0x1202 commited on
Commit
8aa8bf3
·
verified ·
1 Parent(s): ddfbb3a

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 sha256:33a9f82f06f582e81083b06b025d3132023992289ed1dd05caf24047beb4d212
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35af5362202818eed243e291413d57f107bbe0eb2d518f0dd13b631e00bbfc61
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8963732e1d1d0d91866e8b738950c2fcd977d0e4698b01e67696c3ac8188eb5e
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7aa2846ebfa1b6435eab6b11c98501d26941365b7f728a4fe02236f0c1ab10
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1db43b7bf9f52c38092e80b77f5d27987f6e7ddc9cd2265198eec86f2e59935f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac37a0be0d13420c8a252f6e8d22b4b4cbc00b6e1a253cbd17e71c56ce7820f8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7677202820777893,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.06858710562414266,
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": 11.779,
374
  "eval_steps_per_second": 2.945,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.849925068141363e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.672206699848175,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.13717421124828533,
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": 11.779,
374
  "eval_steps_per_second": 2.945,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.06995884773662552,
379
+ "grad_norm": 0.8886013627052307,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.0666,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07133058984910837,
386
+ "grad_norm": 0.9581699967384338,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.0,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.07270233196159122,
393
+ "grad_norm": 0.7953754663467407,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.0147,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.07407407407407407,
400
+ "grad_norm": 0.7907536029815674,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.8676,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.07544581618655692,
407
+ "grad_norm": 0.7577344179153442,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.9509,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.07681755829903979,
414
+ "grad_norm": 0.980762779712677,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.8895,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.07818930041152264,
421
+ "grad_norm": 0.8946378827095032,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.867,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.07956104252400549,
428
+ "grad_norm": 0.9008687734603882,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.8059,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08093278463648834,
435
+ "grad_norm": 0.8883490562438965,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.7215,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0823045267489712,
442
+ "grad_norm": 0.8660940527915955,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.705,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.08367626886145405,
449
+ "grad_norm": 0.8446040153503418,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.8148,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0850480109739369,
456
+ "grad_norm": 0.7114365696907043,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.7353,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.08641975308641975,
463
+ "grad_norm": 0.6913666725158691,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.7051,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0877914951989026,
470
+ "grad_norm": 0.7440309524536133,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.6897,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.08916323731138547,
477
+ "grad_norm": 0.6593201756477356,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.7488,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.09053497942386832,
484
+ "grad_norm": 0.8882130980491638,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.7327,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.09190672153635117,
491
+ "grad_norm": 0.7141872644424438,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.763,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.09327846364883402,
498
+ "grad_norm": 0.7310812473297119,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.6181,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.09465020576131687,
505
+ "grad_norm": 0.6965682506561279,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.736,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.09602194787379972,
512
+ "grad_norm": 0.6382268071174622,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.666,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.09739368998628258,
519
+ "grad_norm": 0.738567054271698,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.7502,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.09876543209876543,
526
+ "grad_norm": 0.7237371802330017,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.7352,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.10013717421124829,
533
+ "grad_norm": 0.6134920716285706,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.699,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.10150891632373114,
540
+ "grad_norm": 0.6023762822151184,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.5733,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.102880658436214,
547
+ "grad_norm": 0.7722994685173035,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.712,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.10425240054869685,
554
+ "grad_norm": 0.6359792351722717,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.6032,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.1056241426611797,
561
+ "grad_norm": 1.0157991647720337,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.6771,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.10699588477366255,
568
+ "grad_norm": 0.7552648186683655,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.8228,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.1083676268861454,
575
+ "grad_norm": 0.6754823923110962,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.7058,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.10973936899862825,
582
+ "grad_norm": 0.7087421417236328,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.7568,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.1111111111111111,
589
+ "grad_norm": 0.907531201839447,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.7217,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.11248285322359397,
596
+ "grad_norm": 0.6867223381996155,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.6275,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.11385459533607682,
603
+ "grad_norm": 0.6423940658569336,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.5992,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.11522633744855967,
610
+ "grad_norm": 0.7836233973503113,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.7563,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.11659807956104253,
617
+ "grad_norm": 0.7429043054580688,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.7826,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.11796982167352538,
624
+ "grad_norm": 0.7121160626411438,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.6765,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.11934156378600823,
631
+ "grad_norm": 0.6519823670387268,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.6412,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.12071330589849108,
638
+ "grad_norm": 0.7616689801216125,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.6675,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.12208504801097393,
645
+ "grad_norm": 0.7042734026908875,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.6333,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.12345679012345678,
652
+ "grad_norm": 0.7615177035331726,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.6755,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.12482853223593965,
659
+ "grad_norm": 0.6770451068878174,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.6777,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1262002743484225,
666
+ "grad_norm": 0.7251375913619995,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.7271,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.12757201646090535,
673
+ "grad_norm": 0.762030839920044,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.7694,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.1289437585733882,
680
+ "grad_norm": 0.7940636873245239,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.67,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.13031550068587106,
687
+ "grad_norm": 0.7140344381332397,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.7463,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.13168724279835392,
694
+ "grad_norm": 0.8514577150344849,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.7389,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.13305898491083676,
701
+ "grad_norm": 0.8461818099021912,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.7734,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.13443072702331962,
708
+ "grad_norm": 0.6528753042221069,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.5591,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.13580246913580246,
715
+ "grad_norm": 0.829468846321106,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.693,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.13717421124828533,
722
+ "grad_norm": 0.6663625240325928,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.5723,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.13717421124828533,
729
+ "eval_loss": 0.672206699848175,
730
+ "eval_runtime": 104.206,
731
+ "eval_samples_per_second": 11.784,
732
+ "eval_steps_per_second": 2.946,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5733112530639258e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null