lesso commited on
Commit
cdba7db
·
verified ·
1 Parent(s): ae1b6ac

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:d9d2c681506b1989d661aa6a2cd8aa54152e503e9d71f3faa54dbdee9edd5890
3
  size 800116456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e4e6f1eb0abaa0d8d2cab98b34bcc459b3e576688459d60fec600ed9cc5f41
3
  size 800116456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb5c64ba55e0eb10f1d79445c7eb7469dfd68c56334b31e35a88c5ed02ec93c2
3
  size 406743412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30f29727e23641c9ab5b64772f1b01ab5c0f66212c68c72a8bfcb2f331932ab
3
  size 406743412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4adc05e824990bdc2a4825b6e0764a51a9e63e40ed65b3679fb938ec170b34eb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcbf7d5e4aa7b38b8ebe707846794c5b3732e8a4cdd09857174a2fb83ed221a8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2f1cc7ac96b43e89afbf900f41769c2bbe93e9d76b453a576e60002b6ad5d48
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429ac0058d053852a57e244c528ad2a9ef374afdf80fd23f716aee5119cd57d1
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1290020942687988,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0017515895675325357,
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": 5.83,
374
  "eval_steps_per_second": 1.458,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.618497791374131e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.029884696006775,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0035031791350650715,
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": 5.83,
374
  "eval_steps_per_second": 1.458,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0017866213588831866,
379
+ "grad_norm": 5.159853458404541,
380
+ "learning_rate": 7.904842105263158e-05,
381
+ "loss": 1.027,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0018216531502338372,
386
+ "grad_norm": 5.4184088706970215,
387
+ "learning_rate": 7.85178947368421e-05,
388
+ "loss": 1.286,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0018566849415844878,
393
+ "grad_norm": 6.966073989868164,
394
+ "learning_rate": 7.798736842105263e-05,
395
+ "loss": 1.4248,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0018917167329351387,
400
+ "grad_norm": 6.474468231201172,
401
+ "learning_rate": 7.745684210526315e-05,
402
+ "loss": 1.5506,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0019267485242857893,
407
+ "grad_norm": 6.7876811027526855,
408
+ "learning_rate": 7.692631578947369e-05,
409
+ "loss": 1.6668,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.00196178031563644,
414
+ "grad_norm": 6.088242530822754,
415
+ "learning_rate": 7.639578947368421e-05,
416
+ "loss": 1.4712,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0019968121069870908,
421
+ "grad_norm": 4.957919597625732,
422
+ "learning_rate": 7.586526315789473e-05,
423
+ "loss": 1.2942,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0020318438983377416,
428
+ "grad_norm": 5.453049659729004,
429
+ "learning_rate": 7.533473684210526e-05,
430
+ "loss": 1.1897,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.002066875689688392,
435
+ "grad_norm": 8.739358901977539,
436
+ "learning_rate": 7.480421052631578e-05,
437
+ "loss": 1.2799,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.002101907481039043,
442
+ "grad_norm": 8.237629890441895,
443
+ "learning_rate": 7.427368421052632e-05,
444
+ "loss": 1.5075,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0021369392723896937,
449
+ "grad_norm": 6.064999580383301,
450
+ "learning_rate": 7.374315789473685e-05,
451
+ "loss": 1.4072,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0021719710637403446,
456
+ "grad_norm": 7.591026306152344,
457
+ "learning_rate": 7.321263157894737e-05,
458
+ "loss": 1.4841,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.002207002855090995,
463
+ "grad_norm": 6.479332447052002,
464
+ "learning_rate": 7.26821052631579e-05,
465
+ "loss": 1.3464,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.002242034646441646,
470
+ "grad_norm": 7.660516738891602,
471
+ "learning_rate": 7.215157894736842e-05,
472
+ "loss": 1.3947,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0022770664377922967,
477
+ "grad_norm": 6.516019821166992,
478
+ "learning_rate": 7.162105263157894e-05,
479
+ "loss": 0.9144,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.002312098229142947,
484
+ "grad_norm": 8.34161376953125,
485
+ "learning_rate": 7.109052631578947e-05,
486
+ "loss": 1.6912,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.002347130020493598,
491
+ "grad_norm": 10.69320297241211,
492
+ "learning_rate": 7.055999999999999e-05,
493
+ "loss": 1.9,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0023821618118442488,
498
+ "grad_norm": 10.620810508728027,
499
+ "learning_rate": 7.002947368421052e-05,
500
+ "loss": 1.0454,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.002417193603194899,
505
+ "grad_norm": 7.011707305908203,
506
+ "learning_rate": 6.949894736842105e-05,
507
+ "loss": 0.8123,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.00245222539454555,
512
+ "grad_norm": 7.232404708862305,
513
+ "learning_rate": 6.896842105263158e-05,
514
+ "loss": 1.4846,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.002487257185896201,
519
+ "grad_norm": 7.875359535217285,
520
+ "learning_rate": 6.843789473684211e-05,
521
+ "loss": 1.2222,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.0025222889772468517,
