arcwarden46 commited on
Commit
737a1a4
·
verified ·
1 Parent(s): 0a663ba

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 sha256:0850b88147138e1ff0c52b9b1dcfb38a39fe04cb4b184c61f1118b027b6a9d78
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d67cc171e7cef6437374d3890cd52fa82c29c2f8dc74627b09f129bb934dcb
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3bf6728ebeca61fbdf7b9b070296c746ad58c5aa5b04ce1b34d0380c222a647
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04c5cbf95495eff51819f747c1308edcb572b9f9ca9dfc663ea03d9c1d86c57e
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b0aca825ec1dda73de5fbb4a6c3982b205ae8ae6b150a52368b32366cecc6e9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf2d95f55605664fc73443e4d56e2c5a5e0fe63fdd9ec66adb81e46fa7f6d80
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4115de2c01c3d59fcd37954d68205c37368a627faed4921a08f3cc6375d25614
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7e3cdff407f71f983ac7ffef25e6d551bbdff8be7e11f26e01dcebe54f37b0
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.8274506330490112,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 1.3157894736842106,
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": 13.39,
374
  "eval_steps_per_second": 3.347,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -387,7 +745,7 @@
387
  "early_stopping_threshold": 0.0
388
  },
389
  "attributes": {
390
- "early_stopping_patience_counter": 0
391
  }
392
  },
393
  "TrainerControl": {
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.123694981323162e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
  "best_metric": 0.8274506330490112,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 2.6315789473684212,
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": 13.39,
374
  "eval_steps_per_second": 3.347,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.3421052631578947,
379
+ "grad_norm": 9.546468734741211,
380
+ "learning_rate": 6.631013946104347e-05,
381
+ "loss": 1.7558,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 1.368421052631579,
386
+ "grad_norm": 9.4080228805542,
387
+ "learning_rate": 6.487515269276016e-05,
388
+ "loss": 1.4641,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 1.3947368421052633,
393
+ "grad_norm": 7.666134834289551,
394
+ "learning_rate": 6.342659337371885e-05,
395
+ "loss": 1.0689,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 1.4210526315789473,
400
+ "grad_norm": 9.010215759277344,
401
+ "learning_rate": 6.19657832143779e-05,
402
+ "loss": 1.2617,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 1.4473684210526316,
407
+ "grad_norm": 11.879247665405273,
408
+ "learning_rate": 6.049405510324238e-05,
409
+ "loss": 1.1061,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 1.4736842105263157,
414
+ "grad_norm": 15.107841491699219,
415
+ "learning_rate": 5.90127518906953e-05,
416
+ "loss": 1.5306,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 1.5,
421
+ "grad_norm": 9.882277488708496,
422
+ "learning_rate": 5.752322516373916e-05,
423
+ "loss": 2.4832,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.526315789473684,
428
+ "grad_norm": 8.323047637939453,
429
+ "learning_rate": 5.602683401276615e-05,
430
+ "loss": 1.656,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.5526315789473686,
435
+ "grad_norm": 9.123269081115723,
436
+ "learning_rate": 5.45249437914819e-05,
437
+ "loss": 1.592,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.5789473684210527,
442
+ "grad_norm": 10.40864086151123,
443
+ "learning_rate": 5.3018924871114305e-05,
444
+ "loss": 1.4905,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.6052631578947367,
449
+ "grad_norm": 9.093459129333496,
450
+ "learning_rate": 5.151015139004445e-05,
451
+ "loss": 1.2591,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.631578947368421,
456
+ "grad_norm": 10.694282531738281,
457
+ "learning_rate": 5e-05,
458
+ "loss": 1.351,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.6578947368421053,
463
+ "grad_norm": 12.236539840698242,
464
+ "learning_rate": 4.848984860995557e-05,
465
+ "loss": 1.1828,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.6842105263157894,
470
+ "grad_norm": 10.095430374145508,
471
+ "learning_rate": 4.6981075128885693e-05,
472
+ "loss": 1.1513,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.7105263157894737,
477
+ "grad_norm": 12.897542953491211,
478
+ "learning_rate": 4.547505620851811e-05,
479
+ "loss": 1.0376,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.736842105263158,
484
+ "grad_norm": 10.298996925354004,
485
+ "learning_rate": 4.397316598723385e-05,
486
+ "loss": 2.2939,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.763157894736842,
491
+ "grad_norm": 8.406174659729004,
492
+ "learning_rate": 4.2476774836260845e-05,
493
+ "loss": 1.4841,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.7894736842105263,
498
+ "grad_norm": 8.802860260009766,
499
+ "learning_rate": 4.0987248109304714e-05,
500
+ "loss": 1.567,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.8157894736842106,
505
+ "grad_norm": 10.089945793151855,
506
+ "learning_rate": 3.950594489675763e-05,
507
+ "loss": 1.2052,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.8421052631578947,
512
+ "grad_norm": 11.97966194152832,
513
+ "learning_rate": 3.803421678562213e-05,
514
+ "loss": 1.4612,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.868421052631579,
519
+ "grad_norm": 11.531331062316895,
520
+ "learning_rate": 3.657340662628116e-05,
521
+ "loss": 1.2934,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.8947368421052633,
526
+ "grad_norm": 8.967305183410645,
