Commit
•
fc2f4cd
1
Parent(s):
6012db9
Training in progress, step 2700
Browse files- {checkpoint-1500 → checkpoint-2600}/config.json +0 -0
- {checkpoint-1500 → checkpoint-2600}/optimizer.pt +1 -1
- {checkpoint-1500 → checkpoint-2600}/preprocessor_config.json +0 -0
- {checkpoint-1600 → checkpoint-2600}/pytorch_model.bin +1 -1
- {checkpoint-1600 → checkpoint-2600}/rng_state.pth +1 -1
- {checkpoint-1600 → checkpoint-2600}/scaler.pt +1 -1
- {checkpoint-1500 → checkpoint-2600}/scheduler.pt +1 -1
- {checkpoint-1600 → checkpoint-2600}/trainer_state.json +393 -3
- {checkpoint-1500 → checkpoint-2600}/training_args.bin +0 -0
- {checkpoint-1600 → checkpoint-2700}/config.json +0 -0
- {checkpoint-1600 → checkpoint-2700}/optimizer.pt +1 -1
- {checkpoint-1600 → checkpoint-2700}/preprocessor_config.json +0 -0
- {checkpoint-1500 → checkpoint-2700}/pytorch_model.bin +1 -1
- {checkpoint-1500 → checkpoint-2700}/rng_state.pth +2 -2
- {checkpoint-1500 → checkpoint-2700}/scaler.pt +1 -1
- {checkpoint-1600 → checkpoint-2700}/scheduler.pt +1 -1
- {checkpoint-1500 → checkpoint-2700}/trainer_state.json +471 -3
- {checkpoint-1600 → checkpoint-2700}/training_args.bin +0 -0
{checkpoint-1500 → checkpoint-2600}/config.json
RENAMED
|
File without changes
|
{checkpoint-1500 → checkpoint-2600}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2490337809
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:446a2b6be86378473522da6f8340e8995c1f93f317dbf12dd45b200fe2a7cc10
|
| 3 |
size 2490337809
|
{checkpoint-1500 → checkpoint-2600}/preprocessor_config.json
RENAMED
|
File without changes
|
{checkpoint-1600 → checkpoint-2600}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262063089
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91a8acf504932720b905a27cdf2f6f7fe41c15519686ef918a30514dacbc0cee
|
| 3 |
size 1262063089
|
{checkpoint-1600 → checkpoint-2600}/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:c9452e603549f04f4903c5fb527b7bfc83e1fbaca4162bb7fdd612e22dd24235
|
| 3 |
size 14567
|
{checkpoint-1600 → checkpoint-2600}/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 sha256:981227375b8c6d2439b9fd2664e9cd784500649faa2e607c97ed38e07fc17be3
|
| 3 |
size 559
|
{checkpoint-1500 → checkpoint-2600}/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 sha256:7e6505acc346b949554e5cbd939e1a9cf4a757843e611b8b1dc1e36690134723
|
| 3 |
size 623
|
{checkpoint-1600 → checkpoint-2600}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -630,11 +630,401 @@
|
|
| 630 |
"eval_steps_per_second": 0.795,
|
| 631 |
"eval_wer": 0.17885325007096226,
|
| 632 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 633 |
}
|
| 634 |
],
|
| 635 |
"max_steps": 4550,
|
| 636 |
"num_train_epochs": 50,
|
| 637 |
-
"total_flos":
|
| 638 |
"trial_name": null,
|
| 639 |
"trial_params": null
|
| 640 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 28.56830601092896,
|
| 5 |
+
"global_step": 2600,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 630 |
"eval_steps_per_second": 0.795,
|
| 631 |
"eval_wer": 0.17885325007096226,
|
| 632 |
"step": 1600
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 17.8,
|
| 636 |
+
"learning_rate": 0.00020250000000000002,
|
| 637 |
+
"loss": 1.0322,
|
| 638 |
+
"step": 1620
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 18.02,
|
| 642 |
+
"learning_rate": 0.000205,
|
| 643 |
+
"loss": 1.0176,
|
| 644 |
+
"step": 1640
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 18.24,
|
| 648 |
+
"learning_rate": 0.0002075,
|
| 649 |
+
"loss": 1.0272,
|
| 650 |
+
"step": 1660
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 18.46,
|
| 654 |
+
"learning_rate": 0.00021,
|
| 655 |
+
"loss": 0.9675,
|
| 656 |
+
"step": 1680
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 18.68,
|
| 660 |
+
