Commit
•
0062eb5
1
Parent(s):
e0ccb33
Training in progress, step 1000
Browse files- {checkpoint-700 → checkpoint-1000}/config.json +0 -0
- {checkpoint-700 → checkpoint-1000}/optimizer.pt +1 -1
- {checkpoint-700 → checkpoint-1000}/preprocessor_config.json +0 -0
- {checkpoint-700 → checkpoint-1000}/pytorch_model.bin +1 -1
- {checkpoint-700 → checkpoint-1000}/rng_state.pth +1 -1
- {checkpoint-700 → checkpoint-1000}/scaler.pt +1 -1
- {checkpoint-700 → checkpoint-1000}/scheduler.pt +1 -1
- {checkpoint-700 → checkpoint-1000}/trainer_state.json +210 -3
- {checkpoint-700 → checkpoint-1000}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-700 → checkpoint-1000}/config.json
RENAMED
|
File without changes
|
{checkpoint-700 → checkpoint-1000}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2490346001
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7366ea0f0c13b52774f5b65c9237727cabcae8df11565fda3d45477aa2f04998
|
| 3 |
size 2490346001
|
{checkpoint-700 → checkpoint-1000}/preprocessor_config.json
RENAMED
|
File without changes
|
{checkpoint-700 → checkpoint-1000}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262067185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:215e82f2b95ddb6481797f61b17faad7070953e16644208286be9592449527ca
|
| 3 |
size 1262067185
|
{checkpoint-700 → checkpoint-1000}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a99d24035e5ff3cbd9dc315b818c70efc6bc64689f3aea3ad3aeea51446c2e6
|
| 3 |
size 14567
|
{checkpoint-700 → checkpoint-1000}/scaler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b5445ebb608f848fc4858bff0aee1c5e183c4aaa9123cfc6cd096717ff96db5
|
| 3 |
size 559
|
{checkpoint-700 → checkpoint-1000}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51077c0775f8e63b91513c5020d22be0afef1f97e1846c4b1d969f7f83bbe0d8
|
| 3 |
size 623
|
{checkpoint-700 → checkpoint-1000}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -489,11 +489,218 @@
|
|
| 489 |
"eval_steps_per_second": 1.12,
|
| 490 |
"eval_wer": 0.9999694058618369,
|
| 491 |
"step": 700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 492 |
}
|
| 493 |
],
|
| 494 |
"max_steps": 6501,
|
| 495 |
"num_train_epochs": 3,
|
| 496 |
-
"total_flos": 1.
|
| 497 |
"trial_name": null,
|
| 498 |
"trial_params": null
|
| 499 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.461361014994233,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 489 |
"eval_steps_per_second": 1.12,
|
| 490 |
"eval_wer": 0.9999694058618369,
|
| 491 |
"step": 700
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.33,
|
| 495 |
+
"learning_rate": 6.838304552590267e-05,
|
| 496 |
+
"loss": 2.9139,
|
| 497 |
+
"step": 710
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.33,
|
| 501 |
+
"learning_rate": 6.826530612244897e-05,
|
| 502 |
+
"loss": 2.9957,
|
| 503 |
+
"step": 720
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.34,
|
| 507 |
+
"learning_rate": 6.814756671899528e-05,
|
| 508 |
+
"loss": 2.9842,
|
| 509 |
+
"step": 730
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.34,
|
| 513 |
+
"learning_rate": 6.802982731554159e-05,
|
| 514 |
+
"loss": 3.2804,
|
| 515 |
+
"step": 740
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.35,
|
| 519 |
+
"learning_rate": 6.792386185243327e-05,
|
| 520 |
+
"loss": 3.4944,
|
| 521 |
+
"step": 750
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.35,
|
| 525 |
+
"learning_rate": 6.780612244897958e-05,
|
| 526 |
+
"loss": 2.9905,
|
| 527 |
+
"step": 760
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.36,
|
| 531 |
+
"learning_rate": 6.768838304552589e-05,
|
| 532 |
+
"loss": 2.9692,
|
| 533 |
+
"step": 770
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.36,
|
| 537 |
+
"learning_rate": 6.757064364207221e-05,
|
| 538 |
+
"loss": 2.9747,
|
| 539 |
+
"step": 780
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.36,
|
| 543 |
+
"learning_rate": 6.745290423861852e-05,
|
| 544 |
+
"loss": 3.294,
|
| 545 |
+
"step": 790
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.37,
|
| 549 |
+
"learning_rate": 6.73469387755102e-05,
|
| 550 |
+
"loss": 3.5998,
|
| 551 |
+
"step": 800
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.37,
|
| 555 |
+
"eval_loss": 3.059178590774536,
|
| 556 |
+
"eval_runtime": 129.2337,
|
| 557 |
+
"eval_samples_per_second": 35.749,
|
| 558 |
+
"eval_steps_per_second": 1.122,
|
| 559 |
+
