Hugging Face's logo

JRHuy
/
whisper-small-vietnamese

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JRHuy commited on
Commit
b7e39b2
•
1 Parent(s): 0b4f7cb

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 +253 -3
  6. pytorch_model.bin +1 -1
  7. runs/Aug21_16-43-21_8bad39564bfa/events.out.tfevents.1692636213.8bad39564bfa.55.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70ac9a1100fe08433429d4ef61555e6f26a0841e2993c699bc40cef2a156d6a3
3
  size 1934161157
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d9f310e7215fa53772a26e73c8bfe99258430f637a0e7c6a57b1411a3fc046
3
  size 1934161157
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74715a76afe58148a58e60fd60640fb48ee3007e4b51f3fc186ec4d3e2f6432f
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08268c9356743b28c4219f4829b0833b9e174958fd62a1cb1e2061f4cf025441
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:fd6139d29a3af961e597704354b793fa883745b34895fbb57194352edccac9ed
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11dbcedeb462d624e874b21e47f755022f531a9db8eea64f2e44191aab46241b
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": 16.120763315294788,
3
  "best_model_checkpoint": "./whisper-small-vietnamese/checkpoint-1000",
4
- "epoch": 2.865329512893983,
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": 0.099,
257
  "eval_wer": 16.120763315294788,
258
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
259
  }
260
  ],
261
  "max_steps": 4000,
262
  "num_train_epochs": 12,
263
- "total_flos": 4.61044035551232e+18,
264
  "trial_name": null,
265
  "trial_params": null
266
  }
 
