prxy5604 commited on
Commit
6dd2035
·
verified ·
1 Parent(s): 572f80d

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 sha256:2ebd0228c8d3fe753720b121a416f4c895586c07725c3b86e47dc3efa5feb2c1
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6afb43221df3e4361d024069416b03aa5e6f137c283cc929d3f96eb7db013205
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec43f14b1f3ba2b182c9487afbbf614503dacc50ad02845ce45fb8016153bad4
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6b693844dfb7001d154079ee1a99b2e554a784c55a728273850e6ab80aac1e0
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5494196aa2f0c5f6a425d9651678c9533c2a11a2fb0b62a8189d3ce2926b86b6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40015f9b0060360be0dbdeaab42222ac37ca1d65e73bfdbacc136d49a439e80
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79f5b4ba066d00b62be68b9f9ec9376def1ffea9a45f98d620f3198033186a6a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7931326031684875,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.035143208574942894,
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": 7.209,
374
  "eval_steps_per_second": 3.606,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.22128410083328e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6699920892715454,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.07028641714988579,
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": 7.209,
374
  "eval_steps_per_second": 3.606,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03584607274644175,
379
+ "grad_norm": 5.554098606109619,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 0.7428,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03654893691794061,
386
+ "grad_norm": 0.6978570222854614,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 0.4409,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.037251801089439464,
393
+ "grad_norm": 0.28626111149787903,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 0.3601,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.037954665260938325,
400
+ "grad_norm": 0.1934920996427536,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 0.3868,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03865752943243718,
407
+ "grad_norm": 0.18251414597034454,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 0.3611,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.03936039360393604,
414
+ "grad_norm": 0.2201131284236908,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 0.4773,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.040063257775434895,
421
+ "grad_norm": 0.21173296868801117,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 0.486,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.040766121946933756,
428
+ "grad_norm": 0.2153291255235672,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 0.4396,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.04146898611843261,
435
+ "grad_norm": 0.20555301010608673,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 0.5213,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.04217185028993147,
442
+ "grad_norm": 0.19719314575195312,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 0.5652,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.042874714461430326,
449
+ "grad_norm": 0.18588709831237793,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 0.5582,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.04357757863292919,
456
+ "grad_norm": 0.22327612340450287,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 0.7321,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04428044280442804,
463
+ "grad_norm": 0.21731068193912506,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 0.7298,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0449833069759269,
470
+ "grad_norm": 0.21543888747692108,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 0.6652,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.04568617114742576,
477
+ "grad_norm": 0.23041720688343048,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 0.7261,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.04638903531892462,
484
+ "grad_norm": 0.20984987914562225,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 0.6916,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.04709189949042347,
491
+ "grad_norm": 0.22370988130569458,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 0.6645,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.04779476366192233,
498
+ "grad_norm": 0.2238708734512329,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 0.6684,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.048497627833421195,
505
+ "grad_norm": 0.2282782942056656,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 0.6836,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.04920049200492005,
512
+ "grad_norm": 0.22426971793174744,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 0.6277,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04990335617641891,
519
+ "grad_norm": 0.24329598248004913,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 0.7216,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.050606220347917764,
526
+ "grad_norm": 0.23810680210590363,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 0.6573,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.051309084519416626,
533
+ "grad_norm": 0.2418031245470047,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 0.7383,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.05201194869091548,
540
+ "grad_norm": 0.23166213929653168,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 0.7561,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.05271481286241434,
547
+ "grad_norm": 0.24179698526859283,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 0.6931,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.053417677033913195,
554
+ "grad_norm": 0.25874027609825134,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 0.8606,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.05412054120541206,
561
+ "grad_norm": 0.2505108118057251,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 0.8458,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.05482340537691091,
568
+ "grad_norm": 0.2619728446006775,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 0.857,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.05552626954840977,
575
+ "grad_norm": 0.2551406919956207,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 0.8475,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.056229133719908626,
582
+ "grad_norm": 0.26327502727508545,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 0.7916,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05693199789140749,
589
+ "grad_norm": 0.28274351358413696,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 0.8075,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.05763486206290634,
596
+ "grad_norm": 0.2752515971660614,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 0.8331,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0583377262344052,
603
+ "grad_norm": 0.4340633451938629,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 0.7778,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.05904059040590406,
610
+ "grad_norm": 0.362873911857605,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 0.863,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.05974345457740292,
617
+ "grad_norm": 0.3778440058231354,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 0.7936,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.06044631874890177,
624
+ "grad_norm": 0.3569698929786682,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 0.8301,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.061149182920400634,
631
+ "grad_norm": 0.3684358596801758,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 0.8868,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.06185204709189949,
638
+ "grad_norm": 0.3750736117362976,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 0.9028,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.06255491126339835,
645
+ "grad_norm": 0.3491847813129425,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 0.8992,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0632577754348972,
652
+ "grad_norm": 0.30583202838897705,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 0.881,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.06396063960639606,
659
+ "grad_norm": 0.25735631585121155,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 0.8979,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.06466350377789493,
666
+ "grad_norm": 0.2660073935985565,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 0.8359,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06536636794939378,
673
+ "grad_norm": 0.3032679557800293,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 0.8739,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.06606923212089263,
680
+ "grad_norm": 0.334891140460968,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 0.85,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.06677209629239149,
687
+ "grad_norm": 0.3186686933040619,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 0.874,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.06747496046389036,
694
+ "grad_norm": 0.32608991861343384,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 0.9199,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.06817782463538921,
701
+ "grad_norm": 0.3285480737686157,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 0.8406,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.06888068880688807,
708
+ "grad_norm": 0.35589680075645447,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 0.8486,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.06958355297838692,
715
+ "grad_norm": 0.3586467206478119,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 0.9165,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.07028641714988579,
722
+ "grad_norm": 0.49421557784080505,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 0.9244,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.07028641714988579,
729
+ "eval_loss": 0.6699920892715454,
730
+ "eval_runtime": 332.5314,
731
+ "eval_samples_per_second": 7.208,
732
+ "eval_steps_per_second": 3.606,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.43583936364544e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null