risolmayo commited on
Commit
8e36465
·
verified ·
1 Parent(s): f469268

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 sha256:1d4ba656bac2827003e74950ce255bbc9295264f54228257485c5cafc4f0175b
3
  size 1163996488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95ca017198e889f2b49ecba5031f599f8aff94d5e4b6700d1b0edda2f8d98ff9
3
  size 1163996488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf7bde612d66fc236dcdb99b93fb200d5b7edfaae1c5aca3e10603039c8f9dff
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c577071787452e79d94449ff76435a7595581913be4d251e46e3e31cb8522dd0
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15e38c0bdaf72c1866421620c572054dba719f461b3529d6524c0346809de5e7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd49f4b5c9171d7d413a6308a1432a43aa3be22f5e06b7d1382cc08f11a113b3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0149711e8b0d5ef3903d9d19787165d98c2601e242e137eebd29bf8de54b0133
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2481782945fd527fd68f03d6ecc086ae38c0c705bfbe5de3172ab751f2e6c8
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5850434303283691,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.018005041411595247,
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": 13.275,
374
  "eval_steps_per_second": 3.321,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.752270141305651e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4850772619247437,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.036010082823190494,
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": 13.275,
374
  "eval_steps_per_second": 3.321,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.018365142239827152,
379
+ "grad_norm": 0.5396647453308105,
380
+ "learning_rate": 7.11550911504845e-05,
381
+ "loss": 1.3308,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.018725243068059057,
386
+ "grad_norm": 0.5886169672012329,
387
+ "learning_rate": 7.073604443427437e-05,
388
+ "loss": 1.1507,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.019085343896290963,
393
+ "grad_norm": 0.6277225613594055,
394
+ "learning_rate": 7.03085947904134e-05,
395
+ "loss": 1.2221,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.019445444724522868,
400
+ "grad_norm": 0.552457869052887,
401
+ "learning_rate": 6.987285907936617e-05,
402
+ "loss": 1.0,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.01980554555275477,
407
+ "grad_norm": 0.47208383679389954,
408
+ "learning_rate": 6.942895642692527e-05,
409
+ "loss": 1.1913,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.020165646380986675,
414
+ "grad_norm": 0.40564197301864624,
415
+ "learning_rate": 6.897700819164357e-05,
416
+ "loss": 1.1485,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.02052574720921858,
421
+ "grad_norm": 0.34190523624420166,
422
+ "learning_rate": 6.851713793165589e-05,
423
+ "loss": 1.0862,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.020885848037450486,
428
+ "grad_norm": 0.31114333868026733,
429
+ "learning_rate": 6.804947137089955e-05,
430
+ "loss": 0.9792,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.02124594886568239,
435
+ "grad_norm": 0.2748708128929138,
436
+ "learning_rate": 6.757413636474263e-05,
437
+ "loss": 1.1398,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.021606049693914296,
442
+ "grad_norm": 0.28262221813201904,
443
+ "learning_rate": 6.709126286502965e-05,
444
+ "loss": 1.0137,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0219661505221462,
449
+ "grad_norm": 0.3110496401786804,
450
+ "learning_rate": 6.660098288455393e-05,
451
+ "loss": 1.1065,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.022326251350378107,
456
+ "grad_norm": 0.28911370038986206,
457
+ "learning_rate": 6.610343046096674e-05,
458
+ "loss": 1.0633,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.022686352178610012,
463
+ "grad_norm": 0.30962398648262024,
464
+ "learning_rate": 6.559874162013267e-05,
465
+ "loss": 1.2423,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.023046453006841917,
470
+ "grad_norm": 0.30083462595939636,
471
+ "learning_rate": 6.508705433894149e-05,
472
+ "loss": 1.1315,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.02340655383507382,
477
+ "grad_norm": 0.3204285800457001,
478
+ "learning_rate": 6.456850850758673e-05,
479
+ "loss": 1.1024,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.023766654663305724,
484
+ "grad_norm": 0.32156258821487427,
485
+ "learning_rate": 6.404324589132101e-05,
486
+ "loss": 1.1587,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.02412675549153763,
491
+ "grad_norm": 0.3117810785770416,
492
+ "learning_rate": 6.351141009169893e-05,
493
+ "loss": 1.0853,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.024486856319769535,
498
+ "grad_norm": 0.32040199637413025,
499
+ "learning_rate": 6.297314650731775e-05,
500
+ "loss": 1.1984,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.02484695714800144,
505
+ "grad_norm": 0.3659551441669464,
506
+ "learning_rate": 6.242860229406692e-05,
507
+ "loss": 1.117,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.025207057976233346,
512
+ "grad_norm": 0.3537808060646057,
513
+ "learning_rate": 6.18779263248971e-05,
514
+ "loss": 1.2022,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.02556715880446525,
519
+ "grad_norm": 0.33273327350616455,
520
+ "learning_rate": 6.132126914911976e-05,
521
+ "loss": 1.2369,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.025927259632697156,
526
