marinone94 commited on
Commit
e932e54
β€’
1 Parent(s): 6afffc7

Training in progress, step 1100

Browse files
{checkpoint-800 β†’ checkpoint-1100}/config.json RENAMED
File without changes
{checkpoint-800 β†’ checkpoint-1100}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3228c2d654fd3d25a0ad00a301f5ce6f4265d0cc4c922a869f44a37a2b0f0f2
3
  size 2490337809
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2764c7b6a7ab8b996c7f8b013c511bd3930da2122168a0414e1ca544a9e84f2
3
  size 2490337809
{checkpoint-800 β†’ checkpoint-1100}/preprocessor_config.json RENAMED
File without changes
{checkpoint-800 β†’ checkpoint-1100}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83f2151485570eebb9c2c7ead79b5dbb947c911745136ec08aec4531150fc59d
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52f572d7d82915632c807843bc385396652654a3642cc0c48a960f29f61ae2c
3
  size 1262063089
{checkpoint-800 β†’ checkpoint-1100}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:191ab0b0b7f850bd200dd0e9733735c31b1e7d63b3150165c4de6c4a12c5ef5e
3
- size 14567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecce699b9acc62a6e6d026fa16dc32a7b0705c4e3b0ae1ece12b2b69d2fab156
3
+ size 14503
{checkpoint-800 β†’ checkpoint-1100}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c2074cdcefbaa0a39f736d6b0f7bf018c350d49e85648bc8accc4f756ad816e
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb16c30b686aa43e110b0d33f9d46bf3127b7124542ca8dc34831233d4675a0
3
  size 559
{checkpoint-800 β†’ checkpoint-1100}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:595ce5051ecea72321f0a4e15d7e1d59293398355f90dbde31fcccb29f2b4f95
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e7aeb62a4a52ddfec85a856a87b7012a808e573de75503e41cc84ea035b66c
3
  size 623
{checkpoint-800 β†’ checkpoint-1100}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 8.78688524590164,
5
- "global_step": 800,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -318,11 +318,128 @@
318
  "eval_steps_per_second": 0.792,
319
  "eval_wer": 1.0,
320
  "step": 800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
321
  }
322
  ],
323
  "max_steps": 4550,
324
  "num_train_epochs": 50,
325
- "total_flos": 1.2402928809554872e+19,
326
  "trial_name": null,
327
  "trial_params": null
328
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 12.087431693989071,
5
+ "global_step": 1100,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
318
  "eval_steps_per_second": 0.792,
319
  "eval_wer": 1.0,
320
  "step": 800
321
+ },
322
+ {
323
+ "epoch": 9.01,
324
+ "learning_rate": 0.0001025,
325
+ "loss": 2.8933,
326
+ "step": 820
327
+ },
328
+ {
329
+ "epoch": 9.23,
330
+ "learning_rate": 0.000105,
331
+ "loss": 2.7318,
332
+ "step": 840
333
+ },
334
+ {
335
+ "epoch": 9.45,
336
+ "learning_rate": 0.0001075,
337
+ "loss": 2.5941,
338
+ "step": 860
339
+ },
340
+ {
341
+ "epoch": 9.67,
342
+ "learning_rate": 0.00011,
343
+ "loss": 2.4441,
344
+ "step": 880
345
+ },
346
+ {
347
+ "epoch": 9.89,
348
+ "learning_rate": 0.00011250000000000001,
349
+ "loss": 2.2931,
350
+ "step": 900
351
+ },
352
+ {
353
+ "epoch": 9.89,
354
+ "eval_loss": 1.5057899951934814,
355
+ "eval_runtime": 196.4368,
356
+ "eval_samples_per_second": 24.654,
357
+ "eval_steps_per_second": 0.774,
358
+ "eval_wer": 0.9775759296054499,
359
+ "step": 900
360
+ },
361
+ {
362
+ "epoch": 10.11,
363
+ "learning_rate": 0.000115,
364
+ "loss": 2.1999,
365
+ "step": 920
366
+ },
367
+ {
368
+ "epoch": 10.33,
369
+ "learning_rate": 0.0001175,
370
+ "loss": 2.0574,
371
+ "step": 940
372
+ },
373
+ {
374
+ "epoch": 10.55,
375
+ "learning_rate": 0.00012,
376
+ "loss": 1.9672,
377
+ "step": 960
378
+ },
379
+ {
380
+ "epoch": 10.77,
381
+ "learning_rate": 0.0001225,
382
+ "loss": 1.9015,
383
+ "step": 980
384
+ },
385
+ {
386
+ "epoch": 10.98,
387
+ "learning_rate": 0.000125,
388
+ "loss": 1.8427,
389
+ "step": 1000
390
+ },
391
+ {
392
+ "epoch": 10.98,
393
+ "eval_loss": 0.9154536724090576,
394
+ "eval_runtime": 203.1168,
395
+ "eval_samples_per_second": 23.843,
396
+ "eval_steps_per_second": 0.748,
397
+ "eval_wer": 0.7832245245529378,
398
+ "step": 1000
399
+ },
400
+ {
401
+ "epoch": 11.21,
402
+ "learning_rate": 0.0001275,
403
+ "loss": 1.8155,
404
+ "step": 1020
405
+ },
406
+ {
407
+ "epoch": 11.43,
408
+ "learning_rate": 0.00013000000000000002,
409
+ "loss": 1.6767,
410
+ "step": 1040
411
+ },
412
+ {
413
+ "epoch": 11.64,
414
+ "learning_rate": 0.00013250000000000002,
415
+ "loss": 1.5184,
416
+ "step": 1060
417
+ },
418
+ {
419
+ "epoch": 11.86,
420
+ "learning_rate": 0.000135,
421
+ "loss": 1.4505,
422
+ "step": 1080
423
+ },
424
+ {
425
+ "epoch": 12.09,
426
+ "learning_rate": 0.0001375,
427
+ "loss": 1.4286,
428
+ "step": 1100
429
+ },
430
+ {
431
+ "epoch": 12.09,
432
+ "eval_loss": 0.4074769914150238,
433
+ "eval_runtime": 194.7798,
434
+ "eval_samples_per_second": 24.864,
435
+ "eval_steps_per_second": 0.78,
436
+ "eval_wer": 0.37964802724950325,
437
+ "step": 1100
438
  }
439
  ],
440
  "max_steps": 4550,
441
  "num_train_epochs": 50,
442
+ "total_flos": 1.7049406331377541e+19,
443
  "trial_name": null,
444
  "trial_params": null
445
  }
{checkpoint-800 β†’ checkpoint-1100}/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 sha256:8dccfbc86aa27461d23f7422a406db1866d4a1ca82d159e2b5e3bcbdbc5a4a7a
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52f572d7d82915632c807843bc385396652654a3642cc0c48a960f29f61ae2c
3
  size 1262063089