elsayedissa commited on
Commit
3537a9c
1 Parent(s): 69113d2

Training in progress, step 14000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b82e023bcdce3d9867de00994de7448663053d12658724461977f225ef150ba
3
  size 12347192855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c929302bb74af8414f1457bdac983a5167c48fc62743f2a944292a9ec355ff19
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:b873f46f3287d785fe9e0e65cbecdf06f727c84e188245367c48b687b9339708
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b1dd609226add0a62fefe86375dc5ab0e6ba03119c133d085ae905f7776bb4
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:c516e23ac00a4fed94805529a2f025da998c6366d20bf4032bb8f1a2f5ae0ce3
3
- size 14511
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ebdb9d6f339d52dd1aed7a35020ec74669f26e08d2625423357b179393847c
3
+ size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c19297e7f4fe97d7584a052fffbfde0e921e6770e0bba0e78fc588359f317245
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb80279c059163717a04958ac0f1db273c6cbef42cd2cc5782804246c1bb647e
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52755b2d249438bf866dbd6a565d7c609e276075f6ad3cb63ef2a63e3670f1cd
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b246a509473d8d83986a3f679e62ae072d94abb1f10b20f190de183087d405e3
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": 0.4512478739282863,
5
- "global_step": 13000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -3243,11 +3243,260 @@
3243
  "eval_steps_per_second": 0.062,
3244
  "eval_wer": 0.09758505793813547,
3245
  "step": 13000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3246
  }
3247
  ],
3248
  "max_steps": 25000,
3249
  "num_train_epochs": 1,
3250
- "total_flos": 4.416195723264e+20,
3251
  "trial_name": null,
3252
  "trial_params": null
3253
  }
 
