lesso commited on
Commit
3371221
·
verified ·
1 Parent(s): 9eb0dea

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:d16f2cb5485eb9d035c008c29e342283bd1326c9ae402cc3f15298094637023b
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4422e2517de197d437dd35026b454bcf539ca2849dbd1f92d6f49dc5ea3e554
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8f5f554a26e90b4c8f8dbb198528873bcd4086999bf25c221275151cffebdcf
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:482d4d18e216e777f40237eb2a2469d5ad1decc5a7d37be6488018d586a2782e
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d22f141261206d19e6aae84d225cb2bcd6c465d1ed4da6d260b25ebf6fc06a1f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d607bc7c580e23a708525d795c51d57a9c28aca39594a62357269fd2b28fb604
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a210782c84f08cec5c1f73ff4599823e8ad776e9390c849271024afb8e72ba55
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b73d3ab03a9f3cb0edf1405ad22e2439bfc633b9abdf025e1224c6f0ad183c3
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.24128209054470062,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.07256894049346879,
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": 1.989,
374
  "eval_steps_per_second": 0.499,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.021510397427712e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2286633849143982,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.14513788098693758,
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": 1.989,
374
  "eval_steps_per_second": 0.499,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07402031930333818,
379
+ "grad_norm": 0.15042653679847717,
380
+ "learning_rate": 7.928368421052632e-05,
381
+ "loss": 0.5749,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07547169811320754,
386
+ "grad_norm": 0.14070290327072144,
387
+ "learning_rate": 7.875157894736842e-05,
388
+ "loss": 0.3815,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.07692307692307693,
393
+ "grad_norm": 0.12616680562496185,
394
+ "learning_rate": 7.821947368421053e-05,
395
+ "loss": 0.3485,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0783744557329463,
400
+ "grad_norm": 0.1807371824979782,
401
+ "learning_rate": 7.768736842105263e-05,
402
+ "loss": 0.6332,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.07982583454281568,
407
+ "grad_norm": 0.1610403060913086,
408
+ "learning_rate": 7.715526315789474e-05,
409
+ "loss": 0.4334,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.08127721335268505,
414
+ "grad_norm": 0.16740575432777405,
415
+ "learning_rate": 7.662315789473685e-05,
416
+ "loss": 0.5169,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.08272859216255443,
421
+ "grad_norm": 0.13583853840827942,
422
+ "learning_rate": 7.609105263157895e-05,
423
+ "loss": 0.3515,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0841799709724238,
428
+ "grad_norm": 0.20852766931056976,
429
+ "learning_rate": 7.555894736842105e-05,
430
+ "loss": 0.8417,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08563134978229318,
435
+ "grad_norm": 0.12840092182159424,
436
+ "learning_rate": 7.502684210526316e-05,
437
+ "loss": 0.3527,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.08708272859216255,
442
+ "grad_norm": 0.20794260501861572,
443
+ "learning_rate": 7.449473684210526e-05,
444
+ "loss": 0.8209,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.08853410740203194,
449
+ "grad_norm": 0.15332041680812836,
450
+ "learning_rate": 7.396263157894738e-05,
451
+ "loss": 0.5123,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0899854862119013,
456
+ "grad_norm": 0.12152067571878433,
457
+ "learning_rate": 7.343052631578949e-05,
458
+ "loss": 0.5442,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.09143686502177069,
463
+ "grad_norm": 0.15734325349330902,
464
+ "learning_rate": 7.289842105263158e-05,
465
+ "loss": 0.4926,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.09288824383164006,
470
+ "grad_norm": 0.10759459435939789,
471
+ "learning_rate": 7.236631578947369e-05,
472
+ "loss": 0.2285,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.09433962264150944,
477
+ "grad_norm": 0.11365488916635513,
478
+ "learning_rate": 7.183421052631579e-05,
479
+ "loss": 0.3032,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.09579100145137881,
484
+ "grad_norm": 0.13057614862918854,
485
+ "learning_rate": 7.13021052631579e-05,
486
+ "loss": 0.4789,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.09724238026124818,
491
+ "grad_norm": 0.1509314924478531,
492
+ "learning_rate": 7.077e-05,
493
+ "loss": 0.5571,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.09869375907111756,
498
+ "grad_norm": 0.16016532480716705,
499
+ "learning_rate": 7.023789473684211e-05,
500
+ "loss": 0.2708,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.10014513788098693,
505
+ "grad_norm": 0.2185145616531372,
506
+ "learning_rate": 6.970578947368422e-05,
507
+ "loss": 0.4046,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.10159651669085631,
512
+ "grad_norm": 0.14823275804519653,
513
+ "learning_rate": 6.917368421052633e-05,
514
+ "loss": 0.5717,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.10304789550072568,
519
+ "grad_norm": 0.16261740028858185,
520
+ "learning_rate": 6.864157894736842e-05,
521
+ "loss": 0.3313,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.10449927431059507,
526
+ "grad_norm": 0.1639692485332489,