"learning_rate": 0.0002125,
|
| 661 |
+
"loss": 0.9816,
|
| 662 |
+
"step": 1700
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 18.68,
|
| 666 |
+
"eval_loss": 0.19402356445789337,
|
| 667 |
+
"eval_runtime": 194.75,
|
| 668 |
+
"eval_samples_per_second": 24.868,
|
| 669 |
+
"eval_steps_per_second": 0.78,
|
| 670 |
+
"eval_wer": 0.18010218563724098,
|
| 671 |
+
"step": 1700
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 18.9,
|
| 675 |
+
"learning_rate": 0.000215,
|
| 676 |
+
"loss": 1.0023,
|
| 677 |
+
"step": 1720
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 19.12,
|
| 681 |
+
"learning_rate": 0.0002175,
|
| 682 |
+
"loss": 1.013,
|
| 683 |
+
"step": 1740
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 19.34,
|
| 687 |
+
"learning_rate": 0.00022,
|
| 688 |
+
"loss": 0.9664,
|
| 689 |
+
"step": 1760
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 19.56,
|
| 693 |
+
"learning_rate": 0.00022250000000000001,
|
| 694 |
+
"loss": 0.9736,
|
| 695 |
+
"step": 1780
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 19.78,
|
| 699 |
+
"learning_rate": 0.00022500000000000002,
|
| 700 |
+
"loss": 0.9814,
|
| 701 |
+
"step": 1800
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 19.78,
|
| 705 |
+
"eval_loss": 0.18596723675727844,
|
| 706 |
+
"eval_runtime": 188.4639,
|
| 707 |
+
"eval_samples_per_second": 25.697,
|
| 708 |
+
"eval_steps_per_second": 0.807,
|
| 709 |
+
"eval_wer": 0.16667612829974454,
|
| 710 |
+
"step": 1800
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 19.99,
|
| 714 |
+
"learning_rate": 0.0002275,
|
| 715 |
+
"loss": 1.0064,
|
| 716 |
+
"step": 1820
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 20.22,
|
| 720 |
+
"learning_rate": 0.00023,
|
| 721 |
+
"loss": 0.9583,
|
| 722 |
+
"step": 1840
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 20.44,
|
| 726 |
+
"learning_rate": 0.0002325,
|
| 727 |
+
"loss": 0.9646,
|
| 728 |
+
"step": 1860
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 20.66,
|
| 732 |
+
"learning_rate": 0.000235,
|
| 733 |
+
"loss": 0.9762,
|
| 734 |
+
"step": 1880
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 20.87,
|
| 738 |
+
"learning_rate": 0.0002375,
|
| 739 |
+
"loss": 0.9787,
|
| 740 |
+
"step": 1900
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 20.87,
|
| 744 |
+
"eval_loss": 0.18878202140331268,
|
| 745 |
+
"eval_runtime": 188.244,
|
| 746 |
+
"eval_samples_per_second": 25.727,
|
| 747 |
+
"eval_steps_per_second": 0.807,
|
| 748 |
+
"eval_wer": 0.16420664206642066,
|
| 749 |
+
"step": 1900
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 21.1,
|
| 753 |
+
"learning_rate": 0.00024,
|
| 754 |
+
"loss": 1.0218,
|
| 755 |
+
"step": 1920
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 21.32,
|
| 759 |
+
"learning_rate": 0.00024249999999999999,
|
| 760 |
+
"loss": 0.9505,
|
| 761 |
+
"step": 1940
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 21.54,
|
| 765 |
+
"learning_rate": 0.000245,
|
| 766 |
+
"loss": 0.9554,
|
| 767 |
+
"step": 1960
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 21.75,
|
| 771 |
+
"learning_rate": 0.0002475,
|
| 772 |
+
"loss": 0.9728,
|
| 773 |
+
"step": 1980
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 21.97,
|
| 777 |
+
"learning_rate": 0.00025,
|
| 778 |
+
"loss": 0.9699,
|
| 779 |
+
"step": 2000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 21.97,
|
| 783 |
+
"eval_loss": 0.18748582899570465,
|
| 784 |
+
"eval_runtime": 190.7875,
|
| 785 |
+
"eval_samples_per_second": 25.384,
|
| 786 |
+
"eval_steps_per_second": 0.797,
|
| 787 |
+
"eval_wer": 0.17042293499858074,
|
| 788 |
+
"step": 2000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 22.2,
|
| 792 |
+
"learning_rate": 0.00024803921568627453,
|
| 793 |
+
"loss": 0.9624,
|
| 794 |
