bbytxt commited on
Commit
28a71e7
·
verified ·
1 Parent(s): 4d48800

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:c297f7022428ffef2ff8edbd160385f192496e4ea55c1b71ca5aaf299db03a3c
3
  size 1163996488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e5886c701b592ffbe8ffbbb2857042e7e5251ee15a6559f5ef1b071fd4d7d1
3
  size 1163996488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb93c58f3e8ce862ebc6c4769cb61632910565f4b88bf96e8ac5a6dfefcd0c8e
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289f8cd84b023e7b8d7b298de7203a789ddf22f04662b0d0d75c56dec758a2eb
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43e7dfd12bbe9a467024798d101723cb27865763a62a4fac815209a6e638e837
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2275c91757d31577450d039735611baaffa5ab54ceb0d90c9668f0d41713225c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79f5b4ba066d00b62be68b9f9ec9376def1ffea9a45f98d620f3198033186a6a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8538514971733093,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.05178663904712584,
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": 12.206,
374
  "eval_steps_per_second": 6.103,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.65248289783808e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.46107152104377747,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.10357327809425168,
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": 12.206,
374
  "eval_steps_per_second": 6.103,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.05282237182806836,
379
+ "grad_norm": 5.02744197845459,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 0.9884,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.05385810460901087,
386
+ "grad_norm": 2.4663264751434326,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 0.8416,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.05489383738995339,
393
+ "grad_norm": 1.7390788793563843,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 0.8593,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.055929570170895906,
400
+ "grad_norm": 1.908245325088501,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 0.732,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.05696530295183842,
407
+ "grad_norm": 2.3819148540496826,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 0.6403,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.05800103573278094,
414
+ "grad_norm": 1.402185082435608,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 0.6708,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.059036768513723456,
421
+ "grad_norm": 1.2513192892074585,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 0.6277,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.06007250129466598,
428
+ "grad_norm": 1.1688061952590942,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 0.5229,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.061108234075608496,
435
+ "grad_norm": 1.108825922012329,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 0.5915,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.06214396685655101,
442
+ "grad_norm": 1.0653815269470215,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 0.6964,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.06317969963749352,
449
+ "grad_norm": 1.674397587776184,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 0.5143,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.06421543241843604,
456
+ "grad_norm": 0.9258373379707336,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 0.4886,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.06525116519937856,
463
+ "grad_norm": 0.8897579908370972,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 0.4374,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.06628689798032107,
470
+ "grad_norm": 0.9600769281387329,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 0.4138,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.06732263076126359,
477
+ "grad_norm": 0.7555741667747498,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 0.35,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0683583635422061,
484
+ "grad_norm": 1.175614595413208,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 0.5386,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.06939409632314862,
491
+ "grad_norm": 0.9770200252532959,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 0.4241,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.07042982910409114,
498
+ "grad_norm": 1.079787254333496,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 0.4143,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.07146556188503367,
505
+ "grad_norm": 0.921312689781189,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 0.3022,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.07250129466597618,
512
+ "grad_norm": 0.830862283706665,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 0.2061,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.0735370274469187,
519
+ "grad_norm": 0.9453504085540771,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 0.283,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.07457276022786122,
526
+ "grad_norm": 1.1474324464797974,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 0.4113,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.07560849300880373,
533
+ "grad_norm": 1.249191164970398,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 0.5516,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.07664422578974625,
540
+ "grad_norm": 1.1734344959259033,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 0.5408,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.07767995857068877,
547
+ "grad_norm": 1.2528908252716064,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 0.5155,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.07871569135163128,
554
+ "grad_norm": 0.936934232711792,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 0.2787,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0797514241325738,
561
+ "grad_norm": 0.708920419216156,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 0.3339,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.08078715691351632,
568
+ "grad_norm": 1.2183189392089844,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 0.5208,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.08182288969445883,
575
+ "grad_norm": 1.1501481533050537,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 0.408,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.08285862247540135,
582
+ "grad_norm": 0.823788046836853,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 0.3337,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.08389435525634387,
589
+ "grad_norm": 0.9144259095191956,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 0.3301,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.08493008803728638,
596
+ "grad_norm": 0.7938789129257202,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 0.234,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0859658208182289,
603
+ "grad_norm": 0.8019108772277832,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 0.2253,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.08700155359917142,
610
+ "grad_norm": 0.9795384407043457,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 0.3915,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.08803728638011393,
617
+ "grad_norm": 1.122196912765503,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 0.4886,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.08907301916105645,
624
+ "grad_norm": 0.8640231490135193,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 0.2448,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.09010875194199897,
631
+ "grad_norm": 2.5851869583129883,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 0.3743,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.09114448472294148,
638
+ "grad_norm": 0.8353838920593262,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 0.3504,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.092180217503884,
645
+ "grad_norm": 1.0095223188400269,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 0.3531,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.09321595028482652,
652
+ "grad_norm": 1.6652759313583374,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 0.4985,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.09425168306576903,
659
+ "grad_norm": 1.2830318212509155,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 0.5003,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.09528741584671155,
666
+ "grad_norm": 0.8330721855163574,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 0.1982,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.09632314862765406,
673
+ "grad_norm": 0.6261827945709229,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 0.2427,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.09735888140859658,
680
+ "grad_norm": 0.6739867925643921,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 0.2442,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0983946141895391,
687
+ "grad_norm": 0.5700361132621765,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 0.09,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.09943034697048161,
694
+ "grad_norm": 1.3761444091796875,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 0.1098,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.10046607975142413,
701
+ "grad_norm": 1.5139930248260498,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 0.5464,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.10150181253236665,
708
+ "grad_norm": 0.995734691619873,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 0.4197,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.10253754531330916,
715
+ "grad_norm": 1.7123396396636963,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 0.4591,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.10357327809425168,
722
+ "grad_norm": 1.226818323135376,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 0.4507,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.10357327809425168,
729
+ "eval_loss": 0.46107152104377747,
730
+ "eval_runtime": 132.5673,
731
+ "eval_samples_per_second": 12.265,
732
+ "eval_steps_per_second": 6.133,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.330496579567616e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null