cilooor commited on
Commit
b3be402
·
verified ·
1 Parent(s): ffe23a3

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:ec89153c50f401cbf1ea57f9f7a920846b3055bcb8968e3b81832a19a7d43c77
3
  size 1157746040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:617397a66998dc85aaacf57470b8976595c3ab24410abfd384397d96cda45668
3
  size 1157746040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7708810515963a10bf98c097239f05734e0fb928f71f789c8887f5ffc4854a7
3
  size 588699796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d3391a74912a1055ddf55ee1d159dc9dd510b2592b6cad4f65f72f114ae299
3
  size 588699796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ee6871f676069948b6b0a62cef72e5a25947c389dfa923654692c2b7431f4c5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfb78e63dd0caace9942911d22dceeb62fc651302b1631639b026a0672f1883
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a082d9f43294c7d6cb209c323e2cc3ffb27bb22e3e2a2cc0e278db992f01a390
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ec0190ac34c757a155eb68c88baf326e3bb9c4f0972c60aacd4f72225da731
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 3.0577471256256104,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.5154639175257731,
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": 6.13,
374
  "eval_steps_per_second": 1.542,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.7165122145353728e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.017237663269043,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.0309278350515463,
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": 6.13,
374
  "eval_steps_per_second": 1.542,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5257731958762887,
379
+ "grad_norm": 0.47260257601737976,
380
+ "learning_rate": 4.4471931969052816e-05,
381
+ "loss": 2.815,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.5360824742268041,
386
+ "grad_norm": 0.43616193532943726,
387
+ "learning_rate": 4.421002777142148e-05,
388
+ "loss": 2.8286,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.5463917525773195,
393
+ "grad_norm": 0.4014701843261719,
394
+ "learning_rate": 4.3942871744008374e-05,
395
+ "loss": 2.8379,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.5567010309278351,
400
+ "grad_norm": 0.39639467000961304,
401
+ "learning_rate": 4.367053692460385e-05,
402
+ "loss": 2.9016,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.5670103092783505,
407
+ "grad_norm": 0.381337970495224,
408
+ "learning_rate": 4.3393097766828293e-05,
409
+ "loss": 2.8124,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.5773195876288659,
414
+ "grad_norm": 0.4028090536594391,
415
+ "learning_rate": 4.311063011977723e-05,
416
+ "loss": 2.9316,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.5876288659793815,
421
+ "grad_norm": 0.42682573199272156,
422
+ "learning_rate": 4.282321120728493e-05,
423
+ "loss": 2.8443,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.5979381443298969,
428
+ "grad_norm": 0.44584202766418457,
429
+ "learning_rate": 4.2530919606812216e-05,
430
+ "loss": 2.9408,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.6082474226804123,
435
+ "grad_norm": 0.433085173368454,
436
+ "learning_rate": 4.223383522796415e-05,
437
+ "loss": 2.9357,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.6185567010309279,
442
+ "grad_norm": 0.47807031869888306,
443
+ "learning_rate": 4.193203929064353e-05,
444
+ "loss": 3.019,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.6288659793814433,
449
+ "grad_norm": 0.49546951055526733,
450
+ "learning_rate": 4.16256143028462e-05,
451
+ "loss": 3.0494,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.6391752577319587,
456
+ "grad_norm": 0.5444744825363159,
457
+ "learning_rate": 4.131464403810422e-05,
458
+ "loss": 2.9607,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.6494845360824743,
463
+ "grad_norm": 0.5479447841644287,
464
+ "learning_rate": 4.099921351258292e-05,
465
+ "loss": 2.8932,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.6597938144329897,
470
+ "grad_norm": 0.5946363806724548,
471
+ "learning_rate": 4.067940896183843e-05,
472
+ "loss": 3.009,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.6701030927835051,
477
+ "grad_norm": 0.6165184378623962,
478
+ "learning_rate": 4.03553178172417e-05,
479
+ "loss": 3.0396,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.6804123711340206,
484
+ "grad_norm": 0.6681923270225525,
485
+ "learning_rate": 4.002702868207563e-05,
486
+ "loss": 3.0034,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.6907216494845361,
491
+ "grad_norm": 0.8056145906448364,
492
+ "learning_rate": 3.969463130731183e-05,
493
+ "loss": 3.2141,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.7010309278350515,
498
+ "grad_norm": 0.8759458661079407,
499
+ "learning_rate": 3.935821656707359e-05,
500
+ "loss": 3.1521,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.711340206185567,
505
+ "grad_norm": 1.1017142534255981,
506
+ "learning_rate": 3.901787643379182e-05,
507
+ "loss": 3.0594,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.7216494845360825,
512
+ "grad_norm": 1.3815213441848755,
513
+ "learning_rate": 3.867370395306068e-05,
514
+ "loss": 3.0674,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.7319587628865979,
519
+ "grad_norm": 1.998239278793335,
520
+ "learning_rate": 3.832579321819985e-05,
521
+ "loss": 3.2075,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.7422680412371134,
