"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/trainer_state.json +421 -4
- model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629624809.9967573/events.out.tfevents.1629624809.91f414e9573a.903.101 +3 -0
- model-bin/finetune/base/log/1629625474.1459835/events.out.tfevents.1629625474.91f414e9573a.903.103 +3 -0
- model-bin/finetune/base/log/1629626127.0900104/events.out.tfevents.1629626127.91f414e9573a.903.105 +3 -0
- model-bin/finetune/base/log/1629626777.5200148/events.out.tfevents.1629626777.91f414e9573a.903.107 +3 -0
- model-bin/finetune/base/log/1629627538.5357363/events.out.tfevents.1629627538.91f414e9573a.903.109 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629624809.91f414e9573a.903.100 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629625474.91f414e9573a.903.102 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629626127.91f414e9573a.903.104 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629626777.91f414e9573a.903.106 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629627538.91f414e9573a.903.108 +3 -0
model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/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 sha256:5401d06dbcb0a37f2474a0b2342f6303d367668234a32078f30412a9a0558b59
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/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:a4fb595ebe4e29f5964c9bd81fdad32ddc86cbb66c1146335ffb9d4a9d1341f7
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/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 sha256:3dac2225984b5ea54ab466007eec47cf69b3bf1d0cb4c807ac8b559f81b772cd
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/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 sha256:1649df062a4967a054ab70170e4b975014ed744f851c13b8199f78139481d1e6
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/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 sha256:21060f272211ffdcae35201a596acf2da1e9bc5ab5edc4f2c03519a3d0fe76d5
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2158154859967051,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-25631",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -141690,11 +141690,428 @@
|
|
| 141690 |
"eval_steps_per_second": 0.66,
|
| 141691 |
"eval_wer": 0.23211915646659784,
|
| 141692 |
"step": 28862
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141693 |
}
|
| 141694 |
],
|
| 141695 |
-
"max_steps":
|
| 141696 |
"num_train_epochs": 5000,
|
| 141697 |
-
"total_flos": 8.
|
| 141698 |
"trial_name": null,
|
| 141699 |
"trial_params": null
|
| 141700 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2158154859967051,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-25631",
|
| 4 |
+
"epoch": 236.99598393574297,
|
| 5 |
+
"global_step": 29484,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 141690 |
"eval_steps_per_second": 0.66,
|
| 141691 |
"eval_wer": 0.23211915646659784,
|
| 141692 |
"step": 28862
|
| 141693 |
+
},
|
| 141694 |
+
{
|
| 141695 |
+
"epoch": 232.06,
|
| 141696 |
+
"learning_rate": 9.549919224555736e-06,
|
| 141697 |
+
