|
| 128 |
+
"loss": 2.3977,
|
| 129 |
"step": 200
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.13,
|
| 133 |
+
"learning_rate": 4.835390946502058e-05,
|
| 134 |
+
"loss": 1.9927,
|
| 135 |
"step": 210
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.14,
|
| 139 |
+
"learning_rate": 4.801097393689987e-05,
|
| 140 |
+
"loss": 1.7865,
|
| 141 |
"step": 220
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 0.14,
|
| 145 |
+
"learning_rate": 4.766803840877915e-05,
|
| 146 |
+
"loss": 2.5667,
|
| 147 |
"step": 230
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 0.15,
|
| 151 |
+
"learning_rate": 4.732510288065844e-05,
|
| 152 |
+
"loss": 2.239,
|
| 153 |
"step": 240
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 0.15,
|
| 157 |
+
"learning_rate": 4.6982167352537723e-05,
|
| 158 |
+
"loss": 1.7814,
|
| 159 |
"step": 250
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.16,
|
| 163 |
+
"learning_rate": 4.6639231824417016e-05,
|
| 164 |
+
"loss": 1.9021,
|
| 165 |
"step": 260
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 0.17,
|
| 169 |
+
"learning_rate": 4.62962962962963e-05,
|
| 170 |
+
"loss": 1.6087,
|
| 171 |
"step": 270
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.17,
|
| 175 |
+
"eval_accuracy": 0.3719806763285024,
|
| 176 |
+
"eval_loss": 1.6755967140197754,
|
| 177 |
+
"eval_runtime": 23.2696,
|
| 178 |
+
"eval_samples_per_second": 8.896,
|
| 179 |
+
"eval_steps_per_second": 8.896,
|
| 180 |
"step": 270
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 1.01,
|
| 184 |
+
"learning_rate": 4.5953360768175586e-05,
|
| 185 |
+
"loss": 1.7744,
|
| 186 |
"step": 280
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 1.01,
|
| 190 |
+
"learning_rate": 4.561042524005487e-05,
|
| 191 |
+
"loss": 1.6711,
|
| 192 |
"step": 290
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 1.02,
|
| 196 |
+
"learning_rate": 4.5267489711934157e-05,
|
| 197 |
+
"loss": 2.2113,
|
| 198 |
"step": 300
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 1.02,
|
| 202 |
+
"learning_rate": 4.492455418381344e-05,
|
| 203 |
+
"loss": 1.2746,
|
| 204 |
"step": 310
|
| 205 |
},
|
| 206 |
{
|
| 207 |
+
"epoch": 1.03,
|
| 208 |
+
"learning_rate": 4.4581618655692734e-05,
|
| 209 |
+
"loss": 1.8943,
|
| 210 |
"step": 320
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 1.04,
|
| 214 |
+
"learning_rate": 4.423868312757202e-05,
|
| 215 |
+
"loss": 2.0154,
|
| 216 |
"step": 330
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"epoch": 1.04,
|
| 220 |
+
"learning_rate": 4.3895747599451304e-05,
|
| 221 |
+
"loss": 1.4239,
|
| 222 |
"step": 340
|
| 223 |
},
|
| 224 |
{
|
| 225 |
+
"epoch": 1.05,
|
| 226 |
+
"learning_rate": 4.355281207133059e-05,
|
| 227 |
+
"loss": 1.7982,
|
| 228 |
"step": 350
|
| 229 |
},
|
| 230 |
{
|
| 231 |
+
"epoch": 1.06,
|
| 232 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 233 |
+
"loss": 1.3468,
|
| 234 |
"step": 360
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 1.06,
|
| 238 |
+
"learning_rate": 4.286694101508916e-05,
|
| 239 |
+
"loss": 1.9243,
|
| 240 |
"step": 370
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 1.07,
|
| 244 |
+
"learning_rate": 4.252400548696845e-05,
|
| 245 |