526
+ "grad_norm": 3.7883167266845703,
527
+ "learning_rate": 3.797423934453038e-05,
528
+ "loss": 3.6778,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.7525773195876289,
533
+ "grad_norm": 0.4328075349330902,
534
+ "learning_rate": 3.76191384433711e-05,
535
+ "loss": 2.7459,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.7628865979381443,
540
+ "grad_norm": 0.45698049664497375,
541
+ "learning_rate": 3.726058759576271e-05,
542
+ "loss": 2.9859,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.7731958762886598,
547
+ "grad_norm": 0.438618004322052,
548
+ "learning_rate": 3.689868482592684e-05,
549
+ "loss": 2.7904,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.7835051546391752,
554
+ "grad_norm": 0.5066232681274414,
555
+ "learning_rate": 3.65335290744672e-05,
556
+ "loss": 2.7998,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.7938144329896907,
561
+ "grad_norm": 0.46536940336227417,
562
+ "learning_rate": 3.616522017132017e-05,
563
+ "loss": 2.9379,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.8041237113402062,
568
+ "grad_norm": 0.42527785897254944,
569
+ "learning_rate": 3.579385880846232e-05,
570
+ "loss": 2.8253,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.8144329896907216,
575
+ "grad_norm": 0.42742273211479187,
576
+ "learning_rate": 3.5419546512382266e-05,
577
+ "loss": 2.8514,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.8247422680412371,
582
+ "grad_norm": 0.4061543047428131,
583
+ "learning_rate": 3.504238561632424e-05,
584
+ "loss": 2.9048,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.8350515463917526,
589
+ "grad_norm": 0.4020075500011444,
590
+ "learning_rate": 3.4662479232311306e-05,
591
+ "loss": 2.8037,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.845360824742268,
596
+ "grad_norm": 0.42477673292160034,
597
+ "learning_rate": 3.427993122295552e-05,
598
+ "loss": 2.978,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.8556701030927835,
603
+ "grad_norm": 0.42732954025268555,
604
+ "learning_rate": 3.389484617306292e-05,
605
+ "loss": 2.8408,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.865979381443299,
610
+ "grad_norm": 0.4450121819972992,
611
+ "learning_rate": 3.350732936104108e-05,
612
+ "loss": 2.8482,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.8762886597938144,
617
+ "grad_norm": 0.47379016876220703,
618
+ "learning_rate": 3.311748673011709e-05,
619
+ "loss": 3.1114,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.8865979381443299,
624
+ "grad_norm": 0.5056093335151672,
625
+ "learning_rate": 3.272542485937369e-05,
626
+ "loss": 2.899,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.8969072164948454,
631
+ "grad_norm": 0.5079435706138611,
632
+ "learning_rate": 3.2331250934611624e-05,
633
+ "loss": 2.9127,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.9072164948453608,
638
+ "grad_norm": 0.528727114200592,
639
+ "learning_rate": 3.1935072719046115e-05,
640
+ "loss": 2.8429,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.9175257731958762,
645
+ "grad_norm": 0.6188112497329712,
646
+ "learning_rate": 3.1536998523845494e-05,
647
+ "loss": 2.9843,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.9278350515463918,
652
+ "grad_norm": 0.6579887270927429,
653
+ "learning_rate": 3.1137137178519985e-05,
654
+ "loss": 3.0106,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.9381443298969072,
659
+ "grad_norm": 0.6882231831550598,
660
+ "learning_rate": 3.073559800116879e-05,
661
+ "loss": 2.8984,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.9484536082474226,
666
+ "grad_norm": 0.7555760145187378,
667
+ "learning_rate": 3.0332490768593675e-05,
668
+ "loss": 2.9194,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.9587628865979382,
673
+ "grad_norm": 0.8831885457038879,
674
+ "learning_rate": 2.9927925686287006e-05,
675
+ "loss": 3.1264,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.9690721649484536,
680
+ "grad_norm": 1.096960425376892,
681
+ "learning_rate": 2.952201335830275e-05,
682
+ "loss": 3.1721,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.979381443298969,
687
+ "grad_norm": 1.495573878288269,
688
+ "learning_rate": 2.9114864757018352e-05,
689
+ "loss": 3.2052,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.9896907216494846,
694
+ "grad_norm": 2.9404430389404297,
695
+ "learning_rate": 2.870659119279605e-05,
696
+ "loss": 3.5505,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.0,
701
+ "grad_norm": 0.5354474782943726,
702
+ "learning_rate": 2.8297304283551728e-05,
703
+ "loss": 2.838,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.0103092783505154,
708
+ "grad_norm": 0.4110664129257202,
709
+ "learning_rate": 2.788711592423966e-05,
710
+ "loss": 2.8808,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.0206185567010309,
715
+ "grad_norm": 0.41403889656066895,
716
+ "learning_rate": 2.7476138256261575e-05,
717
+ "loss": 2.7885,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.0309278350515463,
722
+ "grad_norm": 0.39670178294181824,
723
+ "learning_rate": 2.7064483636808313e-05,
724
+ "loss": 2.7802,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.0309278350515463,
729
+ "eval_loss": 3.017237663269043,
730
+ "eval_runtime": 26.5947,
731
+ "eval_samples_per_second": 6.129,
732
+ "eval_steps_per_second": 1.542,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.420645735215923e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null