nttx commited on
Commit
3d902c5
·
verified ·
1 Parent(s): cfb87b9

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:d83d3ac5bcd107eaf323974c803a00234d5c1a8a922c2ef8fbc680907a4a1d0f
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:557f788ac8f9f84fb1529be7c94cd42b90c8100cb0ecb95b27ccc921b56ff6fb
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b14f02511295c6abf37352d794e6932d9b597e1d52a07700782796e3b46c1f67
3
  size 281824770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99104d29dfdc693f297ee344b476497765ac2850f0e40c790993caede0c0321a
3
  size 281824770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00a895e63d6b3a22126d047733370fc31baad0f2ed2c6c4e5dc548933185505f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662ed273284082075a9a8743bf567e4a0231d807d0b53d1e58173ef5539ba37d
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": 2.1213467121124268,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0029549954197570995,
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": 41.696,
374
  "eval_steps_per_second": 20.848,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3864241215897600.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.066779136657715,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.005909990839514199,
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": 41.696,
374
  "eval_steps_per_second": 20.848,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0030140953281522415,
379
+ "grad_norm": 5.36259126663208,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 2.25,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.003073195236547383,
386
+ "grad_norm": 4.400323867797852,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 2.3144,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.003132295144942525,
393
+ "grad_norm": 4.434739112854004,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 2.2359,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0031913950533376673,
400
+ "grad_norm": 3.8840668201446533,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 2.1431,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0032504949617328093,
407
+ "grad_norm": 3.4554171562194824,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 2.3377,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0033095948701279514,
414
+ "grad_norm": 3.1983530521392822,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 2.0718,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0033686947785230934,
421
+ "grad_norm": 3.158194065093994,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 2.1517,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0034277946869182355,
428
+ "grad_norm": 3.890373468399048,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 2.441,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.003486894595313377,
435
+ "grad_norm": 3.167813777923584,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 2.2091,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.003545994503708519,
442
+ "grad_norm": 3.1658525466918945,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 2.0947,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.003605094412103661,
449
+ "grad_norm": 3.408245325088501,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 2.2448,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0036641943204988032,
456
+ "grad_norm": 3.817218542098999,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 2.2507,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0037232942288939453,
463
+ "grad_norm": 3.1942789554595947,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 1.9487,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0037823941372890873,
470
+ "grad_norm": 4.15613317489624,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 2.2011,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0038414940456842294,
477
+ "grad_norm": 3.4071335792541504,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 1.9582,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.003900593954079371,
484
+ "grad_norm": 3.021066665649414,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 2.3522,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.003959693862474513,
491
+ "grad_norm": 3.616442918777466,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 2.098,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.004018793770869655,
498
+ "grad_norm": 2.8962440490722656,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 2.0984,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.004077893679264797,
505
+ "grad_norm": 3.579745292663574,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 2.0251,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.004136993587659939,
512
+ "grad_norm": 3.775783061981201,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 2.119,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.004196093496055081,
519
+ "grad_norm": 3.080296754837036,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 2.2573,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.004255193404450223,
526
+ "grad_norm": 2.8051774501800537,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 1.9605,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.004314293312845365,
533
+ "grad_norm": 2.691725730895996,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 1.9226,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.004373393221240507,
540
+ "grad_norm": 2.9309446811676025,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 1.8635,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0044324931296356495,
547
+ "grad_norm": 3.0920376777648926,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 2.3189,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.004491593038030791,
554
+ "grad_norm": 3.608562707901001,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 2.1573,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.004550692946425933,
561
+ "grad_norm": 3.4357681274414062,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 2.3833,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.004609792854821075,
568
+ "grad_norm": 3.2600772380828857,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 1.8943,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.004668892763216217,
575
+ "grad_norm": 3.176687002182007,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 1.8515,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.004727992671611359,
582
+ "grad_norm": 3.3577382564544678,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 1.8858,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.004787092580006501,
589
+ "grad_norm": 3.1467320919036865,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 2.0871,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.004846192488401643,
596
+ "grad_norm": 2.7516732215881348,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 1.8316,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.004905292396796785,
603
+ "grad_norm": 3.2467401027679443,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 2.0702,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.004964392305191927,
610
+ "grad_norm": 3.381272315979004,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 2.2569,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.005023492213587069,
617
+ "grad_norm": 2.826927661895752,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 2.1583,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.005082592121982211,
624
+ "grad_norm": 3.259561061859131,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 1.9269,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.005141692030377353,
631
+ "grad_norm": 3.7768051624298096,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 2.362,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.005200791938772495,
638
+ "grad_norm": 2.951033592224121,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 2.0554,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.005259891847167637,
645
+ "grad_norm": 2.699878454208374,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 1.6497,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0053189917555627785,
652
+ "grad_norm": 2.780122756958008,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 1.904,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.0053780916639579205,
659
+ "grad_norm": 2.7070605754852295,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 1.8025,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.005437191572353063,
666
+ "grad_norm": 2.740710973739624,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 1.9662,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.005496291480748205,
673
+ "grad_norm": 3.0559332370758057,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 2.0185,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.005555391389143347,
680
+ "grad_norm": 2.9242119789123535,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 2.0248,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.005614491297538489,
687
+ "grad_norm": 2.762571334838867,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 1.7682,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.005673591205933631,
694
+ "grad_norm": 2.9518630504608154,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 1.88,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.005732691114328773,
701
+ "grad_norm": 2.976564645767212,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 1.8969,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.005791791022723915,
708
+ "grad_norm": 2.815509796142578,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 1.972,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.005850890931119057,
715
+ "grad_norm": 3.5287201404571533,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 2.125,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.005909990839514199,
722
+ "grad_norm": 3.9216277599334717,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 1.9601,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.005909990839514199,
729
+ "eval_loss": 2.066779136657715,
730
+ "eval_runtime": 683.3126,
731
+ "eval_samples_per_second": 41.706,
732
+ "eval_steps_per_second": 20.853,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 7728482431795200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null