"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/trainer_state.json +421 -4
- model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629601332.9347947/events.out.tfevents.1629601332.91f414e9573a.903.31 +3 -0
- model-bin/finetune/base/log/1629601981.3327703/events.out.tfevents.1629601981.91f414e9573a.903.33 +3 -0
- model-bin/finetune/base/log/1629602645.363557/events.out.tfevents.1629602645.91f414e9573a.903.35 +3 -0
- model-bin/finetune/base/log/1629603289.4152238/events.out.tfevents.1629603289.91f414e9573a.903.37 +3 -0
- model-bin/finetune/base/log/1629603939.0035386/events.out.tfevents.1629603939.91f414e9573a.903.39 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629601332.91f414e9573a.903.30 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629601981.91f414e9573a.903.32 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629602645.91f414e9573a.903.34 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629603289.91f414e9573a.903.36 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629603938.91f414e9573a.903.38 +3 -0
model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/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:c65af66a9ec99c63cc3fff323424dab1f1141e90b21c0a566f3200033b973133
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/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 sha256:8cba4f098524a8d0522ad99578fa5e62706f650e11c2cba1cac0f2dba4a2d900
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/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:e2a48ed5d2e128753c565b3e9c630183540c6ed35cc1c2b133d5d319360d459d
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/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:e9560e647b01e124e3618004cca53bacf8606eab38f2784197313e7658fa0e3a
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/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 sha256:2a6e05a5e73b54783a4c60baff17f796a60f4d2f00160338b30bd9f3e3315fcc
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2172567645365573,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-23890",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -138765,11 +138765,428 @@
|
|
| 138765 |
"eval_steps_per_second": 0.665,
|
| 138766 |
"eval_wer": 0.22446705786228924,
|
| 138767 |
"step": 24512
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 138768 |
}
|
| 138769 |
],
|
| 138770 |
-
"max_steps":
|
| 138771 |
"num_train_epochs": 5000,
|
| 138772 |
-
"total_flos":
|
| 138773 |
"trial_name": null,
|
| 138774 |
"trial_params": null
|
| 138775 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2172567645365573,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-23890",
|
| 4 |
+
"epoch": 201.0,
|
| 5 |
+
"global_step": 25132,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 138765 |
"eval_steps_per_second": 0.665,
|
| 138766 |
"eval_wer": 0.22446705786228924,
|
| 138767 |
"step": 24512
|
| 138768 |
+
},
|
| 138769 |
+
{
|
| 138770 |
+
"epoch": 197.06,
|
| 138771 |
+
"learning_rate": 9.620193861066237e-06,
|
| 138772 |
+
"loss": 0.4979,
|
| 138773 |
+