"loss": 0.3783,
|
| 141698 |
+
"step": 28870
|
| 141699 |
+
},
|
| 141700 |
+
{
|
| 141701 |
+
"epoch": 232.14,
|
| 141702 |
+
"learning_rate": 9.549757673667206e-06,
|
| 141703 |
+
"loss": 0.4123,
|
| 141704 |
+
"step": 28880
|
| 141705 |
+
},
|
| 141706 |
+
{
|
| 141707 |
+
"epoch": 232.22,
|
| 141708 |
+
"learning_rate": 9.549596122778676e-06,
|
| 141709 |
+
"loss": 0.922,
|
| 141710 |
+
"step": 28890
|
| 141711 |
+
},
|
| 141712 |
+
{
|
| 141713 |
+
"epoch": 232.31,
|
| 141714 |
+
"learning_rate": 9.549434571890146e-06,
|
| 141715 |
+
"loss": 0.4084,
|
| 141716 |
+
"step": 28900
|
| 141717 |
+
},
|
| 141718 |
+
{
|
| 141719 |
+
"epoch": 232.39,
|
| 141720 |
+
"learning_rate": 9.549273021001616e-06,
|
| 141721 |
+
"loss": 0.7414,
|
| 141722 |
+
"step": 28910
|
| 141723 |
+
},
|
| 141724 |
+
{
|
| 141725 |
+
"epoch": 232.47,
|
| 141726 |
+
"learning_rate": 9.549111470113086e-06,
|
| 141727 |
+
"loss": 0.6556,
|
| 141728 |
+
"step": 28920
|
| 141729 |
+
},
|
| 141730 |
+
{
|
| 141731 |
+
"epoch": 232.55,
|
| 141732 |
+
"learning_rate": 9.548949919224556e-06,
|
| 141733 |
+
"loss": 0.4671,
|
| 141734 |
+
"step": 28930
|
| 141735 |
+
},
|
| 141736 |
+
{
|
| 141737 |
+
"epoch": 232.63,
|
| 141738 |
+
"learning_rate": 9.548788368336027e-06,
|
| 141739 |
+
"loss": 1.015,
|
| 141740 |
+
"step": 28940
|
| 141741 |
+
},
|
| 141742 |
+
{
|
| 141743 |
+
"epoch": 232.71,
|
| 141744 |
+
"learning_rate": 9.548626817447497e-06,
|
| 141745 |
+
"loss": 0.3851,
|
| 141746 |
+
"step": 28950
|
| 141747 |
+
},
|
| 141748 |
+
{
|
| 141749 |
+
"epoch": 232.79,
|
| 141750 |
+
"learning_rate": 9.548465266558967e-06,
|
| 141751 |
+
"loss": 0.6922,
|
| 141752 |
+
"step": 28960
|
| 141753 |
+
},
|
| 141754 |
+
{
|
| 141755 |
+
"epoch": 232.87,
|
| 141756 |
+
"learning_rate": 9.548303715670437e-06,
|
| 141757 |
+
"loss": 0.6798,
|
| 141758 |
+
"step": 28970
|
| 141759 |
+
},
|
| 141760 |
+
{
|
| 141761 |
+
"epoch": 232.95,
|
| 141762 |
+
"learning_rate": 9.548142164781907e-06,
|
| 141763 |
+
"loss": 0.4282,
|
| 141764 |
+
"step": 28980
|
| 141765 |
+
},
|
| 141766 |
+
{
|
| 141767 |
+
"epoch": 233.0,
|
| 141768 |
+
"eval_loss": 0.45882371068000793,
|
| 141769 |
+
"eval_runtime": 41.231,
|
| 141770 |
+
"eval_samples_per_second": 20.373,
|
| 141771 |
+
"eval_steps_per_second": 0.655,
|
| 141772 |
+
"eval_wer": 0.22208418591055246,
|
| 141773 |
+
"step": 28986
|
| 141774 |
+
},
|
| 141775 |
+
{
|
| 141776 |
+
"epoch": 231.03,
|
| 141777 |
+
"learning_rate": 9.547980613893377e-06,
|
| 141778 |
+
"loss": 0.4324,
|
| 141779 |
+
"step": 28990
|
| 141780 |
+
},
|
| 141781 |
+
{
|
| 141782 |
+
"epoch": 231.11,
|
| 141783 |
+
"learning_rate": 9.547819063004847e-06,
|
| 141784 |
+
"loss": 0.3894,
|
| 141785 |
+
"step": 29000
|
| 141786 |
+
},
|
| 141787 |
+
{
|
| 141788 |
+
"epoch": 231.19,
|
| 141789 |
+
"learning_rate": 9.547657512116317e-06,
|
| 141790 |
+
"loss": 0.8287,
|
| 141791 |
+
"step": 29010
|
| 141792 |
+
},
|
| 141793 |
+
{
|
| 141794 |
+
"epoch": 231.27,
|
| 141795 |
+
"learning_rate": 9.547495961227787e-06,
|
| 141796 |
+
