bbytxt commited on
Commit
1b65c78
·
verified ·
1 Parent(s): 704b4ea

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:ee4d9edc95d45a2c74c8819c7fd0cf39b22515aeb27461670ea386ac77aa35ca
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3949dd076fd0aeeec958399ed4b5676bf638e110d8016c582f03f4d18888e6
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55ca144fefb3a11c075ce9c6a62ad8bddbe6aff0ee885b76d8b2765f298eaff8
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7026000ba83a3be51da75be4ece6f7828b68489b4e491b35943b719917b25d9
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:c678e778033e0c65217623c1c912a58a5ee49880e1ecafd5a47cf1a17dc24e5e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce785178bd7396d9910aa19eddfa2ed8c2271b3c81591ffa85674baac189a66d
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": 2.397188186645508,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.2053388090349076,
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": 9.034,
374
  "eval_steps_per_second": 2.269,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.0710446409095578e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.362854480743408,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.4106776180698152,
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": 9.034,
374
  "eval_steps_per_second": 2.269,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.20944558521560575,
379
+ "grad_norm": 0.5794761180877686,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.4273,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.2135523613963039,
386
+ "grad_norm": 0.39014923572540283,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.4078,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.21765913757700206,
393
+ "grad_norm": 0.3453044891357422,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.4478,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.22176591375770022,
400
+ "grad_norm": 0.3471531867980957,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.2902,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.22587268993839835,
407
+ "grad_norm": 0.28497612476348877,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.3663,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.2299794661190965,
414
+ "grad_norm": 0.27953407168388367,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.4229,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.23408624229979466,
421
+ "grad_norm": 0.2591160237789154,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.3187,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.23819301848049282,
428
+ "grad_norm": 0.2484808713197708,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.3382,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.24229979466119098,
435
+ "grad_norm": 0.2553481161594391,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.3109,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2464065708418891,
442
+ "grad_norm": 0.26387447118759155,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.405,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.25051334702258726,
449
+ "grad_norm": 0.24189330637454987,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.3397,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.2546201232032854,
456
+ "grad_norm": 0.2473788559436798,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.3868,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2587268993839836,
463
+ "grad_norm": 0.2503631114959717,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.2831,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.26283367556468173,
470
+ "grad_norm": 0.24004723131656647,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.3741,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.2669404517453799,
477
+ "grad_norm": 0.2441152185201645,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.3254,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.27104722792607805,
484
+ "grad_norm": 0.2660163938999176,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.2818,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.2751540041067762,
491
+ "grad_norm": 0.254585862159729,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.2796,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2792607802874743,
498
+ "grad_norm": 0.2543337941169739,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.2795,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.28336755646817247,
505
+ "grad_norm": 0.2710717022418976,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.2723,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.2874743326488706,
512
+ "grad_norm": 0.2980392873287201,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.3951,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.2915811088295688,
519
+ "grad_norm": 0.2811497449874878,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.2955,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.29568788501026694,
526
+ "grad_norm": 0.27456995844841003,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.3536,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2997946611909651,
533
+ "grad_norm": 0.27245110273361206,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.3628,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.30390143737166325,
540
+ "grad_norm": 0.28173360228538513,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.3959,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.3080082135523614,
547
+ "grad_norm": 0.288441002368927,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.3812,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.31211498973305957,
554
+ "grad_norm": 0.293016254901886,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.3411,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3162217659137577,
561
+ "grad_norm": 0.2989495098590851,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.3633,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3203285420944558,
568
+ "grad_norm": 0.2963714897632599,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.3702,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.324435318275154,
575
+ "grad_norm": 0.32292625308036804,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.3771,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.32854209445585214,
582
+ "grad_norm": 0.3097062408924103,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.3655,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.3326488706365503,
589
+ "grad_norm": 0.3158957064151764,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.3183,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.33675564681724846,
596
+ "grad_norm": 0.32411056756973267,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.3707,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.3408624229979466,
603
+ "grad_norm": 0.32971060276031494,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.3214,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.34496919917864477,
610
+ "grad_norm": 0.3237762451171875,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.2978,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.3490759753593429,
617
+ "grad_norm": 0.30338796973228455,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.3783,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.3531827515400411,
624
+ "grad_norm": 0.33562251925468445,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.4431,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.35728952772073924,
631
+ "grad_norm": 0.3178534209728241,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.4342,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3613963039014374,
638
+ "grad_norm": 0.32157230377197266,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.2591,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.3655030800821355,
645
+ "grad_norm": 0.343168705701828,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.335,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.36960985626283366,
652
+ "grad_norm": 0.34791627526283264,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.3692,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.3737166324435318,
659
+ "grad_norm": 0.3411727249622345,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.2979,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.37782340862423,
666
+ "grad_norm": 0.3406916856765747,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.4069,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.38193018480492813,
673
+ "grad_norm": 0.34638410806655884,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.2895,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3860369609856263,
680
+ "grad_norm": 0.34439417719841003,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.3482,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.39014373716632444,
687
+ "grad_norm": 0.3640625774860382,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.3401,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.3942505133470226,
694
+ "grad_norm": 0.376729816198349,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.4102,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.39835728952772076,
701
+ "grad_norm": 0.3897058665752411,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.4631,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.4024640657084189,
708
+ "grad_norm": 0.36534807085990906,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.3228,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.406570841889117,
715
+ "grad_norm": 0.42786386609077454,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.3745,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.4106776180698152,
722
+ "grad_norm": 0.4445665180683136,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.3634,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.4106776180698152,
729
+ "eval_loss": 2.362854480743408,
730
+ "eval_runtime": 45.2342,
731
+ "eval_samples_per_second": 9.064,
732
+ "eval_steps_per_second": 2.277,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.127004146031657e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null