+
"loss": 1.7117,
|
| 246 |
"step": 380
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 1.07,
|
| 250 |
+
"learning_rate": 4.2181069958847744e-05,
|
| 251 |
+
"loss": 1.9821,
|
| 252 |
"step": 390
|
| 253 |
},
|
| 254 |
{
|
| 255 |
+
"epoch": 1.08,
|
| 256 |
+
"learning_rate": 4.183813443072703e-05,
|
| 257 |
+
"loss": 1.3613,
|
| 258 |
"step": 400
|
| 259 |
},
|
| 260 |
{
|
| 261 |
+
"epoch": 1.09,
|
| 262 |
+
"learning_rate": 4.1495198902606315e-05,
|
| 263 |
+
"loss": 1.3157,
|
| 264 |
"step": 410
|
| 265 |
},
|
| 266 |
{
|
| 267 |
+
"epoch": 1.09,
|
| 268 |
+
"learning_rate": 4.11522633744856e-05,
|
| 269 |
+
"loss": 2.9511,
|
| 270 |
"step": 420
|
| 271 |
},
|
| 272 |
{
|
| 273 |
+
"epoch": 1.1,
|
| 274 |
+
"learning_rate": 4.0809327846364885e-05,
|
| 275 |
+
"loss": 2.1262,
|
| 276 |
"step": 430
|
| 277 |
},
|
| 278 |
{
|
| 279 |
+
"epoch": 1.1,
|
| 280 |
+
"learning_rate": 4.046639231824417e-05,
|
| 281 |
+
"loss": 1.7427,
|
| 282 |
"step": 440
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 1.11,
|
| 286 |
+
"learning_rate": 4.012345679012346e-05,
|
| 287 |
+
"loss": 1.4527,
|
| 288 |
"step": 450
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 1.12,
|
| 292 |
+
"learning_rate": 3.978052126200275e-05,
|
| 293 |
+
"loss": 1.4661,
|
| 294 |
"step": 460
|
| 295 |
},
|
| 296 |
{
|
| 297 |
+
"epoch": 1.12,
|
| 298 |
+
"learning_rate": 3.943758573388203e-05,
|
| 299 |
+
"loss": 1.7663,
|
| 300 |
"step": 470
|
| 301 |
},
|
| 302 |
{
|
| 303 |
+
"epoch": 1.13,
|
| 304 |
+
"learning_rate": 3.909465020576132e-05,
|
| 305 |
+
"loss": 1.5297,
|
| 306 |
"step": 480
|
| 307 |
},
|
| 308 |
{
|
| 309 |
+
"epoch": 1.14,
|
| 310 |
+
"learning_rate": 3.8751714677640603e-05,
|
| 311 |
+
"loss": 1.3894,
|
| 312 |
"step": 490
|
| 313 |
},
|
| 314 |
{
|
| 315 |
+
"epoch": 1.14,
|
| 316 |
+
"learning_rate": 3.840877914951989e-05,
|
| 317 |
+
"loss": 1.3816,
|
| 318 |
"step": 500
|
| 319 |
},
|
| 320 |
{
|
| 321 |
+
"epoch": 1.15,
|
| 322 |
+
"learning_rate": 3.806584362139918e-05,
|
| 323 |
+
"loss": 1.2794,
|
| 324 |
"step": 510
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 1.15,
|
| 328 |
+
"learning_rate": 3.7722908093278466e-05,
|
| 329 |
+
"loss": 1.616,
|
| 330 |
"step": 520
|
| 331 |
},
|
| 332 |
{
|
| 333 |
+
"epoch": 1.16,
|
| 334 |
+
"learning_rate": 3.737997256515775e-05,
|
| 335 |
+
"loss": 1.9916,
|
| 336 |
"step": 530
|
| 337 |
},
|
| 338 |
{
|
| 339 |
+
"epoch": 1.17,
|
| 340 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 341 |
+
"loss": 1.1954,
|
| 342 |
"step": 540
|
| 343 |
},
|
| 344 |
{
|
| 345 |
+
"epoch": 1.17,
|
| 346 |
+
"eval_accuracy": 0.5990338164251208,
|
| 347 |
+
"eval_loss": 1.100610375404358,
|
| 348 |
+
"eval_runtime": 23.1997,
|
| 349 |
+
"eval_samples_per_second": 8.923,
|
| 350 |
+
"eval_steps_per_second": 8.923,
|
| 351 |
"step": 540
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 2.01,
|
| 355 |
+
"learning_rate": 3.669410150891632e-05,
|
| 356 |
+
"loss": 1.2202,
|
| 357 |
"step": 550
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 2.01,
|
| 361 |
+
"learning_rate": 3.635116598079561e-05,
|
| 362 |
+
"loss": 0.502,
|
| 363 |
"step": 560
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 2.02,