"step": 24520
|
| 138774 |
+
},
|
| 138775 |
+
{
|
| 138776 |
+
"epoch": 197.14,
|
| 138777 |
+
"learning_rate": 9.620032310177707e-06,
|
| 138778 |
+
"loss": 0.4723,
|
| 138779 |
+
"step": 24530
|
| 138780 |
+
},
|
| 138781 |
+
{
|
| 138782 |
+
"epoch": 197.22,
|
| 138783 |
+
"learning_rate": 9.619870759289177e-06,
|
| 138784 |
+
"loss": 1.0379,
|
| 138785 |
+
"step": 24540
|
| 138786 |
+
},
|
| 138787 |
+
{
|
| 138788 |
+
"epoch": 197.31,
|
| 138789 |
+
"learning_rate": 9.619709208400647e-06,
|
| 138790 |
+
"loss": 0.3889,
|
| 138791 |
+
"step": 24550
|
| 138792 |
+
},
|
| 138793 |
+
{
|
| 138794 |
+
"epoch": 197.39,
|
| 138795 |
+
"learning_rate": 9.619547657512117e-06,
|
| 138796 |
+
"loss": 0.7348,
|
| 138797 |
+
"step": 24560
|
| 138798 |
+
},
|
| 138799 |
+
{
|
| 138800 |
+
"epoch": 197.47,
|
| 138801 |
+
"learning_rate": 9.619386106623587e-06,
|
| 138802 |
+
"loss": 0.7806,
|
| 138803 |
+
"step": 24570
|
| 138804 |
+
},
|
| 138805 |
+
{
|
| 138806 |
+
"epoch": 197.55,
|
| 138807 |
+
"learning_rate": 9.619224555735057e-06,
|
| 138808 |
+
"loss": 0.477,
|
| 138809 |
+
"step": 24580
|
| 138810 |
+
},
|
| 138811 |
+
{
|
| 138812 |
+
"epoch": 197.63,
|
| 138813 |
+
"learning_rate": 9.619063004846527e-06,
|
| 138814 |
+
"loss": 0.9734,
|
| 138815 |
+
"step": 24590
|
| 138816 |
+
},
|
| 138817 |
+
{
|
| 138818 |
+
"epoch": 197.71,
|
| 138819 |
+
"learning_rate": 9.618901453957997e-06,
|
| 138820 |
+
"loss": 0.4244,
|
| 138821 |
+
"step": 24600
|
| 138822 |
+
},
|
| 138823 |
+
{
|
| 138824 |
+
"epoch": 197.79,
|
| 138825 |
+
"learning_rate": 9.618739903069467e-06,
|
| 138826 |
+
"loss": 0.7103,
|
| 138827 |
+
"step": 24610
|
| 138828 |
+
},
|
| 138829 |
+
{
|
| 138830 |
+
"epoch": 197.87,
|
| 138831 |
+
"learning_rate": 9.618578352180937e-06,
|
| 138832 |
+
"loss": 0.7796,
|
| 138833 |
+
"step": 24620
|
| 138834 |
+
},
|
| 138835 |
+
{
|
| 138836 |
+
"epoch": 197.95,
|
| 138837 |
+
"learning_rate": 9.618416801292409e-06,
|
| 138838 |
+
"loss": 0.5144,
|
| 138839 |
+
"step": 24630
|
| 138840 |
+
},
|
| 138841 |
+
{
|
| 138842 |
+
"epoch": 198.0,
|
| 138843 |
+
"eval_loss": 0.46397992968559265,
|
| 138844 |
+
"eval_runtime": 40.8749,
|
| 138845 |
+
"eval_samples_per_second": 20.673,
|
| 138846 |
+
"eval_steps_per_second": 0.661,
|
| 138847 |
+
"eval_wer": 0.21918200701955448,
|
| 138848 |
+
"step": 24636
|
| 138849 |
+
},
|
| 138850 |
+
{
|
| 138851 |
+
"epoch": 198.03,
|
| 138852 |
+
"learning_rate": 9.618255250403879e-06,
|
| 138853 |
+
"loss": 0.4148,
|
| 138854 |
+
"step": 24640
|
| 138855 |
+
},
|
| 138856 |
+
{
|
| 138857 |
+
"epoch": 198.11,
|
| 138858 |
+
"learning_rate": 9.618093699515349e-06,
|
| 138859 |
+
"loss": 0.4704,
|
| 138860 |
+
"step": 24650
|
| 138861 |
+
},
|
| 138862 |
+
{
|
| 138863 |
+
"epoch": 198.19,
|
| 138864 |
+
"learning_rate": 9.617932148626819e-06,
|
| 138865 |
+
"loss": 0.9196,
|
| 138866 |
+
"step": 24660
|
| 138867 |
+
},
|
| 138868 |
+
{
|
| 138869 |
+
"epoch": 198.27,
|
| 138870 |
+
"learning_rate": 9.617770597738289e-06,
|
| 138871 |
+
"loss": 0.594,
|
| 138872 |
