Commit
•
f97408c
1
Parent(s):
c617c44
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 +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +255 -5
- pytorch_model.bin +1 -1
- runs/Aug17_16-46-37_8582233f681d/events.out.tfevents.1692290809.8582233f681d.216.0 +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 1934161157
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a64142a477ac995752a5a07600ba81b284532e8e4d4037e38e0f8eb87ad0740
|
| 3 |
size 1934161157
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 967102729
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b5e8a23f34e7b9601f22dcc073ac75de81211e5c61813bbbd64f9c96d30afbd
|
| 3 |
size 967102729
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac80e31889643159eab6698b68e325c45c28c5fc3ac3d7375688097866a7d5e9
|
| 3 |
size 14575
|
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 sha256:7714285e54100d4ac40dc418b750401bda88dd754c30602720da851473b84959
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "./whisper-vietnamese-3/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -506,11 +506,261 @@
|
|
| 506 |
"eval_steps_per_second": 0.125,
|
| 507 |
"eval_wer": 111.96070726915521,
|
| 508 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 509 |
}
|
| 510 |
],
|
| 511 |
"max_steps": 4000,
|
| 512 |
"num_train_epochs": 29,
|
| 513 |
-
"total_flos":
|
| 514 |
"trial_name": null,
|
| 515 |
"trial_params": null
|
| 516 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 109.13163064833007,
|
| 3 |
+
"best_model_checkpoint": "./whisper-vietnamese-3/checkpoint-3000",
|
| 4 |
+
"epoch": 21.58273381294964,
|
| 5 |
+
"global_step": 3000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 506 |
"eval_steps_per_second": 0.125,
|
| 507 |
"eval_wer": 111.96070726915521,
|
| 508 |
"step": 2000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 14.57,
|
| 512 |
+
"learning_rate": 5.6485714285714285e-06,
|
| 513 |
+
"loss": 0.0027,
|
| 514 |
+
"step": 2025
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 14.75,
|
| 518 |
+
"learning_rate": 5.5771428571428575e-06,
|
| 519 |
+
"loss": 0.0024,
|
| 520 |
+
"step": 2050
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 14.93,
|
| 524 |
+
"learning_rate": 5.5057142857142865e-06,
|
| 525 |
+
"loss": 0.0029,
|
| 526 |
+
"step": 2075
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 15.11,
|
| 530 |
+
"learning_rate": 5.4342857142857155e-06,
|
| 531 |
+
"loss": 0.0016,
|
| 532 |
+
"step": 2100
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 15.29,
|
| 536 |
+
"learning_rate": 5.362857142857143e-06,
|
| 537 |
+
"loss": 0.0018,
|
| 538 |
+
"step": 2125
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 15.47,
|
| 542 |
+
"learning_rate": 5.291428571428572e-06,
|
| 543 |
+
"loss": 0.0018,
|
| 544 |
+
"step": 2150
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 15.65,
|
| 548 |
+
"learning_rate": 5.220000000000001e-06,
|
| 549 |
+
"loss": 0.0027,
|
| 550 |
+
"step": 2175
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 15.83,
|
| 554 |
+
"learning_rate": 5.14857142857143e-06,
|
| 555 |
+
"loss": 0.0015,
|
| 556 |
+
"step": 2200
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 16.01,
|
| 560 |
+
"learning_rate": 5.077142857142857e-06,
|
| 561 |
+
"loss": 0.0016,
|
| 562 |
+
"step": 2225
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 16.19,
|
| 566 |
+
"learning_rate": 5.005714285714286e-06,
|
| 567 |
+
"loss": 0.0013,
|
| 568 |
+
"step": 2250
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 16.37,
|
| 572 |
+
"learning_rate": 4.934285714285715e-06,
|
| 573 |
+
"loss": 0.002,
|
| 574 |
+
"step": 2275
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 16.55,
|
| 578 |
+
"learning_rate": 4.862857142857143e-06,
|
| 579 |
+
"loss": 0.0019,
|
| 580 |
+
"step": 2300
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 16.73,
|
| 584 |
+
"learning_rate": 4.7914285714285715e-06,
|
| 585 |
+
"loss": 0.0013,
|
| 586 |
+
"step": 2325
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 16.91,
|
| 590 |
+
"learning_rate": 4.7200000000000005e-06,
|
| 591 |
+
"loss": 0.0017,
|
| 592 |
+
"step": 2350
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 17.09,
|
| 596 |
+
"learning_rate": 4.648571428571429e-06,
|
| 597 |
+
"loss": 0.0015,
|
| 598 |
+
"step": 2375
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 17.27,
|
| 602 |
+
"learning_rate": 4.577142857142858e-06,
|
| 603 |
+
"loss": 0.0013,
|
| 604 |
+
"step": 2400
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 17.45,
|
| 608 |
+
"learning_rate": 4.505714285714286e-06,
|
| 609 |
+
"loss": 0.0017,
|
| 610 |
+
"step": 2425
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 17.63,
|
| 614 |
+
