Upload 11 files
Browse files- config.json +1 -1
- generation_config.json +3 -2
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +2 -2
- scheduler.pt +1 -1
- trainer_state.json +252 -3
- training_args.bin +1 -1
config.json
CHANGED
@@ -43,7 +43,7 @@
|
|
43 |
"num_mel_bins": 128,
|
44 |
"pad_token_id": 50256,
|
45 |
"scale_embedding": false,
|
46 |
-
"torch_dtype": "
|
47 |
"transformers_version": "4.37.0.dev0",
|
48 |
"use_cache": true,
|
49 |
"use_weighted_layer_sum": false,
|
|
|
43 |
"num_mel_bins": 128,
|
44 |
"pad_token_id": 50256,
|
45 |
"scale_embedding": false,
|
46 |
+
"torch_dtype": "float32",
|
47 |
"transformers_version": "4.37.0.dev0",
|
48 |
"use_cache": true,
|
49 |
"use_weighted_layer_sum": false,
|
generation_config.json
CHANGED
@@ -55,7 +55,7 @@
|
|
55 |
],
|
56 |
[
|
57 |
2,
|
58 |
-
|
59 |
]
|
60 |
],
|
61 |
"is_multilingual": true,
|
@@ -161,10 +161,11 @@
|
|
161 |
"<|yue|>": 50358,
|
162 |
"<|zh|>": 50260
|
163 |
},
|
164 |
-
"max_initial_timestamp_index":
|
165 |
"max_length": 448,
|
166 |
"no_timestamps_token_id": 50364,
|
167 |
"pad_token_id": 50257,
|
|
|
168 |
"return_timestamps": false,
|
169 |
"suppress_tokens": [
|
170 |
1,
|
|
|
55 |
],
|
56 |
[
|
57 |
2,
|
58 |
+
50359
|
59 |
]
|
60 |
],
|
61 |
"is_multilingual": true,
|
|
|
161 |
"<|yue|>": 50358,
|
162 |
"<|zh|>": 50260
|
163 |
},
|
164 |
+
"max_initial_timestamp_index": 50,
|
165 |
"max_length": 448,
|
166 |
"no_timestamps_token_id": 50364,
|
167 |
"pad_token_id": 50257,
|
168 |
+
"prev_sot_token_id": 50362,
|
169 |
"return_timestamps": false,
|
170 |
"suppress_tokens": [
|
171 |
1,
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4993448880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fedb9cc896a6388bb4f5cddb373b7392782ec965512769af969c60e1af1a4e14
|
3 |
size 4993448880
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1180663192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c6b0edf383dba5a20a86c58366da587af2b11f57f3238809e22174428275ba2
|
3 |
size 1180663192
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 12333660476
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80e4f108eb5557c44d32434b4917e37c96c5a7f16fb94640266fc8260e5fd15e
|
3 |
size 12333660476
|
rng_state.pth
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 sha256:49966cb04e594c410fd0e18084a8363564e6ac46de2a7e2d0b5f4cc3add8b713
|
3 |
+
size 14308
|
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 sha256:063989716508e91f1978729efb82b7e19b19c1473686b3b12f8b0931dcd025b2
|
3 |
size 1064
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -754,6 +754,255 @@
|
|
754 |
"eval_steps_per_second": 0.006,
|
755 |
"eval_wer": 0.09970911441499677,
|
756 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
757 |
}
|
758 |
],
|
759 |
"logging_steps": 25,
|
@@ -761,7 +1010,7 @@
|
|
761 |
"num_input_tokens_seen": 0,
|
762 |
"num_train_epochs": 2,
|
763 |
"save_steps": 1000,
|
764 |
-
"total_flos":
|
765 |
"train_batch_size": 8,
|
766 |
"trial_name": null,
|
767 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.032258064516129,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 4000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
754 |
"eval_steps_per_second": 0.006,
|
755 |
"eval_wer": 0.09970911441499677,
|
756 |
"step": 3000
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.78,
|
760 |
+
"learning_rate": 6.59e-07,
|
761 |
+
"loss": 0.1334,
|
762 |
+
