Training in progress, step 250, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 150486964
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5744af8f22d56944d2d945034e5a025b6de0020efd45cc44c9b8cb27e1e94f71
|
| 3 |
size 150486964
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50c8f9662444a91e91f01d69a445b49517e278e5e03e01795aa31274466481e0
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d90c730646140ec36d7749c40daa51b09c4e3a0b620d5c95eeda7764b46e3d79
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 125,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -310,6 +310,308 @@
|
|
| 310 |
"eval_samples_per_second": 45.33,
|
| 311 |
"eval_steps_per_second": 22.666,
|
| 312 |
"step": 125
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 313 |
}
|
| 314 |
],
|
| 315 |
"logging_steps": 3,
|
|
@@ -329,7 +631,7 @@
|
|
| 329 |
"attributes": {}
|
| 330 |
}
|
| 331 |
},
|
| 332 |
-
"total_flos":
|
| 333 |
"train_batch_size": 2,
|
| 334 |
"trial_name": null,
|
| 335 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.00808142847329694,
|
| 5 |
"eval_steps": 125,
|
| 6 |
+
"global_step": 250,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 310 |
"eval_samples_per_second": 45.33,
|
| 311 |
"eval_steps_per_second": 22.666,
|
| 312 |
"step": 125
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.004073039950541658,
|
| 316 |
+
"grad_norm": NaN,
|
| 317 |
+
"learning_rate": 8.679762062923175e-05,
|
| 318 |
+
"loss": 0.0,
|
| 319 |
+
"step": 126
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.004170017092221221,
|
| 323 |
+
"grad_norm": NaN,
|
| 324 |
+
"learning_rate": 8.613974319136958e-05,
|
| 325 |
+
"loss": 0.0,
|
| 326 |
+
"step": 129
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.004266994233900785,
|
| 330 |
+
"grad_norm": NaN,
|
| 331 |
+
"learning_rate": 8.54684960502629e-05,
|
| 332 |
+
"loss": 0.0,
|
| 333 |
+
"step": 132
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.0043639713755803475,
|
| 337 |
+
"grad_norm": NaN,
|
| 338 |
+
"learning_rate": 8.478412753017433e-05,
|
| 339 |
+
"loss": 0.0,
|
| 340 |
+
"step": 135
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.004460948517259911,
|
| 344 |
+
"grad_norm": NaN,
|
| 345 |
+
"learning_rate": 8.408689080954998e-05,
|
| 346 |
+
"loss": 0.0,
|
| 347 |
+
"step": 138
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.004557925658939474,
|
| 351 |
+
"grad_norm": NaN,
|
| 352 |
+
"learning_rate": 8.33770438273574e-05,
|
| 353 |
+
"loss": 0.0,
|
| 354 |
+
"step": 141
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.004654902800619037,
|
| 358 |
+
"grad_norm": NaN,
|
| 359 |
+
"learning_rate": 8.265484918766243e-05,
|
| 360 |
+
"loss": 0.0,
|
| 361 |
+
"step": 144
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.004751879942298601,
|
| 365 |
+
"grad_norm": NaN,
|
| 366 |
+
"learning_rate": 8.192057406248028e-05,
|
| 367 |
+
"loss": 0.0,
|
| 368 |
+
"step": 147
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.004848857083978164,
|
| 372 |
+
"grad_norm": NaN,
|
| 373 |
+
"learning_rate": 8.117449009293668e-05,
|
| 374 |
+
"loss": 0.0,
|
| 375 |
+
"step": 150
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.004945834225657727,
|
| 379 |
+
"grad_norm": NaN,
|
| 380 |
+
"learning_rate": 8.041687328877567e-05,
|
| 381 |
+
"loss": 0.0,
|
| 382 |
+
"step": 153
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.00504281136733729,
|
| 386 |
+
"grad_norm": NaN,
|
| 387 |
+
"learning_rate": 7.964800392625129e-05,
