nttx commited on
Commit
98a3f99
·
verified ·
1 Parent(s): 9c29757

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:b659ce5fe2e4aed2dda723caef8005baad7dcd545a0dde434cfdb8fd5c826e2b
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd6a6bb2377f74ac63612be8875afe306b566f64d25229a77cabd3df7d9a8ce
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5a408de0710aa8b9f3467cfc04a7ec4705b685b22bef2c2b2038087a65cc01a
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:618e68dc60d7bd6a57d782a774e4fa8231e9a264d567f94a2afb69617ebbf245
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae37e1cfed7fc15c4d76ea5604e0057583865b9b0e776d2d984078576aa57a0b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4535e66e10faee8f4ad5952419fef78909e92a02e423ceb9a1ed544966d6656a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.360590934753418,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.18709073900841908,
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": 449.425,
374
  "eval_steps_per_second": 113.854,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2654349164544.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.354866981506348,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.37418147801683815,
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": 449.425,
374
  "eval_steps_per_second": 113.854,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.19083255378858746,
379
+ "grad_norm": 0.09554930776357651,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 10.3688,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.19457436856875585,
386
+ "grad_norm": 0.11902095377445221,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 10.3692,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.19831618334892423,
393
+ "grad_norm": 0.12059039622545242,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 10.3641,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.20205799812909261,
400
+ "grad_norm": 0.10143259167671204,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 10.368,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.205799812909261,
407
+ "grad_norm": 0.09884634613990784,
408
+ "learning_rate": 5e-05,
409
+ "loss": 10.3629,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.20954162768942938,
414
+ "grad_norm": 0.10848794132471085,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 10.3616,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.21328344246959777,
421
+ "grad_norm": 0.13325229287147522,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 10.3641,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.21702525724976612,
428
+ "grad_norm": 0.12123550474643707,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 10.36,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.2207670720299345,
435
+ "grad_norm": 0.10715597867965698,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 10.3617,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2245088868101029,
442
+ "grad_norm": 0.11302831023931503,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 10.3647,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.22825070159027128,
449
+ "grad_norm": 0.12114818394184113,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 10.3587,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.23199251637043966,
456
+ "grad_norm": 0.11377459764480591,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 10.357,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.23573433115060805,
463
+ "grad_norm": 0.12018445879220963,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 10.3685,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.23947614593077643,
470
+ "grad_norm": 0.1285586953163147,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 10.3648,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.2432179607109448,
477
+ "grad_norm": 0.12001438438892365,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 10.3643,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.2469597754911132,
484
+ "grad_norm": 0.1223025992512703,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 10.3576,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.2507015902712816,
491
+ "grad_norm": 0.11740434914827347,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 10.3603,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.25444340505144997,
498
+ "grad_norm": 0.15202081203460693,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 10.3611,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.25818521983161835,
505
+ "grad_norm": 0.1387818604707718,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 10.3537,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.26192703461178674,
512
+ "grad_norm": 0.1355273574590683,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 10.3625,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.2656688493919551,
519
+ "grad_norm": 0.14213471114635468,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 10.3525,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.2694106641721235,
526
+ "grad_norm": 0.14831231534481049,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 10.3529,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2731524789522919,
533
+ "grad_norm": 0.213363915681839,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 10.3541,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.2768942937324602,
540
+ "grad_norm": 0.18954288959503174,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 10.3467,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.2806361085126286,
547
+ "grad_norm": 0.17982767522335052,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 10.3606,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.284377923292797,
554
+ "grad_norm": 0.207661435008049,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 10.35,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.28811973807296537,
561
+ "grad_norm": 0.17610113322734833,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 10.3644,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.29186155285313375,
568
+ "grad_norm": 0.2197764813899994,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 10.3594,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.29560336763330214,
575
+ "grad_norm": 0.22157828509807587,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 10.3587,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.2993451824134705,
582
+ "grad_norm": 0.24235649406909943,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 10.3604,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.3030869971936389,
589
+ "grad_norm": 0.23388098180294037,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 10.3626,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.3068288119738073,
596
+ "grad_norm": 0.261380672454834,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 10.3574,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.3105706267539757,
603
+ "grad_norm": 0.30021607875823975,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 10.3516,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.31431244153414406,
610
+ "grad_norm": 0.2100362479686737,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 10.3579,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.31805425631431244,
617
+ "grad_norm": 0.288947731256485,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 10.3607,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.32179607109448083,
624
+ "grad_norm": 0.27355027198791504,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 10.3402,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3255378858746492,
631
+ "grad_norm": 0.2753260135650635,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 10.3475,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3292797006548176,
638
+ "grad_norm": 0.2534031271934509,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 10.3564,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.333021515434986,
645
+ "grad_norm": 0.2658593952655792,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 10.3543,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.33676333021515437,
652
+ "grad_norm": 0.25391411781311035,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 10.3543,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.34050514499532275,
659
+ "grad_norm": 0.324995756149292,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 10.3548,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.34424695977549113,
666
+ "grad_norm": 0.32911059260368347,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 10.3534,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.3479887745556595,
673
+ "grad_norm": 0.2742116153240204,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 10.3507,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3517305893358279,
680
+ "grad_norm": 0.3698386251926422,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 10.3485,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.35547240411599623,
687
+ "grad_norm": 0.3568093180656433,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 10.3549,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.3592142188961646,
694
+ "grad_norm": 0.3698900043964386,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 10.3409,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.362956033676333,
701
+ "grad_norm": 0.40813785791397095,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 10.3428,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.3666978484565014,
708
+ "grad_norm": 0.34429776668548584,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 10.3661,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.37043966323666977,
715
+ "grad_norm": 0.43575209379196167,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 10.3468,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.37418147801683815,
722
+ "grad_norm": 0.4491109848022461,
723
+ "learning_rate": 0.0,
724
+ "loss": 10.3544,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.37418147801683815,
729
+ "eval_loss": 10.354866981506348,
730
+ "eval_runtime": 0.5101,
731
+ "eval_samples_per_second": 441.125,
732
+ "eval_steps_per_second": 111.752,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 5295622717440.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null