"eval_wer": 1.0,
|
| 560 |
+
"step": 800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.37,
|
| 564 |
+
"learning_rate": 6.72291993720565e-05,
|
| 565 |
+
"loss": 2.9902,
|
| 566 |
+
"step": 810
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.38,
|
| 570 |
+
"learning_rate": 6.711145996860281e-05,
|
| 571 |
+
"loss": 2.9644,
|
| 572 |
+
"step": 820
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.38,
|
| 576 |
+
"learning_rate": 6.699372056514913e-05,
|
| 577 |
+
"loss": 2.9529,
|
| 578 |
+
"step": 830
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.39,
|
| 582 |
+
"learning_rate": 6.687598116169544e-05,
|
| 583 |
+
"loss": 3.2737,
|
| 584 |
+
"step": 840
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.39,
|
| 588 |
+
"learning_rate": 6.677001569858712e-05,
|
| 589 |
+
"loss": 3.6534,
|
| 590 |
+
"step": 850
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.4,
|
| 594 |
+
"learning_rate": 6.665227629513343e-05,
|
| 595 |
+
"loss": 2.9664,
|
| 596 |
+
"step": 860
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.4,
|
| 600 |
+
"learning_rate": 6.653453689167974e-05,
|
| 601 |
+
"loss": 2.9463,
|
| 602 |
+
"step": 870
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.41,
|
| 606 |
+
"learning_rate": 6.641679748822606e-05,
|
| 607 |
+
"loss": 2.9591,
|
| 608 |
+
"step": 880
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.41,
|
| 612 |
+
"learning_rate": 6.629905808477237e-05,
|
| 613 |
+
"loss": 3.2701,
|
| 614 |
+
"step": 890
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.42,
|
| 618 |
+
"learning_rate": 6.618131868131867e-05,
|
| 619 |
+
"loss": 3.3784,
|
| 620 |
+
"step": 900
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.42,
|
| 624 |
+
"eval_loss": 3.0334482192993164,
|
| 625 |
+
"eval_runtime": 129.072,
|
| 626 |
+
"eval_samples_per_second": 35.794,
|
| 627 |
+
"eval_steps_per_second": 1.123,
|
| 628 |
+
"eval_wer": 1.0,
|
| 629 |
+
"step": 900
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.42,
|
| 633 |
+
"learning_rate": 6.606357927786498e-05,
|
| 634 |
+
"loss": 2.9729,
|
| 635 |
+
"step": 910
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.42,
|
| 639 |
+
"learning_rate": 6.594583987441129e-05,
|
| 640 |
+
"loss": 2.9444,
|
| 641 |
+
"step": 920
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.43,
|
| 645 |
+
"learning_rate": 6.582810047095761e-05,
|
| 646 |
+
"loss": 2.9441,
|
| 647 |
+
"step": 930
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.43,
|
| 651 |
+
"learning_rate": 6.571036106750392e-05,
|
| 652 |
+
"loss": 3.2629,
|
| 653 |
+
"step": 940
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.44,
|
| 657 |
+
"learning_rate": 6.56043956043956e-05,
|
| 658 |
+
"loss": 3.6467,
|
| 659 |
+
"step": 950
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.44,
|
| 663 |
+
"learning_rate": 6.548665620094191e-05,
|
| 664 |
+
"loss": 2.9472,
|
| 665 |
+
"step": 960
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.45,
|
| 669 |
+
"learning_rate": 6.536891679748822e-05,
|
| 670 |
+
"loss": 2.9301,
|
| 671 |
+
"step": 970
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.45,
|
| 675 |
+
"learning_rate": 6.525117739403452e-05,
|
| 676 |
+
"loss": 2.9555,
|
| 677 |
+
"step": 980
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.46,
|
| 681 |
+
"learning_rate": 6.513343799058084e-05,
|
| 682 |
+
"loss": 3.2888,
|
| 683 |
+
"step": 990
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.46,
|
| 687 |
+
"learning_rate": 6.502747252747253e-05,
|
| 688 |
+
"loss": 3.6354,
|
| 689 |
+
"step": 1000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.46,
|
| 693 |
+
"eval_loss": 2.9995181560516357,
|
| 694 |
+
"eval_runtime": 128.998,
|
| 695 |
+
"eval_samples_per_second": 35.815,
|
| 696 |
+
"eval_steps_per_second": 1.124,
|
| 697 |
+
"eval_wer": 1.0,
|
| 698 |
+
"step": 1000
|
| 699 |
}
|
| 700 |
],
|
| 701 |
"max_steps": 6501,
|
| 702 |
"num_train_epochs": 3,
|
| 703 |
+
"total_flos": 1.8908999903639437e+19,
|
| 704 |
"trial_name": null,
|
| 705 |
"trial_params": null
|
| 706 |
}
|
{checkpoint-700 → checkpoint-1000}/training_args.bin
RENAMED
|
File without changes
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262067185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:215e82f2b95ddb6481797f61b17faad7070953e16644208286be9592449527ca
|
| 3 |
size 1262067185
|