Commit
•
e2a01cb
1
Parent(s):
e41d355
End of training
Browse files- .ipynb_checkpoints/all_results-checkpoint.json +14 -0
- .ipynb_checkpoints/eval_results-checkpoint.json +9 -0
- all_results.json +10 -10
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/Feb04_14-58-29_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643989411.job-336a688f-553a-4e6e-83b3-ad5d10274b51.728502.0 +2 -2
- runs/Feb04_14-58-29_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1644061137.job-336a688f-553a-4e6e-83b3-ad5d10274b51.728502.2 +3 -0
- train_results.json +5 -5
- trainer_state.json +267 -12
.ipynb_checkpoints/all_results-checkpoint.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 12.0,
|
| 3 |
+
"eval_loss": 0.25491979718208313,
|
| 4 |
+
"eval_runtime": 392.0567,
|
| 5 |
+
"eval_samples": 4297,
|
| 6 |
+
"eval_samples_per_second": 10.96,
|
| 7 |
+
"eval_steps_per_second": 0.344,
|
| 8 |
+
"eval_wer": 0.15725760362438562,
|
| 9 |
+
"train_loss": 0.5676147035501541,
|
| 10 |
+
"train_runtime": 172546.67,
|
| 11 |
+
"train_samples": 240334,
|
| 12 |
+
"train_samples_per_second": 16.714,
|
| 13 |
+
"train_steps_per_second": 0.131
|
| 14 |
+
}
|
.ipynb_checkpoints/eval_results-checkpoint.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 12.0,
|
| 3 |
+
"eval_loss": 0.25491979718208313,
|
| 4 |
+
"eval_runtime": 392.0567,
|
| 5 |
+
"eval_samples": 4297,
|
| 6 |
+
"eval_samples_per_second": 10.96,
|
| 7 |
+
"eval_steps_per_second": 0.344,
|
| 8 |
+
"eval_wer": 0.15725760362438562
|
| 9 |
+
}
|
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 4297,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
-
"eval_wer": 0.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 240334,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second": 0.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 18.0,
|
| 3 |
+
"eval_loss": 0.2472492903470993,
|
| 4 |
+
"eval_runtime": 373.4142,
|
| 5 |
"eval_samples": 4297,
|
| 6 |
+
"eval_samples_per_second": 11.507,
|
| 7 |
+
"eval_steps_per_second": 0.362,
|
| 8 |
+
"eval_wer": 0.14990076581772083,
|
| 9 |
+
"train_loss": 0.16521977071390054,
|
| 10 |
+
"train_runtime": 71350.5908,
|
| 11 |
"train_samples": 240334,
|
| 12 |
+
"train_samples_per_second": 60.63,
|
| 13 |
+
"train_steps_per_second": 0.474
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 4297,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
-
"eval_wer": 0.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 18.0,
|
| 3 |
+
"eval_loss": 0.2472492903470993,
|
| 4 |
+
"eval_runtime": 373.4142,
|
| 5 |
"eval_samples": 4297,
|
| 6 |
+
"eval_samples_per_second": 11.507,
|
| 7 |
+
"eval_steps_per_second": 0.362,
|
| 8 |
+
"eval_wer": 0.14990076581772083
|
| 9 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262112241
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:382829868e73fa85ab4aea6f9cfa1e2258955546556cfbc4c1aa0ac435d86981
|
| 3 |
size 1262112241
|
runs/Feb04_14-58-29_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643989411.job-336a688f-553a-4e6e-83b3-ad5d10274b51.728502.0
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 sha256:7dd620d37e0221c513ea85f339709d22725b2e11e30fd5c4c973ce761b4e5e24
|
| 3 |
+
size 7529
|
runs/Feb04_14-58-29_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1644061137.job-336a688f-553a-4e6e-83b3-ad5d10274b51.728502.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ba70b885ace8400ed4e1f00fd81e27187a8a5dabaf13d4b441e91a0dff4eb3c
|
| 3 |
+
size 364
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 240334,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 18.0,
|
| 3 |
+
"train_loss": 0.16521977071390054,
|
| 4 |
+
"train_runtime": 71350.5908,
|
| 5 |
"train_samples": 240334,
|
| 6 |
+
"train_samples_per_second": 60.63,
|
| 7 |
+
"train_steps_per_second": 0.474
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -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,
|
|
@@ -683,18 +683,273 @@
|
|
| 683 |
"step": 22500
|
| 684 |
},
|
| 685 |
{
|
| 686 |
-
"epoch": 12.
