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
e940b73
•
1 Parent(s): dcbccaa

Training in progress, step 6000

Browse files
Files changed (10) hide show
  1. {checkpoint-3000 → checkpoint-6000}/config.json +0 -0
  2. {checkpoint-3000 → checkpoint-6000}/optimizer.pt +1 -1
  3. {checkpoint-3000 → checkpoint-6000}/preprocessor_config.json +0 -0
  4. {checkpoint-3000 → checkpoint-6000}/pytorch_model.bin +1 -1
  5. {checkpoint-3000 → checkpoint-6000}/rng_state.pth +1 -1
  6. {checkpoint-3000 → checkpoint-6000}/scaler.pt +1 -1
  7. {checkpoint-3000 → checkpoint-6000}/scheduler.pt +1 -1
  8. {checkpoint-3000 → checkpoint-6000}/trainer_state.json +210 -3
  9. {checkpoint-3000 → checkpoint-6000}/training_args.bin +0 -0
  10. pytorch_model.bin +1 -1
{checkpoint-3000 → checkpoint-6000}/config.json RENAMED
File without changes
{checkpoint-3000 → checkpoint-6000}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94450a47c3ca62b991db9a57550d81b8cd90698ed4ef2543b783aa61e5c1766d
3
  size 2490337809
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a02e3f0c79bd1e97834af9735ae9ea2c51e986a0e4aebe78745ac090bd29bf
3
  size 2490337809
{checkpoint-3000 → checkpoint-6000}/preprocessor_config.json RENAMED
File without changes
{checkpoint-3000 → checkpoint-6000}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:327bed48381999df4748f541a4a9fa0c348c7ae5d4e4f883c614432b3a8395bd
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14c1a98519a72a2d3a4339ab78f6a4b41d391852271790078767a444fe87beb
3
  size 1262063089
{checkpoint-3000 → checkpoint-6000}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f80481468e633ed17f4d3b953b5bfd7af41f1fc73703fdad42f6fc3bad5c020f
3
  size 14567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7855b43fb50533e2e01cf47c566be51da5a7cd11b3be55d9d7c0c79407094c18
3
  size 14567
{checkpoint-3000 → checkpoint-6000}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05430fc7d2676bfa8c337884b4956f58b83fbf1ce211afb4952306653777fc6c
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d156164b5a9269c6c2ad987484964bc9fa0a7b461cee526f820c65c9c09e374a
3
  size 559
{checkpoint-3000 → checkpoint-6000}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14f025f6209560d43d4588b308395c8f0162d863f3099cf81ce8917d61699085
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b52dcc81c772638b05def04e150569a1ebe5930008f73931aa734959b1a983
3
  size 623
{checkpoint-3000 → checkpoint-6000}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 31.24935064935065,
5
- "global_step": 3000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -213,11 +213,218 @@
213
  "eval_steps_per_second": 0.795,
214
  "eval_wer": 0.1388858784003468,
215
  "step": 3000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
216
  }
217
  ],
218
  "max_steps": 9600,
219
  "num_train_epochs": 100,
220
- "total_flos": 4.660374091191037e+19,
221
  "trial_name": null,
222
  "trial_params": null
223
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 62.4987012987013,
5
+ "global_step": 6000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
213
  "eval_steps_per_second": 0.795,
214
  "eval_wer": 0.1388858784003468,
215
  "step": 3000
216
+ },
217
+ {
218
+ "epoch": 32.29,
219
+ "learning_rate": 6.3505859375e-05,
220
+ "loss": 0.9285,
221
+ "step": 3100
222
+ },
223
+ {
224
+ "epoch": 33.33,
225
+ "learning_rate": 6.252929687499999e-05,
226
+ "loss": 0.9121,
227
+ "step": 3200
228
+ },
229
+ {
230
+ "epoch": 34.37,
231
+ "learning_rate": 6.155273437499999e-05,
232
+ "loss": 0.9016,
233
+ "step": 3300
234
+ },
235
+ {
236
+ "epoch": 35.42,
237
+ "learning_rate": 6.0576171875e-05,
238
+ "loss": 0.9023,
239
+ "step": 3400
240
+ },
241
+ {
242
+ "epoch": 36.46,
243
+ "learning_rate": 5.9599609374999994e-05,
244
+ "loss": 0.9004,
245
+ "step": 3500
246
+ },
247
+ {
248
+ "epoch": 37.5,
249
+ "learning_rate": 5.862304687499999e-05,
250
+ "loss": 0.8844,
251
+ "step": 3600
252
+ },
253
+ {
254
+ "epoch": 38.54,
255
+ "learning_rate": 5.7646484375e-05,
256
+ "loss": 0.8771,
257
+ "step": 3700
258
+ },
259
+ {
260
+ "epoch": 39.58,
261
+ "learning_rate": 5.6669921875e-05,
262
+ "loss": 0.876,
263
+ "step": 3800
264
+ },
265
+ {
266
+ "epoch": 40.62,
267
+ "learning_rate": 5.569335937499999e-05,
268
+ "loss": 0.8708,
269
+ "step": 3900
270
+ },
271
+ {
272
+ "epoch": 41.66,
273
+ "learning_rate": 5.4716796874999997e-05,
274
+ "loss": 0.8691,
275
+ "step": 4000
276
+ },
277
+ {
278
+ "epoch": 41.66,
279
+ "eval_loss": 0.14571049809455872,
280
+ "eval_runtime": 195.237,
281
+ "eval_samples_per_second": 25.84,
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
  "max_steps": 9600,
426
  "num_train_epochs": 100,
427
+ "total_flos": 9.319334032985827e+19,
428
  "trial_name": null,
429
  "trial_params": null
430
  }
{checkpoint-3000 → checkpoint-6000}/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:fa6cf3410bd0459e255908bdf44aa100963a7896b62986289a4263c9bba0a128
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14c1a98519a72a2d3a4339ab78f6a4b41d391852271790078767a444fe87beb
3
  size 1262063089