"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/trainer_state.json +421 -4
- model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629665002.2003953/events.out.tfevents.1629665002.91f414e9573a.903.221 +3 -0
- model-bin/finetune/base/log/1629665657.2222176/events.out.tfevents.1629665657.91f414e9573a.903.223 +3 -0
- model-bin/finetune/base/log/1629666308.4602919/events.out.tfevents.1629666308.91f414e9573a.903.225 +3 -0
- model-bin/finetune/base/log/1629666956.4992223/events.out.tfevents.1629666956.91f414e9573a.903.227 +3 -0
- model-bin/finetune/base/log/1629667615.440723/events.out.tfevents.1629667615.91f414e9573a.903.229 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629665002.91f414e9573a.903.220 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629665657.91f414e9573a.903.222 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629666308.91f414e9573a.903.224 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629666956.91f414e9573a.903.226 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629667615.91f414e9573a.903.228 +3 -0
model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 722165009
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a5d5e61443ff9a117138ad14388b1199f53558c65299d7bd6ba82dc660af1ce
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/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 sha256:00fb5eba330032b566647cbeac61302e6032883e818a2ad93e204a6a023e1078
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/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:b27d5f48b836ef02b73c13604c4518fbbc1b9d743315b636f987ce4d073ff465
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/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 sha256:56214a05319eef06e28daac562558da51b9a0135e1dc7ebabafe1e6d95c55fad
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/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:f6628287393478d3ea6c80d0fcc8f9cce9e1b4d914e5b5a063bce178a7575a35
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.20553532410779315,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-31352",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -146712,11 +146712,428 @@
|
|
| 146712 |
"eval_steps_per_second": 0.693,
|
| 146713 |
"eval_wer": 0.21878310882397456,
|
| 146714 |
"step": 36333
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146715 |
}
|
| 146716 |
],
|
| 146717 |
-
"max_steps":
|
| 146718 |
"num_train_epochs": 5000,
|
| 146719 |
-
"total_flos": 1.
|
| 146720 |
"trial_name": null,
|
| 146721 |
"trial_params": null
|
| 146722 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.20553532410779315,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-31352",
|
| 4 |
+
"epoch": 295.0,
|
| 5 |
+
"global_step": 36957,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 146712 |
"eval_steps_per_second": 0.693,
|
| 146713 |
"eval_wer": 0.21878310882397456,
|
| 146714 |
"step": 36333
|
| 146715 |
+
},
|
| 146716 |
+
{
|
| 146717 |
+
"epoch": 293.06,
|
| 146718 |
+
"learning_rate": 9.429289176090468e-06,
|
| 146719 |
+
"loss": 0.3878,
