brixeus commited on
Commit
f2cf35a
·
verified ·
1 Parent(s): cfd4cf8

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 sha256:122465abc635566cec3e9893252fffff29136020502638903654256e55762434
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b43824e1496694355ed79957dd9541c6926bedbc4167e95c1e9e0078e14e530
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d1d8833a85e92ed7826e9b515c48332d62694fb4d7d53d2b61571615301c31d
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2fe9563d4a2a89618e2915503614f5bd5b5a41eef0d25c4f74ab69c9d3fcca
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c49b766bbad8374c2fb10d916ca56f20ec77fd773e4fcc32d8a9cd800c8e53e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3514cbecf0d7e207fb8bf90bd483caade5f5181dd0b1292bc044d61598ee582a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1315d7eec29cf9168c9f163c958c5df6ae2472b96d8ab0aa2f59aeca18e9936b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70676b886bdad671d073176c81ea76c66ddac446539f48ac64f4e9bef2e2a776
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3599679470062256,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.8658008658008658,
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": 21.077,
374
  "eval_steps_per_second": 5.432,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.9668765675290624e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3433974981307983,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.7359307359307359,
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": 21.077,
374
  "eval_steps_per_second": 5.432,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.8831168831168831,
379
+ "grad_norm": 0.5181626081466675,
380
+ "learning_rate": 8.518457335743926e-05,
381
+ "loss": 1.4489,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.9004329004329005,
386
+ "grad_norm": 0.5752385854721069,
387
+ "learning_rate": 8.449338172278059e-05,
388
+ "loss": 1.5145,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.9177489177489178,
393
+ "grad_norm": 0.65139240026474,
394
+ "learning_rate": 8.378937720492384e-05,
395
+ "loss": 1.4028,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.935064935064935,
400
+ "grad_norm": 0.8399358987808228,
401
+ "learning_rate": 8.307282131280804e-05,
402
+ "loss": 1.5549,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.9523809523809523,
407
+ "grad_norm": 0.9761013388633728,
408
+ "learning_rate": 8.23439802176954e-05,
409
+ "loss": 1.5483,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.9696969696969697,
414
+ "grad_norm": 1.5134563446044922,
415
+ "learning_rate": 8.160312465429952e-05,
416
+ "loss": 1.4882,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.987012987012987,
421
+ "grad_norm": 0.37874630093574524,
422
+ "learning_rate": 8.085052982021847e-05,
423
+ "loss": 1.2874,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.0086580086580086,
428
+ "grad_norm": 0.8670079708099365,
429
+ "learning_rate": 8.008647527371023e-05,
430
+ "loss": 1.9227,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.025974025974026,
435
+ "grad_norm": 0.28728023171424866,
436
+ "learning_rate": 7.931124482984802e-05,
437
+ "loss": 1.2465,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.0432900432900434,
442
+ "grad_norm": 0.2963547110557556,
443
+ "learning_rate": 7.85251264550948e-05,
444
+ "loss": 1.1765,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.0606060606060606,
449
+ "grad_norm": 0.3141789138317108,
450
+ "learning_rate": 7.772841216033533e-05,
451
+ "loss": 1.1228,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.077922077922078,
456
+ "grad_norm": 0.32667580246925354,
457
+ "learning_rate": 7.692139789240611e-05,
458
+ "loss": 1.1514,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.0952380952380953,
463
+ "grad_norm": 0.3543757200241089,
464
+ "learning_rate": 7.610438342416319e-05,
465
+ "loss": 1.0842,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.1125541125541125,
470
+ "grad_norm": 0.367701917886734,
471
+ "learning_rate": 7.527767224312883e-05,
472
+ "loss": 1.1141,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.12987012987013,
477
+ "grad_norm": 0.4170190989971161,
478
+ "learning_rate": 7.44415714387582e-05,
479
+ "loss": 1.3028,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.1471861471861473,
484
+ "grad_norm": 0.44387149810791016,
485
+ "learning_rate": 7.359639158836828e-05,
486
+ "loss": 1.1789,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.1645021645021645,
491
+ "grad_norm": 0.46756917238235474,
492
+ "learning_rate": 7.274244664177097e-05,
493
+ "loss": 1.2253,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.1818181818181819,
498
+ "grad_norm": 0.5271068215370178,
499
+ "learning_rate": 7.188005380465364e-05,
500
+ "loss": 1.0931,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.199134199134199,
505
+ "grad_norm": 0.5228838920593262,
506
+ "learning_rate": 7.10095334207501e-05,
507
+ "loss": 0.9346,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.2164502164502164,
512
+ "grad_norm": 0.7063124775886536,
513
+ "learning_rate": 7.013120885284598e-05,
514
+ "loss": 1.1747,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.2337662337662338,
519
+ "grad_norm": 1.0697877407073975,
520
+ "learning_rate": 6.924540636266272e-05,
521
+ "loss": 1.2499,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.251082251082251,
526
+ "grad_norm": 0.7471345067024231,
