0x1202 commited on
Commit
f611050
·
verified ·
1 Parent(s): 42db88c

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 sha256:0628d4f2a071e648e2094c349d8b579cbfb6e0fe077bcd0d81114699bbfa3230
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7b13319842c308ca7c9e7b3be72f196865baccdeba453ce8daa90facf0a8813
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cef2e2da8c9f2bddfb5d88c1bd105e4e172fa80ede17d01185c31e5c04d597c4
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5cea42f5ecd80d6163cc2ff7029407d2bef933122e0e121b8d0c75298fc58ee
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08808d95ec3aa7cf3c963363e7043c73131136c72c24e78707a17199b72cdfca
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ce16549c5ce648bc4cd70eabfbfffcac03ae175cbb67d6f132b32b27e35e91
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": 1.554507851600647,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.029563932002956393,
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": 11.831,
374
  "eval_steps_per_second": 5.917,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.655837193889382e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5086487531661987,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.059127864005912786,
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": 11.831,
374
  "eval_steps_per_second": 5.917,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03015521064301552,
379
+ "grad_norm": 1.0917247533798218,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 1.5219,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03074648928307465,
386
+ "grad_norm": 0.827164888381958,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 1.1768,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.03133776792313378,
393
+ "grad_norm": 0.6853762865066528,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 1.1451,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.031929046563192905,
400
+ "grad_norm": 0.49232950806617737,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 0.9411,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.032520325203252036,
407
+ "grad_norm": 0.4476233422756195,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 1.1122,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.03311160384331116,
414
+ "grad_norm": 0.4419047236442566,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 1.0147,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03370288248337029,
421
+ "grad_norm": 0.4565959572792053,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 1.0099,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.034294161123429416,
428
+ "grad_norm": 0.4500262439250946,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 1.0234,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03488543976348855,
435
+ "grad_norm": 0.4970146715641022,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 1.1916,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03547671840354767,
442
+ "grad_norm": 0.47627344727516174,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 1.1908,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0360679970436068,
449
+ "grad_norm": 0.4862278401851654,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 1.2919,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.03665927568366593,
456
+ "grad_norm": 0.4928499758243561,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 1.1914,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.03725055432372506,
463
+ "grad_norm": 0.4977535009384155,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 0.9937,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.03784183296378418,
470
+ "grad_norm": 0.5224493741989136,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 1.1944,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.038433111603843315,
477
+ "grad_norm": 0.48349031805992126,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 1.2238,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.03902439024390244,
484
+ "grad_norm": 0.5637966394424438,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 1.0459,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.03961566888396157,
491
+ "grad_norm": 0.48639440536499023,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 1.2357,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.040206947524020695,
498
+ "grad_norm": 0.5311177968978882,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 1.3658,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.040798226164079826,
505
+ "grad_norm": 0.5076618194580078,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 1.2805,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.04138950480413895,
512
+ "grad_norm": 0.5162557363510132,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 1.2492,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04198078344419808,
519
+ "grad_norm": 0.5348551273345947,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 1.2662,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.042572062084257206,
526
+ "grad_norm": 0.60564786195755,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 1.3764,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.04316334072431634,
533
+ "grad_norm": 0.5648425817489624,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 1.2899,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04375461936437546,
540
+ "grad_norm": 0.5424509644508362,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 1.2899,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04434589800443459,
547
+ "grad_norm": 0.5881377458572388,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 1.3669,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.04493717664449372,
554
+ "grad_norm": 0.6511968970298767,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 1.5635,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.04552845528455285,
561
+ "grad_norm": 0.6166760921478271,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 1.4059,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.04611973392461197,
568
+ "grad_norm": 0.6581703424453735,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 1.4527,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.046711012564671105,
575
+ "grad_norm": 0.6670029759407043,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 1.5274,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.04730229120473023,
582
+ "grad_norm": 0.6847637891769409,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 1.5385,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.04789356984478936,
589
+ "grad_norm": 0.6912352442741394,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 1.5992,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.048484848484848485,
596
+ "grad_norm": 0.7077720761299133,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 1.6395,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.049076127124907616,
603
+ "grad_norm": 0.7005457878112793,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 1.6255,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.04966740576496674,
610
+ "grad_norm": 0.7903986573219299,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 1.6549,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.05025868440502587,
617
+ "grad_norm": 0.7845456600189209,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 1.656,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.050849963045084996,
624
+ "grad_norm": 0.7979168891906738,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 1.6816,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.05144124168514413,
631
+ "grad_norm": 0.8112163543701172,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 1.7633,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.05203252032520325,
638
+ "grad_norm": 0.9452254772186279,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 1.7828,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.05262379896526238,
645
+ "grad_norm": 0.9549803137779236,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 1.8957,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.05321507760532151,
652
+ "grad_norm": 0.9207380414009094,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 1.8178,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.05380635624538064,
659
+ "grad_norm": 0.8830947279930115,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 1.7794,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.05439763488543976,
666
+ "grad_norm": 1.052901029586792,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 2.2168,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.054988913525498895,
673
+ "grad_norm": 0.9535877704620361,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 1.8164,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.05558019216555802,
680
+ "grad_norm": 1.0035942792892456,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 1.8322,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.05617147080561715,
687
+ "grad_norm": 1.0457316637039185,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 2.1471,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.056762749445676275,
694
+ "grad_norm": 1.2736159563064575,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 2.2044,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.057354028085735406,
701
+ "grad_norm": 1.1406478881835938,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 1.9954,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.05794530672579453,
708
+ "grad_norm": 1.3486875295639038,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 2.2088,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.05853658536585366,
715
+ "grad_norm": 1.2860016822814941,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 2.2645,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.059127864005912786,
722
+ "grad_norm": 1.523383617401123,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 2.2205,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.059127864005912786,
729
+ "eval_loss": 1.5086487531661987,
730
+ "eval_runtime": 240.7653,
731
+ "eval_samples_per_second": 11.833,
732
+ "eval_steps_per_second": 5.919,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5273960904065024e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null