"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/trainer_state.json +164 -5
- model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629851520.6004615/events.out.tfevents.1629851520.7e498afd5545.905.1 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629851520.7e498afd5545.905.0 +3 -0
model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 722165393
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77022871d4d16e1a6abf7862c31f887bf686b21ff263b353dacc9bf8a7185f44
|
| 3 |
size 722165393
|
model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377909911
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2416f58e079fdfb65089d7ccf515e39a6055d0689ca3b35a02f39e7d4a0e1312
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fafcc65abfd4682ae095ab576326a5af3fb802a7266c4ec486940e474dbaff42
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/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 sha256:33966f27faae6e899c84739e9e14c43c7026dc7d03c59a6b5b5d53c1d7cd8e27
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/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 sha256:9192f137391547b40811c289ac77fff24076f09eac9bbc72de295bb8bfd8c024
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -187716,11 +187716,170 @@
|
|
| 187716 |
"eval_steps_per_second": 0.664,
|
| 187717 |
"eval_wer": 0.18589017831870933,
|
| 187718 |
"step": 69440
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 187719 |
}
|
| 187720 |
],
|
| 187721 |
"max_steps": 625000,
|
| 187722 |
"num_train_epochs": 5000,
|
| 187723 |
-
"total_flos": 1.
|
| 187724 |
"trial_name": null,
|
| 187725 |
"trial_params": null
|
| 187726 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.18412114350410416,
|
| 3 |
+
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-69565",
|
| 4 |
+
"epoch": 556.0,
|
| 5 |
+
"global_step": 69565,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 187716 |
"eval_steps_per_second": 0.664,
|
| 187717 |
"eval_wer": 0.18589017831870933,
|
| 187718 |
"step": 69440
|
| 187719 |
+
},
|
| 187720 |
+
{
|
| 187721 |
+
"epoch": 555.04,
|
| 187722 |
+
"learning_rate": 8.903541666666667e-06,
|
| 187723 |
+
"loss": 0.376,
|
| 187724 |
+
"step": 69445
|
| 187725 |
+
},
|
| 187726 |
+
{
|
| 187727 |
+
"epoch": 555.08,
|
| 187728 |
+
"learning_rate": 8.90346153846154e-06,
|
| 187729 |
+
"loss": 0.2794,
|
| 187730 |
+
"step": 69450
|
| 187731 |
+
},
|
| 187732 |
+
{
|
| 187733 |
+
"epoch": 555.12,
|
| 187734 |
+
"learning_rate": 8.903381410256412e-06,
|
| 187735 |
+
"loss": 0.4327,
|
| 187736 |
+
"step": 69455
|
| 187737 |
+
},
|
| 187738 |
+
{
|
| 187739 |
+
"epoch": 555.16,
|
| 187740 |
+
"learning_rate": 8.903301282051283e-06,
|
| 187741 |
+
"loss": 0.6141,
|
| 187742 |
+
"step": 69460
|
| 187743 |
+
},
|
| 187744 |
+
{
|
| 187745 |
+
"epoch": 555.2,
|
| 187746 |
+
"learning_rate": 8.903221153846154e-06,
|
| 187747 |
+
"loss": 1.2486,
|
| 187748 |
+
"step": 69465
|
| 187749 |
+
},
|
| 187750 |
+
{
|
| 187751 |
+
"epoch": 555.24,
|
| 187752 |
+
"learning_rate": 8.903141025641027e-06,
|
| 187753 |
+
"loss": 0.5636,
|
| 187754 |
+
"step": 69470
|
| 187755 |
+
},
|
| 187756 |
+
{
|
| 187757 |
+
"epoch": 555.28,
|
| 187758 |
+
"learning_rate": 8.903060897435899e-06,
|
| 187759 |
+
"loss": 0.2681,
|
| 187760 |
+
"step": 69475
|
| 187761 |
+
},
|
| 187762 |
+
{
|
| 187763 |
+
"epoch": 555.32,
|
| 187764 |
+
"learning_rate": 8.90298076923077e-06,
|
| 187765 |
+
"loss": 0.3946,
|
| 187766 |
+
"step": 69480
|
| 187767 |
+
},
|
| 187768 |
+
{
|
| 187769 |
+
"epoch": 555.36,
|
| 187770 |
+
"learning_rate": 8.902900641025641e-06,
|
| 187771 |
+
"loss": 0.4832,
|
| 187772 |
+
"step": 69485
|
| 187773 |
+
},
|
| 187774 |
+
{
|
| 187775 |
+
"epoch": 555.4,
|
| 187776 |
+
"learning_rate": 8.902820512820514e-06,
|
| 187777 |
+
"loss": 1.2986,
|
| 187778 |
+
