abaddon182 commited on
Commit
9584bc4
·
verified ·
1 Parent(s): 3223a10

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 sha256:01f611b47e1fa292a95a6dc2b2b49ebbcfe71c30d680da8b7731b34fd767f914
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bc0192b6d5cdc91678a9049cc88728b7a8b4a6292f0c3e7a7818c9175d3fb40
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f8cd7892a95ebcae261c84f370d72e3b346768dad7316400ebe269d9ab0001b
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:348efcd20b7738204c0b1ba2d7cd5db15c4a5799b4eee39697da58f0d34b3a95
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ecf615a9ccff4a167b317adfdd8d5addb344ae0703ba3ddde89ff48021f0506
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c6a7ec003b64082f1f48f698b55a2c456a65dc4cabaa4268f868a574ea1993a
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": 0.7170376777648926,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.7142857142857143,
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": 10.167,
374
  "eval_steps_per_second": 2.585,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 9.739937494597632e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5829328298568726,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.4285714285714286,
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": 10.167,
374
  "eval_steps_per_second": 2.585,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.7285714285714285,
379
+ "grad_norm": 2.934380292892456,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.3184,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.7428571428571429,
386
+ "grad_norm": 2.639586925506592,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.1347,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.7571428571428571,
393
+ "grad_norm": 1.953918218612671,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.7801,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.7714285714285715,
400
+ "grad_norm": 1.699932336807251,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.8282,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.7857142857142857,
407
+ "grad_norm": 2.004262685775757,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.9015,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.8,
414
+ "grad_norm": 2.690697193145752,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.6823,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.8142857142857143,
421
+ "grad_norm": 3.4753313064575195,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.5769,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.8285714285714286,
428
+ "grad_norm": 2.999044895172119,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.6295,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.8428571428571429,
435
+ "grad_norm": 2.3511900901794434,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.6905,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.8571428571428571,
442
+ "grad_norm": 2.1141486167907715,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.603,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.8714285714285714,
449
+ "grad_norm": 1.5743640661239624,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.6214,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.8857142857142857,
456
+ "grad_norm": 1.8264353275299072,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.4951,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.9,
463
+ "grad_norm": 1.8982853889465332,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.707,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.9142857142857143,
470
+ "grad_norm": 1.6748406887054443,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.6687,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.9285714285714286,
477
+ "grad_norm": 1.6021674871444702,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.6786,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.9428571428571428,
484
+ "grad_norm": 1.7680158615112305,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.5064,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.9571428571428572,
491
+ "grad_norm": 2.2200098037719727,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.5501,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.9714285714285714,
498
+ "grad_norm": 3.1830990314483643,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.7414,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.9857142857142858,
505
+ "grad_norm": 1.3926595449447632,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.6525,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.0,
512
+ "grad_norm": 1.7112162113189697,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.5554,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.0142857142857142,
519
+ "grad_norm": 1.6711753606796265,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.7621,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.0285714285714285,
526
+ "grad_norm": 1.2971895933151245,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.5844,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.042857142857143,
533
+ "grad_norm": 1.1436983346939087,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.655,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.0571428571428572,
540
+ "grad_norm": 1.364099383354187,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.5002,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.0714285714285714,
547
+ "grad_norm": 1.8819807767868042,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.5487,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.0857142857142856,
554
+ "grad_norm": 2.837761163711548,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.5375,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.1,
561
+ "grad_norm": 1.5943292379379272,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.597,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.1142857142857143,
568
+ "grad_norm": 1.2622092962265015,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.4901,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.1285714285714286,
575
+ "grad_norm": 1.1407673358917236,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.3664,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.1428571428571428,
582
+ "grad_norm": 1.1375619173049927,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.4146,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.157142857142857,
589
+ "grad_norm": 1.943062663078308,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.3615,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.1714285714285715,
596
+ "grad_norm": 1.3213945627212524,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.2736,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.1857142857142857,
603
+ "grad_norm": 1.1036525964736938,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.2924,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.2,
610
+ "grad_norm": 1.7500133514404297,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.4516,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.2142857142857142,
617
+ "grad_norm": 1.616390585899353,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.2837,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.2285714285714286,
624
+ "grad_norm": 1.2593103647232056,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.3234,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.2428571428571429,
631
+ "grad_norm": 4.43123197555542,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.8322,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.2571428571428571,
638
+ "grad_norm": 1.5008331537246704,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.7254,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.2714285714285714,
645
+ "grad_norm": 1.5865715742111206,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.6037,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.2857142857142856,
652
+ "grad_norm": 1.4093844890594482,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.3552,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.3,
659
+ "grad_norm": 1.5126615762710571,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.4734,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.3142857142857143,
666
+ "grad_norm": 2.392476797103882,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.5126,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.3285714285714285,
673
+ "grad_norm": 3.056910276412964,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.4428,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.342857142857143,
680
+ "grad_norm": 1.5416685342788696,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.4955,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.3571428571428572,
687
+ "grad_norm": 1.495749831199646,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.3283,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.3714285714285714,
694
+ "grad_norm": 1.6940240859985352,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.3397,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.3857142857142857,
701
+ "grad_norm": 1.7251911163330078,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.3825,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.4,
708
+ "grad_norm": 1.6736160516738892,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.4352,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.4142857142857144,
715
+ "grad_norm": 1.4652953147888184,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.4346,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.4285714285714286,
722
+ "grad_norm": 1.5905109643936157,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.2946,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.4285714285714286,
729
+ "eval_loss": 0.5829328298568726,
730
+ "eval_runtime": 11.8793,
731
+ "eval_samples_per_second": 9.933,
732
+ "eval_steps_per_second": 2.525,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.9648724270579712e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null