|
| 146720 |
+
"step": 36340
|
| 146721 |
+
},
|
| 146722 |
+
{
|
| 146723 |
+
"epoch": 293.14,
|
| 146724 |
+
"learning_rate": 9.42912762520194e-06,
|
| 146725 |
+
"loss": 0.4094,
|
| 146726 |
+
"step": 36350
|
| 146727 |
+
},
|
| 146728 |
+
{
|
| 146729 |
+
"epoch": 293.22,
|
| 146730 |
+
"learning_rate": 9.42896607431341e-06,
|
| 146731 |
+
"loss": 0.994,
|
| 146732 |
+
"step": 36360
|
| 146733 |
+
},
|
| 146734 |
+
{
|
| 146735 |
+
"epoch": 293.3,
|
| 146736 |
+
"learning_rate": 9.42880452342488e-06,
|
| 146737 |
+
"loss": 0.5573,
|
| 146738 |
+
"step": 36370
|
| 146739 |
+
},
|
| 146740 |
+
{
|
| 146741 |
+
"epoch": 293.38,
|
| 146742 |
+
"learning_rate": 9.42864297253635e-06,
|
| 146743 |
+
"loss": 0.7763,
|
| 146744 |
+
"step": 36380
|
| 146745 |
+
},
|
| 146746 |
+
{
|
| 146747 |
+
"epoch": 293.46,
|
| 146748 |
+
"learning_rate": 9.42848142164782e-06,
|
| 146749 |
+
"loss": 0.8797,
|
| 146750 |
+
"step": 36390
|
| 146751 |
+
},
|
| 146752 |
+
{
|
| 146753 |
+
"epoch": 293.54,
|
| 146754 |
+
"learning_rate": 9.42831987075929e-06,
|
| 146755 |
+
"loss": 0.3829,
|
| 146756 |
+
"step": 36400
|
| 146757 |
+
},
|
| 146758 |
+
{
|
| 146759 |
+
"epoch": 293.62,
|
| 146760 |
+
"learning_rate": 9.42815831987076e-06,
|
| 146761 |
+
"loss": 1.0447,
|
| 146762 |
+
"step": 36410
|
| 146763 |
+
},
|
| 146764 |
+
{
|
| 146765 |
+
"epoch": 293.7,
|
| 146766 |
+
"learning_rate": 9.42799676898223e-06,
|
| 146767 |
+
"loss": 0.3371,
|
| 146768 |
+
"step": 36420
|
| 146769 |
+
},
|
| 146770 |
+
{
|
| 146771 |
+
"epoch": 293.78,
|
| 146772 |
+
"learning_rate": 9.4278352180937e-06,
|
| 146773 |
+
"loss": 0.5268,
|
| 146774 |
+
"step": 36430
|
| 146775 |
+
},
|
| 146776 |
+
{
|
| 146777 |
+
"epoch": 293.86,
|
| 146778 |
+
"learning_rate": 9.42767366720517e-06,
|
| 146779 |
+
"loss": 0.6914,
|
| 146780 |
+
"step": 36440
|
| 146781 |
+
},
|
| 146782 |
+
{
|
| 146783 |
+
"epoch": 293.94,
|
| 146784 |
+
"learning_rate": 9.42751211631664e-06,
|
| 146785 |
+
"loss": 0.4328,
|
| 146786 |
+
"step": 36450
|
| 146787 |
+
},
|
| 146788 |
+
{
|
| 146789 |
+
"epoch": 294.0,
|
| 146790 |
+
"eval_loss": 0.41599977016448975,
|
| 146791 |
+
"eval_runtime": 41.3009,
|
| 146792 |
+
"eval_samples_per_second": 20.339,
|
| 146793 |
+
"eval_steps_per_second": 0.654,
|
| 146794 |
+
"eval_wer": 0.21309171597633136,
|
| 146795 |
+
"step": 36457
|
| 146796 |
+
},
|
| 146797 |
+
{
|
| 146798 |
+
"epoch": 291.02,
|
| 146799 |
+
"learning_rate": 9.42735056542811e-06,
|
| 146800 |
+
"loss": 0.4333,
|
| 146801 |
+
"step": 36460
|
| 146802 |
+
},
|
| 146803 |
+
{
|
| 146804 |
+
"epoch": 291.1,
|
| 146805 |
+
"learning_rate": 9.42718901453958e-06,
|
| 146806 |
+
"loss": 0.3786,
|
| 146807 |
+
"step": 36470
|
| 146808 |
+
},
|
| 146809 |
+
{
|
| 146810 |
+
"epoch": 291.18,
|
| 146811 |
+
"learning_rate": 9.42702746365105e-06,
|
| 146812 |
+
"loss": 0.5848,
|
| 146813 |
+
"step": 36480
|
| 146814 |
+
},
|
| 146815 |
+
{
|
| 146816 |
+
"epoch": 291.26,
|
| 146817 |
+
"learning_rate": 9.426865912762521e-06,
|
| 146818 |
+
"loss": 0.6391,
|
| 146819 |
