0x1202 commited on
Commit
273f471
·
verified ·
1 Parent(s): c9f3e88

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:aae8f49846f919ec30159e71bec53b933f99035988eaf9efdd7ceb5816c2a854
3
  size 838906392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deaf17e4eb73a48c86f668cee3d16b2d2e4ac920e80c2d9bc49537a366c88a60
3
  size 838906392
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f61849be6a16e57b016ab0efcecfd9bd7bcc336bf1de084521bd5ff115e8e2a
3
  size 426360596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e30d01525465b0362fc4fd5dcf71a4fddf5ecfdaf7c823345702539f897c82
3
  size 426360596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93231d61f5533741882309e30ebe094f052450bb948486852c1c6838366b6cbe
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5e85bab9429dbcd6c01fa98ef85afd8b65fc9d0c7f91c9bcd7e6deac3dcc97
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": 0.005853595212101936,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.08064516129032258,
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": 9.588,
374
  "eval_steps_per_second": 2.397,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.27296891518976e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.0026835536118596792,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.16129032258064516,
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": 9.588,
374
  "eval_steps_per_second": 2.397,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.08225806451612903,
379
+ "grad_norm": 0.23463483154773712,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.0046,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.08387096774193549,
386
+ "grad_norm": 0.17040041089057922,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.0168,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.08548387096774193,
393
+ "grad_norm": 0.5608404278755188,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.0148,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.08709677419354839,
400
+ "grad_norm": 0.6543734669685364,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.0197,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.08870967741935484,
407
+ "grad_norm": 0.3093203604221344,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.0463,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.09032258064516129,
414
+ "grad_norm": 0.10087056457996368,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.0044,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.09193548387096774,
421
+ "grad_norm": 0.267266184091568,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.0129,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0935483870967742,
428
+ "grad_norm": 0.31064850091934204,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.0484,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.09516129032258064,
435
+ "grad_norm": 0.2512148916721344,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.0344,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0967741935483871,
442
+ "grad_norm": 1.4665775299072266,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.0336,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.09838709677419355,
449
+ "grad_norm": 0.33774101734161377,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.0152,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.1,
456
+ "grad_norm": 0.22360168397426605,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.0147,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.10161290322580645,
463
+ "grad_norm": 0.2551698684692383,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.0167,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.1032258064516129,
470
+ "grad_norm": 0.4298221170902252,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.0314,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.10483870967741936,
477
+ "grad_norm": 0.292525053024292,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.0198,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.1064516129032258,
484
+ "grad_norm": 0.3462181091308594,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.0245,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.10806451612903226,
491
+ "grad_norm": 0.45068007707595825,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0589,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.10967741935483871,
498
+ "grad_norm": 0.7323125004768372,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.0683,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.11129032258064517,
505
+ "grad_norm": 0.07402742654085159,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.0051,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.11290322580645161,
512
+ "grad_norm": 0.3788389265537262,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.0351,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.11451612903225807,
519
+ "grad_norm": 0.25281745195388794,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.0136,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.11612903225806452,
526
+ "grad_norm": 0.1284315288066864,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.0052,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.11774193548387096,
533
+ "grad_norm": 0.41634923219680786,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.0169,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.11935483870967742,
540
+ "grad_norm": 0.2020844668149948,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.0286,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.12096774193548387,
547
+ "grad_norm": 0.4097118377685547,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.008,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.12258064516129032,
554
+ "grad_norm": 0.11246518790721893,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.0045,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.12419354838709677,
561
+ "grad_norm": 0.45286452770233154,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.0197,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.12580645161290321,
568
+ "grad_norm": 0.6798192262649536,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.0305,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.12741935483870967,
575
+ "grad_norm": 0.9303900599479675,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0721,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.12903225806451613,
582
+ "grad_norm": 0.7090916633605957,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.0278,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.13064516129032258,
589
+ "grad_norm": 0.7841101884841919,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.0387,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.13225806451612904,
596
+ "grad_norm": 0.03361155465245247,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.0017,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.1338709677419355,
603
+ "grad_norm": 0.1516152322292328,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.0035,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.13548387096774195,
610
+ "grad_norm": 0.5641607046127319,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.0269,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.13709677419354838,
617
+ "grad_norm": 1.0881990194320679,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.0965,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.13870967741935483,
624
+ "grad_norm": 0.9148401021957397,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0939,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.1403225806451613,
631
+ "grad_norm": 0.5051007866859436,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0244,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.14193548387096774,
638
+ "grad_norm": 0.33277037739753723,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.0206,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.1435483870967742,
645
+ "grad_norm": 0.05165182799100876,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.0026,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.14516129032258066,
652
+ "grad_norm": 0.8755428194999695,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.0526,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.14677419354838708,
659
+ "grad_norm": 0.4138418734073639,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0187,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.14838709677419354,
666
+ "grad_norm": 1.0819470882415771,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.0331,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.15,
673
+ "grad_norm": 0.10007546097040176,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.0043,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.15161290322580645,
680
+ "grad_norm": 0.0890575647354126,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0046,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.1532258064516129,
687
+ "grad_norm": 0.9824152588844299,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0265,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.15483870967741936,
694
+ "grad_norm": 0.061418917030096054,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.003,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.15645161290322582,
701
+ "grad_norm": 0.07597987353801727,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0037,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.15806451612903225,
708
+ "grad_norm": 1.8876456022262573,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0701,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.1596774193548387,
715
+ "grad_norm": 0.22971439361572266,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.0046,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.16129032258064516,
722
+ "grad_norm": 0.6317911148071289,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0164,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.16129032258064516,
729
+ "eval_loss": 0.0026835536118596792,
730
+ "eval_runtime": 109.2889,
731
+ "eval_samples_per_second": 9.553,
732
+ "eval_steps_per_second": 2.388,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.54593783037952e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null