bbytxt commited on
Commit
91c7e99
·
verified ·
1 Parent(s): e4e9a7b

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 sha256:25e201633d004ea0085590a7e01a26b5caf95b2d9f09781256f2e33b7241dc9a
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56dae72d2ded421fb1ac1d98de1a923199af8e5633a46d226d38880dda056beb
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27d095386825dc1a3a59acb2073d4ce0ef6386a9121fbeabc6b3e42b89fe24d8
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ad6d6bdcb4e7b87fa7a1337c324ef22d3e77504ff3f1a17723d2a18ce1b3e1
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5b7db10a1f179656f27aa2a3b0e003c6cb62c8fca6acfa72451d972d7f513c1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b50d39a6832c16889429256fa411c483ef50ece42179d23082831c86404ca9
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": 1.4609953165054321,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.2094240837696335,
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": 13.889,
374
  "eval_steps_per_second": 3.481,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.71020323176448e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.351357102394104,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.418848167539267,
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": 13.889,
374
  "eval_steps_per_second": 3.481,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.2136125654450262,
379
+ "grad_norm": 0.7326249480247498,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.5822,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.21780104712041884,
386
+ "grad_norm": 0.6222273111343384,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.4945,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.22198952879581152,
393
+ "grad_norm": 0.4404517710208893,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.4369,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.2261780104712042,
400
+ "grad_norm": 0.3408048450946808,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.3665,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.23036649214659685,
407
+ "grad_norm": 0.3527311384677887,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.4797,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.23455497382198953,
414
+ "grad_norm": 0.34772562980651855,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.3664,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2387434554973822,
421
+ "grad_norm": 0.31533706188201904,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.358,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.24293193717277486,
428
+ "grad_norm": 0.28406214714050293,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.3421,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.24712041884816754,
435
+ "grad_norm": 0.297507107257843,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.3763,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2513089005235602,
442
+ "grad_norm": 0.32910609245300293,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.3574,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.2554973821989529,
449
+ "grad_norm": 0.3502568304538727,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.4294,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.25968586387434556,
456
+ "grad_norm": 0.31924673914909363,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.3464,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2638743455497382,
463
+ "grad_norm": 0.3037525415420532,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.2925,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.2680628272251309,
470
+ "grad_norm": 0.30458396673202515,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.3565,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.27225130890052357,
477
+ "grad_norm": 0.31747856736183167,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.3534,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.2764397905759162,
484
+ "grad_norm": 0.3151717782020569,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.3482,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.2806282722513089,
491
+ "grad_norm": 0.3036843538284302,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.3459,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2848167539267016,
498
+ "grad_norm": 0.3110540211200714,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.3271,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.28900523560209423,
505
+ "grad_norm": 0.3139282763004303,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.3885,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.2931937172774869,
512
+ "grad_norm": 0.32266420125961304,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.3249,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.2973821989528796,
519
+ "grad_norm": 0.3372081518173218,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.2639,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.30157068062827225,
526
+ "grad_norm": 0.3430722951889038,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.3682,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.3057591623036649,
533
+ "grad_norm": 0.35122257471084595,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.3369,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3099476439790576,
540
+ "grad_norm": 0.3526090085506439,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.3259,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.31413612565445026,
547
+ "grad_norm": 0.37421196699142456,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.3914,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.3183246073298429,
554
+ "grad_norm": 0.37143388390541077,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.4003,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3225130890052356,
561
+ "grad_norm": 0.3665562868118286,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.2909,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3267015706806283,
568
+ "grad_norm": 0.3665645122528076,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.3176,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3308900523560209,
575
+ "grad_norm": 0.3843286335468292,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.2935,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.33507853403141363,
582
+ "grad_norm": 0.42542752623558044,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.3432,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.3392670157068063,
589
+ "grad_norm": 0.4372069239616394,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.3206,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.34345549738219894,
596
+ "grad_norm": 0.46938851475715637,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.3445,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.34764397905759165,
603
+ "grad_norm": 0.46583279967308044,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.3522,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.3518324607329843,
610
+ "grad_norm": 0.5285698771476746,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.3371,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.35602094240837695,
617
+ "grad_norm": 0.5335991382598877,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.3201,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.36020942408376966,
624
+ "grad_norm": 0.48621413111686707,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.2709,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3643979057591623,
631
+ "grad_norm": 0.5229520201683044,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.2761,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.36858638743455496,
638
+ "grad_norm": 0.5092804431915283,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.3199,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.37277486910994767,
645
+ "grad_norm": 0.5382634401321411,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.3828,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.3769633507853403,
652
+ "grad_norm": 0.5918077230453491,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.2516,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.381151832460733,
659
+ "grad_norm": 0.5466107726097107,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.2599,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.38534031413612563,
666
+ "grad_norm": 0.61199951171875,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.3207,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.38952879581151834,
673
+ "grad_norm": 0.6159107685089111,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.2706,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.393717277486911,
680
+ "grad_norm": 0.6025269627571106,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.3188,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.39790575916230364,
687
+ "grad_norm": 0.6132339239120483,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.233,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.40209424083769635,
694
+ "grad_norm": 0.6684319972991943,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.3105,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.406282722513089,
701
+ "grad_norm": 0.7070481181144714,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.2007,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.41047120418848165,
708
+ "grad_norm": 0.7131744027137756,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.1659,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.41465968586387436,
715
+ "grad_norm": 0.7557907104492188,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.2086,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.418848167539267,
722
+ "grad_norm": 1.0365667343139648,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.0911,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.418848167539267,
729
+ "eval_loss": 1.351357102394104,
730
+ "eval_runtime": 28.9204,
731
+ "eval_samples_per_second": 13.935,
732
+ "eval_steps_per_second": 3.492,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.342040646352896e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null