elsayedissa commited on
Commit
96fdeb1
1 Parent(s): fd6aa0d

Training in progress, step 4000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:524b22890142e47419a06d19ae61852f9787098118564b0f950aec1179e74230
3
  size 12347192855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071c5f4b0d6b94f41e4ec3d1d9e0d746d356fee79d390bbf5696fdec12d09eee
3
  size 12347192855
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:292c0ca92f5d9cb9248a1b9129a7ce107758f2f0a9b6c7ce62018b59f5e453ca
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d13c1515c5bec3b1b6df88233162654239b2f0a7c1119dddff788e8c045bd24
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:d9598b49b7afca30659c27619764c7fd04e3ef4e5f28cc734910a1ae47804866
3
- size 14639
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec70788b682d89359da85d225e858c6024d3fd2773541d2690bca2b322a42f06
3
+ size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac1686cb80dfe456f1ee071e6b209db73517d8bbd97cb9595254e481a753285f
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d92186bd8b7a36cbab743326563ee77d960ade57f12c3c59d4d213b20af4bd62
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c01e440b61cade1b20bb9e797abdc166ebdff6380a8b18ea5ba5855bc546f3fa
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e131db79df8f2c3d12190a618e4f984ac87c57b6930e6ec08f7edadfe13646
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 0.11536111854119403,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
4
- "epoch": 0.10413412475268145,
5
- "global_step": 3000,
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": 0.062,
754
  "eval_wer": 0.11325757951014288,
755
  "step": 3000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
756
  }
757
  ],
758
  "max_steps": 25000,
759
  "num_train_epochs": 1,
760
- "total_flos": 1.019122089984e+20,
761
  "trial_name": null,
762
  "trial_params": null
763
  }
 
1
  {
2
  "best_metric": 0.11536111854119403,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
4
+ "epoch": 0.13884549967024193,
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": 0.062,
754
  "eval_wer": 0.11325757951014288,
755
  "step": 3000
756
+ },
757
+ {
758
+ "epoch": 0.11,
759
+ "learning_rate": 8.971836734693879e-06,
760
+ "loss": 0.1969,
761
+ "step": 3025
762
+ },
763
+ {
764
+ "epoch": 0.11,
765
+ "learning_rate": 8.961632653061225e-06,
766
+ "loss": 0.1797,
767
+ "step": 3050
768
+ },
769
+ {
770
+ "epoch": 0.11,
771
+ "learning_rate": 8.951428571428572e-06,
772
+ "loss": 0.2003,
773
+ "step": 3075
774
+ },
775
+ {
776
+ "epoch": 0.11,
777
+ "learning_rate": 8.941224489795918e-06,
778
+ "loss": 0.1641,
779
+ "step": 3100
780
+ },
781
+ {
782
+ "epoch": 0.11,
783
+ "learning_rate": 8.931020408163266e-06,
784
+ "loss": 0.2025,
785
+ "step": 3125
786
+ },
787
+ {
788
+ "epoch": 0.11,
789
+ "learning_rate": 8.921224489795918e-06,
790
+ "loss": 0.1992,
791
+ "step": 3150
792
+ },
793
+ {
794
+ "epoch": 0.11,
795
+ "learning_rate": 8.911020408163266e-06,
796
+ "loss": 0.2187,
797
+ "step": 3175
798
+ },
799
+ {
800
+ "epoch": 0.11,
801
+ "learning_rate": 8.900816326530612e-06,
802
+ "loss": 0.1746,
803
+ "step": 3200
804
+ },
805
+ {
806
+ "epoch": 0.11,
807
+ "learning_rate": 8.89061224489796e-06,
808
+ "loss": 0.1978,
809
+ "step": 3225
810
+ },
811
+ {
812
+ "epoch": 0.11,
813
+ "learning_rate": 8.880408163265307e-06,
814
+ "loss": 0.2066,
815
+ "step": 3250
816
+ },
817
+ {
818
+ "epoch": 0.11,
819
+ "learning_rate": 8.870204081632654e-06,
820
+ "loss": 0.2032,
821
+ "step": 3275
822
+ },
823
+ {
824
+ "epoch": 0.11,
825
+ "learning_rate": 8.860000000000002e-06,
826
+ "loss": 0.1744,
827
+ "step": 3300
828
+ },
829
+ {
830
+ "epoch": 0.12,
831
+ "learning_rate": 8.849795918367347e-06,
832
+ "loss": 0.2074,
833
+ "step": 3325
834
+ },
835
+ {
836
+ "epoch": 0.12,
837
+ "learning_rate": 8.839591836734695e-06,
838
+ "loss": 0.1732,
839
+ "step": 3350
840
+ },
841
+ {
842
+ "epoch": 0.12,
843
+ "learning_rate": 8.82938775510204e-06,
844
+ "loss": 0.2097,
845
+ "step": 3375
846
+ },
847
+ {
848
+ "epoch": 0.12,
849
