prxy5606 commited on
Commit
65340e2
·
verified ·
1 Parent(s): d46560b

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 sha256:81701a2a826d8c3717d9bc498ff9edc168c1debc64c543df8d7eadabee050ab4
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51424c28086f94e19dc131077ecadd0d4390629ed8f6408bdb3d22bfd68141b7
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:528d4dd180acd734d85614258dbeebbc5e675c609458916e795e940980447c02
3
  size 156656510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950bbaa108344976f14cf502a4c69a9af03ac17552ceab8f01a16e60c4680880
3
  size 156656510
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4e5696617cb3185657b9b9114762baf127062e4b4345287d34431920aa2f8bc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf69b39deaf4ceca685dfbcc23736d2b58b7133cb9b3922c08857d6baece73ab
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": 2.0050954818725586,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.008557980316645272,
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": 37.99,
374
  "eval_steps_per_second": 18.995,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1928297315303424.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.9593321084976196,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.017115960633290545,
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": 37.99,
374
  "eval_steps_per_second": 18.995,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008729139922978177,
379
+ "grad_norm": 0.22430455684661865,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 1.8785,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008900299529311083,
386
+ "grad_norm": 0.20247997343540192,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 1.9007,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.009071459135643988,
393
+ "grad_norm": 0.18127155303955078,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 1.9556,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.009242618741976894,
400
+ "grad_norm": 0.1620718389749527,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 1.8055,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.009413778348309799,
407
+ "grad_norm": 0.16836689412593842,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 1.7112,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009584937954642705,
414
+ "grad_norm": 0.15607057511806488,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 1.7295,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.00975609756097561,
421
+ "grad_norm": 0.15433867275714874,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 1.7898,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009927257167308514,
428
+ "grad_norm": 0.1581793874502182,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 1.8115,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01009841677364142,
435
+ "grad_norm": 0.1593821793794632,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 1.8821,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.010269576379974325,
442
+ "grad_norm": 0.13692297041416168,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 1.9019,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.010440735986307232,
449
+ "grad_norm": 0.13366976380348206,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 1.8569,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.010611895592640136,
456
+ "grad_norm": 0.13981181383132935,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 2.0179,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.010783055198973043,
463
+ "grad_norm": 0.11422371119260788,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 1.9594,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010954214805305947,
470
+ "grad_norm": 0.12120245397090912,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 1.9958,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.011125374411638854,
477
+ "grad_norm": 0.10169228911399841,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 1.9392,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.011296534017971758,
484
+ "grad_norm": 0.09632351249456406,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 1.8104,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.011467693624304665,
491
+ "grad_norm": 0.10891255736351013,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 2.1084,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01163885323063757,
498
+ "grad_norm": 0.09422247111797333,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 1.8242,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011810012836970476,
505
+ "grad_norm": 0.097730353474617,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 1.8866,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01198117244330338,
512
+ "grad_norm": 0.0988590195775032,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 2.0188,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.012152332049636286,
519
+ "grad_norm": 0.09687261283397675,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 1.9782,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.012323491655969191,
526
+ "grad_norm": 0.10483600199222565,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 1.9285,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.012494651262302097,
533
+ "grad_norm": 0.10860675573348999,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 1.9643,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.012665810868635002,
540
+ "grad_norm": 0.10306871682405472,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 1.8897,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012836970474967908,
547
+ "grad_norm": 0.09955226629972458,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 1.9064,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.013008130081300813,
554
+ "grad_norm": 0.11086455732584,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 1.9856,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.013179289687633718,
561
+ "grad_norm": 0.106622114777565,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 1.9768,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.013350449293966624,
568
+ "grad_norm": 0.11136943846940994,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 2.0076,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.013521608900299529,
575
+ "grad_norm": 0.10378699749708176,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 2.0183,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.013692768506632435,
582
+ "grad_norm": 0.10002272576093674,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 1.9106,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01386392811296534,
589
+ "grad_norm": 0.10468745976686478,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 2.1109,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.014035087719298246,
596
+ "grad_norm": 0.1047583818435669,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 1.8169,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.01420624732563115,
603
+ "grad_norm": 0.11088533699512482,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 2.0148,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.014377406931964057,
610
+ "grad_norm": 0.11189869791269302,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 1.9053,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.014548566538296961,
617
+ "grad_norm": 0.11222604662179947,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 1.85,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.014719726144629868,
624
+ "grad_norm": 0.11671954393386841,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 1.8606,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.014890885750962772,
631
+ "grad_norm": 0.11258739233016968,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 1.9892,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.015062045357295679,
638
+ "grad_norm": 0.12018974870443344,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 2.0688,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.015233204963628583,
645
+ "grad_norm": 0.1348743736743927,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 1.9919,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.01540436456996149,
652
+ "grad_norm": 0.13200099766254425,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 1.9153,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.015575524176294394,
659
+ "grad_norm": 0.1338081955909729,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 1.7685,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0157466837826273,
666
+ "grad_norm": 0.13655497133731842,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 1.9897,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.015917843388960205,
673
+ "grad_norm": 0.1462564319372177,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 1.692,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.01608900299529311,
680
+ "grad_norm": 0.16037926077842712,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 1.9882,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.016260162601626018,
687
+ "grad_norm": 0.16777467727661133,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 1.8377,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.016431322207958923,
694
+ "grad_norm": 0.21440783143043518,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 1.9863,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.016602481814291827,
701
+ "grad_norm": 0.23396961390972137,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 2.1281,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.016773641420624732,
708
+ "grad_norm": 0.29652488231658936,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 2.373,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.016944801026957636,
715
+ "grad_norm": 0.403049498796463,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 2.1079,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.017115960633290545,
722
+ "grad_norm": 0.7542735934257507,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 2.4682,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.017115960633290545,
729
+ "eval_loss": 1.9593321084976196,
730
+ "eval_runtime": 259.8209,
731
+ "eval_samples_per_second": 37.872,
732
+ "eval_steps_per_second": 18.936,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3850414190493696.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null