Training in progress, step 138, 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 335922386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d64006a8240d0814491b2db4b937e17fb7b606088a33ab275a336effb5b52496
|
| 3 |
size 335922386
|
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 sha256:4ac89b50eb49875d4fc6320c442b1f1a2bb0c6ca5dcf4534babea7e4fa581fbf
|
| 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:aa2482d7eb8b9907f50055efed6d979a680e476b4380cec06a223fb30358eb52
|
| 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 sha256:05243bc9418b5d027b9cd58d0b804f8898dee9480e9cd6d09120cb4b16d4e2f3
|
| 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": 69,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -506,6 +506,497 @@
|
|
| 506 |
"eval_samples_per_second": 8.365,
|
| 507 |
"eval_steps_per_second": 2.096,
|
| 508 |
"step": 69
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 509 |
}
|
| 510 |
],
|
| 511 |
"logging_steps": 1,
|
|
@@ -525,7 +1016,7 @@
|
|
| 525 |
"attributes": {}
|
| 526 |
}
|
| 527 |
},
|
| 528 |
-
"total_flos":
|
| 529 |
"train_batch_size": 2,
|
| 530 |
"trial_name": null,
|
| 531 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5025034137460173,
|
| 5 |
"eval_steps": 69,
|
| 6 |
+
"global_step": 138,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 506 |
"eval_samples_per_second": 8.365,
|
| 507 |
"eval_steps_per_second": 2.096,
|
| 508 |
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.25489303595812474,
|
| 512 |
+
"grad_norm": NaN,
|
| 513 |
+
"learning_rate": 0.00019609173219450998,
|
| 514 |
+
"loss": 0.0,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.2585343650432408,
|
| 519 |
+
"grad_norm": NaN,
|
| 520 |
+
"learning_rate": 0.0001956940335732209,
|
| 521 |
+
"loss": 0.0,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.26217569412835684,
|
| 526 |
+
"grad_norm": NaN,
|
| 527 |
+
"learning_rate": 0.00019527751227228963,
|
| 528 |
+
"loss": 0.0,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.2658170232134729,
|
| 533 |
+
"grad_norm": NaN,
|
| 534 |
+
"learning_rate": 0.0001948422502199903,
|
| 535 |
+
"loss": 0.0,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.269458352298589,
|
| 540 |
+
"grad_norm": NaN,
|
| 541 |
+
"learning_rate": 0.00019438833303083678,
|
| 542 |
+
"loss": 0.0,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.27309968138370505,
|
| 547 |
+
"grad_norm": NaN,
|
| 548 |
+
"learning_rate": 0.0001939158499887428,
|
| 549 |
+
"loss": 0.0,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.2767410104688211,
|
| 554 |
+
"grad_norm": NaN,
|
| 555 |
+
"learning_rate": 0.00019342489402945998,
|
| 556 |
+
"loss": 0.0,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.2803823395539372,
|
| 561 |
+
"grad_norm": NaN,
|
| 562 |
+
"learning_rate": 0.00019291556172229785,
|
| 563 |
+
"loss": 0.0,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.28402366863905326,
|
| 568 |
+
"grad_norm": NaN,
|
| 569 |
+
"learning_rate": 0.0001923879532511287,
|
| 570 |
+
"loss": 0.0,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.2876649977241693,
|
| 575 |
+
"grad_norm": NaN,
|
| 576 |
+
"learning_rate": 0.00019184217239468212,
|
| 577 |
+
"loss": 0.0,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.29130632680928537,
|
| 582 |
+
"grad_norm": NaN,
|
| 583 |
+
"learning_rate": 0.00019127832650613189,
|
| 584 |
+
"loss": 0.0,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.2949476558944015,
|
| 589 |
+
"grad_norm": NaN,
|
| 590 |
+
"learning_rate": 0.00019069652649198005,
|
| 591 |
+
"loss": 0.0,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.2985889849795175,
|
| 596 |
+
"grad_norm": NaN,
|
| 597 |
+
"learning_rate": 0.0001900968867902419,
|
| 598 |
+
"loss": 0.0,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.3022303140646336,
