Training in progress, step 100, 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 1279641042
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3970db0bac34513cc84ff47a44aaa006b961504c46b67784d6ed39cd6d8adcf
|
| 3 |
size 1279641042
|
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 sha256:91ddfbb85a3a0df100422aa99c4f4174c82b02a911fb24764f6544c6f63ebdcf
|
| 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 sha256:03ad66011cfc1fc727a51190602a41adc332b48eeef62a5ee87c2ca9f9b90b2b
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": NaN,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -373,6 +373,364 @@
|
|
| 373 |
"eval_samples_per_second": 13.797,
|
| 374 |
"eval_steps_per_second": 3.451,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -387,7 +745,7 @@
|
|
| 387 |
"early_stopping_threshold": 0.0
|
| 388 |
},
|
| 389 |
"attributes": {
|
| 390 |
-
"early_stopping_patience_counter":
|
| 391 |
}
|
| 392 |
},
|
| 393 |
"TrainerControl": {
|
|
@@ -396,12 +754,12 @@
|
|
| 396 |
"should_evaluate": false,
|
| 397 |
"should_log": false,
|
| 398 |
"should_save": true,
|
| 399 |
-
"should_training_stop":
|
| 400 |
},
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 4,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": NaN,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.007173343854237653,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 373 |
"eval_samples_per_second": 13.797,
|
| 374 |
"eval_steps_per_second": 3.451,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.003658405365661203,
|
| 379 |
+
"grad_norm": NaN,
|
| 380 |
+
"learning_rate": 2.3816778784387097e-05,
|
| 381 |
+
"loss": 0.0,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.0037301388042035796,
|
| 386 |
+
"grad_norm": NaN,
|
| 387 |
+
"learning_rate": 2.3263454721781537e-05,
|
| 388 |
+
"loss": 0.0,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.003801872242745956,
|
| 393 |
+
"grad_norm": NaN,
|
| 394 |
+
"learning_rate": 2.2693489161088592e-05,
|
| 395 |
+
"loss": 0.0,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.0038736056812883326,
|
| 400 |
+
"grad_norm": NaN,
|
| 401 |
+
"learning_rate": 2.210802993709498e-05,
|
| 402 |
+
"loss": 0.0,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.003945339119830709,
|
| 407 |
+
"grad_norm": NaN,
|
| 408 |
+
"learning_rate": 2.1508256086763372e-05,
|
| 409 |
+
"loss": 0.0,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.004017072558373086,
|
| 414 |
+
"grad_norm": NaN,
|
| 415 |
+
"learning_rate": 2.0895375474808857e-05,
|
| 416 |
+
"loss": 0.0,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.0040888059969154626,
|
| 421 |
+
"grad_norm": NaN,
|
| 422 |
+
"learning_rate": 2.0270622361220143e-05,
|
| 423 |
+
"loss": 0.0,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.004160539435457839,
|
| 428 |
+
"grad_norm": NaN,
|
| 429 |
+
"learning_rate": 1.963525491562421e-05,
|
| 430 |
+
"loss": 0.0,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.0042322728740002155,
|
| 435 |
+
"grad_norm": NaN,
|
| 436 |
+
"learning_rate": 1.8990552683500128e-05,
|
| 437 |
+
"loss": 0.0,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.004304006312542592,
|
| 442 |
+
"grad_norm": NaN,
|
| 443 |
+
"learning_rate": 1.8337814009344716e-05,
|
| 444 |
+
"loss": 0.0,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.0043757397510849685,
|
| 449 |
+
"grad_norm": NaN,
|
| 450 |
+
"learning_rate": 1.767835342197955e-05,
|
| 451 |
+
"loss": 0.0,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.004447473189627345,
|
| 456 |
+
"grad_norm": NaN,
|
| 457 |
+
"learning_rate": 1.7013498987264832e-05,
|
| 458 |
+
"loss": 0.0,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.0045192066281697215,
|
| 463 |
+
"grad_norm": NaN,
|
