Hugging Face's logo

JRHuy
/
whisper-small-vietnamese

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JRHuy commited on
Commit
9df37bb
•
1 Parent(s): f00b6c0

Training in progress, step 4000

Browse files
Files changed (7) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +253 -3
  6. pytorch_model.bin +1 -1
  7. runs/Aug21_16-43-21_8bad39564bfa/events.out.tfevents.1692636213.8bad39564bfa.55.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7cf542d1162861a412322de0843a71f9b7d2a2491fed87f740beafd324feb87
3
  size 1934161157
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907aac9c83b6b79968f0febc00dccd07a40b6d1fda09d66dc7fb8b344f3335d8
3
  size 1934161157
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aed36cd0774277c3bc7d2577938faa840a081b7219a5939e6d8e3f7908a9e51
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9444715d1c7dae1eff48b8c035739bfd6101a03c0047cdb26f72b4f864a81984
3
  size 967102729
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85dcd9588829e28a34b471fbefe47c5b729c37261cb017e050a2c52e69019df0
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bd79c6dc311729172b27086764740160249cf885002e068daabb1df29b526ba
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f375f0ec2d81d3bc0adbea21cfba80dd771ec303d1e16586405d497868a3b309
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05c5f02f34690b6cdc36257cc6f4b53027dee7ea004e5e07023153262401341
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 15.545946505787006,
3
  "best_model_checkpoint": "./whisper-small-vietnamese/checkpoint-3000",
4
- "epoch": 8.595988538681949,
5
- "global_step": 3000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -756,11 +756,261 @@
756
  "eval_steps_per_second": 0.099,
757
  "eval_wer": 15.545946505787006,
758
  "step": 3000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
759
  }
760
  ],
761
  "max_steps": 4000,
762
  "num_train_epochs": 12,
763
- "total_flos": 1.382439501692928e+19,
764
  "trial_name": null,
765
  "trial_params": null
766
  }
 
