prxy5605 commited on
Commit
1a2b82d
·
verified ·
1 Parent(s): 9021905

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 sha256:9d58533245eb229134b0615975c967f5e555fa015e467e554d94ba9f05542f16
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9cc691fdac667153291911db045d42cbe12929ffe99b1c7122484d29eef80f1
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66479865051de20fd7d4d5d2034bb80a4a03ed4dd0a735e6670b308052307939
3
  size 463916180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bdea0cd94a989c4e8548c54914a7e4d8fd21e29a10f4bda91ec39726775b763
3
  size 463916180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b5a948384b103b752cb6c1c6900dc8a8835be22e3583d4dadb1e3f7e720933f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbd3a3c0783fb7b2338f92d469617c910ce26599a127901d7000d26ae96fd614
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": 0.8194975256919861,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.273972602739726,
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": 6.815,
374
  "eval_steps_per_second": 1.704,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.6594506967154688e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5193338990211487,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.547945205479452,
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": 6.815,
374
  "eval_steps_per_second": 1.704,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.27945205479452057,
379
+ "grad_norm": 7.425979137420654,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 4.607,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.28493150684931506,
386
+ "grad_norm": 5.817314624786377,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 3.4188,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.29041095890410956,
393
+ "grad_norm": 6.273691177368164,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 3.8499,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.2958904109589041,
400
+ "grad_norm": 4.588272571563721,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.4864,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.3013698630136986,
407
+ "grad_norm": 6.175556182861328,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.4496,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.30684931506849317,
414
+ "grad_norm": 6.041647434234619,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 3.4513,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.31232876712328766,
421
+ "grad_norm": 6.051809310913086,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.8065,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.3178082191780822,
428
+ "grad_norm": 5.9933085441589355,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 3.0325,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.3232876712328767,
435
+ "grad_norm": 7.8386054039001465,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 4.0459,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.3287671232876712,
442
+ "grad_norm": 7.559600830078125,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.9939,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.33424657534246577,
449
+ "grad_norm": 5.800102710723877,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.7337,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.33972602739726027,
456
+ "grad_norm": 8.976499557495117,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 4.0395,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.3452054794520548,
463
+ "grad_norm": 8.108333587646484,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 3.0305,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.3506849315068493,
470
+ "grad_norm": 7.5701165199279785,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.9634,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.3561643835616438,
477
+ "grad_norm": 6.603546619415283,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 3.0778,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.36164383561643837,
484
+ "grad_norm": 5.186285495758057,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.3056,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.36712328767123287,
491
+ "grad_norm": 7.2703375816345215,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.7308,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.3726027397260274,
498
+ "grad_norm": 6.352651119232178,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 3.3469,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.3780821917808219,
505
+ "grad_norm": 4.730004787445068,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.4582,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.3835616438356164,
512
+ "grad_norm": 7.018665313720703,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 3.1767,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.38904109589041097,
519
+ "grad_norm": 4.880072116851807,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.5717,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.39452054794520547,
526
+ "grad_norm": 6.6348724365234375,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.8853,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.4,
533
+ "grad_norm": 6.321679592132568,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 3.0309,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.4054794520547945,
540
+ "grad_norm": 5.9580607414245605,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.9534,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.410958904109589,
547
+ "grad_norm": 7.704655170440674,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.8195,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.41643835616438357,
554
+ "grad_norm": 6.245016098022461,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.1046,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.42191780821917807,
561
+ "grad_norm": 6.447231769561768,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 3.0456,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.4273972602739726,
568
+ "grad_norm": 6.793859481811523,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.9127,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.4328767123287671,
575
+ "grad_norm": 7.1470255851745605,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.6011,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.4383561643835616,
582
+ "grad_norm": 7.638210296630859,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.8653,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.4438356164383562,
589
+ "grad_norm": 8.20581340789795,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.5194,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.44931506849315067,
596
+ "grad_norm": 7.874269962310791,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 3.2452,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.4547945205479452,
603
+ "grad_norm": 8.305530548095703,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.7718,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.4602739726027397,
610
+ "grad_norm": 12.325811386108398,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.7301,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.4657534246575342,
617
+ "grad_norm": 7.521613597869873,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.0855,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.4712328767123288,
624
+ "grad_norm": 6.810982704162598,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.8149,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.4767123287671233,
631
+ "grad_norm": 5.873499393463135,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.8463,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.4821917808219178,
638
+ "grad_norm": 8.883861541748047,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.6975,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.4876712328767123,
645
+ "grad_norm": 7.85122537612915,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.1403,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.4931506849315068,
652
+ "grad_norm": 9.159356117248535,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.6294,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.4986301369863014,
659
+ "grad_norm": 11.891826629638672,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 4.7088,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.5041095890410959,
666
+ "grad_norm": 8.85066032409668,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 3.2274,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.5095890410958904,
673
+ "grad_norm": 9.487573623657227,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 3.4859,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.5150684931506849,
680
+ "grad_norm": 6.103641510009766,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.5251,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.5205479452054794,
687
+ "grad_norm": 5.212517738342285,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.3956,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.5260273972602739,
694
+ "grad_norm": 6.487666130065918,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.2505,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.5315068493150685,
701
+ "grad_norm": 4.33821964263916,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.9735,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.536986301369863,
708
+ "grad_norm": 5.6743621826171875,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.1636,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.5424657534246575,
715
+ "grad_norm": 4.478014945983887,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.4474,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.547945205479452,
722
+ "grad_norm": 4.142763137817383,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.6394,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.547945205479452,
729
+ "eval_loss": 0.5193338990211487,
730
+ "eval_runtime": 45.6069,
731
+ "eval_samples_per_second": 6.753,
732
+ "eval_steps_per_second": 1.688,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.307296843104256e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null