prxy5608 commited on
Commit
8ae0413
·
verified ·
1 Parent(s): d50b1e9

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 sha256:8dedffd8550efe6cef1264ca534f2ebfdd3e9298833032c7f316796eeb1b1f05
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab05564fb44196c5cba92d365a858ab95e05f5d8bc72db4656a1e1bd23149531
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea7c19235bf4e5ff6a997efbd1d3c4b826ba06a3cca2fe0892904b272c2b13b6
3
  size 281824770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f54111d2ccd24bd89866b0d094f10aff1f4f7a249c164dd7bad23f974ae3120d
3
  size 281824770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00227713f699917b1c3ffed83e964fa9547c9b417b55a6adb09048496d05dd32
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59eafd554f9dd23e02f02cfe6313d07221fb83f041422662ed1b942860089ced
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": 3.3963160514831543,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.01858045336306206,
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": 41.146,
374
  "eval_steps_per_second": 20.573,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3883562421977088.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.239711284637451,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.03716090672612412,
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": 41.146,
374
  "eval_steps_per_second": 20.573,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0189520624303233,
379
+ "grad_norm": 3.2213802337646484,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 3.7682,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.01932367149758454,
386
+ "grad_norm": 2.897183418273926,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 3.6962,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.019695280564845784,
393
+ "grad_norm": 2.333893299102783,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 3.55,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.020066889632107024,
400
+ "grad_norm": 2.0622718334198,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 3.6484,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.020438498699368264,
407
+ "grad_norm": 1.9058257341384888,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 3.5701,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.020810107766629504,
414
+ "grad_norm": 1.4503419399261475,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 3.4605,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.021181716833890748,
421
+ "grad_norm": 1.41510808467865,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 3.3843,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.021553325901151988,
428
+ "grad_norm": 1.5639384984970093,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 3.2906,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.021924934968413228,
435
+ "grad_norm": 1.5347603559494019,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 3.586,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.022296544035674472,
442
+ "grad_norm": 1.5613843202590942,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 3.3605,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.022668153102935712,
449
+ "grad_norm": 1.5832593441009521,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 3.415,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.023039762170196952,
456
+ "grad_norm": 1.6786587238311768,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 3.3806,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.023411371237458192,
463
+ "grad_norm": 1.6316285133361816,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 3.4167,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.023782980304719436,
470
+ "grad_norm": 1.6437264680862427,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 3.4412,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.024154589371980676,
477
+ "grad_norm": 1.5929906368255615,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 3.379,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.024526198439241916,
484
+ "grad_norm": 1.6711010932922363,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 3.2288,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.02489780750650316,
491
+ "grad_norm": 1.816035509109497,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 3.2581,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0252694165737644,
498
+ "grad_norm": 1.5691595077514648,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 3.3002,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.02564102564102564,
505
+ "grad_norm": 1.7285726070404053,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 3.3853,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.026012634708286884,
512
+ "grad_norm": 1.6965199708938599,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 3.1998,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.026384243775548124,
519
+ "grad_norm": 1.7152042388916016,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 3.304,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.026755852842809364,
526
+ "grad_norm": 1.8366388082504272,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 3.1231,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.027127461910070604,
533
+ "grad_norm": 1.8617119789123535,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 3.3145,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.027499070977331848,
540
+ "grad_norm": 1.8905341625213623,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 3.3134,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.027870680044593088,
547
+ "grad_norm": 1.882635474205017,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 3.3169,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.028242289111854328,
554
+ "grad_norm": 2.0442984104156494,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 3.1649,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.028613898179115572,
561
+ "grad_norm": 1.940576434135437,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 3.1936,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.028985507246376812,
568
+ "grad_norm": 2.0615429878234863,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 3.3171,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.029357116313638052,
575
+ "grad_norm": 2.0494372844696045,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 3.2035,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.029728725380899292,
582
+ "grad_norm": 2.0333774089813232,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 3.1547,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.030100334448160536,
589
+ "grad_norm": 2.141954183578491,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 2.9143,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.030471943515421776,
596
+ "grad_norm": 2.22705340385437,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 3.1911,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.030843552582683016,
603
+ "grad_norm": 2.196378231048584,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 3.2222,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.03121516164994426,
610
+ "grad_norm": 2.2278859615325928,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 3.0329,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.031586770717205497,
617
+ "grad_norm": 2.3488399982452393,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 2.9382,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.031958379784466744,
624
+ "grad_norm": 2.3422460556030273,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 3.1308,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.032329988851727984,
631
+ "grad_norm": 2.4222495555877686,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 2.9883,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.032701597918989224,
638
+ "grad_norm": 2.425354242324829,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 3.1242,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.033073206986250464,
645
+ "grad_norm": 2.56612491607666,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 3.0771,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.033444816053511704,
652
+ "grad_norm": 2.566655397415161,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 2.9399,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.033816425120772944,
659
+ "grad_norm": 2.3641583919525146,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 2.9741,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.03418803418803419,
666
+ "grad_norm": 2.47420334815979,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 2.7321,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03455964325529543,
673
+ "grad_norm": 2.7138381004333496,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 3.027,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.03493125232255667,
680
+ "grad_norm": 2.655938148498535,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 2.9049,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03530286138981791,
687
+ "grad_norm": 2.87831974029541,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 3.2944,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03567447045707915,
694
+ "grad_norm": 2.891333818435669,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 3.2566,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03604607952434039,
701
+ "grad_norm": 2.8243558406829834,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 3.1022,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.03641768859160163,
708
+ "grad_norm": 3.1256723403930664,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 3.3878,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03678929765886288,
715
+ "grad_norm": 3.284562349319458,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 3.376,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.03716090672612412,
722
+ "grad_norm": 3.2456462383270264,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 3.7382,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.03716090672612412,
729
+ "eval_loss": 3.239711284637451,
730
+ "eval_runtime": 109.8084,
731
+ "eval_samples_per_second": 41.272,
732
+ "eval_steps_per_second": 20.636,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 7747803637874688.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null