| 464 |
+
"learning_rate": 1.6344589633551502e-05,
|
| 465 |
+
"loss": 0.0,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.004590940066712098,
|
| 470 |
+
"grad_norm": NaN,
|
| 471 |
+
"learning_rate": 1.5672972455257726e-05,
|
| 472 |
+
"loss": 0.0,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.0046626735052544745,
|
| 477 |
+
"grad_norm": NaN,
|
| 478 |
+
"learning_rate": 1.5e-05,
|
| 479 |
+
"loss": 0.0,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.004734406943796851,
|
| 484 |
+
"grad_norm": NaN,
|
| 485 |
+
"learning_rate": 1.4327027544742281e-05,
|
| 486 |
+
"loss": 0.0,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.0048061403823392275,
|
| 491 |
+
"grad_norm": NaN,
|
| 492 |
+
"learning_rate": 1.36554103664485e-05,
|
| 493 |
+
"loss": 0.0,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.004877873820881604,
|
| 498 |
+
"grad_norm": NaN,
|
| 499 |
+
"learning_rate": 1.2986501012735174e-05,
|
| 500 |
+
"loss": 0.0,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.0049496072594239805,
|
| 505 |
+
"grad_norm": NaN,
|
| 506 |
+
"learning_rate": 1.2321646578020452e-05,
|
| 507 |
+
"loss": 0.0,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.005021340697966357,
|
| 512 |
+
"grad_norm": NaN,
|
| 513 |
+
"learning_rate": 1.1662185990655285e-05,
|
| 514 |
+
"loss": 0.0,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.0050930741365087335,
|
| 519 |
+
"grad_norm": NaN,
|
| 520 |
+
"learning_rate": 1.1009447316499875e-05,
|
| 521 |
+
"loss": 0.0,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.0051648075750511105,
|
| 526 |
+
"grad_norm": NaN,
|
| 527 |
+
"learning_rate": 1.036474508437579e-05,
|
| 528 |
+
"loss": 0.0,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.0052365410135934865,
|
| 533 |
+
"grad_norm": NaN,
|
| 534 |
+
"learning_rate": 9.729377638779859e-06,
|
| 535 |
+
"loss": 0.0,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.0053082744521358634,
|
| 540 |
+
"grad_norm": NaN,
|
| 541 |
+
"learning_rate": 9.104624525191147e-06,
|
| 542 |
+
"loss": 0.0,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.0053800078906782395,
|
| 547 |
+
"grad_norm": NaN,
|
| 548 |
+
"learning_rate": 8.491743913236629e-06,
|
| 549 |
+
"loss": 0.0,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.0054517413292206164,
|
| 554 |
+
"grad_norm": NaN,
|
| 555 |
+
"learning_rate": 7.89197006290502e-06,
|
| 556 |
+
"loss": 0.0,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.0055234747677629925,
|
| 561 |
+
"grad_norm": NaN,
|
| 562 |
+
"learning_rate": 7.30651083891141e-06,
|
| 563 |
+
"loss": 0.0,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.0055952082063053694,
|
| 568 |
+
"grad_norm": NaN,
|
| 569 |
+
"learning_rate": 6.736545278218464e-06,
|
| 570 |
+
"loss": 0.0,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.0056669416448477455,
|
| 575 |
+
"grad_norm": NaN,
|
| 576 |
+
"learning_rate": 6.1832212156129045e-06,
|
| 577 |
+
"loss": 0.0,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.0057386750833901224,
|
| 582 |
+
"grad_norm": NaN,
|
| 583 |
+
"learning_rate": 5.647652972118998e-06,
|
| 584 |
+
"loss": 0.0,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.0058104085219324985,
|
| 589 |
+
"grad_norm": NaN,
|
| 590 |
+
"learning_rate": 5.130919110904311e-06,
|
| 591 |
+
"loss": 0.0,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.005882141960474875,
|
| 596 |
+
"grad_norm": NaN,
|
| 597 |
+
"learning_rate": 4.6340602651970304e-06,
|
| 598 |
+
"loss": 0.0,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.0059538753990172515,
|
| 603 |
+
"grad_norm": NaN,
|
| 604 |
+
"learning_rate": 4.158077042589129e-06,
|
| 605 |
+
"loss": 0.0,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.006025608837559628,