|
| 687 |
-
"
|
| 688 |
-
"
|
| 689 |
-
"
|
| 690 |
-
|
| 691 |
-
|
| 692 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 693 |
}
|
| 694 |
],
|
| 695 |
-
"max_steps":
|
| 696 |
-
"num_train_epochs":
|
| 697 |
-
"total_flos":
|
| 698 |
"trial_name": null,
|
| 699 |
"trial_params": null
|
| 700 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 17.99960058580748,
|
| 5 |
+
"global_step": 33786,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 683 |
"step": 22500
|
| 684 |
},
|
| 685 |
{
|
| 686 |
+
"epoch": 12.25,
|
| 687 |
+
"learning_rate": 2.5471119360724847e-05,
|
| 688 |
+
"loss": 1.0835,
|
| 689 |
+
"step": 23000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 12.25,
|
| 693 |
+
"eval_loss": 0.25863561034202576,
|
| 694 |
+
"eval_runtime": 369.3533,
|
| 695 |
+
"eval_samples_per_second": 11.634,
|
| 696 |
+
"eval_steps_per_second": 0.366,
|
| 697 |
+
"eval_wer": 0.15212444278188222,
|
| 698 |
+
"step": 23000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 12.52,
|
| 702 |
+
"learning_rate": 2.4293714213804817e-05,
|
| 703 |
+
"loss": 1.0883,
|
| 704 |
+
"step": 23500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 12.52,
|
| 708 |
+
"eval_loss": 0.25827670097351074,
|
| 709 |
+
"eval_runtime": 370.2467,
|
| 710 |
+
"eval_samples_per_second": 11.606,
|
| 711 |
+
"eval_steps_per_second": 0.365,
|
| 712 |
+
"eval_wer": 0.15193740453256024,
|
| 713 |
+
"step": 23500
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 12.79,
|
| 717 |
+
"learning_rate": 2.3113949537532244e-05,
|
| 718 |
+
"loss": 1.0888,
|
| 719 |
+
"step": 24000
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 12.79,
|
| 723 |
+
"eval_loss": 0.2551300823688507,
|
| 724 |
+
"eval_runtime": 367.9843,
|
| 725 |
+
"eval_samples_per_second": 11.677,
|
| 726 |
+
"eval_steps_per_second": 0.367,
|
| 727 |
+
"eval_wer": 0.15819279487099555,
|
| 728 |
+
"step": 24000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 13.05,
|
| 732 |
+
"learning_rate": 2.1934184861259672e-05,
|
| 733 |
+
"loss": 1.0933,
|
| 734 |
+
"step": 24500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 13.05,
|
| 738 |
+
"eval_loss": 0.2628032863140106,
|
| 739 |
+
"eval_runtime": 369.9671,
|
| 740 |
+
"eval_samples_per_second": 11.615,
|
| 741 |
+
"eval_steps_per_second": 0.365,
|
| 742 |
+
"eval_wer": 0.1537142679011191,
|
| 743 |
+
"step": 24500
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 13.32,
|
| 747 |
+
"learning_rate": 2.07544201849871e-05,
|
| 748 |
+
"loss": 1.0799,
|
| 749 |
+
"step": 25000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 13.32,
|
| 753 |
+
"eval_loss": 0.2600410580635071,
|
| 754 |
+
"eval_runtime": 374.9827,
|
| 755 |
+
"eval_samples_per_second": 11.459,
|
| 756 |
+
"eval_steps_per_second": 0.36,
|
| 757 |
+
"eval_wer": 0.150752828953521,
|
| 758 |
+
"step": 25000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 13.59,
|
| 762 |
+
"learning_rate": 1.957701503806707e-05,
|
| 763 |
+
"loss": 1.0804,
|
| 764 |
+
