prxy5605 commited on
Commit
37fc756
·
verified ·
1 Parent(s): 0b32f1f

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:e8fb2163cdb0ed19414e6d37260aede7b4bb936c32fd43bf921a48895b28726a
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81a973d193312053a869634fc411f23cac12be03c65cb382078adb109f64ad29
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9680bbde7b26f5bc60d3ce4ea75cd6d3ce6187ddbac37bd0d81e5d75fe78fe91
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63d173bb78399bc7edd07e12400a5df44ea2f231a2e2d8796c67cffd263e3b8b
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:f6e00fccede0604ef3c62d65b2240190a3aa6fca37d681a1a1f57a08829b0155
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:736ae02480f4960d6d5b47c03465d751c29b956ca31cb3049640818aca2810e1
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": 1.0552418231964111,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.17152658662092624,
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": 11.948,
374
  "eval_steps_per_second": 5.986,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.333864796061696e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9467170834541321,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.34305317324185247,
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": 11.948,
374
  "eval_steps_per_second": 5.986,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.17495711835334476,
379
+ "grad_norm": 7.74439811706543,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 4.8988,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.1783876500857633,
386
+ "grad_norm": 5.500019073486328,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 4.8596,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.18181818181818182,
393
+ "grad_norm": 3.838832378387451,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 4.4589,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.18524871355060035,
400
+ "grad_norm": 3.795142650604248,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 4.2005,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.18867924528301888,
407
+ "grad_norm": 3.751390218734741,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 4.1903,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.19210977701543738,
414
+ "grad_norm": 3.823895215988159,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 3.9744,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1955403087478559,
421
+ "grad_norm": 3.9442529678344727,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 4.3034,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.19897084048027444,
428
+ "grad_norm": 4.070255279541016,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 4.0883,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.20240137221269297,
435
+ "grad_norm": 3.7813539505004883,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 3.9695,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2058319039451115,
442
+ "grad_norm": 3.8070478439331055,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 3.7485,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.20926243567753003,
449
+ "grad_norm": 3.9176182746887207,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 4.011,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.21269296740994853,
456
+ "grad_norm": 4.07338809967041,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 4.0232,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.21612349914236706,
463
+ "grad_norm": 4.0383782386779785,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 3.978,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.2195540308747856,
470
+ "grad_norm": 3.6648452281951904,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 3.4885,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.22298456260720412,
477
+ "grad_norm": 3.8878605365753174,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 3.8533,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.22641509433962265,
484
+ "grad_norm": 4.185667991638184,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 3.6215,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.22984562607204118,
491
+ "grad_norm": 4.071247100830078,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 3.531,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2332761578044597,
498
+ "grad_norm": 4.344533443450928,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 3.7186,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.2367066895368782,
505
+ "grad_norm": 4.426985740661621,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 3.6128,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.24013722126929674,
512
+ "grad_norm": 4.162020206451416,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 3.3318,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.24356775300171526,
519
+ "grad_norm": 4.368765354156494,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 3.4157,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.2469982847341338,
526
+ "grad_norm": 4.309731960296631,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 3.5808,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2504288164665523,
533
+ "grad_norm": 4.442713260650635,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 3.4605,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.2538593481989708,
540
+ "grad_norm": 4.398868083953857,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 3.6249,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.25728987993138935,
547
+ "grad_norm": 4.782496929168701,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 3.7258,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.2607204116638079,
554
+ "grad_norm": 4.372551918029785,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 3.7134,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.2641509433962264,
561
+ "grad_norm": 4.290441989898682,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 3.7541,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.26758147512864494,
568
+ "grad_norm": 4.507718086242676,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 3.9408,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.27101200686106347,
575
+ "grad_norm": 4.117275714874268,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 3.4982,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.274442538593482,
582
+ "grad_norm": 4.557469844818115,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 3.7516,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.27787307032590053,
589
+ "grad_norm": 5.15295934677124,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 3.5183,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.28130360205831906,
596
+ "grad_norm": 4.726450443267822,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 3.526,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.2847341337907376,
603
+ "grad_norm": 4.847685813903809,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 3.858,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.2881646655231561,
610
+ "grad_norm": 4.568885803222656,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 3.6064,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.2915951972555746,
617
+ "grad_norm": 4.916790962219238,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 3.383,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.2950257289879931,
624
+ "grad_norm": 5.058016777038574,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 3.8242,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.29845626072041165,
631
+ "grad_norm": 4.883471965789795,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 3.9667,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3018867924528302,
638
+ "grad_norm": 4.773396968841553,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 3.5179,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.3053173241852487,
645
+ "grad_norm": 5.102062225341797,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 3.7781,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.30874785591766724,
652
+ "grad_norm": 4.849315643310547,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 3.59,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.31217838765008576,
659
+ "grad_norm": 5.05657958984375,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 3.8574,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.3156089193825043,
666
+ "grad_norm": 5.094900608062744,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 3.6297,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.3190394511149228,
673
+ "grad_norm": 5.497709274291992,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 3.4883,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.32246998284734135,
680
+ "grad_norm": 5.846022605895996,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 3.5978,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.3259005145797599,
687
+ "grad_norm": 5.982120990753174,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 3.7544,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.3293310463121784,
694
+ "grad_norm": 5.516687870025635,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 3.3577,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.33276157804459694,
701
+ "grad_norm": 5.789833068847656,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 3.3941,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.3361921097770154,
708
+ "grad_norm": 5.645137310028076,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 3.3852,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.33962264150943394,
715
+ "grad_norm": 7.209895610809326,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 3.7848,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.34305317324185247,
722
+ "grad_norm": 9.69320011138916,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 3.4986,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.34305317324185247,
729
+ "eval_loss": 0.9467170834541321,
730
+ "eval_runtime": 41.1492,
731
+ "eval_samples_per_second": 11.932,
732
+ "eval_steps_per_second": 5.978,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.4739279492572774e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null