brew35 commited on
Commit
983d63e
·
verified ·
1 Parent(s): 3012181

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:c287287197c23b4af9150ab490eb984aa34254eb1f381d58031e46503dec5527
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a72775db0d3f1b7582db276cf43a150f24e637684824e02107b196a32d57141
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8740cf2e24751c4ac184f2bb760fc98f2524335c6bdad1b368cc00fe2a3d781c
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c8ef8111de90ea23d4c2868b27a70197558f6897d44b4463c39f3bd99c654f
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fe8763c56fb011fdf8c7ee37e70b44872eb29cbf7f4399aeab04b4abf01ea94
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1864a6f7cdef58c33b16eeb6593307302909325725e6a54377e39a358fc971f4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed340328d62f63f2d9d00f6904395875dd09851f050e03ae91b4b798d852ce41
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ca67f9a35cd1c50df3d93bedf5a6642db2c7847c021a0a8d3f44c1bf4993d3
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7081581354141235,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.005761862233873988,
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": 26.745,
374
  "eval_steps_per_second": 6.687,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6375998006231040.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6656689643859863,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.011523724467747977,
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": 26.745,
374
  "eval_steps_per_second": 6.687,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.005877099478551468,
379
+ "grad_norm": 0.6722015142440796,
380
+ "learning_rate": 9.729774092143627e-05,
381
+ "loss": 0.5825,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.005992336723228947,
386
+ "grad_norm": 0.6303715705871582,
387
+ "learning_rate": 9.716559066288715e-05,
388
+ "loss": 0.6244,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.006107573967906428,
393
+ "grad_norm": 0.6753822565078735,
394
+ "learning_rate": 9.703037989675087e-05,
395
+ "loss": 0.7524,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.006222811212583907,
400
+ "grad_norm": 0.571438729763031,
401
+ "learning_rate": 9.689211739666023e-05,
402
+ "loss": 0.5751,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0063380484572613865,
407
+ "grad_norm": 0.6231772303581238,
408
+ "learning_rate": 9.675081213427076e-05,
409
+ "loss": 0.74,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.006453285701938867,
414
+ "grad_norm": 0.5662903189659119,
415
+ "learning_rate": 9.66064732786784e-05,
416
+ "loss": 0.5992,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.006568522946616346,
421
+ "grad_norm": 0.7178725600242615,
422
+ "learning_rate": 9.645911019582467e-05,
423
+ "loss": 0.7747,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.006683760191293826,
428
+ "grad_norm": 0.6594935655593872,
429
+ "learning_rate": 9.630873244788883e-05,
430
+ "loss": 0.6761,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.006798997435971306,
435
+ "grad_norm": 0.6650819778442383,
436
+ "learning_rate": 9.615534979266745e-05,
437
+ "loss": 0.8188,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.006914234680648786,
442
+ "grad_norm": 0.6455956101417542,
443
+ "learning_rate": 9.599897218294122e-05,
444
+ "loss": 0.6711,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.007029471925326265,
449
+ "grad_norm": 0.6445301175117493,
450
+ "learning_rate": 9.583960976582913e-05,
451
+ "loss": 0.7227,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.007144709170003745,
456
+ "grad_norm": 1.0128474235534668,
457
+ "learning_rate": 9.567727288213005e-05,
458
+ "loss": 0.6944,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.007259946414681225,
463
+ "grad_norm": 0.7492349147796631,
464
+ "learning_rate": 9.551197206565173e-05,
465
+ "loss": 0.7062,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.007375183659358704,
470
+ "grad_norm": 0.7735145092010498,
471
+ "learning_rate": 9.534371804252728e-05,
472
+ "loss": 0.7259,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.007490420904036185,
477
+ "grad_norm": 0.8398394584655762,
478
+ "learning_rate": 9.517252173051911e-05,
479
+ "loss": 0.6226,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.007605658148713664,
484
+ "grad_norm": 0.8292278051376343,
485
+ "learning_rate": 9.49983942383106e-05,
486
+ "loss": 0.658,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.007720895393391144,
491
+ "grad_norm": 0.7968212962150574,
492
+ "learning_rate": 9.482134686478519e-05,
493
+ "loss": 0.6969,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.007836132638068623,
498
+ "grad_norm": 0.9180437326431274,
499
+ "learning_rate": 9.464139109829321e-05,
500
+ "loss": 0.7717,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.007951369882746103,
505
+ "grad_norm": 0.9269341826438904,
506
+ "learning_rate": 9.445853861590647e-05,
507
+ "loss": 0.7169,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.008066607127423584,
512
+ "grad_norm": 0.9348207712173462,
513
+ "learning_rate": 9.42728012826605e-05,
514
+ "loss": 0.6536,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.008181844372101062,
519
+ "grad_norm": 1.1747376918792725,
520
+ "learning_rate": 9.408419115078471e-05,
521
+ "loss": 0.7902,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.008297081616778543,
526
+ "grad_norm": 1.1941821575164795,