"step": 25500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 13.59,
|
| 768 |
+
"eval_loss": 0.26200664043426514,
|
| 769 |
+
"eval_runtime": 369.1646,
|
| 770 |
+
"eval_samples_per_second": 11.64,
|
| 771 |
+
"eval_steps_per_second": 0.366,
|
| 772 |
+
"eval_wer": 0.14753161465964235,
|
| 773 |
+
"step": 25500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 13.85,
|
| 777 |
+
"learning_rate": 1.8397250361794498e-05,
|
| 778 |
+
"loss": 1.0814,
|
| 779 |
+
"step": 26000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 13.85,
|
| 783 |
+
"eval_loss": 0.2537305951118469,
|
| 784 |
+
"eval_runtime": 368.6655,
|
| 785 |
+
"eval_samples_per_second": 11.656,
|
| 786 |
+
"eval_steps_per_second": 0.366,
|
| 787 |
+
"eval_wer": 0.15170880222783337,
|
| 788 |
+
"step": 26000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 14.12,
|
| 792 |
+
"learning_rate": 1.7217485685521926e-05,
|
| 793 |
+
"loss": 1.0693,
|
| 794 |
+
"step": 26500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 14.12,
|
| 798 |
+
"eval_loss": 0.25602129101753235,
|
| 799 |
+
"eval_runtime": 368.3159,
|
| 800 |
+
"eval_samples_per_second": 11.667,
|
| 801 |
+
"eval_steps_per_second": 0.367,
|
| 802 |
+
"eval_wer": 0.15421303656597773,
|
| 803 |
+
"step": 26500
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 14.38,
|
| 807 |
+
"learning_rate": 1.6037721009249354e-05,
|
| 808 |
+
"loss": 1.0724,
|
| 809 |
+
"step": 27000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 14.38,
|
| 813 |
+
"eval_loss": 0.2540068030357361,
|
| 814 |
+
"eval_runtime": 369.0094,
|
| 815 |
+
"eval_samples_per_second": 11.645,
|
| 816 |
+
"eval_steps_per_second": 0.366,
|
| 817 |
+
"eval_wer": 0.15736151376289784,
|
| 818 |
+
"step": 27000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 14.65,
|
| 822 |
+
"learning_rate": 1.4857956332976782e-05,
|
| 823 |
+
"loss": 1.0704,
|
| 824 |
+
"step": 27500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 14.65,
|
| 828 |
+
"eval_loss": 0.25483617186546326,
|
| 829 |
+
"eval_runtime": 365.0658,
|
| 830 |
+
"eval_samples_per_second": 11.77,
|
| 831 |
+
"eval_steps_per_second": 0.37,
|
| 832 |
+
"eval_wer": 0.16258819373006225,
|
| 833 |
+
"step": 27500
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 14.92,
|
| 837 |
+
"learning_rate": 1.3678191656704208e-05,
|
| 838 |
+
"loss": 1.0729,
|
| 839 |
+
"step": 28000
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 14.92,
|
| 843 |
+
"eval_loss": 0.254844069480896,
|
| 844 |
+
"eval_runtime": 367.5842,
|
| 845 |
+
"eval_samples_per_second": 11.69,
|
| 846 |
+
"eval_steps_per_second": 0.367,
|
| 847 |
+
"eval_wer": 0.16009435040576908,
|
| 848 |
+
"step": 28000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 15.18,
|
| 852 |
+
"learning_rate": 1.2498426980431636e-05,
|
| 853 |
+
"loss": 1.0724,
|
| 854 |
+
"step": 28500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 15.18,
|
| 858 |
+
"eval_loss": 0.25110504031181335,
|
| 859 |
+
"eval_runtime": 367.3861,
|
| 860 |
+
"eval_samples_per_second": 11.696,