|
| 610 |
+
"grad_norm": NaN,
|
| 611 |
+
"learning_rate": 3.7039280099458373e-06,
|
| 612 |
+
"loss": 0.0,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.006097342276102005,
|
| 617 |
+
"grad_norm": NaN,
|
| 618 |
+
"learning_rate": 3.272527762979553e-06,
|
| 619 |
+
"loss": 0.0,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.006169075714644381,
|
| 624 |
+
"grad_norm": NaN,
|
| 625 |
+
"learning_rate": 2.86474508437579e-06,
|
| 626 |
+
"loss": 0.0,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.006240809153186758,
|
| 631 |
+
"grad_norm": NaN,
|
| 632 |
+
"learning_rate": 2.4814011941804603e-06,
|
| 633 |
+
"loss": 0.0,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.006312542591729134,
|
| 638 |
+
"grad_norm": NaN,
|
| 639 |
+
"learning_rate": 2.1232680959720085e-06,
|
| 640 |
+
"loss": 0.0,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.006384276030271511,
|
| 645 |
+
"grad_norm": NaN,
|
| 646 |
+
"learning_rate": 1.79106702214893e-06,
|
| 647 |
+
"loss": 0.0,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.006456009468813887,
|
| 652 |
+
"grad_norm": NaN,
|
| 653 |
+
"learning_rate": 1.4854669814637145e-06,
|
| 654 |
+
"loss": 0.0,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.006527742907356264,
|
| 659 |
+
"grad_norm": NaN,
|
| 660 |
+
"learning_rate": 1.2070834117282414e-06,
|
| 661 |
+
"loss": 0.0,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.00659947634589864,
|
| 666 |
+
"grad_norm": NaN,
|
| 667 |
+
"learning_rate": 9.56476940403942e-07,
|
| 668 |
+
"loss": 0.0,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.006671209784441017,
|
| 673 |
+
"grad_norm": NaN,
|
| 674 |
+
"learning_rate": 7.341522555726971e-07,
|
| 675 |
+
"loss": 0.0,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.006742943222983393,
|
| 680 |
+
"grad_norm": NaN,
|
| 681 |
+
"learning_rate": 5.405570895622014e-07,
|
| 682 |
+
"loss": 0.0,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.00681467666152577,
|
| 687 |
+
"grad_norm": NaN,
|
| 688 |
+
"learning_rate": 3.760813172726457e-07,
|
| 689 |
+
"loss": 0.0,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.006886410100068146,
|
| 694 |
+
"grad_norm": NaN,
|
| 695 |
+
"learning_rate": 2.41056171020555e-07,
|
| 696 |
+
"loss": 0.0,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.006958143538610523,
|
| 701 |
+
"grad_norm": NaN,
|
| 702 |
+
"learning_rate": 1.357535734809795e-07,
|
| 703 |
+
"loss": 0.0,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.007029876977152899,
|
| 708 |
+
"grad_norm": NaN,
|
| 709 |
+
"learning_rate": 6.038559007141397e-08,
|
| 710 |
+
"loss": 0.0,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.007101610415695276,
|
| 715 |
+
"grad_norm": NaN,
|
| 716 |
+
"learning_rate": 1.510400188028116e-08,
|
| 717 |
+
"loss": 0.0,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.007173343854237653,
|
| 722 |
+
"grad_norm": NaN,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 0.0,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.007173343854237653,
|
| 729 |
+
"eval_loss": NaN,
|
| 730 |
+
"eval_runtime": 425.6455,
|
| 731 |
+
"eval_samples_per_second": 13.791,
|
| 732 |
+
"eval_steps_per_second": 3.449,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 745 |
"early_stopping_threshold": 0.0
|
| 746 |
},
|
| 747 |
"attributes": {
|
| 748 |
+
"early_stopping_patience_counter": 1
|
| 749 |
}
|
| 750 |
},
|
| 751 |
"TrainerControl": {
|
|
|
|
| 754 |
"should_evaluate": false,
|
| 755 |
"should_log": false,
|
| 756 |
"should_save": true,
|
| 757 |
+
"should_training_stop": true
|
| 758 |
},
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 3.3886526320410624e+16,
|
| 763 |
"train_batch_size": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|