bbytxt commited on
Commit
bd2ca9f
·
verified ·
1 Parent(s): 43bb5da

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 sha256:01978505775e75aa75ad77fe9c1686467c99e6603062cdbf08119b09c06b4d0d
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1033432107bb453250512855bb4417555fb261809e1513428bad2c18002473
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:949c2ff6b2d749bd4d72a02675491e754d1438c7ff1e393da730d0f0f3df8e33
3
  size 156656510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ae8dfb1b88d4dfc431b29329c34520fa281e9dfc7bbba64cf6fb35fc81f89b
3
  size 156656510
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4e5696617cb3185657b9b9114762baf127062e4b4345287d34431920aa2f8bc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf69b39deaf4ceca685dfbcc23736d2b58b7133cb9b3922c08857d6baece73ab
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79f5b4ba066d00b62be68b9f9ec9376def1ffea9a45f98d620f3198033186a6a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.0112826824188232,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.008557980316645272,
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": 38.87,
374
  "eval_steps_per_second": 19.435,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1928297315303424.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.9608962535858154,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.017115960633290545,
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": 38.87,
374
  "eval_steps_per_second": 19.435,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008729139922978177,
379
+ "grad_norm": 0.24028153717517853,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 1.8849,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008900299529311083,
386
+ "grad_norm": 0.2163541167974472,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 1.9064,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.009071459135643988,
393
+ "grad_norm": 0.1897958517074585,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 1.962,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.009242618741976894,
400
+ "grad_norm": 0.1701580286026001,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 1.8102,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.009413778348309799,
407
+ "grad_norm": 0.17404377460479736,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 1.7162,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009584937954642705,
414
+ "grad_norm": 0.16066402196884155,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 1.7332,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.00975609756097561,
421
+ "grad_norm": 0.15609973669052124,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 1.7929,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009927257167308514,
428
+ "grad_norm": 0.15920859575271606,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 1.8153,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01009841677364142,
435
+ "grad_norm": 0.1596253216266632,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 1.8854,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.010269576379974325,
442
+ "grad_norm": 0.136519655585289,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 1.9049,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.010440735986307232,
449
+ "grad_norm": 0.1335257738828659,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 1.8594,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.010611895592640136,
456
+ "grad_norm": 0.1406267285346985,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 2.0214,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.010783055198973043,
463
+ "grad_norm": 0.11417517811059952,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 1.9628,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010954214805305947,
470
+ "grad_norm": 0.12227802723646164,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 1.9979,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.011125374411638854,
477
+ "grad_norm": 0.11370483040809631,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 1.9422,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.011296534017971758,
484
+ "grad_norm": 0.09835387021303177,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 1.8134,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.011467693624304665,
491
+ "grad_norm": 0.11144676804542542,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 2.1119,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01163885323063757,
498
+ "grad_norm": 0.09735066443681717,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 1.827,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011810012836970476,
505
+ "grad_norm": 0.10068103671073914,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 1.8899,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01198117244330338,
512
+ "grad_norm": 0.10140778869390488,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 2.0218,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.012152332049636286,
519
+ "grad_norm": 0.0990547463297844,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 1.981,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.012323491655969191,
526
+ "grad_norm": 0.1076335459947586,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 1.9312,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.012494651262302097,
533
+ "grad_norm": 0.11169704794883728,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 1.9669,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.012665810868635002,
540
+ "grad_norm": 0.10578777641057968,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 1.8923,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012836970474967908,
547
+ "grad_norm": 0.1006617322564125,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 1.9088,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.013008130081300813,
554
+ "grad_norm": 0.11208891868591309,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 1.9875,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.013179289687633718,
561
+ "grad_norm": 0.1086820513010025,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 1.979,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.013350449293966624,
568
+ "grad_norm": 0.11209630221128464,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 2.0093,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.013521608900299529,
575
+ "grad_norm": 0.1047407016158104,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 2.0194,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.013692768506632435,
582
+ "grad_norm": 0.10114631056785583,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 1.9117,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01386392811296534,
589
+ "grad_norm": 0.10660432279109955,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 2.1128,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.014035087719298246,
596
+ "grad_norm": 0.10562874376773834,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 1.819,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.01420624732563115,
603
+ "grad_norm": 0.1116420328617096,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 2.0161,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.014377406931964057,
610
+ "grad_norm": 0.1135152131319046,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 1.9062,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.014548566538296961,
617
+ "grad_norm": 0.11426131427288055,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 1.8512,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.014719726144629868,
624
+ "grad_norm": 0.11805808544158936,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 1.862,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.014890885750962772,
631
+ "grad_norm": 0.11407601833343506,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 1.9902,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.015062045357295679,
638
+ "grad_norm": 0.12108225375413895,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 2.0695,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.015233204963628583,
645
+ "grad_norm": 0.1370498389005661,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 1.9937,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.01540436456996149,
652
+ "grad_norm": 0.13261045515537262,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 1.9162,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.015575524176294394,
659
+ "grad_norm": 0.13481606543064117,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 1.7693,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0157466837826273,
666
+ "grad_norm": 0.13738499581813812,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 1.9906,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.015917843388960205,
673
+ "grad_norm": 0.14677368104457855,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 1.6928,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.01608900299529311,
680
+ "grad_norm": 0.16111257672309875,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 1.9891,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.016260162601626018,
687
+ "grad_norm": 0.1692948341369629,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 1.8375,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.016431322207958923,
694
+ "grad_norm": 0.21693989634513855,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 1.9869,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.016602481814291827,
701
+ "grad_norm": 0.23700051009655,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 2.1276,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.016773641420624732,
708
+ "grad_norm": 0.29915517568588257,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 2.3728,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.016944801026957636,
715
+ "grad_norm": 0.4070492386817932,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 2.1064,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.017115960633290545,
722
+ "grad_norm": 0.7625799775123596,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 2.4645,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.017115960633290545,
729
+ "eval_loss": 1.9608962535858154,
730
+ "eval_runtime": 254.4528,
731
+ "eval_samples_per_second": 38.671,
732
+ "eval_steps_per_second": 19.336,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3850414190493696.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null