+
"step": 2020
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 22.42,
|
| 798 |
+
"learning_rate": 0.000246078431372549,
|
| 799 |
+
"loss": 0.9419,
|
| 800 |
+
"step": 2040
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 22.63,
|
| 804 |
+
"learning_rate": 0.00024411764705882354,
|
| 805 |
+
"loss": 0.9563,
|
| 806 |
+
"step": 2060
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 22.85,
|
| 810 |
+
"learning_rate": 0.00024215686274509804,
|
| 811 |
+
"loss": 0.9643,
|
| 812 |
+
"step": 2080
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 23.08,
|
| 816 |
+
"learning_rate": 0.00024019607843137256,
|
| 817 |
+
"loss": 0.9616,
|
| 818 |
+
"step": 2100
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 23.08,
|
| 822 |
+
"eval_loss": 0.18017500638961792,
|
| 823 |
+
"eval_runtime": 191.3932,
|
| 824 |
+
"eval_samples_per_second": 25.304,
|
| 825 |
+
"eval_steps_per_second": 0.794,
|
| 826 |
+
"eval_wer": 0.16173715583309678,
|
| 827 |
+
"step": 2100
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 23.3,
|
| 831 |
+
"learning_rate": 0.00023823529411764704,
|
| 832 |
+
"loss": 0.917,
|
| 833 |
+
"step": 2120
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 23.51,
|
| 837 |
+
"learning_rate": 0.00023627450980392157,
|
| 838 |
+
"loss": 0.945,
|
| 839 |
+
"step": 2140
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 23.73,
|
| 843 |
+
"learning_rate": 0.0002343137254901961,
|
| 844 |
+
"loss": 0.9243,
|
| 845 |
+
"step": 2160
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 23.95,
|
| 849 |
+
"learning_rate": 0.0002323529411764706,
|
| 850 |
+
"loss": 0.9288,
|
| 851 |
+
"step": 2180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 24.17,
|
| 855 |
+
"learning_rate": 0.0002303921568627451,
|
| 856 |
+
"loss": 0.9378,
|
| 857 |
+
"step": 2200
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 24.17,
|
| 861 |
+
"eval_loss": 0.17928896844387054,
|
| 862 |
+
"eval_runtime": 189.7619,
|
| 863 |
+
"eval_samples_per_second": 25.521,
|
| 864 |
+
"eval_steps_per_second": 0.801,
|
| 865 |
+
"eval_wer": 0.1577348850411581,
|
| 866 |
+
"step": 2200
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 24.39,
|
| 870 |
+
"learning_rate": 0.0002284313725490196,
|
| 871 |
+
"loss": 0.9071,
|
| 872 |
+
"step": 2220
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 24.61,
|
| 876 |
+
"learning_rate": 0.00022647058823529412,
|
| 877 |
+
"loss": 0.9054,
|
| 878 |
+
"step": 2240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 24.83,
|
| 882 |
+
"learning_rate": 0.0002246078431372549,
|
| 883 |
+
"loss": 0.9303,
|
| 884 |
+
"step": 2260
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 25.05,
|
| 888 |
+
"learning_rate": 0.00022264705882352943,
|
| 889 |
+
"loss": 0.9376,
|
| 890 |
+
"step": 2280
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 25.27,
|
| 894 |
+
"learning_rate": 0.0002206862745098039,
|
| 895 |
+
"loss": 0.888,
|
| 896 |
+
"step": 2300
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 25.27,
|
| 900 |
+
"eval_loss": 0.17642559111118317,
|
| 901 |
+
"eval_runtime": 187.0437,
|
| 902 |
+
"eval_samples_per_second": 25.892,
|
| 903 |
+
"eval_steps_per_second": 0.813,
|
| 904 |
+
"eval_wer": 0.15452739142776042,
|
| 905 |
+
"step": 2300
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 25.49,
|
| 909 |
+
"learning_rate": 0.00021872549019607843,
|
| 910 |
+
"loss": 0.9135,
|
| 911 |
+
"step": 2320
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 25.71,
|
| 915 |
+
"learning_rate": 0.00021676470588235294,
|
| 916 |
+
"loss": 0.9094,
|
| 917 |
+
"step": 2340
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 25.93,
|
| 921 |
+
"learning_rate": 0.00021480392156862746,
|
| 922 |
+
"loss": 0.8879,
|
| 923 |
+
"step": 2360
