nttx commited on
Commit
48d7cc7
·
verified ·
1 Parent(s): f285da8

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 sha256:7f0b497ddfdb7ffef79f7dedf124ecfe1bdf1986ae17d8d70661b831ff59d4ed
3
  size 985240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d200bd4fcf6bb981ea8f201247cf014eebe232475b46252ff2e22acd9b01eabd
3
  size 985240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fbfe3c0256858cda78e7a7b1eadd72bdd568871b36fe56a871323cec9d0b9f5
3
  size 1980078
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4fe96e14881c634467ff27b6b00f1c7696c620cfd3c3c999d50a817a81c5876
3
  size 1980078
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:282b0ed0502e23dcef15dbd43aa8b4e5f854ee98f94cb1cf5430983de4dea5b2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68eb74958fdc275bdc5e5f304b68598a3d2b2aa529bba012e0dd443da4fbd110
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": 11.117125511169434,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.2949852507374631,
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": 433.596,
374
  "eval_steps_per_second": 54.579,
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": 5971850035200.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.062679290771484,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.5899705014749262,
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": 433.596,
374
  "eval_steps_per_second": 54.579,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3008849557522124,
379
+ "grad_norm": 11.262834548950195,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 44.5064,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.30678466076696165,
386
+ "grad_norm": 11.28780460357666,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 44.4551,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.31268436578171094,
393
+ "grad_norm": 11.082712173461914,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 44.4367,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3185840707964602,
400
+ "grad_norm": 11.272944450378418,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 44.495,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.32448377581120946,
407
+ "grad_norm": 11.367984771728516,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 44.4521,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.3303834808259587,
414
+ "grad_norm": 11.50567626953125,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 44.4069,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.336283185840708,
421
+ "grad_norm": 11.37206745147705,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 44.4106,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.3421828908554572,
428
+ "grad_norm": 11.600016593933105,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 44.3691,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.3480825958702065,
435
+ "grad_norm": 11.29223918914795,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 44.3776,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.35398230088495575,
442
+ "grad_norm": 11.168807983398438,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 44.3662,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.35988200589970504,
449
+ "grad_norm": 11.356904029846191,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 44.3792,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.36578171091445427,
456
+ "grad_norm": 11.171018600463867,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 44.3577,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.37168141592920356,
463
+ "grad_norm": 11.397581100463867,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 44.3313,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.3775811209439528,
470
+ "grad_norm": 11.264802932739258,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 44.33,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.3834808259587021,
477
+ "grad_norm": 11.5596923828125,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 44.3594,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3893805309734513,
484
+ "grad_norm": 11.320469856262207,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 44.3022,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3952802359882006,
491
+ "grad_norm": 11.212388038635254,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 44.3685,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.40117994100294985,
498
+ "grad_norm": 11.267321586608887,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 44.3347,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.40707964601769914,
505
+ "grad_norm": 11.387954711914062,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 44.2862,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.41297935103244837,
512
+ "grad_norm": 11.291707992553711,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 44.3167,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.41887905604719766,
519
+ "grad_norm": 11.472674369812012,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 44.3085,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.4247787610619469,
526
+ "grad_norm": 11.46934700012207,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 44.3146,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.4306784660766962,
533
+ "grad_norm": 11.346488952636719,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 44.2872,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.4365781710914454,
540
+ "grad_norm": 11.554361343383789,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 44.2945,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.4424778761061947,
547
+ "grad_norm": 11.511228561401367,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 44.3073,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.44837758112094395,
554
+ "grad_norm": 11.469541549682617,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 44.3281,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.45427728613569324,
561
+ "grad_norm": 11.547125816345215,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 44.3098,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.46017699115044247,
568
+ "grad_norm": 11.442727088928223,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 44.2586,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.46607669616519176,
575
+ "grad_norm": 11.528830528259277,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 44.2821,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.471976401179941,
582
+ "grad_norm": 11.535983085632324,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 44.3261,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.4778761061946903,
589
+ "grad_norm": 11.634220123291016,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 44.275,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.4837758112094395,
596
+ "grad_norm": 11.648545265197754,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 44.2439,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.4896755162241888,
603
+ "grad_norm": 11.617422103881836,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 44.3185,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.49557522123893805,
610
+ "grad_norm": 11.682761192321777,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 44.2801,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5014749262536873,
617
+ "grad_norm": 11.089653968811035,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 44.2543,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.5073746312684366,
624
+ "grad_norm": 11.051488876342773,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 44.2673,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.5132743362831859,
631
+ "grad_norm": 11.184460639953613,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 44.2306,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.5191740412979351,
638
+ "grad_norm": 11.230326652526855,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 44.2451,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.5250737463126843,
645
+ "grad_norm": 11.29784107208252,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 44.2646,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.5309734513274337,
652
+ "grad_norm": 11.078227996826172,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 44.2559,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.5368731563421829,
659
+ "grad_norm": 11.108466148376465,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 44.2589,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.5427728613569321,
666
+ "grad_norm": 11.564451217651367,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 44.2609,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.5486725663716814,
673
+ "grad_norm": 11.223318099975586,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 44.2762,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.5545722713864307,
680
+ "grad_norm": 11.573466300964355,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 44.2708,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.56047197640118,
687
+ "grad_norm": 11.500224113464355,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 44.2757,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.5663716814159292,
694
+ "grad_norm": 11.30689525604248,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 44.224,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.5722713864306784,
701
+ "grad_norm": 11.348673820495605,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 44.2502,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.5781710914454278,
708
+ "grad_norm": 11.519439697265625,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 44.2666,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.584070796460177,
715
+ "grad_norm": 11.413444519042969,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 44.3009,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.5899705014749262,
722
+ "grad_norm": 11.36845588684082,
723
+ "learning_rate": 0.0,
724
+ "loss": 44.1867,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.5899705014749262,
729
+ "eval_loss": 11.062679290771484,
730
+ "eval_runtime": 0.6567,
731
+ "eval_samples_per_second": 435.541,
732
+ "eval_steps_per_second": 54.823,
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": 11943700070400.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null