|
| 388 |
+
"loss": 0.0,
|
| 389 |
+
"step": 156
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.005139788509016854,
|
| 393 |
+
"grad_norm": NaN,
|
| 394 |
+
"learning_rate": 7.886816644444098e-05,
|
| 395 |
+
"loss": 0.0,
|
| 396 |
+
"step": 159
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.005236765650696417,
|
| 400 |
+
"grad_norm": NaN,
|
| 401 |
+
"learning_rate": 7.807764934001874e-05,
|
| 402 |
+
"loss": 0.0,
|
| 403 |
+
"step": 162
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.005333742792375981,
|
| 407 |
+
"grad_norm": NaN,
|
| 408 |
+
"learning_rate": 7.727674506052743e-05,
|
| 409 |
+
"loss": 0.0,
|
| 410 |
+
"step": 165
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.0054307199340555435,
|
| 414 |
+
"grad_norm": NaN,
|
| 415 |
+
"learning_rate": 7.646574989618938e-05,
|
| 416 |
+
"loss": 0.0,
|
| 417 |
+
"step": 168
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.005527697075735107,
|
| 421 |
+
"grad_norm": NaN,
|
| 422 |
+
"learning_rate": 7.564496387029532e-05,
|
| 423 |
+
"loss": 0.0,
|
| 424 |
+
"step": 171
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.00562467421741467,
|
| 428 |
+
"grad_norm": NaN,
|
| 429 |
+
"learning_rate": 7.481469062821252e-05,
|
| 430 |
+
"loss": 0.0,
|
| 431 |
+
"step": 174
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.005721651359094234,
|
| 435 |
+
"grad_norm": NaN,
|
| 436 |
+
"learning_rate": 7.39752373250527e-05,
|
| 437 |
+
"loss": 0.0,
|
| 438 |
+
"step": 177
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.005818628500773797,
|
| 442 |
+
"grad_norm": NaN,
|
| 443 |
+
"learning_rate": 7.312691451204178e-05,
|
| 444 |
+
"loss": 0.0,
|
| 445 |
+
"step": 180
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.0059156056424533605,
|
| 449 |
+
"grad_norm": NaN,
|
| 450 |
+
"learning_rate": 7.227003602163295e-05,
|
| 451 |
+
"loss": 0.0,
|
| 452 |
+
"step": 183
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.006012582784132923,
|
| 456 |
+
"grad_norm": NaN,
|
| 457 |
+
"learning_rate": 7.14049188514063e-05,
|
| 458 |
+
"loss": 0.0,
|
| 459 |
+
"step": 186
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.006109559925812486,
|
| 463 |
+
"grad_norm": NaN,
|
| 464 |
+
"learning_rate": 7.05318830467969e-05,
|
| 465 |
+
"loss": 0.0,
|
| 466 |
+
"step": 189
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.00620653706749205,
|
| 470 |
+
"grad_norm": NaN,
|
| 471 |
+
"learning_rate": 6.965125158269619e-05,
|
| 472 |
+
"loss": 0.0,
|
| 473 |
+
"step": 192
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.006303514209171613,
|
| 477 |
+
"grad_norm": NaN,
|
| 478 |
+
"learning_rate": 6.876335024396872e-05,
|
| 479 |
+
"loss": 0.0,
|
| 480 |
+
"step": 195
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.006400491350851177,
|
| 484 |
+
"grad_norm": NaN,
|
| 485 |
+
"learning_rate": 6.786850750493006e-05,
|
| 486 |
+
"loss": 0.0,
|
| 487 |
+
"step": 198
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.0064974684925307395,
|
| 491 |
+
"grad_norm": NaN,
|
| 492 |
+
"learning_rate": 6.696705440782938e-05,
|
| 493 |
+
"loss": 0.0,
|
| 494 |
+
"step": 201
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.006594445634210303,
|
| 498 |
+
"grad_norm": NaN,
|
| 499 |
+
"learning_rate": 6.605932444038229e-05,
|
| 500 |
+
"loss": 0.0,
|
| 501 |
+
"step": 204
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.006691422775889866,
|
| 505 |
+
"grad_norm": NaN,
|
| 506 |
+