+
"step": 36490
|
| 146820 |
+
},
|
| 146821 |
+
{
|
| 146822 |
+
"epoch": 291.34,
|
| 146823 |
+
"learning_rate": 9.426704361873991e-06,
|
| 146824 |
+
"loss": 0.4333,
|
| 146825 |
+
"step": 36500
|
| 146826 |
+
},
|
| 146827 |
+
{
|
| 146828 |
+
"epoch": 291.42,
|
| 146829 |
+
"learning_rate": 9.426542810985461e-06,
|
| 146830 |
+
"loss": 0.9275,
|
| 146831 |
+
"step": 36510
|
| 146832 |
+
},
|
| 146833 |
+
{
|
| 146834 |
+
"epoch": 291.5,
|
| 146835 |
+
"learning_rate": 9.426381260096931e-06,
|
| 146836 |
+
"loss": 0.3723,
|
| 146837 |
+
"step": 36520
|
| 146838 |
+
},
|
| 146839 |
+
{
|
| 146840 |
+
"epoch": 291.58,
|
| 146841 |
+
"learning_rate": 9.426219709208401e-06,
|
| 146842 |
+
"loss": 0.6229,
|
| 146843 |
+
"step": 36530
|
| 146844 |
+
},
|
| 146845 |
+
{
|
| 146846 |
+
"epoch": 291.66,
|
| 146847 |
+
"learning_rate": 9.426058158319871e-06,
|
| 146848 |
+
"loss": 0.7672,
|
| 146849 |
+
"step": 36540
|
| 146850 |
+
},
|
| 146851 |
+
{
|
| 146852 |
+
"epoch": 291.74,
|
| 146853 |
+
"learning_rate": 9.425896607431341e-06,
|
| 146854 |
+
"loss": 0.3943,
|
| 146855 |
+
"step": 36550
|
| 146856 |
+
},
|
| 146857 |
+
{
|
| 146858 |
+
"epoch": 291.82,
|
| 146859 |
+
"learning_rate": 9.425735056542811e-06,
|
| 146860 |
+
"loss": 0.87,
|
| 146861 |
+
"step": 36560
|
| 146862 |
+
},
|
| 146863 |
+
{
|
| 146864 |
+
"epoch": 291.9,
|
| 146865 |
+
"learning_rate": 9.425573505654281e-06,
|
| 146866 |
+
"loss": 0.4,
|
| 146867 |
+
"step": 36570
|
| 146868 |
+
},
|
| 146869 |
+
{
|
| 146870 |
+
"epoch": 291.98,
|
| 146871 |
+
"learning_rate": 9.425411954765751e-06,
|
| 146872 |
+
"loss": 0.792,
|
| 146873 |
+
"step": 36580
|
| 146874 |
+
},
|
| 146875 |
+
{
|
| 146876 |
+
"epoch": 292.0,
|
| 146877 |
+
"eval_loss": 0.48018544912338257,
|
| 146878 |
+
"eval_runtime": 40.6729,
|
| 146879 |
+
"eval_samples_per_second": 20.653,
|
| 146880 |
+
"eval_steps_per_second": 0.664,
|
| 146881 |
+
"eval_wer": 0.21601571023347152,
|
| 146882 |
+
"step": 36582
|
| 146883 |
+
},
|
| 146884 |
+
{
|
| 146885 |
+
"epoch": 292.06,
|
| 146886 |
+
"learning_rate": 9.425250403877221e-06,
|
| 146887 |
+
"loss": 0.4069,
|
| 146888 |
+
"step": 36590
|
| 146889 |
+
},
|
| 146890 |
+
{
|
| 146891 |
+
"epoch": 292.14,
|
| 146892 |
+
"learning_rate": 9.425088852988691e-06,
|
| 146893 |
+
"loss": 0.4469,
|
| 146894 |
+
"step": 36600
|
| 146895 |
+
},
|
| 146896 |
+
{
|
| 146897 |
+
"epoch": 292.22,
|
| 146898 |
+
"learning_rate": 9.424927302100161e-06,
|
| 146899 |
+
"loss": 0.8959,
|
| 146900 |
+
"step": 36610
|
| 146901 |
+
},
|
| 146902 |
+
{
|
| 146903 |
+
"epoch": 292.3,
|
| 146904 |
+
"learning_rate": 9.424765751211633e-06,
|
| 146905 |
+
"loss": 0.3796,
|
| 146906 |
+
"step": 36620
|
| 146907 |
+
},
|
| 146908 |
+
{
|
| 146909 |
+
"epoch": 292.38,
|
| 146910 |
+
"learning_rate": 9.424604200323103e-06,
|
| 146911 |
+
"loss": 0.7193,
|
| 146912 |
+
"step": 36630
|
| 146913 |
+
},
|
| 146914 |
+
{
|
| 146915 |
+
"epoch": 292.46,
|
| 146916 |
+
"learning_rate": 9.424442649434573e-06,
|
| 146917 |
+
"loss": 0.6228,
|
| 146918 |
+