526
+ "grad_norm": 6.384848594665527,
527
+ "learning_rate": 6.790736842105263e-05,
528
+ "loss": 1.0321,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.002557320768597502,
533
+ "grad_norm": 6.461179733276367,
534
+ "learning_rate": 6.737684210526315e-05,
535
+ "loss": 0.9518,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.002592352559948153,
540
+ "grad_norm": 7.334846019744873,
541
+ "learning_rate": 6.684631578947368e-05,
542
+ "loss": 1.2871,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.002627384351298804,
547
+ "grad_norm": 5.616960048675537,
548
+ "learning_rate": 6.631578947368421e-05,
549
+ "loss": 0.9077,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0026624161426494542,
554
+ "grad_norm": 4.717360496520996,
555
+ "learning_rate": 6.578526315789473e-05,
556
+ "loss": 0.6344,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.002697447934000105,
561
+ "grad_norm": 4.63266658782959,
562
+ "learning_rate": 6.525473684210526e-05,
563
+ "loss": 0.7442,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.002732479725350756,
568
+ "grad_norm": 6.365645408630371,
569
+ "learning_rate": 6.47242105263158e-05,
570
+ "loss": 0.9088,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0027675115167014063,
575
+ "grad_norm": 5.476707935333252,
576
+ "learning_rate": 6.419368421052632e-05,
577
+ "loss": 0.7585,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.002802543308052057,
582
+ "grad_norm": 6.600567817687988,
583
+ "learning_rate": 6.366315789473684e-05,
584
+ "loss": 1.1681,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.002837575099402708,
589
+ "grad_norm": 4.197580337524414,
590
+ "learning_rate": 6.313263157894736e-05,
591
+ "loss": 0.5965,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.002872606890753359,
596
+ "grad_norm": 5.1230788230896,
597
+ "learning_rate": 6.26021052631579e-05,
598
+ "loss": 0.978,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0029076386821040093,
603
+ "grad_norm": 5.09016752243042,
604
+ "learning_rate": 6.207157894736842e-05,
605
+ "loss": 0.663,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.00294267047345466,
610
+ "grad_norm": 6.350630283355713,
611
+ "learning_rate": 6.154105263157894e-05,
612
+ "loss": 0.9641,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.002977702264805311,
617
+ "grad_norm": 6.287975788116455,
618
+ "learning_rate": 6.1010526315789474e-05,
619
+ "loss": 1.2104,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0030127340561559614,
624
+ "grad_norm": 5.212226867675781,
625
+ "learning_rate": 6.048e-05,
626
+ "loss": 0.9887,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.0030477658475066122,
631
+ "grad_norm": 6.213005542755127,
632
+ "learning_rate": 5.994947368421052e-05,
633
+ "loss": 0.6417,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.003082797638857263,
638
+ "grad_norm": 6.072321891784668,
639
+ "learning_rate": 5.941894736842104e-05,
640
+ "loss": 0.8963,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0031178294302079135,
645
+ "grad_norm": 4.825734615325928,
646
+ "learning_rate": 5.888842105263158e-05,
647
+ "loss": 0.742,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0031528612215585643,
652
+ "grad_norm": 5.300004959106445,
653
+ "learning_rate": 5.835789473684211e-05,
654
+ "loss": 0.7844,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.003187893012909215,
659
+ "grad_norm": 8.157235145568848,
660
+ "learning_rate": 5.782736842105263e-05,
661
+ "loss": 1.2107,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.003222924804259866,
666
+ "grad_norm": 4.026047706604004,
667
+ "learning_rate": 5.7296842105263154e-05,
668
+ "loss": 0.503,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0032579565956105164,
673
+ "grad_norm": 5.493070125579834,
674
+ "learning_rate": 5.676631578947368e-05,
675
+ "loss": 0.8302,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0032929883869611673,
680
+ "grad_norm": 5.728854179382324,
681
+ "learning_rate": 5.623578947368421e-05,
682
+ "loss": 0.7791,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.003328020178311818,
687
+ "grad_norm": 5.390102863311768,
688
+ "learning_rate": 5.570526315789474e-05,
689
+ "loss": 0.9903,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.0033630519696624685,
694
+ "grad_norm": 6.115237712860107,
695
+ "learning_rate": 5.5174736842105266e-05,
696
+ "loss": 0.7596,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0033980837610131194,
701
+ "grad_norm": 5.043397426605225,
702
+ "learning_rate": 5.464421052631579e-05,
703
+ "loss": 0.7616,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.00343311555236377,
708
+ "grad_norm": 5.883362293243408,
709
+ "learning_rate": 5.411368421052631e-05,
710
+ "loss": 0.8057,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0034681473437144206,
715
+ "grad_norm": 6.632864952087402,
716
+ "learning_rate": 5.358315789473684e-05,
717
+ "loss": 1.0609,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0035031791350650715,
722
+ "grad_norm": 4.529953956604004,
723
+ "learning_rate": 5.3052631578947364e-05,
724
+ "loss": 0.6286,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0035031791350650715,
729
+ "eval_loss": 1.029884696006775,
730
+ "eval_runtime": 2061.1807,
731
+ "eval_samples_per_second": 5.831,
732
+ "eval_steps_per_second": 1.458,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 5.236995582748262e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null