"loss": 0.676,
|
| 141797 |
+
"step": 29020
|
| 141798 |
+
},
|
| 141799 |
+
{
|
| 141800 |
+
"epoch": 231.35,
|
| 141801 |
+
"learning_rate": 9.547334410339257e-06,
|
| 141802 |
+
"loss": 0.4795,
|
| 141803 |
+
"step": 29030
|
| 141804 |
+
},
|
| 141805 |
+
{
|
| 141806 |
+
"epoch": 231.43,
|
| 141807 |
+
"learning_rate": 9.547172859450727e-06,
|
| 141808 |
+
"loss": 0.9887,
|
| 141809 |
+
"step": 29040
|
| 141810 |
+
},
|
| 141811 |
+
{
|
| 141812 |
+
"epoch": 231.51,
|
| 141813 |
+
"learning_rate": 9.547011308562197e-06,
|
| 141814 |
+
"loss": 0.505,
|
| 141815 |
+
"step": 29050
|
| 141816 |
+
},
|
| 141817 |
+
{
|
| 141818 |
+
"epoch": 231.59,
|
| 141819 |
+
"learning_rate": 9.546849757673669e-06,
|
| 141820 |
+
"loss": 0.8797,
|
| 141821 |
+
"step": 29060
|
| 141822 |
+
},
|
| 141823 |
+
{
|
| 141824 |
+
"epoch": 231.67,
|
| 141825 |
+
"learning_rate": 9.546688206785139e-06,
|
| 141826 |
+
"loss": 0.6167,
|
| 141827 |
+
"step": 29070
|
| 141828 |
+
},
|
| 141829 |
+
{
|
| 141830 |
+
"epoch": 231.75,
|
| 141831 |
+
"learning_rate": 9.546526655896609e-06,
|
| 141832 |
+
"loss": 0.4744,
|
| 141833 |
+
"step": 29080
|
| 141834 |
+
},
|
| 141835 |
+
{
|
| 141836 |
+
"epoch": 231.83,
|
| 141837 |
+
"learning_rate": 9.546365105008079e-06,
|
| 141838 |
+
"loss": 1.0646,
|
| 141839 |
+
"step": 29090
|
| 141840 |
+
},
|
| 141841 |
+
{
|
| 141842 |
+
"epoch": 231.91,
|
| 141843 |
+
"learning_rate": 9.546203554119549e-06,
|
| 141844 |
+
"loss": 0.6295,
|
| 141845 |
+
"step": 29100
|
| 141846 |
+
},
|
| 141847 |
+
{
|
| 141848 |
+
"epoch": 231.99,
|
| 141849 |
+
"learning_rate": 9.546042003231019e-06,
|
| 141850 |
+
"loss": 0.8269,
|
| 141851 |
+
"step": 29110
|
| 141852 |
+
},
|
| 141853 |
+
{
|
| 141854 |
+
"epoch": 232.0,
|
| 141855 |
+
"eval_loss": 0.5006926655769348,
|
| 141856 |
+
"eval_runtime": 40.3876,
|
| 141857 |
+
"eval_samples_per_second": 20.823,
|
| 141858 |
+
"eval_steps_per_second": 0.669,
|
| 141859 |
+
"eval_wer": 0.22166506894771773,
|
| 141860 |
+
"step": 29111
|
| 141861 |
+
},
|
| 141862 |
+
{
|
| 141863 |
+
"epoch": 234.07,
|
| 141864 |
+
"learning_rate": 9.545880452342489e-06,
|
| 141865 |
+
"loss": 0.5086,
|
| 141866 |
+
"step": 29120
|
| 141867 |
+
},
|
| 141868 |
+
{
|
| 141869 |
+
"epoch": 234.15,
|
| 141870 |
+
"learning_rate": 9.545718901453959e-06,
|
| 141871 |
+
"loss": 0.4732,
|
| 141872 |
+
"step": 29130
|
| 141873 |
+
},
|
| 141874 |
+
{
|
| 141875 |
+
"epoch": 234.23,
|
| 141876 |
+
"learning_rate": 9.545557350565429e-06,
|
| 141877 |
+
"loss": 0.9403,
|
| 141878 |
+
"step": 29140
|
| 141879 |
+
},
|
| 141880 |
+
{
|
| 141881 |
+
"epoch": 234.31,
|
| 141882 |
+
"learning_rate": 9.545395799676899e-06,
|
| 141883 |
+
"loss": 0.425,
|
| 141884 |
+
"step": 29150
|
| 141885 |
+
},
|
| 141886 |
+
{
|
| 141887 |
+
"epoch": 234.39,
|
| 141888 |
+
"learning_rate": 9.545234248788369e-06,
|
| 141889 |
+
"loss": 0.7885,
|
| 141890 |
+
"step": 29160
|
| 141891 |
+
},
|
| 141892 |
+
{
|
| 141893 |
+
"epoch": 234.47,
|
| 141894 |
+
"learning_rate": 9.545072697899839e-06,
|
| 141895 |
+
"loss": 0.5998,
