elsayedissa commited on
Commit
8fb8892
1 Parent(s): 4010f44

Training in progress, step 16000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36dbc50cf9140fb7f0d07a538501afa688944f7d4db346dd9f7ac42fb1be590a
3
  size 12347192855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2828bba9c0610d92bcb9ced115dba1825e24c111402867d65a37cba2fd4cdf3
3
  size 12347192855
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1327fc0bd4b84f3f75a5ae566a31c8d3866b9addc072e36ebcf7aa9bd4b067fa
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ddc7f21fd5cb7cbeac420cbf26556fe05d0d0276c5d96c3c5d572508243cc6
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:a48bbb35f10fc80761770aebcc3f7c466fe7a23a21b518a2ddab7c9475727995
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6024b9a42abf2c5787dca8b8ac21caaa78ef8edc18fdd3f5727713a6bded2de
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:870e427bfebba6376a09e42afc7cf27343ead25cf07419d6ca98b32ac4723fc2
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8beddb254d719968614077f7da7885f0decec146856dee753939f87ce125fd6c
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee2e34fac94bd8efbe6863121732ff5580c12a2335033285d23cf8ff6a7c8cb1
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd534b0cae4142fc61b98b6723afbc5b4255a5022df3ad8a29653d61c4f84f8
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": 0.5206706237634072,
5
- "global_step": 15000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -3741,11 +3741,260 @@
3741
  "eval_steps_per_second": 0.062,
3742
  "eval_wer": 0.09415070849968464,
3743
  "step": 15000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3744
  }
3745
  ],
3746
  "max_steps": 25000,
3747
  "num_train_epochs": 1,
3748
- "total_flos": 5.09561044992e+20,
3749
  "trial_name": null,
3750
  "trial_params": null
3751
  }
 
1
  {
2
  "best_metric": 0.11536111854119403,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
4
+ "epoch": 0.5553819986809677,
5
+ "global_step": 16000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
3741
  "eval_steps_per_second": 0.062,
3742
  "eval_wer": 0.09415070849968464,
3743
  "step": 15000
3744
+ },
3745
+ {
3746
+ "epoch": 0.52,
3747
+ "learning_rate": 4.075918367346939e-06,
3748
+ "loss": 0.1621,
3749
+ "step": 15025
3750
+ },
3751
+ {
3752
+ "epoch": 0.52,
3753
+ "learning_rate": 4.065714285714286e-06,
3754
+ "loss": 0.1453,
3755
+ "step": 15050
3756
+ },
3757
+ {
3758
+ "epoch": 0.52,
3759
+ "learning_rate": 4.055510204081633e-06,
3760
+ "loss": 0.1684,
3761
+ "step": 15075
3762
+ },
3763
+ {
3764
+ "epoch": 0.52,
3765
+ "learning_rate": 4.04530612244898e-06,
3766
+ "loss": 0.1425,
3767
+ "step": 15100
3768
+ },
3769
+ {
3770
+ "epoch": 0.53,
3771
+ "learning_rate": 4.035102040816327e-06,
3772
+ "loss": 0.173,
3773
+ "step": 15125
3774
+ },
3775
+ {
3776
+ "epoch": 0.53,
3777
+ "learning_rate": 4.024897959183674e-06,
3778
+ "loss": 0.1417,
3779
+ "step": 15150
3780
+ },
3781
+ {
3782
+ "epoch": 0.53,
3783
+ "learning_rate": 4.014693877551021e-06,
3784
+ "loss": 0.1659,
3785
+ "step": 15175
3786
+ },
3787
+ {
3788
+ "epoch": 0.53,
3789
+ "learning_rate": 4.004489795918367e-06,
3790
+ "loss": 0.1472,
3791
+ "step": 15200
3792
+ },
3793
+ {
3794
+ "epoch": 0.53,
3795
+ "learning_rate": 3.994285714285714e-06,
3796
+ "loss": 0.1528,
3797
+ "step": 15225
3798
+ },
3799
+ {
3800
+ "epoch": 0.53,
3801
+ "learning_rate": 3.9840816326530615e-06,
3802
+ "loss": 0.1337,
3803
+ "step": 15250
3804
+ },
3805
+ {
3806
+ "epoch": 0.53,
3807
+ "learning_rate": 3.973877551020409e-06,
3808
+ "loss": 0.1851,
3809
+ "step": 15275
3810
+ },
3811
+ {
3812
+ "epoch": 0.53,
3813
+ "learning_rate": 3.963673469387756e-06,
3814
+ "loss": 0.1305,
3815
+ "step": 15300
3816
+ },
3817
+ {
3818
+ "epoch": 0.53,
3819
+ "learning_rate": 3.953469387755102e-06,
3820
+ "loss": 0.161,
3821
+ "step": 15325
3822
+ },
3823
+ {
3824
+ "epoch": 0.53,
3825
+ "learning_rate": 3.943265306122449e-06,
3826
+ "loss": 0.1332,
3827
+ "step": 15350
3828
+ },
3829
+ {
3830
+ "epoch": 0.53,
3831
+ "learning_rate": 3.933061224489796e-06,
3832
+ "loss": 0.1638,
3833
+ "step": 15375
3834
+ },
3835
+ {
3836
+ "epoch": 0.53,
3837
+ "learning_rate": 3.922857142857143e-06,
