Training in progress, step 2600, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc9ce79fc599740aef87f7fd48706228015ab07b2a1dfd751d72c6184f855c03
|
3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1925064044
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d306912bc344aaf32285eaf9f48c11bfb51cf53853d6ee359fddf97240bd0bb9
|
3 |
size 1925064044
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdbc32589e7c655d36a5fb4597ce0c5aa1b6a41b9f31868102fdf367046c16aa
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:709fa179bb7fc9a25ddcbc282cb67b6963af0127c69eb4336b37c5b7c5aba9e9
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
-
"epoch": 4.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -799,6 +799,72 @@
|
|
799 |
"eval_steps_per_second": 0.106,
|
800 |
"eval_wer": 179.64503605102607,
|
801 |
"step": 2400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
802 |
}
|
803 |
],
|
804 |
"logging_steps": 25,
|
@@ -806,7 +872,7 @@
|
|
806 |
"num_input_tokens_seen": 0,
|
807 |
"num_train_epochs": 8,
|
808 |
"save_steps": 100,
|
809 |
-
"total_flos": 2.
|
810 |
"trial_name": null,
|
811 |
"trial_params": null
|
812 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
+
"epoch": 4.961832061068702,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
799 |
"eval_steps_per_second": 0.106,
|
800 |
"eval_wer": 179.64503605102607,
|
801 |
"step": 2400
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 4.63,
|
805 |
+
"learning_rate": 4.5171428571428575e-06,
|
806 |
+
"loss": 0.0165,
|
807 |
+
"step": 2425
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 4.68,
|
811 |
+
"learning_rate": 4.445714285714286e-06,
|
812 |
+
"loss": 0.0159,
|
813 |
+
"step": 2450
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 4.72,
|
817 |
+
"learning_rate": 4.374285714285715e-06,
|
818 |
+
"loss": 0.0161,
|
819 |
+
"step": 2475
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 4.77,
|
823 |
+
"learning_rate": 4.302857142857143e-06,
|
824 |
+
"loss": 0.0172,
|
825 |
+
"step": 2500
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 4.77,
|
829 |
+
"eval_loss": 0.418465793132782,
|
830 |
+
"eval_runtime": 1826.6437,
|
831 |
+
"eval_samples_per_second": 0.821,
|
832 |
+
"eval_steps_per_second": 0.103,
|
833 |
+
"eval_wer": 186.09262340543538,
|
834 |
+
"step": 2500
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 4.82,
|
838 |
+
"learning_rate": 4.231428571428572e-06,
|
839 |
+
"loss": 0.016,
|
840 |
+
"step": 2525
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 4.87,
|
844 |
+
"learning_rate": 4.16e-06,
|
845 |
+
"loss": 0.0163,
|
846 |
+
"step": 2550
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 4.91,
|
850 |
+
"learning_rate": 4.088571428571429e-06,
|
851 |
+
"loss": 0.0163,
|
852 |
+
"step": 2575
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 4.96,
|
856 |
+
"learning_rate": 4.017142857142857e-06,
|
857 |
+
"loss": 0.0142,
|
858 |
+
"step": 2600
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 4.96,
|
862 |
+
"eval_loss": 0.41750070452690125,
|
863 |
+
"eval_runtime": 1819.7416,
|
864 |
+
"eval_samples_per_second": 0.824,
|
865 |
+
"eval_steps_per_second": 0.103,
|
866 |
+
"eval_wer": 181.14254021075985,
|
867 |
+
"step": 2600
|
868 |
}
|
869 |
],
|
870 |
"logging_steps": 25,
|
|
|
872 |
"num_input_tokens_seen": 0,
|
873 |
"num_train_epochs": 8,
|
874 |
"save_steps": 100,
|
875 |
+
"total_flos": 2.400222491541504e+19,
|
876 |
"trial_name": null,
|
877 |
"trial_params": null
|
878 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96eac9b215a976aa2dd9548a4525c1b8963c1f6f7769df3b71271d00769da268
|
3 |
size 4856
|