|
| 861 |
+
"eval_steps_per_second": 0.367,
|
| 862 |
+
"eval_wer": 0.15124120660452842,
|
| 863 |
+
"step": 28500
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 15.45,
|
| 867 |
+
"learning_rate": 1.1318662304159062e-05,
|
| 868 |
+
"loss": 1.0655,
|
| 869 |
+
"step": 29000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 15.45,
|
| 873 |
+
"eval_loss": 0.24978148937225342,
|
| 874 |
+
"eval_runtime": 375.4183,
|
| 875 |
+
"eval_samples_per_second": 11.446,
|
| 876 |
+
"eval_steps_per_second": 0.36,
|
| 877 |
+
"eval_wer": 0.14903831166806944,
|
| 878 |
+
"step": 29000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 15.98,
|
| 882 |
+
"learning_rate": 8.963852010319007e-06,
|
| 883 |
+
"loss": 1.0608,
|
| 884 |
+
"step": 30000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 15.98,
|
| 888 |
+
"eval_loss": 0.24873663485050201,
|
| 889 |
+
"eval_runtime": 370.6074,
|
| 890 |
+
"eval_samples_per_second": 11.594,
|
| 891 |
+
"eval_steps_per_second": 0.364,
|
| 892 |
+
"eval_wer": 0.14812390244916196,
|
| 893 |
+
"step": 30000
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 16.52,
|
| 897 |
+
"learning_rate": 6.604322657773862e-06,
|
| 898 |
+
"loss": 1.0541,
|
| 899 |
+
"step": 31000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 16.52,
|
| 903 |
+
"eval_loss": 0.2467627078294754,
|
| 904 |
+
"eval_runtime": 371.5001,
|
| 905 |
+
"eval_samples_per_second": 11.567,
|
| 906 |
+
"eval_steps_per_second": 0.363,
|
| 907 |
+
"eval_wer": 0.15039953448257948,
|
| 908 |
+
"step": 31000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 17.05,
|
| 912 |
+
"learning_rate": 4.244793305228717e-06,
|
| 913 |
+
"loss": 1.0584,
|
| 914 |
+
"step": 32000
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 17.05,
|
| 918 |
+
"eval_loss": 0.2466605007648468,
|
| 919 |
+
"eval_runtime": 370.8863,
|
| 920 |
+
"eval_samples_per_second": 11.586,
|
| 921 |
+
"eval_steps_per_second": 0.364,
|
| 922 |
+
"eval_wer": 0.1493084780282012,
|
| 923 |
+
"step": 32000
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 17.58,
|
| 927 |
+
"learning_rate": 1.8852639526835713e-06,
|
| 928 |
+
"loss": 1.0507,
|
| 929 |
+
"step": 33000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 17.58,
|
| 933 |
+
"eval_loss": 0.2480592578649521,
|
| 934 |
+
"eval_runtime": 373.0281,
|
| 935 |
+
"eval_samples_per_second": 11.519,
|
| 936 |
+
"eval_steps_per_second": 0.362,
|
| 937 |
+
"eval_wer": 0.15173997526938704,
|
| 938 |
+
"step": 33000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 18.0,
|
| 942 |
+
"step": 33786,
|
| 943 |
+
"total_flos": 9.499341430600616e+20,
|
| 944 |
+
"train_loss": 0.16521977071390054,
|
| 945 |
+
"train_runtime": 71350.5908,
|
| 946 |
+
"train_samples_per_second": 60.63,
|
| 947 |
+
"train_steps_per_second": 0.474
|
| 948 |
}
|
| 949 |
],
|
| 950 |
+
"max_steps": 33786,
|
| 951 |
+
"num_train_epochs": 18,
|
| 952 |
+
"total_flos": 9.499341430600616e+20,
|
| 953 |
"trial_name": null,
|
| 954 |
"trial_params": null
|
| 955 |
}
|