Hugging Face's logo

marinone94
/
xls-r-300m-sv-robust

Automatic Speech Recognition
Transformers
PyTorch
Swedish
wav2vec2
mozilla-foundation/common_voice_9_0
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Community
1
marinone94 commited on
Commit
7b7da48
•
1 Parent(s): e940b73

Training in progress, step 7000

Browse files
Files changed (10) hide show
  1. {checkpoint-4000 → checkpoint-7000}/config.json +0 -0
  2. {checkpoint-4000 → checkpoint-7000}/optimizer.pt +1 -1
  3. {checkpoint-4000 → checkpoint-7000}/preprocessor_config.json +0 -0
  4. {checkpoint-4000 → checkpoint-7000}/pytorch_model.bin +1 -1
  5. {checkpoint-4000 → checkpoint-7000}/rng_state.pth +1 -1
  6. {checkpoint-4000 → checkpoint-7000}/scaler.pt +1 -1
  7. {checkpoint-4000 → checkpoint-7000}/scheduler.pt +1 -1
  8. {checkpoint-4000 → checkpoint-7000}/trainer_state.json +210 -3
  9. {checkpoint-4000 → checkpoint-7000}/training_args.bin +0 -0
  10. pytorch_model.bin +1 -1
{checkpoint-4000 → checkpoint-7000}/config.json RENAMED
File without changes
{checkpoint-4000 → checkpoint-7000}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32099ae8af68aa995295f81388cedfcdf53750287e2cd1926f799776c785dc9c
3
  size 2490337809
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8149cd19098a48ee10ff74dee0cc2084d94a4c41fe150d746e1b5709140f44ea
3
  size 2490337809
{checkpoint-4000 → checkpoint-7000}/preprocessor_config.json RENAMED
File without changes
{checkpoint-4000 → checkpoint-7000}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fab49963e9b9398b213516e5f111a4b3c94b65baca6eae9896d23b2cf617fc05
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37627cfc478091e469aa3336008b88b7357fe78bf289ef0337ff080db2b580d
3
  size 1262063089
{checkpoint-4000 → checkpoint-7000}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e559b653fce1fd6e42abc077a407aa059eb06e45c8ac45dcbf93fe543450eb17
3
  size 14567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0098bfe058c915bbbc841978f5eadb77f3664601fc66d811f09cf306ed86a3e2
3
  size 14567
{checkpoint-4000 → checkpoint-7000}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffc5542c3d0c9ad1fafea3de6341fb1dabeb7678f192c2521c05b244b277441d
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681e98dfadb561ae4866d369f1998b470f759d7fcd031000d9858bd09b56b85e
3
  size 559
{checkpoint-4000 → checkpoint-7000}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75e54b5a1f763d35b841701c1be7a179a2db0d635cfe3a56e3782e5e0cf62c90
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574187f5c73b47275ae699804d39777465bf9ef54d00a758e6fa127b339126d6
3
  size 623
{checkpoint-4000 → checkpoint-7000}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 41.664935064935065,
5
- "global_step": 4000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -282,11 +282,218 @@
282
  "eval_steps_per_second": 0.809,
283
  "eval_wer": 0.12899642353961202,
284
  "step": 4000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
285
  }
286
  ],
287
  "max_steps": 9600,
288
  "num_train_epochs": 100,
289
- "total_flos": 6.217407889828844e+19,
290
  "trial_name": null,
291
  "trial_params": null
292
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 72.91428571428571,
5
+ "global_step": 7000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
282
  "eval_steps_per_second": 0.809,
283
  "eval_wer": 0.12899642353961202,
284
  "step": 4000
285
+ },
286
+ {
287
+ "epoch": 42.71,
288
+ "learning_rate": 5.3740234374999996e-05,
289
+ "loss": 0.8624,
290
+ "step": 4100
291
+ },
292
+ {
293
+ "epoch": 43.75,
294
+ "learning_rate": 5.2763671874999995e-05,
295
+ "loss": 0.8556,
296
+ "step": 4200
297
+ },
298
+ {
299
+ "epoch": 44.79,
300
+ "learning_rate": 5.1787109375e-05,
301
+ "loss": 0.8607,
302
+ "step": 4300
303
+ },
304
+ {
305
+ "epoch": 45.83,
306
+ "learning_rate": 5.0810546875e-05,
307
+ "loss": 0.8536,
308
+ "step": 4400
309
+ },
310
+ {
311
+ "epoch": 46.87,
312
+ "learning_rate": 4.983398437499999e-05,
313
+ "loss": 0.8493,
314
+ "step": 4500
315
+ },
316
+ {
317
+ "epoch": 47.91,
318
+ "learning_rate": 4.8857421875e-05,
319
+ "loss": 0.8456,
320
+ "step": 4600
321
+ },
322
+ {
323
+ "epoch": 48.96,
324