+ "learning_rate": 8.819183673469388e-06,
850
+ "loss": 0.1759,
851
+ "step": 3400
852
+ },
853
+ {
854
+ "epoch": 0.12,
855
+ "learning_rate": 8.808979591836736e-06,
856
+ "loss": 0.198,
857
+ "step": 3425
858
+ },
859
+ {
860
+ "epoch": 0.12,
861
+ "learning_rate": 8.798775510204083e-06,
862
+ "loss": 0.2081,
863
+ "step": 3450
864
+ },
865
+ {
866
+ "epoch": 0.12,
867
+ "learning_rate": 8.788571428571429e-06,
868
+ "loss": 0.205,
869
+ "step": 3475
870
+ },
871
+ {
872
+ "epoch": 0.12,
873
+ "learning_rate": 8.778367346938776e-06,
874
+ "loss": 0.2008,
875
+ "step": 3500
876
+ },
877
+ {
878
+ "epoch": 0.12,
879
+ "learning_rate": 8.768163265306124e-06,
880
+ "loss": 0.1978,
881
+ "step": 3525
882
+ },
883
+ {
884
+ "epoch": 0.12,
885
+ "learning_rate": 8.75795918367347e-06,
886
+ "loss": 0.2026,
887
+ "step": 3550
888
+ },
889
+ {
890
+ "epoch": 0.12,
891
+ "learning_rate": 8.747755102040817e-06,
892
+ "loss": 0.2027,
893
+ "step": 3575
894
+ },
895
+ {
896
+ "epoch": 0.12,
897
+ "learning_rate": 8.737551020408163e-06,
898
+ "loss": 0.2174,
899
+ "step": 3600
900
+ },
901
+ {
902
+ "epoch": 0.13,
903
+ "learning_rate": 8.72734693877551e-06,
904
+ "loss": 0.2304,
905
+ "step": 3625
906
+ },
907
+ {
908
+ "epoch": 0.13,
909
+ "learning_rate": 8.717142857142858e-06,
910
+ "loss": 0.2116,
911
+ "step": 3650
912
+ },
913
+ {
914
+ "epoch": 0.13,
915
+ "learning_rate": 8.706938775510205e-06,
916
+ "loss": 0.1946,
917
+ "step": 3675
918
+ },
919
+ {
920
+ "epoch": 0.13,
921
+ "learning_rate": 8.696734693877553e-06,
922
+ "loss": 0.1663,
923
+ "step": 3700
924
+ },
925
+ {
926
+ "epoch": 0.13,
927
+ "learning_rate": 8.686530612244899e-06,
928
+ "loss": 0.2299,
929
+ "step": 3725
930
+ },
931
+ {
932
+ "epoch": 0.13,
933
+ "learning_rate": 8.676326530612246e-06,
934
+ "loss": 0.1811,
935
+ "step": 3750
936
+ },
937
+ {
938
+ "epoch": 0.13,
939
+ "learning_rate": 8.666122448979592e-06,
940
+ "loss": 0.2082,
941
+ "step": 3775
942
+ },
943
+ {
944
+ "epoch": 0.13,
945
+ "learning_rate": 8.65591836734694e-06,
946
+ "loss": 0.1697,
947
+ "step": 3800
948
+ },
949
+ {
950
+ "epoch": 0.13,
951
+ "learning_rate": 8.645714285714287e-06,
952
+ "loss": 0.2177,
953
+ "step": 3825
954
+ },
955
+ {
956
+ "epoch": 0.13,
957
+ "learning_rate": 8.635510204081633e-06,
958
+ "loss": 0.1829,
959
+ "step": 3850
960
+ },
961
+ {
962
+ "epoch": 0.13,
963
+ "learning_rate": 8.62530612244898e-06,
964
+ "loss": 0.2004,
965
+ "step": 3875
966
+ },
967
+ {
968
+ "epoch": 0.14,
969
+ "learning_rate": 8.615102040816328e-06,
970
+ "loss": 0.1872,
971
+ "step": 3900
972
+ },
973
+ {
974
+ "epoch": 0.14,
975
+ "learning_rate": 8.604897959183675e-06,
976
+ "loss": 0.1981,
977
+ "step": 3925
978
+ },
979
+ {
980
+ "epoch": 0.14,
981
+ "learning_rate": 8.594693877551021e-06,
982
+ "loss": 0.1981,
983
+ "step": 3950
984
+ },
985
+ {
986
+ "epoch": 0.14,
987
+ "learning_rate": 8.584489795918368e-06,
988
+ "loss": 0.1967,
989
+ "step": 3975
990
+ },
991
+ {
992
+ "epoch": 0.14,
993
+ "learning_rate": 8.574285714285714e-06,
994
+ "loss": 0.1752,
995
+ "step": 4000
996
+ },
997
+ {
998
+ "epoch": 0.14,
999
+ "eval_loss": 0.2080826610326767,
1000
+ "eval_runtime": 31400.8611,
1001
+ "eval_samples_per_second": 0.988,
1002
+ "eval_steps_per_second": 0.062,
1003
+ "eval_wer": 0.11463792380367409,
1004
+ "step": 4000
1005
  }
1006
  ],
1007
  "max_steps": 25000,
1008
  "num_train_epochs": 1,
1009
+ "total_flos": 1.358829453312e+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 sha256:292c0ca92f5d9cb9248a1b9129a7ce107758f2f0a9b6c7ce62018b59f5e453ca
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d13c1515c5bec3b1b6df88233162654239b2f0a7c1119dddff788e8c045bd24
3
  size 6173655480
runs/Dec26_19-57-19_gpu07.cyverse.org/events.out.tfevents.1672109970.gpu07.cyverse.org.126369.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6ad16952cc6df1dc554ae3afa7930fec5d15256f3fee9a4261fcb24610e6c56
3
- size 24183
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be876d39b9ffab345bd37299ad53f20801693f40e6411525ec37c8d2d55b4dd
3
+ size 30781