prxy5608 commited on
Commit
b19332f
·
verified ·
1 Parent(s): 3739918

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 sha256:6db5ac775aab3bff248b5103efad1f089df2ea7148f486c4a8657136c6070cf3
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:826c36ca30366c7ee75ff79ce8b9bf88fcf43a79bdb8b4ee95564dd71b7afb77
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57dbeda70a5d0b65ea2d7c760ca07efbdd7f9f4d6376c22a5dd40b35c1feb9a7
3
  size 281824770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b59a1a31f25665c0627e2bb70f978205718eaf26a2c65d552282f0856cb2322a
3
  size 281824770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c40a150aaac8e5bf32e9ecbabb34037955faf78a4152e20e651de98192e3704
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa7b44789e269747b34fd32afff7933f1573ae1e6e1cabed2899757679411e09
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": 1.432480812072754,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.05648121999435188,
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": 37.008,
374
  "eval_steps_per_second": 18.517,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 4791659107713024.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3735841512680054,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.11296243998870376,
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": 37.008,
374
  "eval_steps_per_second": 18.517,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.057610844394238914,
379
+ "grad_norm": 6.058037281036377,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 1.3163,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.058740468794125957,
386
+ "grad_norm": 4.502705097198486,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 1.3347,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.05987009319401299,
393
+ "grad_norm": 2.17488694190979,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 1.2591,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.06099971759390003,
400
+ "grad_norm": 0.9344148635864258,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 1.3128,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.062129341993787064,
407
+ "grad_norm": 0.6633459329605103,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 1.2463,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.06325896639367411,
414
+ "grad_norm": 0.5168513655662537,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 1.4022,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.06438859079356114,
421
+ "grad_norm": 0.4739576280117035,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 1.4488,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.06551821519344818,
428
+ "grad_norm": 0.47201716899871826,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 1.4155,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.06664783959333521,
435
+ "grad_norm": 0.5001115202903748,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 1.4252,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.06777746399322225,
442
+ "grad_norm": 0.5142220258712769,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 1.5093,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.06890708839310929,
449
+ "grad_norm": 0.5015035271644592,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 1.4912,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.07003671279299632,
456
+ "grad_norm": 0.46737051010131836,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 1.1751,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.07116633719288337,
463
+ "grad_norm": 0.4706385135650635,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 1.3106,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.07229596159277041,
470
+ "grad_norm": 0.45581290125846863,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 1.1907,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.07342558599265744,
477
+ "grad_norm": 0.46465736627578735,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 1.1932,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.07455521039254448,
484
+ "grad_norm": 0.48178812861442566,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 1.2628,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.07568483479243152,
491
+ "grad_norm": 0.4830457270145416,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 1.2991,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.07681445919231855,
498
+ "grad_norm": 0.462005615234375,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 1.1688,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.07794408359220559,
505
+ "grad_norm": 0.458380788564682,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 1.1544,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.07907370799209262,
512
+ "grad_norm": 0.4663032591342926,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 1.2183,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.08020333239197967,
519
+ "grad_norm": 0.46658870577812195,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 1.1824,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.08133295679186671,
526
+ "grad_norm": 0.481890469789505,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 1.3568,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.08246258119175374,
533
+ "grad_norm": 0.47948282957077026,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 1.3212,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.08359220559164078,
540
+ "grad_norm": 0.48503363132476807,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 1.3575,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.08472182999152782,
547
+ "grad_norm": 0.4890155792236328,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 1.2868,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.08585145439141485,
554
+ "grad_norm": 0.509662389755249,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 1.2104,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.08698107879130189,
561
+ "grad_norm": 0.5349501371383667,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 1.261,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.08811070319118892,
568
+ "grad_norm": 0.4927584230899811,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 1.2917,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.08924032759107597,
575
+ "grad_norm": 0.5024597644805908,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 1.3051,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.09036995199096301,
582
+ "grad_norm": 0.506453812122345,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 1.2326,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.09149957639085005,
589
+ "grad_norm": 0.5375275015830994,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 1.2622,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.09262920079073708,
596
+ "grad_norm": 0.5495799779891968,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 1.3801,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.09375882519062412,
603
+ "grad_norm": 0.5337545871734619,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 1.265,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.09488844959051115,
610
+ "grad_norm": 0.617557168006897,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 1.4319,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.09601807399039819,
617
+ "grad_norm": 0.5542303919792175,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 1.3273,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.09714769839028523,
624
+ "grad_norm": 0.6230977177619934,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 1.4884,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.09827732279017226,
631
+ "grad_norm": 0.6454778909683228,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 1.4153,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.09940694719005931,
638
+ "grad_norm": 0.6431711912155151,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 1.4105,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.10053657158994635,
645
+ "grad_norm": 0.6007747054100037,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 1.5489,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.10166619598983338,
652
+ "grad_norm": 0.7283254861831665,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 1.5462,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.10279582038972042,
659
+ "grad_norm": 0.6557906270027161,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 1.4465,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.10392544478960745,
666
+ "grad_norm": 0.6841725707054138,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 1.5167,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.10505506918949449,
673
+ "grad_norm": 0.6644818782806396,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 1.5386,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.10618469358938153,
680
+ "grad_norm": 0.7009238004684448,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 1.5738,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.10731431798926856,
687
+ "grad_norm": 0.8302545547485352,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 1.6512,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.10844394238915561,
694
+ "grad_norm": 0.8315028548240662,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 1.5656,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.10957356678904265,
701
+ "grad_norm": 0.8375591039657593,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 1.6308,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.11070319118892968,
708
+ "grad_norm": 0.9466162323951721,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 1.5572,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.11183281558881672,
715
+ "grad_norm": 1.0481469631195068,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 1.5684,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.11296243998870376,
722
+ "grad_norm": 1.371314525604248,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 1.4859,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.11296243998870376,
729
+ "eval_loss": 1.3735841512680054,
730
+ "eval_runtime": 40.2716,
731
+ "eval_samples_per_second": 37.024,
732
+ "eval_steps_per_second": 18.524,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 9544675803267072.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null