1
  {
2
  "best_metric": 16.120763315294788,
3
  "best_model_checkpoint": "./whisper-small-vietnamese/checkpoint-1000",
4
+ "epoch": 5.730659025787966,
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": 0.099,
257
  "eval_wer": 16.120763315294788,
258
  "step": 1000
259
+ },
260
+ {
261
+ "epoch": 2.94,
262
+ "learning_rate": 1e-05,
263
+ "loss": 0.1508,
264
+ "step": 1025
265
+ },
266
+ {
267
+ "epoch": 3.01,
268
+ "learning_rate": 1e-05,
269
+ "loss": 0.1379,
270
+ "step": 1050
271
+ },
272
+ {
273
+ "epoch": 3.08,
274
+ "learning_rate": 1e-05,
275
+ "loss": 0.0688,
276
+ "step": 1075
277
+ },
278
+ {
279
+ "epoch": 3.15,
280
+ "learning_rate": 1e-05,
281
+ "loss": 0.0738,
282
+ "step": 1100
283
+ },
284
+ {
285
+ "epoch": 3.22,
286
+ "learning_rate": 1e-05,
287
+ "loss": 0.0731,
288
+ "step": 1125
289
+ },
290
+ {
291
+ "epoch": 3.3,
292
+ "learning_rate": 1e-05,
293
+ "loss": 0.0767,
294
+ "step": 1150
295
+ },
296
+ {
297
+ "epoch": 3.37,
298
+ "learning_rate": 1e-05,
299
+ "loss": 0.0742,
300
+ "step": 1175
301
+ },
302
+ {
303
+ "epoch": 3.44,
304
+ "learning_rate": 1e-05,
305
+ "loss": 0.0734,
306
+ "step": 1200
307
+ },
308
+ {
309
+ "epoch": 3.51,
310
+ "learning_rate": 1e-05,
311
+ "loss": 0.0774,
312
+ "step": 1225
313
+ },
314
+ {
315
+ "epoch": 3.58,
316
+ "learning_rate": 1e-05,
317
+ "loss": 0.0738,
318
+ "step": 1250
319
+ },
320
+ {
321
+ "epoch": 3.65,
322
+ "learning_rate": 1e-05,
323
+ "loss": 0.0742,
324
+ "step": 1275
325
+ },
326
+ {
327
+ "epoch": 3.72,
328
+ "learning_rate": 1e-05,
329
+ "loss": 0.0737,
330
+ "step": 1300
331
+ },
332
+ {
333
+ "epoch": 3.8,
334
+ "learning_rate": 1e-05,
335
+ "loss": 0.0781,
336
+ "step": 1325
337
+ },
338
+ {
339
+ "epoch": 3.87,
340
+ "learning_rate": 1e-05,
341
+ "loss": 0.0741,
342
+ "step": 1350
343
+ },
344
+ {
345
+ "epoch": 3.94,
346
+ "learning_rate": 1e-05,
347
+ "loss": 0.0732,
348
+ "step": 1375
349
+ },
350
+ {
351
+ "epoch": 4.01,
352
+ "learning_rate": 1e-05,
353
+ "loss": 0.0726,
354
+ "step": 1400
355
+ },
356
+ {
357
+ "epoch": 4.08,
358
+ "learning_rate": 1e-05,
359
+ "loss": 0.0364,
360
+ "step": 1425
361
+ },
362
+ {
363
+ "epoch": 4.15,
364
+ "learning_rate": 1e-05,
365
+ "loss": 0.0324,
366
+ "step": 1450
367
+ },
368
+ {
369
+ "epoch": 4.23,
370
+ "learning_rate": 1e-05,
371
+ "loss": 0.0331,
372
+ "step": 1475
373
+ },
374
+ {
375
+ "epoch": 4.3,
376
+ "learning_rate": 1e-05,
377
+ "loss": 0.0339,
378
+ "step": 1500
379
+ },
380
+ {
381
+ "epoch": 4.37,
382
+ "learning_rate": 1e-05,
383
+ "loss": 0.043,
384
+ "step": 1525
385
+ },
386
+ {
387
+ "epoch": 4.44,
388
+ "learning_rate": 1e-05,
389
+ "loss": 0.0402,
390
+ "step": 1550
391
+ },
392
+ {
393
+ "epoch": 4.51,
394
+ "learning_rate": 1e-05,
395
+ "loss": 0.0359,
396
+ "step": 1575
397
+ },
398
+ {
399
+ "epoch": 4.58,
400
+ "learning_rate": 1e-05,
401
+ "loss": 0.0351,
402
+ "step": 1600
403
+ },
404
+ {
405
+ "epoch": 4.66,
406
+ "learning_rate": 1e-05,
407
+ "loss": 0.0381,
408
+ "step": 1625
409
+ },
410
+ {
411
+ "epoch": 4.73,
412
+ "learning_rate": 1e-05,
413
+ "loss": 0.0391,
414
+ "step": 1650
415
+ },
416
+ {
417
+ "epoch": 4.8,
418
+ "learning_rate": 1e-05,
419
+ "loss": 0.0357,
420
+ "step": 1675
421
+ },
422
+ {
423
+ "epoch": 4.87,
424
+ "learning_rate": 1e-05,
425
+ "loss": 0.0372,
426
+ "step": 1700
427
+ },
428
+ {
429
+ "epoch": 4.94,
430
+ "learning_rate": 1e-05,
431
+ "loss": 0.039,
432
+ "step": 1725
433
+ },
434
+ {
435
+ "epoch": 5.01,
436
+ "learning_rate": 1e-05,
437
+ "loss": 0.0318,
438
+ "step": 1750
439
+ },
440
+ {
441
+ "epoch": 5.09,
442
+ "learning_rate": 1e-05,
443
+ "loss": 0.0191,
444
+ "step": 1775
445
+ },
446
+ {
447
+ "epoch": 5.16,
448
+ "learning_rate": 1e-05,
449
+ "loss": 0.0216,
450
+ "step": 1800
451
+ },
452
+ {
453
+ "epoch": 5.23,
454
+ "learning_rate": 1e-05,
455
+ "loss": 0.019,
456
+ "step": 1825
457
+ },
458
+ {
459
+ "epoch": 5.3,
460
+ "learning_rate": 1e-05,
461
+ "loss": 0.0203,
462
+ "step": 1850
463
+ },
464
+ {
465
+ "epoch": 5.37,
466
+ "learning_rate": 1e-05,
467
+ "loss": 0.0198,
468
+ "step": 1875
469
+ },
470
+ {
471
+ "epoch": 5.44,
472
+ "learning_rate": 1e-05,
473
+ "loss": 0.0191,
474
+ "step": 1900
475
+ },
476
+ {
477
+ "epoch": 5.52,
478
+ "learning_rate": 1e-05,
479
+ "loss": 0.018,
480
+ "step": 1925
481
+ },
482
+ {
483
+ "epoch": 5.59,
484
+ "learning_rate": 1e-05,
485
+ "loss": 0.0198,
486
+ "step": 1950
487
+ },
488
+ {
489
+ "epoch": 5.66,
490
+ "learning_rate": 1e-05,
491
+ "loss": 0.0236,
492
+ "step": 1975
493
+ },
494
+ {
495
+ "epoch": 5.73,
496
+ "learning_rate": 1e-05,
497
+ "loss": 0.0198,
498
+ "step": 2000
499
+ },
500
+ {
501
+ "epoch": 5.73,
502
+ "eval_cer": 9.205097697985662,
503
+ "eval_loss": 0.4001982510089874,
504
+ "eval_runtime": 712.4165,
505
+ "eval_samples_per_second": 1.55,
506
+ "eval_steps_per_second": 0.097,
507
+ "eval_wer": 16.708526449341033,
508
+ "step": 2000
509
  }
510
  ],
511
  "max_steps": 4000,
512
  "num_train_epochs": 12,
513
+ "total_flos": 9.2174176862208e+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 sha256:74715a76afe58148a58e60fd60640fb48ee3007e4b51f3fc186ec4d3e2f6432f
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08268c9356743b28c4219f4829b0833b9e174958fd62a1cb1e2061f4cf025441
3
  size 967102729
runs/Aug21_16-43-21_8bad39564bfa/events.out.tfevents.1692636213.8bad39564bfa.55.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9e663811895efe0c3519d166c491e09afc9b573b83de53f4c752fb8831083e6
3
- size 12494
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd7e56f2ee548b2300e461b19266ec105f9ed5c6c75687d5ded64b101777e0c
3
+ size 19139