lesso commited on
Commit
735efb4
·
verified ·
1 Parent(s): a48acd4

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 sha256:3576f7309c28aaaf482a6f74610b3804274dff845516720593a066d83702aca9
3
  size 1157746040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e8b6c5004cadadcee7bffe3f18c4df91c7b2344bc6ac431bbabd26d942180d
3
  size 1157746040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f1a4d4ca9c5deb98730691de1a680ec22c04168253a0c0f5973e913329e1874
3
  size 588699796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a984aa5f63bf027215664d1a58bcd0e008839c332182dfc76555c78dd01792
3
  size 588699796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1990208685a3753e0c687b5a22be726c777b0465fdd9f344c698e78745f7774f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d4f82194923c4e839c5b924f9c84d17ba32c8dc232adb7a3f482821b860cb9e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff52bfbef9cf63f1b4a99aeb499cfc330b3f7bf178a825c21249094bbf544e39
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a046f3bc9d619a7e62601f3cf33ff02f6ad189db5b564eab88c1bb00e13b059d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6652013063430786,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.05042864346949067,
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": 4.111,
374
  "eval_steps_per_second": 1.033,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 4.357300236897485e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6350612640380859,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.10085728693898134,
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": 4.111,
374
  "eval_steps_per_second": 1.033,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.05143721633888049,
379
+ "grad_norm": 0.7430902123451233,
380
+ "learning_rate": 7.944052631578947e-05,
381
+ "loss": 0.4593,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.052445789208270296,
386
+ "grad_norm": 0.6915680170059204,
387
+ "learning_rate": 7.890736842105263e-05,
388
+ "loss": 0.6674,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.05345436207766011,
393
+ "grad_norm": 0.6954211592674255,
394
+ "learning_rate": 7.837421052631579e-05,
395
+ "loss": 0.7528,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.05446293494704992,
400
+ "grad_norm": 0.6784757971763611,
401
+ "learning_rate": 7.784105263157893e-05,
402
+ "loss": 0.617,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.05547150781643974,
407
+ "grad_norm": 0.750968337059021,
408
+ "learning_rate": 7.730789473684211e-05,
409
+ "loss": 0.6296,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.05648008068582955,
414
+ "grad_norm": 0.6823384761810303,
415
+ "learning_rate": 7.677473684210526e-05,
416
+ "loss": 0.6229,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.057488653555219364,
421
+ "grad_norm": 0.9757019877433777,
422
+ "learning_rate": 7.624157894736842e-05,
423
+ "loss": 0.6533,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.05849722642460918,
428
+ "grad_norm": 0.9269747734069824,
429
+ "learning_rate": 7.570842105263158e-05,
430
+ "loss": 0.5794,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.05950579929399899,
435
+ "grad_norm": 0.6206308007240295,
436
+ "learning_rate": 7.517526315789474e-05,
437
+ "loss": 0.5007,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.060514372163388806,
442
+ "grad_norm": 0.6674503684043884,
443
+ "learning_rate": 7.464210526315789e-05,
444
+ "loss": 0.4885,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.061522945032778616,
449
+ "grad_norm": 0.7698457837104797,
450
+ "learning_rate": 7.410894736842106e-05,
451
+ "loss": 0.773,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.06253151790216843,
456
+ "grad_norm": 0.7389516234397888,
457
+ "learning_rate": 7.35757894736842e-05,
458
+ "loss": 0.5738,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.06354009077155824,
463
+ "grad_norm": 0.770261287689209,
464
+ "learning_rate": 7.304263157894737e-05,
465
+ "loss": 0.6907,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.06454866364094806,
470
+ "grad_norm": 0.7029135227203369,
471
+ "learning_rate": 7.250947368421053e-05,
472
+ "loss": 0.6071,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.06555723651033787,
477
+ "grad_norm": 0.7364175319671631,
478
+ "learning_rate": 7.197631578947368e-05,
479
+ "loss": 0.6433,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.06656580937972768,
484
+ "grad_norm": 0.6604887247085571,
485
+ "learning_rate": 7.144315789473684e-05,
486
+ "loss": 0.5419,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.06757438224911749,
491
+ "grad_norm": 0.6892684102058411,
492
+ "learning_rate": 7.091e-05,
493
+ "loss": 0.6809,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.06858295511850732,
498
+ "grad_norm": 0.6906418204307556,
499
+ "learning_rate": 7.037684210526316e-05,
500
+ "loss": 0.5438,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.06959152798789713,
505
+ "grad_norm": 0.7817425727844238,
506
+ "learning_rate": 6.984368421052632e-05,
507
+ "loss": 0.7386,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.07060010085728693,
512
+ "grad_norm": 0.5860413312911987,
513
+ "learning_rate": 6.931052631578947e-05,
514
+ "loss": 0.4939,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.07160867372667676,
519
+ "grad_norm": 0.6654998660087585,
520
+ "learning_rate": 6.877736842105263e-05,
521
+ "loss": 0.5478,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.07261724659606657,