3838
+ "loss": 0.151,
3839
+ "step": 15400
3840
+ },
3841
+ {
3842
+ "epoch": 0.54,
3843
+ "learning_rate": 3.91265306122449e-06,
3844
+ "loss": 0.1606,
3845
+ "step": 15425
3846
+ },
3847
+ {
3848
+ "epoch": 0.54,
3849
+ "learning_rate": 3.902448979591837e-06,
3850
+ "loss": 0.1567,
3851
+ "step": 15450
3852
+ },
3853
+ {
3854
+ "epoch": 0.54,
3855
+ "learning_rate": 3.892244897959185e-06,
3856
+ "loss": 0.1601,
3857
+ "step": 15475
3858
+ },
3859
+ {
3860
+ "epoch": 0.54,
3861
+ "learning_rate": 3.882040816326531e-06,
3862
+ "loss": 0.1424,
3863
+ "step": 15500
3864
+ },
3865
+ {
3866
+ "epoch": 0.54,
3867
+ "learning_rate": 3.871836734693878e-06,
3868
+ "loss": 0.1705,
3869
+ "step": 15525
3870
+ },
3871
+ {
3872
+ "epoch": 0.54,
3873
+ "learning_rate": 3.861632653061225e-06,
3874
+ "loss": 0.1169,
3875
+ "step": 15550
3876
+ },
3877
+ {
3878
+ "epoch": 0.54,
3879
+ "learning_rate": 3.851428571428571e-06,
3880
+ "loss": 0.176,
3881
+ "step": 15575
3882
+ },
3883
+ {
3884
+ "epoch": 0.54,
3885
+ "learning_rate": 3.841224489795919e-06,
3886
+ "loss": 0.1359,
3887
+ "step": 15600
3888
+ },
3889
+ {
3890
+ "epoch": 0.54,
3891
+ "learning_rate": 3.831020408163265e-06,
3892
+ "loss": 0.1479,
3893
+ "step": 15625
3894
+ },
3895
+ {
3896
+ "epoch": 0.54,
3897
+ "learning_rate": 3.820816326530613e-06,
3898
+ "loss": 0.1404,
3899
+ "step": 15650
3900
+ },
3901
+ {
3902
+ "epoch": 0.54,
3903
+ "learning_rate": 3.8106122448979595e-06,
3904
+ "loss": 0.1683,
3905
+ "step": 15675
3906
+ },
3907
+ {
3908
+ "epoch": 0.54,
3909
+ "learning_rate": 3.8004081632653065e-06,
3910
+ "loss": 0.1315,
3911
+ "step": 15700
3912
+ },
3913
+ {
3914
+ "epoch": 0.55,
3915
+ "learning_rate": 3.7902040816326536e-06,
3916
+ "loss": 0.1603,
3917
+ "step": 15725
3918
+ },
3919
+ {
3920
+ "epoch": 0.55,
3921
+ "learning_rate": 3.7800000000000002e-06,
3922
+ "loss": 0.1294,
3923
+ "step": 15750
3924
+ },
3925
+ {
3926
+ "epoch": 0.55,
3927
+ "learning_rate": 3.7697959183673473e-06,
3928
+ "loss": 0.1443,
3929
+ "step": 15775
3930
+ },
3931
+ {
3932
+ "epoch": 0.55,
3933
+ "learning_rate": 3.759591836734694e-06,
3934
+ "loss": 0.1243,
3935
+ "step": 15800
3936
+ },
3937
+ {
3938
+ "epoch": 0.55,
3939
+ "learning_rate": 3.7493877551020414e-06,
3940
+ "loss": 0.1358,
3941
+ "step": 15825
3942
+ },
3943
+ {
3944
+ "epoch": 0.55,
3945
+ "learning_rate": 3.739183673469388e-06,
3946
+ "loss": 0.1554,
3947
+ "step": 15850
3948
+ },
3949
+ {
3950
+ "epoch": 0.55,
3951
+ "learning_rate": 3.728979591836735e-06,
3952
+ "loss": 0.1695,
3953
+ "step": 15875
3954
+ },
3955
+ {
3956
+ "epoch": 0.55,
3957
+ "learning_rate": 3.7187755102040818e-06,
3958
+ "loss": 0.1207,
3959
+ "step": 15900
3960
+ },
3961
+ {
3962
+ "epoch": 0.55,
3963
+ "learning_rate": 3.7085714285714284e-06,
3964
+ "loss": 0.1588,
3965
+ "step": 15925
3966
+ },
3967
+ {
3968
+ "epoch": 0.55,
3969
+ "learning_rate": 3.698367346938776e-06,
3970
+ "loss": 0.1268,
3971
+ "step": 15950
3972
+ },
3973
+ {
3974
+ "epoch": 0.55,
3975
+ "learning_rate": 3.688163265306123e-06,
3976
+ "loss": 0.1597,
3977
+ "step": 15975
3978
+ },
3979
+ {
3980
+ "epoch": 0.56,
3981
+ "learning_rate": 3.6779591836734696e-06,
3982
+ "loss": 0.1448,
3983
+ "step": 16000
3984
+ },
3985
+ {
3986
+ "epoch": 0.56,
3987
+ "eval_loss": 0.1646193414926529,
3988
+ "eval_runtime": 30931.6929,
3989
+ "eval_samples_per_second": 1.003,
3990
+ "eval_steps_per_second": 0.063,
3991
+ "eval_wer": 0.09301142911866007,
3992
+ "step": 16000
3993
  }
3994
  ],
3995
  "max_steps": 25000,
3996
  "num_train_epochs": 1,
3997
+ "total_flos": 5.435317813248e+20,
3998
  "trial_name": null,
3999
  "trial_params": null
4000
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1327fc0bd4b84f3f75a5ae566a31c8d3866b9addc072e36ebcf7aa9bd4b067fa
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ddc7f21fd5cb7cbeac420cbf26556fe05d0d0276c5d96c3c5d572508243cc6
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 sha256:6358803618c5f009d0a7ba4001fd025bc6f24e6e4315f0b1153ccc109884fa00
3
- size 103359
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75cd60efea19799c78e56543455f4479b2c2960615ec3453f56a3b9470094bf2
3
+ size 109957