527
+ "learning_rate": 6.810947368421053e-05,
528
+ "loss": 0.7474,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.10595065312046444,
533
+ "grad_norm": 0.11137572675943375,
534
+ "learning_rate": 6.757736842105264e-05,
535
+ "loss": 0.3237,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.10740203193033382,
540
+ "grad_norm": 0.09403427690267563,
541
+ "learning_rate": 6.704526315789473e-05,
542
+ "loss": 0.213,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.10885341074020319,
547
+ "grad_norm": 0.1198626309633255,
548
+ "learning_rate": 6.651315789473685e-05,
549
+ "loss": 0.3147,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.11030478955007257,
554
+ "grad_norm": 0.18822187185287476,
555
+ "learning_rate": 6.598105263157895e-05,
556
+ "loss": 0.2479,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.11175616835994194,
561
+ "grad_norm": 0.08338137716054916,
562
+ "learning_rate": 6.544894736842106e-05,
563
+ "loss": 0.1284,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.11320754716981132,
568
+ "grad_norm": 0.11395663768053055,
569
+ "learning_rate": 6.491684210526317e-05,
570
+ "loss": 0.304,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.11465892597968069,
575
+ "grad_norm": 0.12172822654247284,
576
+ "learning_rate": 6.438473684210526e-05,
577
+ "loss": 0.5225,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.11611030478955008,
582
+ "grad_norm": 0.18436570465564728,
583
+ "learning_rate": 6.385263157894737e-05,
584
+ "loss": 1.1369,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.11756168359941944,
589
+ "grad_norm": 0.08676780015230179,
590
+ "learning_rate": 6.332052631578948e-05,
591
+ "loss": 0.2241,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.11901306240928883,
596
+ "grad_norm": 0.14665937423706055,
597
+ "learning_rate": 6.278842105263159e-05,
598
+ "loss": 0.4818,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.1204644412191582,
603
+ "grad_norm": 0.12407947331666946,
604
+ "learning_rate": 6.22563157894737e-05,
605
+ "loss": 0.4061,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.12191582002902758,
610
+ "grad_norm": 0.12156087160110474,
611
+ "learning_rate": 6.172421052631579e-05,
612
+ "loss": 0.4842,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.12336719883889695,
617
+ "grad_norm": 0.164754256606102,
618
+ "learning_rate": 6.11921052631579e-05,
619
+ "loss": 0.6039,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.12481857764876633,
624
+ "grad_norm": 0.13035471737384796,
625
+ "learning_rate": 6.066e-05,
626
+ "loss": 0.5963,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.1262699564586357,
631
+ "grad_norm": 0.08667127043008804,
632
+ "learning_rate": 6.012789473684211e-05,
633
+ "loss": 0.104,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.12772133526850507,
638
+ "grad_norm": 0.12500996887683868,
639
+ "learning_rate": 5.959578947368421e-05,
640
+ "loss": 0.1519,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.12917271407837447,
645
+ "grad_norm": 0.1052846610546112,
646
+ "learning_rate": 5.9063684210526324e-05,
647
+ "loss": 0.168,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.13062409288824384,
652
+ "grad_norm": 0.16326619684696198,
653
+ "learning_rate": 5.8531578947368425e-05,
654
+ "loss": 1.0778,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.1320754716981132,
659
+ "grad_norm": 0.18031665682792664,
660
+ "learning_rate": 5.7999473684210527e-05,
661
+ "loss": 0.8578,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.13352685050798258,
666
+ "grad_norm": 0.14327001571655273,
667
+ "learning_rate": 5.7467368421052635e-05,
668
+ "loss": 0.8367,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.13497822931785197,
673
+ "grad_norm": 0.12158166617155075,
674
+ "learning_rate": 5.6935263157894736e-05,
675
+ "loss": 0.2978,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.13642960812772134,
680
+ "grad_norm": 0.17898587882518768,
681
+ "learning_rate": 5.640315789473684e-05,
682
+ "loss": 0.7248,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.1378809869375907,
687
+ "grad_norm": 0.1620013415813446,
688
+ "learning_rate": 5.587105263157895e-05,
689
+ "loss": 0.5909,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.13933236574746008,
694
+ "grad_norm": 0.24596630036830902,
695
+ "learning_rate": 5.533894736842106e-05,
696
+ "loss": 1.3,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.14078374455732948,
701
+ "grad_norm": 0.28974536061286926,
702
+ "learning_rate": 5.480684210526316e-05,
703
+ "loss": 1.0699,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.14223512336719885,
708
+ "grad_norm": 0.2533659338951111,
709
+ "learning_rate": 5.4274736842105264e-05,
710
+ "loss": 0.6266,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.14368650217706821,
715
+ "grad_norm": 0.36984333395957947,
716
+ "learning_rate": 5.374263157894737e-05,
717
+ "loss": 1.3249,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.14513788098693758,
722
+ "grad_norm": 0.4221994876861572,
723
+ "learning_rate": 5.3210526315789474e-05,
724
+ "loss": 0.9726,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.14513788098693758,
729
+ "eval_loss": 0.2286633849143982,
730
+ "eval_runtime": 145.162,
731
+ "eval_samples_per_second": 2.005,
732
+ "eval_steps_per_second": 0.503,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.2010820204494848e+17,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null