|
| 367 |
+
"learning_rate": 3.60082304526749e-05,
|
| 368 |
+
"loss": 1.3205,
|
| 369 |
"step": 570
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 2.02,
|
| 373 |
+
"learning_rate": 3.566529492455419e-05,
|
| 374 |
+
"loss": 0.7886,
|
| 375 |
"step": 580
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 2.03,
|
| 379 |
+
"learning_rate": 3.5322359396433476e-05,
|
| 380 |
+
"loss": 1.1766,
|
| 381 |
"step": 590
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 2.04,
|
| 385 |
+
"learning_rate": 3.497942386831276e-05,
|
| 386 |
+
"loss": 0.7688,
|
| 387 |
"step": 600
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 2.04,
|
| 391 |
+
"learning_rate": 3.463648834019205e-05,
|
| 392 |
+
"loss": 1.3003,
|
| 393 |
"step": 610
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"epoch": 2.05,
|
| 397 |
+
"learning_rate": 3.429355281207133e-05,
|
| 398 |
+
"loss": 0.7499,
|
| 399 |
"step": 620
|
| 400 |
},
|
| 401 |
{
|
| 402 |
+
"epoch": 2.06,
|
| 403 |
+
"learning_rate": 3.395061728395062e-05,
|
| 404 |
+
"loss": 0.4675,
|
| 405 |
"step": 630
|
| 406 |
},
|
| 407 |
{
|
| 408 |
+
"epoch": 2.06,
|
| 409 |
+
"learning_rate": 3.360768175582991e-05,
|
| 410 |
+
"loss": 1.2491,
|
| 411 |
"step": 640
|
| 412 |
},
|
| 413 |
{
|
| 414 |
+
"epoch": 2.07,
|
| 415 |
+
"learning_rate": 3.3264746227709195e-05,
|
| 416 |
+
"loss": 1.1091,
|
| 417 |
"step": 650
|
| 418 |
},
|
| 419 |
{
|
| 420 |
+
"epoch": 2.07,
|
| 421 |
+
"learning_rate": 3.292181069958848e-05,
|
| 422 |
+
"loss": 0.4996,
|
| 423 |
"step": 660
|
| 424 |
},
|
| 425 |
{
|
| 426 |
+
"epoch": 2.08,
|
| 427 |
+
"learning_rate": 3.2578875171467765e-05,
|
| 428 |
+
"loss": 1.112,
|
| 429 |
"step": 670
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 2.09,
|
| 433 |
+
"learning_rate": 3.223593964334705e-05,
|
| 434 |
+
"loss": 0.6491,
|
| 435 |
"step": 680
|
| 436 |
},
|
| 437 |
{
|
| 438 |
+
"epoch": 2.09,
|
| 439 |
+
"learning_rate": 3.1893004115226336e-05,
|
| 440 |
+
"loss": 0.5949,
|
| 441 |
"step": 690
|
| 442 |
},
|
| 443 |
{
|
| 444 |
+
"epoch": 2.1,
|
| 445 |
+
"learning_rate": 3.155006858710563e-05,
|
| 446 |
+
"loss": 1.13,
|
| 447 |
"step": 700
|
| 448 |
},
|
| 449 |
{
|
| 450 |
+
"epoch": 2.1,
|
| 451 |
+
"learning_rate": 3.120713305898491e-05,
|
| 452 |
+
"loss": 0.2593,
|
| 453 |
"step": 710
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 2.11,
|
| 457 |
+
"learning_rate": 3.08641975308642e-05,
|
| 458 |
+
"loss": 0.157,
|
| 459 |
"step": 720
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 2.12,
|
| 463 |
+
"learning_rate": 3.0521262002743484e-05,
|
| 464 |
+
"loss": 0.6718,
|
| 465 |
"step": 730
|
| 466 |
},
|
| 467 |
{
|
| 468 |
+
"epoch": 2.12,
|
| 469 |
+
"learning_rate": 3.017832647462277e-05,
|
| 470 |
+
"loss": 1.2776,
|
| 471 |
"step": 740
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 2.13,
|
| 475 |
+
"learning_rate": 2.9835390946502057e-05,
|
| 476 |
+
"loss": 0.8115,
|
| 477 |
"step": 750
|
| 478 |
},
|
| 479 |
{
|
| 480 |
+
"epoch": 2.14,
|
| 481 |
+
"learning_rate": 2.949245541838135e-05,
|
| 482 |
+
"loss": 0.5362,
|
| 483 |
"step": 760
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 2.14,
|
| 487 |
+
"learning_rate": 2.9149519890260635e-05,
