elsayedissa
commited on
Commit
•
42e75bc
1
Parent(s):
5cf3888
Training in progress, step 4000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +252 -3
- pytorch_model.bin +1 -1
- runs/Jan28_23-42-14_gpu07.cyverse.org/events.out.tfevents.1674974582.gpu07.cyverse.org.94170.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 12347192855
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cabcd18d745237ccff0ec1f82242c3cf6523964b69f61c6d491e0dcca8c96bd7
|
3 |
size 12347192855
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6173655480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6744d734b49bb04f2a83a82c65c40351e020bce2add378d9abffb9d286d369c7
|
3 |
size 6173655480
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9719089c9777993e0b77b3d1ee31f8b1880df71d36ecfa484ab6990dbdfc6a8
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f950b784a3ad9098996d53ce7727828e81f8df26d9869581909648eda25b95a
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:285522fdbcf7692ca0fd2c300f90f1d4ac21d59ac64354db24bfa3599d4d3173
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.7431560204762965,
|
3 |
"best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-japanese-24h/checkpoint-3000",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -753,11 +753,260 @@
|
|
753 |
"eval_steps_per_second": 0.164,
|
754 |
"eval_wer": 0.7431560204762965,
|
755 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
756 |
}
|
757 |
],
|
758 |
"max_steps": 5000,
|
759 |
"num_train_epochs": 39,
|
760 |
-
"total_flos":
|
761 |
"trial_name": null,
|
762 |
"trial_params": null
|
763 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.7431560204762965,
|
3 |
"best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-japanese-24h/checkpoint-3000",
|
4 |
+
"epoch": 30.53435114503817,
|
5 |
+
"global_step": 4000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
753 |
"eval_steps_per_second": 0.164,
|
754 |
"eval_wer": 0.7431560204762965,
|
755 |
"step": 3000
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 23.09,
|
759 |
+
"learning_rate": 4.397777777777778e-06,
|
760 |
+
"loss": 0.0002,
|
761 |
+
"step": 3025
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 23.28,
|
765 |
+
"learning_rate": 4.3422222222222225e-06,
|
766 |
+
"loss": 0.0002,
|
767 |
+
"step": 3050
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 23.47,
|
771 |
+
"learning_rate": 4.2866666666666666e-06,
|
772 |
+
"loss": 0.0002,
|
773 |
+
"step": 3075
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 23.66,
|
777 |
+
"learning_rate": 4.2311111111111114e-06,
|
778 |
+
"loss": 0.0002,
|
779 |
+
"step": 3100
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 23.85,
|
783 |
+
"learning_rate": 4.175555555555556e-06,
|
784 |
+
"loss": 0.0002,
|
785 |
+
"step": 3125
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 24.05,
|
789 |
+
"learning_rate": 4.12e-06,
|
790 |
+
"loss": 0.0002,
|
791 |
+
"step": 3150
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 24.24,
|
795 |
+
"learning_rate": 4.064444444444444e-06,
|
796 |
+
"loss": 0.0002,
|
797 |
+
"step": 3175
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 24.43,
|
801 |
+
"learning_rate": 4.008888888888889e-06,
|
802 |
+
"loss": 0.0002,
|
803 |
+
"step": 3200
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 24.62,
|
807 |
+
"learning_rate": 3.953333333333333e-06,
|
808 |
+
"loss": 0.0002,
|
809 |
+
"step": 3225
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 24.81,
|
813 |
+
"learning_rate": 3.897777777777778e-06,
|
814 |
+
"loss": 0.0002,
|
815 |
+
"step": 3250
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 25.0,
|
819 |
+
"learning_rate": 3.842222222222223e-06,
|
820 |
+
"loss": 0.0002,
|
821 |
+
"step": 3275
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 25.19,
|
825 |
+
"learning_rate": 3.7866666666666667e-06,
|
826 |
+
"loss": 0.0002,
|
827 |
+
"step": 3300
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 25.38,
|
831 |
+
"learning_rate": 3.7311111111111116e-06,
|
832 |
+
"loss": 0.0002,
|
833 |
+
"step": 3325
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 25.57,
|
837 |
+
"learning_rate": 3.675555555555556e-06,
|
838 |
+
"loss": 0.0002,
|
839 |
+
"step": 3350
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 25.76,
|
843 |
+
"learning_rate": 3.62e-06,
|
844 |
+
"loss": 0.0002,
|
845 |
+
"step": 3375
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 25.95,
|
849 |
+
"learning_rate": 3.564444444444445e-06,
|
850 |
+
"loss": 0.0002,
|
851 |
+
"step": 3400
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 26.15,
|
855 |
+
"learning_rate": 3.508888888888889e-06,
|
856 |
+
"loss": 0.0002,
