prxy5606 commited on
Commit
a8faa0e
·
verified ·
1 Parent(s): 202e6e8

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 sha256:4ce8d910db8726d31d85496ee25671bd423f80ca1887b224fa9c0ba36dc40049
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a258ec929d9218770e1f86fd3f1de785918e5b52a2e2c30529f74998eaa2aa
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e550d99da701cdcb6e6a333be295ff8f2d8c8e3642f1b88205d5396d20e49e0
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e1ef4ae464844442d88115251951165c07376033477b3523521d128587207a
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f06d6a4c9bed84c828edb6fda8551d33e80fe0e20455e2ae0cde3a44b0063947
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212dcba99a7b1ae77770a31ef6779f7d223c41005e87ffc275e7c8bccb2d4cfd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4213e97511ad1675d9fb39d8ad82aecd284027b2573bbfd2023f4cf1b821b35c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87acae65691e01ffbaf4c13ce5265904843d2731d4c47c0eed57fce5257b0710
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8939120173454285,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.7782101167315175,
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": 41.512,
374
  "eval_steps_per_second": 10.378,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.3012201900081152e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8714919686317444,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.556420233463035,
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": 41.512,
374
  "eval_steps_per_second": 10.378,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.7937743190661478,
379
+ "grad_norm": 0.3049919009208679,
380
+ "learning_rate": 8.811768194241952e-05,
381
+ "loss": 0.8823,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.8093385214007782,
386
+ "grad_norm": 0.3248423635959625,
387
+ "learning_rate": 8.755659654352599e-05,
388
+ "loss": 0.9283,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.8249027237354085,
393
+ "grad_norm": 0.3247882127761841,
394
+ "learning_rate": 8.698444304324835e-05,
395
+ "loss": 0.9166,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.8404669260700389,
400
+ "grad_norm": 0.30053266882896423,
401
+ "learning_rate": 8.640139005784924e-05,
402
+ "loss": 0.858,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.8560311284046692,
407
+ "grad_norm": 0.33963730931282043,
408
+ "learning_rate": 8.580760941571967e-05,
409
+ "loss": 0.8852,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.8715953307392996,
414
+ "grad_norm": 0.31807518005371094,
415
+ "learning_rate": 8.520327610674029e-05,
416
+ "loss": 0.9407,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.8871595330739299,
421
+ "grad_norm": 0.3238030970096588,
422
+ "learning_rate": 8.458856823071111e-05,
423
+ "loss": 0.8734,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.9027237354085603,
428
+ "grad_norm": 0.3245297372341156,
429
+ "learning_rate": 8.396366694486466e-05,
430
+ "loss": 0.8825,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.9182879377431906,
435
+ "grad_norm": 0.3227308988571167,
436
+ "learning_rate": 8.332875641047817e-05,
437
+ "loss": 0.8962,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.933852140077821,
442
+ "grad_norm": 0.3529612123966217,
443
+ "learning_rate": 8.26840237386003e-05,
444
+ "loss": 0.9568,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.9494163424124513,
449
+ "grad_norm": 0.36405235528945923,
450
+ "learning_rate": 8.202965893490878e-05,
451
+ "loss": 0.897,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.9649805447470817,
456
+ "grad_norm": 0.3392234444618225,
457
+ "learning_rate": 8.13658548437147e-05,
458
+ "loss": 0.8032,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.980544747081712,
463
+ "grad_norm": 0.3424031436443329,
464
+ "learning_rate": 8.06928070911306e-05,
465
+ "loss": 0.8227,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.9961089494163424,
470
+ "grad_norm": 0.38254794478416443,
471
+ "learning_rate": 8.001071402741842e-05,
472
+ "loss": 0.9149,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.0116731517509727,
477
+ "grad_norm": 0.9797287583351135,
478
+ "learning_rate": 7.931977666853479e-05,
479
+ "loss": 1.5691,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.027237354085603,
484
+ "grad_norm": 0.2772282361984253,
485
+ "learning_rate": 7.862019863689074e-05,
486
+ "loss": 0.8003,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.0428015564202335,
491
+ "grad_norm": 0.285792738199234,
492
+ "learning_rate": 7.791218610134323e-05,
493
+ "loss": 0.8685,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.0583657587548638,
498
+ "grad_norm": 0.32011640071868896,
499
+ "learning_rate": 7.719594771643623e-05,
500
+ "loss": 0.9241,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.0739299610894941,
505
+ "grad_norm": 0.30448997020721436,
506
+ "learning_rate": 7.647169456090925e-05,
507
+ "loss": 0.8244,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.0894941634241244,
512
+ "grad_norm": 0.3131871819496155,
513
+ "learning_rate": 7.573964007549155e-05,
514
+ "loss": 0.8418,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.105058365758755,
519
+ "grad_norm": 0.3209502398967743,
520
+ "learning_rate": 7.500000000000001e-05,
521
+ "loss": 0.7923,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.1206225680933852,
526
+ "grad_norm": 0.3268880844116211,
