Training in progress, step 125, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 838904832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2440a1d3e22839736f91530c2d0b5e782e46dd86e3e53bef2a6625a989fa1466
|
| 3 |
size 838904832
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 420633876
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d641a4b63d536e0fd9d4977cc8e26c75ac197343f60b2667be917fff151993b
|
| 3 |
size 420633876
|
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:cdbe66e8af9f834d341b8251d0055801aa4003f83845bb327b01afad2c063103
|
| 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:efdbfe8676cd24a75fed7e6e38125bb1bb838a4b70c0fbf7469557659d9b1fec
|
| 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": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -457,13 +457,313 @@
|
|
| 457 |
"learning_rate": 0.0002,
|
| 458 |
"loss": 0.531,
|
| 459 |
"step": 75
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 460 |
}
|
| 461 |
],
|
| 462 |
"logging_steps": 1,
|
| 463 |
"max_steps": 250,
|
| 464 |
"num_train_epochs": 1,
|
| 465 |
"save_steps": 25,
|
| 466 |
-
"total_flos":
|
| 467 |
"trial_name": null,
|
| 468 |
"trial_params": null
|
| 469 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 125,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 457 |
"learning_rate": 0.0002,
|
| 458 |
"loss": 0.531,
|
| 459 |
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.3,
|
| 463 |
+
"learning_rate": 0.0002,
|
| 464 |
+
"loss": 0.4584,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.31,
|
| 469 |
+
"learning_rate": 0.0002,
|
| 470 |
+
"loss": 0.4835,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.31,
|
| 475 |
+
"learning_rate": 0.0002,
|
| 476 |
+
"loss": 0.5493,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.32,
|
| 481 |
+
"learning_rate": 0.0002,
|
| 482 |
+
"loss": 0.5379,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.32,
|
| 487 |
+
"learning_rate": 0.0002,
|
| 488 |
+
"loss": 0.5795,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.32,
|
| 493 |
+
"learning_rate": 0.0002,
|
| 494 |
+
"loss": 0.4421,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.33,
|
| 499 |
+
"learning_rate": 0.0002,
|
| 500 |
+
"loss": 0.4947,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.33,
|
| 505 |
+
"learning_rate": 0.0002,
|
| 506 |
+
"loss": 0.4997,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.34,
|
| 511 |
+
"learning_rate": 0.0002,
|
| 512 |
+
"loss": 0.4571,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.34,
|
| 517 |
+
"learning_rate": 0.0002,
|
| 518 |
+
"loss": 0.3947,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.34,
|
| 523 |
+
"learning_rate": 0.0002,
|
| 524 |
+
"loss": 0.4796,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.35,
|
| 529 |
+
"learning_rate": 0.0002,
|
| 530 |
+
"loss": 0.3846,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.35,
|
| 535 |
+
"learning_rate": 0.0002,
|
| 536 |
+
"loss": 0.4606,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.36,
|
| 541 |
+
"learning_rate": 0.0002,
|
| 542 |
+
"loss": 0.3776,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.36,
|
| 547 |
+
"learning_rate": 0.0002,
|
| 548 |
+
"loss": 0.4627,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.36,
|
| 553 |
+
"learning_rate": 0.0002,
|
| 554 |
+
"loss": 0.4095,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.37,
|
| 559 |
+
"learning_rate": 0.0002,
|
| 560 |
+
"loss": 0.4047,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.37,
|
| 565 |
+
"learning_rate": 0.0002,
|
| 566 |
+
"loss": 0.3684,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.38,
|
| 571 |
+
"learning_rate": 0.0002,
|
| 572 |
+
"loss": 0.4086,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.38,
|
| 577 |
+
"learning_rate": 0.0002,
|
| 578 |
+
"loss": 0.358,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.38,
|
| 583 |
+
