lesso commited on
Commit
6e37ef8
·
verified ·
1 Parent(s): 470ef43

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 sha256:4793d35af2022ddc85a6107ae4c775c13f7790f74083e80a1191b72aef785cae
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3864acfd1014d1a0df8fa27f82cfce48218ec637e63876f792c3bed4c0f1a5e
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a190363bab573cf216752e2d428a29581fc36859c54d812cd5370238a24ffb34
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a211302c27b69a338500ec852ad9e883d840459d8a2d3446d7d8c14b02d137fa
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6407a315479689bb0f1822f32b6804adda0a7a68b2f72688f91849a6c5fc2dea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1aa6e4674a8b4ab54dbebd0dd5739511029a591dcd8c88101728092c1e72f7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14c7988274ea42082ca98c4badf72b98ef1698024d0fb100dd463f8f4922415a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3388093bd4c4d331382d0016aa94fd7868af3fa4dd50305298d21879ce809e93
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.20289373397827148,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.1272264631043257,
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": 16.358,
374
  "eval_steps_per_second": 4.139,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 8419190243328000.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.1450011283159256,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.2544529262086514,
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": 16.358,
374
  "eval_steps_per_second": 4.139,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.1297709923664122,
379
+ "grad_norm": 1.5103840827941895,
380
+ "learning_rate": 7.855436842105262e-05,
381
+ "loss": 0.4364,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.13231552162849872,
386
+ "grad_norm": 1.3223518133163452,
387
+ "learning_rate": 7.802715789473684e-05,
388
+ "loss": 0.3782,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.13486005089058525,
393
+ "grad_norm": 1.2647677659988403,
394
+ "learning_rate": 7.749994736842104e-05,
395
+ "loss": 0.401,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.13740458015267176,
400
+ "grad_norm": 0.7807660102844238,
401
+ "learning_rate": 7.697273684210526e-05,
402
+ "loss": 0.1596,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.13994910941475827,
407
+ "grad_norm": 0.8354874849319458,
408
+ "learning_rate": 7.644552631578947e-05,
409
+ "loss": 0.165,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.14249363867684478,
414
+ "grad_norm": 0.6091985702514648,
415
+ "learning_rate": 7.591831578947369e-05,
416
+ "loss": 0.0962,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1450381679389313,
421
+ "grad_norm": 0.7430208325386047,
422
+ "learning_rate": 7.539110526315789e-05,
423
+ "loss": 0.1676,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.1475826972010178,
428
+ "grad_norm": 0.6381292343139648,
429
+ "learning_rate": 7.48638947368421e-05,
430
+ "loss": 0.1042,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.15012722646310434,
435
+ "grad_norm": 0.8650558590888977,
436
+ "learning_rate": 7.433668421052632e-05,
437
+ "loss": 0.1513,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.15267175572519084,
442
+ "grad_norm": 0.7318075895309448,
443
+ "learning_rate": 7.380947368421052e-05,
444
+ "loss": 0.1286,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.15521628498727735,
449
+ "grad_norm": 0.5076261758804321,
450
+ "learning_rate": 7.328226315789473e-05,
451
+ "loss": 0.0677,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.15776081424936386,
456
+ "grad_norm": 0.5992767214775085,
457
+ "learning_rate": 7.275505263157895e-05,
458
+ "loss": 0.0658,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.16030534351145037,
463
+ "grad_norm": 1.0940337181091309,
464
+ "learning_rate": 7.222784210526316e-05,
465
+ "loss": 0.1328,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.1628498727735369,
470
+ "grad_norm": 0.41800355911254883,
471
+ "learning_rate": 7.170063157894737e-05,
472
+ "loss": 0.0529,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.16539440203562342,
477
+ "grad_norm": 0.410457968711853,
478
+ "learning_rate": 7.117342105263158e-05,
479
+ "loss": 0.0427,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.16793893129770993,
484
+ "grad_norm": 0.928383469581604,
485
+ "learning_rate": 7.064621052631578e-05,
486
+ "loss": 0.0959,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.17048346055979643,
491
+ "grad_norm": 0.39881715178489685,
492
+ "learning_rate": 7.0119e-05,
493
+ "loss": 0.0456,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.17302798982188294,
498
+ "grad_norm": 0.6098618507385254,
499
+ "learning_rate": 6.959178947368421e-05,
500
+ "loss": 0.0535,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.17557251908396945,
505
+ "grad_norm": 0.6409094333648682,
506
+ "learning_rate": 6.906457894736843e-05,
507
+ "loss": 0.0848,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.178117048346056,
512
+ "grad_norm": 0.3413279950618744,
513
+ "learning_rate": 6.853736842105263e-05,
514
+ "loss": 0.0257,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.1806615776081425,
519
+ "grad_norm": 0.41074299812316895,
520
+ "learning_rate": 6.801015789473684e-05,
521
+ "loss": 0.0237,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.183206106870229,
526
+ "grad_norm": 0.6176720857620239,