|
| 603 |
+
"grad_norm": NaN,
|
| 604 |
+
"learning_rate": 0.00018947952534793661,
|
| 605 |
+
"loss": 0.0,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.3058716431497497,
|
| 610 |
+
"grad_norm": NaN,
|
| 611 |
+
"learning_rate": 0.00018884456359788724,
|
| 612 |
+
"loss": 0.0,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.30951297223486574,
|
| 617 |
+
"grad_norm": NaN,
|
| 618 |
+
"learning_rate": 0.0001881921264348355,
|
| 619 |
+
"loss": 0.0,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.3131543013199818,
|
| 624 |
+
"grad_norm": NaN,
|
| 625 |
+
"learning_rate": 0.00018752234219087538,
|
| 626 |
+
"loss": 0.0,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.31679563040509784,
|
| 631 |
+
"grad_norm": NaN,
|
| 632 |
+
"learning_rate": 0.00018683534261021057,
|
| 633 |
+
"loss": 0.0,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.32043695949021395,
|
| 638 |
+
"grad_norm": NaN,
|
| 639 |
+
"learning_rate": 0.00018613126282324092,
|
| 640 |
+
"loss": 0.0,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.32407828857533,
|
| 645 |
+
"grad_norm": NaN,
|
| 646 |
+
"learning_rate": 0.00018541024131998274,
|
| 647 |
+
"loss": 0.0,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.32771961766044605,
|
| 652 |
+
"grad_norm": NaN,
|
| 653 |
+
"learning_rate": 0.00018467241992282843,
|
| 654 |
+
"loss": 0.0,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.33136094674556216,
|
| 659 |
+
"grad_norm": NaN,
|
| 660 |
+
"learning_rate": 0.00018391794375865024,
|
| 661 |
+
"loss": 0.0,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.3350022758306782,
|
| 666 |
+
"grad_norm": NaN,
|
| 667 |
+
"learning_rate": 0.00018314696123025454,
|
| 668 |
+
"loss": 0.0,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.33864360491579426,
|
| 673 |
+
"grad_norm": NaN,
|
| 674 |
+
"learning_rate": 0.00018235962398719147,
|
| 675 |
+
"loss": 0.0,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.3422849340009103,
|
| 680 |
+
"grad_norm": NaN,
|
| 681 |
+
"learning_rate": 0.00018155608689592604,
|
| 682 |
+
"loss": 0.0,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.3459262630860264,
|
| 687 |
+
"grad_norm": NaN,
|
| 688 |
+
"learning_rate": 0.00018073650800937624,
|
| 689 |
+
"loss": 0.0,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.34956759217114247,
|
| 694 |
+
"grad_norm": NaN,
|
| 695 |
+
"learning_rate": 0.00017990104853582493,
|
| 696 |
+
"loss": 0.0,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.3532089212562585,
|
| 701 |
+
"grad_norm": NaN,
|
| 702 |
+
"learning_rate": 0.00017904987280721035,
|
| 703 |
+
"loss": 0.0,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.3568502503413746,
|
| 708 |
+
"grad_norm": NaN,
|
| 709 |
+
"learning_rate": 0.000178183148246803,
|
| 710 |
+
"loss": 0.0,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.3604915794264907,
|
| 715 |
+
"grad_norm": NaN,
|
| 716 |
+
"learning_rate": 0.0001773010453362737,
|
| 717 |
+
"loss": 0.0,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.36413290851160673,
|
| 722 |
+
"grad_norm": NaN,
|
| 723 |
+
"learning_rate": 0.00017640373758216077,
|
| 724 |
+
"loss": 0.0,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.3677742375967228,
|
| 729 |
+
"grad_norm": NaN,
|
| 730 |
+
"learning_rate": 0.0001754914014817416,
|
| 731 |
+
"loss": 0.0,
|
| 732 |
+
"step": 101
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.3714155666818389,
|
| 736 |
+
"grad_norm": NaN,
|
| 737 |
+
"learning_rate": 0.00017456421648831655,
|
| 738 |
+
"loss": 0.0,
|
| 739 |
+
"step": 102
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.37505689576695495,
|
| 743 |
+
"grad_norm": NaN,
|
| 744 |
+
"learning_rate": 0.00017362236497591094,
|
| 745 |
+
"loss": 0.0,
|
| 746 |
+
"step": 103
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.378698224852071,