+
"step": 24670
|
| 138873 |
+
},
|
| 138874 |
+
{
|
| 138875 |
+
"epoch": 198.35,
|
| 138876 |
+
"learning_rate": 9.617609046849759e-06,
|
| 138877 |
+
"loss": 0.5186,
|
| 138878 |
+
"step": 24680
|
| 138879 |
+
},
|
| 138880 |
+
{
|
| 138881 |
+
"epoch": 198.43,
|
| 138882 |
+
"learning_rate": 9.617447495961229e-06,
|
| 138883 |
+
"loss": 1.0653,
|
| 138884 |
+
"step": 24690
|
| 138885 |
+
},
|
| 138886 |
+
{
|
| 138887 |
+
"epoch": 198.51,
|
| 138888 |
+
"learning_rate": 9.617285945072699e-06,
|
| 138889 |
+
"loss": 0.4178,
|
| 138890 |
+
"step": 24700
|
| 138891 |
+
},
|
| 138892 |
+
{
|
| 138893 |
+
"epoch": 198.59,
|
| 138894 |
+
"learning_rate": 9.617124394184169e-06,
|
| 138895 |
+
"loss": 0.9037,
|
| 138896 |
+
"step": 24710
|
| 138897 |
+
},
|
| 138898 |
+
{
|
| 138899 |
+
"epoch": 198.67,
|
| 138900 |
+
"learning_rate": 9.616962843295639e-06,
|
| 138901 |
+
"loss": 0.5858,
|
| 138902 |
+
"step": 24720
|
| 138903 |
+
},
|
| 138904 |
+
{
|
| 138905 |
+
"epoch": 198.76,
|
| 138906 |
+
"learning_rate": 9.616801292407109e-06,
|
| 138907 |
+
"loss": 0.5078,
|
| 138908 |
+
"step": 24730
|
| 138909 |
+
},
|
| 138910 |
+
{
|
| 138911 |
+
"epoch": 198.84,
|
| 138912 |
+
"learning_rate": 9.616639741518579e-06,
|
| 138913 |
+
"loss": 1.0187,
|
| 138914 |
+
"step": 24740
|
| 138915 |
+
},
|
| 138916 |
+
{
|
| 138917 |
+
"epoch": 198.92,
|
| 138918 |
+
"learning_rate": 9.61647819063005e-06,
|
| 138919 |
+
"loss": 0.4836,
|
| 138920 |
+
"step": 24750
|
| 138921 |
+
},
|
| 138922 |
+
{
|
| 138923 |
+
"epoch": 199.0,
|
| 138924 |
+
"learning_rate": 9.61631663974152e-06,
|
| 138925 |
+
"loss": 0.8794,
|
| 138926 |
+
"step": 24760
|
| 138927 |
+
},
|
| 138928 |
+
{
|
| 138929 |
+
"epoch": 199.0,
|
| 138930 |
+
"eval_loss": 0.5073041319847107,
|
| 138931 |
+
"eval_runtime": 40.7573,
|
| 138932 |
+
"eval_samples_per_second": 20.732,
|
| 138933 |
+
"eval_steps_per_second": 0.662,
|
| 138934 |
+
"eval_wer": 0.221430669800235,
|
| 138935 |
+
"step": 24760
|
| 138936 |
+
},
|
| 138937 |
+
{
|
| 138938 |
+
"epoch": 201.08,
|
| 138939 |
+
"learning_rate": 9.61615508885299e-06,
|
| 138940 |
+
"loss": 0.4919,
|
| 138941 |
+
"step": 24770
|
| 138942 |
+
},
|
| 138943 |
+
{
|
| 138944 |
+
"epoch": 201.16,
|
| 138945 |
+
"learning_rate": 9.61599353796446e-06,
|
| 138946 |
+
"loss": 0.5007,
|
| 138947 |
+
"step": 24780
|
| 138948 |
+
},
|
| 138949 |
+
{
|
| 138950 |
+
"epoch": 201.24,
|
| 138951 |
+
"learning_rate": 9.61583198707593e-06,
|
| 138952 |
+
"loss": 0.9708,
|
| 138953 |
+
"step": 24790
|
| 138954 |
+
},
|
| 138955 |
+
{
|
| 138956 |
+
"epoch": 201.32,
|
| 138957 |
+
"learning_rate": 9.6156704361874e-06,
|
| 138958 |
+
"loss": 0.4545,
|
| 138959 |
+
"step": 24800
|
| 138960 |
+
},
|
| 138961 |
+
{
|
| 138962 |
+
"epoch": 201.4,
|
| 138963 |
+
"learning_rate": 9.61550888529887e-06,
|
| 138964 |
+
"loss": 1.0798,
|
| 138965 |
+
"step": 24810
|
| 138966 |
+
},
|
| 138967 |
+
{
|
| 138968 |
+
"epoch": 201.49,
|
| 138969 |
+
"learning_rate": 9.61534733441034e-06,
|
| 138970 |
+
"loss": 0.461,
|
| 138971 |
+