|
| 488 |
+
"loss": 0.5839,
|
| 489 |
"step": 770
|
| 490 |
},
|
| 491 |
{
|
| 492 |
+
"epoch": 2.15,
|
| 493 |
+
"learning_rate": 2.880658436213992e-05,
|
| 494 |
+
"loss": 1.6678,
|
| 495 |
"step": 780
|
| 496 |
},
|
| 497 |
{
|
| 498 |
+
"epoch": 2.15,
|
| 499 |
+
"learning_rate": 2.846364883401921e-05,
|
| 500 |
+
"loss": 0.2518,
|
| 501 |
"step": 790
|
| 502 |
},
|
| 503 |
{
|
| 504 |
+
"epoch": 2.16,
|
| 505 |
+
"learning_rate": 2.8120713305898494e-05,
|
| 506 |
+
"loss": 0.805,
|
| 507 |
"step": 800
|
| 508 |
},
|
| 509 |
{
|
| 510 |
+
"epoch": 2.17,
|
| 511 |
+
"learning_rate": 2.777777777777778e-05,
|
| 512 |
+
"loss": 0.9847,
|
| 513 |
"step": 810
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 2.17,
|
| 517 |
+
"eval_accuracy": 0.6714975845410628,
|
| 518 |
+
"eval_loss": 0.9659531712532043,
|
| 519 |
+
"eval_runtime": 23.2172,
|
| 520 |
+
"eval_samples_per_second": 8.916,
|
| 521 |
+
"eval_steps_per_second": 8.916,
|
| 522 |
"step": 810
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 3.01,
|
| 526 |
+
"learning_rate": 2.7434842249657068e-05,
|
| 527 |
+
"loss": 0.5909,
|
| 528 |
"step": 820
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 3.01,
|
| 532 |
+
"learning_rate": 2.7091906721536353e-05,
|
| 533 |
+
"loss": 0.4683,
|
| 534 |
"step": 830
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 3.02,
|
| 538 |
+
"learning_rate": 2.6748971193415638e-05,
|
| 539 |
+
"loss": 0.767,
|
| 540 |
"step": 840
|
| 541 |
},
|
| 542 |
{
|
| 543 |
+
"epoch": 3.02,
|
| 544 |
+
"learning_rate": 2.6406035665294927e-05,
|
| 545 |
+
"loss": 0.8964,
|
| 546 |
"step": 850
|
| 547 |
},
|
| 548 |
{
|
| 549 |
+
"epoch": 3.03,
|
| 550 |
+
"learning_rate": 2.6063100137174212e-05,
|
| 551 |
+
"loss": 0.1575,
|
| 552 |
"step": 860
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 3.04,
|
| 556 |
+
"learning_rate": 2.5720164609053497e-05,
|
| 557 |
+
"loss": 0.4401,
|
| 558 |
"step": 870
|
| 559 |
},
|
| 560 |
{
|
| 561 |
+
"epoch": 3.04,
|
| 562 |
+
"learning_rate": 2.5377229080932786e-05,
|
| 563 |
+
"loss": 0.8977,
|
| 564 |
"step": 880
|
| 565 |
},
|
| 566 |
{
|
| 567 |
+
"epoch": 3.05,
|
| 568 |
+
"learning_rate": 2.503429355281207e-05,
|
| 569 |
+
"loss": 0.9708,
|
| 570 |
"step": 890
|
| 571 |
},
|
| 572 |
{
|
| 573 |
+
"epoch": 3.06,
|
| 574 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 575 |
+
"loss": 0.2658,
|
| 576 |
"step": 900
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 3.06,
|
| 580 |
+
"learning_rate": 2.434842249657065e-05,
|
| 581 |
+
"loss": 0.052,
|
| 582 |
"step": 910
|
| 583 |
},
|
| 584 |
{
|
| 585 |
+
"epoch": 3.07,
|
| 586 |
+
"learning_rate": 2.4005486968449934e-05,
|
| 587 |
+
"loss": 0.0205,
|
| 588 |
"step": 920
|
| 589 |
},
|
| 590 |
{
|
| 591 |
+
"epoch": 3.07,
|
| 592 |
+
"learning_rate": 2.366255144032922e-05,
|
| 593 |
+
"loss": 0.7582,
|
| 594 |
"step": 930
|
| 595 |
},
|
| 596 |
{
|
| 597 |
+
"epoch": 3.08,
|
| 598 |
+
"learning_rate": 2.3319615912208508e-05,
|
| 599 |
+
"loss": 0.0451,
|
| 600 |
"step": 940
|
| 601 |
},
|
| 602 |
{
|
| 603 |
+
"epoch": 3.09,
|
| 604 |
+
"learning_rate": 2.2976680384087793e-05,
|
| 605 |
+
"loss": 0.8926,
|
| 606 |
"step": 950
|
| 607 |
},
|
| 608 |
{
|
