prxy5608 commited on
Commit
2dd4ab9
·
verified ·
1 Parent(s): 071ddbb

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:be06e6848a228ae170456d16345bf3e282d9484c275f1f03e0f7a9efe9d70d9c
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dc0803f239ff2deb3e8bb9822e446198087d63452c49e07aa48f7afb834dc5a
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b441757eb4037b83c864cf144a035fffa3ae14c0f9bcdf893961346fb60c2650
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3085bc481fe797076dbef1e65fb08d552de3be8cda794f7e9e07918327e079a
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8dfc992e8e2897a67e5d6a2e301733a55fda10f6bff17c193cc5906f6b72e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81edb2912a9f7207db2fc684d22dbcd71e5ceb0f3c5fb6ae62aad188793672f
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": 1.222476840019226,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.3184713375796178,
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": 11.534,
374
  "eval_steps_per_second": 5.789,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.759883743002624e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9518508911132812,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.6369426751592356,
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": 11.534,
374
  "eval_steps_per_second": 5.789,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3248407643312102,
379
+ "grad_norm": 9.273707389831543,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 4.2956,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.33121019108280253,
386
+ "grad_norm": 8.437464714050293,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 4.1599,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.3375796178343949,
393
+ "grad_norm": 8.612960815429688,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 4.1081,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.34394904458598724,
400
+ "grad_norm": 11.117528915405273,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 4.3433,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.3503184713375796,
407
+ "grad_norm": 10.288155555725098,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 4.5473,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.35668789808917195,
414
+ "grad_norm": 10.283195495605469,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 4.3766,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.3630573248407643,
421
+ "grad_norm": 11.619425773620605,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 4.5981,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.36942675159235666,
428
+ "grad_norm": 12.74874210357666,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 4.98,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.37579617834394907,
435
+ "grad_norm": 11.369183540344238,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 3.341,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.3821656050955414,
442
+ "grad_norm": 13.796540260314941,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 4.6845,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.3885350318471338,
449
+ "grad_norm": 13.996506690979004,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 4.5114,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.39490445859872614,
456
+ "grad_norm": 16.951208114624023,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 5.0782,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.4012738853503185,
463
+ "grad_norm": 14.65240478515625,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 4.6793,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.40764331210191085,
470
+ "grad_norm": 18.088653564453125,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 4.7098,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.4140127388535032,
477
+ "grad_norm": 17.526235580444336,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 4.4782,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.42038216560509556,
484
+ "grad_norm": 18.589906692504883,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 4.4513,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4267515923566879,
491
+ "grad_norm": 22.394956588745117,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 4.823,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.43312101910828027,
498
+ "grad_norm": 19.558523178100586,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 4.3261,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.4394904458598726,
505
+ "grad_norm": 19.380760192871094,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 4.6877,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.445859872611465,
512
+ "grad_norm": 23.139272689819336,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 4.5216,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.45222929936305734,
519
+ "grad_norm": 20.861736297607422,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 4.1113,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.4585987261146497,
526
+ "grad_norm": 21.064624786376953,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 3.894,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.46496815286624205,
533
+ "grad_norm": 23.0689697265625,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 4.061,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.4713375796178344,
540
+ "grad_norm": 25.696874618530273,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 4.2541,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.47770700636942676,
547
+ "grad_norm": 23.2997989654541,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 4.3783,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.4840764331210191,
554
+ "grad_norm": 33.244049072265625,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 3.9646,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.49044585987261147,
561
+ "grad_norm": 34.73582077026367,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 4.3941,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.4968152866242038,
568
+ "grad_norm": 68.82785034179688,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 3.9351,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5031847133757962,
575
+ "grad_norm": 48.5151252746582,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 6.4497,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.5095541401273885,
582
+ "grad_norm": 20.338134765625,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 4.1436,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.5159235668789809,
589
+ "grad_norm": 8.380877494812012,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 4.0942,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.5222929936305732,
596
+ "grad_norm": 6.018649101257324,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 3.5251,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.5286624203821656,
603
+ "grad_norm": 7.0183796882629395,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 3.6932,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.535031847133758,
610
+ "grad_norm": 6.874508380889893,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 3.8955,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5414012738853503,
617
+ "grad_norm": 7.094663143157959,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 4.4996,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.5477707006369427,
624
+ "grad_norm": 6.800449848175049,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 4.3487,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.554140127388535,
631
+ "grad_norm": 6.512099742889404,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 3.7667,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.5605095541401274,
638
+ "grad_norm": 7.194104194641113,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 3.907,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.5668789808917197,
645
+ "grad_norm": 6.929054260253906,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 3.7032,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.5732484076433121,
652
+ "grad_norm": 6.628689289093018,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 3.3508,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.5796178343949044,
659
+ "grad_norm": 7.876663684844971,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 4.032,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.5859872611464968,
666
+ "grad_norm": 7.960112571716309,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 3.8419,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.5923566878980892,
673
+ "grad_norm": 8.09794807434082,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 3.9603,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.5987261146496815,
680
+ "grad_norm": 9.845130920410156,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 4.0276,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.6050955414012739,
687
+ "grad_norm": 8.297134399414062,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 3.4893,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.6114649681528662,
694
+ "grad_norm": 8.784958839416504,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 3.8555,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.6178343949044586,
701
+ "grad_norm": 10.812994003295898,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 3.7086,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.6242038216560509,
708
+ "grad_norm": 9.371301651000977,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 3.957,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.6305732484076433,
715
+ "grad_norm": 11.402350425720215,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 3.8245,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.6369426751592356,
722
+ "grad_norm": 10.444782257080078,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 3.4607,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.6369426751592356,
729
+ "eval_loss": 0.9518508911132812,
730
+ "eval_runtime": 22.9599,
731
+ "eval_samples_per_second": 11.542,
732
+ "eval_steps_per_second": 5.793,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.52310276258005e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null