+ "learning_rate": 4.7880859375e-05,
325
+ "loss": 0.8333,
326
+ "step": 4700
327
+ },
328
+ {
329
+ "epoch": 50.0,
330
+ "learning_rate": 4.6904296874999996e-05,
331
+ "loss": 0.8346,
332
+ "step": 4800
333
+ },
334
+ {
335
+ "epoch": 51.04,
336
+ "learning_rate": 4.5927734375e-05,
337
+ "loss": 0.8403,
338
+ "step": 4900
339
+ },
340
+ {
341
+ "epoch": 52.08,
342
+ "learning_rate": 4.4951171874999995e-05,
343
+ "loss": 0.8328,
344
+ "step": 5000
345
+ },
346
+ {
347
+ "epoch": 52.08,
348
+ "eval_loss": 0.14348936080932617,
349
+ "eval_runtime": 197.7739,
350
+ "eval_samples_per_second": 25.509,
351
+ "eval_steps_per_second": 0.799,
352
+ "eval_wer": 0.12054297171344966,
353
+ "step": 5000
354
+ },
355
+ {
356
+ "epoch": 53.12,
357
+ "learning_rate": 4.3974609374999994e-05,
358
+ "loss": 0.8275,
359
+ "step": 5100
360
+ },
361
+ {
362
+ "epoch": 54.17,
363
+ "learning_rate": 4.2998046875e-05,
364
+ "loss": 0.8262,
365
+ "step": 5200
366
+ },
367
+ {
368
+ "epoch": 55.21,
369
+ "learning_rate": 4.2021484375e-05,
370
+ "loss": 0.8167,
371
+ "step": 5300
372
+ },
373
+ {
374
+ "epoch": 56.25,
375
+ "learning_rate": 4.1044921875e-05,
376
+ "loss": 0.8194,
377
+ "step": 5400
378
+ },
379
+ {
380
+ "epoch": 57.29,
381
+ "learning_rate": 4.0068359375e-05,
382
+ "loss": 0.8192,
383
+ "step": 5500
384
+ },
385
+ {
386
+ "epoch": 58.33,
387
+ "learning_rate": 3.9091796874999996e-05,
388
+ "loss": 0.8176,
389
+ "step": 5600
390
+ },
391
+ {
392
+ "epoch": 59.37,
393
+ "learning_rate": 3.8115234374999995e-05,
394
+ "loss": 0.8115,
395
+ "step": 5700
396
+ },
397
+ {
398
+ "epoch": 60.42,
399
+ "learning_rate": 3.7138671874999994e-05,
400
+ "loss": 0.8129,
401
+ "step": 5800
402
+ },
403
+ {
404
+ "epoch": 61.46,
405
+ "learning_rate": 3.6162109375e-05,
406
+ "loss": 0.8052,
407
+ "step": 5900
408
+ },
409
+ {
410
+ "epoch": 62.5,
411
+ "learning_rate": 3.518554687499999e-05,
412
+ "loss": 0.8068,
413
+ "step": 6000
414
+ },
415
+ {
416
+ "epoch": 62.5,
417
+ "eval_loss": 0.13501569628715515,
418
+ "eval_runtime": 207.5786,
419
+ "eval_samples_per_second": 24.304,
420
+ "eval_steps_per_second": 0.761,
421
+ "eval_wer": 0.11913406307575593,
422
+ "step": 6000
423
+ },
424
+ {
425
+ "epoch": 63.54,
426
+ "learning_rate": 3.4208984375e-05,
427
+ "loss": 0.8004,
428
+ "step": 6100
429
+ },
430
+ {
431
+ "epoch": 64.58,
432
+ "learning_rate": 3.32421875e-05,
433
+ "loss": 0.7904,
434
+ "step": 6200
435
+ },
436
+ {
437
+ "epoch": 65.62,
438
+ "learning_rate": 3.2265625e-05,
439
+ "loss": 0.7947,
440
+ "step": 6300
441
+ },
442
+ {
443
+ "epoch": 66.66,
444
+ "learning_rate": 3.12890625e-05,
445
+ "loss": 0.7981,
446
+ "step": 6400
447
+ },
448
+ {
449
+ "epoch": 67.71,
450
+ "learning_rate": 3.0312499999999998e-05,
451
+ "loss": 0.8018,
452
+ "step": 6500
453
+ },
454
+ {
455
+ "epoch": 68.75,
456
+ "learning_rate": 2.93359375e-05,
457
+ "loss": 0.7922,
458
+ "step": 6600
459
+ },
460
+ {
461
+ "epoch": 69.79,
462
+ "learning_rate": 2.8359374999999996e-05,
463
+ "loss": 0.796,
464
+ "step": 6700
465
+ },
466
+ {
467
+ "epoch": 70.83,
468
+ "learning_rate": 2.73828125e-05,
469
+ "loss": 0.7887,
470
+ "step": 6800
471
+ },
472
+ {
473
+ "epoch": 71.87,
474
+ "learning_rate": 2.6406249999999998e-05,
475
+ "loss": 0.7796,
476
+ "step": 6900
477
+ },
478
+ {
479
+ "epoch": 72.91,
480
+ "learning_rate": 2.5429687499999997e-05,
481
+ "loss": 0.7822,
482
+ "step": 7000
483
+ },
484
+ {
485
+ "epoch": 72.91,
486
+ "eval_loss": 0.1346774846315384,
487
+ "eval_runtime": 195.6804,
488
+ "eval_samples_per_second": 25.782,
489
+ "eval_steps_per_second": 0.807,
490
+ "eval_wer": 0.11550341389400672,
491
+ "step": 7000
492
  }
493
  ],
494
  "max_steps": 9600,
495
  "num_train_epochs": 100,
496
+ "total_flos": 1.0876707707200464e+20,
497
  "trial_name": null,
498
  "trial_params": null
499
  }
{checkpoint-4000 → checkpoint-7000}/training_args.bin RENAMED
File without changes
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c14c1a98519a72a2d3a4339ab78f6a4b41d391852271790078767a444fe87beb
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37627cfc478091e469aa3336008b88b7357fe78bf289ef0337ff080db2b580d
3
  size 1262063089