lesso commited on
Commit
330f5cc
·
verified ·
1 Parent(s): 53444e0

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 sha256:84da01682d68fc6b885d230458b56dcfb3f88928699dc88780600fe256b536c3
3
  size 34456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8895600a81c9aa3d0d5c497a7f4c267843a1aa6c53aaacebeb0ce264dbe4484b
3
  size 34456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f12395374f893550dfb4231921f3a78786efdddefb0da25f6b7b0178027a62ba
3
  size 73222
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d1e3be788bd7e51b0e486a9baa2de4820f7d8277f4f1f37ad0bcec5fedf456
3
  size 73222
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:881608cbb07448770a5e76289b30723e66073325ba435fcdc41b961bd5ae0ba0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a12a5e8afd30c780590eb2445717bbb87066db78b3c939bc2c7f33f2825041
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b10e9e3e5958a34724fb544f11514b9a1b966537b22b0051516d96de8ed7dbc2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ecea9fcf3691efde7f6f95771ff564391b1328126afca676a14949850bebad
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 11.5,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.001818909381934592,
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": 76.573,
374
  "eval_steps_per_second": 19.145,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -387,7 +745,7 @@
387
  "early_stopping_threshold": 0.0
388
  },
389
  "attributes": {
390
- "early_stopping_patience_counter": 0
391
  }
392
  },
393
  "TrainerControl": {
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2030002962432.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
  "best_metric": 11.5,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.003637818763869184,
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": 76.573,
374
  "eval_steps_per_second": 19.145,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0018552875695732839,
379
+ "grad_norm": 7.084694516379386e-05,
380
+ "learning_rate": 7.865631578947369e-05,
381
+ "loss": 23.0,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0018916657572119757,
386
+ "grad_norm": 5.6916571338661015e-05,
387
+ "learning_rate": 7.812842105263157e-05,
388
+ "loss": 23.0,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0019280439448506675,
393
+ "grad_norm": 0.00013821788888890296,
394
+ "learning_rate": 7.760052631578947e-05,
395
+ "loss": 23.0,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0019644221324893593,
400
+ "grad_norm": 0.00010073825251311064,
401
+ "learning_rate": 7.707263157894737e-05,
402
+ "loss": 23.0,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0020008003201280513,
407
+ "grad_norm": 3.989057950093411e-05,
408
+ "learning_rate": 7.654473684210527e-05,
409
+ "loss": 23.0,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.002037178507766743,
414
+ "grad_norm": 0.00011672514665406197,
415
+ "learning_rate": 7.601684210526316e-05,
416
+ "loss": 23.0,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.002073556695405435,
421
+ "grad_norm": 0.00011147064651595429,
422
+ "learning_rate": 7.548894736842105e-05,
423
+ "loss": 23.0,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.002109934883044127,
428
+ "grad_norm": 0.00014741995255462825,
429
+ "learning_rate": 7.496105263157895e-05,
430
+ "loss": 23.0,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0021463130706828185,
435
+ "grad_norm": 0.00019834299746435136,
436
+ "learning_rate": 7.443315789473683e-05,
437
+ "loss": 23.0,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0021826912583215105,
442
+ "grad_norm": 7.386082143057138e-05,
443
+ "learning_rate": 7.390526315789473e-05,
444
+ "loss": 23.0,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.002219069445960202,
449
+ "grad_norm": 0.00012008604971924797,
450
+ "learning_rate": 7.337736842105263e-05,
451
+ "loss": 23.0,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.002255447633598894,
456
+ "grad_norm": 0.00010102576925419271,
457
+ "learning_rate": 7.284947368421053e-05,
458
+ "loss": 23.0,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.002291825821237586,
463
+ "grad_norm": 8.834318578010425e-05,
464
+ "learning_rate": 7.232157894736843e-05,
465
+ "loss": 23.0,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0023282040088762777,
470
+ "grad_norm": 0.00017303289496339858,
471
+ "learning_rate": 7.179368421052631e-05,
472
+ "loss": 23.0,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0023645821965149697,
477
+ "grad_norm": 0.00021577121515292674,
478
+ "learning_rate": 7.126578947368421e-05,
479
+ "loss": 23.0,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0024009603841536613,
484
+ "grad_norm": 0.00012508737563621253,
485
+ "learning_rate": 7.07378947368421e-05,
486
+ "loss": 23.0,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0024373385717923533,
491
+ "grad_norm": 0.00021092577662784606,
492
+ "learning_rate": 7.021e-05,
493
+ "loss": 23.0,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0024737167594310453,
498
+ "grad_norm": 9.400040289619938e-05,
499
+ "learning_rate": 6.968210526315789e-05,
500
+ "loss": 23.0,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.002510094947069737,
505
+ "grad_norm": 0.00022102220100350678,
506
+ "learning_rate": 6.915421052631579e-05,
507
+ "loss": 23.0,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.002546473134708429,
512
+ "grad_norm": 0.00022005224309396,
513
+ "learning_rate": 6.862631578947369e-05,
514
+ "loss": 23.0,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.0025828513223471205,
519
+ "grad_norm": 0.0001787764485925436,
520
+ "learning_rate": 6.809842105263157e-05,
521
+ "loss": 23.0,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.0026192295099858125,
526
