prxy5605 commited on
Commit
995d057
·
verified ·
1 Parent(s): 3b1e8cd

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:ac7fe9788fea5f81665ac1921995e4140f240f2385ee40191b37ad52fbe5f6d7
3
  size 479005064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46deb5f47b2e75f7005e553797a8003f2e3a5c5fd95560fdb21f5d24903afa6
3
  size 479005064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:043c102f30b6422556a03a4eab9febb92e2dc9dae69516964dda006a16969865
3
  size 958299770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e9dd8ccca39ba5c7932daded2fdbbcc9cc65f07a1f100149ba68981fa8f3f69
3
  size 958299770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:608853108661bb6ee2098f99c4ae5fae42ebd6f75ef9c7e7cf2bd8b77abfecef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f9f0802e6e749168560e6c9986384a27f97e33cdb8b8f802220fa706649da58
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5335737b4b4d079cdec612fe6ee661ed4d29f9e0e55eb4eada44a9677240228
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 5.311061859130859,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.5076142131979695,
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": 18.983,
374
  "eval_steps_per_second": 9.491,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.84541717577728e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 5.2339911460876465,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.015228426395939,
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": 18.983,
374
  "eval_steps_per_second": 9.491,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5177664974619289,
379
+ "grad_norm": 0.99236661195755,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 5.3363,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.5279187817258884,
386
+ "grad_norm": 0.48146185278892517,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 5.3438,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.5380710659898477,
393
+ "grad_norm": 0.33013349771499634,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 5.3068,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.5482233502538071,
400
+ "grad_norm": 0.37118765711784363,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 5.306,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.5583756345177665,
407
+ "grad_norm": 0.4362952411174774,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 5.2849,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.5685279187817259,
414
+ "grad_norm": 0.3819132149219513,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 5.3258,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.5786802030456852,
421
+ "grad_norm": 0.3916621804237366,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 5.3383,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.5888324873096447,
428
+ "grad_norm": 0.36510735750198364,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 5.2607,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.5989847715736041,
435
+ "grad_norm": 0.40830719470977783,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 5.3212,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.6091370558375635,
442
+ "grad_norm": 0.4307074248790741,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 5.2596,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.6192893401015228,
449
+ "grad_norm": 0.3730439245700836,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 5.2363,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.6294416243654822,
456
+ "grad_norm": 0.4428587555885315,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 5.267,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.6395939086294417,
463
+ "grad_norm": 0.41558074951171875,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 5.1866,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.649746192893401,
470
+ "grad_norm": 0.4241006672382355,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 5.1834,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.6598984771573604,
477
+ "grad_norm": 0.3360666036605835,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 5.2194,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.6700507614213198,
484
+ "grad_norm": 0.38096800446510315,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 5.2324,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.6802030456852792,
491
+ "grad_norm": 0.437884122133255,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 5.2587,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.6903553299492385,
498
+ "grad_norm": 0.48057064414024353,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 5.2374,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.700507614213198,
505
+ "grad_norm": 0.5798227787017822,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 5.1645,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.7106598984771574,
512
+ "grad_norm": 0.5949220061302185,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 5.1196,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.7208121827411168,
519
+ "grad_norm": 0.6557019948959351,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 5.1316,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.7309644670050761,
526
+ "grad_norm": 0.7752095460891724,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 5.0944,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.7411167512690355,
533
+ "grad_norm": 0.8926941156387329,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 5.3464,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.751269035532995,
540
+ "grad_norm": 0.7516569495201111,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 5.3015,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.7614213197969543,
547
+ "grad_norm": 0.6225847005844116,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 5.3173,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.7715736040609137,
554
+ "grad_norm": 0.47938278317451477,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 5.3143,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.7817258883248731,
561
+ "grad_norm": 0.3764425814151764,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 5.3017,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.7918781725888325,
568
+ "grad_norm": 0.3587036430835724,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 5.2366,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.8020304568527918,
575
+ "grad_norm": 0.3250347673892975,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 5.2564,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.8121827411167513,
582
+ "grad_norm": 0.345753937959671,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 5.2704,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.8223350253807107,
589
+ "grad_norm": 0.3820163905620575,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 5.3212,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.8324873096446701,
596
+ "grad_norm": 0.40871894359588623,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 5.2279,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.8426395939086294,
603
+ "grad_norm": 0.36811622977256775,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 5.263,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.8527918781725888,
610
+ "grad_norm": 0.3945890963077545,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 5.309,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.8629441624365483,
617
+ "grad_norm": 0.37406954169273376,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 5.2704,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.8730964467005076,
624
+ "grad_norm": 0.39915502071380615,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 5.2693,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.883248730964467,
631
+ "grad_norm": 0.4481967091560364,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 5.2332,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.8934010152284264,
638
+ "grad_norm": 0.4243590235710144,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 5.2426,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.9035532994923858,
645
+ "grad_norm": 0.46772047877311707,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 5.1668,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.9137055837563451,
652
+ "grad_norm": 0.4974723756313324,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 5.17,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.9238578680203046,
659
+ "grad_norm": 0.4955981373786926,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 5.2168,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.934010152284264,
666
+ "grad_norm": 0.4544804096221924,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 5.218,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.9441624365482234,
673
+ "grad_norm": 0.5566396117210388,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 5.1191,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.9543147208121827,
680
+ "grad_norm": 0.5591332316398621,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 5.0513,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.9644670050761421,
687
+ "grad_norm": 0.6510249972343445,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 5.0533,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.9746192893401016,
694
+ "grad_norm": 0.8038920760154724,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 5.0682,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.9847715736040609,
701
+ "grad_norm": 0.5465517640113831,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 5.3038,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.9949238578680203,
708
+ "grad_norm": 0.4467344582080841,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 5.2282,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.0050761421319796,
715
+ "grad_norm": 0.6803540587425232,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 7.978,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.015228426395939,
722
+ "grad_norm": 0.3697003424167633,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 5.1768,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.015228426395939,
729
+ "eval_loss": 5.2339911460876465,
730
+ "eval_runtime": 8.769,
731
+ "eval_samples_per_second": 18.93,
732
+ "eval_steps_per_second": 9.465,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 5.681942422880256e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null