|
| 141896 |
+
"step": 29170
|
| 141897 |
+
},
|
| 141898 |
+
{
|
| 141899 |
+
"epoch": 234.55,
|
| 141900 |
+
"learning_rate": 9.54491114701131e-06,
|
| 141901 |
+
"loss": 0.4842,
|
| 141902 |
+
"step": 29180
|
| 141903 |
+
},
|
| 141904 |
+
{
|
| 141905 |
+
"epoch": 234.63,
|
| 141906 |
+
"learning_rate": 9.54474959612278e-06,
|
| 141907 |
+
"loss": 1.0059,
|
| 141908 |
+
"step": 29190
|
| 141909 |
+
},
|
| 141910 |
+
{
|
| 141911 |
+
"epoch": 234.71,
|
| 141912 |
+
"learning_rate": 9.54458804523425e-06,
|
| 141913 |
+
"loss": 0.425,
|
| 141914 |
+
"step": 29200
|
| 141915 |
+
},
|
| 141916 |
+
{
|
| 141917 |
+
"epoch": 234.8,
|
| 141918 |
+
"learning_rate": 9.54442649434572e-06,
|
| 141919 |
+
"loss": 0.8474,
|
| 141920 |
+
"step": 29210
|
| 141921 |
+
},
|
| 141922 |
+
{
|
| 141923 |
+
"epoch": 234.88,
|
| 141924 |
+
"learning_rate": 9.54426494345719e-06,
|
| 141925 |
+
"loss": 0.6058,
|
| 141926 |
+
"step": 29220
|
| 141927 |
+
},
|
| 141928 |
+
{
|
| 141929 |
+
"epoch": 234.96,
|
| 141930 |
+
"learning_rate": 9.54410339256866e-06,
|
| 141931 |
+
"loss": 0.4977,
|
| 141932 |
+
"step": 29230
|
| 141933 |
+
},
|
| 141934 |
+
{
|
| 141935 |
+
"epoch": 235.0,
|
| 141936 |
+
"eval_loss": 0.4852975904941559,
|
| 141937 |
+
"eval_runtime": 40.4365,
|
| 141938 |
+
"eval_samples_per_second": 20.798,
|
| 141939 |
+
"eval_steps_per_second": 0.668,
|
| 141940 |
+
"eval_wer": 0.22384875680447255,
|
| 141941 |
+
"step": 29235
|
| 141942 |
+
},
|
| 141943 |
+
{
|
| 141944 |
+
"epoch": 233.04,
|
| 141945 |
+
"learning_rate": 9.54394184168013e-06,
|
| 141946 |
+
"loss": 0.5366,
|
| 141947 |
+
"step": 29240
|
| 141948 |
+
},
|
| 141949 |
+
{
|
| 141950 |
+
"epoch": 233.12,
|
| 141951 |
+
"learning_rate": 9.5437802907916e-06,
|
| 141952 |
+
"loss": 0.4135,
|
| 141953 |
+
"step": 29250
|
| 141954 |
+
},
|
| 141955 |
+
{
|
| 141956 |
+
"epoch": 233.2,
|
| 141957 |
+
"learning_rate": 9.54361873990307e-06,
|
| 141958 |
+
"loss": 1.087,
|
| 141959 |
+
"step": 29260
|
| 141960 |
+
},
|
| 141961 |
+
{
|
| 141962 |
+
"epoch": 233.28,
|
| 141963 |
+
"learning_rate": 9.54345718901454e-06,
|
| 141964 |
+
"loss": 0.442,
|
| 141965 |
+
"step": 29270
|
| 141966 |
+
},
|
| 141967 |
+
{
|
| 141968 |
+
"epoch": 233.36,
|
| 141969 |
+
"learning_rate": 9.54329563812601e-06,
|
| 141970 |
+
"loss": 0.4927,
|
| 141971 |
+
"step": 29280
|
| 141972 |
+
},
|
| 141973 |
+
{
|
| 141974 |
+
"epoch": 233.44,
|
| 141975 |
+
"learning_rate": 9.543134087237482e-06,
|
| 141976 |
+
"loss": 0.9727,
|
| 141977 |
+
"step": 29290
|
| 141978 |
+
},
|
| 141979 |
+
{
|
| 141980 |
+
"epoch": 233.52,
|
| 141981 |
+
"learning_rate": 9.542972536348952e-06,
|
| 141982 |
+
"loss": 0.3817,
|
| 141983 |
+
"step": 29300
|
| 141984 |
+
},
|
| 141985 |
+
{
|
| 141986 |
+
"epoch": 233.6,
|
| 141987 |
+
"learning_rate": 9.542810985460422e-06,
|
| 141988 |
+
"loss": 1.0012,
|
| 141989 |
+
"step": 29310
|
| 141990 |
+
},
|
| 141991 |
+
{
|
| 141992 |
+
"epoch": 233.68,
|
| 141993 |
+
"learning_rate": 9.542649434571892e-06,
|
| 141994 |
+
"loss": 0.4276,
|
| 141995 |
