prxy5605 commited on
Commit
154c90a
·
verified ·
1 Parent(s): 18ab469

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:f65d2c1333ccc970f711499a0e70e48e33077fd3ec20011b87d310ca6e212b85
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c73e9d75b0afc283dd48d81525cc60d4f7b1ed577d7cd8cc5fdd0558ca783570
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c28e4b1cd747f81a8fc628b104353eede171333580a68f66a85eb073c19887f
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2ff2bbcc888790747a3832b980c40d7934fd5945bc19a66701c0ec0744c5a2
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:594a2cfe90bccfefb5a578195b629fb6c22e3753cb17872b47078036f4522885
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51976e59481e843efd8941870fae785ef575a7aa0bbeceaf5008a9abf204dd11
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5335737b4b4d079cdec612fe6ee661ed4d29f9e0e55eb4eada44a9677240228
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.9729824066162109,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.014164305949008499,
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": 12.257,
374
  "eval_steps_per_second": 6.128,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.8634147815424e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8940727710723877,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.028328611898016998,
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": 12.257,
374
  "eval_steps_per_second": 6.128,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.014447592067988669,
379
+ "grad_norm": 0.3290400803089142,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 0.7674,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.014730878186968839,
386
+ "grad_norm": 0.422162264585495,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 0.8912,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.01501416430594901,
393
+ "grad_norm": 0.38885658979415894,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 0.8074,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01529745042492918,
400
+ "grad_norm": 0.32865843176841736,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 0.8353,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.015580736543909348,
407
+ "grad_norm": 0.29051336646080017,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 0.8639,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.01586402266288952,
414
+ "grad_norm": 0.2875722646713257,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 0.8683,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.01614730878186969,
421
+ "grad_norm": 0.26893699169158936,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 0.8548,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01643059490084986,
428
+ "grad_norm": 0.2714105248451233,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 0.8185,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01671388101983003,
435
+ "grad_norm": 0.2685096561908722,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 0.8188,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0169971671388102,
442
+ "grad_norm": 0.27536776661872864,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 0.806,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.017280453257790367,
449
+ "grad_norm": 0.26395905017852783,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 0.7769,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.017563739376770537,
456
+ "grad_norm": 0.28983741998672485,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 0.856,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.017847025495750707,
463
+ "grad_norm": 0.24493105709552765,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 0.7598,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.018130311614730877,
470
+ "grad_norm": 0.25833049416542053,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 0.8238,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.018413597733711047,
477
+ "grad_norm": 0.23423363268375397,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 0.838,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.018696883852691217,
484
+ "grad_norm": 0.24402977526187897,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 0.7818,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.018980169971671387,
491
+ "grad_norm": 0.2572822868824005,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 0.8178,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.019263456090651557,
498
+ "grad_norm": 0.24587130546569824,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 0.8298,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.019546742209631728,
505
+ "grad_norm": 0.2567668557167053,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 0.82,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.019830028328611898,
512
+ "grad_norm": 0.25297489762306213,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 0.7948,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.020113314447592068,
519
+ "grad_norm": 0.24557141959667206,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 0.8097,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.020396600566572238,
526
+ "grad_norm": 0.28915223479270935,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 0.7822,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.020679886685552408,
533
+ "grad_norm": 0.2591084837913513,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 0.7799,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.020963172804532578,
540
+ "grad_norm": 0.28063005208969116,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 0.85,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.021246458923512748,
547
+ "grad_norm": 0.3160620927810669,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 0.8925,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.02152974504249292,
554
+ "grad_norm": 0.3204711079597473,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 0.7994,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.02181303116147309,
561
+ "grad_norm": 0.31728625297546387,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 0.865,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.02209631728045326,
568
+ "grad_norm": 0.33611783385276794,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 0.8099,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.02237960339943343,
575
+ "grad_norm": 0.3129088580608368,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 0.8857,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0226628895184136,
582
+ "grad_norm": 0.3404497802257538,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 0.8408,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.02294617563739377,
589
+ "grad_norm": 0.31922274827957153,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 0.8155,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.02322946175637394,
596
+ "grad_norm": 0.4240337610244751,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 0.9036,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.02351274787535411,
603
+ "grad_norm": 0.402992308139801,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 0.9222,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.02379603399433428,
610
+ "grad_norm": 0.4444620907306671,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 0.9426,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.024079320113314446,
617
+ "grad_norm": 0.5036823153495789,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 0.8989,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.024362606232294616,
624
+ "grad_norm": 0.5430697202682495,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 1.0644,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.024645892351274786,
631
+ "grad_norm": 0.47117090225219727,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 0.8856,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.024929178470254956,
638
+ "grad_norm": 0.6156890392303467,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 0.9403,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.025212464589235126,
645
+ "grad_norm": 0.5698954463005066,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 0.8913,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.025495750708215296,
652
+ "grad_norm": 0.5107197165489197,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 0.9912,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.025779036827195467,
659
+ "grad_norm": 0.6079100966453552,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 0.9322,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.026062322946175637,
666
+ "grad_norm": 0.6184947490692139,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 0.9983,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.026345609065155807,
673
+ "grad_norm": 0.6620588302612305,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 0.9366,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.026628895184135977,
680
+ "grad_norm": 0.7128224968910217,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 1.0045,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.026912181303116147,
687
+ "grad_norm": 0.7751644253730774,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 0.8427,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.027195467422096317,
694
+ "grad_norm": 0.8441152572631836,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 0.9694,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.027478753541076487,
701
+ "grad_norm": 0.9727038145065308,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 1.0076,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.027762039660056657,
708
+ "grad_norm": 0.9640235900878906,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 0.9572,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.028045325779036828,
715
+ "grad_norm": 1.6535217761993408,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 1.0303,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.028328611898016998,
722
+ "grad_norm": 3.554504632949829,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 0.9742,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.028328611898016998,
729
+ "eval_loss": 0.8940727710723877,
730
+ "eval_runtime": 484.5241,
731
+ "eval_samples_per_second": 12.272,
732
+ "eval_steps_per_second": 6.136,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.37604737531904e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null