"step": 69490
|
| 187779 |
+
},
|
| 187780 |
+
{
|
| 187781 |
+
"epoch": 555.44,
|
| 187782 |
+
"learning_rate": 8.902740384615384e-06,
|
| 187783 |
+
"loss": 0.6412,
|
| 187784 |
+
"step": 69495
|
| 187785 |
+
},
|
| 187786 |
+
{
|
| 187787 |
+
"epoch": 555.48,
|
| 187788 |
+
"learning_rate": 8.902660256410257e-06,
|
| 187789 |
+
"loss": 0.3092,
|
| 187790 |
+
"step": 69500
|
| 187791 |
+
},
|
| 187792 |
+
{
|
| 187793 |
+
"epoch": 555.52,
|
| 187794 |
+
"learning_rate": 8.90258012820513e-06,
|
| 187795 |
+
"loss": 0.3213,
|
| 187796 |
+
"step": 69505
|
| 187797 |
+
},
|
| 187798 |
+
{
|
| 187799 |
+
"epoch": 555.56,
|
| 187800 |
+
"learning_rate": 8.9025e-06,
|
| 187801 |
+
"loss": 0.5671,
|
| 187802 |
+
"step": 69510
|
| 187803 |
+
},
|
| 187804 |
+
{
|
| 187805 |
+
"epoch": 555.6,
|
| 187806 |
+
"learning_rate": 8.902419871794873e-06,
|
| 187807 |
+
"loss": 1.5722,
|
| 187808 |
+
"step": 69515
|
| 187809 |
+
},
|
| 187810 |
+
{
|
| 187811 |
+
"epoch": 555.64,
|
| 187812 |
+
"learning_rate": 8.902339743589744e-06,
|
| 187813 |
+
"loss": 0.3612,
|
| 187814 |
+
"step": 69520
|
| 187815 |
+
},
|
| 187816 |
+
{
|
| 187817 |
+
"epoch": 555.68,
|
| 187818 |
+
"learning_rate": 8.902259615384616e-06,
|
| 187819 |
+
"loss": 0.3524,
|
| 187820 |
+
"step": 69525
|
| 187821 |
+
},
|
| 187822 |
+
{
|
| 187823 |
+
"epoch": 555.72,
|
| 187824 |
+
"learning_rate": 8.902179487179487e-06,
|
| 187825 |
+
"loss": 0.3638,
|
| 187826 |
+
"step": 69530
|
| 187827 |
+
},
|
| 187828 |
+
{
|
| 187829 |
+
"epoch": 555.76,
|
| 187830 |
+
"learning_rate": 8.90209935897436e-06,
|
| 187831 |
+
"loss": 0.5201,
|
| 187832 |
+
"step": 69535
|
| 187833 |
+
},
|
| 187834 |
+
{
|
| 187835 |
+
"epoch": 555.8,
|
| 187836 |
+
"learning_rate": 8.902019230769231e-06,
|
| 187837 |
+
"loss": 1.2726,
|
| 187838 |
+
"step": 69540
|
| 187839 |
+
},
|
| 187840 |
+
{
|
| 187841 |
+
"epoch": 555.84,
|
| 187842 |
+
"learning_rate": 8.901939102564103e-06,
|
| 187843 |
+
"loss": 0.3403,
|
| 187844 |
+
"step": 69545
|
| 187845 |
+
},
|
| 187846 |
+
{
|
| 187847 |
+
"epoch": 555.88,
|
| 187848 |
+
"learning_rate": 8.901858974358976e-06,
|
| 187849 |
+
"loss": 0.364,
|
| 187850 |
+
"step": 69550
|
| 187851 |
+
},
|
| 187852 |
+
{
|
| 187853 |
+
"epoch": 555.92,
|
| 187854 |
+
"learning_rate": 8.901778846153847e-06,
|
| 187855 |
+
"loss": 0.3376,
|
| 187856 |
+
"step": 69555
|
| 187857 |
+
},
|
| 187858 |
+
{
|
| 187859 |
+
"epoch": 555.96,
|
| 187860 |
+
"learning_rate": 8.901698717948719e-06,
|
| 187861 |
+
"loss": 0.504,
|
| 187862 |
+
"step": 69560
|
| 187863 |
+
},
|
| 187864 |
+
{
|
| 187865 |
+
"epoch": 556.0,
|
| 187866 |
+
"learning_rate": 8.90161858974359e-06,
|
| 187867 |
+
"loss": 1.2661,
|
| 187868 |
+
"step": 69565
|
| 187869 |
+
},
|
| 187870 |
+
{
|
| 187871 |
+
"epoch": 556.0,
|
| 187872 |
+
"eval_loss": 0.34267231822013855,
|
| 187873 |
+
"eval_runtime": 39.6183,
|
| 187874 |
+
"eval_samples_per_second": 21.177,
|
| 187875 |
+
"eval_steps_per_second": 0.682,
|
| 187876 |
+
"eval_wer": 0.18412114350410416,
|
| 187877 |
+
"step": 69565
|
| 187878 |
}
|
| 187879 |
],
|
| 187880 |
"max_steps": 625000,
|
| 187881 |
"num_train_epochs": 5000,
|
| 187882 |
+
"total_flos": 1.9576033736107534e+20,
|
| 187883 |
"trial_name": null,
|
| 187884 |
"trial_params": null
|
| 187885 |
}
|
model-bin/finetune/base/{checkpoint-69440 β checkpoint-69565}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629851520.6004615/events.out.tfevents.1629851520.7e498afd5545.905.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df03764ecf32460054f69f5d503526a64a8429c13994ba3135af14cc290b9afb
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629851520.7e498afd5545.905.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f68a8f0b376ef8c770384e82f52f97295dec22990c7aa120f3a13d5b71722791
|
| 3 |
+
size 8630
|