Training in progress, step 110, 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 70667778
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66b50de734a57f4149204459b0eefa71c0b46be714bf3a2829837139b5a1c454
|
| 3 |
size 70667778
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4985f63a234e94e52ce70f511ff64b319d639bd89932962250d34e37660950a
|
| 3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c561f324290309be40e4f19d025d41391083141eb974d31c9a22d1421f84d13
|
| 3 |
size 14512
|
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 sha256:2a700d7c88dac270d972078db7e3edfc0fcb4e737d0f2a4361488c55daa58ece
|
| 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": 55,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -408,6 +408,399 @@
|
|
| 408 |
"eval_samples_per_second": 21.963,
|
| 409 |
"eval_steps_per_second": 5.491,
|
| 410 |
"step": 55
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 411 |
}
|
| 412 |
],
|
| 413 |
"logging_steps": 1,
|
|
@@ -427,7 +820,7 @@
|
|
| 427 |
"attributes": {}
|
| 428 |
}
|
| 429 |
},
|
| 430 |
-
"total_flos":
|
| 431 |
"train_batch_size": 2,
|
| 432 |
"trial_name": null,
|
| 433 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4983012457531144,
|
| 5 |
"eval_steps": 55,
|
| 6 |
+
"global_step": 110,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 408 |
"eval_samples_per_second": 21.963,
|
| 409 |
"eval_steps_per_second": 5.491,
|
| 410 |
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.2536806342015855,
|
| 414 |
+
"grad_norm": NaN,
|
| 415 |
+
"learning_rate": 9.96929568447637e-05,
|
| 416 |
+
"loss": 0.0,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.2582106455266138,
|
| 421 |
+
"grad_norm": NaN,
|
| 422 |
+
"learning_rate": 9.958223477553714e-05,
|
| 423 |
+
"loss": 0.0,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.2627406568516421,
|
| 428 |
+
"grad_norm": NaN,
|
| 429 |
+
"learning_rate": 9.94545804185573e-05,
|
| 430 |
+
"loss": 0.0,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.26727066817667045,
|
| 435 |
+
"grad_norm": NaN,
|
| 436 |
+
"learning_rate": 9.931003736767013e-05,
|
| 437 |
+
"loss": 0.0,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.2718006795016987,
|
| 442 |
+
"grad_norm": NaN,
|
| 443 |
+
"learning_rate": 9.91486549841951e-05,
|
| 444 |
+
"loss": 0.0,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.27633069082672707,
|
| 449 |
+
"grad_norm": NaN,
|
| 450 |
+
"learning_rate": 9.89704883800683e-05,
|
| 451 |
+
"loss": 0.0,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.2808607021517554,
|
| 456 |
+
"grad_norm": NaN,
|
| 457 |
+
"learning_rate": 9.877559839902184e-05,
|
| 458 |
+
"loss": 0.0,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.2853907134767837,
|
| 463 |
+
"grad_norm": NaN,
|
| 464 |
+
"learning_rate": 9.85640515958057e-05,
|
| 465 |
+
"loss": 0.0,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.289920724801812,
|
| 470 |
+
"grad_norm": NaN,
|
| 471 |
+
"learning_rate": 9.833592021345937e-05,
|
| 472 |
+
"loss": 0.0,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.2944507361268403,
|
| 477 |
+
"grad_norm": NaN,
|
| 478 |
+
"learning_rate": 9.809128215864097e-05,
|
| 479 |
+
"loss": 0.0,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.29898074745186864,
|
| 484 |
+
"grad_norm": NaN,
|
| 485 |
+
"learning_rate": 9.783022097502204e-05,
|
| 486 |
+
"loss": 0.0,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.3035107587768969,
|
| 491 |
+
"grad_norm": NaN,
|
| 492 |
+
"learning_rate": 9.755282581475769e-05,
|
| 493 |
+
"loss": 0.0,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.30804077010192527,
|
| 498 |
+
"grad_norm": NaN,
|
| 499 |
+
"learning_rate": 9.725919140804099e-05,
|
| 500 |
+
"loss": 0.0,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.31257078142695355,
|
| 505 |
+
"grad_norm": NaN,
|
| 506 |
+
"learning_rate": 9.694941803075283e-05,
|
| 507 |
+
"loss": 0.0,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.3171007927519819,
|
| 512 |
+
