diaenra commited on
Commit
d8d30e0
1 Parent(s): b7f1184

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 sha256:836932d777997ccbc2e9e68e8ccbf5134b9d2c217603f288aaf8687fcda892cb
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b6445b64b6e50e2225b413a99da509f2cca84b79ebd0500d5b218fd7c5d76f
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24e1e86eea0277a46007796ac83611c3fa7e05fef2a2713eb206672b32a0f9e4
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c14d403920bae62816c4d23300dec984e24da168e7f756b739378603874b426
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9da0555bddb64911e8a662b656541c40f617e29d437ec53f7a43f1ae9e4c575e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca52855cae0496e166f9032b821abef474984e6bd211398e61e2e6d4464c325e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9567f2f3182e832808fd621212e0dd5e8f1a88bd24ddda3ea0d289496073738c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.13963158428668976,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.1266624445851805,
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": 3.664,
374
  "eval_steps_per_second": 1.843,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.6109411688448e+16,
405
  "train_batch_size": 2,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.12361826002597809,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.253324889170361,
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": 3.664,
374
  "eval_steps_per_second": 1.843,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.12919569347688412,
379
+ "grad_norm": 4.131649494171143,
380
+ "learning_rate": 0.00010495837546732224,
381
+ "loss": 0.0664,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.1317289423685877,
386
+ "grad_norm": 1.5766167640686035,
387
+ "learning_rate": 0.00010165339447663587,
388
+ "loss": 0.0462,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.13426219126029132,
393
+ "grad_norm": 0.21246828138828278,
394
+ "learning_rate": 9.834660552336415e-05,
395
+ "loss": 0.017,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.13679544015199493,
400
+ "grad_norm": 0.4235173761844635,
401
+ "learning_rate": 9.504162453267777e-05,
402
+ "loss": 0.0497,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.13932868904369855,
407
+ "grad_norm": 1.9022583961486816,
408
+ "learning_rate": 9.174206545276677e-05,
409
+ "loss": 0.1731,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.14186193793540217,
414
+ "grad_norm": 0.0696033164858818,
415
+ "learning_rate": 8.845153630304139e-05,
416
+ "loss": 0.0074,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.14439518682710575,
421
+ "grad_norm": 0.38361629843711853,
422
+ "learning_rate": 8.517363522881579e-05,
423
+ "loss": 0.0308,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.14692843571880937,
428
+ "grad_norm": 0.0552719309926033,
429
+ "learning_rate": 8.191194656678904e-05,
430
+ "loss": 0.0051,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.14946168461051298,
435
+ "grad_norm": 0.4546244144439697,
436
+ "learning_rate": 7.867003692562534e-05,
437
+ "loss": 0.0815,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.1519949335022166,
442
+ "grad_norm": 1.4817312955856323,
443
+ "learning_rate": 7.54514512859201e-05,
444
+ "loss": 0.0728,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.15452818239392022,
449
+ "grad_norm": 0.29890382289886475,
450
+ "learning_rate": 7.225970912381556e-05,
451
+ "loss": 0.023,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.1570614312856238,
456
+ "grad_norm": 0.16949699819087982,
457
+ "learning_rate": 6.909830056250527e-05,
458
+ "loss": 0.0116,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.15959468017732742,
463
+ "grad_norm": 0.6186251044273376,
464
+ "learning_rate": 6.59706825558357e-05,
465
+ "loss": 0.1467,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.16212792906903103,
470
+ "grad_norm": 0.24091556668281555,
471
+ "learning_rate": 6.28802751081779e-05,
472
+ "loss": 0.0387,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.16466117796073465,
477
+ "grad_norm": 0.2896825969219208,
478
+ "learning_rate": 5.983045753470308e-05,
479
+ "loss": 0.0173,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.16719442685243824,
484
+ "grad_norm": 0.030425388365983963,
485
+ "learning_rate": 5.6824564766150726e-05,
486
+ "loss": 0.0029,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.16972767574414185,
491
+ "grad_norm": 0.41832366585731506,
492
+ "learning_rate": 5.386588370213124e-05,
493
+ "loss": 0.0403,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.17226092463584547,
498
+ "grad_norm": 1.3154964447021484,
499
+ "learning_rate": 5.095764961694922e-05,
500
+ "loss": 0.2766,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.17479417352754908,
505
+ "grad_norm": 1.726725459098816,
506
+ "learning_rate": 4.810304262187852e-05,
507
+ "loss": 0.4326,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.1773274224192527,
512
+ "grad_norm": 0.03612220287322998,
513
+ "learning_rate": 4.530518418775733e-05,
514
+ "loss": 0.0035,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.1798606713109563,
519
+ "grad_norm": 0.5889875292778015,
520
+ "learning_rate": 4.256713373170564e-05,
521
+ "loss": 0.1592,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.1823939202026599,
526
+ "grad_norm": 1.068608283996582,
527
+ "learning_rate": 3.9891885271697496e-05,
528