| 609 |
+
"epoch": 3.09,
|
| 610 |
+
"learning_rate": 2.2633744855967078e-05,
|
| 611 |
+
"loss": 0.6986,
|
| 612 |
"step": 960
|
| 613 |
},
|
| 614 |
{
|
| 615 |
+
"epoch": 3.1,
|
| 616 |
+
"learning_rate": 2.2290809327846367e-05,
|
| 617 |
+
"loss": 0.5859,
|
| 618 |
"step": 970
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 3.1,
|
| 622 |
+
"learning_rate": 2.1947873799725652e-05,
|
| 623 |
+
"loss": 0.3363,
|
| 624 |
"step": 980
|
| 625 |
},
|
| 626 |
{
|
| 627 |
+
"epoch": 3.11,
|
| 628 |
+
"learning_rate": 2.1604938271604937e-05,
|
| 629 |
+
"loss": 0.2691,
|
| 630 |
"step": 990
|
| 631 |
},
|
| 632 |
{
|
| 633 |
+
"epoch": 3.12,
|
| 634 |
+
"learning_rate": 2.1262002743484226e-05,
|
| 635 |
+
"loss": 0.495,
|
| 636 |
"step": 1000
|
| 637 |
},
|
| 638 |
{
|
| 639 |
+
"epoch": 3.12,
|
| 640 |
+
"learning_rate": 2.0919067215363515e-05,
|
| 641 |
+
"loss": 0.6676,
|
| 642 |
"step": 1010
|
| 643 |
},
|
| 644 |
{
|
| 645 |
+
"epoch": 3.13,
|
| 646 |
+
"learning_rate": 2.05761316872428e-05,
|
| 647 |
+
"loss": 1.4811,
|
| 648 |
"step": 1020
|
| 649 |
},
|
| 650 |
{
|
| 651 |
+
"epoch": 3.14,
|
| 652 |
+
"learning_rate": 2.0233196159122085e-05,
|
| 653 |
+
"loss": 0.564,
|
| 654 |
"step": 1030
|
| 655 |
},
|
| 656 |
{
|
| 657 |
+
"epoch": 3.14,
|
| 658 |
+
"learning_rate": 1.9890260631001374e-05,
|
| 659 |
+
"loss": 0.6851,
|
| 660 |
"step": 1040
|
| 661 |
},
|
| 662 |
{
|
| 663 |
+
"epoch": 3.15,
|
| 664 |
+
"learning_rate": 1.954732510288066e-05,
|
| 665 |
+
"loss": 0.883,
|
| 666 |
"step": 1050
|
| 667 |
},
|
| 668 |
{
|
| 669 |
+
"epoch": 3.15,
|
| 670 |
+
"learning_rate": 1.9204389574759944e-05,
|
| 671 |
+
"loss": 0.7177,
|
| 672 |
"step": 1060
|
| 673 |
},
|
| 674 |
{
|
| 675 |
+
"epoch": 3.16,
|
| 676 |
+
"learning_rate": 1.8861454046639233e-05,
|
| 677 |
+
"loss": 0.0267,
|
| 678 |
"step": 1070
|
| 679 |
},
|
| 680 |
{
|
| 681 |
+
"epoch": 3.17,
|
| 682 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 683 |
+
"loss": 0.0737,
|
| 684 |
"step": 1080
|
| 685 |
},
|
| 686 |
{
|
| 687 |
+
"epoch": 3.17,
|
| 688 |
+
"eval_accuracy": 0.8309178743961353,
|
| 689 |
+
"eval_loss": 0.6721560955047607,
|
| 690 |
+
"eval_runtime": 22.244,
|
| 691 |
+
"eval_samples_per_second": 9.306,
|
| 692 |
+
"eval_steps_per_second": 9.306,
|
| 693 |
"step": 1080
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 4.01,
|
| 697 |
+
"learning_rate": 1.8175582990397804e-05,
|
| 698 |
+
"loss": 0.0189,
|
| 699 |
"step": 1090
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 4.01,
|
| 703 |
+
"learning_rate": 1.7832647462277096e-05,
|
| 704 |
+
"loss": 0.9507,
|
| 705 |
"step": 1100
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 4.02,
|
| 709 |
+
"learning_rate": 1.748971193415638e-05,
|
| 710 |
+
"loss": 0.0717,
|
| 711 |
"step": 1110
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 4.02,
|
| 715 |
+
"learning_rate": 1.7146776406035666e-05,
|
| 716 |
+
"loss": 0.2791,
|
| 717 |
"step": 1120
|
| 718 |
},
|
| 719 |
{
|
| 720 |
+
"epoch": 4.03,
|
| 721 |
+
"learning_rate": 1.6803840877914955e-05,
|
| 722 |
+
"loss": 0.2997,
|
| 723 |
"step": 1130
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 4.04,
|
| 727 |
+
"learning_rate": 1.646090534979424e-05,
