nttx commited on
Commit
8ed922b
·
verified ·
1 Parent(s): 9701e62

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 sha256:7608303689dabba08e1cfea93d66970c32e19939b8532154df71f0bc3c1bcd79
3
  size 93608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f2f4bbbc5ba7a046685bedadcb69b02f0d2469ef65417d56b8f971dfc47ecf1
3
  size 93608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:456fbbaa363b56a7ca32356ebd5d3a0ab9b00327e01c7cbec562c054225d26eb
3
  size 204106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962904fe51a5a48312c113d9c72a9d3af3c15e51fb5cc697e2c59151b79ac208
3
  size 204106
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:076a571ce49013f8da812abd6fecd4f7c78eeb9ff3b825655de3403286307ea0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3c3970eafa8b568941eb9b79a92b3c1e5e04a8d1841b081151c242ffd494a3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d90116c540b4ff0066495fbccc9c914a568905fb44c6564f227952cc4231b00
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ad66011cfc1fc727a51190602a41adc332b48eeef62a5ee87c2ca9f9b90b2b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 11.932531356811523,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.02844950213371266,
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": 158.824,
374
  "eval_steps_per_second": 39.706,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 60260352000.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.932267189025879,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.05689900426742532,
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": 158.824,
374
  "eval_steps_per_second": 39.706,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.029018492176386912,
379
+ "grad_norm": 0.024920569732785225,
380
+ "learning_rate": 2.3816778784387097e-05,
381
+ "loss": 11.9347,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.029587482219061167,
386
+ "grad_norm": 0.01942363753914833,
387
+ "learning_rate": 2.3263454721781537e-05,
388
+ "loss": 11.9334,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.030156472261735418,
393
+ "grad_norm": 0.018219970166683197,
394
+ "learning_rate": 2.2693489161088592e-05,
395
+ "loss": 11.9342,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.030725462304409673,
400
+ "grad_norm": 0.0270726066082716,
401
+ "learning_rate": 2.210802993709498e-05,
402
+ "loss": 11.9365,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.031294452347083924,
407
+ "grad_norm": 0.025170834735035896,
408
+ "learning_rate": 2.1508256086763372e-05,
409
+ "loss": 11.933,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.031863442389758176,
414
+ "grad_norm": 0.023072171956300735,
415
+ "learning_rate": 2.0895375474808857e-05,
416
+ "loss": 11.9331,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.032432432432432434,
421
+ "grad_norm": 0.024829139932990074,
422
+ "learning_rate": 2.0270622361220143e-05,
423
+ "loss": 11.9322,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.033001422475106686,
428
+ "grad_norm": 0.020406652241945267,
429
+ "learning_rate": 1.963525491562421e-05,
430
+ "loss": 11.9335,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03357041251778094,
435
+ "grad_norm": 0.016411518678069115,
436
+ "learning_rate": 1.8990552683500128e-05,
437
+ "loss": 11.9311,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.034139402560455195,
442
+ "grad_norm": 0.02456144243478775,
443
+ "learning_rate": 1.8337814009344716e-05,
444
+ "loss": 11.9308,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.03470839260312945,
449
+ "grad_norm": 0.02477637305855751,
450
+ "learning_rate": 1.767835342197955e-05,
451
+ "loss": 11.9348,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0352773826458037,
456
+ "grad_norm": 0.023375025019049644,
457
+ "learning_rate": 1.7013498987264832e-05,
458
+ "loss": 11.9328,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.03584637268847795,
463
+ "grad_norm": 0.06162303313612938,
464
+ "learning_rate": 1.6344589633551502e-05,
465
+ "loss": 11.9297,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.03641536273115221,
470
+ "grad_norm": 0.02088780514895916,
471
+ "learning_rate": 1.5672972455257726e-05,
472
+ "loss": 11.9305,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.03698435277382646,
477
+ "grad_norm": 0.014960064552724361,
478
+ "learning_rate": 1.5e-05,
479
+ "loss": 11.9316,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.03755334281650071,
484
+ "grad_norm": 0.02649613656103611,
485
+ "learning_rate": 1.4327027544742281e-05,
486
+ "loss": 11.9351,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.03812233285917496,
491
+ "grad_norm": 0.015364968217909336,
492
+ "learning_rate": 1.36554103664485e-05,
493
+ "loss": 11.937,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.03869132290184922,
498
+ "grad_norm": 0.02552586793899536,
499
+ "learning_rate": 1.2986501012735174e-05,
500
+ "loss": 11.9334,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.03926031294452347,
505
+ "grad_norm": 0.03519086167216301,
506
+ "learning_rate": 1.2321646578020452e-05,
507
+ "loss": 11.9332,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.03982930298719772,
512
+ "grad_norm": 0.03798099234700203,
513
+ "learning_rate": 1.1662185990655285e-05,
514
+ "loss": 11.9313,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.040398293029871975,
519
+ "grad_norm": 0.024176588281989098,
520
+ "learning_rate": 1.1009447316499875e-05,
521
+ "loss": 11.9347,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04096728307254623,