"learning_rate": 6.514565341239861e-05,
|
| 507 |
+
"loss": 0.0,
|
| 508 |
+
"step": 207
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.00678839991756943,
|
| 512 |
+
"grad_norm": NaN,
|
| 513 |
+
"learning_rate": 6.422637933155162e-05,
|
| 514 |
+
"loss": 0.0,
|
| 515 |
+
"step": 210
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.006885377059248993,
|
| 519 |
+
"grad_norm": NaN,
|
| 520 |
+
"learning_rate": 6.330184227833376e-05,
|
| 521 |
+
"loss": 0.0,
|
| 522 |
+
"step": 213
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.006982354200928556,
|
| 526 |
+
"grad_norm": NaN,
|
| 527 |
+
"learning_rate": 6.237238428024572e-05,
|
| 528 |
+
"loss": 0.0,
|
| 529 |
+
"step": 216
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.007079331342608119,
|
| 533 |
+
"grad_norm": NaN,
|
| 534 |
+
"learning_rate": 6.143834918526527e-05,
|
| 535 |
+
"loss": 0.0,
|
| 536 |
+
"step": 219
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.007176308484287683,
|
| 540 |
+
"grad_norm": NaN,
|
| 541 |
+
"learning_rate": 6.0500082534642464e-05,
|
| 542 |
+
"loss": 0.0,
|
| 543 |
+
"step": 222
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.007273285625967246,
|
| 547 |
+
"grad_norm": NaN,
|
| 548 |
+
"learning_rate": 5.955793143506863e-05,
|
| 549 |
+
"loss": 0.0,
|
| 550 |
+
"step": 225
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.00737026276764681,
|
| 554 |
+
"grad_norm": NaN,
|
| 555 |
+
"learning_rate": 5.861224443026595e-05,
|
| 556 |
+
"loss": 0.0,
|
| 557 |
+
"step": 228
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.0074672399093263725,
|
| 561 |
+
"grad_norm": NaN,
|
| 562 |
+
"learning_rate": 5.766337137204579e-05,
|
| 563 |
+
"loss": 0.0,
|
| 564 |
+
"step": 231
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.007564217051005935,
|
| 568 |
+
"grad_norm": NaN,
|
| 569 |
+
"learning_rate": 5.6711663290882776e-05,
|
| 570 |
+
"loss": 0.0,
|
| 571 |
+
"step": 234
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.007661194192685499,
|
| 575 |
+
"grad_norm": NaN,
|
| 576 |
+
"learning_rate": 5.575747226605298e-05,
|
| 577 |
+
"loss": 0.0,
|
| 578 |
+
"step": 237
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.007758171334365062,
|
| 582 |
+
"grad_norm": NaN,
|
| 583 |
+
"learning_rate": 5.480115129538409e-05,
|
| 584 |
+
"loss": 0.0,
|
| 585 |
+
"step": 240
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.007855148476044625,
|
| 589 |
+
"grad_norm": NaN,
|
| 590 |
+
"learning_rate": 5.384305416466584e-05,
|
| 591 |
+
"loss": 0.0,
|
| 592 |
+
"step": 243
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.007952125617724189,
|
| 596 |
+
"grad_norm": NaN,
|
| 597 |
+
"learning_rate": 5.288353531676873e-05,
|
| 598 |
+
"loss": 0.0,
|
| 599 |
+
"step": 246
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.008049102759403752,
|
| 603 |
+
"grad_norm": NaN,
|
| 604 |
+
"learning_rate": 5.192294972051992e-05,
|
| 605 |
+
"loss": 0.0,
|
| 606 |
+
"step": 249
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.00808142847329694,
|
| 610 |
+
"eval_loss": NaN,
|
| 611 |
+
"eval_runtime": 575.6933,
|
| 612 |
+
"eval_samples_per_second": 45.252,
|
| 613 |
+
"eval_steps_per_second": 22.627,
|
| 614 |
+
"step": 250
|
| 615 |
}
|
| 616 |
],
|
| 617 |
"logging_steps": 3,
|
|
|
|
| 631 |
"attributes": {}
|
| 632 |
}
|
| 633 |
},
|
| 634 |
+
"total_flos": 1.700904566784e+16,
|
| 635 |
"train_batch_size": 2,
|
| 636 |
"trial_name": null,
|
| 637 |
"trial_params": null
|