elsayedissa commited on
Commit
4010f44
1 Parent(s): 3537a9c

Training in progress, step 15000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c929302bb74af8414f1457bdac983a5167c48fc62743f2a944292a9ec355ff19
3
  size 12347192855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36dbc50cf9140fb7f0d07a538501afa688944f7d4db346dd9f7ac42fb1be590a
3
  size 12347192855
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29b1dd609226add0a62fefe86375dc5ab0e6ba03119c133d085ae905f7776bb4
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1327fc0bd4b84f3f75a5ae566a31c8d3866b9addc072e36ebcf7aa9bd4b067fa
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:e0ebdb9d6f339d52dd1aed7a35020ec74669f26e08d2625423357b179393847c
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a48bbb35f10fc80761770aebcc3f7c466fe7a23a21b518a2ddab7c9475727995
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb80279c059163717a04958ac0f1db273c6cbef42cd2cc5782804246c1bb647e
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:870e427bfebba6376a09e42afc7cf27343ead25cf07419d6ca98b32ac4723fc2
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b246a509473d8d83986a3f679e62ae072d94abb1f10b20f190de183087d405e3
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee2e34fac94bd8efbe6863121732ff5580c12a2335033285d23cf8ff6a7c8cb1
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": 0.4859592488458468,
5
- "global_step": 14000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -3492,11 +3492,260 @@
3492
  "eval_steps_per_second": 0.062,
3493
  "eval_wer": 0.09559709797472452,
3494
  "step": 14000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3495
  }
3496
  ],
3497
  "max_steps": 25000,
3498
  "num_train_epochs": 1,
3499
- "total_flos": 4.755903086592e+20,
3500
  "trial_name": null,
3501
  "trial_params": null
3502
  }
 