+ "loss": 0.2189,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.18492716909436352,
533
+ "grad_norm": 0.20104023814201355,
534
+ "learning_rate": 3.7282364152646297e-05,
535
+ "loss": 0.0261,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.18746041798606713,
540
+ "grad_norm": 0.7733007073402405,
541
+ "learning_rate": 3.4741423847583134e-05,
542
+ "loss": 0.1253,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.18999366687777075,
547
+ "grad_norm": 1.527602195739746,
548
+ "learning_rate": 3.227184283742591e-05,
549
+ "loss": 0.1233,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.19252691576947434,
554
+ "grad_norm": 0.035904768854379654,
555
+ "learning_rate": 2.9876321572751144e-05,
556
+ "loss": 0.0033,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.19506016466117795,
561
+ "grad_norm": 1.0097168684005737,
562
+ "learning_rate": 2.7557479520891104e-05,
563
+ "loss": 0.1862,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.19759341355288157,
568
+ "grad_norm": 0.6764742732048035,
569
+ "learning_rate": 2.5317852301584643e-05,
570
+ "loss": 0.1849,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.20012666244458518,
575
+ "grad_norm": 0.2706001102924347,
576
+ "learning_rate": 2.315988891431412e-05,
577
+ "loss": 0.018,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.2026599113362888,
582
+ "grad_norm": 0.06733691692352295,
583
+ "learning_rate": 2.1085949060360654e-05,
584
+ "loss": 0.0067,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.2051931602279924,
589
+ "grad_norm": 0.09681247174739838,
590
+ "learning_rate": 1.9098300562505266e-05,
591
+ "loss": 0.0049,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.207726409119696,
596
+ "grad_norm": 0.052867814898490906,
597
+ "learning_rate": 1.7199116885197995e-05,
598
+ "loss": 0.0051,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.21025965801139962,
603
+ "grad_norm": 0.16184115409851074,
604
+ "learning_rate": 1.5390474757906446e-05,
605
+ "loss": 0.0129,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.21279290690310323,
610
+ "grad_norm": 1.406388759613037,
611
+ "learning_rate": 1.3674351904242611e-05,
612
+ "loss": 0.1817,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.21532615579480685,
617
+ "grad_norm": 0.08576802909374237,
618
+ "learning_rate": 1.2052624879351104e-05,
619
+ "loss": 0.007,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.21785940468651044,
624
+ "grad_norm": 1.425647497177124,
625
+ "learning_rate": 1.0527067017923654e-05,
626
+ "loss": 0.1835,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.22039265357821405,
631
+ "grad_norm": 0.06112959608435631,
632
+ "learning_rate": 9.09934649508375e-06,
633
+ "loss": 0.0061,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.22292590246991767,
638
+ "grad_norm": 0.14833374321460724,
639
+ "learning_rate": 7.771024502261526e-06,
640
+ "loss": 0.0081,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.22545915136162129,
645
+ "grad_norm": 0.27038395404815674,
646
+ "learning_rate": 6.543553540053926e-06,
647
+ "loss": 0.0451,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.2279924002533249,
652
+ "grad_norm": 0.3804483115673065,
653
+ "learning_rate": 5.418275829936537e-06,
654
+ "loss": 0.0779,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.2305256491450285,
659
+ "grad_norm": 0.04810729995369911,
660
+ "learning_rate": 4.3964218465642355e-06,
661
+ "loss": 0.0033,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.2330588980367321,
666
+ "grad_norm": 0.12134478241205215,
667
+ "learning_rate": 3.4791089722651436e-06,
668
+ "loss": 0.0067,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.23559214692843572,
673
+ "grad_norm": 1.7594163417816162,
674
+ "learning_rate": 2.667340275199426e-06,
675
+ "loss": 0.0616,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.23812539582013934,
680
+ "grad_norm": 1.7588186264038086,
681
+ "learning_rate": 1.9620034125190644e-06,
682
+ "loss": 0.2098,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.24065864471184295,
687
+ "grad_norm": 0.091976098716259,
688
+ "learning_rate": 1.3638696597277679e-06,
689
+ "loss": 0.0068,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.24319189360354654,
694
+ "grad_norm": 0.14842090010643005,
695
+ "learning_rate": 8.735930673024806e-07,
696
+ "loss": 0.0052,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.24572514249525015,
701
+ "grad_norm": 0.11459323018789291,
702
+ "learning_rate": 4.917097454988584e-07,
703
+ "loss": 0.0039,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.24825839138695377,
708
+ "grad_norm": 0.2080399990081787,
709
+ "learning_rate": 2.1863727812254653e-07,
710
+ "loss": 0.007,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.25079164027865736,
715
+ "grad_norm": 0.6975619792938232,
716
+ "learning_rate": 5.467426590739511e-08,
717
+ "loss": 0.0261,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.253324889170361,
722
+ "grad_norm": 0.08974107354879379,
723
+ "learning_rate": 0.0,
724
+ "loss": 0.0033,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.253324889170361,
729
+ "eval_loss": 0.12361826002597809,
730
+ "eval_runtime": 45.5565,
731
+ "eval_samples_per_second": 3.666,
732
+ "eval_steps_per_second": 1.844,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.32218823376896e+17,
763
  "train_batch_size": 2,
764
  "trial_name": null,
765
  "trial_params": null