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 26.15,
|
| 927 |
+
"learning_rate": 0.00021284313725490196,
|
| 928 |
+
"loss": 0.929,
|
| 929 |
+
"step": 2380
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 26.37,
|
| 933 |
+
"learning_rate": 0.00021088235294117647,
|
| 934 |
+
"loss": 0.8942,
|
| 935 |
+
"step": 2400
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 26.37,
|
| 939 |
+
"eval_loss": 0.16744859516620636,
|
| 940 |
+
"eval_runtime": 190.6796,
|
| 941 |
+
"eval_samples_per_second": 25.399,
|
| 942 |
+
"eval_steps_per_second": 0.797,
|
| 943 |
+
"eval_wer": 0.14916264547260857,
|
| 944 |
+
"step": 2400
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 26.59,
|
| 948 |
+
"learning_rate": 0.000208921568627451,
|
| 949 |
+
"loss": 0.8717,
|
| 950 |
+
"step": 2420
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 26.81,
|
| 954 |
+
"learning_rate": 0.0002069607843137255,
|
| 955 |
+
"loss": 0.8952,
|
| 956 |
+
"step": 2440
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 27.03,
|
| 960 |
+
"learning_rate": 0.000205,
|
| 961 |
+
"loss": 0.8849,
|
| 962 |
+
"step": 2460
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 27.25,
|
| 966 |
+
"learning_rate": 0.00020313725490196078,
|
| 967 |
+
"loss": 0.8781,
|
| 968 |
+
"step": 2480
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 27.47,
|
| 972 |
+
"learning_rate": 0.0002011764705882353,
|
| 973 |
+
"loss": 0.8701,
|
| 974 |
+
"step": 2500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 27.47,
|
| 978 |
+
"eval_loss": 0.1738910973072052,
|
| 979 |
+
"eval_runtime": 187.7205,
|
| 980 |
+
"eval_samples_per_second": 25.799,
|
| 981 |
+
"eval_steps_per_second": 0.81,
|
| 982 |
+
"eval_wer": 0.1511779733181947,
|
| 983 |
+
"step": 2500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 27.69,
|
| 987 |
+
"learning_rate": 0.0001992156862745098,
|
| 988 |
+
"loss": 0.8674,
|
| 989 |
+
"step": 2520
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 27.91,
|
| 993 |
+
"learning_rate": 0.00019725490196078433,
|
| 994 |
+
"loss": 0.8752,
|
| 995 |
+
"step": 2540
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 28.13,
|
| 999 |
+
"learning_rate": 0.0001952941176470588,
|
| 1000 |
+
"loss": 0.91,
|
| 1001 |
+
"step": 2560
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 28.35,
|
| 1005 |
+
"learning_rate": 0.00019333333333333333,
|
| 1006 |
+
"loss": 0.8693,
|
| 1007 |
+
"step": 2580
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 28.57,
|
| 1011 |
+
"learning_rate": 0.00019137254901960786,
|
| 1012 |
+
"loss": 0.8555,
|
| 1013 |
+
"step": 2600
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 28.57,
|
| 1017 |
+
"eval_loss": 0.1689654141664505,
|
| 1018 |
+
"eval_runtime": 196.2665,
|
| 1019 |
+
"eval_samples_per_second": 24.676,
|
| 1020 |
+
"eval_steps_per_second": 0.774,
|
| 1021 |
+
"eval_wer": 0.14459267669599773,
|
| 1022 |
+
"step": 2600
|
| 1023 |
}
|
| 1024 |
],
|
| 1025 |
"max_steps": 4550,
|
| 1026 |
"num_train_epochs": 50,
|
| 1027 |
+
"total_flos": 4.023333138533005e+19,
|
| 1028 |
"trial_name": null,
|
| 1029 |
"trial_params": null
|
| 1030 |
}
|
{checkpoint-1500 → checkpoint-2600}/training_args.bin
RENAMED
|
File without changes
|
{checkpoint-1600 → checkpoint-2700}/config.json
RENAMED
|
File without changes
|
{checkpoint-1600 → checkpoint-2700}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2490337809
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:865f44abdd5045a8acf626b3b992e8fdc983a2d4a3ba5dd6901b27ee83a91484
|
| 3 |
size 2490337809
|
{checkpoint-1600 → checkpoint-2700}/preprocessor_config.json
RENAMED
|
File without changes
|
{checkpoint-1500 → checkpoint-2700}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262063089