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,
 
3243
  "eval_steps_per_second": 0.062,
3244
  "eval_wer": 0.09758505793813547,
3245
  "step": 13000
3246
+ },
3247
+ {
3248
+ "epoch": 0.45,
3249
+ "learning_rate": 4.8918367346938775e-06,
3250
+ "loss": 0.171,
3251
+ "step": 13025
3252
+ },
3253
+ {
3254
+ "epoch": 0.45,
3255
+ "learning_rate": 4.881632653061225e-06,
3256
+ "loss": 0.1501,
3257
+ "step": 13050
3258
+ },
3259
+ {
3260
+ "epoch": 0.45,
3261
+ "learning_rate": 4.871428571428572e-06,
3262
+ "loss": 0.1588,
3263
+ "step": 13075
3264
+ },
3265
+ {
3266
+ "epoch": 0.45,
3267
+ "learning_rate": 4.861224489795919e-06,
3268
+ "loss": 0.1441,
3269
+ "step": 13100
3270
+ },
3271
+ {
3272
+ "epoch": 0.46,
3273
+ "learning_rate": 4.851020408163266e-06,
3274
+ "loss": 0.1788,
3275
+ "step": 13125
3276
+ },
3277
+ {
3278
+ "epoch": 0.46,
3279
+ "learning_rate": 4.840816326530612e-06,
3280
+ "loss": 0.143,
3281
+ "step": 13150
3282
+ },
3283
+ {
3284
+ "epoch": 0.46,
3285
+ "learning_rate": 4.83061224489796e-06,
3286
+ "loss": 0.1754,
3287
+ "step": 13175
3288
+ },
3289
+ {
3290
+ "epoch": 0.46,
3291
+ "learning_rate": 4.8204081632653065e-06,
3292
+ "loss": 0.164,
3293
+ "step": 13200
3294
+ },
3295
+ {
3296
+ "epoch": 0.46,
3297
+ "learning_rate": 4.810204081632653e-06,
3298
+ "loss": 0.1595,
3299
+ "step": 13225
3300
+ },
3301
+ {
3302
+ "epoch": 0.46,
3303
+ "learning_rate": 4.800000000000001e-06,
3304
+ "loss": 0.1265,
3305
+ "step": 13250
3306
+ },
3307
+ {
3308
+ "epoch": 0.46,
3309
+ "learning_rate": 4.789795918367347e-06,
3310
+ "loss": 0.1808,
3311
+ "step": 13275
3312
+ },
3313
+ {
3314
+ "epoch": 0.46,
3315
+ "learning_rate": 4.779591836734695e-06,
3316
+ "loss": 0.1587,
3317
+ "step": 13300
3318
+ },
3319
+ {
3320
+ "epoch": 0.46,
3321
+ "learning_rate": 4.769387755102041e-06,
3322
+ "loss": 0.1571,
3323
+ "step": 13325
3324
+ },
3325
+ {
3326
+ "epoch": 0.46,
3327
+ "learning_rate": 4.759183673469388e-06,
3328
+ "loss": 0.1386,
3329
+ "step": 13350
3330
+ },
3331
+ {
3332
+ "epoch": 0.46,
3333
+ "learning_rate": 4.749387755102042e-06,
3334
+ "loss": 0.1759,
3335
+ "step": 13375
3336
+ },
3337
+ {
3338
+ "epoch": 0.47,
3339
+ "learning_rate": 4.739183673469388e-06,
3340
+ "loss": 0.1349,
3341
+ "step": 13400
3342
+ },
3343
+ {
3344
+ "epoch": 0.47,
3345
+ "learning_rate": 4.728979591836735e-06,
3346
+ "loss": 0.1766,
3347
+ "step": 13425
3348
+ },
3349
+ {
3350
+ "epoch": 0.47,
3351
+ "learning_rate": 4.718775510204082e-06,
3352
+ "loss": 0.128,
3353
+ "step": 13450
3354
+ },
3355
+ {
3356
+ "epoch": 0.47,
3357
+ "learning_rate": 4.708571428571429e-06,
3358
+ "loss": 0.1595,
3359
+ "step": 13475
3360
+ },
3361
+ {
3362
+ "epoch": 0.47,
3363
+ "learning_rate": 4.698367346938776e-06,
3364
+ "loss": 0.1543,
3365
+ "step": 13500
3366
+ },
3367
+ {
3368
+ "epoch": 0.47,
3369
+ "learning_rate": 4.688163265306122e-06,
3370
+ "loss": 0.175,
3371
+ "step": 13525
3372
+ },
3373
+ {
3374
+ "epoch": 0.47,
3375
+ "learning_rate": 4.67795918367347e-06,
3376
+ "loss": 0.1498,
3377
+ "step": 13550
3378
+ },
3379
+ {
3380
+ "epoch": 0.47,
3381
+ "learning_rate": 4.667755102040817e-06,
3382
+ "loss": 0.1575,
3383
+ "step": 13575
3384
+ },
3385
+ {
3386
+ "epoch": 0.47,
3387
+ "learning_rate": 4.657551020408164e-06,
3388
+ "loss": 0.1401,
3389
+ "step": 13600
3390
+ },
3391
+ {
3392
+ "epoch": 0.47,
3393
+ "learning_rate": 4.6473469387755105e-06,
3394
+ "loss": 0.1734,
3395
+ "step": 13625
3396
+ },
3397
+ {
3398
+ "epoch": 0.47,
3399
+ "learning_rate": 4.637142857142857e-06,
3400
+ "loss": 0.1205,
3401
+ "step": 13650
3402
+ },
3403
+ {
3404
+ "epoch": 0.47,
3405
+ "learning_rate": 4.626938775510205e-06,
3406
+ "loss": 0.1529,
3407
+ "step": 13675
3408
+ },
3409
+ {
3410
+ "epoch": 0.48,
3411
+ "learning_rate": 4.616734693877551e-06,
3412
+ "loss": 0.1529,
3413
+ "step": 13700
3414
+ },
3415
+ {
3416
+ "epoch": 0.48,
3417
+ "learning_rate": 4.606530612244898e-06,
3418
+ "loss": 0.1689,
3419
+ "step": 13725
3420
+ },
3421
+ {
3422
+ "epoch": 0.48,
3423
+ "learning_rate": 4.596326530612245e-06,
3424
+ "loss": 0.138,
3425
+ "step": 13750
3426
+ },
3427
+ {
3428
+ "epoch": 0.48,
3429
+ "learning_rate": 4.586122448979593e-06,
3430
+ "loss": 0.1709,
3431
+ "step": 13775
3432
+ },
3433
+ {
3434
+ "epoch": 0.48,
3435
+ "learning_rate": 4.5759183673469395e-06,
3436
+ "loss": 0.1455,
3437
+ "step": 13800
3438
+ },
3439
+ {
3440
+ "epoch": 0.48,
3441
+ "learning_rate": 4.565714285714286e-06,
3442
+ "loss": 0.1806,
3443
+ "step": 13825
3444
+ },
3445
+ {
3446
+ "epoch": 0.48,
3447
+ "learning_rate": 4.555510204081633e-06,
3448
+ "loss": 0.1415,
3449
+ "step": 13850
3450
+ },
3451
+ {
3452
+ "epoch": 0.48,
3453
+ "learning_rate": 4.5453061224489794e-06,
3454
+ "loss": 0.1753,
3455
+ "step": 13875
3456
+ },
3457
+ {
3458
+ "epoch": 0.48,
3459
+ "learning_rate": 4.535102040816327e-06,
3460
+ "loss": 0.1414,
3461
+ "step": 13900
3462
+ },
3463
+ {
3464
+ "epoch": 0.48,
3465
+ "learning_rate": 4.5248979591836736e-06,
3466
+ "loss": 0.17,
3467
+ "step": 13925
3468
+ },
3469
+ {
3470
+ "epoch": 0.48,
3471
+ "learning_rate": 4.514693877551021e-06,
3472
+ "loss": 0.1453,
3473
+ "step": 13950
3474
+ },
3475
+ {
3476
+ "epoch": 0.49,
3477
+ "learning_rate": 4.504489795918368e-06,
3478
+ "loss": 0.1933,
3479
+ "step": 13975
3480
+ },
3481
+ {
3482
+ "epoch": 0.49,
3483
+ "learning_rate": 4.494285714285715e-06,
3484
+ "loss": 0.1616,
3485
+ "step": 14000
3486
+ },
3487
+ {
3488
+ "epoch": 0.49,
3489
+ "eval_loss": 0.16927780210971832,
3490
+ "eval_runtime": 31097.4541,
3491
+ "eval_samples_per_second": 0.998,
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
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b873f46f3287d785fe9e0e65cbecdf06f727c84e188245367c48b687b9339708
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b1dd609226add0a62fefe86375dc5ab0e6ba03119c133d085ae905f7776bb4
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 sha256:6a3ad336968cb511fe9ae780cd83e8101970e1c047eb76f8596c5e84f34771a2
3
- size 90163
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a774424dd1f706b0778295046bad47acca2f0a8722db7ce4662169f20deeee88
3
+ size 96761