antimage88 commited on
Commit
9a68636
·
verified ·
1 Parent(s): 9ee9237

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 sha256:3849730e6b21809d48f652480fbfc06925748307b7d60880e5e0daceebfc4a4f
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30946b12847e4178479d31cee5349a7e807d64be58ea6108a9c5076c291d90ea
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbcc24e286698fa7dbab55b9fd3e4eba2e7df4afa55d90eba5da85b5220a61ef
3
  size 463916180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5868ce4e94bd924fbec234759b82d94ba2acb97ea206138e1bf70b61c5b0f536
3
  size 463916180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c7a4522cd5d583e81ddadd27c713cce3270c4b92c59f0a32dee357e4fc7faf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:832f96becf62ce3c99965ff88bf9ff1130662fdd5e44a7ab4bde242106c4bf99
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": 0.7489818334579468,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.1718213058419244,
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": 8.433,
374
  "eval_steps_per_second": 2.117,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.2648959856082944e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7277113199234009,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.3436426116838488,
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": 8.433,
374
  "eval_steps_per_second": 2.117,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.17525773195876287,
379
+ "grad_norm": 3.229118824005127,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 3.9858,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.17869415807560138,
386
+ "grad_norm": 3.4312267303466797,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 4.7884,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.18213058419243985,
393
+ "grad_norm": 2.815904140472412,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 4.1316,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.18556701030927836,
400
+ "grad_norm": 2.907052755355835,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 3.8479,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.18900343642611683,
407
+ "grad_norm": 2.1939303874969482,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.9194,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.19243986254295534,
414
+ "grad_norm": 2.066952705383301,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.71,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1958762886597938,
421
+ "grad_norm": 2.301304817199707,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.3676,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.19931271477663232,
428
+ "grad_norm": 3.6853837966918945,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.4181,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.2027491408934708,
435
+ "grad_norm": 2.3933732509613037,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.6629,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.20618556701030927,
442
+ "grad_norm": 2.310511350631714,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.5932,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.20962199312714777,
449
+ "grad_norm": 2.1882212162017822,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.5533,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.21305841924398625,
456
+ "grad_norm": 2.224141836166382,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.6595,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.21649484536082475,
463
+ "grad_norm": 2.0371408462524414,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.4645,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.21993127147766323,
470
+ "grad_norm": 1.9904556274414062,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.815,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.22336769759450173,
477
+ "grad_norm": 1.9936702251434326,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.6361,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.2268041237113402,
484
+ "grad_norm": 2.063617467880249,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.8328,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.23024054982817868,
491
+ "grad_norm": 1.778960108757019,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.5526,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.23367697594501718,
498
+ "grad_norm": 1.8721736669540405,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.2001,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.23711340206185566,
505
+ "grad_norm": 2.1718900203704834,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.6618,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.24054982817869416,
512
+ "grad_norm": 1.905144453048706,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.4549,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.24398625429553264,
519
+ "grad_norm": 2.322458028793335,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.6667,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.24742268041237114,
526
+ "grad_norm": 2.112133741378784,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.4297,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2508591065292096,
533
+ "grad_norm": 2.050910472869873,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.512,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.2542955326460481,
540
+ "grad_norm": 2.034681558609009,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.4437,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.25773195876288657,
547
+ "grad_norm": 1.984123945236206,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.5732,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.2611683848797251,
554
+ "grad_norm": 2.2462446689605713,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.6211,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.2646048109965636,
561
+ "grad_norm": 2.473987102508545,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.7826,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.26804123711340205,
568
+ "grad_norm": 2.3901572227478027,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.5584,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.27147766323024053,
575
+ "grad_norm": 2.2320001125335693,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.4833,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.27491408934707906,
582
+ "grad_norm": 2.112913131713867,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.4669,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.27835051546391754,
589
+ "grad_norm": 2.4999232292175293,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.633,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.281786941580756,
596
+ "grad_norm": 2.5236027240753174,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.6726,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.2852233676975945,
603
+ "grad_norm": 2.610469341278076,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.6783,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.28865979381443296,
610
+ "grad_norm": 2.888082504272461,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 3.0809,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.2920962199312715,
617
+ "grad_norm": 3.045673370361328,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 3.2255,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.29553264604810997,
624
+ "grad_norm": 3.2517120838165283,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 3.0398,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.29896907216494845,
631
+ "grad_norm": 2.757512331008911,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.72,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3024054982817869,
638
+ "grad_norm": 2.845644235610962,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 3.4635,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.30584192439862545,
645
+ "grad_norm": 2.752856492996216,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 3.3043,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.30927835051546393,
652
+ "grad_norm": 3.0697596073150635,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 3.2902,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.3127147766323024,
659
+ "grad_norm": 3.290828227996826,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 3.6147,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.3161512027491409,
666
+ "grad_norm": 3.5331523418426514,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 3.3361,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.31958762886597936,
673
+ "grad_norm": 3.4285762310028076,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 3.216,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3230240549828179,
680
+ "grad_norm": 3.717268466949463,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 3.1196,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.32646048109965636,
687
+ "grad_norm": 3.960413932800293,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 3.3172,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.32989690721649484,
694
+ "grad_norm": 4.5019850730896,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 3.2663,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.3333333333333333,
701
+ "grad_norm": 6.533929347991943,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 3.5329,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.33676975945017185,
708
+ "grad_norm": 5.7289719581604,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 3.3525,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.3402061855670103,
715
+ "grad_norm": 5.30385684967041,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 3.2372,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.3436426116838488,
722
+ "grad_norm": 7.11011266708374,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 4.2534,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.3436426116838488,
729
+ "eval_loss": 0.7277113199234009,
730
+ "eval_runtime": 58.1102,
731
+ "eval_samples_per_second": 8.432,
732
+ "eval_steps_per_second": 2.117,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.5413965215432704e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null