Hugging Face's logo

JRHuy
/
whisper-small-vivos

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JRHuy commited on
Commit
6ed888a
•
1 Parent(s): a7af0ed

Training in progress, step 2000

Browse files
Files changed (7) 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/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +255 -5
  6. pytorch_model.bin +1 -1
  7. runs/Aug20_17-07-13_713cba38a708/events.out.tfevents.1692551245.713cba38a708.95.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5a0364b80d7da28a472b485617d9fd03601e396d96c284dde0cf058c312d114
3
  size 1934161157
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9345b866ebc9159328815b3ecdcc308b8a2e853a3e173aee675d508068a92b2d
3
  size 1934161157
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:383ebae7d6ef21ae47fd894b8df9f65cfb2f7f9d22e0541de8b6117cf1dea24f
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65503e2d287eeb93231cc3f6e123f111f05e00b5886775a96c9f0f3234a9cb60
3
  size 967102729
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a414e764969027db59f536475e679fa837f5cf868456c551dece078e20eb451
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def05a477428754b4320528e52a0b3ae385799f784ed0d816af6d7b633b37a5a
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59963924066510fdace06e40de705170e7801273e45f984c4330d09d2783e55d
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cd37dd530bd467817ba99df096031e0ec04862523fd363efae5f40294a6a156
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 20.616420616420616,
3
- "best_model_checkpoint": "./whisper-small-vivos/checkpoint-1000",
4
- "epoch": 1.3717421124828533,
5
- "global_step": 1000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -256,11 +256,261 @@
256
  "eval_steps_per_second": 0.122,
257
  "eval_wer": 20.616420616420616,
258
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
259
  }
260
  ],
261
  "max_steps": 4000,
262
  "num_train_epochs": 6,
263
- "total_flos": 4.61621206351872e+18,
264
  "trial_name": null,
265
  "trial_params": null
266
  }
 