"step": 36640
|
| 146919 |
+
},
|
| 146920 |
+
{
|
| 146921 |
+
"epoch": 292.54,
|
| 146922 |
+
"learning_rate": 9.424281098546043e-06,
|
| 146923 |
+
"loss": 0.453,
|
| 146924 |
+
"step": 36650
|
| 146925 |
+
},
|
| 146926 |
+
{
|
| 146927 |
+
"epoch": 292.62,
|
| 146928 |
+
"learning_rate": 9.424119547657513e-06,
|
| 146929 |
+
"loss": 0.9797,
|
| 146930 |
+
"step": 36660
|
| 146931 |
+
},
|
| 146932 |
+
{
|
| 146933 |
+
"epoch": 292.7,
|
| 146934 |
+
"learning_rate": 9.423957996768983e-06,
|
| 146935 |
+
"loss": 0.3778,
|
| 146936 |
+
"step": 36670
|
| 146937 |
+
},
|
| 146938 |
+
{
|
| 146939 |
+
"epoch": 292.78,
|
| 146940 |
+
"learning_rate": 9.423796445880453e-06,
|
| 146941 |
+
"loss": 0.6548,
|
| 146942 |
+
"step": 36680
|
| 146943 |
+
},
|
| 146944 |
+
{
|
| 146945 |
+
"epoch": 292.86,
|
| 146946 |
+
"learning_rate": 9.423634894991923e-06,
|
| 146947 |
+
"loss": 0.7433,
|
| 146948 |
+
"step": 36690
|
| 146949 |
+
},
|
| 146950 |
+
{
|
| 146951 |
+
"epoch": 292.94,
|
| 146952 |
+
"learning_rate": 9.423473344103393e-06,
|
| 146953 |
+
"loss": 0.4356,
|
| 146954 |
+
"step": 36700
|
| 146955 |
+
},
|
| 146956 |
+
{
|
| 146957 |
+
"epoch": 293.0,
|
| 146958 |
+
"eval_loss": 0.42647257447242737,
|
| 146959 |
+
"eval_runtime": 40.4543,
|
| 146960 |
+
"eval_samples_per_second": 20.764,
|
| 146961 |
+
"eval_steps_per_second": 0.667,
|
| 146962 |
+
"eval_wer": 0.20683848294040122,
|
| 146963 |
+
"step": 36707
|
| 146964 |
+
},
|
| 146965 |
+
{
|
| 146966 |
+
"epoch": 293.02,
|
| 146967 |
+
"learning_rate": 9.423311793214863e-06,
|
| 146968 |
+
"loss": 0.5523,
|
| 146969 |
+
"step": 36710
|
| 146970 |
+
},
|
| 146971 |
+
{
|
| 146972 |
+
"epoch": 293.1,
|
| 146973 |
+
"learning_rate": 9.423150242326333e-06,
|
| 146974 |
+
"loss": 0.4192,
|
| 146975 |
+
"step": 36720
|
| 146976 |
+
},
|
| 146977 |
+
{
|
| 146978 |
+
"epoch": 293.18,
|
| 146979 |
+
"learning_rate": 9.422988691437803e-06,
|
| 146980 |
+
"loss": 0.6616,
|
| 146981 |
+
"step": 36730
|
| 146982 |
+
},
|
| 146983 |
+
{
|
| 146984 |
+
"epoch": 293.26,
|
| 146985 |
+
"learning_rate": 9.422827140549272e-06,
|
| 146986 |
+
"loss": 0.6354,
|
| 146987 |
+
"step": 36740
|
| 146988 |
+
},
|
| 146989 |
+
{
|
| 146990 |
+
"epoch": 293.34,
|
| 146991 |
+
"learning_rate": 9.422665589660744e-06,
|
| 146992 |
+
"loss": 0.4289,
|
| 146993 |
+
"step": 36750
|
| 146994 |
+
},
|
| 146995 |
+
{
|
| 146996 |
+
"epoch": 293.42,
|
| 146997 |
+
"learning_rate": 9.422504038772214e-06,
|
| 146998 |
+
"loss": 1.0179,
|
| 146999 |
+
"step": 36760
|
| 147000 |
+
},
|
| 147001 |
+
{
|
| 147002 |
+
"epoch": 293.5,
|
| 147003 |
+
"learning_rate": 9.422342487883684e-06,
|
| 147004 |
+
"loss": 0.4228,
|
| 147005 |
+
"step": 36770
|
| 147006 |
+
},
|
| 147007 |
+
{
|
| 147008 |
+
"epoch": 293.58,
|
| 147009 |
+
"learning_rate": 9.422180936995154e-06,
|
| 147010 |
+
"loss": 0.6327,
|
| 147011 |
+
"step": 36780
|
| 147012 |
+
},
|
| 147013 |
+
{
|
| 147014 |
+
"epoch": 293.66,
|
| 147015 |
+
"learning_rate": 9.422019386106624e-06,
|
| 147016 |
+
"loss": 0.6403,
|
| 147017 |
+