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dbbb4678046f14503aa95af2d02c0cc6a2fb7071e468967b463cf71594e2914
|
| 3 |
size 1262063089
|
{checkpoint-1500 → checkpoint-2700}/rng_state.pth
RENAMED
|
@@ -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 sha256:9213f1eed5d75326eef26e352d35aa78d567c2885250ab304bce7d59c834157a
|
| 3 |
+
size 14631
|
{checkpoint-1500 → checkpoint-2700}/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 sha256:7970626d52baf6e9c965f8503c1a6318b3c55b1f5ba73fdd8b8209e28d5d529e
|
| 3 |
size 559
|
{checkpoint-1600 → checkpoint-2700}/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 sha256:89b50e7b743fe5caf734a580430810fca62d132f602e2a17e8e075ce20b82717
|
| 3 |
size 623
|
{checkpoint-1500 → checkpoint-2700}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -591,11 +591,479 @@
|
|
| 591 |
"eval_steps_per_second": 0.804,
|
| 592 |
"eval_wer": 0.18944081748509792,
|
| 593 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 594 |
}
|
| 595 |
],
|
| 596 |
"max_steps": 4550,
|
| 597 |
"num_train_epochs": 50,
|
| 598 |
-
"total_flos":
|
| 599 |
"trial_name": null,
|
| 600 |
"trial_params": null
|
| 601 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 29.666666666666668,
|
| 5 |
+
"global_step": 2700,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 591 |
"eval_steps_per_second": 0.804,
|
| 592 |
"eval_wer": 0.18944081748509792,
|
| 593 |
"step": 1500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 16.7,
|
| 597 |
+
"learning_rate": 0.00019,
|
| 598 |
+
"loss": 1.0204,
|
| 599 |
+
"step": 1520
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 16.92,
|
| 603 |
+
"learning_rate": 0.00019250000000000002,
|
| 604 |
+
"loss": 1.0356,
|
| 605 |
+
"step": 1540
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 17.14,
|
| 609 |
+
"learning_rate": 0.00019500000000000002,
|
| 610 |
+
"loss": 1.0538,
|
| 611 |
+
"step": 1560
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 17.36,
|
| 615 |
+
"learning_rate": 0.0001975,
|
| 616 |
+
"loss": 1.0228,
|
| 617 |
+
"step": 1580
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 17.58,
|
| 621 |
+
"learning_rate": 0.0002,
|
| 622 |
+
"loss": 1.0193,
|
| 623 |
+
"step": 1600
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 17.58,
|
| 627 |
+
"eval_loss": 0.1991206556558609,
|
| 628 |
+
"eval_runtime": 191.1717,
|
| 629 |
+
"eval_samples_per_second": 25.333,
|
| 630 |
+
"eval_steps_per_second": 0.795,
|
| 631 |
+
"eval_wer": 0.17885325007096226,
|
| 632 |
+
"step": 1600
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 17.8,
|
| 636 |
+
"learning_rate": 0.00020250000000000002,
|
| 637 |
+
"loss": 1.0322,
|
| 638 |
+
"step": 1620
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 18.02,
|
| 642 |
+
"learning_rate": 0.000205,
|
| 643 |
+
"loss": 1.0176,
|
| 644 |
+
"step": 1640
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 18.24,
|
| 648 |
+
"learning_rate": 0.0002075,
|
| 649 |
+
"loss": 1.0272,
|
| 650 |
+
"step": 1660
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 18.46,
|
| 654 |
+
"learning_rate": 0.00021,
|
| 655 |
+
"loss": 0.9675,
|
| 656 |
+
"step": 1680
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 18.68,
|
| 660 |
+
"learning_rate": 0.0002125,
|
| 661 |
+
"loss": 0.9816,
|
| 662 |
+
"step": 1700
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 18.68,
|
| 666 |
+
"eval_loss": 0.19402356445789337,
|
| 667 |
+
"eval_runtime": 194.75,
|
| 668 |
+
"eval_samples_per_second": 24.868,
|
| 669 |
+
"eval_steps_per_second": 0.78,
|
| 670 |
+
"eval_wer": 0.18010218563724098,
|
| 671 |
+
"step": 1700
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 18.9,
|
| 675 |
+
"learning_rate": 0.000215,
|
| 676 |
+
"loss": 1.0023,
|
| 677 |
+
"step": 1720
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 19.12,
|
| 681 |
