Hugging Face's logo

clu-ling
/
whisper-large-v2-spanish

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
elsayedissa commited on
Commit
42c8e1d
•
1 Parent(s): 7e23e4e

Training in progress, step 2000

Browse files
Files changed (8) 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/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +252 -3
  7. pytorch_model.bin +1 -1
  8. runs/Dec26_19-57-19_gpu07.cyverse.org/events.out.tfevents.1672109970.gpu07.cyverse.org.126369.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7caccb4814ea111a55de79f3b0f1b7eb20582444f51cf2089aad345126b34b9
3
  size 12347192855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c369c8776f1d8bbc3ed46a23dee4fc1c4e7bed3a383f11325adc1996199e2e
3
  size 12347192855
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f77f043740c59e3f92e8854de8cbf501f8b2ebb4879d9251a07b28a085d8540
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e2e9b2d8a6b71aca3a201dfdf9d5a8975658e82c8fdc5eb479bf91513d7de5
3
  size 6173655480
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dc60cce2d38966cefce7400b19fe51042929b4467fc1fb949feebc41453404d
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e3df258f0547ec2d8be103a88caf8ca6a1bb43373f3e23e93edf5a078821006
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de76d1924076a6f3ba31996f9c19d828fb19747461069f774423f20cc1b7bd1b
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e3f2f8deed500d0480cfb6cae701de6428749c6cff4864a11c535491f3c53d
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:781c6e782cde2f269dcaede95e567ef88774fa64959dc73143f1f45777794033
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39554cad34a34a80d4b0d52798fa2ca7cde8896ce0157d14076822670fd4690a
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": 0.03471137491756048,
5
- "global_step": 1000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -255,11 +255,260 @@
255
  "eval_steps_per_second": 0.062,
256
  "eval_wer": 0.11536111854119403,
257
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
258
  }
259
  ],
260
  "max_steps": 25000,
261
  "num_train_epochs": 1,
262
- "total_flos": 3.39707363328e+19,
263
  "trial_name": null,
264
  "trial_params": null
265
  }
 
