aleegis12 commited on
Commit
e18bdd4
·
verified ·
1 Parent(s): 1bbf200

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 sha256:0b9f6eb62b83e7eaf0e984dc6293472a9144387e3f508431d71a2e6cbd41e35e
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4cc5725855a18ad58bf29989cb19260a2cccb74d619d9dac418e17a1a2d6a61
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8013be9d00b5fd67c505552b63233b5307170e552c9d2f002dbf76f4f627985c
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b491bba7ad5655f4192de1e79e1be9967049139e8885e2e0d44a4d14ef79b211
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:802b15870024b99686308fe58ceaf85c065d9eca1f047147b155da30c92f17eb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6d12920d34bbbddfed84ee3c0293843b273c2232647c594011490f09b9c86f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.48922795057296753,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0019685814402141816,
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": 21.519,
374
  "eval_steps_per_second": 5.38,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3.62025180463104e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.36916714906692505,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.003937162880428363,
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": 21.519,
374
  "eval_steps_per_second": 5.38,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0020079530690184652,
379
+ "grad_norm": 1.1396428346633911,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.5298,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.002047324697822749,
386
+ "grad_norm": 0.575873613357544,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.4576,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0020866963266270326,
393
+ "grad_norm": 0.29430681467056274,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.4226,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0021260679554313162,
400
+ "grad_norm": 0.22301702201366425,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.3945,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0021654395842356,
407
+ "grad_norm": 0.19866794347763062,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.3653,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0022048112130398836,
414
+ "grad_norm": 0.22038273513317108,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.3928,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0022441828418441672,
421
+ "grad_norm": 0.2194378525018692,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.384,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.002283554470648451,
428
+ "grad_norm": 0.22321100533008575,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.3963,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0023229260994527346,
435
+ "grad_norm": 0.20015667378902435,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.3944,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.002362297728257018,
442
+ "grad_norm": 0.1830534040927887,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.3929,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0024016693570613015,
449
+ "grad_norm": 0.17937935888767242,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.3737,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.002441040985865585,
456
+ "grad_norm": 0.17047609388828278,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.3544,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.002480412614669869,
463
+ "grad_norm": 0.16016490757465363,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.3535,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0025197842434741525,
470
+ "grad_norm": 0.17423444986343384,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.3662,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.002559155872278436,
477
+ "grad_norm": 0.16964031755924225,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.3414,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.00259852750108272,
484
+ "grad_norm": 0.17602507770061493,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.3599,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0026378991298870035,
491
+ "grad_norm": 0.17280983924865723,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.3634,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.002677270758691287,
498
+ "grad_norm": 0.17735128104686737,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.3395,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.002716642387495571,
505
+ "grad_norm": 0.19342201948165894,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.3339,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0027560140162998545,
512
+ "grad_norm": 0.18403244018554688,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.3639,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.002795385645104138,
519
+ "grad_norm": 0.1859416365623474,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.3689,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.002834757273908422,
526
+ "grad_norm": 0.17948848009109497,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.3145,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.002874128902712705,
533
+ "grad_norm": 0.19565199315547943,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.3687,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.0029135005315169887,
540
+ "grad_norm": 0.17460434138774872,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.3372,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0029528721603212724,
547
+ "grad_norm": 0.1879396140575409,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.3313,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.002992243789125556,
554
+ "grad_norm": 0.18079061806201935,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.3339,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0030316154179298397,
561
+ "grad_norm": 0.19918537139892578,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.3329,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0030709870467341234,
568
+ "grad_norm": 0.19581687450408936,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.3256,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.003110358675538407,
575
+ "grad_norm": 0.21447274088859558,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.3618,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0031497303043426907,
582
+ "grad_norm": 0.2164623737335205,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.3543,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.0031891019331469744,
589
+ "grad_norm": 0.21725690364837646,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.325,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.003228473561951258,
596
+ "grad_norm": 0.23109690845012665,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.3482,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0032678451907555417,
603
+ "grad_norm": 0.2352961301803589,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.3401,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0033072168195598254,
610
+ "grad_norm": 0.26041918992996216,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.3655,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.003346588448364109,
617
+ "grad_norm": 0.24683479964733124,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.3365,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0033859600771683923,
624
+ "grad_norm": 0.2742876708507538,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.3544,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.003425331705972676,
631
+ "grad_norm": 0.3074694573879242,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.3455,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.0034647033347769596,
638
+ "grad_norm": 0.28489139676094055,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.3248,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0035040749635812433,
645
+ "grad_norm": 0.32520392537117004,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.373,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.003543446592385527,
652
+ "grad_norm": 0.3589666783809662,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.3843,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.0035828182211898106,
659
+ "grad_norm": 0.39428192377090454,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.3816,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0036221898499940943,
666
+ "grad_norm": 0.38958320021629333,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.3553,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.003661561478798378,
673
+ "grad_norm": 0.44357359409332275,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.3812,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0037009331076026616,
680
+ "grad_norm": 0.49647799134254456,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.3667,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0037403047364069453,
687
+ "grad_norm": 0.6239516139030457,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.438,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.003779676365211229,
694
+ "grad_norm": 0.5736242532730103,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.3732,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0038190479940155126,
701
+ "grad_norm": 0.8299224376678467,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.4323,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0038584196228197963,
708
+ "grad_norm": 1.0015686750411987,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.5042,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0038977912516240795,
715
+ "grad_norm": 0.9972793459892273,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.541,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.003937162880428363,
722
+ "grad_norm": 1.5904582738876343,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.5061,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.003937162880428363,
729
+ "eval_loss": 0.36916714906692505,
730
+ "eval_runtime": 1987.5486,
731
+ "eval_samples_per_second": 21.523,
732
+ "eval_steps_per_second": 5.381,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 7.223665228775424e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null