527
+ "learning_rate": 9.389272045892024e-05,
528
+ "loss": 0.8089,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.008412318861456023,
533
+ "grad_norm": 1.107926368713379,
534
+ "learning_rate": 9.36984016313259e-05,
535
+ "loss": 0.6773,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.008527556106133502,
540
+ "grad_norm": 1.135667324066162,
541
+ "learning_rate": 9.350124727707197e-05,
542
+ "loss": 0.7162,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.008642793350810982,
547
+ "grad_norm": 1.1049367189407349,
548
+ "learning_rate": 9.330127018922194e-05,
549
+ "loss": 0.81,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.008758030595488462,
554
+ "grad_norm": 1.4167182445526123,
555
+ "learning_rate": 9.309848334400246e-05,
556
+ "loss": 0.7369,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.008873267840165941,
561
+ "grad_norm": 1.6046768426895142,
562
+ "learning_rate": 9.289289989996133e-05,
563
+ "loss": 0.7633,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.008988505084843421,
568
+ "grad_norm": 1.4069336652755737,
569
+ "learning_rate": 9.268453319711363e-05,
570
+ "loss": 0.7567,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.009103742329520902,
575
+ "grad_norm": 1.0434424877166748,
576
+ "learning_rate": 9.247339675607605e-05,
577
+ "loss": 0.5982,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.00921897957419838,
582
+ "grad_norm": 1.1521142721176147,
583
+ "learning_rate": 9.225950427718975e-05,
584
+ "loss": 0.6323,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.00933421681887586,
589
+ "grad_norm": 0.8314908742904663,
590
+ "learning_rate": 9.204286963963111e-05,
591
+ "loss": 0.6323,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.009449454063553341,
596
+ "grad_norm": 0.8419124484062195,
597
+ "learning_rate": 9.182350690051133e-05,
598
+ "loss": 0.6278,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.00956469130823082,
603
+ "grad_norm": 0.9470197558403015,
604
+ "learning_rate": 9.160143029396422e-05,
605
+ "loss": 0.6473,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0096799285529083,
610
+ "grad_norm": 0.8800526857376099,
611
+ "learning_rate": 9.13766542302225e-05,
612
+ "loss": 0.5913,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.00979516579758578,
617
+ "grad_norm": 0.9016923308372498,
618
+ "learning_rate": 9.114919329468282e-05,
619
+ "loss": 0.5914,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.009910403042263259,
624
+ "grad_norm": 0.9425757527351379,
625
+ "learning_rate": 9.091906224695935e-05,
626
+ "loss": 0.6713,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.010025640286940739,
631
+ "grad_norm": 1.0047729015350342,
632
+ "learning_rate": 9.068627601992598e-05,
633
+ "loss": 0.6046,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.01014087753161822,
638
+ "grad_norm": 1.045275092124939,
639
+ "learning_rate": 9.045084971874738e-05,
640
+ "loss": 0.6654,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.010256114776295698,
645
+ "grad_norm": 1.0444538593292236,
646
+ "learning_rate": 9.021279861989885e-05,
647
+ "loss": 0.6605,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.010371352020973178,
652
+ "grad_norm": 1.0272176265716553,
653
+ "learning_rate": 8.997213817017507e-05,
654
+ "loss": 0.7068,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.010486589265650659,
659
+ "grad_norm": 1.094701886177063,
660
+ "learning_rate": 8.972888398568772e-05,
661
+ "loss": 0.6086,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.010601826510328137,
666
+ "grad_norm": 1.1884337663650513,
667
+ "learning_rate": 8.948305185085225e-05,
668
+ "loss": 0.6948,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.010717063755005618,
673
+ "grad_norm": 1.0921660661697388,
674
+ "learning_rate": 8.92346577173636e-05,
675
+ "loss": 0.664,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.010832300999683098,
680
+ "grad_norm": 1.253016710281372,
681
+ "learning_rate": 8.898371770316111e-05,
682
+ "loss": 0.6962,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.010947538244360577,
687
+ "grad_norm": 1.1953667402267456,
688
+ "learning_rate": 8.873024809138272e-05,
689
+ "loss": 0.6155,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.011062775489038057,
694
+ "grad_norm": 1.0429881811141968,
695
+ "learning_rate": 8.847426532930831e-05,
696
+ "loss": 0.5882,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.011178012733715537,
701
+ "grad_norm": 1.3511476516723633,
702
+ "learning_rate": 8.821578602729242e-05,
703
+ "loss": 0.6557,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.011293249978393016,
708
+ "grad_norm": 1.132889986038208,
709
+ "learning_rate": 8.795482695768658e-05,
710
+ "loss": 0.6294,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.011408487223070496,
715
+ "grad_norm": 1.3862687349319458,
716
+ "learning_rate": 8.769140505375085e-05,
717
+ "loss": 0.6493,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.011523724467747977,
722
+ "grad_norm": 1.5808641910552979,
723
+ "learning_rate": 8.742553740855506e-05,
724
+ "loss": 0.5728,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.011523724467747977,
729
+ "eval_loss": 0.6656689643859863,
730
+ "eval_runtime": 547.0519,
731
+ "eval_samples_per_second": 26.716,
732
+ "eval_steps_per_second": 6.679,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.25587839516672e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null