1
  {
2
  "best_metric": 0.11536111854119403,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
4
+ "epoch": 0.06942274983512096,
5
+ "global_step": 2000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
255
  "eval_steps_per_second": 0.062,
256
  "eval_wer": 0.11536111854119403,
257
  "step": 1000
258
+ },
259
+ {
260
+ "epoch": 0.04,
261
+ "learning_rate": 9.788163265306123e-06,
262
+ "loss": 0.2357,
263
+ "step": 1025
264
+ },
265
+ {
266
+ "epoch": 0.04,
267
+ "learning_rate": 9.77795918367347e-06,
268
+ "loss": 0.1857,
269
+ "step": 1050
270
+ },
271
+ {
272
+ "epoch": 0.04,
273
+ "learning_rate": 9.767755102040818e-06,
274
+ "loss": 0.2053,
275
+ "step": 1075
276
+ },
277
+ {
278
+ "epoch": 0.04,
279
+ "learning_rate": 9.757551020408163e-06,
280
+ "loss": 0.1809,
281
+ "step": 1100
282
+ },
283
+ {
284
+ "epoch": 0.04,
285
+ "learning_rate": 9.74734693877551e-06,
286
+ "loss": 0.2423,
287
+ "step": 1125
288
+ },
289
+ {
290
+ "epoch": 0.04,
291
+ "learning_rate": 9.737142857142858e-06,
292
+ "loss": 0.2082,
293
+ "step": 1150
294
+ },
295
+ {
296
+ "epoch": 0.04,
297
+ "learning_rate": 9.726938775510206e-06,
298
+ "loss": 0.2195,
299
+ "step": 1175
300
+ },
301
+ {
302
+ "epoch": 0.04,
303
+ "learning_rate": 9.716734693877552e-06,
304
+ "loss": 0.2152,
305
+ "step": 1200
306
+ },
307
+ {
308
+ "epoch": 0.04,
309
+ "learning_rate": 9.706530612244899e-06,
310
+ "loss": 0.2174,
311
+ "step": 1225
312
+ },
313
+ {
314
+ "epoch": 0.04,
315
+ "learning_rate": 9.696326530612245e-06,
316
+ "loss": 0.2078,
317
+ "step": 1250
318
+ },
319
+ {
320
+ "epoch": 0.04,
321
+ "learning_rate": 9.686122448979592e-06,
322
+ "loss": 0.2472,
323
+ "step": 1275
324
+ },
325
+ {
326
+ "epoch": 0.05,
327
+ "learning_rate": 9.67591836734694e-06,
328
+ "loss": 0.1914,
329
+ "step": 1300
330
+ },
331
+ {
332
+ "epoch": 0.05,
333
+ "learning_rate": 9.665714285714286e-06,
334
+ "loss": 0.2179,
335
+ "step": 1325
336
+ },
337
+ {
338
+ "epoch": 0.05,
339
+ "learning_rate": 9.655510204081635e-06,
340
+ "loss": 0.2018,
341
+ "step": 1350
342
+ },
343
+ {
344
+ "epoch": 0.05,
345
+ "learning_rate": 9.64530612244898e-06,
346
+ "loss": 0.2004,
347
+ "step": 1375
348
+ },
349
+ {
350
+ "epoch": 0.05,
351
+ "learning_rate": 9.635102040816328e-06,
352
+ "loss": 0.2058,
353
+ "step": 1400
354
+ },
355
+ {
356
+ "epoch": 0.05,
357
+ "learning_rate": 9.624897959183674e-06,
358
+ "loss": 0.2167,
359
+ "step": 1425
360
+ },
361
+ {
362
+ "epoch": 0.05,
363
+ "learning_rate": 9.614693877551021e-06,
364
+ "loss": 0.1683,
365
+ "step": 1450
366
+ },
367
+ {
368
+ "epoch": 0.05,
369
+ "learning_rate": 9.604489795918369e-06,
370
+ "loss": 0.177,
371
+ "step": 1475
372
+ },
373
+ {
374
+ "epoch": 0.05,
375
+ "learning_rate": 9.594285714285715e-06,
376
+ "loss": 0.1716,
377
+ "step": 1500
378
+ },
379
+ {
380
+ "epoch": 0.05,
381
+ "learning_rate": 9.584081632653062e-06,
382
+ "loss": 0.245,
383
+ "step": 1525
384
+ },
385
+ {
386
+ "epoch": 0.05,
387
+ "learning_rate": 9.573877551020408e-06,
388
+ "loss": 0.1928,
389
+ "step": 1550
390
+ },
391
+ {
392
+ "epoch": 0.05,
393
+ "learning_rate": 9.563673469387757e-06,
394
+ "loss": 0.2055,
395
+ "step": 1575
396
+ },
397
+ {
398
+ "epoch": 0.06,
399
+ "learning_rate": 9.553469387755103e-06,
400
+ "loss": 0.2019,
401
+ "step": 1600
402
+ },
403
+ {
404
+ "epoch": 0.06,
405
+ "learning_rate": 9.54326530612245e-06,
406
+ "loss": 0.2102,
407
+ "step": 1625
408
+ },
409
+ {
410
+ "epoch": 0.06,
411
+ "learning_rate": 9.533061224489796e-06,
412
+ "loss": 0.2043,
413
+ "step": 1650
414
+ },
415
+ {
416
+ "epoch": 0.06,
417
+ "learning_rate": 9.522857142857144e-06,
418
+ "loss": 0.2076,
419
+ "step": 1675
420
+ },
421
+ {
422
+ "epoch": 0.06,
423
+ "learning_rate": 9.512653061224491e-06,
424
+ "loss": 0.1988,
425
+ "step": 1700
426
+ },
427
+ {
428
+ "epoch": 0.06,
429
+ "learning_rate": 9.502448979591837e-06,
430
+ "loss": 0.2055,
431
+ "step": 1725
432
+ },
433
+ {
434
+ "epoch": 0.06,
435
+ "learning_rate": 9.492244897959184e-06,
436
+ "loss": 0.1982,
437
+ "step": 1750
438
+ },
439
+ {
440
+ "epoch": 0.06,
441
+ "learning_rate": 9.48204081632653e-06,
442
+ "loss": 0.2156,
443
+ "step": 1775
444
+ },
445
+ {
446
+ "epoch": 0.06,
447
+ "learning_rate": 9.47183673469388e-06,
448
+ "loss": 0.18,
449
+ "step": 1800
450
+ },
451
+ {
452
+ "epoch": 0.06,
453
+ "learning_rate": 9.461632653061225e-06,
454
+ "loss": 0.1985,
455
+ "step": 1825
456
+ },
457
+ {
458
+ "epoch": 0.06,
459
+ "learning_rate": 9.451428571428573e-06,
460
+ "loss": 0.2107,
461
+ "step": 1850
462
+ },
463
+ {
464
+ "epoch": 0.07,
465
+ "learning_rate": 9.44122448979592e-06,
466
+ "loss": 0.2168,
467
+ "step": 1875
468
+ },
469
+ {
470
+ "epoch": 0.07,
471
+ "learning_rate": 9.431020408163266e-06,
472
+ "loss": 0.2024,
473
+ "step": 1900
474
+ },
475
+ {
476
+ "epoch": 0.07,
477
+ "learning_rate": 9.420816326530613e-06,
478
+ "loss": 0.2318,
479
+ "step": 1925
480
+ },
481
+ {
482
+ "epoch": 0.07,
483
+ "learning_rate": 9.41061224489796e-06,
484
+ "loss": 0.1885,
485
+ "step": 1950
486
+ },
487
+ {
488
+ "epoch": 0.07,
489
+ "learning_rate": 9.400408163265307e-06,
490
+ "loss": 0.1939,
491
+ "step": 1975
492
+ },
493
+ {
494
+ "epoch": 0.07,
495
+ "learning_rate": 9.390204081632654e-06,
496
+ "loss": 0.1888,
497
+ "step": 2000
498
+ },
499
+ {
500
+ "epoch": 0.07,
501
+ "eval_loss": 0.21315988898277283,
502
+ "eval_runtime": 31190.3149,
503
+ "eval_samples_per_second": 0.995,
504
+ "eval_steps_per_second": 0.062,
505
+ "eval_wer": 0.11313539592435184,
506
+ "step": 2000
507
  }
508
  ],
509
  "max_steps": 25000,
510
  "num_train_epochs": 1,
511
+ "total_flos": 6.79414726656e+19,
512
  "trial_name": null,
513
  "trial_params": null
514
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f77f043740c59e3f92e8854de8cbf501f8b2ebb4879d9251a07b28a085d8540
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e2e9b2d8a6b71aca3a201dfdf9d5a8975658e82c8fdc5eb479bf91513d7de5
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 sha256:893f6b4ba91fc4613defcac59be86f805f3ce586dde326edb555f99d00c99d05
3
- size 10987
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc1976bb9aa3aa2282f8a4933412a747b15621808bb2de8544db13179c0b4c00
3
+ size 17585