526
+ "grad_norm": 0.02996925264596939,
527
+ "learning_rate": 1.036474508437579e-05,
528
+ "loss": 11.9315,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.041536273115220484,
533
+ "grad_norm": 0.02919541671872139,
534
+ "learning_rate": 9.729377638779859e-06,
535
+ "loss": 11.9331,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.042105263157894736,
540
+ "grad_norm": 0.028178086504340172,
541
+ "learning_rate": 9.104624525191147e-06,
542
+ "loss": 11.9248,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04267425320056899,
547
+ "grad_norm": 0.01623309962451458,
548
+ "learning_rate": 8.491743913236629e-06,
549
+ "loss": 11.9352,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.043243243243243246,
554
+ "grad_norm": 0.018746746703982353,
555
+ "learning_rate": 7.89197006290502e-06,
556
+ "loss": 11.9348,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0438122332859175,
561
+ "grad_norm": 0.0497860461473465,
562
+ "learning_rate": 7.30651083891141e-06,
563
+ "loss": 11.9303,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.04438122332859175,
568
+ "grad_norm": 0.028148330748081207,
569
+ "learning_rate": 6.736545278218464e-06,
570
+ "loss": 11.9365,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.044950213371266,
575
+ "grad_norm": 0.0570177286863327,
576
+ "learning_rate": 6.1832212156129045e-06,
577
+ "loss": 11.9323,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.04551920341394026,
582
+ "grad_norm": 0.01971592754125595,
583
+ "learning_rate": 5.647652972118998e-06,
584
+ "loss": 11.9343,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.04608819345661451,
589
+ "grad_norm": 0.02897561341524124,
590
+ "learning_rate": 5.130919110904311e-06,
591
+ "loss": 11.9351,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.04665718349928876,
596
+ "grad_norm": 0.02293010614812374,
597
+ "learning_rate": 4.6340602651970304e-06,
598
+ "loss": 11.9322,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.04722617354196301,
603
+ "grad_norm": 0.040468648076057434,
604
+ "learning_rate": 4.158077042589129e-06,
605
+ "loss": 11.9341,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.04779516358463727,
610
+ "grad_norm": 0.02485041506588459,
611
+ "learning_rate": 3.7039280099458373e-06,
612
+ "loss": 11.9351,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.04836415362731152,
617
+ "grad_norm": 0.034283898770809174,
618
+ "learning_rate": 3.272527762979553e-06,
619
+ "loss": 11.931,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.048933143669985774,
624
+ "grad_norm": 0.037042126059532166,
625
+ "learning_rate": 2.86474508437579e-06,
626
+ "loss": 11.9342,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.049502133712660025,
631
+ "grad_norm": 0.0422203503549099,
632
+ "learning_rate": 2.4814011941804603e-06,
633
+ "loss": 11.9373,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.05007112375533428,
638
+ "grad_norm": 0.044131770730018616,
639
+ "learning_rate": 2.1232680959720085e-06,
640
+ "loss": 11.932,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.050640113798008535,
645
+ "grad_norm": 0.03228357434272766,
646
+ "learning_rate": 1.79106702214893e-06,
647
+ "loss": 11.9307,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.051209103840682786,
652
+ "grad_norm": 0.07020854204893112,
653
+ "learning_rate": 1.4854669814637145e-06,
654
+ "loss": 11.93,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.051778093883357044,
659
+ "grad_norm": 0.04166794195771217,
660
+ "learning_rate": 1.2070834117282414e-06,
661
+ "loss": 11.9275,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.052347083926031296,
666
+ "grad_norm": 0.046017613261938095,
667
+ "learning_rate": 9.56476940403942e-07,
668
+ "loss": 11.9365,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.05291607396870555,
673
+ "grad_norm": 0.06281369924545288,
674
+ "learning_rate": 7.341522555726971e-07,
675
+ "loss": 11.935,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0534850640113798,
680
+ "grad_norm": 0.06520992517471313,
681
+ "learning_rate": 5.405570895622014e-07,
682
+ "loss": 11.929,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.05405405405405406,
687
+ "grad_norm": 0.051743801683187485,
688
+ "learning_rate": 3.760813172726457e-07,
689
+ "loss": 11.9319,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.05462304409672831,
694
+ "grad_norm": 0.0535205602645874,
695
+ "learning_rate": 2.41056171020555e-07,
696
+ "loss": 11.9327,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.05519203413940256,
701
+ "grad_norm": 0.047187186777591705,
702
+ "learning_rate": 1.357535734809795e-07,
703
+ "loss": 11.93,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.05576102418207681,
708
+ "grad_norm": 0.05550428852438927,
709
+ "learning_rate": 6.038559007141397e-08,
710
+ "loss": 11.9327,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.05633001422475107,
715
+ "grad_norm": 0.05680185556411743,
716
+ "learning_rate": 1.510400188028116e-08,
717
+ "loss": 11.9274,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.05689900426742532,
722
+ "grad_norm": 0.0982510969042778,
723
+ "learning_rate": 0.0,
724
+ "loss": 11.9319,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.05689900426742532,
729
+ "eval_loss": 11.932267189025879,
730
+ "eval_runtime": 4.6533,
731
+ "eval_samples_per_second": 159.026,
732
+ "eval_steps_per_second": 39.757,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 120520704000.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null