"grad_norm": NaN,
|
| 513 |
+
"learning_rate": 9.662361147021779e-05,
|
| 514 |
+
"loss": 0.0,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.32163080407701017,
|
| 519 |
+
"grad_norm": NaN,
|
| 520 |
+
"learning_rate": 9.628188298907782e-05,
|
| 521 |
+
"loss": 0.0,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.3261608154020385,
|
| 526 |
+
"grad_norm": NaN,
|
| 527 |
+
"learning_rate": 9.592434928729616e-05,
|
| 528 |
+
"loss": 0.0,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.33069082672706684,
|
| 533 |
+
"grad_norm": NaN,
|
| 534 |
+
"learning_rate": 9.555113246230442e-05,
|
| 535 |
+
"loss": 0.0,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.3352208380520951,
|
| 540 |
+
"grad_norm": NaN,
|
| 541 |
+
"learning_rate": 9.516235996730645e-05,
|
| 542 |
+
"loss": 0.0,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.33975084937712347,
|
| 547 |
+
"grad_norm": NaN,
|
| 548 |
+
"learning_rate": 9.475816456775313e-05,
|
| 549 |
+
"loss": 0.0,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.34428086070215175,
|
| 554 |
+
"grad_norm": NaN,
|
| 555 |
+
"learning_rate": 9.43386842960031e-05,
|
| 556 |
+
"loss": 0.0,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.3488108720271801,
|
| 561 |
+
"grad_norm": NaN,
|
| 562 |
+
"learning_rate": 9.39040624041849e-05,
|
| 563 |
+
"loss": 0.0,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.35334088335220837,
|
| 568 |
+
"grad_norm": NaN,
|
| 569 |
+
"learning_rate": 9.345444731527642e-05,
|
| 570 |
+
"loss": 0.0,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.3578708946772367,
|
| 575 |
+
"grad_norm": NaN,
|
| 576 |
+
"learning_rate": 9.298999257241863e-05,
|
| 577 |
+
"loss": 0.0,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.362400906002265,
|
| 582 |
+
"grad_norm": NaN,
|
| 583 |
+
"learning_rate": 9.251085678648072e-05,
|
| 584 |
+
"loss": 0.0,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.3669309173272933,
|
| 589 |
+
"grad_norm": NaN,
|
| 590 |
+
"learning_rate": 9.201720358189464e-05,
|
| 591 |
+
"loss": 0.0,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.3714609286523216,
|
| 596 |
+
"grad_norm": NaN,
|
| 597 |
+
"learning_rate": 9.150920154077754e-05,
|
| 598 |
+
"loss": 0.0,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.37599093997734995,
|
| 603 |
+
"grad_norm": NaN,
|
| 604 |
+
"learning_rate": 9.098702414536107e-05,
|
| 605 |
+
"loss": 0.0,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.38052095130237823,
|
| 610 |
+
"grad_norm": NaN,
|
| 611 |
+
"learning_rate": 9.045084971874738e-05,
|
| 612 |
+
"loss": 0.0,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.38505096262740657,
|
| 617 |
+
"grad_norm": NaN,
|
| 618 |
+
"learning_rate": 8.9900861364012e-05,
|
| 619 |
+
"loss": 0.0,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.3895809739524349,
|
| 624 |
+
"grad_norm": NaN,
|
| 625 |
+
"learning_rate": 8.933724690167417e-05,
|
| 626 |
+
"loss": 0.0,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.3941109852774632,
|
| 631 |
+
"grad_norm": NaN,
|
| 632 |
+
"learning_rate": 8.876019880555649e-05,
|
| 633 |
+
"loss": 0.0,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.3986409966024915,
|
| 638 |
+
"grad_norm": NaN,
|
| 639 |
+
"learning_rate": 8.816991413705516e-05,
|
| 640 |
+
"loss": 0.0,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.4031710079275198,
|
| 645 |
+
"grad_norm": NaN,
|
| 646 |
+
"learning_rate": 8.756659447784368e-05,
|
| 647 |
+
"loss": 0.0,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.40770101925254815,
|
| 652 |
+
"grad_norm": NaN,
|
| 653 |
+
"learning_rate": 8.695044586103296e-05,
|
| 654 |
+
"loss": 0.0,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.41223103057757643,
|
| 659 |
+
"grad_norm": NaN,
|
| 660 |
+
"learning_rate": 8.632167870081121e-05,
|
| 661 |
+
"loss": 0.0,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.41676104190260477,
|
| 666 |
+
"grad_norm": NaN,
|
| 667 |
+
"learning_rate": 8.568050772058762e-05,
|
