prxy5607 commited on
Commit
b067488
·
verified ·
1 Parent(s): fc6ad3f

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:bb00cc804e7e0b6f1e63863452ae7f93b7fb14f76a7b8c6ae86069078e4e7595
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c011ea615fa8346fb63b6207cec7f0c738cd5aa0ad6c1c4780bbbef382806f
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b446654fc8b7d817785d6a1f8dadc74928239aad070b55d78c29aad1e5c60f15
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:422ac40e7cd3172d33a7ea4a8b9cea20f6afabe807acfa5082f090d79736b3b6
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5f5b3aac7d18d96da45dd1eb4c8774232b922529d95092c9bc2f16dbaf17b7e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39b8a7320cafcd5ff8802e007f9544df0c657ce806f89ddf789e113fb02bb8e1
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": 0.6958192586898804,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.028113578858588697,
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": 49.567,
374
  "eval_steps_per_second": 12.396,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.06657392623616e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5721317529678345,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.056227157717177394,
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": 49.567,
374
  "eval_steps_per_second": 12.396,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.028675850435760472,
379
+ "grad_norm": 1.617163062095642,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.8293,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.029238122012932247,
386
+ "grad_norm": 1.5228155851364136,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.834,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.02980039359010402,
393
+ "grad_norm": 1.3696954250335693,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.8516,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.030362665167275794,
400
+ "grad_norm": 0.9437366724014282,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.7302,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03092493674444757,
407
+ "grad_norm": 0.7396307587623596,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.6234,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.031487208321619345,
414
+ "grad_norm": 0.6352867484092712,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.6283,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03204947989879112,
421
+ "grad_norm": 0.6413976550102234,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.7315,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.03261175147596289,
428
+ "grad_norm": 0.6398018598556519,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.5883,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03317402305313467,
435
+ "grad_norm": 0.6652855277061462,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.6167,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03373629463030644,
442
+ "grad_norm": 0.6662874817848206,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.6626,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.03429856620747821,
449
+ "grad_norm": 0.6972583532333374,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.6922,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.03486083778464998,
456
+ "grad_norm": 0.5826914310455322,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.5906,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.03542310936182176,
463
+ "grad_norm": 0.6414178013801575,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.5979,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.03598538093899353,
470
+ "grad_norm": 0.614965558052063,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.6806,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.036547652516165305,
477
+ "grad_norm": 0.6080766320228577,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.6056,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.037109924093337084,
484
+ "grad_norm": 0.599414587020874,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.5893,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.037672195670508855,
491
+ "grad_norm": 0.6107190847396851,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.6567,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.03823446724768063,
498
+ "grad_norm": 0.6296833157539368,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.6634,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.038796738824852406,
505
+ "grad_norm": 0.6974261999130249,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.5943,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.03935901040202418,
512
+ "grad_norm": 0.650062084197998,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.5836,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.03992128197919595,
519
+ "grad_norm": 0.6339553594589233,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.5484,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04048355355636773,
526
+ "grad_norm": 0.6875646710395813,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.6858,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0410458251335395,
533
+ "grad_norm": 0.64603191614151,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.623,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04160809671071127,
540
+ "grad_norm": 0.6082363128662109,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.5215,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04217036828788305,
547
+ "grad_norm": 0.6290409564971924,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.4936,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.04273263986505482,
554
+ "grad_norm": 0.6085454821586609,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.5462,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.043294911442226594,
561
+ "grad_norm": 0.7018570303916931,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.6391,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.04385718301939837,
568
+ "grad_norm": 0.5906082391738892,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.4946,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.044419454596570145,
575
+ "grad_norm": 0.645088791847229,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.4762,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.044981726173741916,
582
+ "grad_norm": 0.6799085140228271,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.543,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.04554399775091369,
589
+ "grad_norm": 0.6760143041610718,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.5326,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.04610626932808547,
596
+ "grad_norm": 0.6451261639595032,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.4561,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.04666854090525724,
603
+ "grad_norm": 0.6407421231269836,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.4899,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.04723081248242901,
610
+ "grad_norm": 0.659145712852478,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.4942,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.04779308405960079,
617
+ "grad_norm": 0.6394976377487183,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.4354,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.04835535563677256,
624
+ "grad_norm": 0.6170784831047058,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.455,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.04891762721394433,
631
+ "grad_norm": 0.6625480651855469,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.458,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.04947989879111611,
638
+ "grad_norm": 0.6765840649604797,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.3961,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.05004217036828788,
645
+ "grad_norm": 0.6819695234298706,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.5176,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.050604441945459655,
652
+ "grad_norm": 0.7992807626724243,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.4787,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.051166713522631434,
659
+ "grad_norm": 0.6881734132766724,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.4361,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.051728985099803206,
666
+ "grad_norm": 0.7603946328163147,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.4724,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.05229125667697498,
673
+ "grad_norm": 0.8886284828186035,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.5389,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.052853528254146756,
680
+ "grad_norm": 0.7603895664215088,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.5042,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.05341579983131853,
687
+ "grad_norm": 0.8904877305030823,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.6202,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.0539780714084903,
694
+ "grad_norm": 0.726782500743866,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.5166,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.05454034298566207,
701
+ "grad_norm": 0.8900876045227051,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.6052,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.05510261456283385,
708
+ "grad_norm": 0.919487714767456,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.5764,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.05566488614000562,
715
+ "grad_norm": 1.2879389524459839,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.6897,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.056227157717177394,
722
+ "grad_norm": 1.9414801597595215,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.4912,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.056227157717177394,
729
+ "eval_loss": 0.5721317529678345,
730
+ "eval_runtime": 60.446,
731
+ "eval_samples_per_second": 49.548,
732
+ "eval_steps_per_second": 12.391,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.13314785247232e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null