"step": 24820
|
| 138972 |
+
},
|
| 138973 |
+
{
|
| 138974 |
+
"epoch": 201.57,
|
| 138975 |
+
"learning_rate": 9.61518578352181e-06,
|
| 138976 |
+
"loss": 0.5125,
|
| 138977 |
+
"step": 24830
|
| 138978 |
+
},
|
| 138979 |
+
{
|
| 138980 |
+
"epoch": 201.65,
|
| 138981 |
+
"learning_rate": 9.61502423263328e-06,
|
| 138982 |
+
"loss": 0.9715,
|
| 138983 |
+
"step": 24840
|
| 138984 |
+
},
|
| 138985 |
+
{
|
| 138986 |
+
"epoch": 201.73,
|
| 138987 |
+
"learning_rate": 9.61486268174475e-06,
|
| 138988 |
+
"loss": 0.4949,
|
| 138989 |
+
"step": 24850
|
| 138990 |
+
},
|
| 138991 |
+
{
|
| 138992 |
+
"epoch": 201.81,
|
| 138993 |
+
"learning_rate": 9.614701130856222e-06,
|
| 138994 |
+
"loss": 1.0068,
|
| 138995 |
+
"step": 24860
|
| 138996 |
+
},
|
| 138997 |
+
{
|
| 138998 |
+
"epoch": 201.89,
|
| 138999 |
+
"learning_rate": 9.614539579967692e-06,
|
| 139000 |
+
"loss": 0.4748,
|
| 139001 |
+
"step": 24870
|
| 139002 |
+
},
|
| 139003 |
+
{
|
| 139004 |
+
"epoch": 201.97,
|
| 139005 |
+
"learning_rate": 9.614378029079162e-06,
|
| 139006 |
+
"loss": 0.606,
|
| 139007 |
+
"step": 24880
|
| 139008 |
+
},
|
| 139009 |
+
{
|
| 139010 |
+
"epoch": 202.0,
|
| 139011 |
+
"eval_loss": 0.5188912749290466,
|
| 139012 |
+
"eval_runtime": 41.1958,
|
| 139013 |
+
"eval_samples_per_second": 20.512,
|
| 139014 |
+
"eval_steps_per_second": 0.655,
|
| 139015 |
+
"eval_wer": 0.23777341762953275,
|
| 139016 |
+
"step": 24883
|
| 139017 |
+
},
|
| 139018 |
+
{
|
| 139019 |
+
"epoch": 200.06,
|
| 139020 |
+
"learning_rate": 9.614216478190632e-06,
|
| 139021 |
+
"loss": 0.5252,
|
| 139022 |
+
"step": 24890
|
| 139023 |
+
},
|
| 139024 |
+
{
|
| 139025 |
+
"epoch": 200.14,
|
| 139026 |
+
"learning_rate": 9.614054927302102e-06,
|
| 139027 |
+
"loss": 0.564,
|
| 139028 |
+
"step": 24900
|
| 139029 |
+
},
|
| 139030 |
+
{
|
| 139031 |
+
"epoch": 200.22,
|
| 139032 |
+
"learning_rate": 9.613893376413572e-06,
|
| 139033 |
+
"loss": 0.9814,
|
| 139034 |
+
"step": 24910
|
| 139035 |
+
},
|
| 139036 |
+
{
|
| 139037 |
+
"epoch": 200.3,
|
| 139038 |
+
"learning_rate": 9.613731825525042e-06,
|
| 139039 |
+
"loss": 0.4039,
|
| 139040 |
+
"step": 24920
|
| 139041 |
+
},
|
| 139042 |
+
{
|
| 139043 |
+
"epoch": 200.38,
|
| 139044 |
+
"learning_rate": 9.613570274636511e-06,
|
| 139045 |
+
"loss": 0.5923,
|
| 139046 |
+
"step": 24930
|
| 139047 |
+
},
|
| 139048 |
+
{
|
| 139049 |
+
"epoch": 200.46,
|
| 139050 |
+
"learning_rate": 9.613408723747981e-06,
|
| 139051 |
+
"loss": 0.9005,
|
| 139052 |
+
"step": 24940
|
| 139053 |
+
},
|
| 139054 |
+
{
|
| 139055 |
+
"epoch": 200.54,
|
| 139056 |
+
"learning_rate": 9.613247172859451e-06,
|
| 139057 |
+
"loss": 0.4075,
|
| 139058 |
+
"step": 24950
|
| 139059 |
+
},
|
| 139060 |
+
{
|
| 139061 |
+
"epoch": 200.62,
|
| 139062 |
+
"learning_rate": 9.613085621970921e-06,
|
| 139063 |
+
"loss": 1.0365,
|
| 139064 |
+
"step": 24960
|
| 139065 |
+
},
|
| 139066 |
+
{
|
| 139067 |
+
"epoch": 200.7,
|
| 139068 |
+
"learning_rate": 9.612924071082391e-06,
|
| 139069 |
+
"loss": 0.4891,
|
| 139070 |
+
