nttx commited on
Commit
d61b672
·
verified ·
1 Parent(s): 4bcd219

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 sha256:9252fb0dea7116419496853ed9c6c8fd5051228d5ed0a31f06b75fb2585f58b4
3
  size 34456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad5e1faeecd2a228b04ca00585c74583cf18dcefe2ef94da1c5161e5296c784
3
  size 34456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:298649d4988a7886a1eb221c1b4e4d028f5099dfe8202fe027d48bac6c583079
3
  size 76154
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ad896fb43775412d8b5acf7b10c527bc08ad51c2236a074b72aa9c4e10c2473
3
  size 76154
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72cbe2313d88a37281f12750c89b1676aade09734a9ba776758e58c5ced3a865
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20a9edab4597771a6b5349b3ab408a49ae96684ab5027c1a78bc719184ac7620
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": 11.5,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.4672897196261682,
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": 160.208,
374
  "eval_steps_per_second": 80.547,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -387,7 +745,7 @@
387
  "early_stopping_threshold": 0.0
388
  },
389
  "attributes": {
390
- "early_stopping_patience_counter": 0
391
  }
392
  },
393
  "TrainerControl": {
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 8039615692800.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
  "best_metric": 11.5,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.9345794392523364,
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": 160.208,
374
  "eval_steps_per_second": 80.547,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.4766355140186916,
379
+ "grad_norm": 9.963639604393393e-05,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 46.0,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.48598130841121495,
386
+ "grad_norm": 0.00012790461187250912,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 46.0,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.4953271028037383,
393
+ "grad_norm": 9.55718569457531e-05,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 46.0,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.5046728971962616,
400
+ "grad_norm": 0.00014584721066057682,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 46.0,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.514018691588785,
407
+ "grad_norm": 0.00011913034541066736,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 46.0,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.5233644859813084,
414
+ "grad_norm": 9.888441854855046e-05,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 46.0,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.5327102803738317,
421
+ "grad_norm": 0.00010833790292963386,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 46.0,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.5420560747663551,
428
+ "grad_norm": 0.00012922610039822757,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 46.0,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.5514018691588785,
435
+ "grad_norm": 0.0001300368458032608,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 46.0,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.5607476635514018,
442
+ "grad_norm": 8.210381929529831e-05,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 46.0,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.5700934579439252,
449
+ "grad_norm": 0.0001599452516529709,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 46.0,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.5794392523364486,
456
+ "grad_norm": 0.0001269468484679237,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 46.0,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.5887850467289719,
463
+ "grad_norm": 0.0001564062258694321,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 46.0,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.5981308411214953,
470
+ "grad_norm": 0.00021565529459621757,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 46.0,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.6074766355140186,
477
+ "grad_norm": 0.00012543653429020196,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 46.0,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.616822429906542,
484
+ "grad_norm": 0.00016946744290180504,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 46.0,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.6261682242990654,
491
+ "grad_norm": 0.00016576446068938822,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 46.0,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.6355140186915887,
498
+ "grad_norm": 0.00015629635890945792,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 46.0,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.6448598130841121,
505
+ "grad_norm": 0.00017187913181260228,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 46.0,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.6542056074766355,
512
+ "grad_norm": 0.00017371830472256988,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 46.0,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.6635514018691588,
519
+ "grad_norm": 0.00018266221741214395,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 46.0,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.6728971962616822,
526
+ "grad_norm": 0.00013964249228592962,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 46.0,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.6822429906542056,
533
+ "grad_norm": 0.00014923812705092132,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 46.0,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.6915887850467289,
540
+ "grad_norm": 0.00016153555770870298,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 46.0,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.7009345794392523,
547
+ "grad_norm": 0.00014358038606587797,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 46.0,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.7102803738317757,
554
+ "grad_norm": 0.00019736040849238634,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 46.0,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.719626168224299,
561
+ "grad_norm": 0.0003134732542093843,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 46.0,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.7289719626168224,
568
+ "grad_norm": 0.0002348859270568937,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 46.0,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.7383177570093458,
575
+ "grad_norm": 0.00017541946726851165,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 46.0,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.7476635514018691,
582
+ "grad_norm": 0.00016056875756476074,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 46.0,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.7570093457943925,
589
+ "grad_norm": 0.00022755710233468562,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 46.0,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.7663551401869159,
596
+ "grad_norm": 0.0002692342677619308,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 46.0,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.7757009345794392,
603
+ "grad_norm": 0.0002028964809142053,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 46.0,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.7850467289719626,
610
+ "grad_norm": 0.000286884926026687,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 46.0,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.794392523364486,
617
+ "grad_norm": 0.00020119328110013157,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 46.0,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.8037383177570093,
624
+ "grad_norm": 0.00034160970244556665,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 46.0,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.8130841121495327,
631
+ "grad_norm": 0.0002135804679710418,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 46.0,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.822429906542056,
638
+ "grad_norm": 0.00017743604257702827,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 46.0,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.8317757009345794,
645
+ "grad_norm": 0.0001699524582363665,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 46.0,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.8411214953271028,
652
+ "grad_norm": 0.00032696506241336465,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 46.0,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.8504672897196262,
659
+ "grad_norm": 0.00027825115830637515,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 46.0,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.8598130841121495,
666
+ "grad_norm": 0.0001989601005334407,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 46.0,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.8691588785046729,
673
+ "grad_norm": 0.0003293946501798928,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 46.0,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.8785046728971962,
680
+ "grad_norm": 0.00025171003653667867,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 46.0,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.8878504672897196,
687
+ "grad_norm": 0.00037094487925060093,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 46.0,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.897196261682243,
694
+ "grad_norm": 0.00023440983204636723,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 46.0,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.9065420560747663,
701
+ "grad_norm": 0.0004414333088789135,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 46.0,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.9158878504672897,
708
+ "grad_norm": 0.00024191121337935328,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 46.0,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.9252336448598131,
715
+ "grad_norm": 0.00048082045395858586,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 46.0,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.9345794392523364,
722
+ "grad_norm": 0.00038313641562126577,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 46.0,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.9345794392523364,
729
+ "eval_loss": 11.5,
730
+ "eval_runtime": 1.1284,
731
+ "eval_samples_per_second": 160.407,
732
+ "eval_steps_per_second": 80.647,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
745
  "early_stopping_threshold": 0.0
746
  },
747
  "attributes": {
748
+ "early_stopping_patience_counter": 1
749
  }
750
  },
751
  "TrainerControl": {
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 16079231385600.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null