elsayedissa
commited on
Commit
·
9d744d9
1
Parent(s):
abd3c44
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_23-19-38_gpu07.cyverse.org/events.out.tfevents.1674973221.gpu07.cyverse.org.79624.0 +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:eb55c91b103628f5be95896e1614ad2bc546605cf6236721f0622634adcd689e
|
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 sha256:43e47f260dd1b8c823dbd2ec8239c2bf713fcf544791f3f0b436803f94dc5f60
|
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 sha256:640548085210c8490898cfba017d8bd1baf3553a19e27f9821a34801ec2b3a88
|
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 sha256:2f245e4bee87e5915781db8b8b7a3b00fd2ef949a525de0dd949823efc21b2f4
|
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 sha256:455fa7fbc6657e0c30aabe935c34b61e115426f0bbb7f1106461aac75d23221b
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.4207764409383577,
|
3 |
"best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-arabic-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": 0.149,
|
754 |
"eval_wer": 0.4207764409383577,
|
755 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
756 |
}
|
757 |
],
|
758 |
"max_steps": 5000,
|
759 |
"num_train_epochs": 9,
|
760 |
-
"total_flos":
|
761 |
"trial_name": null,
|
762 |
"trial_params": null
|
763 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.4207764409383577,
|
3 |
"best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-arabic-24h/checkpoint-3000",
|
4 |
+
"epoch": 7.1301247771836005,
|
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": 0.149,
|
754 |
"eval_wer": 0.4207764409383577,
|
755 |
"step": 3000
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 5.39,
|
759 |
+
"learning_rate": 4.402222222222223e-06,
|
760 |
+
"loss": 0.0152,
|
761 |
+
"step": 3025
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 5.44,
|
765 |
+
"learning_rate": 4.346666666666667e-06,
|
766 |
+
"loss": 0.0143,
|
767 |
+
"step": 3050
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 5.48,
|
771 |
+
"learning_rate": 4.291111111111112e-06,
|
772 |
+
"loss": 0.0143,
|
773 |
+
"step": 3075
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 5.53,
|
777 |
+
"learning_rate": 4.235555555555556e-06,
|
778 |
+
"loss": 0.0136,
|
779 |
+
"step": 3100
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 5.57,
|
783 |
+
"learning_rate": 4.18e-06,
|
784 |
+
"loss": 0.0173,
|
785 |
+
"step": 3125
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 5.61,
|
789 |
+
"learning_rate": 4.124444444444445e-06,
|
790 |
+
"loss": 0.0136,
|
791 |
+
"step": 3150
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 5.66,
|
795 |
+
"learning_rate": 4.0688888888888896e-06,
|
796 |
+
"loss": 0.0154,
|
797 |
+
"step": 3175
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 5.7,
|
801 |
+
"learning_rate": 4.013333333333334e-06,
|
802 |
+
"loss": 0.0119,
|
803 |
+
"step": 3200
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 5.75,
|
807 |
+
"learning_rate": 3.9577777777777785e-06,
|
808 |
+
"loss": 0.0138,
|
809 |
+
"step": 3225
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 5.79,
|
813 |
+
"learning_rate": 3.9022222222222225e-06,
|
814 |
+
"loss": 0.0131,
|
815 |
+
"step": 3250
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 5.84,
|
819 |
+
"learning_rate": 3.8466666666666665e-06,
|
820 |
+
"loss": 0.0154,
|
821 |
+
"step": 3275
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 5.88,
|
825 |
+
"learning_rate": 3.7911111111111114e-06,
|
826 |
+
"loss": 0.0134,
|
827 |
+
"step": 3300
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 5.93,
|
831 |
+
"learning_rate": 3.7355555555555555e-06,
|
832 |
+
"loss": 0.0145,
|
833 |
+
"step": 3325
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 5.97,
|
837 |
+
"learning_rate": 3.6800000000000003e-06,
|
838 |
+
"loss": 0.0125,
|
839 |
+
"step": 3350
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 6.02,
|
843 |
+
"learning_rate": 3.624444444444445e-06,
|
844 |
+
"loss": 0.0111,
|
845 |
+
"step": 3375
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 6.06,
|
849 |
+
"learning_rate": 3.568888888888889e-06,
|
850 |
+
"loss": 0.0072,
|
851 |
+
"step": 3400
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 6.11,
|
855 |
+
"learning_rate": 3.5133333333333337e-06,
|
856 |
+
"loss": 0.0072,
|
857 |
+
"step": 3425
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 6.15,
|