+
"learning_rate": 0.0002175,
|
| 682 |
+
"loss": 1.013,
|
| 683 |
+
"step": 1740
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 19.34,
|
| 687 |
+
"learning_rate": 0.00022,
|
| 688 |
+
"loss": 0.9664,
|
| 689 |
+
"step": 1760
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 19.56,
|
| 693 |
+
"learning_rate": 0.00022250000000000001,
|
| 694 |
+
"loss": 0.9736,
|
| 695 |
+
"step": 1780
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 19.78,
|
| 699 |
+
"learning_rate": 0.00022500000000000002,
|
| 700 |
+
"loss": 0.9814,
|
| 701 |
+
"step": 1800
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 19.78,
|
| 705 |
+
"eval_loss": 0.18596723675727844,
|
| 706 |
+
"eval_runtime": 188.4639,
|
| 707 |
+
"eval_samples_per_second": 25.697,
|
| 708 |
+
"eval_steps_per_second": 0.807,
|
| 709 |
+
"eval_wer": 0.16667612829974454,
|
| 710 |
+
"step": 1800
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 19.99,
|
| 714 |
+
"learning_rate": 0.0002275,
|
| 715 |
+
"loss": 1.0064,
|
| 716 |
+
"step": 1820
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 20.22,
|
| 720 |
+
"learning_rate": 0.00023,
|
| 721 |
+
"loss": 0.9583,
|
| 722 |
+
"step": 1840
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 20.44,
|
| 726 |
+
"learning_rate": 0.0002325,
|
| 727 |
+
"loss": 0.9646,
|
| 728 |
+
"step": 1860
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 20.66,
|
| 732 |
+
"learning_rate": 0.000235,
|
| 733 |
+
"loss": 0.9762,
|
| 734 |
+
"step": 1880
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 20.87,
|
| 738 |
+
"learning_rate": 0.0002375,
|
| 739 |
+
"loss": 0.9787,
|
| 740 |
+
"step": 1900
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 20.87,
|
| 744 |
+
"eval_loss": 0.18878202140331268,
|
| 745 |
+
"eval_runtime": 188.244,
|
| 746 |
+
"eval_samples_per_second": 25.727,
|
| 747 |
+
"eval_steps_per_second": 0.807,
|
| 748 |
+
"eval_wer": 0.16420664206642066,
|
| 749 |
+
"step": 1900
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 21.1,
|
| 753 |
+
"learning_rate": 0.00024,
|
| 754 |
+
"loss": 1.0218,
|
| 755 |
+
"step": 1920
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 21.32,
|
| 759 |
+
"learning_rate": 0.00024249999999999999,
|
| 760 |
+
"loss": 0.9505,
|
| 761 |
+
"step": 1940
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 21.54,
|
| 765 |
+
"learning_rate": 0.000245,
|
| 766 |
+
"loss": 0.9554,
|
| 767 |
+
"step": 1960
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 21.75,
|
| 771 |
+
"learning_rate": 0.0002475,
|
| 772 |
+
"loss": 0.9728,
|
| 773 |
+
"step": 1980
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 21.97,
|
| 777 |
+
"learning_rate": 0.00025,
|
| 778 |
+
"loss": 0.9699,
|
| 779 |
+
"step": 2000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 21.97,
|
| 783 |
+
"eval_loss": 0.18748582899570465,
|
| 784 |
+
"eval_runtime": 190.7875,
|
| 785 |
+
"eval_samples_per_second": 25.384,
|
| 786 |
+
"eval_steps_per_second": 0.797,
|
| 787 |
+
"eval_wer": 0.17042293499858074,
|
| 788 |
+
"step": 2000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 22.2,
|
| 792 |
+
"learning_rate": 0.00024803921568627453,
|
| 793 |
+
"loss": 0.9624,
|
| 794 |
+
"step": 2020
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 22.42,
|
| 798 |
+
"learning_rate": 0.000246078431372549,
|
| 799 |
+
"loss": 0.9419,
|
| 800 |
+
"step": 2040
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 22.63,
|
| 804 |
+
"learning_rate": 0.00024411764705882354,
|
| 805 |
+
"loss": 0.9563,
|
| 806 |
+
"step": 2060
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 22.85,
|
| 810 |
+
"learning_rate": 0.00024215686274509804,
|
| 811 |
+
"loss": 0.9643,
|
| 812 |
+
"step": 2080
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 23.08,
|
| 816 |
+
