ancient41 commited on
Commit
0bb7cfa
·
verified ·
1 Parent(s): 0232f76

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:a414eb84fcc045f5d14dfcaf453ea55e3b692027408415681edf699fbfe16df4
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c787b24bd44024109d98f8aa2676ee56e0943e69cb98bfad922603d0a98efff0
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c8a4e64eaed276e4079129c897699759c3a51c1c5f01c080d8631528363f114
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd91ecc945c8019ccf633e240736cea161c3be8b97177861276864b9d9c4411
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ab6f2c757fbd3b8bae3186d5f4af4852bc053159f9526c938f9390e835c5b66
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0969d39b6a03726473076e368e61af462cb30662f72d9029993a14099772069b
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": 0.9335125088691711,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.1890359168241966,
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": 13.572,
374
  "eval_steps_per_second": 3.408,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.15499809800192e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8677875995635986,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.3780718336483932,
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": 13.572,
374
  "eval_steps_per_second": 3.408,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.19281663516068054,
379
+ "grad_norm": 21.29393196105957,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 4.0358,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.19659735349716445,
386
+ "grad_norm": 11.304404258728027,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 3.7355,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.2003780718336484,
393
+ "grad_norm": 10.158336639404297,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 3.8875,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.20415879017013233,
400
+ "grad_norm": 10.010252952575684,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 3.599,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.20793950850661624,
407
+ "grad_norm": 9.562002182006836,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.869,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.21172022684310018,
414
+ "grad_norm": 8.870956420898438,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 3.3619,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.21550094517958412,
421
+ "grad_norm": 9.110651969909668,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 3.4124,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.21928166351606806,
428
+ "grad_norm": 7.6697678565979,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 3.3309,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.22306238185255198,
435
+ "grad_norm": 8.301525115966797,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 3.1453,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.22684310018903592,
442
+ "grad_norm": 10.347870826721191,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 3.5897,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.23062381852551986,
449
+ "grad_norm": 8.439586639404297,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 3.4303,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.23440453686200377,
456
+ "grad_norm": 9.513819694519043,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 3.6442,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2381852551984877,
463
+ "grad_norm": 8.744819641113281,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 3.0771,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.24196597353497165,
470
+ "grad_norm": 11.595215797424316,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 3.8367,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.24574669187145556,
477
+ "grad_norm": 8.577299118041992,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 3.3196,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.2495274102079395,
484
+ "grad_norm": 10.696349143981934,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 3.3712,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.2533081285444234,
491
+ "grad_norm": 9.022214889526367,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 3.317,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2570888468809074,
498
+ "grad_norm": 8.869611740112305,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 3.3489,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.2608695652173913,
505
+ "grad_norm": 8.902680397033691,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 3.4113,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.2646502835538752,
512
+ "grad_norm": 8.611761093139648,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 3.4823,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.2684310018903592,
519
+ "grad_norm": 9.569182395935059,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 3.6526,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.2722117202268431,
526
+ "grad_norm": 8.870281219482422,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 3.2249,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.27599243856332706,
533
+ "grad_norm": 9.278509140014648,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 3.4246,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.27977315689981097,
540
+ "grad_norm": 8.466548919677734,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 3.4338,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.2835538752362949,
547
+ "grad_norm": 8.425887107849121,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 3.5268,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.28733459357277885,
554
+ "grad_norm": 8.38651180267334,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 3.4466,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.29111531190926276,
561
+ "grad_norm": 10.235416412353516,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 3.3785,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.2948960302457467,
568
+ "grad_norm": 10.151168823242188,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 3.4663,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.29867674858223064,
575
+ "grad_norm": 9.136027336120605,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 3.2603,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.30245746691871456,
582
+ "grad_norm": 8.610246658325195,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 3.442,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.30623818525519847,
589
+ "grad_norm": 8.665996551513672,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 3.3577,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.31001890359168244,
596
+ "grad_norm": 8.941457748413086,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 3.14,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.31379962192816635,
603
+ "grad_norm": 14.6861572265625,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 3.138,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.31758034026465026,
610
+ "grad_norm": 9.767927169799805,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 3.5077,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.32136105860113423,
617
+ "grad_norm": 9.671030044555664,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 3.3803,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.32514177693761814,
624
+ "grad_norm": 9.433391571044922,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 3.032,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.32892249527410206,
631
+ "grad_norm": 9.82751178741455,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 3.3651,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.332703213610586,
638
+ "grad_norm": 10.734698295593262,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 3.7739,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.33648393194706994,
645
+ "grad_norm": 10.445623397827148,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 3.3833,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.34026465028355385,
652
+ "grad_norm": 9.154644966125488,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 3.2674,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.3440453686200378,
659
+ "grad_norm": 12.329596519470215,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 3.5239,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.34782608695652173,
666
+ "grad_norm": 9.883134841918945,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 3.3821,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.3516068052930057,
673
+ "grad_norm": 10.114555358886719,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 3.6195,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3553875236294896,
680
+ "grad_norm": 10.966856002807617,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 3.7073,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.3591682419659735,
687
+ "grad_norm": 10.266011238098145,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 3.2225,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.3629489603024575,
694
+ "grad_norm": 10.050321578979492,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 3.3454,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.3667296786389414,
701
+ "grad_norm": 10.897590637207031,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 3.317,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.3705103969754253,
708
+ "grad_norm": 10.815629005432129,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 3.197,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.3742911153119093,
715
+ "grad_norm": 11.034646987915039,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.9457,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.3780718336483932,
722
+ "grad_norm": 13.58685302734375,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 3.2583,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.3780718336483932,
729
+ "eval_loss": 0.8677875995635986,
730
+ "eval_runtime": 32.8636,
731
+ "eval_samples_per_second": 13.571,
732
+ "eval_steps_per_second": 3.408,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.430999619600384e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null