526
+ "grad_norm": 0.7202038168907166,
527
+ "learning_rate": 6.824421052631579e-05,
528
+ "loss": 0.5561,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.07362581946545638,
533
+ "grad_norm": 0.7074757218360901,
534
+ "learning_rate": 6.771105263157895e-05,
535
+ "loss": 0.5294,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.07463439233484619,
540
+ "grad_norm": 0.7609388828277588,
541
+ "learning_rate": 6.71778947368421e-05,
542
+ "loss": 0.6816,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.07564296520423601,
547
+ "grad_norm": 0.7042875289916992,
548
+ "learning_rate": 6.664473684210527e-05,
549
+ "loss": 0.6686,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.07665153807362582,
554
+ "grad_norm": 0.697859525680542,
555
+ "learning_rate": 6.611157894736842e-05,
556
+ "loss": 0.5751,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.07766011094301563,
561
+ "grad_norm": 0.7064348459243774,
562
+ "learning_rate": 6.557842105263158e-05,
563
+ "loss": 0.5744,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.07866868381240545,
568
+ "grad_norm": 0.5865401029586792,
569
+ "learning_rate": 6.504526315789474e-05,
570
+ "loss": 0.5026,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.07967725668179526,
575
+ "grad_norm": 0.7729213237762451,
576
+ "learning_rate": 6.451210526315789e-05,
577
+ "loss": 0.5335,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.08068582955118507,
582
+ "grad_norm": 0.791968584060669,
583
+ "learning_rate": 6.397894736842105e-05,
584
+ "loss": 0.6654,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.08169440242057488,
589
+ "grad_norm": 0.8126956820487976,
590
+ "learning_rate": 6.344578947368421e-05,
591
+ "loss": 0.6091,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0827029752899647,
596
+ "grad_norm": 0.7012320160865784,
597
+ "learning_rate": 6.291263157894737e-05,
598
+ "loss": 0.587,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.08371154815935451,
603
+ "grad_norm": 0.7842673659324646,
604
+ "learning_rate": 6.237947368421053e-05,
605
+ "loss": 0.6438,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.08472012102874432,
610
+ "grad_norm": 0.7788791656494141,
611
+ "learning_rate": 6.184631578947368e-05,
612
+ "loss": 0.6173,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.08572869389813415,
617
+ "grad_norm": 0.7247044444084167,
618
+ "learning_rate": 6.131315789473684e-05,
619
+ "loss": 0.6625,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.08673726676752395,
624
+ "grad_norm": 0.7117682099342346,
625
+ "learning_rate": 6.078e-05,
626
+ "loss": 0.6324,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.08774583963691376,
631
+ "grad_norm": 0.7648577094078064,
632
+ "learning_rate": 6.024684210526315e-05,
633
+ "loss": 0.6915,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.08875441250630359,
638
+ "grad_norm": 0.8128008842468262,
639
+ "learning_rate": 5.9713684210526305e-05,
640
+ "loss": 0.6515,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0897629853756934,
645
+ "grad_norm": 0.8586528301239014,
646
+ "learning_rate": 5.918052631578947e-05,
647
+ "loss": 0.7476,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0907715582450832,
652
+ "grad_norm": 0.9298937916755676,
653
+ "learning_rate": 5.8647368421052634e-05,
654
+ "loss": 0.792,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.09178013111447302,
659
+ "grad_norm": 0.8197916746139526,
660
+ "learning_rate": 5.811421052631579e-05,
661
+ "loss": 0.6175,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.09278870398386284,
666
+ "grad_norm": 0.7706024050712585,
667
+ "learning_rate": 5.758105263157894e-05,
668
+ "loss": 0.719,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.09379727685325265,
673
+ "grad_norm": 0.853099524974823,
674
+ "learning_rate": 5.70478947368421e-05,
675
+ "loss": 0.6546,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.09480584972264246,
680
+ "grad_norm": 0.796420156955719,
681
+ "learning_rate": 5.6514736842105256e-05,
682
+ "loss": 0.6689,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.09581442259203228,
687
+ "grad_norm": 0.7574595212936401,
688
+ "learning_rate": 5.5981578947368424e-05,
689
+ "loss": 0.5644,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.09682299546142209,
694
+ "grad_norm": 0.9858140349388123,
695
+ "learning_rate": 5.544842105263158e-05,
696
+ "loss": 0.83,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0978315683308119,
701
+ "grad_norm": 0.9185313582420349,
702
+ "learning_rate": 5.491526315789474e-05,
703
+ "loss": 0.7675,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.09884014120020171,
708
+ "grad_norm": 0.9572092890739441,
709
+ "learning_rate": 5.438210526315789e-05,
710
+ "loss": 0.7159,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.09984871406959153,
715
+ "grad_norm": 1.0749398469924927,
716
+ "learning_rate": 5.384894736842105e-05,
717
+ "loss": 0.8607,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.10085728693898134,
722
+ "grad_norm": 1.266366958618164,
723
+ "learning_rate": 5.331578947368421e-05,
724
+ "loss": 0.8676,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.10085728693898134,
729
+ "eval_loss": 0.6350612640380859,
730
+ "eval_runtime": 101.2691,
731
+ "eval_samples_per_second": 4.128,
732
+ "eval_steps_per_second": 1.037,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 8.648580773235917e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null