"step": 24970
|
| 139071 |
+
},
|
| 139072 |
+
{
|
| 139073 |
+
"epoch": 200.78,
|
| 139074 |
+
"learning_rate": 9.612762520193863e-06,
|
| 139075 |
+
"loss": 0.6625,
|
| 139076 |
+
"step": 24980
|
| 139077 |
+
},
|
| 139078 |
+
{
|
| 139079 |
+
"epoch": 200.86,
|
| 139080 |
+
"learning_rate": 9.612600969305333e-06,
|
| 139081 |
+
"loss": 0.8385,
|
| 139082 |
+
"step": 24990
|
| 139083 |
+
},
|
| 139084 |
+
{
|
| 139085 |
+
"epoch": 200.94,
|
| 139086 |
+
"learning_rate": 9.612439418416803e-06,
|
| 139087 |
+
"loss": 0.5504,
|
| 139088 |
+
"step": 25000
|
| 139089 |
+
},
|
| 139090 |
+
{
|
| 139091 |
+
"epoch": 201.0,
|
| 139092 |
+
"eval_loss": 0.5322402715682983,
|
| 139093 |
+
"eval_runtime": 39.5678,
|
| 139094 |
+
"eval_samples_per_second": 21.33,
|
| 139095 |
+
"eval_steps_per_second": 0.682,
|
| 139096 |
+
"eval_wer": 0.22988161246815525,
|
| 139097 |
+
"step": 25007
|
| 139098 |
+
},
|
| 139099 |
+
{
|
| 139100 |
+
"epoch": 200.02,
|
| 139101 |
+
"learning_rate": 9.612277867528273e-06,
|
| 139102 |
+
"loss": 0.4325,
|
| 139103 |
+
"step": 25010
|
| 139104 |
+
},
|
| 139105 |
+
{
|
| 139106 |
+
"epoch": 200.1,
|
| 139107 |
+
"learning_rate": 9.612116316639743e-06,
|
| 139108 |
+
"loss": 0.4277,
|
| 139109 |
+
"step": 25020
|
| 139110 |
+
},
|
| 139111 |
+
{
|
| 139112 |
+
"epoch": 200.18,
|
| 139113 |
+
"learning_rate": 9.611954765751213e-06,
|
| 139114 |
+
"loss": 0.6847,
|
| 139115 |
+
"step": 25030
|
| 139116 |
+
},
|
| 139117 |
+
{
|
| 139118 |
+
"epoch": 200.26,
|
| 139119 |
+
"learning_rate": 9.611793214862683e-06,
|
| 139120 |
+
"loss": 0.8183,
|
| 139121 |
+
"step": 25040
|
| 139122 |
+
},
|
| 139123 |
+
{
|
| 139124 |
+
"epoch": 200.34,
|
| 139125 |
+
"learning_rate": 9.611631663974153e-06,
|
| 139126 |
+
"loss": 0.4621,
|
| 139127 |
+
"step": 25050
|
| 139128 |
+
},
|
| 139129 |
+
{
|
| 139130 |
+
"epoch": 200.42,
|
| 139131 |
+
"learning_rate": 9.611470113085623e-06,
|
| 139132 |
+
"loss": 0.9832,
|
| 139133 |
+
"step": 25060
|
| 139134 |
+
},
|
| 139135 |
+
{
|
| 139136 |
+
"epoch": 200.5,
|
| 139137 |
+
"learning_rate": 9.611308562197093e-06,
|
| 139138 |
+
"loss": 0.4897,
|
| 139139 |
+
"step": 25070
|
| 139140 |
+
},
|
| 139141 |
+
{
|
| 139142 |
+
"epoch": 200.58,
|
| 139143 |
+
"learning_rate": 9.611147011308563e-06,
|
| 139144 |
+
"loss": 1.0011,
|
| 139145 |
+
"step": 25080
|
| 139146 |
+
},
|
| 139147 |
+
{
|
| 139148 |
+
"epoch": 200.66,
|
| 139149 |
+
"learning_rate": 9.610985460420033e-06,
|
| 139150 |
+
"loss": 0.7532,
|
| 139151 |
+
"step": 25090
|
| 139152 |
+
},
|
| 139153 |
+
{
|
| 139154 |
+
"epoch": 200.74,
|
| 139155 |
+
"learning_rate": 9.610823909531504e-06,
|
| 139156 |
+
"loss": 0.4999,
|
| 139157 |
+
"step": 25100
|
| 139158 |
+
},
|
| 139159 |
+
{
|
| 139160 |
+
"epoch": 200.82,
|
| 139161 |
+
"learning_rate": 9.610662358642974e-06,
|
| 139162 |
+
"loss": 1.0194,
|
| 139163 |
+
"step": 25110
|
| 139164 |
+
},
|
| 139165 |
+
{
|
| 139166 |
+
"epoch": 200.9,
|
| 139167 |
+
"learning_rate": 9.610500807754444e-06,
|
| 139168 |
+
"loss": 0.4002,
|
| 139169 |