"step": 36790
|
| 147018 |
+
},
|
| 147019 |
+
{
|
| 147020 |
+
"epoch": 293.74,
|
| 147021 |
+
"learning_rate": 9.421857835218094e-06,
|
| 147022 |
+
"loss": 0.5178,
|
| 147023 |
+
"step": 36800
|
| 147024 |
+
},
|
| 147025 |
+
{
|
| 147026 |
+
"epoch": 293.82,
|
| 147027 |
+
"learning_rate": 9.421696284329564e-06,
|
| 147028 |
+
"loss": 0.9299,
|
| 147029 |
+
"step": 36810
|
| 147030 |
+
},
|
| 147031 |
+
{
|
| 147032 |
+
"epoch": 293.9,
|
| 147033 |
+
"learning_rate": 9.421534733441034e-06,
|
| 147034 |
+
"loss": 0.5403,
|
| 147035 |
+
"step": 36820
|
| 147036 |
+
},
|
| 147037 |
+
{
|
| 147038 |
+
"epoch": 293.98,
|
| 147039 |
+
"learning_rate": 9.421373182552504e-06,
|
| 147040 |
+
"loss": 0.728,
|
| 147041 |
+
"step": 36830
|
| 147042 |
+
},
|
| 147043 |
+
{
|
| 147044 |
+
"epoch": 294.0,
|
| 147045 |
+
"eval_loss": 0.46654313802719116,
|
| 147046 |
+
"eval_runtime": 40.7857,
|
| 147047 |
+
"eval_samples_per_second": 20.595,
|
| 147048 |
+
"eval_steps_per_second": 0.662,
|
| 147049 |
+
"eval_wer": 0.2105934003682198,
|
| 147050 |
+
"step": 36832
|
| 147051 |
+
},
|
| 147052 |
+
{
|
| 147053 |
+
"epoch": 294.06,
|
| 147054 |
+
"learning_rate": 9.421211631663974e-06,
|
| 147055 |
+
"loss": 0.3939,
|
| 147056 |
+
"step": 36840
|
| 147057 |
+
},
|
| 147058 |
+
{
|
| 147059 |
+
"epoch": 294.14,
|
| 147060 |
+
"learning_rate": 9.421050080775444e-06,
|
| 147061 |
+
"loss": 0.4253,
|
| 147062 |
+
"step": 36850
|
| 147063 |
+
},
|
| 147064 |
+
{
|
| 147065 |
+
"epoch": 294.22,
|
| 147066 |
+
"learning_rate": 9.420888529886914e-06,
|
| 147067 |
+
"loss": 0.9068,
|
| 147068 |
+
"step": 36860
|
| 147069 |
+
},
|
| 147070 |
+
{
|
| 147071 |
+
"epoch": 294.3,
|
| 147072 |
+
"learning_rate": 9.420726978998386e-06,
|
| 147073 |
+
"loss": 0.3763,
|
| 147074 |
+
"step": 36870
|
| 147075 |
+
},
|
| 147076 |
+
{
|
| 147077 |
+
"epoch": 294.38,
|
| 147078 |
+
"learning_rate": 9.420565428109856e-06,
|
| 147079 |
+
"loss": 0.634,
|
| 147080 |
+
"step": 36880
|
| 147081 |
+
},
|
| 147082 |
+
{
|
| 147083 |
+
"epoch": 294.46,
|
| 147084 |
+
"learning_rate": 9.420403877221326e-06,
|
| 147085 |
+
"loss": 0.6775,
|
| 147086 |
+
"step": 36890
|
| 147087 |
+
},
|
| 147088 |
+
{
|
| 147089 |
+
"epoch": 294.54,
|
| 147090 |
+
"learning_rate": 9.420242326332795e-06,
|
| 147091 |
+
"loss": 0.3811,
|
| 147092 |
+
"step": 36900
|
| 147093 |
+
},
|
| 147094 |
+
{
|
| 147095 |
+
"epoch": 294.62,
|
| 147096 |
+
"learning_rate": 9.420080775444265e-06,
|
| 147097 |
+
"loss": 0.9304,
|
| 147098 |
+
"step": 36910
|
| 147099 |
+
},
|
| 147100 |
+
{
|
| 147101 |
+
"epoch": 294.7,
|
| 147102 |
+
"learning_rate": 9.419919224555735e-06,
|
| 147103 |
+
"loss": 0.4567,
|
| 147104 |
+
"step": 36920
|
| 147105 |
+
},
|
| 147106 |
+
{
|
| 147107 |
+
"epoch": 294.78,
|
| 147108 |
+
"learning_rate": 9.419757673667205e-06,
|
| 147109 |
+
"loss": 0.6287,
|
| 147110 |
+
"step": 36930
|
| 147111 |
+
},
|
| 147112 |
+
{
|
| 147113 |
+
"epoch": 294.86,
|
| 147114 |
+
"learning_rate": 9.419596122778675e-06,
|
| 147115 |
+
"loss": 0.8565,
|
| 147116 |
+
