dimasik2987 commited on
Commit
11e3e7a
·
verified ·
1 Parent(s): a306dea

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 sha256:25d722f72922ce6c4a2ff79b19fcaf9663bdad953e604ef17715ee6673f6582a
3
  size 239906848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:149f6ec4c2145ed791ada448402a9604046ac1d15b90795d22e553a3d0ac547c
3
  size 239906848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4165c69f471a80aa4aa7aa359544993a436b1d0c1632532d6cd0e6f68d315617
3
  size 122200212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6ab624d2cb3d757e8bb28f5137f8dc13c3e2db7f16ed9b46719a3bc82931a4
3
  size 122200212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5bfb8fb0cfabb058d2ff58695c7e9e80a0a3c04e66e37fc50754c4d1b8fcc41
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e28b8a8412b4ac30b72dc5f43b77bee4c83c89982038652139b7c9e2905be9a
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": 0.04788399860262871,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.03762227238525207,
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": 24.983,
374
  "eval_steps_per_second": 6.246,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3424535130931200.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.04449079558253288,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.07524454477050414,
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": 24.983,
374
  "eval_steps_per_second": 6.246,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03837471783295711,
379
+ "grad_norm": 0.3795923590660095,
380
+ "learning_rate": 7.873473684210526e-05,
381
+ "loss": 0.0368,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03912716328066215,
386
+ "grad_norm": 0.7790267467498779,
387
+ "learning_rate": 7.820631578947369e-05,
388
+ "loss": 0.1122,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0398796087283672,
393
+ "grad_norm": 0.4049144983291626,
394
+ "learning_rate": 7.76778947368421e-05,
395
+ "loss": 0.0085,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.040632054176072234,
400
+ "grad_norm": 0.07192933559417725,
401
+ "learning_rate": 7.714947368421052e-05,
402
+ "loss": 0.0009,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.04138449962377728,
407
+ "grad_norm": 0.09724583476781845,
408
+ "learning_rate": 7.662105263157896e-05,
409
+ "loss": 0.0029,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.042136945071482315,
414
+ "grad_norm": 0.17651653289794922,
415
+ "learning_rate": 7.609263157894737e-05,
416
+ "loss": 0.0082,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.04288939051918736,
421
+ "grad_norm": 0.28293490409851074,
422
+ "learning_rate": 7.556421052631579e-05,
423
+ "loss": 0.003,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0436418359668924,
428
+ "grad_norm": 1.0796512365341187,
429
+ "learning_rate": 7.503578947368421e-05,
430
+ "loss": 0.0071,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.04439428141459744,
435
+ "grad_norm": 0.5031782388687134,
436
+ "learning_rate": 7.450736842105263e-05,
437
+ "loss": 0.016,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.045146726862302484,
442
+ "grad_norm": 0.2986276149749756,
443
+ "learning_rate": 7.397894736842105e-05,
444
+ "loss": 0.0068,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.04589917231000752,
449
+ "grad_norm": 1.870119571685791,
450
+ "learning_rate": 7.345052631578948e-05,
451
+ "loss": 0.0103,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.046651617757712566,
456
+ "grad_norm": 0.13697421550750732,
457
+ "learning_rate": 7.29221052631579e-05,
458
+ "loss": 0.0025,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04740406320541761,
463
+ "grad_norm": 0.03275276720523834,
464
+ "learning_rate": 7.239368421052631e-05,
465
+ "loss": 0.0011,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.04815650865312265,
470
+ "grad_norm": 0.06320174783468246,
471
+ "learning_rate": 7.186526315789474e-05,
472
+ "loss": 0.0031,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.04890895410082769,
477
+ "grad_norm": 0.03870139271020889,
478
+ "learning_rate": 7.133684210526316e-05,
479
+ "loss": 0.0012,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.04966139954853273,
484
+ "grad_norm": 0.03169720619916916,
485
+ "learning_rate": 7.080842105263158e-05,
486
+ "loss": 0.0012,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.05041384499623777,
491
+ "grad_norm": 0.8996763825416565,
492
+ "learning_rate": 7.028e-05,
493
+ "loss": 0.0197,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.051166290443942816,
498
+ "grad_norm": 0.05753805488348007,
499
+ "learning_rate": 6.975157894736843e-05,
500
+ "loss": 0.0011,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.05191873589164785,
505
+ "grad_norm": 0.16330073773860931,
506
+ "learning_rate": 6.922315789473685e-05,
507
+ "loss": 0.0029,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0526711813393529,
512
+ "grad_norm": 0.1298224925994873,
513
+ "learning_rate": 6.869473684210527e-05,
514
+ "loss": 0.0022,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.05342362678705794,
519
+ "grad_norm": 0.04153815284371376,
520
+ "learning_rate": 6.816631578947368e-05,
521
+ "loss": 0.0014,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.05417607223476298,
526
+ "grad_norm": 0.06644019484519958,
527
+ "learning_rate": 6.76378947368421e-05,
528