1
  {
2
  "best_metric": 15.545946505787006,
3
  "best_model_checkpoint": "./whisper-small-vietnamese/checkpoint-3000",
4
+ "epoch": 11.461318051575931,
5
+ "global_step": 4000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
756
  "eval_steps_per_second": 0.099,
757
  "eval_wer": 15.545946505787006,
758
  "step": 3000
759
+ },
760
+ {
761
+ "epoch": 8.67,
762
+ "learning_rate": 1e-05,
763
+ "loss": 0.0065,
764
+ "step": 3025
765
+ },
766
+ {
767
+ "epoch": 8.74,
768
+ "learning_rate": 1e-05,
769
+ "loss": 0.0068,
770
+ "step": 3050
771
+ },
772
+ {
773
+ "epoch": 8.81,
774
+ "learning_rate": 1e-05,
775
+ "loss": 0.0058,
776
+ "step": 3075
777
+ },
778
+ {
779
+ "epoch": 8.88,
780
+ "learning_rate": 1e-05,
781
+ "loss": 0.0066,
782
+ "step": 3100
783
+ },
784
+ {
785
+ "epoch": 8.95,
786
+ "learning_rate": 1e-05,
787
+ "loss": 0.0047,
788
+ "step": 3125
789
+ },
790
+ {
791
+ "epoch": 9.03,
792
+ "learning_rate": 1e-05,
793
+ "loss": 0.0041,
794
+ "step": 3150
795
+ },
796
+ {
797
+ "epoch": 9.1,
798
+ "learning_rate": 1e-05,
799
+ "loss": 0.0049,
800
+ "step": 3175
801
+ },
802
+ {
803
+ "epoch": 9.17,
804
+ "learning_rate": 1e-05,
805
+ "loss": 0.0049,
806
+ "step": 3200
807
+ },
808
+ {
809
+ "epoch": 9.24,
810
+ "learning_rate": 1e-05,
811
+ "loss": 0.0063,
812
+ "step": 3225
813
+ },
814
+ {
815
+ "epoch": 9.31,
816
+ "learning_rate": 1e-05,
817
+ "loss": 0.0059,
818
+ "step": 3250
819
+ },
820
+ {
821
+ "epoch": 9.38,
822
+ "learning_rate": 1e-05,
823
+ "loss": 0.0051,
824
+ "step": 3275
825
+ },
826
+ {
827
+ "epoch": 9.46,
828
+ "learning_rate": 1e-05,
829
+ "loss": 0.0053,
830
+ "step": 3300
831
+ },
832
+ {
833
+ "epoch": 9.53,
834
+ "learning_rate": 1e-05,
835
+ "loss": 0.0052,
836
+ "step": 3325
837
+ },
838
+ {
839
+ "epoch": 9.6,
840
+ "learning_rate": 1e-05,
841
+ "loss": 0.005,
842
+ "step": 3350
843
+ },
844
+ {
845
+ "epoch": 9.67,
846
+ "learning_rate": 1e-05,
847
+ "loss": 0.0047,
848
+ "step": 3375
849
+ },
850
+ {
851
+ "epoch": 9.74,
852
+ "learning_rate": 1e-05,
853
+ "loss": 0.0047,
854
+ "step": 3400
855
+ },
856
+ {
857
+ "epoch": 9.81,
858
+ "learning_rate": 1e-05,
859
+ "loss": 0.0049,
860
+ "step": 3425
861
+ },
862
+ {
863
+ "epoch": 9.89,
864
+ "learning_rate": 1e-05,
865
+ "loss": 0.006,
866
+ "step": 3450
867
+ },
868
+ {
869
+ "epoch": 9.96,
870
+ "learning_rate": 1e-05,
871
+ "loss": 0.0047,
872
+ "step": 3475
873
+ },
874
+ {
875
+ "epoch": 10.03,
876
+ "learning_rate": 1e-05,
877
+ "loss": 0.0059,
878
+ "step": 3500
879
+ },
880
+ {
881
+ "epoch": 10.1,
882
+ "learning_rate": 1e-05,
883
+ "loss": 0.0044,
884
+ "step": 3525
885
+ },
886
+ {
887
+ "epoch": 10.17,
888
+ "learning_rate": 1e-05,
889
+ "loss": 0.0034,
890
+ "step": 3550
891
+ },
892
+ {
893
+ "epoch": 10.24,
894
+ "learning_rate": 1e-05,
895
+ "loss": 0.004,
896
+ "step": 3575
897
+ },
898
+ {
899
+ "epoch": 10.32,
900
+ "learning_rate": 1e-05,
901
+ "loss": 0.0048,
902
+ "step": 3600
903
+ },
904
+ {
905
+ "epoch": 10.39,
906
+ "learning_rate": 1e-05,
907
+ "loss": 0.0029,
908
+ "step": 3625
909
+ },
910
+ {
911
+ "epoch": 10.46,
912
+ "learning_rate": 1e-05,
913
+ "loss": 0.0039,
914
+ "step": 3650
915
+ },
916
+ {
917
+ "epoch": 10.53,
918
+ "learning_rate": 1e-05,
919
+ "loss": 0.0047,
920
+ "step": 3675
921
+ },
922
+ {
923
+ "epoch": 10.6,
924
+ "learning_rate": 1e-05,
925
+ "loss": 0.0048,
926
+ "step": 3700
927
+ },
928
+ {
929
+ "epoch": 10.67,
930
+ "learning_rate": 1e-05,
931
+ "loss": 0.0036,
932
+ "step": 3725
933
+ },
934
+ {
935
+ "epoch": 10.74,
936
+ "learning_rate": 1e-05,
937
+ "loss": 0.0036,
938
+ "step": 3750
939
+ },
940
+ {
941
+ "epoch": 10.82,
942
+ "learning_rate": 1e-05,
943
+ "loss": 0.0065,
944
+ "step": 3775
945
+ },
946
+ {
947
+ "epoch": 10.89,
948
+ "learning_rate": 1e-05,
949
+ "loss": 0.0052,
950
+ "step": 3800
951
+ },
952
+ {
953
+ "epoch": 10.96,
954
+ "learning_rate": 1e-05,
955
+ "loss": 0.0047,
956
+ "step": 3825
957
+ },
958
+ {
959
+ "epoch": 11.03,
960
+ "learning_rate": 1e-05,
961
+ "loss": 0.0044,
962
+ "step": 3850
963
+ },
964
+ {
965
+ "epoch": 11.1,
966
+ "learning_rate": 1e-05,
967
+ "loss": 0.0045,
968
+ "step": 3875
969
+ },
970
+ {
971
+ "epoch": 11.17,
972
+ "learning_rate": 1e-05,
973
+ "loss": 0.0047,
974
+ "step": 3900
975
+ },
976
+ {
977
+ "epoch": 11.25,
978
+ "learning_rate": 1e-05,
979
+ "loss": 0.0043,
980
+ "step": 3925
981
+ },
982
+ {
983
+ "epoch": 11.32,
984
+ "learning_rate": 1e-05,
985
+ "loss": 0.006,
986
+ "step": 3950
987
+ },
988
+ {
989
+ "epoch": 11.39,
990
+ "learning_rate": 1e-05,
991
+ "loss": 0.0062,
992
+ "step": 3975
993
+ },
994
+ {
995
+ "epoch": 11.46,
996
+ "learning_rate": 1e-05,
997
+ "loss": 0.0049,
998
+ "step": 4000
999
+ },
1000
+ {
1001
+ "epoch": 11.46,
1002
+ "eval_cer": 8.560486329385162,
1003
+ "eval_loss": 0.4479295611381531,
1004
+ "eval_runtime": 720.058,
1005
+ "eval_samples_per_second": 1.533,
1006
+ "eval_steps_per_second": 0.096,
1007
+ "eval_wer": 16.030139043525544,
1008
+ "step": 4000
1009
  }
1010
  ],
1011
  "max_steps": 4000,
1012
  "num_train_epochs": 12,
1013
+ "total_flos": 1.843137234763776e+19,
1014
  "trial_name": null,
1015
  "trial_params": null
1016
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aed36cd0774277c3bc7d2577938faa840a081b7219a5939e6d8e3f7908a9e51
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9444715d1c7dae1eff48b8c035739bfd6101a03c0047cdb26f72b4f864a81984
3
  size 967102729
runs/Aug21_16-43-21_8bad39564bfa/events.out.tfevents.1692636213.8bad39564bfa.55.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:234771433c64a48dbfa61992972eca3ff4220b661982fa138194e7c8a3af2d0e
3
- size 25784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6648219f404076f6212b04fb8698ba6bf20f93c3762bb341e6a10a29c6ad1a
3
+ size 32429