"step": 36940
|
| 147117 |
+
},
|
| 147118 |
+
{
|
| 147119 |
+
"epoch": 294.94,
|
| 147120 |
+
"learning_rate": 9.419434571890145e-06,
|
| 147121 |
+
"loss": 0.4649,
|
| 147122 |
+
"step": 36950
|
| 147123 |
+
},
|
| 147124 |
+
{
|
| 147125 |
+
"epoch": 295.0,
|
| 147126 |
+
"eval_loss": 0.5100269317626953,
|
| 147127 |
+
"eval_runtime": 40.5186,
|
| 147128 |
+
"eval_samples_per_second": 20.731,
|
| 147129 |
+
"eval_steps_per_second": 0.666,
|
| 147130 |
+
"eval_wer": 0.21227696600337764,
|
| 147131 |
+
"step": 36957
|
| 147132 |
}
|
| 147133 |
],
|
| 147134 |
+
"max_steps": 625000,
|
| 147135 |
"num_train_epochs": 5000,
|
| 147136 |
+
"total_flos": 1.0399899536899316e+20,
|
| 147137 |
"trial_name": null,
|
| 147138 |
"trial_params": null
|
| 147139 |
}
|
model-bin/finetune/base/{checkpoint-36333 → checkpoint-36957}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629665002.2003953/events.out.tfevents.1629665002.91f414e9573a.903.221
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c1fc0243611ed94b3ac0593a4d6aa6921e445d3db141477a2f6edee4bbaa592
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629665657.2222176/events.out.tfevents.1629665657.91f414e9573a.903.223
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2345ab474231f83aa257beb42888fd7aa59a6c597c2a12580375603a4ba1a437
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629666308.4602919/events.out.tfevents.1629666308.91f414e9573a.903.225
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3282038fe3ebdecb8920ee4a7f80752dccc327b7c2468d09d4d99d105dcd666
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629666956.4992223/events.out.tfevents.1629666956.91f414e9573a.903.227
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14fdf7187776e3697651188f2ee5d7a4fbaefc70349e2ed3e55470d66920c488
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629667615.440723/events.out.tfevents.1629667615.91f414e9573a.903.229
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:456eb63854099a07960f18a5575fbd3eea4a94bc7f420e210a667e3a902ef398
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629665002.91f414e9573a.903.220
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc16a327e86709e9bfe5b65b77a013f5e2307e57eedfe65169b2366b74db612d
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629665657.91f414e9573a.903.222
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a5ea9489fb34f7b9d0a9d33be17d9e6c18b7bab4dc81a2db9f94150d72e62ba
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629666308.91f414e9573a.903.224
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acc3d3f75edca0c3729e3623821067cf7d2eb0c72fed52c5b583b716442181e5
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629666956.91f414e9573a.903.226
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8dd62cdf9478c7a0c70971bcafb38751de0d97c0e2e7e2c68983e399f0de2b7
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629667615.91f414e9573a.903.228
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a51e27481862f895977ebc30e1352ca220062d99f2066136dfa11f9610335930
|
| 3 |
+
size 6543
|