"learning_rate": 0.00024019607843137256,
|
| 817 |
+
"loss": 0.9616,
|
| 818 |
+
"step": 2100
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 23.08,
|
| 822 |
+
"eval_loss": 0.18017500638961792,
|
| 823 |
+
"eval_runtime": 191.3932,
|
| 824 |
+
"eval_samples_per_second": 25.304,
|
| 825 |
+
"eval_steps_per_second": 0.794,
|
| 826 |
+
"eval_wer": 0.16173715583309678,
|
| 827 |
+
"step": 2100
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 23.3,
|
| 831 |
+
"learning_rate": 0.00023823529411764704,
|
| 832 |
+
"loss": 0.917,
|
| 833 |
+
"step": 2120
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 23.51,
|
| 837 |
+
"learning_rate": 0.00023627450980392157,
|
| 838 |
+
"loss": 0.945,
|
| 839 |
+
"step": 2140
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 23.73,
|
| 843 |
+
"learning_rate": 0.0002343137254901961,
|
| 844 |
+
"loss": 0.9243,
|
| 845 |
+
"step": 2160
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 23.95,
|
| 849 |
+
"learning_rate": 0.0002323529411764706,
|
| 850 |
+
"loss": 0.9288,
|
| 851 |
+
"step": 2180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 24.17,
|
| 855 |
+
"learning_rate": 0.0002303921568627451,
|
| 856 |
+
"loss": 0.9378,
|
| 857 |
+
"step": 2200
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 24.17,
|
| 861 |
+
"eval_loss": 0.17928896844387054,
|
| 862 |
+
"eval_runtime": 189.7619,
|
| 863 |
+
"eval_samples_per_second": 25.521,
|
| 864 |
+
"eval_steps_per_second": 0.801,
|
| 865 |
+
"eval_wer": 0.1577348850411581,
|
| 866 |
+
"step": 2200
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 24.39,
|
| 870 |
+
"learning_rate": 0.0002284313725490196,
|
| 871 |
+
"loss": 0.9071,
|
| 872 |
+
"step": 2220
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 24.61,
|
| 876 |
+
"learning_rate": 0.00022647058823529412,
|
| 877 |
+
"loss": 0.9054,
|
| 878 |
+
"step": 2240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 24.83,
|
| 882 |
+
"learning_rate": 0.0002246078431372549,
|
| 883 |
+
"loss": 0.9303,
|
| 884 |
+
"step": 2260
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 25.05,
|
| 888 |
+
"learning_rate": 0.00022264705882352943,
|
| 889 |
+
"loss": 0.9376,
|
| 890 |
+
"step": 2280
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 25.27,
|
| 894 |
+
"learning_rate": 0.0002206862745098039,
|
| 895 |
+
"loss": 0.888,
|
| 896 |
+
"step": 2300
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 25.27,
|
| 900 |
+
"eval_loss": 0.17642559111118317,
|
| 901 |
+
"eval_runtime": 187.0437,
|
| 902 |
+
"eval_samples_per_second": 25.892,
|
| 903 |
+
"eval_steps_per_second": 0.813,
|
| 904 |
+
"eval_wer": 0.15452739142776042,
|
| 905 |
+
"step": 2300
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 25.49,
|
| 909 |
+
"learning_rate": 0.00021872549019607843,
|
| 910 |
+
"loss": 0.9135,
|
| 911 |
+
"step": 2320
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 25.71,
|
| 915 |
+
"learning_rate": 0.00021676470588235294,
|
| 916 |
+
"loss": 0.9094,
|
| 917 |
+
"step": 2340
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 25.93,
|
| 921 |
+
"learning_rate": 0.00021480392156862746,
|
| 922 |
+
"loss": 0.8879,
|
| 923 |
+
"step": 2360
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 26.15,
|
| 927 |
+
"learning_rate": 0.00021284313725490196,
|
| 928 |
+
"loss": 0.929,
|
| 929 |
+
"step": 2380
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 26.37,
|
| 933 |
+
"learning_rate": 0.00021088235294117647,
|
| 934 |
+
"loss": 0.8942,
|
| 935 |
+
"step": 2400
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 26.37,
|
| 939 |
+
"eval_loss": 0.16744859516620636,
|
| 940 |
+
"eval_runtime": 190.6796,
|
| 941 |
+
"eval_samples_per_second": 25.399,
|
| 942 |
+
"eval_steps_per_second": 0.797,
|
| 943 |
+
"eval_wer": 0.14916264547260857,