"learning_rate": 0.0002,
|
| 584 |
+
"loss": 0.3824,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.39,
|
| 589 |
+
"learning_rate": 0.0002,
|
| 590 |
+
"loss": 0.3751,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.39,
|
| 595 |
+
"learning_rate": 0.0002,
|
| 596 |
+
"loss": 0.3897,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.4,
|
| 601 |
+
"learning_rate": 0.0002,
|
| 602 |
+
"loss": 0.349,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.4,
|
| 607 |
+
"learning_rate": 0.0002,
|
| 608 |
+
"loss": 0.4674,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.4,
|
| 613 |
+
"learning_rate": 0.0002,
|
| 614 |
+
"loss": 0.7479,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.41,
|
| 619 |
+
"learning_rate": 0.0002,
|
| 620 |
+
"loss": 0.7174,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.41,
|
| 625 |
+
"learning_rate": 0.0002,
|
| 626 |
+
"loss": 0.7081,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.42,
|
| 631 |
+
"learning_rate": 0.0002,
|
| 632 |
+
"loss": 0.6064,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.42,
|
| 637 |
+
"learning_rate": 0.0002,
|
| 638 |
+
"loss": 0.6217,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.42,
|
| 643 |
+
"learning_rate": 0.0002,
|
| 644 |
+
"loss": 0.5967,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.43,
|
| 649 |
+
"learning_rate": 0.0002,
|
| 650 |
+
"loss": 0.5808,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.43,
|
| 655 |
+
"learning_rate": 0.0002,
|
| 656 |
+
"loss": 0.5926,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.44,
|
| 661 |
+
"learning_rate": 0.0002,
|
| 662 |
+
"loss": 0.5861,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.44,
|
| 667 |
+
"learning_rate": 0.0002,
|
| 668 |
+
"loss": 0.5996,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.44,
|
| 673 |
+
"learning_rate": 0.0002,
|
| 674 |
+
"loss": 0.5933,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.45,
|
| 679 |
+
"learning_rate": 0.0002,
|
| 680 |
+
"loss": 0.5812,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.45,
|
| 685 |
+
"learning_rate": 0.0002,
|
| 686 |
+
"loss": 0.5401,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.46,
|
| 691 |
+
"learning_rate": 0.0002,
|
| 692 |
+
"loss": 0.5436,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.46,
|
| 697 |
+
"learning_rate": 0.0002,
|
| 698 |
+
"loss": 0.5415,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.46,
|
| 703 |
+
"learning_rate": 0.0002,
|
| 704 |
+
"loss": 0.5266,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.47,
|
| 709 |
+
"learning_rate": 0.0002,
|
| 710 |
+
"loss": 0.5048,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.47,
|
| 715 |
+
"learning_rate": 0.0002,
|
| 716 |
+
"loss": 0.5286,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.48,
|
| 721 |
+
"learning_rate": 0.0002,
|
| 722 |
+
"loss": 0.5292,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.48,
|
| 727 |
+
"learning_rate": 0.0002,
|
| 728 |
+
"loss": 0.594,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.48,
|
| 733 |
+
"learning_rate": 0.0002,
|
| 734 |
+
"loss": 0.5481,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.49,
|
| 739 |
+
"learning_rate": 0.0002,
|
| 740 |
+
"loss": 0.493,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.49,
|
| 745 |
+
"learning_rate": 0.0002,
|
| 746 |
+
"loss": 0.4596,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.5,
|
| 751 |
+
"learning_rate": 0.0002,
|
| 752 |
+
"loss": 0.5249,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.5,
|
| 757 |
+
"learning_rate": 0.0002,
|
| 758 |
+
"loss": 0.5121,
|
| 759 |
+
"step": 125
|
| 760 |
}
|
| 761 |
],
|
| 762 |
"logging_steps": 1,
|
| 763 |
"max_steps": 250,
|
| 764 |
"num_train_epochs": 1,
|
| 765 |
"save_steps": 25,
|
| 766 |
+
"total_flos": 1.527345774944256e+16,
|
| 767 |
"trial_name": null,
|
| 768 |
"trial_params": null
|
| 769 |
}
|