bbytxt commited on
Commit
361400c
·
verified ·
1 Parent(s): 8f6f3fd

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:c3c9cf9dbae368dfac3f58bf49d46ee0a1897ca22ece5cbabecfca068574df51
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646dc19f5a91dc1181967a11b5fefecfeeafeea9ff0667965d405a8b1e04d579
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2114add492187404967090b17d6f2f14b300d9aecf759a2211243c9866a8e948
3
  size 156656510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aedd48ff7fb5a12139a7d393843d3fc15df18076939e2848e9bdb0566008a2aa
3
  size 156656510
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6206d3d335f185a034477457dcd3c2a25d5c1257ebacf8e80074f038d706a39
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f40ed1f3a666b9ace6f149bce4e7f73c350693f365e4fdf7209bc8407c788c9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79f5b4ba066d00b62be68b9f9ec9376def1ffea9a45f98d620f3198033186a6a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 4.380072593688965,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.03984857541342897,
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": 42.888,
374
  "eval_steps_per_second": 21.444,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1236088022630400.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.2464494705200195,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.07969715082685794,
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": 42.888,
374
  "eval_steps_per_second": 21.444,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.04064554692169755,
379
+ "grad_norm": 0.624276340007782,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 4.6153,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.04144251842996613,
386
+ "grad_norm": 0.5702478289604187,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 4.5537,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.04223948993823471,
393
+ "grad_norm": 0.5568172931671143,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 4.3303,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.04303646144650329,
400
+ "grad_norm": 0.5124043226242065,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 4.4411,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.043833432954771864,
407
+ "grad_norm": 0.4467545747756958,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 4.3182,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.044630404463040445,
414
+ "grad_norm": 0.3773902654647827,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 4.3299,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.045427375971309025,
421
+ "grad_norm": 0.32421058416366577,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 4.5109,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.046224347479577606,
428
+ "grad_norm": 0.297109454870224,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 4.4707,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.047021318987846186,
435
+ "grad_norm": 0.2981337308883667,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 4.1532,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.04781829049611477,
442
+ "grad_norm": 0.3211049437522888,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 4.3803,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.04861526200438334,
449
+ "grad_norm": 0.2942092716693878,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 4.1606,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.04941223351265192,
456
+ "grad_norm": 0.2600642144680023,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 4.3328,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0502092050209205,
463
+ "grad_norm": 0.2833946943283081,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 4.3028,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.05100617652918908,
470
+ "grad_norm": 0.2821059226989746,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 4.2651,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.05180314803745766,
477
+ "grad_norm": 0.24731014668941498,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 4.4582,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.05260011954572624,
484
+ "grad_norm": 0.28231242299079895,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 4.3979,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.053397091053994816,
491
+ "grad_norm": 0.286496102809906,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 4.2518,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0541940625622634,
498
+ "grad_norm": 0.28141117095947266,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 4.3857,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.05499103407053198,
505
+ "grad_norm": 0.3005343973636627,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 4.2947,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.05578800557880056,
512
+ "grad_norm": 0.2838599383831024,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 4.3911,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.05658497708706914,
519
+ "grad_norm": 0.2848851978778839,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 4.1967,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.05738194859533772,
526
+ "grad_norm": 0.26664552092552185,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 4.1475,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0581789201036063,
533
+ "grad_norm": 0.24472041428089142,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 4.0612,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.05897589161187487,
540
+ "grad_norm": 0.2784044146537781,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 4.3801,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.05977286312014345,
547
+ "grad_norm": 0.25716060400009155,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 4.2731,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.060569834628412034,
554
+ "grad_norm": 0.2857103943824768,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 4.2079,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.061366806136680614,
561
+ "grad_norm": 0.27076512575149536,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 4.3116,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.062163777644949195,
568
+ "grad_norm": 0.28855860233306885,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 4.3531,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.06296074915321777,
575
+ "grad_norm": 0.25299739837646484,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 4.2343,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.06375772066148636,
582
+ "grad_norm": 0.2638589143753052,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 4.1138,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.06455469216975493,
589
+ "grad_norm": 0.26530274748802185,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 4.2572,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.06535166367802352,
596
+ "grad_norm": 0.26153290271759033,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 4.1664,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.06614863518629209,
603
+ "grad_norm": 0.2668301463127136,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 4.1899,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.06694560669456066,
610
+ "grad_norm": 0.2707118093967438,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 4.0062,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.06774257820282925,
617
+ "grad_norm": 0.26167628169059753,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 4.1416,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.06853954971109782,
624
+ "grad_norm": 0.28571200370788574,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 4.1765,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.06933652121936641,
631
+ "grad_norm": 0.2865961492061615,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 4.0639,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.07013349272763499,
638
+ "grad_norm": 0.3028181493282318,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 4.2758,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.07093046423590357,
645
+ "grad_norm": 0.2957330346107483,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 4.0516,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.07172743574417215,
652
+ "grad_norm": 0.2807944118976593,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 3.9975,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.07252440725244072,
659
+ "grad_norm": 0.28562647104263306,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 3.9309,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.07332137876070931,
666
+ "grad_norm": 0.3081153333187103,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 4.1601,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.07411835026897788,
673
+ "grad_norm": 0.2935575842857361,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 4.1423,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.07491532177724647,
680
+ "grad_norm": 0.31277942657470703,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 4.2067,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.07571229328551504,
687
+ "grad_norm": 0.36462724208831787,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 4.132,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.07650926479378362,
694
+ "grad_norm": 0.3712453842163086,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 4.1583,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0773062363020522,
701
+ "grad_norm": 0.4156951606273651,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 4.1631,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.07810320781032078,
708
+ "grad_norm": 0.542849600315094,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 4.3338,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.07890017931858936,
715
+ "grad_norm": 0.6674630045890808,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 3.8856,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.07969715082685794,
722
+ "grad_norm": 1.0902327299118042,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 4.1106,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.07969715082685794,
729
+ "eval_loss": 4.2464494705200195,
730
+ "eval_runtime": 49.1082,
731
+ "eval_samples_per_second": 43.048,
732
+ "eval_steps_per_second": 21.524,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2472176045260800.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null