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,
 
3492
  "eval_steps_per_second": 0.062,
3493
  "eval_wer": 0.09559709797472452,
3494
  "step": 14000
3495
+ },
3496
+ {
3497
+ "epoch": 0.49,
3498
+ "learning_rate": 4.484081632653062e-06,
3499
+ "loss": 0.1841,
3500
+ "step": 14025
3501
+ },
3502
+ {
3503
+ "epoch": 0.49,
3504
+ "learning_rate": 4.4738775510204085e-06,
3505
+ "loss": 0.1254,
3506
+ "step": 14050
3507
+ },
3508
+ {
3509
+ "epoch": 0.49,
3510
+ "learning_rate": 4.463673469387755e-06,
3511
+ "loss": 0.1598,
3512
+ "step": 14075
3513
+ },
3514
+ {
3515
+ "epoch": 0.49,
3516
+ "learning_rate": 4.453469387755103e-06,
3517
+ "loss": 0.1339,
3518
+ "step": 14100
3519
+ },
3520
+ {
3521
+ "epoch": 0.49,
3522
+ "learning_rate": 4.443265306122449e-06,
3523
+ "loss": 0.1844,
3524
+ "step": 14125
3525
+ },
3526
+ {
3527
+ "epoch": 0.49,
3528
+ "learning_rate": 4.433061224489797e-06,
3529
+ "loss": 0.1493,
3530
+ "step": 14150
3531
+ },
3532
+ {
3533
+ "epoch": 0.49,
3534
+ "learning_rate": 4.422857142857143e-06,
3535
+ "loss": 0.1661,
3536
+ "step": 14175
3537
+ },
3538
+ {
3539
+ "epoch": 0.49,
3540
+ "learning_rate": 4.41265306122449e-06,
3541
+ "loss": 0.1306,
3542
+ "step": 14200
3543
+ },
3544
+ {
3545
+ "epoch": 0.49,
3546
+ "learning_rate": 4.4024489795918375e-06,
3547
+ "loss": 0.1602,
3548
+ "step": 14225
3549
+ },
3550
+ {
3551
+ "epoch": 0.49,
3552
+ "learning_rate": 4.392244897959184e-06,
3553
+ "loss": 0.1421,
3554
+ "step": 14250
3555
+ },
3556
+ {
3557
+ "epoch": 0.5,
3558
+ "learning_rate": 4.382040816326531e-06,
3559
+ "loss": 0.1714,
3560
+ "step": 14275
3561
+ },
3562
+ {
3563
+ "epoch": 0.5,
3564
+ "learning_rate": 4.371836734693878e-06,
3565
+ "loss": 0.1213,
3566
+ "step": 14300
3567
+ },
3568
+ {
3569
+ "epoch": 0.5,
3570
+ "learning_rate": 4.361632653061225e-06,
3571
+ "loss": 0.1728,
3572
+ "step": 14325
3573
+ },
3574
+ {
3575
+ "epoch": 0.5,
3576
+ "learning_rate": 4.351428571428572e-06,
3577
+ "loss": 0.1521,
3578
+ "step": 14350
3579
+ },
3580
+ {
3581
+ "epoch": 0.5,
3582
+ "learning_rate": 4.341224489795919e-06,
3583
+ "loss": 0.1479,
3584
+ "step": 14375
3585
+ },
3586
+ {
3587
+ "epoch": 0.5,
3588
+ "learning_rate": 4.331020408163266e-06,
3589
+ "loss": 0.1485,
3590
+ "step": 14400
3591
+ },
3592
+ {
3593
+ "epoch": 0.5,
3594
+ "learning_rate": 4.320816326530612e-06,
3595
+ "loss": 0.1618,
3596
+ "step": 14425
3597
+ },
3598
+ {
3599
+ "epoch": 0.5,
3600
+ "learning_rate": 4.310612244897959e-06,
3601
+ "loss": 0.1676,
3602
+ "step": 14450
3603
+ },
3604
+ {
3605
+ "epoch": 0.5,
3606
+ "learning_rate": 4.300408163265306e-06,
3607
+ "loss": 0.1593,
3608
+ "step": 14475
3609
+ },
3610
+ {
3611
+ "epoch": 0.5,
3612
+ "learning_rate": 4.290204081632653e-06,
3613
+ "loss": 0.1525,
3614
+ "step": 14500
3615
+ },
3616
+ {
3617
+ "epoch": 0.5,
3618
+ "learning_rate": 4.2800000000000005e-06,
3619
+ "loss": 0.1589,
3620
+ "step": 14525
3621
+ },
3622
+ {
3623
+ "epoch": 0.51,
3624
+ "learning_rate": 4.269795918367347e-06,
3625
+ "loss": 0.182,
3626
+ "step": 14550
3627
+ },
3628
+ {
3629
+ "epoch": 0.51,
3630
+ "learning_rate": 4.259591836734695e-06,
3631
+ "loss": 0.1746,
3632
+ "step": 14575
3633
+ },
3634
+ {
3635
+ "epoch": 0.51,
3636
+ "learning_rate": 4.249387755102041e-06,
3637
+ "loss": 0.1475,
3638
+ "step": 14600
3639
+ },
3640
+ {
3641
+ "epoch": 0.51,
3642
+ "learning_rate": 4.239183673469388e-06,
3643
+ "loss": 0.1718,
3644
+ "step": 14625
3645
+ },
3646
+ {
3647
+ "epoch": 0.51,
3648
+ "learning_rate": 4.2289795918367346e-06,
3649
+ "loss": 0.1515,
3650
+ "step": 14650
3651
+ },
3652
+ {
3653
+ "epoch": 0.51,
3654
+ "learning_rate": 4.218775510204082e-06,
3655
+ "loss": 0.1739,
3656
+ "step": 14675
3657
+ },
3658
+ {
3659
+ "epoch": 0.51,
3660
+ "learning_rate": 4.208571428571429e-06,
3661
+ "loss": 0.1415,
3662
+ "step": 14700
3663
+ },
3664
+ {
3665
+ "epoch": 0.51,
3666
+ "learning_rate": 4.198367346938776e-06,
3667
+ "loss": 0.175,
3668
+ "step": 14725
3669
+ },
3670
+ {
3671
+ "epoch": 0.51,
3672
+ "learning_rate": 4.188163265306123e-06,
3673
+ "loss": 0.1489,
3674
+ "step": 14750
3675
+ },
3676
+ {
3677
+ "epoch": 0.51,
3678
+ "learning_rate": 4.1779591836734695e-06,
3679
+ "loss": 0.165,
3680
+ "step": 14775
3681
+ },
3682
+ {
3683
+ "epoch": 0.51,
3684
+ "learning_rate": 4.167755102040817e-06,
3685
+ "loss": 0.1568,
3686
+ "step": 14800
3687
+ },
3688
+ {
3689
+ "epoch": 0.51,
3690
+ "learning_rate": 4.157551020408164e-06,
3691
+ "loss": 0.1959,
3692
+ "step": 14825
3693
+ },
3694
+ {
3695
+ "epoch": 0.52,
3696
+ "learning_rate": 4.14734693877551e-06,
3697
+ "loss": 0.1389,
3698
+ "step": 14850
3699
+ },
3700
+ {
3701
+ "epoch": 0.52,
3702
+ "learning_rate": 4.137142857142858e-06,
3703
+ "loss": 0.1741,
3704
+ "step": 14875
3705
+ },
3706
+ {
3707
+ "epoch": 0.52,
3708
+ "learning_rate": 4.126938775510204e-06,
3709
+ "loss": 0.1576,
3710
+ "step": 14900
3711
+ },
3712
+ {
3713
+ "epoch": 0.52,
3714
+ "learning_rate": 4.116734693877552e-06,
3715
+ "loss": 0.1984,
3716
+ "step": 14925
3717
+ },
3718
+ {
3719
+ "epoch": 0.52,
3720
+ "learning_rate": 4.1065306122448985e-06,
3721
+ "loss": 0.1307,
3722
+ "step": 14950
3723
+ },
3724
+ {
3725
+ "epoch": 0.52,
3726
+ "learning_rate": 4.096326530612245e-06,
3727
+ "loss": 0.1745,
3728
+ "step": 14975
3729
+ },
3730
+ {
3731
+ "epoch": 0.52,
3732
+ "learning_rate": 4.086122448979592e-06,
3733
+ "loss": 0.1556,
3734
+ "step": 15000
3735
+ },
3736
+ {
3737
+ "epoch": 0.52,
3738
+ "eval_loss": 0.16709309816360474,
3739
+ "eval_runtime": 31213.067,
3740
+ "eval_samples_per_second": 0.994,
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
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29b1dd609226add0a62fefe86375dc5ab0e6ba03119c133d085ae905f7776bb4
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1327fc0bd4b84f3f75a5ae566a31c8d3866b9addc072e36ebcf7aa9bd4b067fa
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:a774424dd1f706b0778295046bad47acca2f0a8722db7ce4662169f20deeee88
3
- size 96761
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6358803618c5f009d0a7ba4001fd025bc6f24e6e4315f0b1153ccc109884fa00
3
+ size 103359