+ "grad_norm": 0.00012445311585906893,
527
+ "learning_rate": 6.757052631578947e-05,
528
+ "loss": 23.0,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0026556076976245045,
533
+ "grad_norm": 0.00024370021128561348,
534
+ "learning_rate": 6.704263157894737e-05,
535
+ "loss": 23.0,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.002691985885263196,
540
+ "grad_norm": 0.00029588048346340656,
541
+ "learning_rate": 6.651473684210526e-05,
542
+ "loss": 23.0,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.002728364072901888,
547
+ "grad_norm": 0.00026139113469980657,
548
+ "learning_rate": 6.598684210526317e-05,
549
+ "loss": 23.0,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0027647422605405797,
554
+ "grad_norm": 9.695452899904922e-05,
555
+ "learning_rate": 6.545894736842105e-05,
556
+ "loss": 23.0,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0028011204481792717,
561
+ "grad_norm": 0.00018712144810706377,
562
+ "learning_rate": 6.493105263157895e-05,
563
+ "loss": 23.0,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0028374986358179637,
568
+ "grad_norm": 0.00016666650481056422,
569
+ "learning_rate": 6.440315789473684e-05,
570
+ "loss": 23.0,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0028738768234566553,
575
+ "grad_norm": 0.00029639736749231815,
576
+ "learning_rate": 6.387526315789473e-05,
577
+ "loss": 23.0,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0029102550110953473,
582
+ "grad_norm": 0.00020341298659332097,
583
+ "learning_rate": 6.334736842105263e-05,
584
+ "loss": 23.0,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.002946633198734039,
589
+ "grad_norm": 0.0003866904880851507,
590
+ "learning_rate": 6.281947368421052e-05,
591
+ "loss": 23.0,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.002983011386372731,
596
+ "grad_norm": 0.0003410225035622716,
597
+ "learning_rate": 6.229157894736843e-05,
598
+ "loss": 23.0,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.003019389574011423,
603
+ "grad_norm": 0.0003634164750110358,
604
+ "learning_rate": 6.176368421052631e-05,
605
+ "loss": 23.0,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0030557677616501145,
610
+ "grad_norm": 0.00019395571143832058,
611
+ "learning_rate": 6.123578947368421e-05,
612
+ "loss": 23.0,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.0030921459492888066,
617
+ "grad_norm": 0.00014450523303821683,
618
+ "learning_rate": 6.0707894736842105e-05,
619
+ "loss": 23.0,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.003128524136927498,
624
+ "grad_norm": 0.0003423929156269878,
625
+ "learning_rate": 6.0179999999999996e-05,
626
+ "loss": 23.0,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.00316490232456619,
631
+ "grad_norm": 0.00019756775873247534,
632
+ "learning_rate": 5.965210526315789e-05,
633
+ "loss": 23.0,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.003201280512204882,
638
+ "grad_norm": 0.0003216055629309267,
639
+ "learning_rate": 5.912421052631578e-05,
640
+ "loss": 23.0,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0032376586998435737,
645
+ "grad_norm": 0.0005142286536283791,
646
+ "learning_rate": 5.8596315789473685e-05,
647
+ "loss": 23.0,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0032740368874822658,
652
+ "grad_norm": 0.00019845775386784226,
653
+ "learning_rate": 5.8068421052631583e-05,
654
+ "loss": 23.0,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.0033104150751209573,
659
+ "grad_norm": 0.0002886882866732776,
660
+ "learning_rate": 5.7540526315789475e-05,
661
+ "loss": 23.0,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0033467932627596494,
666
+ "grad_norm": 0.0003776240337174386,
667
+ "learning_rate": 5.701263157894737e-05,
668
+ "loss": 23.0,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.003383171450398341,
673
+ "grad_norm": 0.00038095013587735593,
674
+ "learning_rate": 5.648473684210526e-05,
675
+ "loss": 23.0,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.003419549638037033,
680
+ "grad_norm": 0.0003583188517950475,
681
+ "learning_rate": 5.595684210526315e-05,
682
+ "loss": 23.0,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.003455927825675725,
687
+ "grad_norm": 0.0004853124264627695,
688
+ "learning_rate": 5.5428947368421055e-05,
689
+ "loss": 23.0,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.0034923060133144166,
694
+ "grad_norm": 0.00038572377525269985,
695
+ "learning_rate": 5.490105263157895e-05,
696
+ "loss": 23.0,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0035286842009531086,
701
+ "grad_norm": 0.0003467136702965945,
702
+ "learning_rate": 5.4373157894736846e-05,
703
+ "loss": 23.0,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0035650623885918,
708
+ "grad_norm": 0.0002495538501534611,
709
+ "learning_rate": 5.384526315789474e-05,
710
+ "loss": 23.0,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.003601440576230492,
715
+ "grad_norm": 0.0007139640511013567,
716
+ "learning_rate": 5.331736842105263e-05,
717
+ "loss": 23.0,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.003637818763869184,
722
+ "grad_norm": 0.0005742310895584524,
723
+ "learning_rate": 5.278947368421052e-05,
724
+ "loss": 23.0,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.003637818763869184,
729
+ "eval_loss": 11.5,
730
+ "eval_runtime": 151.1117,
731
+ "eval_samples_per_second": 76.599,
732
+ "eval_steps_per_second": 19.151,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
745
  "early_stopping_threshold": 0.0
746
  },
747
  "attributes": {
748
+ "early_stopping_patience_counter": 1
749
  }
750
  },
751
  "TrainerControl": {
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4039906885632.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null