nttx commited on
Commit
4b12481
·
verified ·
1 Parent(s): ecedc89

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:c8c02aa708c291e0eea70feb5e9f38cf9913e491c1f5818047df88b837b8e48a
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a8a134e697760cd920b025f558e56e5322cd52591e028f4c9dc8de18e2a890
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd251ba2660823f5a7c3937cc857fdf02f30399abfa5eaff4f414225121ffd04
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573957c3c709c22721d2676e7cde32d079e87daf4d70374a360a95e6084e7fae
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21279ccb5d0a5f42f8bbcd3e43f95f672c3da9da4b8cd0f63d1a5329b035a175
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f99d60c34c5e0afbaf90da0043467577d559b315976c49cee303ef279be3fcc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.611772060394287,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.18570102135561745,
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": 13.409,
374
  "eval_steps_per_second": 1.684,
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": 6.7624822112256e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.974936306476593,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.3714020427112349,
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": 13.409,
374
  "eval_steps_per_second": 1.684,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.1894150417827298,
379
+ "grad_norm": 1.2142438888549805,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 0.8321,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.19312906220984216,
386
+ "grad_norm": 2.127845048904419,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 1.1498,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.1968430826369545,
393
+ "grad_norm": 2.3324849605560303,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 1.2167,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.20055710306406685,
400
+ "grad_norm": 2.875474691390991,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 1.3003,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.2042711234911792,
407
+ "grad_norm": 2.1670145988464355,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 1.3164,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.20798514391829154,
414
+ "grad_norm": 2.674121379852295,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 1.2361,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2116991643454039,
421
+ "grad_norm": 2.671863555908203,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 1.2381,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.21541318477251625,
428
+ "grad_norm": 2.4426980018615723,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 1.3495,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.2191272051996286,
435
+ "grad_norm": 2.743527412414551,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 1.3194,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.22284122562674094,
442
+ "grad_norm": 2.485083818435669,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 1.3947,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.2265552460538533,
449
+ "grad_norm": 2.3887181282043457,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 1.2135,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.23026926648096566,
456
+ "grad_norm": 2.7468771934509277,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 1.2523,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.233983286908078,
463
+ "grad_norm": 2.5111334323883057,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 1.2471,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.23769730733519034,
470
+ "grad_norm": 2.4568049907684326,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 1.1975,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.2414113277623027,
477
+ "grad_norm": 2.5363759994506836,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 1.1698,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.24512534818941503,
484
+ "grad_norm": 2.9774973392486572,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 0.9025,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.2488393686165274,
491
+ "grad_norm": 3.5985605716705322,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 1.22,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2525533890436397,
498
+ "grad_norm": 2.659881830215454,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 1.1345,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.2562674094707521,
505
+ "grad_norm": 2.756131172180176,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 1.1833,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.25998142989786444,
512
+ "grad_norm": 2.8494410514831543,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 1.3538,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.26369545032497677,
519
+ "grad_norm": 2.196274518966675,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 0.8695,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.26740947075208915,
526
+ "grad_norm": 2.421745538711548,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 1.1275,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2711234911792015,
533
+ "grad_norm": 3.1137969493865967,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 1.2171,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.2748375116063138,
540
+ "grad_norm": 2.646501064300537,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 1.234,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.2785515320334262,
547
+ "grad_norm": 2.5165648460388184,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 1.1426,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.2822655524605385,
554
+ "grad_norm": 2.521559476852417,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 1.0068,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.28597957288765086,
561
+ "grad_norm": 2.283813238143921,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 1.1615,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.28969359331476324,
568
+ "grad_norm": 3.4305078983306885,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 1.1356,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.2934076137418756,
575
+ "grad_norm": 2.714026927947998,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 1.086,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.2971216341689879,
582
+ "grad_norm": 2.8863515853881836,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 0.854,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.3008356545961003,
589
+ "grad_norm": 2.6695327758789062,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 1.1173,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.3045496750232126,
596
+ "grad_norm": 2.6120901107788086,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 0.9034,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.308263695450325,
603
+ "grad_norm": 2.606943368911743,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 1.0242,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.31197771587743733,
610
+ "grad_norm": 2.955063819885254,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 0.9499,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.31569173630454966,
617
+ "grad_norm": 2.4737842082977295,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 1.0119,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.31940575673166205,
624
+ "grad_norm": 3.265795946121216,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 0.855,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3231197771587744,
631
+ "grad_norm": 3.479175090789795,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 0.8147,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3268337975858867,
638
+ "grad_norm": 3.1530840396881104,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 1.1186,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.3305478180129991,
645
+ "grad_norm": 4.578067779541016,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 0.9307,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.3342618384401114,
652
+ "grad_norm": 3.7903590202331543,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 0.8859,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.33797585886722376,
659
+ "grad_norm": 4.344192028045654,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 0.9719,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.34168987929433614,
666
+ "grad_norm": 6.286164283752441,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 1.1164,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.34540389972144847,
673
+ "grad_norm": 4.787858963012695,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 1.0283,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3491179201485608,
680
+ "grad_norm": 7.135058403015137,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 0.9365,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.3528319405756732,
687
+ "grad_norm": 7.054929256439209,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 1.0428,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.3565459610027855,
694
+ "grad_norm": 8.841050148010254,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 0.9227,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.36025998142989785,
701
+ "grad_norm": 9.116321563720703,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 1.0278,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.36397400185701023,
708
+ "grad_norm": 8.069734573364258,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 1.2367,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.36768802228412256,
715
+ "grad_norm": 10.388524055480957,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 1.0777,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.3714020427112349,
722
+ "grad_norm": 9.496840476989746,
723
+ "learning_rate": 0.0,
724
+ "loss": 1.8257,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.3714020427112349,
729
+ "eval_loss": 0.974936306476593,
730
+ "eval_runtime": 33.8821,
731
+ "eval_samples_per_second": 13.399,
732
+ "eval_steps_per_second": 1.682,
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": 1.35249644224512e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null