Commit
•
fd6aa0d
1
Parent(s):
42c8e1d
Training in progress, step 3000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +252 -3
- pytorch_model.bin +1 -1
- runs/Dec26_19-57-19_gpu07.cyverse.org/events.out.tfevents.1672109970.gpu07.cyverse.org.126369.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12347192855
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:524b22890142e47419a06d19ae61852f9787098118564b0f950aec1179e74230
|
| 3 |
size 12347192855
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6173655480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:292c0ca92f5d9cb9248a1b9129a7ce107758f2f0a9b6c7ce62018b59f5e453ca
|
| 3 |
size 6173655480
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9598b49b7afca30659c27619764c7fd04e3ef4e5f28cc734910a1ae47804866
|
| 3 |
+
size 14639
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac1686cb80dfe456f1ee071e6b209db73517d8bbd97cb9595254e481a753285f
|
| 3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c01e440b61cade1b20bb9e797abdc166ebdff6380a8b18ea5ba5855bc546f3fa
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.11536111854119403,
|
| 3 |
"best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -504,11 +504,260 @@
|
|
| 504 |
"eval_steps_per_second": 0.062,
|
| 505 |
"eval_wer": 0.11313539592435184,
|
| 506 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 507 |
}
|
| 508 |
],
|
| 509 |
"max_steps": 25000,
|
| 510 |
"num_train_epochs": 1,
|
| 511 |
-
"total_flos":
|
| 512 |
"trial_name": null,
|
| 513 |
"trial_params": null
|
| 514 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.11536111854119403,
|
| 3 |
"best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
|
| 4 |
+
"epoch": 0.10413412475268145,
|
| 5 |
+
"global_step": 3000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 504 |
"eval_steps_per_second": 0.062,
|
| 505 |
"eval_wer": 0.11313539592435184,
|
| 506 |
"step": 2000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.07,
|
| 510 |
+
"learning_rate": 9.38e-06,
|
| 511 |
+
"loss": 0.2271,
|
| 512 |
+
"step": 2025
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.07,
|
| 516 |
+
"learning_rate": 9.369795918367347e-06,
|
| 517 |
+
"loss": 0.2161,
|
| 518 |
+
"step": 2050
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.07,
|
| 522 |
+
"learning_rate": 9.359591836734695e-06,
|
| 523 |
+
"loss": 0.1912,
|
| 524 |
+
"step": 2075
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.07,
|
| 528 |
+
"learning_rate": 9.349387755102042e-06,
|
| 529 |
+
"loss": 0.1926,
|
| 530 |
+
"step": 2100
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.07,
|
| 534 |
+
"learning_rate": 9.339183673469388e-06,
|
| 535 |
+
"loss": 0.2196,
|
| 536 |
+
"step": 2125
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.07,
|
| 540 |
+
"learning_rate": 9.328979591836736e-06,
|
| 541 |
+
"loss": 0.1775,
|
| 542 |
+
"step": 2150
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.08,
|
| 546 |
+
"learning_rate": 9.318775510204082e-06,
|
| 547 |
+
"loss": 0.2127,
|
| 548 |
+
"step": 2175
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.08,
|
| 552 |
+
"learning_rate": 9.308571428571429e-06,
|
| 553 |
+
"loss": 0.2074,
|
| 554 |
+
"step": 2200
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.08,
|
| 558 |
+
"learning_rate": 9.298367346938776e-06,
|
| 559 |
+
"loss": 0.1982,
|
| 560 |
+
"step": 2225
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.08,
|
| 564 |
+
"learning_rate": 9.288163265306122e-06,
|
| 565 |
+
"loss": 0.2007,
|
| 566 |
+
"step": 2250
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.08,
|
| 570 |
+
"learning_rate": 9.27795918367347e-06,
|
| 571 |
+
"loss": 0.2084,
|
| 572 |
+
"step": 2275
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.08,
|
| 576 |
+
"learning_rate": 9.267755102040817e-06,
|
| 577 |
+
"loss": 0.1873,
|
| 578 |
+
"step": 2300
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.08,
|
| 582 |
+
"learning_rate": 9.257551020408165e-06,
|
| 583 |
+
"loss": 0.2065,
|
| 584 |
+
"step": 2325
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.08,
|
| 588 |
+
"learning_rate": 9.24734693877551e-06,
|
| 589 |
+
"loss": 0.1805,
|
| 590 |
+
"step": 2350
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.08,
|
| 594 |
+
"learning_rate": 9.237142857142858e-06,
|
| 595 |
+
"loss": 0.2109,
|
| 596 |
+
"step": 2375
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.08,
|
| 600 |
+
"learning_rate": 9.226938775510205e-06,
|
| 601 |
+
"loss": 0.2101,
|
| 602 |
+
"step": 2400
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.08,
|
| 606 |
+
"learning_rate": 9.216734693877551e-06,
|
| 607 |
+
"loss": 0.2151,
|
| 608 |
+
"step": 2425