|
| 944 |
+
"step": 2400
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 26.59,
|
| 948 |
+
"learning_rate": 0.000208921568627451,
|
| 949 |
+
"loss": 0.8717,
|
| 950 |
+
"step": 2420
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 26.81,
|
| 954 |
+
"learning_rate": 0.0002069607843137255,
|
| 955 |
+
"loss": 0.8952,
|
| 956 |
+
"step": 2440
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 27.03,
|
| 960 |
+
"learning_rate": 0.000205,
|
| 961 |
+
"loss": 0.8849,
|
| 962 |
+
"step": 2460
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 27.25,
|
| 966 |
+
"learning_rate": 0.00020313725490196078,
|
| 967 |
+
"loss": 0.8781,
|
| 968 |
+
"step": 2480
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 27.47,
|
| 972 |
+
"learning_rate": 0.0002011764705882353,
|
| 973 |
+
"loss": 0.8701,
|
| 974 |
+
"step": 2500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 27.47,
|
| 978 |
+
"eval_loss": 0.1738910973072052,
|
| 979 |
+
"eval_runtime": 187.7205,
|
| 980 |
+
"eval_samples_per_second": 25.799,
|
| 981 |
+
"eval_steps_per_second": 0.81,
|
| 982 |
+
"eval_wer": 0.1511779733181947,
|
| 983 |
+
"step": 2500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 27.69,
|
| 987 |
+
"learning_rate": 0.0001992156862745098,
|
| 988 |
+
"loss": 0.8674,
|
| 989 |
+
"step": 2520
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 27.91,
|
| 993 |
+
"learning_rate": 0.00019725490196078433,
|
| 994 |
+
"loss": 0.8752,
|
| 995 |
+
"step": 2540
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 28.13,
|
| 999 |
+
"learning_rate": 0.0001952941176470588,
|
| 1000 |
+
"loss": 0.91,
|
| 1001 |
+
"step": 2560
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 28.35,
|
| 1005 |
+
"learning_rate": 0.00019333333333333333,
|
| 1006 |
+
"loss": 0.8693,
|
| 1007 |
+
"step": 2580
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 28.57,
|
| 1011 |
+
"learning_rate": 0.00019137254901960786,
|
| 1012 |
+
"loss": 0.8555,
|
| 1013 |
+
"step": 2600
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 28.57,
|
| 1017 |
+
"eval_loss": 0.1689654141664505,
|
| 1018 |
+
"eval_runtime": 196.2665,
|
| 1019 |
+
"eval_samples_per_second": 24.676,
|
| 1020 |
+
"eval_steps_per_second": 0.774,
|
| 1021 |
+
"eval_wer": 0.14459267669599773,
|
| 1022 |
+
"step": 2600
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 28.79,
|
| 1026 |
+
"learning_rate": 0.00018941176470588236,
|
| 1027 |
+
"loss": 0.8796,
|
| 1028 |
+
"step": 2620
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 29.01,
|
| 1032 |
+
"learning_rate": 0.00018745098039215686,
|
| 1033 |
+
"loss": 0.9045,
|
| 1034 |
+
"step": 2640
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 29.23,
|
| 1038 |
+
"learning_rate": 0.00018549019607843137,
|
| 1039 |
+
"loss": 0.8515,
|
| 1040 |
+
"step": 2660
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 29.45,
|
| 1044 |
+
"learning_rate": 0.0001835294117647059,
|
| 1045 |
+
"loss": 0.861,
|
| 1046 |
+
"step": 2680
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 29.67,
|
| 1050 |
+
"learning_rate": 0.0001815686274509804,
|
| 1051 |
+
"loss": 0.8513,
|
| 1052 |
+
"step": 2700
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 29.67,
|
| 1056 |
+
"eval_loss": 0.16488835215568542,
|
| 1057 |
+
"eval_runtime": 189.1938,
|
| 1058 |
+
"eval_samples_per_second": 25.598,
|
| 1059 |
+
"eval_steps_per_second": 0.803,
|
| 1060 |
+
"eval_wer": 0.14774340051092819,
|
| 1061 |
+
"step": 2700
|
| 1062 |
}
|
| 1063 |
],
|
| 1064 |
"max_steps": 4550,
|
| 1065 |
"num_train_epochs": 50,
|
| 1066 |
+
"total_flos": 4.176183820424104e+19,
|
| 1067 |
"trial_name": null,
|
| 1068 |
"trial_params": null
|
| 1069 |
}
|
{checkpoint-1600 → checkpoint-2700}/training_args.bin
RENAMED
|
File without changes
|