527
+ "learning_rate": 3.512484730723986e-05,
528
+ "loss": 1.1132,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.9210526315789473,
533
+ "grad_norm": 22.837160110473633,
534
+ "learning_rate": 3.368986053895655e-05,
535
+ "loss": 1.2606,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.9473684210526314,
540
+ "grad_norm": 14.750879287719727,
541
+ "learning_rate": 3.226975564787322e-05,
542
+ "loss": 1.2884,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.973684210526316,
547
+ "grad_norm": 10.757916450500488,
548
+ "learning_rate": 3.086582838174551e-05,
549
+ "loss": 1.8587,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 2.0,
554
+ "grad_norm": 15.325807571411133,
555
+ "learning_rate": 2.9479359727362173e-05,
556
+ "loss": 1.2197,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 2.026315789473684,
561
+ "grad_norm": 5.313655853271484,
562
+ "learning_rate": 2.811161474173297e-05,
563
+ "loss": 1.1478,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 2.0526315789473686,
568
+ "grad_norm": 5.582791328430176,
569
+ "learning_rate": 2.6763841397811573e-05,
570
+ "loss": 0.6872,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 2.0789473684210527,
575
+ "grad_norm": 4.926303863525391,
576
+ "learning_rate": 2.5437269445806145e-05,
577
+ "loss": 0.5424,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 2.1052631578947367,
582
+ "grad_norm": 7.606872081756592,
583
+ "learning_rate": 2.4133109291117156e-05,
584
+ "loss": 0.5015,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 2.1315789473684212,
589
+ "grad_norm": 5.713882923126221,
590
+ "learning_rate": 2.2852550889926067e-05,
591
+ "loss": 0.4867,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 2.1578947368421053,
596
+ "grad_norm": 8.591730117797852,
597
+ "learning_rate": 2.1596762663442218e-05,
598
+ "loss": 0.4267,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 2.1842105263157894,
603
+ "grad_norm": 12.103515625,
604
+ "learning_rate": 2.0366890431799167e-05,
605
+ "loss": 0.2807,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 2.2105263157894735,
610
+ "grad_norm": 8.517769813537598,
611
+ "learning_rate": 1.9164056368572846e-05,
612
+ "loss": 0.3038,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 2.236842105263158,
617
+ "grad_norm": 6.122335433959961,
618
+ "learning_rate": 1.7989357976875603e-05,
619
+ "loss": 0.3068,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 2.263157894736842,
624
+ "grad_norm": 9.968849182128906,
625
+ "learning_rate": 1.684386708796025e-05,
626
+ "loss": 1.396,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 2.2894736842105265,
631
+ "grad_norm": 10.96872615814209,
632
+ "learning_rate": 1.5728628883248007e-05,
633
+ "loss": 0.5336,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 2.3157894736842106,
638
+ "grad_norm": 7.527137279510498,
639
+ "learning_rate": 1.4644660940672627e-05,
640
+ "loss": 0.5198,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 2.3421052631578947,
645
+ "grad_norm": 6.584356784820557,
646
+ "learning_rate": 1.3592952306210588e-05,
647
+ "loss": 0.3041,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 2.3684210526315788,
652
+ "grad_norm": 7.736539363861084,
653
+ "learning_rate": 1.257446259144494e-05,
654
+ "loss": 0.4027,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 2.3947368421052633,
659
+ "grad_norm": 5.754791259765625,
660
+ "learning_rate": 1.159012109798598e-05,
661
+ "loss": 0.2305,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 2.4210526315789473,
666
+ "grad_norm": 6.632175922393799,
667
+ "learning_rate": 1.0640825969547496e-05,
668
+ "loss": 0.2377,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 2.4473684210526314,
673
+ "grad_norm": 12.447802543640137,
674
+ "learning_rate": 9.7274433724527e-06,
675
+ "loss": 0.3519,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 2.473684210526316,
680
+ "grad_norm": 7.3365702629089355,
681
+ "learning_rate": 8.850806705317183e-06,
682
+ "loss": 0.2841,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 2.5,
687
+ "grad_norm": 8.352860450744629,
688
+ "learning_rate": 8.011715838630107e-06,
689
+ "loss": 0.9615,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 2.526315789473684,
694
+ "grad_norm": 7.111477851867676,
695
+ "learning_rate": 7.21093638492763e-06,
696
+ "loss": 0.4884,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 2.5526315789473686,
701
+ "grad_norm": 7.582794189453125,
702
+ "learning_rate": 6.449199000224221e-06,
703
+ "loss": 0.5061,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 2.5789473684210527,
708
+ "grad_norm": 8.334342002868652,
709
+ "learning_rate": 5.727198717339511e-06,
710
+ "loss": 0.5218,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 2.6052631578947367,
715
+ "grad_norm": 15.341864585876465,
716
+ "learning_rate": 5.045594311728707e-06,
717
+ "loss": 0.3552,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 2.6315789473684212,
722
+ "grad_norm": 8.251885414123535,
723
+ "learning_rate": 4.405007700395497e-06,
724
+ "loss": 0.3264,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 2.6315789473684212,
729
+ "eval_loss": 0.9560651779174805,
730
+ "eval_runtime": 4.7813,
731
+ "eval_samples_per_second": 13.385,
732
+ "eval_steps_per_second": 3.346,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
745
  "early_stopping_threshold": 0.0
746
  },
747
  "attributes": {
748
+ "early_stopping_patience_counter": 1
749
  }
750
  },
751
  "TrainerControl": {
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.4247389962646323e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null