prxy5605 commited on
Commit
4f577b3
·
verified ·
1 Parent(s): 2398a3d

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 sha256:5ae8b21b4c533118607968900ced01007831f72fe30819b03b5117fcf7909009
3
  size 800116456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7994544811d6d549db6079d655e84f93b014a1f0392799761c0df4e01ce3f7cf
3
  size 800116456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fb55df696283fb1adaacaa4d67813c6f0c3f2926968142998980a6a280fe076
3
  size 1600457770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03845218c6cd8e496dbcec1d2ba48cfe592ac78a9ac260bd1807e2a4b49b2e52
3
  size 1600457770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63863b64568e3a787c2e95b4e1bf53d37ffeb4199e1731d7a68cf515a74927ed
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46fbf6af52e4d2c80da20f987568326a5117f5f5c4d303d2939708a700fefcbf
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": 1.1298441886901855,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.16891891891891891,
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": 10.846,
374
  "eval_steps_per_second": 5.434,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.855493374122394e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.000538945198059,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.33783783783783783,
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": 10.846,
374
  "eval_steps_per_second": 5.434,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.17229729729729729,
379
+ "grad_norm": 1.6099838018417358,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 0.9751,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.17567567567567569,
386
+ "grad_norm": 1.5371800661087036,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 1.0266,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.17905405405405406,
393
+ "grad_norm": 0.87901771068573,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 0.918,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.18243243243243243,
400
+ "grad_norm": 0.703105628490448,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 0.7213,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.1858108108108108,
407
+ "grad_norm": 0.8392472863197327,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 0.99,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.1891891891891892,
414
+ "grad_norm": 0.962077260017395,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 0.9932,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.19256756756756757,
421
+ "grad_norm": 1.064950942993164,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 0.9774,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.19594594594594594,
428
+ "grad_norm": 1.1014493703842163,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 0.8928,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.19932432432432431,
435
+ "grad_norm": 0.8882946372032166,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 0.8685,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.20270270270270271,
442
+ "grad_norm": 0.7933914661407471,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 0.9081,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.20608108108108109,
449
+ "grad_norm": 0.8522499203681946,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 0.966,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.20945945945945946,
456
+ "grad_norm": 0.7208542823791504,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 0.8446,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.21283783783783783,
463
+ "grad_norm": 0.8307358026504517,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 0.9462,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.21621621621621623,
470
+ "grad_norm": 0.9621148109436035,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 0.9179,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.2195945945945946,
477
+ "grad_norm": 0.836197018623352,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 0.8942,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.22297297297297297,
484
+ "grad_norm": 0.8846750259399414,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 0.8464,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.22635135135135134,
491
+ "grad_norm": 1.0545690059661865,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 0.9341,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.22972972972972974,
498
+ "grad_norm": 0.8369587659835815,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 0.9228,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.23310810810810811,
505
+ "grad_norm": 0.8992530703544617,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 0.933,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.23648648648648649,
512
+ "grad_norm": 0.958665132522583,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 0.9219,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.23986486486486486,
519
+ "grad_norm": 0.9970949292182922,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 1.0344,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.24324324324324326,
526
+ "grad_norm": 0.9001803398132324,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 0.9763,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.24662162162162163,
533
+ "grad_norm": 0.9444774985313416,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 0.9402,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.25,
540
+ "grad_norm": 1.1478818655014038,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 0.9338,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.2533783783783784,
547
+ "grad_norm": 1.1998094320297241,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 1.1677,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.25675675675675674,
554
+ "grad_norm": 1.059282660484314,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 0.8556,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.26013513513513514,
561
+ "grad_norm": 1.0620920658111572,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 0.9813,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.2635135135135135,
568
+ "grad_norm": 1.2135953903198242,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 1.035,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.2668918918918919,
575
+ "grad_norm": 1.229359745979309,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 1.0898,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.2702702702702703,
582
+ "grad_norm": 1.1784802675247192,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 1.1225,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.27364864864864863,
589
+ "grad_norm": 1.334152102470398,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 1.1676,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.27702702702702703,
596
+ "grad_norm": 1.5334789752960205,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 1.2391,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.28040540540540543,
603
+ "grad_norm": 1.2976105213165283,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 1.0586,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.28378378378378377,
610
+ "grad_norm": 1.3772521018981934,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 1.0095,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.28716216216216217,
617
+ "grad_norm": 1.498609185218811,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 1.0406,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.2905405405405405,
624
+ "grad_norm": 1.2996132373809814,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 0.9952,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.2939189189189189,
631
+ "grad_norm": 1.400256872177124,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 0.9913,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.2972972972972973,
638
+ "grad_norm": 1.5387816429138184,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 1.0511,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.30067567567567566,
645
+ "grad_norm": 1.6207197904586792,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 1.1016,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.30405405405405406,
652
+ "grad_norm": 1.9668850898742676,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 1.1591,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.30743243243243246,
659
+ "grad_norm": 1.7193620204925537,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 0.8671,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.3108108108108108,
666
+ "grad_norm": 1.715350866317749,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 1.0375,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.3141891891891892,
673
+ "grad_norm": 1.7534435987472534,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 0.9131,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.31756756756756754,
680
+ "grad_norm": 1.7787106037139893,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 0.9613,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.32094594594594594,
687
+ "grad_norm": 1.7678383588790894,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 0.9469,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.32432432432432434,
694
+ "grad_norm": 2.5767292976379395,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 0.8733,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.3277027027027027,
701
+ "grad_norm": 2.0000483989715576,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 0.7498,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.3310810810810811,
708
+ "grad_norm": 2.2624642848968506,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 0.7368,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.3344594594594595,
715
+ "grad_norm": 2.4766733646392822,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 0.8139,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.33783783783783783,
722
+ "grad_norm": 3.698124885559082,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 0.9995,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.33783783783783783,
729
+ "eval_loss": 1.000538945198059,
730
+ "eval_runtime": 46.0594,
731
+ "eval_samples_per_second": 10.834,
732
+ "eval_steps_per_second": 5.428,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5710986748244787e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null