dimasik2987 commited on
Commit
542badd
·
verified ·
1 Parent(s): 7410f07

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:df7cf14ab8c3d9c57da6a7be43192707e91597f007474d8d60fbbca26d1fa09b
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e184f4951e4d504182ee9dbad8a47a8979c98a79a58accef24d77b28fa0aba7
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8b96b0705684b4019970efa5402e022ffc2e65fe055420a136e8129ee02f479
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f69b479df1c5ef336708f34a1737d1cbb105c8b530fa8f19985e8e3efbfdad8
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:619f48e619614e840891abed165fd2588f57c839e0144005e907c5bb0be8c648
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6be03569ffca8e1a904138d9129ec937cdfa3781af4d7f216a486046f92479f3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6626a958c42744f62f15b40b71145564a751f3973a73662e664e23d40b38c82
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16c2a0a7f4d1c317518a0a40a7c58dbcf9237e9297de7a3c67a0a8ebfbe5ded
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.26625388860702515,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.013042911177774879,
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": 4.512,
374
  "eval_steps_per_second": 1.129,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3.2734116298358784e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.12110025435686111,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.026085822355549758,
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": 4.512,
374
  "eval_steps_per_second": 1.129,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.013303769401330377,
379
+ "grad_norm": 21.080076217651367,
380
+ "learning_rate": 7.873473684210526e-05,
381
+ "loss": 0.898,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.013564627624885875,
386
+ "grad_norm": 7.187935829162598,
387
+ "learning_rate": 7.820631578947369e-05,
388
+ "loss": 0.6007,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.013825485848441373,
393
+ "grad_norm": 2.1182901859283447,
394
+ "learning_rate": 7.76778947368421e-05,
395
+ "loss": 0.4358,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01408634407199687,
400
+ "grad_norm": 1.093733310699463,
401
+ "learning_rate": 7.714947368421052e-05,
402
+ "loss": 0.347,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.014347202295552367,
407
+ "grad_norm": 0.9055514931678772,
408
+ "learning_rate": 7.662105263157896e-05,
409
+ "loss": 0.3856,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.014608060519107865,
414
+ "grad_norm": 0.8669521808624268,
415
+ "learning_rate": 7.609263157894737e-05,
416
+ "loss": 0.3701,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.014868918742663363,
421
+ "grad_norm": 0.9830688238143921,
422
+ "learning_rate": 7.556421052631579e-05,
423
+ "loss": 0.4053,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01512977696621886,
428
+ "grad_norm": 0.7812885046005249,
429
+ "learning_rate": 7.503578947368421e-05,
430
+ "loss": 0.354,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.015390635189774357,
435
+ "grad_norm": 0.7740699648857117,
436
+ "learning_rate": 7.450736842105263e-05,
437
+ "loss": 0.3165,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.015651493413329855,
442
+ "grad_norm": 0.7680047750473022,
443
+ "learning_rate": 7.397894736842105e-05,
444
+ "loss": 0.3313,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.01591235163688535,
449
+ "grad_norm": 0.8641350269317627,
450
+ "learning_rate": 7.345052631578948e-05,
451
+ "loss": 0.3395,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.01617320986044085,
456
+ "grad_norm": 1.396049976348877,
457
+ "learning_rate": 7.29221052631579e-05,
458
+ "loss": 0.3642,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.016434068083996348,
463
+ "grad_norm": 0.8436359763145447,
464
+ "learning_rate": 7.239368421052631e-05,
465
+ "loss": 0.3378,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.016694926307551844,
470
+ "grad_norm": 0.8464940786361694,
471
+ "learning_rate": 7.186526315789474e-05,
472
+ "loss": 0.3668,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.016955784531107344,
477
+ "grad_norm": 0.725881040096283,
478
+ "learning_rate": 7.133684210526316e-05,
479
+ "loss": 0.3661,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.01721664275466284,
484
+ "grad_norm": 0.6846409440040588,
485
+ "learning_rate": 7.080842105263158e-05,
486
+ "loss": 0.3638,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.01747750097821834,
491
+ "grad_norm": 0.7216416001319885,
492
+ "learning_rate": 7.028e-05,
493
+ "loss": 0.3635,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.017738359201773836,
498
+ "grad_norm": 0.6579917073249817,
499
+ "learning_rate": 6.975157894736843e-05,
500
+ "loss": 0.356,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.017999217425329332,
505
+ "grad_norm": 0.8300607204437256,
506
+ "learning_rate": 6.922315789473685e-05,
507
+ "loss": 0.362,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.018260075648884832,
512
+ "grad_norm": 0.8601360321044922,
513
+ "learning_rate": 6.869473684210527e-05,
514
+ "loss": 0.3178,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.018520933872440328,
519
+ "grad_norm": 1.229761004447937,
520
+ "learning_rate": 6.816631578947368e-05,
521
+ "loss": 0.3038,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.018781792095995828,
526
+ "grad_norm": 0.8368088603019714,