|
| 728 |
+
"loss": 0.1088,
|
| 729 |
"step": 1140
|
| 730 |
},
|
| 731 |
{
|
| 732 |
+
"epoch": 4.04,
|
| 733 |
+
"learning_rate": 1.6117969821673525e-05,
|
| 734 |
+
"loss": 0.8001,
|
| 735 |
"step": 1150
|
| 736 |
},
|
| 737 |
{
|
| 738 |
+
"epoch": 4.05,
|
| 739 |
+
"learning_rate": 1.5775034293552814e-05,
|
| 740 |
+
"loss": 0.2641,
|
| 741 |
"step": 1160
|
| 742 |
},
|
| 743 |
{
|
| 744 |
+
"epoch": 4.06,
|
| 745 |
+
"learning_rate": 1.54320987654321e-05,
|
| 746 |
+
"loss": 0.0067,
|
| 747 |
"step": 1170
|
| 748 |
},
|
| 749 |
{
|
| 750 |
+
"epoch": 4.06,
|
| 751 |
+
"learning_rate": 1.5089163237311384e-05,
|
| 752 |
+
"loss": 0.0054,
|
| 753 |
"step": 1180
|
| 754 |
},
|
| 755 |
{
|
| 756 |
+
"epoch": 4.07,
|
| 757 |
+
"learning_rate": 1.4746227709190675e-05,
|
| 758 |
+
"loss": 0.7073,
|
| 759 |
"step": 1190
|
| 760 |
},
|
| 761 |
{
|
| 762 |
+
"epoch": 4.07,
|
| 763 |
+
"learning_rate": 1.440329218106996e-05,
|
| 764 |
+
"loss": 0.2777,
|
| 765 |
"step": 1200
|
| 766 |
},
|
| 767 |
{
|
| 768 |
+
"epoch": 4.08,
|
| 769 |
+
"learning_rate": 1.4060356652949247e-05,
|
| 770 |
+
"loss": 0.014,
|
| 771 |
"step": 1210
|
| 772 |
},
|
| 773 |
{
|
| 774 |
+
"epoch": 4.09,
|
| 775 |
+
"learning_rate": 1.3717421124828534e-05,
|
| 776 |
+
"loss": 0.5616,
|
| 777 |
"step": 1220
|
| 778 |
},
|
| 779 |
{
|
| 780 |
+
"epoch": 4.09,
|
| 781 |
+
"learning_rate": 1.3374485596707819e-05,
|
| 782 |
+
"loss": 0.5849,
|
| 783 |
"step": 1230
|
| 784 |
},
|
| 785 |
{
|
| 786 |
+
"epoch": 4.1,
|
| 787 |
+
"learning_rate": 1.3031550068587106e-05,
|
| 788 |
+
"loss": 0.4199,
|
| 789 |
"step": 1240
|
| 790 |
},
|
| 791 |
{
|
| 792 |
+
"epoch": 4.1,
|
| 793 |
+
"learning_rate": 1.2688614540466393e-05,
|
| 794 |
+
"loss": 1.4511,
|
| 795 |
"step": 1250
|
| 796 |
},
|
| 797 |
{
|
| 798 |
+
"epoch": 4.11,
|
| 799 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 800 |
+
"loss": 0.0497,
|
| 801 |
"step": 1260
|
| 802 |
},
|
| 803 |
{
|
| 804 |
+
"epoch": 4.12,
|
| 805 |
+
"learning_rate": 1.2002743484224967e-05,
|
| 806 |
+
"loss": 0.0345,
|
| 807 |
"step": 1270
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 4.12,
|
| 811 |
+
"learning_rate": 1.1659807956104254e-05,
|
| 812 |
+
"loss": 0.025,
|
| 813 |
"step": 1280
|
| 814 |
},
|
| 815 |
{
|
| 816 |
+
"epoch": 4.13,
|
| 817 |
+
"learning_rate": 1.1316872427983539e-05,
|
| 818 |
+
"loss": 0.1749,
|
| 819 |
"step": 1290
|
| 820 |
},
|
| 821 |
{
|
| 822 |
+
"epoch": 4.14,
|
| 823 |
+
"learning_rate": 1.0973936899862826e-05,
|
| 824 |
+
"loss": 0.737,
|
| 825 |
"step": 1300
|
| 826 |
},
|
| 827 |
{
|
| 828 |
+
"epoch": 4.14,
|
| 829 |
+
"learning_rate": 1.0631001371742113e-05,
|
| 830 |
+
"loss": 0.0137,
|
| 831 |
"step": 1310
|
| 832 |
},
|
| 833 |
{
|
| 834 |
+
"epoch": 4.15,
|
| 835 |
+
"learning_rate": 1.02880658436214e-05,
|
| 836 |
+
"loss": 0.2798,
|
| 837 |
"step": 1320
|
| 838 |
},
|
| 839 |
{
|
| 840 |
+
"epoch": 4.15,
|
| 841 |
+
"learning_rate": 9.945130315500687e-06,
|
| 842 |
+
"loss": 0.6646,
|
| 843 |
"step": 1330
|
| 844 |
},
|
| 845 |
{
|
| 846 |
+
"epoch": 4.16,
|
| 847 |
+
"learning_rate": 9.602194787379972e-06,
|
| 848 |
+
"loss": 0.4453,
|
| 849 |
"step": 1340
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 4.17,