+
"step": 29320
|
| 141996 |
+
},
|
| 141997 |
+
{
|
| 141998 |
+
"epoch": 233.76,
|
| 141999 |
+
"learning_rate": 9.542487883683362e-06,
|
| 142000 |
+
"loss": 0.4482,
|
| 142001 |
+
"step": 29330
|
| 142002 |
+
},
|
| 142003 |
+
{
|
| 142004 |
+
"epoch": 233.84,
|
| 142005 |
+
"learning_rate": 9.542326332794831e-06,
|
| 142006 |
+
"loss": 0.9151,
|
| 142007 |
+
"step": 29340
|
| 142008 |
+
},
|
| 142009 |
+
{
|
| 142010 |
+
"epoch": 233.92,
|
| 142011 |
+
"learning_rate": 9.542164781906301e-06,
|
| 142012 |
+
"loss": 0.3818,
|
| 142013 |
+
"step": 29350
|
| 142014 |
+
},
|
| 142015 |
+
{
|
| 142016 |
+
"epoch": 234.0,
|
| 142017 |
+
"learning_rate": 9.542003231017771e-06,
|
| 142018 |
+
"loss": 1.152,
|
| 142019 |
+
"step": 29360
|
| 142020 |
+
},
|
| 142021 |
+
{
|
| 142022 |
+
"epoch": 234.0,
|
| 142023 |
+
"eval_loss": 0.47633424401283264,
|
| 142024 |
+
"eval_runtime": 40.4169,
|
| 142025 |
+
"eval_samples_per_second": 20.808,
|
| 142026 |
+
"eval_steps_per_second": 0.668,
|
| 142027 |
+
"eval_wer": 0.22683611644746565,
|
| 142028 |
+
"step": 29360
|
| 142029 |
+
},
|
| 142030 |
+
{
|
| 142031 |
+
"epoch": 236.08,
|
| 142032 |
+
"learning_rate": 9.541841680129241e-06,
|
| 142033 |
+
"loss": 0.4573,
|
| 142034 |
+
"step": 29370
|
| 142035 |
+
},
|
| 142036 |
+
{
|
| 142037 |
+
"epoch": 236.16,
|
| 142038 |
+
"learning_rate": 9.541680129240711e-06,
|
| 142039 |
+
"loss": 0.5305,
|
| 142040 |
+
"step": 29380
|
| 142041 |
+
},
|
| 142042 |
+
{
|
| 142043 |
+
"epoch": 236.24,
|
| 142044 |
+
"learning_rate": 9.541518578352181e-06,
|
| 142045 |
+
"loss": 0.9488,
|
| 142046 |
+
"step": 29390
|
| 142047 |
+
},
|
| 142048 |
+
{
|
| 142049 |
+
"epoch": 236.32,
|
| 142050 |
+
"learning_rate": 9.541357027463651e-06,
|
| 142051 |
+
"loss": 0.4103,
|
| 142052 |
+
"step": 29400
|
| 142053 |
+
},
|
| 142054 |
+
{
|
| 142055 |
+
"epoch": 236.4,
|
| 142056 |
+
"learning_rate": 9.541195476575123e-06,
|
| 142057 |
+
"loss": 1.0351,
|
| 142058 |
+
"step": 29410
|
| 142059 |
+
},
|
| 142060 |
+
{
|
| 142061 |
+
"epoch": 236.48,
|
| 142062 |
+
"learning_rate": 9.541033925686593e-06,
|
| 142063 |
+
"loss": 0.3902,
|
| 142064 |
+
"step": 29420
|
| 142065 |
+
},
|
| 142066 |
+
{
|
| 142067 |
+
"epoch": 236.56,
|
| 142068 |
+
"learning_rate": 9.540872374798063e-06,
|
| 142069 |
+
"loss": 0.5328,
|
| 142070 |
+
"step": 29430
|
| 142071 |
+
},
|
| 142072 |
+
{
|
| 142073 |
+
"epoch": 236.64,
|
| 142074 |
+
"learning_rate": 9.540710823909533e-06,
|
| 142075 |
+
"loss": 0.9651,
|
| 142076 |
+
"step": 29440
|
| 142077 |
+
},
|
| 142078 |
+
{
|
| 142079 |
+
"epoch": 236.72,
|
| 142080 |
+
"learning_rate": 9.540549273021003e-06,
|
| 142081 |
+
"loss": 0.4115,
|
| 142082 |
+
"step": 29450
|
| 142083 |
+
},
|
| 142084 |
+
{
|
| 142085 |
+
"epoch": 236.8,
|
| 142086 |
+
"learning_rate": 9.540387722132473e-06,
|
| 142087 |
+
"loss": 0.9956,
|
| 142088 |
+
"step": 29460
|
| 142089 |
+
},
|
| 142090 |
+
{
|
| 142091 |
+
"epoch": 236.88,
|
| 142092 |
+
"learning_rate": 9.540226171243943e-06,
|
| 142093 |
+
"loss": 0.4125,
|
| 142094 |
+