+
"step": 25120
|
| 139170 |
+
},
|
| 139171 |
+
{
|
| 139172 |
+
"epoch": 200.98,
|
| 139173 |
+
"learning_rate": 9.610339256865914e-06,
|
| 139174 |
+
"loss": 0.7423,
|
| 139175 |
+
"step": 25130
|
| 139176 |
+
},
|
| 139177 |
+
{
|
| 139178 |
+
"epoch": 201.0,
|
| 139179 |
+
"eval_loss": 0.5457486510276794,
|
| 139180 |
+
"eval_runtime": 41.422,
|
| 139181 |
+
"eval_samples_per_second": 20.4,
|
| 139182 |
+
"eval_steps_per_second": 0.652,
|
| 139183 |
+
"eval_wer": 0.23441176470588235,
|
| 139184 |
+
"step": 25132
|
| 139185 |
}
|
| 139186 |
],
|
| 139187 |
+
"max_steps": 625000,
|
| 139188 |
"num_train_epochs": 5000,
|
| 139189 |
+
"total_flos": 7.072140303112056e+19,
|
| 139190 |
"trial_name": null,
|
| 139191 |
"trial_params": null
|
| 139192 |
}
|
model-bin/finetune/base/{checkpoint-24512 → checkpoint-25132}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629601332.9347947/events.out.tfevents.1629601332.91f414e9573a.903.31
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2569795065e65aca295df674d7cd40ac5c75d62731663aa4a41416b6ad6d11e
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629601981.3327703/events.out.tfevents.1629601981.91f414e9573a.903.33
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:625d5558a44c45a6a410940cb20c30c65997879a538b4ee21d1ecff4ca6ef996
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629602645.363557/events.out.tfevents.1629602645.91f414e9573a.903.35
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5030320eeb583b6d0cb4209802e2dfaf299ff51353907b68fd66bd3cb523b353
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629603289.4152238/events.out.tfevents.1629603289.91f414e9573a.903.37
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdfbe4b97202be110a618eeb63f3e4149512af74b83cd5c9d3335ccc11d314e4
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629603939.0035386/events.out.tfevents.1629603939.91f414e9573a.903.39
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:685c58faa4329360d82036894236ea72473be846e0e8a903515396f8b90413ce
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629601332.91f414e9573a.903.30
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:850a5f1051f96c03ea0446eee1a06df1c177bd13bc04c3b773c2c05ada81351f
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629601981.91f414e9573a.903.32
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea3241715233b94e8132f18f774557df051a4b724661a7df7db188feb8ce4148
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629602645.91f414e9573a.903.34
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdaf815fe34c9592cf48f15f7d6b97f5da2b14554cd4ce253bd4b9580e2162fe
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629603289.91f414e9573a.903.36
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b24344a5972f7a151a4a3af2f2054a0098730babef74f82f1d463d406aab706
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629603938.91f414e9573a.903.38
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a61866c3c9778fbe05a2ca3e209743293131a387c9707117b5921002aaa9c66e
|
| 3 |
+
size 6703
|