prxy5608 commited on
Commit
25ac4ce
·
verified ·
1 Parent(s): 2f5c8d1

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 sha256:751b9abf98b1c841ff9e44fbd371a9fefc28538e314be4c4fc594870baee37d1
3
  size 800116456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867dc262ace931616d57895e1f48f9c7c5ded046a3d611c04a728e3a62c4886b
3
  size 800116456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eee83ea694960a39ef0e9ef81c868662421a2be1b92a736f475dd6508a69666f
3
  size 1600457770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37070df0d692c8ea5cf5bb7708035ed7c5ad8845fcf531dd81e1368eeeaf19c6
3
  size 1600457770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3b5bfc82f51515d002a948e0a0c4ff7f9c6f9f1c82094a22ec608fd82328be9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9bb49e63119442bb64b93513f9164261109eab01ecabc8ecec6a841b1d1f35c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5335737b4b4d079cdec612fe6ee661ed4d29f9e0e55eb4eada44a9677240228
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3152074813842773,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.5376344086021505,
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": 10.85,
374
  "eval_steps_per_second": 5.46,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.81641131753472e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.115802526473999,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.075268817204301,
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": 10.85,
374
  "eval_steps_per_second": 5.46,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5483870967741935,
379
+ "grad_norm": 3.6186563968658447,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 1.7819,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.5591397849462365,
386
+ "grad_norm": 3.9859840869903564,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 1.2978,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.5698924731182796,
393
+ "grad_norm": 3.9932148456573486,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 1.447,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.5806451612903226,
400
+ "grad_norm": 3.5936036109924316,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 1.3967,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.5913978494623656,
407
+ "grad_norm": 3.375316858291626,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 1.0998,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.6021505376344086,
414
+ "grad_norm": 3.807166814804077,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 1.1404,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.6129032258064516,
421
+ "grad_norm": 3.084326982498169,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 0.988,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.6236559139784946,
428
+ "grad_norm": 3.7563459873199463,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 1.0191,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.6344086021505376,
435
+ "grad_norm": 4.25908899307251,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 0.8702,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.6451612903225806,
442
+ "grad_norm": 3.750455617904663,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 0.8746,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.6559139784946236,
449
+ "grad_norm": 3.6707611083984375,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 0.9337,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.6666666666666666,
456
+ "grad_norm": 3.612056016921997,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 1.1718,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.6774193548387096,
463
+ "grad_norm": 4.298011779785156,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 0.628,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.6881720430107527,
470
+ "grad_norm": 4.248507022857666,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 0.6906,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.6989247311827957,
477
+ "grad_norm": 3.890913963317871,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 1.0229,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.7096774193548387,
484
+ "grad_norm": 4.77676248550415,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 0.8174,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.7204301075268817,
491
+ "grad_norm": 4.285477161407471,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 0.8005,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.7311827956989247,
498
+ "grad_norm": 3.8125786781311035,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 0.5634,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.7419354838709677,
505
+ "grad_norm": 4.32075309753418,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 0.6793,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.7526881720430108,
512
+ "grad_norm": 3.8095755577087402,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 2.0449,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.7634408602150538,
519
+ "grad_norm": 3.9818124771118164,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 1.9486,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.7741935483870968,
526
+ "grad_norm": 3.4325692653656006,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 1.8445,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.7849462365591398,
533
+ "grad_norm": 3.9117205142974854,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 1.9626,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.7956989247311828,
540
+ "grad_norm": 3.40067195892334,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 1.3113,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.8064516129032258,
547
+ "grad_norm": 3.8196802139282227,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 1.7274,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.8172043010752689,
554
+ "grad_norm": 4.589756488800049,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 1.7595,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.8279569892473119,
561
+ "grad_norm": 4.156907081604004,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 1.5407,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.8387096774193549,
568
+ "grad_norm": 3.101147174835205,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 0.9117,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.8494623655913979,
575
+ "grad_norm": 2.96360182762146,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 1.1026,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.8602150537634409,
582
+ "grad_norm": 2.9797332286834717,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 0.8541,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.8709677419354839,
589
+ "grad_norm": 3.0931079387664795,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 0.8875,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.8817204301075269,
596
+ "grad_norm": 2.8962762355804443,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 0.9001,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.8924731182795699,
603
+ "grad_norm": 3.5031051635742188,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 0.8276,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.9032258064516129,
610
+ "grad_norm": 3.142409086227417,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 0.823,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.9139784946236559,
617
+ "grad_norm": 2.962707757949829,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 0.8578,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.9247311827956989,
624
+ "grad_norm": 3.3335912227630615,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 0.8609,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.9354838709677419,
631
+ "grad_norm": 4.589385509490967,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 1.0085,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.946236559139785,
638
+ "grad_norm": 3.5878801345825195,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 0.5649,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.956989247311828,
645
+ "grad_norm": 3.286903142929077,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 0.4883,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.967741935483871,
652
+ "grad_norm": 3.4730312824249268,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 0.7835,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.978494623655914,
659
+ "grad_norm": 3.7954018115997314,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 0.7178,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.989247311827957,
666
+ "grad_norm": 3.0298449993133545,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 0.4597,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.0,
673
+ "grad_norm": 11.850226402282715,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 1.5025,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.010752688172043,
680
+ "grad_norm": 6.41492223739624,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 1.8111,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.021505376344086,
687
+ "grad_norm": 3.9378912448883057,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 1.5149,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.032258064516129,
694
+ "grad_norm": 3.533281087875366,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 1.4312,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.043010752688172,
701
+ "grad_norm": 3.780578136444092,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 1.2979,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.053763440860215,
708
+ "grad_norm": 2.7388339042663574,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 0.988,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.064516129032258,
715
+ "grad_norm": 2.726057767868042,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 1.0731,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.075268817204301,
722
+ "grad_norm": 4.266610622406006,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 1.0392,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.075268817204301,
729
+ "eval_loss": 1.115802526473999,
730
+ "eval_runtime": 14.4453,
731
+ "eval_samples_per_second": 10.869,
732
+ "eval_steps_per_second": 5.469,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.562305212092252e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null