|
| 750 |
+
"grad_norm": NaN,
|
| 751 |
+
"learning_rate": 0.0001726660322034027,
|
| 752 |
+
"loss": 0.0,
|
| 753 |
+
"step": 104
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.38233955393718705,
|
| 757 |
+
"grad_norm": NaN,
|
| 758 |
+
"learning_rate": 0.00017169540627808274,
|
| 759 |
+
"loss": 0.0,
|
| 760 |
+
"step": 105
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.38598088302230316,
|
| 764 |
+
"grad_norm": NaN,
|
| 765 |
+
"learning_rate": 0.00017071067811865476,
|
| 766 |
+
"loss": 0.0,
|
| 767 |
+
"step": 106
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.3896222121074192,
|
| 771 |
+
"grad_norm": NaN,
|
| 772 |
+
"learning_rate": 0.00016971204141768233,
|
| 773 |
+
"loss": 0.0,
|
| 774 |
+
"step": 107
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.39326354119253526,
|
| 778 |
+
"grad_norm": NaN,
|
| 779 |
+
"learning_rate": 0.00016869969260349018,
|
| 780 |
+
"loss": 0.0,
|
| 781 |
+
"step": 108
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.39690487027765137,
|
| 785 |
+
"grad_norm": NaN,
|
| 786 |
+
"learning_rate": 0.00016767383080152742,
|
| 787 |
+
"loss": 0.0,
|
| 788 |
+
"step": 109
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.4005461993627674,
|
| 792 |
+
"grad_norm": NaN,
|
| 793 |
+
"learning_rate": 0.0001666346577952004,
|
| 794 |
+
"loss": 0.0,
|
| 795 |
+
"step": 110
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.40418752844788347,
|
| 799 |
+
"grad_norm": NaN,
|
| 800 |
+
"learning_rate": 0.00016558237798618245,
|
| 801 |
+
"loss": 0.0,
|
| 802 |
+
"step": 111
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.4078288575329995,
|
| 806 |
+
"grad_norm": NaN,
|
| 807 |
+
"learning_rate": 0.00016451719835420877,
|
| 808 |
+
"loss": 0.0,
|
| 809 |
+
"step": 112
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.41147018661811563,
|
| 813 |
+
"grad_norm": NaN,
|
| 814 |
+
"learning_rate": 0.00016343932841636456,
|
| 815 |
+
"loss": 0.0,
|
| 816 |
+
"step": 113
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.4151115157032317,
|
| 820 |
+
"grad_norm": NaN,
|
| 821 |
+
"learning_rate": 0.00016234898018587337,
|
| 822 |
+
"loss": 0.0,
|
| 823 |
+
"step": 114
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.41875284478834773,
|
| 827 |
+
"grad_norm": NaN,
|
| 828 |
+
"learning_rate": 0.00016124636813039502,
|
| 829 |
+
"loss": 0.0,
|
| 830 |
+
"step": 115
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.42239417387346384,
|
| 834 |
+
"grad_norm": NaN,
|
| 835 |
+
"learning_rate": 0.00016013170912984058,
|
| 836 |
+
"loss": 0.0,
|
| 837 |
+
"step": 116
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.4260355029585799,
|
| 841 |
+
"grad_norm": NaN,
|
| 842 |
+
"learning_rate": 0.00015900522243371282,
|
| 843 |
+
"loss": 0.0,
|
| 844 |
+
"step": 117
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.42967683204369594,
|
| 848 |
+
"grad_norm": NaN,
|
| 849 |
+
"learning_rate": 0.0001578671296179806,
|
| 850 |
+
"loss": 0.0,
|
| 851 |
+
"step": 118
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.433318161128812,
|
| 855 |
+
"grad_norm": NaN,
|
| 856 |
+
"learning_rate": 0.00015671765454149559,
|
| 857 |
+
"loss": 0.0,
|
| 858 |
+
"step": 119
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.4369594902139281,
|
| 862 |
+
"grad_norm": NaN,
|
| 863 |
+
"learning_rate": 0.00015555702330196023,
|
| 864 |
+
"loss": 0.0,
|
| 865 |
+
"step": 120
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.44060081929904416,
|
| 869 |
+
"grad_norm": NaN,
|
| 870 |
+
"learning_rate": 0.00015438546419145488,
|
| 871 |
+
"loss": 0.0,
|
| 872 |
+
"step": 121
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.4442421483841602,
|
| 876 |
+
"grad_norm": NaN,
|
| 877 |
+
"learning_rate": 0.00015320320765153367,
|
| 878 |
+
"loss": 0.0,
