Hugging Face's logo

dzanbek
/
b19f0afb-87c9-4c3a-9b22-183983e96095

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files
xet
 Community
dzanbek commited on
Commit
748ed3e
·
verified ·
1 Parent(s): c6b607e

Training in progress, step 75, checkpoint

Browse files
Files changed (4) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/rng_state.pth +1 -1
  3. last-checkpoint/scheduler.pt +1 -1
  4. last-checkpoint/trainer_state.json +187 -4
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92a3a3fce1543dc4ceb4767eea2facf12955e360a68d39ef1223180b1a326fa9
3
  size 47860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8430047d8b90d42bd78b0782f3678dbe6ea191029aa9ec20961ed733e662fe9d
3
  size 47860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e6ebd5d90a901ab3a4882911629cbc8bf4142ee87fa52fdfdbc3ef30adc53d3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fd333563d341e5baa5c8b808fe012ad11a41788bafd15e1988d5d595a4760af
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0017519961806483262,
5
  "eval_steps": 25,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -381,6 +381,189 @@
381
  "eval_samples_per_second": 42.277,
382
  "eval_steps_per_second": 21.139,
383
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -395,12 +578,12 @@
395
  "should_evaluate": false,
396
  "should_log": false,
397
  "should_save": true,
398
- "should_training_stop": false
399
  },
400
  "attributes": {}
401
  }
402
  },
403
- "total_flos": 61656268800.0,
404
  "train_batch_size": 2,
405
  "trial_name": null,
406
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0026279942709724895,
5
  "eval_steps": 25,
6
+ "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
381
  "eval_samples_per_second": 42.277,
382
  "eval_steps_per_second": 21.139,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.0017870361042612926,
387
+ "grad_norm": NaN,
388
+ "learning_rate": 5.000000000000002e-05,
389
+ "loss": 0.0,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.0018220760278742593,
394
+ "grad_norm": NaN,
395
+ "learning_rate": 4.6270039165317605e-05,
396
+ "loss": 0.0,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.0018571159514872257,
401
+ "grad_norm": NaN,
402
+ "learning_rate": 4.264235636489542e-05,
403
+ "loss": 0.0,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.0018921558751001924,
408
+ "grad_norm": NaN,
409
+ "learning_rate": 3.9123857099127936e-05,
410
+ "loss": 0.0,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.0019271957987131588,
415
+ "grad_norm": NaN,
416
+ "learning_rate": 3.5721239031346066e-05,
417
+ "loss": 0.0,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.0019622357223261252,
422
+ "grad_norm": NaN,
423
+ "learning_rate": 3.244097923843398e-05,
424
+ "loss": 0.0,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.001997275645939092,
429
+ "grad_norm": NaN,
430
+ "learning_rate": 2.9289321881345254e-05,
431
+ "loss": 0.0,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.0020323155695520585,
436
+ "grad_norm": NaN,
437
+ "learning_rate": 2.6272266318987603e-05,
438
+ "loss": 0.0,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.0020673554931650248,
443
+ "grad_norm": NaN,
444
+ "learning_rate": 2.339555568810221e-05,
445
+ "loss": 0.0,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.0021023954167779914,
450
+ "grad_norm": NaN,
451
+ "learning_rate": 2.0664665970876496e-05,
452
+ "loss": 0.0,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.002137435340390958,
457
+ "grad_norm": NaN,
458
+ "learning_rate": 1.808479557110081e-05,
459
+ "loss": 0.0,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.0021724752640039243,
464
+ "grad_norm": NaN,
465
+ "learning_rate": 1.566085541871145e-05,
466
+ "loss": 0.0,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.002207515187616891,
471
+ "grad_norm": NaN,
472
+ "learning_rate": 1.339745962155613e-05,
473
+ "loss": 0.0,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.0022425551112298576,
478
+ "grad_norm": NaN,
479
+ "learning_rate": 1.129891668217783e-05,
480
+ "loss": 0.0,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.0022775950348428243,
485
+ "grad_norm": NaN,
486
+ "learning_rate": 9.369221296335006e-06,
487
+ "loss": 0.0,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.0023126349584557905,
492
+ "grad_norm": NaN,
493
+ "learning_rate": 7.612046748871327e-06,
494
+ "loss": 0.0,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.002347674882068757,
499
+ "grad_norm": NaN,
500
+ "learning_rate": 6.030737921409169e-06,
501
+ "loss": 0.0,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.0023827148056817238,
506
+ "grad_norm": NaN,
507
+ "learning_rate": 4.628304925177318e-06,
508
+ "loss": 0.0,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.00241775472929469,
513
+ "grad_norm": NaN,
514
+ "learning_rate": 3.40741737109318e-06,
515
+ "loss": 0.0,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.0024527946529076567,
520
+ "grad_norm": NaN,
521
+ "learning_rate": 2.3703992880066638e-06,
522
+ "loss": 0.0,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.0024878345765206233,
527
+ "grad_norm": NaN,
528
+ "learning_rate": 1.5192246987791981e-06,
529
+ "loss": 0.0,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.0025228745001335895,
534
+ "grad_norm": NaN,
535
+ "learning_rate": 8.555138626189618e-07,
536
+ "loss": 0.0,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.002557914423746556,
541
+ "grad_norm": NaN,
542
+ "learning_rate": 3.805301908254455e-07,
543
+ "loss": 0.0,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 0.002592954347359523,
548
+ "grad_norm": NaN,
549
+ "learning_rate": 9.517784181422019e-08,
550
+ "loss": 0.0,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 0.0026279942709724895,
555
+ "grad_norm": NaN,
556
+ "learning_rate": 0.0,
557
+ "loss": 0.0,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 0.0026279942709724895,
562
+ "eval_loss": NaN,
563
+ "eval_runtime": 568.4882,
564
+ "eval_samples_per_second": 42.275,
565
+ "eval_steps_per_second": 21.139,
566
+ "step": 75
567
  }
568
  ],
569
  "logging_steps": 1,
 
578
  "should_evaluate": false,
579
  "should_log": false,
580
  "should_save": true,
581
+ "should_training_stop": true
582
  },
583
  "attributes": {}
584
  }
585
  },
586
+ "total_flos": 92484403200.0,
587
  "train_batch_size": 2,
588
  "trial_name": null,
589
  "trial_params": null