Nexspear commited on
Commit
d3b3c80
·
verified ·
1 Parent(s): 7501c8e

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 sha256:95780ad94a5db1cbd6b519f40a7e9aba907320f1b6d7b2ba3b86b0ef1ba11143
3
  size 97728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08c10061058c435cc376c329fc3aca3c37929aa5bbbb77dd86d4b1b14dd486a
3
  size 97728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a7a162cdd4a1625075dcbb0329018f699eb2f982170898d63b37162d9b17b10
3
  size 205350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f640e4b420238641c1e69654d694392551e7da0ed31e86fe926192687a304f4a
3
  size 205350
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c6e7276a2f1bb0919034b00b18c6ec9ec6a1e66261c4ba3cc9135e6e70d966b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d2042752f1f49e38179d2b9ca9233856ff37ed72c5319341ace36487c88c82a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.351405143737793,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.6006006006006006,
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": 420.431,
374
  "eval_steps_per_second": 105.108,
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": 5346007449600.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.348917007446289,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.2012012012012012,
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": 420.431,
374
  "eval_steps_per_second": 105.108,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.6126126126126126,
379
+ "grad_norm": 0.1385074406862259,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 10.3523,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.6246246246246246,
386
+ "grad_norm": 0.11994314938783646,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 10.3496,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.6366366366366366,
393
+ "grad_norm": 0.12939238548278809,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 10.35,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.6486486486486487,
400
+ "grad_norm": 0.13329431414604187,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 10.3485,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.6606606606606606,
407
+ "grad_norm": 0.15696164965629578,
408
+ "learning_rate": 5e-05,
409
+ "loss": 10.3508,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.6726726726726727,
414
+ "grad_norm": 0.11817120760679245,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 10.3475,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.6846846846846847,
421
+ "grad_norm": 0.17037023603916168,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 10.3456,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.6966966966966966,
428
+ "grad_norm": 0.27570074796676636,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 10.3418,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.7087087087087087,
435
+ "grad_norm": 0.25951486825942993,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 10.3458,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.7207207207207207,
442
+ "grad_norm": 0.25024840235710144,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 10.3361,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.7327327327327328,
449
+ "grad_norm": 0.15343418717384338,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 10.3538,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.7447447447447447,
456
+ "grad_norm": 0.12202432751655579,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 10.3493,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.7567567567567568,
463
+ "grad_norm": 0.11715935170650482,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 10.3577,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.7687687687687688,
470
+ "grad_norm": 0.12855777144432068,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 10.3495,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.7807807807807807,
477
+ "grad_norm": 0.12814295291900635,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 10.3517,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.7927927927927928,
484
+ "grad_norm": 0.14796307682991028,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 10.3543,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.8048048048048048,
491
+ "grad_norm": 0.10517235845327377,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 10.3526,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.8168168168168168,
498
+ "grad_norm": 0.10510523617267609,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 10.3511,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.8288288288288288,
505
+ "grad_norm": 0.12766772508621216,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 10.3528,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.8408408408408409,
512
+ "grad_norm": 0.09015192091464996,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 10.352,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.8528528528528528,
519
+ "grad_norm": 0.08759531378746033,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 10.3496,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.8648648648648649,
526
+ "grad_norm": 0.08307502418756485,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 10.3479,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.8768768768768769,
533
+ "grad_norm": 0.128950834274292,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 10.3421,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.8888888888888888,
540
+ "grad_norm": 0.12842462956905365,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 10.3464,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.9009009009009009,
547
+ "grad_norm": 0.1564466953277588,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 10.3513,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.9129129129129129,
554
+ "grad_norm": 0.10344736278057098,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 10.347,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.924924924924925,
561
+ "grad_norm": 0.17611975967884064,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 10.3424,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.9369369369369369,
568
+ "grad_norm": 0.17288321256637573,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 10.3423,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.948948948948949,
575
+ "grad_norm": 0.24021244049072266,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 10.3399,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.960960960960961,
582
+ "grad_norm": 0.22334186732769012,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 10.3372,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.972972972972973,
589
+ "grad_norm": 0.10378078371286392,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 10.3536,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.984984984984985,
596
+ "grad_norm": 0.11866383254528046,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 10.356,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.996996996996997,
603
+ "grad_norm": 0.11081431061029434,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 10.3428,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.009009009009009,
610
+ "grad_norm": 0.3789661228656769,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 18.3146,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.021021021021021,
617
+ "grad_norm": 0.11683385819196701,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 10.2473,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.033033033033033,
624
+ "grad_norm": 0.14324098825454712,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 10.2616,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.045045045045045,
631
+ "grad_norm": 0.1403503715991974,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 10.3972,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.057057057057057,
638
+ "grad_norm": 0.10031662881374359,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 10.2818,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.069069069069069,
645
+ "grad_norm": 0.12696465849876404,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 10.498,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.0810810810810811,
652
+ "grad_norm": 0.11515042185783386,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 10.3381,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.093093093093093,
659
+ "grad_norm": 0.09645378589630127,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 10.093,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.105105105105105,
666
+ "grad_norm": 0.11583787947893143,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 10.5066,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.117117117117117,
673
+ "grad_norm": 0.10351304709911346,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 10.373,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.1291291291291292,
680
+ "grad_norm": 0.08083759248256683,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 10.389,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.1411411411411412,
687
+ "grad_norm": 0.13066591322422028,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 10.7377,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.1531531531531531,
694
+ "grad_norm": 0.10491601377725601,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 9.8073,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.165165165165165,
701
+ "grad_norm": 0.11174864321947098,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 10.6638,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.1771771771771773,
708
+ "grad_norm": 0.13597334921360016,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 10.1348,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.1891891891891893,
715
+ "grad_norm": 0.13292589783668518,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 10.5918,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.2012012012012012,
722
+ "grad_norm": 0.16977031528949738,
723
+ "learning_rate": 0.0,
724
+ "loss": 10.1499,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.2012012012012012,
729
+ "eval_loss": 10.348917007446289,
730
+ "eval_runtime": 0.3124,
731
+ "eval_samples_per_second": 448.121,
732
+ "eval_steps_per_second": 112.03,
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": 10678649880576.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null