861 |
+
"learning_rate": 3.457777777777778e-06,
|
862 |
+
"loss": 0.0068,
|
863 |
+
"step": 3450
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 6.19,
|
867 |
+
"learning_rate": 3.4022222222222222e-06,
|
868 |
+
"loss": 0.0076,
|
869 |
+
"step": 3475
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 6.24,
|
873 |
+
"learning_rate": 3.346666666666667e-06,
|
874 |
+
"loss": 0.0068,
|
875 |
+
"step": 3500
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 6.28,
|
879 |
+
"learning_rate": 3.2911111111111116e-06,
|
880 |
+
"loss": 0.0077,
|
881 |
+
"step": 3525
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 6.33,
|
885 |
+
"learning_rate": 3.2355555555555556e-06,
|
886 |
+
"loss": 0.0072,
|
887 |
+
"step": 3550
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 6.37,
|
891 |
+
"learning_rate": 3.1800000000000005e-06,
|
892 |
+
"loss": 0.0082,
|
893 |
+
"step": 3575
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 6.42,
|
897 |
+
"learning_rate": 3.124444444444445e-06,
|
898 |
+
"loss": 0.0064,
|
899 |
+
"step": 3600
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 6.46,
|
903 |
+
"learning_rate": 3.068888888888889e-06,
|
904 |
+
"loss": 0.0072,
|
905 |
+
"step": 3625
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 6.51,
|
909 |
+
"learning_rate": 3.013333333333334e-06,
|
910 |
+
"loss": 0.0063,
|
911 |
+
"step": 3650
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 6.55,
|
915 |
+
"learning_rate": 2.957777777777778e-06,
|
916 |
+
"loss": 0.0082,
|
917 |
+
"step": 3675
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 6.6,
|
921 |
+
"learning_rate": 2.9022222222222223e-06,
|
922 |
+
"loss": 0.0054,
|
923 |
+
"step": 3700
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 6.64,
|
927 |
+
"learning_rate": 2.8466666666666672e-06,
|
928 |
+
"loss": 0.0074,
|
929 |
+
"step": 3725
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 6.68,
|
933 |
+
"learning_rate": 2.7911111111111113e-06,
|
934 |
+
"loss": 0.006,
|
935 |
+
"step": 3750
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 6.73,
|
939 |
+
"learning_rate": 2.7355555555555557e-06,
|
940 |
+
"loss": 0.0074,
|
941 |
+
"step": 3775
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 6.77,
|
945 |
+
"learning_rate": 2.68e-06,
|
946 |
+
"loss": 0.0061,
|
947 |
+
"step": 3800
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 6.82,
|
951 |
+
"learning_rate": 2.6244444444444446e-06,
|
952 |
+
"loss": 0.0089,
|
953 |
+
"step": 3825
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 6.86,
|
957 |
+
"learning_rate": 2.568888888888889e-06,
|
958 |
+
"loss": 0.0066,
|
959 |
+
"step": 3850
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 6.91,
|
963 |
+
"learning_rate": 2.5133333333333336e-06,
|
964 |
+
"loss": 0.0071,
|
965 |
+
"step": 3875
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 6.95,
|
969 |
+
"learning_rate": 2.457777777777778e-06,
|
970 |
+
"loss": 0.0065,
|
971 |
+
"step": 3900
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 7.0,
|
975 |
+
"learning_rate": 2.4022222222222225e-06,
|
976 |
+
"loss": 0.0053,
|
977 |
+
"step": 3925
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 7.04,
|
981 |
+
"learning_rate": 2.346666666666667e-06,
|
982 |
+
"loss": 0.0049,
|
983 |
+
"step": 3950
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 7.09,
|
987 |
+
"learning_rate": 2.2911111111111114e-06,
|
988 |
+
"loss": 0.0021,
|
989 |
+
"step": 3975
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 7.13,
|
993 |
+
"learning_rate": 2.235555555555556e-06,
|
994 |
+
"loss": 0.004,
|
995 |
+
"step": 4000
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 7.13,
|
999 |
+
"eval_loss": 0.3123507499694824,
|
1000 |
+
"eval_runtime": 4382.7686,
|
1001 |
+
"eval_samples_per_second": 2.382,
|
1002 |
+
"eval_steps_per_second": 0.149,
|
1003 |
+
"eval_wer": 0.4251609673577187,
|
1004 |
+
"step": 4000
|
1005 |
}
|
1006 |
],
|
1007 |
"max_steps": 5000,
|
1008 |
"num_train_epochs": 9,
|
1009 |
+
"total_flos": 4.245301687799808e+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 sha256:43e47f260dd1b8c823dbd2ec8239c2bf713fcf544791f3f0b436803f94dc5f60
|
3 |
size 6173655480
|
runs/Jan28_23-19-38_gpu07.cyverse.org/events.out.tfevents.1674973221.gpu07.cyverse.org.79624.0
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:c20785d93f929c6776fb55f65c13ef81d9ad4f46d8a0e0fdba027f22601ec447
|
3 |
+
size 30790
|