1
  {
2
+ "best_metric": 19.08831908831909,
3
+ "best_model_checkpoint": "./whisper-small-vivos/checkpoint-2000",
4
+ "epoch": 2.7434842249657065,
5
+ "global_step": 2000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
256
  "eval_steps_per_second": 0.122,
257
  "eval_wer": 20.616420616420616,
258
  "step": 1000
259
+ },
260
+ {
261
+ "epoch": 1.41,
262
+ "learning_rate": 1e-05,
263
+ "loss": 0.1184,
264
+ "step": 1025
265
+ },
266
+ {
267
+ "epoch": 1.44,
268
+ "learning_rate": 1e-05,
269
+ "loss": 0.125,
270
+ "step": 1050
271
+ },
272
+ {
273
+ "epoch": 1.47,
274
+ "learning_rate": 1e-05,
275
+ "loss": 0.1163,
276
+ "step": 1075
277
+ },
278
+ {
279
+ "epoch": 1.51,
280
+ "learning_rate": 1e-05,
281
+ "loss": 0.1263,
282
+ "step": 1100
283
+ },
284
+ {
285
+ "epoch": 1.54,
286
+ "learning_rate": 1e-05,
287
+ "loss": 0.1129,
288
+ "step": 1125
289
+ },
290
+ {
291
+ "epoch": 1.58,
292
+ "learning_rate": 1e-05,
293
+ "loss": 0.1199,
294
+ "step": 1150
295
+ },
296
+ {
297
+ "epoch": 1.61,
298
+ "learning_rate": 1e-05,
299
+ "loss": 0.1231,
300
+ "step": 1175
301
+ },
302
+ {
303
+ "epoch": 1.65,
304
+ "learning_rate": 1e-05,
305
+ "loss": 0.1195,
306
+ "step": 1200
307
+ },
308
+ {
309
+ "epoch": 1.68,
310
+ "learning_rate": 1e-05,
311
+ "loss": 0.1145,
312
+ "step": 1225
313
+ },
314
+ {
315
+ "epoch": 1.71,
316
+ "learning_rate": 1e-05,
317
+ "loss": 0.1115,
318
+ "step": 1250
319
+ },
320
+ {
321
+ "epoch": 1.75,
322
+ "learning_rate": 1e-05,
323
+ "loss": 0.117,
324
+ "step": 1275
325
+ },
326
+ {
327
+ "epoch": 1.78,
328
+ "learning_rate": 1e-05,
329
+ "loss": 0.1089,
330
+ "step": 1300
331
+ },
332
+ {
333
+ "epoch": 1.82,
334
+ "learning_rate": 1e-05,
335
+ "loss": 0.1143,
336
+ "step": 1325
337
+ },
338
+ {
339
+ "epoch": 1.85,
340
+ "learning_rate": 1e-05,
341
+ "loss": 0.1195,
342
+ "step": 1350
343
+ },
344
+ {
345
+ "epoch": 1.89,
346
+ "learning_rate": 1e-05,
347
+ "loss": 0.1137,
348
+ "step": 1375
349
+ },
350
+ {
351
+ "epoch": 1.92,
352
+ "learning_rate": 1e-05,
353
+ "loss": 0.1142,
354
+ "step": 1400
355
+ },
356
+ {
357
+ "epoch": 1.95,
358
+ "learning_rate": 1e-05,
359
+ "loss": 0.1022,
360
+ "step": 1425
361
+ },
362
+ {
363
+ "epoch": 1.99,
364
+ "learning_rate": 1e-05,
365
+ "loss": 0.1,
366
+ "step": 1450
367
+ },
368
+ {
369
+ "epoch": 2.02,
370
+ "learning_rate": 1e-05,
371
+ "loss": 0.0854,
372
+ "step": 1475
373
+ },
374
+ {
375
+ "epoch": 2.06,
376
+ "learning_rate": 1e-05,
377
+ "loss": 0.0707,
378
+ "step": 1500
379
+ },
380
+ {
381
+ "epoch": 2.09,
382
+ "learning_rate": 1e-05,
383
+ "loss": 0.0702,
384
+ "step": 1525
385
+ },
386
+ {
387
+ "epoch": 2.13,
388
+ "learning_rate": 1e-05,
389
+ "loss": 0.0647,
390
+ "step": 1550
391
+ },
392
+ {
393
+ "epoch": 2.16,
394
+ "learning_rate": 1e-05,
395
+ "loss": 0.0713,
396
+ "step": 1575
397
+ },
398
+ {
399
+ "epoch": 2.19,
400
+ "learning_rate": 1e-05,
401
+ "loss": 0.0627,
402
+ "step": 1600
403
+ },
404
+ {
405
+ "epoch": 2.23,
406
+ "learning_rate": 1e-05,
407
+ "loss": 0.0678,
408
+ "step": 1625
409
+ },
410
+ {
411
+ "epoch": 2.26,
412
+ "learning_rate": 1e-05,
413
+ "loss": 0.0667,
414
+ "step": 1650
415
+ },
416
+ {
417
+ "epoch": 2.3,
418
+ "learning_rate": 1e-05,
419
+ "loss": 0.0795,
420
+ "step": 1675
421
+ },
422
+ {
423
+ "epoch": 2.33,
424
+ "learning_rate": 1e-05,
425
+ "loss": 0.0608,
426
+ "step": 1700
427
+ },
428
+ {
429
+ "epoch": 2.37,
430
+ "learning_rate": 1e-05,
431
+ "loss": 0.0642,
432
+ "step": 1725
433
+ },
434
+ {
435
+ "epoch": 2.4,
436
+ "learning_rate": 1e-05,
437
+ "loss": 0.0684,
438
+ "step": 1750
439
+ },
440
+ {
441
+ "epoch": 2.43,
442
+ "learning_rate": 1e-05,
443
+ "loss": 0.0676,
444
+ "step": 1775
445
+ },
446
+ {
447
+ "epoch": 2.47,
448
+ "learning_rate": 1e-05,
449
+ "loss": 0.0743,
450
+ "step": 1800
451
+ },
452
+ {
453
+ "epoch": 2.5,
454
+ "learning_rate": 1e-05,
455
+ "loss": 0.0713,
456
+ "step": 1825
457
+ },
458
+ {
459
+ "epoch": 2.54,
460
+ "learning_rate": 1e-05,
461
+ "loss": 0.062,
462
+ "step": 1850
463
+ },
464
+ {
465
+ "epoch": 2.57,
466
+ "learning_rate": 1e-05,
467
+ "loss": 0.0678,
468
+ "step": 1875
469
+ },
470
+ {
471
+ "epoch": 2.61,
472
+ "learning_rate": 1e-05,
473
+ "loss": 0.0668,
474
+ "step": 1900
475
+ },
476
+ {
477
+ "epoch": 2.64,
478
+ "learning_rate": 1e-05,
479
+ "loss": 0.0739,
480
+ "step": 1925
481
+ },
482
+ {
483
+ "epoch": 2.67,
484
+ "learning_rate": 1e-05,
485
+ "loss": 0.0672,
486
+ "step": 1950
487
+ },
488
+ {
489
+ "epoch": 2.71,
490
+ "learning_rate": 1e-05,
491
+ "loss": 0.0653,
492
+ "step": 1975
493
+ },
494
+ {
495
+ "epoch": 2.74,
496
+ "learning_rate": 1e-05,
497
+ "loss": 0.0696,
498
+ "step": 2000
499
+ },
500
+ {
501
+ "epoch": 2.74,
502
+ "eval_cer": 7.509688444051142,
503
+ "eval_loss": 0.217300683259964,
504
+ "eval_runtime": 392.9774,
505
+ "eval_samples_per_second": 1.934,
506
+ "eval_steps_per_second": 0.122,
507
+ "eval_wer": 19.08831908831909,
508
+ "step": 2000
509
  }
510
  ],
511
  "max_steps": 4000,
512
  "num_train_epochs": 6,
513
+ "total_flos": 9.23242412703744e+18,
514
  "trial_name": null,
515
  "trial_params": null
516
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:383ebae7d6ef21ae47fd894b8df9f65cfb2f7f9d22e0541de8b6117cf1dea24f
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65503e2d287eeb93231cc3f6e123f111f05e00b5886775a96c9f0f3234a9cb60
3
  size 967102729
runs/Aug20_17-07-13_713cba38a708/events.out.tfevents.1692551245.713cba38a708.95.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d21c93fc97b39bff9f20d4451035bbdf4c8cff4a82b54050f17d54a5a22c4597
3
- size 12474
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7badd4eee194eccbbca23d4b453d756dca52d0772c6e2718bb059f9da62b8d29
3
+ size 19119