527
+ "learning_rate": 6.748294736842105e-05,
528
+ "loss": 0.0628,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.18575063613231552,
533
+ "grad_norm": 0.24736110866069794,
534
+ "learning_rate": 6.695573684210526e-05,
535
+ "loss": 0.0158,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.18829516539440203,
540
+ "grad_norm": 0.8030320405960083,
541
+ "learning_rate": 6.642852631578946e-05,
542
+ "loss": 0.0547,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.19083969465648856,
547
+ "grad_norm": 0.46492913365364075,
548
+ "learning_rate": 6.590131578947369e-05,
549
+ "loss": 0.0397,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.19338422391857507,
554
+ "grad_norm": 0.570913553237915,
555
+ "learning_rate": 6.537410526315789e-05,
556
+ "loss": 0.0731,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.19592875318066158,
561
+ "grad_norm": 0.8975678086280823,
562
+ "learning_rate": 6.484689473684211e-05,
563
+ "loss": 0.1668,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.1984732824427481,
568
+ "grad_norm": 0.10023163259029388,
569
+ "learning_rate": 6.431968421052631e-05,
570
+ "loss": 0.0064,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.2010178117048346,
575
+ "grad_norm": 1.0112429857254028,
576
+ "learning_rate": 6.379247368421052e-05,
577
+ "loss": 0.1961,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.2035623409669211,
582
+ "grad_norm": 1.7674541473388672,
583
+ "learning_rate": 6.326526315789474e-05,
584
+ "loss": 0.4854,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.20610687022900764,
589
+ "grad_norm": 2.2243638038635254,
590
+ "learning_rate": 6.273805263157894e-05,
591
+ "loss": 0.515,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.20865139949109415,
596
+ "grad_norm": 1.8203999996185303,
597
+ "learning_rate": 6.221084210526315e-05,
598
+ "loss": 0.4717,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.21119592875318066,
603
+ "grad_norm": 1.2786808013916016,
604
+ "learning_rate": 6.168363157894737e-05,
605
+ "loss": 0.2411,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.21374045801526717,
610
+ "grad_norm": 1.3873907327651978,
611
+ "learning_rate": 6.115642105263159e-05,
612
+ "loss": 0.2586,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.21628498727735368,
617
+ "grad_norm": 1.169811725616455,
618
+ "learning_rate": 6.0629210526315787e-05,
619
+ "loss": 0.2859,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.21882951653944022,
624
+ "grad_norm": 1.7699614763259888,
625
+ "learning_rate": 6.0101999999999995e-05,
626
+ "loss": 0.3636,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.22137404580152673,
631
+ "grad_norm": 1.0457572937011719,
632
+ "learning_rate": 5.95747894736842e-05,
633
+ "loss": 0.2371,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.22391857506361323,
638
+ "grad_norm": 1.2649692296981812,
639
+ "learning_rate": 5.904757894736841e-05,
640
+ "loss": 0.2149,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.22646310432569974,
645
+ "grad_norm": 0.8703845143318176,
646
+ "learning_rate": 5.852036842105263e-05,
647
+ "loss": 0.1582,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.22900763358778625,
652
+ "grad_norm": 1.6556470394134521,
653
+ "learning_rate": 5.799315789473684e-05,
654
+ "loss": 0.2751,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.23155216284987276,
659
+ "grad_norm": 1.0715538263320923,
660
+ "learning_rate": 5.746594736842105e-05,
661
+ "loss": 0.2189,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.2340966921119593,
666
+ "grad_norm": 1.5337820053100586,
667
+ "learning_rate": 5.693873684210526e-05,
668
+ "loss": 0.3324,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.2366412213740458,
673
+ "grad_norm": 0.6989188194274902,
674
+ "learning_rate": 5.641152631578947e-05,
675
+ "loss": 0.0784,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.23918575063613232,
680
+ "grad_norm": 1.108068585395813,
681
+ "learning_rate": 5.588431578947368e-05,
682
+ "loss": 0.1732,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.24173027989821882,
687
+ "grad_norm": 0.7206950783729553,
688
+ "learning_rate": 5.5357105263157896e-05,
689
+ "loss": 0.08,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.24427480916030533,
694
+ "grad_norm": 1.3309029340744019,
695
+ "learning_rate": 5.482989473684211e-05,
696
+ "loss": 0.1309,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.24681933842239187,
701
+ "grad_norm": 1.4102177619934082,
702
+ "learning_rate": 5.430268421052632e-05,
703
+ "loss": 0.1174,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.24936386768447838,
708
+ "grad_norm": 0.6907632350921631,
709
+ "learning_rate": 5.377547368421053e-05,
710
+ "loss": 0.0753,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.25190839694656486,
715
+ "grad_norm": 0.5914320945739746,
716
+ "learning_rate": 5.3248263157894736e-05,
717
+ "loss": 0.0487,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.2544529262086514,
722
+ "grad_norm": 0.410552054643631,
723
+ "learning_rate": 5.2721052631578944e-05,
724
+ "loss": 0.028,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.2544529262086514,
729
+ "eval_loss": 0.1450011283159256,
730
+ "eval_runtime": 10.1692,
731
+ "eval_samples_per_second": 16.324,
732
+ "eval_steps_per_second": 4.13,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.6838380486656e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null