+ "grad_norm": 0.3848983943462372,
527
+ "learning_rate": 6.075878295124861e-05,
528
+ "loss": 1.6059,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.02628736046092906,
533
+ "grad_norm": 0.3831624686717987,
534
+ "learning_rate": 6.019062150939376e-05,
535
+ "loss": 1.381,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.026647461289160967,
540
+ "grad_norm": 0.3995639979839325,
541
+ "learning_rate": 5.9616940153220336e-05,
542
+ "loss": 1.3304,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.02700756211739287,
547
+ "grad_norm": 0.439020037651062,
548
+ "learning_rate": 5.903789572148295e-05,
549
+ "loss": 1.4991,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.027367662945624774,
554
+ "grad_norm": 0.38694366812705994,
555
+ "learning_rate": 5.845364651914752e-05,
556
+ "loss": 1.3432,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.02772776377385668,
561
+ "grad_norm": 0.4259042739868164,
562
+ "learning_rate": 5.786435227411227e-05,
563
+ "loss": 1.4677,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.028087864602088584,
568
+ "grad_norm": 0.42080992460250854,
569
+ "learning_rate": 5.727017409353971e-05,
570
+ "loss": 1.5115,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.02844796543032049,
575
+ "grad_norm": 0.4072776734828949,
576
+ "learning_rate": 5.667127441981162e-05,
577
+ "loss": 1.4107,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.028808066258552395,
582
+ "grad_norm": 0.43466779589653015,
583
+ "learning_rate": 5.606781698611879e-05,
584
+ "loss": 1.5465,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.0291681670867843,
589
+ "grad_norm": 0.4168336093425751,
590
+ "learning_rate": 5.5459966771698096e-05,
591
+ "loss": 1.6694,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.029528267915016206,
596
+ "grad_norm": 0.5250816345214844,
597
+ "learning_rate": 5.4847889956728834e-05,
598
+ "loss": 1.796,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.02988836874324811,
603
+ "grad_norm": 0.5515179634094238,
604
+ "learning_rate": 5.423175387690067e-05,
605
+ "loss": 1.6945,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.030248469571480016,
610
+ "grad_norm": 0.5818299651145935,
611
+ "learning_rate": 5.361172697766573e-05,
612
+ "loss": 1.634,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.030608570399711918,
617
+ "grad_norm": 0.5926039814949036,
618
+ "learning_rate": 5.298797876818735e-05,
619
+ "loss": 1.7657,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.030968671227943823,
624
+ "grad_norm": 0.6447036862373352,
625
+ "learning_rate": 5.23606797749979e-05,
626
+ "loss": 1.8414,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.03132877205617573,
631
+ "grad_norm": 0.574548602104187,
632
+ "learning_rate": 5.17300014953786e-05,
633
+ "loss": 1.8444,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.03168887288440764,
638
+ "grad_norm": 0.645301103591919,
639
+ "learning_rate": 5.109611635047379e-05,
640
+ "loss": 1.7747,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.03204897371263954,
645
+ "grad_norm": 0.6297435760498047,
646
+ "learning_rate": 5.04591976381528e-05,
647
+ "loss": 1.9292,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.03240907454087144,
652
+ "grad_norm": 0.6943683624267578,
653
+ "learning_rate": 4.981941948563197e-05,
654
+ "loss": 1.8509,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03276917536910335,
659
+ "grad_norm": 0.7677454352378845,
660
+ "learning_rate": 4.9176956801870065e-05,
661
+ "loss": 1.7289,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.03312927619733525,
666
+ "grad_norm": 0.846775233745575,
667
+ "learning_rate": 4.853198522974988e-05,
668
+ "loss": 1.8011,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03348937702556716,
673
+ "grad_norm": 0.9709502458572388,
674
+ "learning_rate": 4.788468109805921e-05,
675
+ "loss": 2.0327,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.03384947785379906,
680
+ "grad_norm": 0.9475632309913635,
681
+ "learning_rate": 4.7235221373284407e-05,
682
+ "loss": 1.8737,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03420957868203097,
687
+ "grad_norm": 0.979775607585907,
688
+ "learning_rate": 4.658378361122936e-05,
689
+ "loss": 1.7808,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03456967951026287,
694
+ "grad_norm": 1.1734482049942017,
695
+ "learning_rate": 4.593054590847368e-05,
696
+ "loss": 1.9409,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03492978033849478,
701
+ "grad_norm": 1.2772958278656006,
702
+ "learning_rate": 4.5275686853682765e-05,
703
+ "loss": 1.9487,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.03528988116672668,
708
+ "grad_norm": 1.4188159704208374,
709
+ "learning_rate": 4.4619385478783456e-05,
710
+ "loss": 1.9205,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.035649981994958585,
715
+ "grad_norm": 1.8587150573730469,
716
+ "learning_rate": 4.396182121001852e-05,
717
+ "loss": 2.1834,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.036010082823190494,
722
+ "grad_norm": 3.5931663513183594,
723
+ "learning_rate": 4.33031738188933e-05,
724
+ "loss": 2.2956,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.036010082823190494,
729
+ "eval_loss": 1.4850772619247437,
730
+ "eval_runtime": 353.549,
731
+ "eval_samples_per_second": 13.229,
732
+ "eval_steps_per_second": 3.309,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.3537802697100493e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null