"step": 29470
|
| 142095 |
+
},
|
| 142096 |
+
{
|
| 142097 |
+
"epoch": 236.96,
|
| 142098 |
+
"learning_rate": 9.540064620355413e-06,
|
| 142099 |
+
"loss": 0.5879,
|
| 142100 |
+
"step": 29480
|
| 142101 |
+
},
|
| 142102 |
+
{
|
| 142103 |
+
"epoch": 237.0,
|
| 142104 |
+
"eval_loss": 0.5837559103965759,
|
| 142105 |
+
"eval_runtime": 39.7867,
|
| 142106 |
+
"eval_samples_per_second": 20.912,
|
| 142107 |
+
"eval_steps_per_second": 0.653,
|
| 142108 |
+
"eval_wer": 0.22174043062200957,
|
| 142109 |
+
"step": 29484
|
| 142110 |
}
|
| 142111 |
],
|
| 142112 |
+
"max_steps": 620000,
|
| 142113 |
"num_train_epochs": 5000,
|
| 142114 |
+
"total_flos": 8.296339872820249e+19,
|
| 142115 |
"trial_name": null,
|
| 142116 |
"trial_params": null
|
| 142117 |
}
|
model-bin/finetune/base/{checkpoint-28862 → checkpoint-29484}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629624809.9967573/events.out.tfevents.1629624809.91f414e9573a.903.101
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cada16b15290764da4cf06850f41e664fc02662bd8f0709c422d6e8004d8bfe5
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629625474.1459835/events.out.tfevents.1629625474.91f414e9573a.903.103
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b4270ec182336d77bbf834eedf66c0c28a826510537defdfe5d8c7280d1225c
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629626127.0900104/events.out.tfevents.1629626127.91f414e9573a.903.105
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bab3f2aa21defab610e3a27de5e3a0020dd61912feb4c687e3be76a7f44769a
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629626777.5200148/events.out.tfevents.1629626777.91f414e9573a.903.107
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f84ec58db421f714e3b70af86e46b652c164895d1c80a309679ab75929383c99
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629627538.5357363/events.out.tfevents.1629627538.91f414e9573a.903.109
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33e15737ba995764ceb1022658965f22e0667424083b87ec0209dc38f1349e4a
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629624809.91f414e9573a.903.100
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19184420e7576134c16b12084c35a589d133ee43e8df66020017dff376b75602
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629625474.91f414e9573a.903.102
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3e2931ccd5f3cb74db76499badb00cf6eee4cf5dd5155123191c510e2b9aba3
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629626127.91f414e9573a.903.104
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1be5e26082ccf2cab580ef73e7eaace433a61ebc39fb174c6e4c1c6509e746b
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629626777.91f414e9573a.903.106
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cc99b97ab641dfd9bd4919229051c4215566697bc6dab4f2e1b691b678e895d
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629627538.91f414e9573a.903.108
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3770384ed03f2d6b70b110b68c9d303cbdb4317a731eb2b19bfebec2fa07780f
|
| 3 |
+
size 6543
|