527
+ "learning_rate": 6.76378947368421e-05,
528
+ "loss": 0.3394,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.019042650319551324,
533
+ "grad_norm": 0.76348876953125,
534
+ "learning_rate": 6.710947368421052e-05,
535
+ "loss": 0.3273,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.01930350854310682,
540
+ "grad_norm": 0.8756521344184875,
541
+ "learning_rate": 6.658105263157894e-05,
542
+ "loss": 0.3483,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.01956436676666232,
547
+ "grad_norm": 1.1323158740997314,
548
+ "learning_rate": 6.605263157894737e-05,
549
+ "loss": 0.1971,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.019825224990217816,
554
+ "grad_norm": 0.7796782851219177,
555
+ "learning_rate": 6.55242105263158e-05,
556
+ "loss": 0.0966,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.020086083213773313,
561
+ "grad_norm": 0.6780573725700378,
562
+ "learning_rate": 6.499578947368422e-05,
563
+ "loss": 0.0203,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.020346941437328812,
568
+ "grad_norm": 23.24646759033203,
569
+ "learning_rate": 6.446736842105264e-05,
570
+ "loss": 0.2551,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.02060779966088431,
575
+ "grad_norm": 8.683259010314941,
576
+ "learning_rate": 6.393894736842105e-05,
577
+ "loss": 0.0885,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.02086865788443981,
582
+ "grad_norm": 0.6611659526824951,
583
+ "learning_rate": 6.341052631578947e-05,
584
+ "loss": 0.0034,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.021129516107995305,
589
+ "grad_norm": 0.1200755164027214,
590
+ "learning_rate": 6.288210526315789e-05,
591
+ "loss": 0.0004,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0213903743315508,
596
+ "grad_norm": 1.164768934249878,
597
+ "learning_rate": 6.235368421052632e-05,
598
+ "loss": 0.0091,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0216512325551063,
603
+ "grad_norm": 0.17707791924476624,
604
+ "learning_rate": 6.182526315789474e-05,
605
+ "loss": 0.0013,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.021912090778661797,
610
+ "grad_norm": 0.21379932761192322,
611
+ "learning_rate": 6.129684210526316e-05,
612
+ "loss": 0.0013,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.022172949002217297,
617
+ "grad_norm": 1.1995000839233398,
618
+ "learning_rate": 6.076842105263158e-05,
619
+ "loss": 0.0081,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.022433807225772793,
624
+ "grad_norm": 0.3035678565502167,
625
+ "learning_rate": 6.024e-05,
626
+ "loss": 0.0008,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02269466544932829,
631
+ "grad_norm": 0.014499887824058533,
632
+ "learning_rate": 5.971157894736842e-05,
633
+ "loss": 0.0002,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.02295552367288379,
638
+ "grad_norm": 1.4160069227218628,
639
+ "learning_rate": 5.9183157894736835e-05,
640
+ "loss": 0.0115,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.023216381896439285,
645
+ "grad_norm": 1.5838091373443604,
646
+ "learning_rate": 5.8654736842105267e-05,
647
+ "loss": 0.0009,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.02347724011999478,
652
+ "grad_norm": 2.2831833362579346,
653
+ "learning_rate": 5.8126315789473684e-05,
654
+ "loss": 0.0095,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.02373809834355028,
659
+ "grad_norm": 1.3635400533676147,
660
+ "learning_rate": 5.759789473684211e-05,
661
+ "loss": 0.0018,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.023998956567105777,
666
+ "grad_norm": 0.0419996902346611,
667
+ "learning_rate": 5.706947368421053e-05,
668
+ "loss": 0.0002,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.024259814790661277,
673
+ "grad_norm": 0.029113048687577248,
674
+ "learning_rate": 5.6541052631578945e-05,
675
+ "loss": 0.0003,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.024520673014216773,
680
+ "grad_norm": 1.1532421112060547,
681
+ "learning_rate": 5.601263157894736e-05,
682
+ "loss": 0.0072,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.02478153123777227,
687
+ "grad_norm": 0.03277314826846123,
688
+ "learning_rate": 5.5484210526315794e-05,
689
+ "loss": 0.0004,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.02504238946132777,
694
+ "grad_norm": 0.19502609968185425,
695
+ "learning_rate": 5.495578947368421e-05,
696
+ "loss": 0.0008,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.025303247684883266,
701
+ "grad_norm": 1.1677289009094238,
702
+ "learning_rate": 5.442736842105264e-05,
703
+ "loss": 0.0045,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.025564105908438762,
708
+ "grad_norm": 0.24581104516983032,
709
+ "learning_rate": 5.3898947368421055e-05,
710
+ "loss": 0.0016,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.02582496413199426,
715
+ "grad_norm": 2.174943685531616,
716
+ "learning_rate": 5.337052631578947e-05,
717
+ "loss": 0.0116,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.026085822355549758,
722
+ "grad_norm": 0.24700959026813507,
723
+ "learning_rate": 5.284210526315789e-05,
724
+ "loss": 0.0014,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.026085822355549758,
729
+ "eval_loss": 0.12110025435686111,
730
+ "eval_runtime": 358.6905,
731
+ "eval_samples_per_second": 4.5,
732
+ "eval_steps_per_second": 1.126,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6.564710754916762e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null