|
| 853 |
+
"learning_rate": 9.259259259259259e-06,
|
| 854 |
+
"loss": 0.0054,
|
| 855 |
"step": 1350
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 4.17,
|
| 859 |
+
"eval_accuracy": 0.8502415458937198,
|
| 860 |
+
"eval_loss": 0.528615415096283,
|
| 861 |
+
"eval_runtime": 23.4632,
|
| 862 |
+
"eval_samples_per_second": 8.822,
|
| 863 |
+
"eval_steps_per_second": 8.822,
|
| 864 |
"step": 1350
|
| 865 |
},
|
| 866 |
{
|
| 867 |
+
"epoch": 5.01,
|
| 868 |
+
"learning_rate": 8.916323731138548e-06,
|
| 869 |
+
"loss": 0.4661,
|
| 870 |
+
"step": 1360
|
|
|
|
|
|
|
|
|
|
| 871 |
},
|
| 872 |
{
|
| 873 |
+
"epoch": 5.01,
|
| 874 |
+
"learning_rate": 8.573388203017833e-06,
|
| 875 |
+
"loss": 0.004,
|
| 876 |
+
"step": 1370
|
|
|
|
|
|
|
|
|
|
| 877 |
},
|
| 878 |
{
|
| 879 |
+
"epoch": 5.02,
|
| 880 |
+
"learning_rate": 8.23045267489712e-06,
|
| 881 |
+
"loss": 0.0031,
|
| 882 |
+
"step": 1380
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 5.02,
|
| 886 |
+
"learning_rate": 7.887517146776407e-06,
|
| 887 |
+
"loss": 0.5041,
|
| 888 |
+
"step": 1390
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 5.03,
|
| 892 |
+
"learning_rate": 7.544581618655692e-06,
|
| 893 |
+
"loss": 0.1095,
|
| 894 |
+
"step": 1400
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 5.04,
|
| 898 |
+
"learning_rate": 7.20164609053498e-06,
|
| 899 |
+
"loss": 0.0438,
|
| 900 |
+
"step": 1410
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 5.04,
|
| 904 |
+
"learning_rate": 6.858710562414267e-06,
|
| 905 |
+
"loss": 0.4582,
|
| 906 |
+
"step": 1420
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 5.05,
|
| 910 |
+
"learning_rate": 6.515775034293553e-06,
|
| 911 |
+
"loss": 0.0087,
|
| 912 |
+
"step": 1430
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 5.06,
|
| 916 |
+
"learning_rate": 6.172839506172839e-06,
|
| 917 |
+
"loss": 0.003,
|
| 918 |
+
"step": 1440
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 5.06,
|
| 922 |
+
"learning_rate": 5.829903978052127e-06,
|
| 923 |
+
"loss": 0.0177,
|
| 924 |
+
"step": 1450
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 5.07,
|
| 928 |
+
"learning_rate": 5.486968449931413e-06,
|
| 929 |
+
"loss": 0.5798,
|
| 930 |
+
"step": 1460
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 5.07,
|
| 934 |
+
"learning_rate": 5.1440329218107e-06,
|
| 935 |
+
"loss": 0.0867,
|
| 936 |
+
"step": 1470
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 5.08,
|
| 940 |
+
"learning_rate": 4.801097393689986e-06,
|
| 941 |
+
"loss": 0.66,
|
| 942 |
+
"step": 1480
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 5.09,
|
| 946 |
+
"learning_rate": 4.458161865569274e-06,
|
| 947 |
+
"loss": 0.003,
|
| 948 |
+
"step": 1490
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 5.09,
|
| 952 |
+
"learning_rate": 4.11522633744856e-06,
|
| 953 |
+
"loss": 0.4618,
|
| 954 |
+
"step": 1500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 5.1,
|
| 958 |
+
"learning_rate": 3.772290809327846e-06,
|
| 959 |
+
"loss": 0.2452,
|
| 960 |
+
"step": 1510
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 5.1,
|
| 964 |
+
"learning_rate": 3.4293552812071335e-06,
|
| 965 |
+
"loss": 0.0234,
|
| 966 |
