prxy5605 commited on
Commit
910d8e8
·
verified ·
1 Parent(s): 5c5231f

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 sha256:8a807bac799b3c3e25f78f1a49867e4c36a6a37ace1ac1b81ed70c5887e4ca49
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97efde25644ce733034b4eb47814f39b31f4de0df69051a60d92636f50451312
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dc4ec48d2948e7d6e6dab1eea064c4155b61254f6d80dc8ce1f52111cbfee11
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7ec2ad0192a041371aa1964a96d6270dcecf67aed6e4fb9a23d19a23b90b36
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:594d010b9f3f06c578b9018f352bd28e7b181a4c1e3fa69885c911e625764908
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a416455331f137495054250517b3069fa88696bc8153f10063ef17ad6e64d86a
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": 1.3878036737442017,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.02178886588953045,
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": 12.16,
374
  "eval_steps_per_second": 6.081,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.171470498830746e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3684649467468262,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0435777317790609,
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": 12.16,
374
  "eval_steps_per_second": 6.081,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.02222464320732106,
379
+ "grad_norm": 0.7175142168998718,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 1.3437,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.022660420525111667,
386
+ "grad_norm": 0.7583256363868713,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 1.3406,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.023096197842902278,
393
+ "grad_norm": 0.677870512008667,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 1.467,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.023531975160692886,
400
+ "grad_norm": 0.725477397441864,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 1.3124,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.023967752478483494,
407
+ "grad_norm": 0.683293342590332,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 1.4094,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.024403529796274102,
414
+ "grad_norm": 0.7447341084480286,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 1.3858,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.024839307114064714,
421
+ "grad_norm": 0.759089469909668,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 1.3845,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.025275084431855322,
428
+ "grad_norm": 0.6921642422676086,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 1.4491,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.02571086174964593,
435
+ "grad_norm": 0.6369518637657166,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 1.3408,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.02614663906743654,
442
+ "grad_norm": 0.7366051077842712,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 1.4087,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.02658241638522715,
449
+ "grad_norm": 0.7187365293502808,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 1.3983,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.027018193703017758,
456
+ "grad_norm": 0.7734277844429016,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 1.5799,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.027453971020808366,
463
+ "grad_norm": 0.6761085391044617,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 1.3576,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.027889748338598978,
470
+ "grad_norm": 0.783863365650177,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 1.4574,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.028325525656389586,
477
+ "grad_norm": 0.7435303330421448,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 1.4734,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.028761302974180194,
484
+ "grad_norm": 0.7461963891983032,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 1.4228,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.029197080291970802,
491
+ "grad_norm": 0.7791002988815308,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 1.4499,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.029632857609761414,
498
+ "grad_norm": 0.692180335521698,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 1.4522,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.03006863492755202,
505
+ "grad_norm": 0.7467637658119202,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 1.3698,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.03050441224534263,
512
+ "grad_norm": 0.7586157321929932,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 1.454,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.030940189563133238,
519
+ "grad_norm": 0.6296893358230591,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 1.34,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.031375966880923846,
526
+ "grad_norm": 0.8413500189781189,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 1.3662,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.03181174419871446,
533
+ "grad_norm": 0.672438383102417,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 1.3177,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.03224752151650507,
540
+ "grad_norm": 0.7362287044525146,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 1.3813,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.032683298834295674,
547
+ "grad_norm": 0.7228344082832336,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 1.4777,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.033119076152086285,
554
+ "grad_norm": 0.6640066504478455,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 1.3769,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.03355485346987689,
561
+ "grad_norm": 0.6730275750160217,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 1.3875,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0339906307876675,
568
+ "grad_norm": 0.7028450965881348,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 1.4002,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.03442640810545811,
575
+ "grad_norm": 0.6365458369255066,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 1.2605,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03486218542324872,
582
+ "grad_norm": 0.6803222894668579,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 1.38,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.03529796274103933,
589
+ "grad_norm": 0.6870620250701904,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 1.3394,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.03573374005882994,
596
+ "grad_norm": 0.7038113474845886,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 1.4702,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.036169517376620546,
603
+ "grad_norm": 0.637474775314331,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 1.3277,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.03660529469441116,
610
+ "grad_norm": 0.7014281153678894,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 1.405,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.03704107201220176,
617
+ "grad_norm": 0.6626453399658203,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 1.4336,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.03747684932999237,
624
+ "grad_norm": 0.6772466897964478,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 1.3221,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.037912626647782985,
631
+ "grad_norm": 0.7135924100875854,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 1.3905,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.03834840396557359,
638
+ "grad_norm": 0.7085152864456177,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 1.3089,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0387841812833642,
645
+ "grad_norm": 0.7906420826911926,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 1.3709,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.03921995860115481,
652
+ "grad_norm": 0.6890827417373657,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 1.2915,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03965573591894542,
659
+ "grad_norm": 0.6224659085273743,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 1.2344,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.04009151323673603,
666
+ "grad_norm": 0.6973520517349243,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 1.3544,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.040527290554526633,
673
+ "grad_norm": 0.6966316103935242,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 1.2701,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.040963067872317245,
680
+ "grad_norm": 0.7485948801040649,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 1.4688,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.04139884519010786,
687
+ "grad_norm": 0.6849566698074341,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 1.2395,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.04183462250789846,
694
+ "grad_norm": 0.7672956585884094,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 1.2718,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.04227039982568907,
701
+ "grad_norm": 0.7076390385627747,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 1.3193,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.042706177143479684,
708
+ "grad_norm": 0.7060564756393433,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 1.2844,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.04314195446127029,
715
+ "grad_norm": 0.7379676699638367,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 1.2361,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0435777317790609,
722
+ "grad_norm": 0.851557731628418,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 1.3533,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0435777317790609,
729
+ "eval_loss": 1.3684649467468262,
730
+ "eval_runtime": 318.0205,
731
+ "eval_samples_per_second": 12.153,
732
+ "eval_steps_per_second": 6.078,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.4307262039955866e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null