"step": 3025
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.79,
|
766 |
+
"learning_rate": 6.506666666666666e-07,
|
767 |
+
"loss": 0.1584,
|
768 |
+
"step": 3050
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.79,
|
772 |
+
"learning_rate": 6.423333333333333e-07,
|
773 |
+
"loss": 0.1331,
|
774 |
+
"step": 3075
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.8,
|
778 |
+
"learning_rate": 6.346666666666666e-07,
|
779 |
+
"loss": 0.1226,
|
780 |
+
"step": 3100
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.81,
|
784 |
+
"learning_rate": 6.263333333333332e-07,
|
785 |
+
"loss": 0.135,
|
786 |
+
"step": 3125
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.81,
|
790 |
+
"learning_rate": 6.18e-07,
|
791 |
+
"loss": 0.1538,
|
792 |
+
"step": 3150
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.82,
|
796 |
+
"learning_rate": 6.096666666666667e-07,
|
797 |
+
"loss": 0.1405,
|
798 |
+
"step": 3175
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.83,
|
802 |
+
"learning_rate": 6.013333333333334e-07,
|
803 |
+
"loss": 0.1534,
|
804 |
+
"step": 3200
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.83,
|
808 |
+
"learning_rate": 5.93e-07,
|
809 |
+
"loss": 0.1628,
|
810 |
+
"step": 3225
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.84,
|
814 |
+
"learning_rate": 5.846666666666667e-07,
|
815 |
+
"loss": 0.2002,
|
816 |
+
"step": 3250
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.85,
|
820 |
+
"learning_rate": 5.763333333333333e-07,
|
821 |
+
"loss": 0.1155,
|
822 |
+
"step": 3275
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.85,
|
826 |
+
"learning_rate": 5.679999999999999e-07,
|
827 |
+
"loss": 0.179,
|
828 |
+
"step": 3300
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.86,
|
832 |
+
"learning_rate": 5.596666666666666e-07,
|
833 |
+
"loss": 0.1471,
|
834 |
+
"step": 3325
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.86,
|
838 |
+
"learning_rate": 5.513333333333333e-07,
|
839 |
+
"loss": 0.1386,
|
840 |
+
"step": 3350
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 0.87,
|
844 |
+
"learning_rate": 5.43e-07,
|
845 |
+
"loss": 0.1185,
|
846 |
+
"step": 3375
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 0.88,
|
850 |
+
"learning_rate": 5.346666666666666e-07,
|
851 |
+
"loss": 0.1418,
|
852 |
+
"step": 3400
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 0.88,
|
856 |
+
"learning_rate": 5.263333333333333e-07,
|
857 |
+
"loss": 0.1015,
|
858 |
+
"step": 3425
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.89,
|
862 |
+
"learning_rate": 5.18e-07,
|
863 |
+
"loss": 0.1525,
|
864 |
+
"step": 3450
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.9,
|
868 |
+
"learning_rate": 5.096666666666667e-07,
|
869 |
+
"loss": 0.1212,
|
870 |
+
"step": 3475
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.9,
|
874 |
+
"learning_rate": 5.013333333333333e-07,
|
875 |
+
"loss": 0.1623,
|
876 |
+
"step": 3500
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 0.91,
|
880 |
+
"learning_rate": 4.93e-07,
|
881 |
+
"loss": 0.1178,
|
882 |
+
"step": 3525
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 0.92,
|
886 |
+
"learning_rate": 4.846666666666667e-07,
|
887 |
+
"loss": 0.1618,
|
888 |
+
"step": 3550
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 0.92,
|
892 |
+
"learning_rate": 4.763333333333333e-07,
|
893 |
+
"loss": 0.1187,
|
894 |
+
