dimasik2987 commited on
Commit
19a9554
·
verified ·
1 Parent(s): f45a932

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e06d0b6d6b43f7d7d50bb5ed71e7530f77397d9d3116a5466142ca1ee0f72ae2
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe32acb668ac047978e3e9f583127cab3bd29b7ac1fa5a4a19b61bf03f0c22e8
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8031430f208482e6de475522a782b4af437af1622f05385549d5c1ee66c79642
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5527a672e02bb7d7279600fe882382948581c0ada899c70b5156a3226e670bcb
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3369e41701d4cea8506012751e67c146aa4ed3530ccf4d9333987fbb0b01b389
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d24e8d03ae53d735f8c639517b54ff927b6527c170a6b1ecd91efe86f65c7547
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6626a958c42744f62f15b40b71145564a751f3973a73662e664e23d40b38c82
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16c2a0a7f4d1c317518a0a40a7c58dbcf9237e9297de7a3c67a0a8ebfbe5ded
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2532055377960205,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.003795642602292568,
5
  "eval_steps": 50,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -373,6 +373,364 @@
373
  "eval_samples_per_second": 22.912,
374
  "eval_steps_per_second": 5.729,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3401809133568000.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0612136125564575,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.007591285204585136,
5
  "eval_steps": 50,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
373
  "eval_samples_per_second": 22.912,
374
  "eval_steps_per_second": 5.729,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0038715554543384194,
379
+ "grad_norm": 3.332703113555908,
380
+ "learning_rate": 7.873473684210526e-05,
381
+ "loss": 1.4012,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.003947468306384271,
386
+ "grad_norm": 3.9371657371520996,
387
+ "learning_rate": 7.820631578947369e-05,
388
+ "loss": 2.001,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.004023381158430122,
393
+ "grad_norm": 2.853745460510254,
394
+ "learning_rate": 7.76778947368421e-05,
395
+ "loss": 1.3783,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.004099294010475973,
400
+ "grad_norm": 3.1998298168182373,
401
+ "learning_rate": 7.714947368421052e-05,
402
+ "loss": 1.8504,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.004175206862521825,
407
+ "grad_norm": 3.126289129257202,
408
+ "learning_rate": 7.662105263157896e-05,
409
+ "loss": 1.862,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.004251119714567676,
414
+ "grad_norm": 2.4768309593200684,
415
+ "learning_rate": 7.609263157894737e-05,
416
+ "loss": 1.3451,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0043270325666135276,
421
+ "grad_norm": 2.919741630554199,
422
+ "learning_rate": 7.556421052631579e-05,
423
+ "loss": 1.4162,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.004402945418659379,
428
+ "grad_norm": 2.9070191383361816,
429
+ "learning_rate": 7.503578947368421e-05,
430
+ "loss": 1.3421,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.00447885827070523,
435
+ "grad_norm": 3.0319571495056152,
436
+ "learning_rate": 7.450736842105263e-05,
437
+ "loss": 1.7147,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.004554771122751082,
442
+ "grad_norm": 3.456721544265747,
443
+ "learning_rate": 7.397894736842105e-05,
444
+ "loss": 1.2985,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.004630683974796933,
449
+ "grad_norm": 3.245173215866089,
450
+ "learning_rate": 7.345052631578948e-05,
451
+ "loss": 1.7002,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.004706596826842785,
456
+ "grad_norm": 2.7266035079956055,
457
+ "learning_rate": 7.29221052631579e-05,
458
+ "loss": 1.527,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.004782509678888636,
463
+ "grad_norm": 3.55993914604187,
464
+ "learning_rate": 7.239368421052631e-05,
465
+ "loss": 1.9147,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.004858422530934488,
470
+ "grad_norm": 2.028764009475708,
471
+ "learning_rate": 7.186526315789474e-05,
472
+ "loss": 1.0744,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.004934335382980338,
477
+ "grad_norm": 3.0651049613952637,
478
+ "learning_rate": 7.133684210526316e-05,
479
+ "loss": 1.1072,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.00501024823502619,
484
+ "grad_norm": 2.8773818016052246,
485
+ "learning_rate": 7.080842105263158e-05,
486
+ "loss": 1.3428,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.005086161087072041,
491
+ "grad_norm": 2.439342737197876,
492
+ "learning_rate": 7.028e-05,
493
+ "loss": 0.9611,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0051620739391178925,
498
+ "grad_norm": 3.0564000606536865,
499
+ "learning_rate": 6.975157894736843e-05,
500
+ "loss": 1.1857,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.005237986791163744,
505
+ "grad_norm": 5.345979690551758,
506
+ "learning_rate": 6.922315789473685e-05,
507
+ "loss": 1.4022,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.005313899643209595,
512
+ "grad_norm": 2.436023712158203,
513
+ "learning_rate": 6.869473684210527e-05,
514
+ "loss": 0.9688,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.005389812495255447,
519
+ "grad_norm": 3.2191972732543945,
520
+ "learning_rate": 6.816631578947368e-05,
521
+ "loss": 1.2126,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.005465725347301298,
