prxy5607 commited on
Commit
3aa7daf
·
verified ·
1 Parent(s): 34db054

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:b05f850b9fa817b92b01477075cac726e8f0333558215fca0aa517e03561fef9
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd28de16ab2e8910fd33b3449727d8f6a3e70e94f72b5d445f1ca925c2d3b6b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:775cab6db7980f9831b3e3237bc390fb7a0f4f51d5cd51193caaa19c7d902e64
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72dc93588cd36711a52172e2b036798cad9bdd97255ccb5e13deab788021545d
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:b9aab07d6198d35589ffa5190b1998b47d675a8f2a8d36b89c8a1eb7452f119e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815777f3787810f86a0bec03cade7f173d0f17fbe8b138ebca07a24d94d69729
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": 0.7593479752540588,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.019807863721897592,
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": 12.5,
374
  "eval_steps_per_second": 6.25,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.15499004493824e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6730939745903015,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.039615727443795185,
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": 12.5,
374
  "eval_steps_per_second": 6.25,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.020204020996335545,
379
+ "grad_norm": 14.763004302978516,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 3.4166,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.020600178270773498,
386
+ "grad_norm": 8.999519348144531,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 2.2951,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.02099633554521145,
393
+ "grad_norm": 7.654372215270996,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 2.9339,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0213924928196494,
400
+ "grad_norm": 6.517328262329102,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 2.4162,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.021788650094087352,
407
+ "grad_norm": 7.003291130065918,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 2.2779,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.022184807368525305,
414
+ "grad_norm": 8.182329177856445,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 2.9609,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.022580964642963258,
421
+ "grad_norm": 7.554233074188232,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 2.6803,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.022977121917401207,
428
+ "grad_norm": 7.749049186706543,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 2.5795,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.02337327919183916,
435
+ "grad_norm": 7.0886149406433105,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 2.3511,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.023769436466277112,
442
+ "grad_norm": 6.84679651260376,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 2.1122,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.024165593740715065,
449
+ "grad_norm": 7.1356329917907715,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 2.3196,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.024561751015153017,
456
+ "grad_norm": 7.6530046463012695,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 2.4788,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.024957908289590967,
463
+ "grad_norm": 8.369495391845703,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 2.3375,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.02535406556402892,
470
+ "grad_norm": 8.36403751373291,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 2.0959,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.025750222838466872,
477
+ "grad_norm": 10.229287147521973,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 3.0627,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.026146380112904825,
484
+ "grad_norm": 8.87305736541748,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 2.5706,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.026542537387342774,
491
+ "grad_norm": 9.638481140136719,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 2.7759,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.026938694661780727,
498
+ "grad_norm": 9.509964942932129,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 2.5595,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.02733485193621868,
505
+ "grad_norm": 9.560708045959473,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 2.6391,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.027731009210656632,
512
+ "grad_norm": 8.581311225891113,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 2.784,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.02812716648509458,
519
+ "grad_norm": 7.63805627822876,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 2.2859,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.028523323759532534,
526
+ "grad_norm": 8.626289367675781,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 2.7975,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.028919481033970486,
533
+ "grad_norm": 11.270418167114258,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 2.5275,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.02931563830840844,
540
+ "grad_norm": 9.097280502319336,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 2.696,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.02971179558284639,
547
+ "grad_norm": 7.862690448760986,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 2.2284,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.03010795285728434,
554
+ "grad_norm": 7.738744735717773,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 2.3424,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.030504110131722294,
561
+ "grad_norm": 9.578076362609863,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 2.8572,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.030900267406160246,
568
+ "grad_norm": 9.798004150390625,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 2.9643,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0312964246805982,
575
+ "grad_norm": 9.317380905151367,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 3.2559,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03169258195503615,
582
+ "grad_norm": 9.332989692687988,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 2.6451,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.032088739229474104,
589
+ "grad_norm": 10.110783576965332,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 3.095,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.03248489650391205,
596
+ "grad_norm": 9.339815139770508,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 2.3127,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.03288105377835,
603
+ "grad_norm": 10.58879280090332,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 2.5449,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.033277211052787956,
610
+ "grad_norm": 10.540449142456055,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 3.362,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.03367336832722591,
617
+ "grad_norm": 12.278244972229004,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 2.5295,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.03406952560166386,
624
+ "grad_norm": 9.675426483154297,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 2.4279,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.034465682876101814,
631
+ "grad_norm": 8.322236061096191,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 2.1438,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.034861840150539766,
638
+ "grad_norm": 15.984248161315918,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 2.4826,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.03525799742497772,
645
+ "grad_norm": 11.099123001098633,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 2.8121,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.035654154699415665,
652
+ "grad_norm": 10.237126350402832,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 2.6013,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03605031197385362,
659
+ "grad_norm": 12.89112663269043,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 2.3039,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.03644646924829157,
666
+ "grad_norm": 8.39738655090332,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 2.0425,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03684262652272952,
673
+ "grad_norm": 10.789386749267578,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 2.7755,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.037238783797167475,
680
+ "grad_norm": 11.95657730102539,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 2.5013,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03763494107160543,
687
+ "grad_norm": 9.726419448852539,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 2.6235,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03803109834604338,
694
+ "grad_norm": 12.768197059631348,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 2.7799,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03842725562048133,
701
+ "grad_norm": 11.749434471130371,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 2.9625,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.038823412894919286,
708
+ "grad_norm": 14.08253002166748,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 2.8971,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03921957016935723,
715
+ "grad_norm": 11.256560325622559,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 2.3274,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.039615727443795185,
722
+ "grad_norm": 12.625090599060059,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 2.6474,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.039615727443795185,
729
+ "eval_loss": 0.6730939745903015,
730
+ "eval_runtime": 340.0276,
731
+ "eval_samples_per_second": 12.505,
732
+ "eval_steps_per_second": 6.252,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.430998008987648e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null