aleegis10 commited on
Commit
c8abfe2
·
verified ·
1 Parent(s): 8a1d9a8

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 sha256:36b586c42f1307168de45947a376cb7eb28a37b0738c68db0e2341e00a4245f3
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0532cf5d2b73ce6bc98b8be93edb50b7ce9899186b88f80162a7d1d3056ccf
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5d696f85cb228cbb23556ae37f9f1270f8f3c946f68228df219061052364ded
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a548119a30483943cab4713b3f1b2385dd9d484a45abf3386038ac90cbcbca2c
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b5976a38c33447bd6f76eb1247c2bd43d2572f9d3ecc46a901cedf74cf0b8e2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c73fcd4daf7b1237297adf8906d6725e5944056550adba50c546c4825abac9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5395351648330688,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.004213897433736463,
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": 12.882,
374
  "eval_steps_per_second": 3.221,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.731132091072512e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.498549461364746,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.008427794867472926,
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": 12.882,
374
  "eval_steps_per_second": 3.221,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.004298175382411192,
379
+ "grad_norm": 0.7310632467269897,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.4223,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.004382453331085921,
386
+ "grad_norm": 0.7230385541915894,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.5037,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.00446673127976065,
393
+ "grad_norm": 0.6643477082252502,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.4662,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.00455100922843538,
400
+ "grad_norm": 0.4829084277153015,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.0906,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.004635287177110109,
407
+ "grad_norm": 0.5533672571182251,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.4786,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0047195651257848385,
414
+ "grad_norm": 0.5138788223266602,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.4468,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.004803843074459567,
421
+ "grad_norm": 0.5894024968147278,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.4552,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.004888121023134297,
428
+ "grad_norm": 0.5128427147865295,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.3466,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.004972398971809026,
435
+ "grad_norm": 0.5286391377449036,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.2589,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.005056676920483756,
442
+ "grad_norm": 0.3991178572177887,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.9813,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.005140954869158484,
449
+ "grad_norm": 0.6020731329917908,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.3982,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.005225232817833214,
456
+ "grad_norm": 0.7451138496398926,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.4749,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.005309510766507943,
463
+ "grad_norm": 0.5871690511703491,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.3155,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.005393788715182673,
470
+ "grad_norm": 0.5240890383720398,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.2181,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0054780666638574015,
477
+ "grad_norm": 0.6134968400001526,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.6436,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.005562344612532131,
484
+ "grad_norm": 0.5027713775634766,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.4021,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.00564662256120686,
491
+ "grad_norm": 0.5690268278121948,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.506,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.00573090050988159,
498
+ "grad_norm": 0.517443835735321,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.301,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.005815178458556319,
505
+ "grad_norm": 0.576786994934082,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.5677,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.005899456407231048,
512
+ "grad_norm": 0.5443838834762573,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.4369,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.005983734355905777,
519
+ "grad_norm": 0.5121707320213318,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.2935,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.006068012304580507,
526
+ "grad_norm": 0.5349838137626648,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.3198,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.006152290253255236,
533
+ "grad_norm": 0.5736881494522095,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.3988,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.006236568201929965,
540
+ "grad_norm": 0.5801308155059814,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.4923,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.006320846150604694,
547
+ "grad_norm": 0.5645437836647034,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.4074,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.006405124099279423,
554
+ "grad_norm": 0.5769533514976501,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.4748,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.006489402047954153,
561
+ "grad_norm": 0.7202831506729126,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.4046,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.006573679996628882,
568
+ "grad_norm": 0.6109544038772583,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.4079,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.006657957945303611,
575
+ "grad_norm": 0.5733642578125,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.5315,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.00674223589397834,
582
+ "grad_norm": 0.5498372912406921,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.3167,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.00682651384265307,
589
+ "grad_norm": 0.6294428706169128,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.5795,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.006910791791327799,
596
+ "grad_norm": 0.5314324498176575,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.3943,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0069950697400025285,
603
+ "grad_norm": 0.6279960870742798,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.2911,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.007079347688677257,
610
+ "grad_norm": 0.6536868810653687,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.5565,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.007163625637351987,
617
+ "grad_norm": 0.5328207015991211,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.3364,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.007247903586026716,
624
+ "grad_norm": 0.67548006772995,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.3383,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.0073321815347014456,
631
+ "grad_norm": 0.5352726578712463,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.509,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.007416459483376174,
638
+ "grad_norm": 0.6060234308242798,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.4048,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.007500737432050904,
645
+ "grad_norm": 0.6160685420036316,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.6497,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.007585015380725633,
652
+ "grad_norm": 0.6280525922775269,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.4788,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.007669293329400363,
659
+ "grad_norm": 0.6451821327209473,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.6193,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0077535712780750915,
666
+ "grad_norm": 0.5721803903579712,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.6932,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.007837849226749821,
673
+ "grad_norm": 0.6705061197280884,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.857,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.007922127175424551,
680
+ "grad_norm": 0.6482031345367432,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.6017,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.008006405124099279,
687
+ "grad_norm": 0.620942234992981,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.6512,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.008090683072774009,
694
+ "grad_norm": 0.8141463398933411,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.8437,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.008174961021448738,
701
+ "grad_norm": 0.6997731328010559,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.728,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.008259238970123468,
708
+ "grad_norm": 0.7608988285064697,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.6754,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.008343516918798196,
715
+ "grad_norm": 0.728373110294342,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.7281,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.008427794867472926,
722
+ "grad_norm": 0.8952184319496155,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.6911,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.008427794867472926,
729
+ "eval_loss": 1.498549461364746,
730
+ "eval_runtime": 1555.394,
731
+ "eval_samples_per_second": 12.849,
732
+ "eval_steps_per_second": 3.213,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5424551342676378e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null