"learning_rate": 4.434285714285715e-06,
|
| 615 |
+
"loss": 0.0019,
|
| 616 |
+
"step": 2450
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 17.81,
|
| 620 |
+
"learning_rate": 4.362857142857143e-06,
|
| 621 |
+
"loss": 0.002,
|
| 622 |
+
"step": 2475
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 17.99,
|
| 626 |
+
"learning_rate": 4.291428571428572e-06,
|
| 627 |
+
"loss": 0.0017,
|
| 628 |
+
"step": 2500
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 18.17,
|
| 632 |
+
"learning_rate": 4.22e-06,
|
| 633 |
+
"loss": 0.001,
|
| 634 |
+
"step": 2525
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 18.35,
|
| 638 |
+
"learning_rate": 4.148571428571429e-06,
|
| 639 |
+
"loss": 0.0009,
|
| 640 |
+
"step": 2550
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 18.53,
|
| 644 |
+
"learning_rate": 4.0771428571428574e-06,
|
| 645 |
+
"loss": 0.0012,
|
| 646 |
+
"step": 2575
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 18.71,
|
| 650 |
+
"learning_rate": 4.0057142857142864e-06,
|
| 651 |
+
"loss": 0.0016,
|
| 652 |
+
"step": 2600
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 18.88,
|
| 656 |
+
"learning_rate": 3.934285714285715e-06,
|
| 657 |
+
"loss": 0.0018,
|
| 658 |
+
"step": 2625
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 19.06,
|
| 662 |
+
"learning_rate": 3.862857142857143e-06,
|
| 663 |
+
"loss": 0.0014,
|
| 664 |
+
"step": 2650
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 19.24,
|
| 668 |
+
"learning_rate": 3.7914285714285722e-06,
|
| 669 |
+
"loss": 0.0012,
|
| 670 |
+
"step": 2675
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 19.42,
|
| 674 |
+
"learning_rate": 3.7200000000000004e-06,
|
| 675 |
+
"loss": 0.001,
|
| 676 |
+
"step": 2700
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 19.6,
|
| 680 |
+
"learning_rate": 3.648571428571429e-06,
|
| 681 |
+
"loss": 0.0014,
|
| 682 |
+
"step": 2725
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 19.78,
|
| 686 |
+
"learning_rate": 3.5771428571428576e-06,
|
| 687 |
+
"loss": 0.0013,
|
| 688 |
+
"step": 2750
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 19.96,
|
| 692 |
+
"learning_rate": 3.505714285714286e-06,
|
| 693 |
+
"loss": 0.0009,
|
| 694 |
+
"step": 2775
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 20.14,
|
| 698 |
+
"learning_rate": 3.4342857142857143e-06,
|
| 699 |
+
"loss": 0.0008,
|
| 700 |
+
"step": 2800
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 20.32,
|
| 704 |
+
"learning_rate": 3.3628571428571433e-06,
|
| 705 |
+
"loss": 0.0016,
|
| 706 |
+
"step": 2825
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 20.5,
|
| 710 |
+
"learning_rate": 3.2914285714285715e-06,
|
| 711 |
+
"loss": 0.0008,
|
| 712 |
+
"step": 2850
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 20.68,
|
| 716 |
+
"learning_rate": 3.2200000000000005e-06,
|
| 717 |
+
"loss": 0.0014,
|
| 718 |
+
"step": 2875
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 20.86,
|
| 722 |
+
"learning_rate": 3.1485714285714287e-06,
|
| 723 |
+
"loss": 0.001,
|
| 724 |
+
"step": 2900
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 21.04,
|
| 728 |
+
"learning_rate": 3.0771428571428573e-06,
|
| 729 |
+
"loss": 0.0009,
|
| 730 |
+
"step": 2925
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 21.22,
|
| 734 |
+
"learning_rate": 3.005714285714286e-06,
|
| 735 |
+
"loss": 0.0007,
|
| 736 |
+
"step": 2950
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 21.4,
|
| 740 |
+
"learning_rate": 2.9342857142857144e-06,
|
| 741 |
+
"loss": 0.0011,
|
| 742 |
+
"step": 2975
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 21.58,
|
| 746 |
+
"learning_rate": 2.8628571428571435e-06,
|
| 747 |
+
"loss": 0.0009,
|
| 748 |
+
"step": 3000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 21.58,
|
| 752 |
+
"eval_cer": 101.53081033112092,
|
| 753 |
+
"eval_loss": 0.6016765236854553,
|
| 754 |
+
"eval_runtime": 253.4179,
|
| 755 |
+
"eval_samples_per_second": 0.975,
|
| 756 |
+
"eval_steps_per_second": 0.122,
|
| 757 |
+
"eval_wer": 109.13163064833007,
|
| 758 |
+
"step": 3000
|
| 759 |
}
|
| 760 |
],
|
| 761 |
"max_steps": 4000,
|
| 762 |
"num_train_epochs": 29,
|
| 763 |
+
"total_flos": 1.380967716151296e+19,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
| 766 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 967102729
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b5e8a23f34e7b9601f22dcc073ac75de81211e5c61813bbbd64f9c96d30afbd
|
| 3 |
size 967102729
|
runs/Aug17_16-46-37_8582233f681d/events.out.tfevents.1692290809.8582233f681d.216.0
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 sha256:6c280ec21aa54cf98fe2a2c7712a454106a1a24645c93578c704ad15b98de349
|
| 3 |
+
size 24821
|