+
"step": 1520
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 5.11,
|
| 970 |
+
"learning_rate": 3.0864197530864196e-06,
|
| 971 |
+
"loss": 0.007,
|
| 972 |
+
"step": 1530
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 5.12,
|
| 976 |
+
"learning_rate": 2.7434842249657065e-06,
|
| 977 |
+
"loss": 0.0066,
|
| 978 |
+
"step": 1540
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 5.12,
|
| 982 |
+
"learning_rate": 2.400548696844993e-06,
|
| 983 |
+
"loss": 0.6313,
|
| 984 |
+
"step": 1550
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 5.13,
|
| 988 |
+
"learning_rate": 2.05761316872428e-06,
|
| 989 |
+
"loss": 0.0198,
|
| 990 |
+
"step": 1560
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 5.14,
|
| 994 |
+
"learning_rate": 1.7146776406035667e-06,
|
| 995 |
+
"loss": 0.5825,
|
| 996 |
+
"step": 1570
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 5.14,
|
| 1000 |
+
"learning_rate": 1.3717421124828533e-06,
|
| 1001 |
+
"loss": 0.6457,
|
| 1002 |
+
"step": 1580
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 5.15,
|
| 1006 |
+
"learning_rate": 1.02880658436214e-06,
|
| 1007 |
+
"loss": 0.0335,
|
| 1008 |
+
"step": 1590
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 5.15,
|
| 1012 |
+
"learning_rate": 6.858710562414266e-07,
|
| 1013 |
+
"loss": 0.0737,
|
| 1014 |
+
"step": 1600
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 5.16,
|
| 1018 |
+
"learning_rate": 3.429355281207133e-07,
|
| 1019 |
+
"loss": 0.7907,
|
| 1020 |
+
"step": 1610
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 5.17,
|
| 1024 |
+
"learning_rate": 0.0,
|
| 1025 |
+
"loss": 0.1586,
|
| 1026 |
+
"step": 1620
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 5.17,
|
| 1030 |
+
"eval_accuracy": 0.8695652173913043,
|
| 1031 |
+
"eval_loss": 0.5369048118591309,
|
| 1032 |
+
"eval_runtime": 23.2611,
|
| 1033 |
+
"eval_samples_per_second": 8.899,
|
| 1034 |
+
"eval_steps_per_second": 8.899,
|
| 1035 |
+
"step": 1620
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 5.17,
|
| 1039 |
+
"step": 1620,
|
| 1040 |
+
"total_flos": 2.0187506515909018e+18,
|
| 1041 |
+
"train_loss": 0.9597556127292782,
|
| 1042 |
+
"train_runtime": 491.4225,
|
| 1043 |
+
"train_samples_per_second": 3.297,
|
| 1044 |
+
"train_steps_per_second": 3.297
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 5.17,
|
| 1048 |
+
"eval_accuracy": 0.8601036269430051,
|
| 1049 |
+
"eval_loss": 0.552123486995697,
|
| 1050 |
+
"eval_runtime": 21.5343,
|
| 1051 |
+
"eval_samples_per_second": 8.962,
|
| 1052 |
+
"eval_steps_per_second": 8.962,
|
| 1053 |
+
"step": 1620
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 5.17,
|
| 1057 |
+
"eval_accuracy": 0.8601036269430051,
|
| 1058 |
+
"eval_loss": 0.552123486995697,
|
| 1059 |
+
"eval_runtime": 21.6981,
|
| 1060 |
+
"eval_samples_per_second": 8.895,
|
| 1061 |
+
"eval_steps_per_second": 8.895,
|
| 1062 |
+
"step": 1620
|
| 1063 |
}
|
| 1064 |
],
|
| 1065 |
"logging_steps": 10,
|
| 1066 |
+
"max_steps": 1620,
|
| 1067 |
"num_train_epochs": 9223372036854775807,
|
| 1068 |
"save_steps": 500,
|
| 1069 |
+
"total_flos": 2.0187506515909018e+18,
|
| 1070 |
"trial_name": null,
|
| 1071 |
"trial_params": null
|
| 1072 |
}
|