527
+ "learning_rate": 7.425299230975981e-05,
528
+ "loss": 0.8179,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.1361867704280155,
533
+ "grad_norm": 0.3202899396419525,
534
+ "learning_rate": 7.3498837151366e-05,
535
+ "loss": 0.8361,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.1517509727626458,
540
+ "grad_norm": 0.33722591400146484,
541
+ "learning_rate": 7.27377567778053e-05,
542
+ "loss": 0.8352,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.1673151750972763,
547
+ "grad_norm": 0.3361928164958954,
548
+ "learning_rate": 7.196997548295708e-05,
549
+ "loss": 0.8771,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.1828793774319066,
554
+ "grad_norm": 0.3383100628852844,
555
+ "learning_rate": 7.119571953549305e-05,
556
+ "loss": 0.8353,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.198443579766537,
561
+ "grad_norm": 0.342599481344223,
562
+ "learning_rate": 7.041521711219467e-05,
563
+ "loss": 0.7851,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.2140077821011672,
568
+ "grad_norm": 0.3692112863063812,
569
+ "learning_rate": 6.96286982307086e-05,
570
+ "loss": 0.7754,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.2295719844357977,
575
+ "grad_norm": 0.3618566691875458,
576
+ "learning_rate": 6.883639468175927e-05,
577
+ "loss": 0.7592,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.245136186770428,
582
+ "grad_norm": 0.3885677456855774,
583
+ "learning_rate": 6.803853996083917e-05,
584
+ "loss": 0.8669,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.2607003891050583,
589
+ "grad_norm": 0.3042435646057129,
590
+ "learning_rate": 6.72353691993967e-05,
591
+ "loss": 0.8014,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.2762645914396886,
596
+ "grad_norm": 0.2926236093044281,
597
+ "learning_rate": 6.642711909554174e-05,
598
+ "loss": 0.757,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.2918287937743191,
603
+ "grad_norm": 0.315763384103775,
604
+ "learning_rate": 6.561402784428974e-05,
605
+ "loss": 0.8411,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.3073929961089494,
610
+ "grad_norm": 0.3296045958995819,
611
+ "learning_rate": 6.479633506736446e-05,
612
+ "loss": 0.8441,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.3229571984435797,
617
+ "grad_norm": 0.3326404392719269,
618
+ "learning_rate": 6.397428174258047e-05,
619
+ "loss": 0.8187,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.3385214007782102,
624
+ "grad_norm": 0.32586634159088135,
625
+ "learning_rate": 6.314811013282574e-05,
626
+ "loss": 0.8349,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.3540856031128405,
631
+ "grad_norm": 0.33808082342147827,
632
+ "learning_rate": 6.231806371466574e-05,
633
+ "loss": 0.848,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.3696498054474708,
638
+ "grad_norm": 0.3542570173740387,
639
+ "learning_rate": 6.14843871065898e-05,
640
+ "loss": 0.8243,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.3852140077821011,
645
+ "grad_norm": 0.356636643409729,
646
+ "learning_rate": 6.064732599692079e-05,
647
+ "loss": 0.8619,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.4007782101167314,
652
+ "grad_norm": 0.3576579689979553,
653
+ "learning_rate": 5.980712707140985e-05,
654
+ "loss": 0.7986,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.416342412451362,
659
+ "grad_norm": 0.36819812655448914,
660
+ "learning_rate": 5.896403794053679e-05,
661
+ "loss": 0.8189,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.4319066147859922,
666
+ "grad_norm": 0.3678414821624756,
667
+ "learning_rate": 5.8118307066538193e-05,
668
+ "loss": 0.7622,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.4474708171206225,
673
+ "grad_norm": 0.38239309191703796,
674
+ "learning_rate": 5.7270183690184495e-05,
675
+ "loss": 0.8324,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.463035019455253,
680
+ "grad_norm": 0.36592909693717957,
681
+ "learning_rate": 5.6419917757327555e-05,
682
+ "loss": 0.7254,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.4785992217898833,
687
+ "grad_norm": 0.3889016807079315,
688
+ "learning_rate": 5.5567759845240444e-05,
689
+ "loss": 0.7894,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.4941634241245136,
694
+ "grad_norm": 0.4369194507598877,
695
+ "learning_rate": 5.4713961088771226e-05,
696
+ "loss": 0.8497,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.509727626459144,
701
+ "grad_norm": 0.3298012614250183,
702
+ "learning_rate": 5.385877310633233e-05,
703
+ "loss": 0.7555,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.5252918287937742,
708
+ "grad_norm": 0.3367776572704315,
709
+ "learning_rate": 5.300244792574742e-05,
710
+ "loss": 0.8044,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.5408560311284045,
715
+ "grad_norm": 0.3444443941116333,
716
+ "learning_rate": 5.214523790997773e-05,
717
+ "loss": 0.8537,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.556420233463035,
722
+ "grad_norm": 0.33900946378707886,
723
+ "learning_rate": 5.128739568274944e-05,
724
+ "loss": 0.7601,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.556420233463035,
729
+ "eval_loss": 0.8714919686317444,
730
+ "eval_runtime": 2.6058,
731
+ "eval_samples_per_second": 41.446,
732
+ "eval_steps_per_second": 10.362,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.581108901491507e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null