527
+ "learning_rate": 6.835245498966461e-05,
528
+ "loss": 0.8715,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.2683982683982684,
533
+ "grad_norm": 0.3865669071674347,
534
+ "learning_rate": 6.745268642883404e-05,
535
+ "loss": 1.2091,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.2857142857142856,
540
+ "grad_norm": 0.3613302409648895,
541
+ "learning_rate": 6.654643490746042e-05,
542
+ "loss": 1.1159,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.303030303030303,
547
+ "grad_norm": 0.38617178797721863,
548
+ "learning_rate": 6.563403706098833e-05,
549
+ "loss": 1.1253,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.3203463203463204,
554
+ "grad_norm": 0.4121956527233124,
555
+ "learning_rate": 6.471583180797121e-05,
556
+ "loss": 1.1525,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.3376623376623376,
561
+ "grad_norm": 0.42778268456459045,
562
+ "learning_rate": 6.379216022417696e-05,
563
+ "loss": 1.1418,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.354978354978355,
568
+ "grad_norm": 0.47594478726387024,
569
+ "learning_rate": 6.286336541589224e-05,
570
+ "loss": 1.2353,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.3722943722943723,
575
+ "grad_norm": 0.46286624670028687,
576
+ "learning_rate": 6.192979239247243e-05,
577
+ "loss": 1.1018,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.3896103896103895,
582
+ "grad_norm": 0.4925539195537567,
583
+ "learning_rate": 6.0991787938184784e-05,
584
+ "loss": 1.0574,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.406926406926407,
589
+ "grad_norm": 0.5687847137451172,
590
+ "learning_rate": 6.004970048339226e-05,
591
+ "loss": 1.2203,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.4242424242424243,
596
+ "grad_norm": 0.6070426106452942,
597
+ "learning_rate": 5.910387997512573e-05,
598
+ "loss": 1.2845,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.4415584415584415,
603
+ "grad_norm": 0.6566668152809143,
604
+ "learning_rate": 5.8154677747093134e-05,
605
+ "loss": 1.1189,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.4588744588744589,
610
+ "grad_norm": 0.8260652422904968,
611
+ "learning_rate": 5.7202446389173223e-05,
612
+ "loss": 1.1718,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.4761904761904763,
617
+ "grad_norm": 1.1566524505615234,
618
+ "learning_rate": 5.624753961644281e-05,
619
+ "loss": 0.8529,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.4935064935064934,
624
+ "grad_norm": 1.3062056303024292,
625
+ "learning_rate": 5.5290312137786146e-05,
626
+ "loss": 0.9415,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.5108225108225108,
631
+ "grad_norm": 0.34991952776908875,
632
+ "learning_rate": 5.433111952413495e-05,
633
+ "loss": 1.213,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.5281385281385282,
638
+ "grad_norm": 0.3678584098815918,
639
+ "learning_rate": 5.33703180763884e-05,
640
+ "loss": 1.1127,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.5454545454545454,
645
+ "grad_norm": 0.3730531334877014,
646
+ "learning_rate": 5.240826469306187e-05,
647
+ "loss": 1.1213,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.5627705627705628,
652
+ "grad_norm": 0.385711669921875,
653
+ "learning_rate": 5.144531673771363e-05,
654
+ "loss": 1.0606,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.5800865800865802,
659
+ "grad_norm": 0.4201517701148987,
660
+ "learning_rate": 5.048183190619904e-05,
661
+ "loss": 1.1155,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.5974025974025974,
666
+ "grad_norm": 0.43522825837135315,
667
+ "learning_rate": 4.951816809380097e-05,
668
+ "loss": 1.1036,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.6147186147186146,
673
+ "grad_norm": 0.46107161045074463,
674
+ "learning_rate": 4.855468326228638e-05,
675
+ "loss": 1.0929,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.6320346320346322,
680
+ "grad_norm": 0.5166659355163574,
681
+ "learning_rate": 4.759173530693814e-05,
682
+ "loss": 1.1499,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.6493506493506493,
687
+ "grad_norm": 0.5847046375274658,
688
+ "learning_rate": 4.6629681923611603e-05,
689
+ "loss": 1.2884,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.6666666666666665,
694
+ "grad_norm": 0.6265720725059509,
695
+ "learning_rate": 4.566888047586507e-05,
696
+ "loss": 1.2245,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.6839826839826841,
701
+ "grad_norm": 0.7204932570457458,
702
+ "learning_rate": 4.4709687862213866e-05,
703
+ "loss": 1.0221,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.7012987012987013,
708
+ "grad_norm": 0.8253524899482727,
709
+ "learning_rate": 4.3752460383557195e-05,
710
+ "loss": 0.915,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.7186147186147185,
715
+ "grad_norm": 1.2134804725646973,
716
+ "learning_rate": 4.27975536108268e-05,
717
+ "loss": 1.0184,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.7359307359307359,
722
+ "grad_norm": 0.7511556148529053,
723
+ "learning_rate": 4.1845322252906864e-05,
724
+ "loss": 0.8647,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.7359307359307359,
729
+ "eval_loss": 1.3433974981307983,
730
+ "eval_runtime": 4.5988,
731
+ "eval_samples_per_second": 21.092,
732
+ "eval_steps_per_second": 5.436,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 5.933753135058125e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null