| 668 |
+
"loss": 0.0,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.42129105322763305,
|
| 673 |
+
"grad_norm": NaN,
|
| 674 |
+
"learning_rate": 8.502715187966455e-05,
|
| 675 |
+
"loss": 0.0,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.4258210645526614,
|
| 680 |
+
"grad_norm": NaN,
|
| 681 |
+
"learning_rate": 8.436183429846313e-05,
|
| 682 |
+
"loss": 0.0,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.43035107587768967,
|
| 687 |
+
"grad_norm": NaN,
|
| 688 |
+
"learning_rate": 8.368478218232787e-05,
|
| 689 |
+
"loss": 0.0,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.434881087202718,
|
| 694 |
+
"grad_norm": NaN,
|
| 695 |
+
"learning_rate": 8.299622674393614e-05,
|
| 696 |
+
"loss": 0.0,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.43941109852774635,
|
| 701 |
+
"grad_norm": NaN,
|
| 702 |
+
"learning_rate": 8.229640312433937e-05,
|
| 703 |
+
"loss": 0.0,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.44394110985277463,
|
| 708 |
+
"grad_norm": NaN,
|
| 709 |
+
"learning_rate": 8.158555031266254e-05,
|
| 710 |
+
"loss": 0.0,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.44847112117780297,
|
| 715 |
+
"grad_norm": NaN,
|
| 716 |
+
"learning_rate": 8.086391106448965e-05,
|
| 717 |
+
"loss": 0.0,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.45300113250283125,
|
| 722 |
+
"grad_norm": NaN,
|
| 723 |
+
"learning_rate": 8.013173181896283e-05,
|
| 724 |
+
"loss": 0.0,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.4575311438278596,
|
| 729 |
+
"grad_norm": NaN,
|
| 730 |
+
"learning_rate": 7.938926261462366e-05,
|
| 731 |
+
"loss": 0.0,
|
| 732 |
+
"step": 101
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.46206115515288787,
|
| 736 |
+
"grad_norm": NaN,
|
| 737 |
+
"learning_rate": 7.863675700402526e-05,
|
| 738 |
+
"loss": 0.0,
|
| 739 |
+
"step": 102
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.4665911664779162,
|
| 743 |
+
"grad_norm": NaN,
|
| 744 |
+
"learning_rate": 7.787447196714427e-05,
|
| 745 |
+
"loss": 0.0,
|
| 746 |
+
"step": 103
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.4711211778029445,
|
| 750 |
+
"grad_norm": NaN,
|
| 751 |
+
"learning_rate": 7.710266782362247e-05,
|
| 752 |
+
"loss": 0.0,
|
| 753 |
+
"step": 104
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.47565118912797283,
|
| 757 |
+
"grad_norm": NaN,
|
| 758 |
+
"learning_rate": 7.63216081438678e-05,
|
| 759 |
+
"loss": 0.0,
|
| 760 |
+
"step": 105
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.4801812004530011,
|
| 764 |
+
"grad_norm": NaN,
|
| 765 |
+
"learning_rate": 7.553155965904535e-05,
|
| 766 |
+
"loss": 0.0,
|
| 767 |
+
"step": 106
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.48471121177802945,
|
| 771 |
+
"grad_norm": NaN,
|
| 772 |
+
"learning_rate": 7.473279216998895e-05,
|
| 773 |
+
"loss": 0.0,
|
| 774 |
+
"step": 107
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.48924122310305773,
|
| 778 |
+
"grad_norm": NaN,
|
| 779 |
+
"learning_rate": 7.392557845506432e-05,
|
| 780 |
+
"loss": 0.0,
|
| 781 |
+
"step": 108
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.49377123442808607,
|
| 785 |
+
"grad_norm": NaN,
|
| 786 |
+
"learning_rate": 7.311019417701566e-05,
|
| 787 |
+
"loss": 0.0,
|
| 788 |
+
"step": 109
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.4983012457531144,
|
| 792 |
+
"grad_norm": NaN,
|
| 793 |
+
"learning_rate": 7.228691778882693e-05,
|
| 794 |
+
"loss": 0.0,
|
| 795 |
+
"step": 110
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.4983012457531144,
|
| 799 |
+
"eval_loss": NaN,
|
| 800 |
+
"eval_runtime": 16.8907,
|
| 801 |
+
"eval_samples_per_second": 22.024,
|
| 802 |
+
"eval_steps_per_second": 5.506,
|
| 803 |
+
"step": 110
|
| 804 |
}
|
| 805 |
],
|
| 806 |
"logging_steps": 1,
|
|
|
|
| 820 |
"attributes": {}
|
| 821 |
}
|
| 822 |
},
|
| 823 |
+
"total_flos": 1.58609946181632e+16,
|
| 824 |
"train_batch_size": 2,
|
| 825 |
"trial_name": null,
|
| 826 |
"trial_params": null
|