"step": 3575
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.93,
|
898 |
+
"learning_rate": 4.68e-07,
|
899 |
+
"loss": 0.1382,
|
900 |
+
"step": 3600
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.94,
|
904 |
+
"learning_rate": 4.5966666666666667e-07,
|
905 |
+
"loss": 0.1211,
|
906 |
+
"step": 3625
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.94,
|
910 |
+
"learning_rate": 4.5133333333333327e-07,
|
911 |
+
"loss": 0.1582,
|
912 |
+
"step": 3650
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.95,
|
916 |
+
"learning_rate": 4.43e-07,
|
917 |
+
"loss": 0.1201,
|
918 |
+
"step": 3675
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 0.95,
|
922 |
+
"learning_rate": 4.3466666666666664e-07,
|
923 |
+
"loss": 0.1571,
|
924 |
+
"step": 3700
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.96,
|
928 |
+
"learning_rate": 4.263333333333333e-07,
|
929 |
+
"loss": 0.1247,
|
930 |
+
"step": 3725
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 0.97,
|
934 |
+
"learning_rate": 4.1799999999999996e-07,
|
935 |
+
"loss": 0.1648,
|
936 |
+
"step": 3750
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 0.97,
|
940 |
+
"learning_rate": 4.0966666666666667e-07,
|
941 |
+
"loss": 0.1313,
|
942 |
+
"step": 3775
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 0.98,
|
946 |
+
"learning_rate": 4.0133333333333333e-07,
|
947 |
+
"loss": 0.1528,
|
948 |
+
"step": 3800
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.99,
|
952 |
+
"learning_rate": 3.93e-07,
|
953 |
+
"loss": 0.1252,
|
954 |
+
"step": 3825
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.99,
|
958 |
+
"learning_rate": 3.8466666666666664e-07,
|
959 |
+
"loss": 0.1674,
|
960 |
+
"step": 3850
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 1.0,
|
964 |
+
"learning_rate": 3.7633333333333335e-07,
|
965 |
+
"loss": 0.1192,
|
966 |
+
"step": 3875
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 1.01,
|
970 |
+
"learning_rate": 3.6799999999999996e-07,
|
971 |
+
"loss": 0.1054,
|
972 |
+
"step": 3900
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 1.01,
|
976 |
+
"learning_rate": 3.5966666666666667e-07,
|
977 |
+
"loss": 0.1353,
|
978 |
+
"step": 3925
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 1.02,
|
982 |
+
"learning_rate": 3.5133333333333333e-07,
|
983 |
+
"loss": 0.1004,
|
984 |
+
"step": 3950
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 1.03,
|
988 |
+
"learning_rate": 3.43e-07,
|
989 |
+
"loss": 0.1382,
|
990 |
+
"step": 3975
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 1.03,
|
994 |
+
"learning_rate": 3.3466666666666665e-07,
|
995 |
+
"loss": 0.0821,
|
996 |
+
"step": 4000
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 1.03,
|
1000 |
+
"eval_loss": 0.13208560645580292,
|
1001 |
+
"eval_runtime": 194476.4747,
|
1002 |
+
"eval_samples_per_second": 0.048,
|
1003 |
+
"eval_steps_per_second": 0.006,
|
1004 |
+
"eval_wer": 1.000743374272786,
|
1005 |
+
"step": 4000
|
1006 |
}
|
1007 |
],
|
1008 |
"logging_steps": 25,
|
|
|
1010 |
"num_input_tokens_seen": 0,
|
1011 |
"num_train_epochs": 2,
|
1012 |
"save_steps": 1000,
|
1013 |
+
"total_flos": 1.0871315081330688e+20,
|
1014 |
"train_batch_size": 8,
|
1015 |
"trial_name": null,
|
1016 |
"trial_params": null
|
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 sha256:8f665d772c299f2cf7e58571e6ed463fc30fe6fa27220a8ca365ab05354ee77f
|
3 |
size 4856
|