526
+ "grad_norm": 1.942346215248108,
527
+ "learning_rate": 6.76378947368421e-05,
528
+ "loss": 0.8721,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.00554163819934715,
533
+ "grad_norm": 4.746232509613037,
534
+ "learning_rate": 6.710947368421052e-05,
535
+ "loss": 1.392,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.005617551051393001,
540
+ "grad_norm": 2.850257158279419,
541
+ "learning_rate": 6.658105263157894e-05,
542
+ "loss": 1.1243,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0056934639034388525,
547
+ "grad_norm": 2.983518362045288,
548
+ "learning_rate": 6.605263157894737e-05,
549
+ "loss": 1.1275,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.005769376755484704,
554
+ "grad_norm": 2.9279556274414062,
555
+ "learning_rate": 6.55242105263158e-05,
556
+ "loss": 1.5262,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0058452896075305546,
561
+ "grad_norm": 6.875275135040283,
562
+ "learning_rate": 6.499578947368422e-05,
563
+ "loss": 0.8056,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.005921202459576406,
568
+ "grad_norm": 2.7808749675750732,
569
+ "learning_rate": 6.446736842105264e-05,
570
+ "loss": 1.097,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.005997115311622257,
575
+ "grad_norm": 6.791175842285156,
576
+ "learning_rate": 6.393894736842105e-05,
577
+ "loss": 0.7137,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.006073028163668109,
582
+ "grad_norm": 3.0166051387786865,
583
+ "learning_rate": 6.341052631578947e-05,
584
+ "loss": 1.3371,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.00614894101571396,
589
+ "grad_norm": 5.060026168823242,
590
+ "learning_rate": 6.288210526315789e-05,
591
+ "loss": 0.8866,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.006224853867759812,
596
+ "grad_norm": 4.755941390991211,
597
+ "learning_rate": 6.235368421052632e-05,
598
+ "loss": 1.1797,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.006300766719805663,
603
+ "grad_norm": 2.5491960048675537,
604
+ "learning_rate": 6.182526315789474e-05,
605
+ "loss": 0.7077,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.006376679571851515,
610
+ "grad_norm": 2.4443137645721436,
611
+ "learning_rate": 6.129684210526316e-05,
612
+ "loss": 0.8194,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.006452592423897366,
617
+ "grad_norm": 2.4709208011627197,
618
+ "learning_rate": 6.076842105263158e-05,
619
+ "loss": 0.8501,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0065285052759432175,
624
+ "grad_norm": 2.1877200603485107,
625
+ "learning_rate": 6.024e-05,
626
+ "loss": 0.768,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.006604418127989069,
631
+ "grad_norm": 3.9589478969573975,
632
+ "learning_rate": 5.971157894736842e-05,
633
+ "loss": 0.8284,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.0066803309800349195,
638
+ "grad_norm": 2.8392932415008545,
639
+ "learning_rate": 5.9183157894736835e-05,
640
+ "loss": 0.7405,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.006756243832080771,
645
+ "grad_norm": 4.0319318771362305,
646
+ "learning_rate": 5.8654736842105267e-05,
647
+ "loss": 0.9588,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.006832156684126622,
652
+ "grad_norm": 4.04771614074707,
653
+ "learning_rate": 5.8126315789473684e-05,
654
+ "loss": 1.0062,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.006908069536172474,
659
+ "grad_norm": 2.8250598907470703,
660
+ "learning_rate": 5.759789473684211e-05,
661
+ "loss": 0.7596,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.006983982388218325,
666
+ "grad_norm": 2.2574899196624756,
667
+ "learning_rate": 5.706947368421053e-05,
668
+ "loss": 0.6135,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.007059895240264177,
673
+ "grad_norm": 2.3029751777648926,
674
+ "learning_rate": 5.6541052631578945e-05,
675
+ "loss": 0.9518,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.007135808092310028,
680
+ "grad_norm": 5.060135364532471,
681
+ "learning_rate": 5.601263157894736e-05,
682
+ "loss": 1.0503,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0072117209443558795,
687
+ "grad_norm": 2.9369940757751465,
688
+ "learning_rate": 5.5484210526315794e-05,
689
+ "loss": 0.7239,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.007287633796401731,
694
+ "grad_norm": 1.8883877992630005,
695
+ "learning_rate": 5.495578947368421e-05,
696
+ "loss": 0.6678,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.007363546648447582,
701
+ "grad_norm": 2.149679660797119,
702
+ "learning_rate": 5.442736842105264e-05,
703
+ "loss": 0.7075,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.007439459500493434,
708
+ "grad_norm": 3.17543888092041,
709
+ "learning_rate": 5.3898947368421055e-05,
710
+ "loss": 0.8025,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.007515372352539285,
715
+ "grad_norm": 4.000500679016113,
716
+ "learning_rate": 5.337052631578947e-05,
717
+ "loss": 0.742,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.007591285204585136,
722
+ "grad_norm": 2.3594398498535156,
723
+ "learning_rate": 5.284210526315789e-05,
724
+ "loss": 0.6751,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.007591285204585136,
729
+ "eval_loss": 1.0612136125564575,
730
+ "eval_runtime": 241.2405,
731
+ "eval_samples_per_second": 22.994,
732
+ "eval_steps_per_second": 5.749,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6803618267136000.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null