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.09,
|
| 612 |
+
"learning_rate": 9.206530612244899e-06,
|
| 613 |
+
"loss": 0.2071,
|
| 614 |
+
"step": 2450
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.09,
|
| 618 |
+
"learning_rate": 9.196326530612245e-06,
|
| 619 |
+
"loss": 0.2099,
|
| 620 |
+
"step": 2475
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.09,
|
| 624 |
+
"learning_rate": 9.186122448979594e-06,
|
| 625 |
+
"loss": 0.1788,
|
| 626 |
+
"step": 2500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.09,
|
| 630 |
+
"learning_rate": 9.17591836734694e-06,
|
| 631 |
+
"loss": 0.2066,
|
| 632 |
+
"step": 2525
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.09,
|
| 636 |
+
"learning_rate": 9.165714285714287e-06,
|
| 637 |
+
"loss": 0.177,
|
| 638 |
+
"step": 2550
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.09,
|
| 642 |
+
"learning_rate": 9.155510204081633e-06,
|
| 643 |
+
"loss": 0.2211,
|
| 644 |
+
"step": 2575
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.09,
|
| 648 |
+
"learning_rate": 9.14530612244898e-06,
|
| 649 |
+
"loss": 0.1929,
|
| 650 |
+
"step": 2600
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.09,
|
| 654 |
+
"learning_rate": 9.135102040816328e-06,
|
| 655 |
+
"loss": 0.2171,
|
| 656 |
+
"step": 2625
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.09,
|
| 660 |
+
"learning_rate": 9.124897959183674e-06,
|
| 661 |
+
"loss": 0.1591,
|
| 662 |
+
"step": 2650
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.09,
|
| 666 |
+
"learning_rate": 9.114693877551021e-06,
|
| 667 |
+
"loss": 0.2001,
|
| 668 |
+
"step": 2675
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.09,
|
| 672 |
+
"learning_rate": 9.104489795918367e-06,
|
| 673 |
+
"loss": 0.1912,
|
| 674 |
+
"step": 2700
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.09,
|
| 678 |
+
"learning_rate": 9.094285714285716e-06,
|
| 679 |
+
"loss": 0.2166,
|
| 680 |
+
"step": 2725
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.1,
|
| 684 |
+
"learning_rate": 9.084081632653062e-06,
|
| 685 |
+
"loss": 0.1903,
|
| 686 |
+
"step": 2750
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.1,
|
| 690 |
+
"learning_rate": 9.07387755102041e-06,
|
| 691 |
+
"loss": 0.2228,
|
| 692 |
+
"step": 2775
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.1,
|
| 696 |
+
"learning_rate": 9.063673469387755e-06,
|
| 697 |
+
"loss": 0.2053,
|
| 698 |
+
"step": 2800
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.1,
|
| 702 |
+
"learning_rate": 9.053469387755103e-06,
|
| 703 |
+
"loss": 0.2006,
|
| 704 |
+
"step": 2825
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.1,
|
| 708 |
+
"learning_rate": 9.04326530612245e-06,
|
| 709 |
+
"loss": 0.191,
|
| 710 |
+
"step": 2850
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.1,
|
| 714 |
+
"learning_rate": 9.033061224489796e-06,
|
| 715 |
+
"loss": 0.225,
|
| 716 |
+
"step": 2875
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.1,
|
| 720 |
+
"learning_rate": 9.022857142857143e-06,
|
| 721 |
+
"loss": 0.2079,
|
| 722 |
+
"step": 2900
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.1,
|
| 726 |
+
"learning_rate": 9.01265306122449e-06,
|
| 727 |
+
"loss": 0.2039,
|
| 728 |
+
"step": 2925
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.1,
|
| 732 |
+
"learning_rate": 9.002448979591838e-06,
|
| 733 |
+
"loss": 0.1795,
|
| 734 |
+
"step": 2950
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.1,
|
| 738 |
+
"learning_rate": 8.992244897959184e-06,
|
| 739 |
+
"loss": 0.2053,
|
| 740 |
+
"step": 2975
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.1,
|
| 744 |
+
"learning_rate": 8.982040816326532e-06,
|
| 745 |
+
"loss": 0.167,
|
| 746 |
+
"step": 3000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.1,
|
| 750 |
+
"eval_loss": 0.21150387823581696,
|
| 751 |
+
"eval_runtime": 31085.4661,
|
| 752 |
+
"eval_samples_per_second": 0.998,
|
| 753 |
+
"eval_steps_per_second": 0.062,
|
| 754 |
+
"eval_wer": 0.11325757951014288,
|
| 755 |
+
"step": 3000
|
| 756 |
}
|
| 757 |
],
|
| 758 |
"max_steps": 25000,
|
| 759 |
"num_train_epochs": 1,
|
| 760 |
+
"total_flos": 1.019122089984e+20,
|
| 761 |
"trial_name": null,
|
| 762 |
"trial_params": null
|
| 763 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6173655480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:292c0ca92f5d9cb9248a1b9129a7ce107758f2f0a9b6c7ce62018b59f5e453ca
|
| 3 |
size 6173655480
|
runs/Dec26_19-57-19_gpu07.cyverse.org/events.out.tfevents.1672109970.gpu07.cyverse.org.126369.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6ad16952cc6df1dc554ae3afa7930fec5d15256f3fee9a4261fcb24610e6c56
|
| 3 |
+
size 24183
|