|
| 879 |
+
"step": 122
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.44788347746927626,
|
| 883 |
+
"grad_norm": NaN,
|
| 884 |
+
"learning_rate": 0.00015201048622789747,
|
| 885 |
+
"loss": 0.0,
|
| 886 |
+
"step": 123
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.45152480655439237,
|
| 890 |
+
"grad_norm": NaN,
|
| 891 |
+
"learning_rate": 0.00015080753452465296,
|
| 892 |
+
"loss": 0.0,
|
| 893 |
+
"step": 124
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.4551661356395084,
|
| 897 |
+
"grad_norm": NaN,
|
| 898 |
+
"learning_rate": 0.0001495945891581668,
|
| 899 |
+
"loss": 0.0,
|
| 900 |
+
"step": 125
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.45880746472462447,
|
| 904 |
+
"grad_norm": NaN,
|
| 905 |
+
"learning_rate": 0.000148371888710524,
|
| 906 |
+
"loss": 0.0,
|
| 907 |
+
"step": 126
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.4624487938097406,
|
| 911 |
+
"grad_norm": NaN,
|
| 912 |
+
"learning_rate": 0.0001471396736825998,
|
| 913 |
+
"loss": 0.0,
|
| 914 |
+
"step": 127
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.46609012289485663,
|
| 918 |
+
"grad_norm": NaN,
|
| 919 |
+
"learning_rate": 0.00014589818644675378,
|
| 920 |
+
"loss": 0.0,
|
| 921 |
+
"step": 128
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.4697314519799727,
|
| 925 |
+
"grad_norm": NaN,
|
| 926 |
+
"learning_rate": 0.00014464767119915629,
|
| 927 |
+
"loss": 0.0,
|
| 928 |
+
"step": 129
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.47337278106508873,
|
| 932 |
+
"grad_norm": NaN,
|
| 933 |
+
"learning_rate": 0.00014338837391175582,
|
| 934 |
+
"loss": 0.0,
|
| 935 |
+
"step": 130
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.47701411015020484,
|
| 939 |
+
"grad_norm": NaN,
|
| 940 |
+
"learning_rate": 0.0001421205422838971,
|
| 941 |
+
"loss": 0.0,
|
| 942 |
+
"step": 131
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.4806554392353209,
|
| 946 |
+
"grad_norm": NaN,
|
| 947 |
+
"learning_rate": 0.00014084442569359964,
|
| 948 |
+
"loss": 0.0,
|
| 949 |
+
"step": 132
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.48429676832043694,
|
| 953 |
+
"grad_norm": NaN,
|
| 954 |
+
"learning_rate": 0.0001395602751485059,
|
| 955 |
+
"loss": 0.0,
|
| 956 |
+
"step": 133
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.48793809740555305,
|
| 960 |
+
"grad_norm": NaN,
|
| 961 |
+
"learning_rate": 0.000138268343236509,
|
| 962 |
+
"loss": 0.0,
|
| 963 |
+
"step": 134
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.4915794264906691,
|
| 967 |
+
"grad_norm": NaN,
|
| 968 |
+
"learning_rate": 0.00013696888407606952,
|
| 969 |
+
"loss": 0.0,
|
| 970 |
+
"step": 135
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.49522075557578515,
|
| 974 |
+
"grad_norm": NaN,
|
| 975 |
+
"learning_rate": 0.0001356621532662313,
|
| 976 |
+
"loss": 0.0,
|
| 977 |
+
"step": 136
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.4988620846609012,
|
| 981 |
+
"grad_norm": NaN,
|
| 982 |
+
"learning_rate": 0.0001343484078363461,
|
| 983 |
+
"loss": 0.0,
|
| 984 |
+
"step": 137
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.5025034137460173,
|
| 988 |
+
"grad_norm": NaN,
|
| 989 |
+
"learning_rate": 0.00013302790619551674,
|
| 990 |
+
"loss": 0.0,
|
| 991 |
+
"step": 138
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.5025034137460173,
|
| 995 |
+
"eval_loss": NaN,
|
| 996 |
+
"eval_runtime": 55.2669,
|
| 997 |
+
"eval_samples_per_second": 8.378,
|
| 998 |
+
"eval_steps_per_second": 2.099,
|
| 999 |
+
"step": 138
|
| 1000 |
}
|
| 1001 |
],
|
| 1002 |
"logging_steps": 1,
|
|
|
|
| 1016 |
"attributes": {}
|
| 1017 |
}
|
| 1018 |
},
|
| 1019 |
+
"total_flos": 3.88127927801217e+17,
|
| 1020 |
"train_batch_size": 2,
|
| 1021 |
"trial_name": null,
|
| 1022 |
"trial_params": null
|