+ "loss": 0.0019,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.05492851768246802,
533
+ "grad_norm": 0.12409530580043793,
534
+ "learning_rate": 6.710947368421052e-05,
535
+ "loss": 0.0017,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.05568096313017306,
540
+ "grad_norm": 0.06674883514642715,
541
+ "learning_rate": 6.658105263157894e-05,
542
+ "loss": 0.0016,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.056433408577878104,
547
+ "grad_norm": 0.09339006245136261,
548
+ "learning_rate": 6.605263157894737e-05,
549
+ "loss": 0.0011,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.05718585402558315,
554
+ "grad_norm": 0.04911891743540764,
555
+ "learning_rate": 6.55242105263158e-05,
556
+ "loss": 0.0015,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.057938299473288185,
561
+ "grad_norm": 0.3085123598575592,
562
+ "learning_rate": 6.499578947368422e-05,
563
+ "loss": 0.0096,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.05869074492099323,
568
+ "grad_norm": 0.11163350194692612,
569
+ "learning_rate": 6.446736842105264e-05,
570
+ "loss": 0.0013,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.059443190368698266,
575
+ "grad_norm": 0.06438886374235153,
576
+ "learning_rate": 6.393894736842105e-05,
577
+ "loss": 0.0011,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.06019563581640331,
582
+ "grad_norm": 0.04296841472387314,
583
+ "learning_rate": 6.341052631578947e-05,
584
+ "loss": 0.0009,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.060948081264108354,
589
+ "grad_norm": 0.03423371911048889,
590
+ "learning_rate": 6.288210526315789e-05,
591
+ "loss": 0.001,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.06170052671181339,
596
+ "grad_norm": 0.09237401187419891,
597
+ "learning_rate": 6.235368421052632e-05,
598
+ "loss": 0.001,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.062452972159518436,
603
+ "grad_norm": 0.01862478442490101,
604
+ "learning_rate": 6.182526315789474e-05,
605
+ "loss": 0.0006,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.06320541760722348,
610
+ "grad_norm": 0.06537121534347534,
611
+ "learning_rate": 6.129684210526316e-05,
612
+ "loss": 0.0016,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.06395786305492852,
617
+ "grad_norm": 0.6745563745498657,
618
+ "learning_rate": 6.076842105263158e-05,
619
+ "loss": 0.0117,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.06471030850263355,
624
+ "grad_norm": 0.16666635870933533,
625
+ "learning_rate": 6.024e-05,
626
+ "loss": 0.0062,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.0654627539503386,
631
+ "grad_norm": 0.017271826043725014,
632
+ "learning_rate": 5.971157894736842e-05,
633
+ "loss": 0.0005,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.06621519939804364,
638
+ "grad_norm": 0.390020489692688,
639
+ "learning_rate": 5.9183157894736835e-05,
640
+ "loss": 0.0117,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.06696764484574869,
645
+ "grad_norm": 0.9855097532272339,
646
+ "learning_rate": 5.8654736842105267e-05,
647
+ "loss": 0.0413,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.06772009029345373,
652
+ "grad_norm": 0.08488702028989792,
653
+ "learning_rate": 5.8126315789473684e-05,
654
+ "loss": 0.002,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.06847253574115876,
659
+ "grad_norm": 0.019529394805431366,
660
+ "learning_rate": 5.759789473684211e-05,
661
+ "loss": 0.0005,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0692249811888638,
666
+ "grad_norm": 2.2314491271972656,
667
+ "learning_rate": 5.706947368421053e-05,
668
+ "loss": 0.0078,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06997742663656885,
673
+ "grad_norm": 0.01869085058569908,
674
+ "learning_rate": 5.6541052631578945e-05,
675
+ "loss": 0.0006,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.07072987208427389,
680
+ "grad_norm": 0.9058141112327576,
681
+ "learning_rate": 5.601263157894736e-05,
682
+ "loss": 0.0469,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.07148231753197894,
687
+ "grad_norm": 0.47502413392066956,
688
+ "learning_rate": 5.5484210526315794e-05,
689
+ "loss": 0.0102,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.07223476297968397,
694
+ "grad_norm": 3.3080074787139893,
695
+ "learning_rate": 5.495578947368421e-05,
696
+ "loss": 0.0324,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.07298720842738901,
701
+ "grad_norm": 2.7681944370269775,
702
+ "learning_rate": 5.442736842105264e-05,
703
+ "loss": 0.027,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.07373965387509406,
708
+ "grad_norm": 0.02752815932035446,
709
+ "learning_rate": 5.3898947368421055e-05,
710
+ "loss": 0.001,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0744920993227991,
715
+ "grad_norm": 0.4413633346557617,
716
+ "learning_rate": 5.337052631578947e-05,
717
+ "loss": 0.0032,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.07524454477050414,
722
+ "grad_norm": 6.715440273284912,
723
+ "learning_rate": 5.284210526315789e-05,
724
+ "loss": 0.0134,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.07524454477050414,
729
+ "eval_loss": 0.04449079558253288,
730
+ "eval_runtime": 22.4889,
731
+ "eval_samples_per_second": 24.901,
732
+ "eval_steps_per_second": 6.225,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6849070261862400.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null