|
857 |
+
"step": 3425
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 26.34,
|
861 |
+
"learning_rate": 3.4533333333333334e-06,
|
862 |
+
"loss": 0.0002,
|
863 |
+
"step": 3450
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 26.53,
|
867 |
+
"learning_rate": 3.3977777777777783e-06,
|
868 |
+
"loss": 0.0002,
|
869 |
+
"step": 3475
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 26.72,
|
873 |
+
"learning_rate": 3.3422222222222224e-06,
|
874 |
+
"loss": 0.0002,
|
875 |
+
"step": 3500
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 26.91,
|
879 |
+
"learning_rate": 3.286666666666667e-06,
|
880 |
+
"loss": 0.0002,
|
881 |
+
"step": 3525
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 27.1,
|
885 |
+
"learning_rate": 3.2311111111111117e-06,
|
886 |
+
"loss": 0.0002,
|
887 |
+
"step": 3550
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 27.29,
|
891 |
+
"learning_rate": 3.1755555555555557e-06,
|
892 |
+
"loss": 0.0002,
|
893 |
+
"step": 3575
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 27.48,
|
897 |
+
"learning_rate": 3.12e-06,
|
898 |
+
"loss": 0.0002,
|
899 |
+
"step": 3600
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 27.67,
|
903 |
+
"learning_rate": 3.064444444444445e-06,
|
904 |
+
"loss": 0.0002,
|
905 |
+
"step": 3625
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 27.86,
|
909 |
+
"learning_rate": 3.008888888888889e-06,
|
910 |
+
"loss": 0.0002,
|
911 |
+
"step": 3650
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 28.05,
|
915 |
+
"learning_rate": 2.9533333333333336e-06,
|
916 |
+
"loss": 0.0002,
|
917 |
+
"step": 3675
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 28.24,
|
921 |
+
"learning_rate": 2.8977777777777785e-06,
|
922 |
+
"loss": 0.0002,
|
923 |
+
"step": 3700
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 28.44,
|
927 |
+
"learning_rate": 2.8422222222222225e-06,
|
928 |
+
"loss": 0.0002,
|
929 |
+
"step": 3725
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 28.63,
|
933 |
+
"learning_rate": 2.786666666666667e-06,
|
934 |
+
"loss": 0.0002,
|
935 |
+
"step": 3750
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 28.82,
|
939 |
+
"learning_rate": 2.7311111111111114e-06,
|
940 |
+
"loss": 0.0002,
|
941 |
+
"step": 3775
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 29.01,
|
945 |
+
"learning_rate": 2.675555555555556e-06,
|
946 |
+
"loss": 0.0002,
|
947 |
+
"step": 3800
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 29.2,
|
951 |
+
"learning_rate": 2.6200000000000003e-06,
|
952 |
+
"loss": 0.0002,
|
953 |
+
"step": 3825
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 29.39,
|
957 |
+
"learning_rate": 2.5644444444444444e-06,
|
958 |
+
"loss": 0.0002,
|
959 |
+
"step": 3850
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 29.58,
|
963 |
+
"learning_rate": 2.5088888888888892e-06,
|
964 |
+
"loss": 0.0002,
|
965 |
+
"step": 3875
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 29.77,
|
969 |
+
"learning_rate": 2.4533333333333333e-06,
|
970 |
+
"loss": 0.0002,
|
971 |
+
"step": 3900
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 29.96,
|
975 |
+
"learning_rate": 2.397777777777778e-06,
|
976 |
+
"loss": 0.0002,
|
977 |
+
"step": 3925
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 30.15,
|
981 |
+
"learning_rate": 2.342222222222222e-06,
|
982 |
+
"loss": 0.0002,
|
983 |
+
"step": 3950
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 30.34,
|
987 |
+
"learning_rate": 2.2866666666666667e-06,
|
988 |
+
"loss": 0.0002,
|
989 |
+
"step": 3975
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 30.53,
|
993 |
+
"learning_rate": 2.2311111111111115e-06,
|
994 |
+
"loss": 0.0002,
|
995 |
+
"step": 4000
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 30.53,
|
999 |
+
"eval_loss": 0.4122720956802368,
|
1000 |
+
"eval_runtime": 1713.6333,
|
1001 |
+
"eval_samples_per_second": 2.617,
|
1002 |
+
"eval_steps_per_second": 0.164,
|
1003 |
+
"eval_wer": 0.7442688626752726,
|
1004 |
+
"step": 4000
|
1005 |
}
|
1006 |
],
|
1007 |
"max_steps": 5000,
|
1008 |
"num_train_epochs": 39,
|
1009 |
+
"total_flos": 4.2176792328192e+20,
|
1010 |
"trial_name": null,
|
1011 |
"trial_params": null
|
1012 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6173655480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6744d734b49bb04f2a83a82c65c40351e020bce2add378d9abffb9d286d369c7
|
3 |
size 6173655480
|
runs/Jan28_23-42-14_gpu07.cyverse.org/events.out.tfevents.1674974582.gpu07.cyverse.org.94170.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e6183fac4cb12f0942d286f36bbc9314f13fcf6e7786a873e26691f74d646f8
|
3 |
+
size 30796
|