aleegis10 commited on
Commit
d33dca1
·
verified ·
1 Parent(s): c44234e

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 sha256:380d7e845812f0bc10261e55674bc5c400fca8a9a71c5da252a0cfdcd9336a8a
3
  size 180385008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7068c6d7d3afedfe23631dd7a779ccbfd98cd1053d078ebefd7ad8c57cf6e30b
3
  size 180385008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fe1ae7e38809bc693dc1dafcbb7a3dfe996eda0327e68dba29dd1f971e19b98
3
  size 91850362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde7816ceac0667dc43f111549d3d262b2f806cfc6c6f28abe6bf433c2e69443
3
  size 91850362
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17aa9c7f67d70cc52594a92658240e655f000c4b5f1484ac47f693666f1ce538
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f0f49b5a732f11d52455d4acbbf5c37d947be6438ba89bd0dcb5c2491fc24d
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": 2.256049871444702,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.6006006006006006,
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": 24.85,
374
  "eval_steps_per_second": 6.212,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.0019312328704e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.191638946533203,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.2012012012012012,
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": 24.85,
374
  "eval_steps_per_second": 6.212,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.6126126126126126,
379
+ "grad_norm": 0.4661988317966461,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.1841,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.6246246246246246,
386
+ "grad_norm": 0.45055660605430603,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.2628,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.6366366366366366,
393
+ "grad_norm": 0.47169768810272217,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.305,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.6486486486486487,
400
+ "grad_norm": 0.47180622816085815,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.2606,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.6606606606606606,
407
+ "grad_norm": 0.47041988372802734,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.2409,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.6726726726726727,
414
+ "grad_norm": 0.454802006483078,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.2503,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.6846846846846847,
421
+ "grad_norm": 0.4808672070503235,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.3921,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.6966966966966966,
428
+ "grad_norm": 0.4827421307563782,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.262,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.7087087087087087,
435
+ "grad_norm": 0.49734070897102356,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.4196,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.7207207207207207,
442
+ "grad_norm": 0.5037516951560974,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.4554,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.7327327327327328,
449
+ "grad_norm": 0.4393552541732788,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.1092,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.7447447447447447,
456
+ "grad_norm": 0.4560452103614807,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.0799,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.7567567567567568,
463
+ "grad_norm": 0.4581015706062317,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.1583,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.7687687687687688,
470
+ "grad_norm": 0.4785716235637665,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.2039,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.7807807807807807,
477
+ "grad_norm": 0.46477729082107544,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.1403,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.7927927927927928,
484
+ "grad_norm": 0.46302974224090576,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.1734,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.8048048048048048,
491
+ "grad_norm": 0.469603955745697,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.2121,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.8168168168168168,
498
+ "grad_norm": 0.48566359281539917,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.216,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.8288288288288288,
505
+ "grad_norm": 0.4689801037311554,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.1911,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.8408408408408409,
512
+ "grad_norm": 0.4652516543865204,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.2589,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.8528528528528528,
519
+ "grad_norm": 0.46898356080055237,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.1985,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.8648648648648649,
526
+ "grad_norm": 0.4824417531490326,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.2688,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.8768768768768769,
533
+ "grad_norm": 0.46958738565444946,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.2605,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.8888888888888888,
540
+ "grad_norm": 0.4817938208580017,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.2527,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.9009009009009009,
547
+ "grad_norm": 0.4745516777038574,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.2814,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.9129129129129129,
554
+ "grad_norm": 0.49045321345329285,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.3105,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.924924924924925,
561
+ "grad_norm": 0.5104289054870605,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.2616,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.9369369369369369,
568
+ "grad_norm": 0.5061110854148865,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.3641,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.948948948948949,
575
+ "grad_norm": 0.49394217133522034,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.4144,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.960960960960961,
582
+ "grad_norm": 0.5313133597373962,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.5564,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.972972972972973,
589
+ "grad_norm": 0.4830684959888458,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.1418,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.984984984984985,
596
+ "grad_norm": 0.47343122959136963,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.1518,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.996996996996997,
603
+ "grad_norm": 0.4916979670524597,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.2134,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.009009009009009,
610
+ "grad_norm": 1.7826623916625977,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 4.0989,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.021021021021021,
617
+ "grad_norm": 0.48136138916015625,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.0882,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.033033033033033,
624
+ "grad_norm": 0.48217904567718506,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.0661,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.045045045045045,
631
+ "grad_norm": 0.4503604769706726,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.0021,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.057057057057057,
638
+ "grad_norm": 0.482292115688324,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.0701,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.069069069069069,
645
+ "grad_norm": 0.47316575050354004,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.0497,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.0810810810810811,
652
+ "grad_norm": 0.48678597807884216,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.1136,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.093093093093093,
659
+ "grad_norm": 0.511247992515564,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.1374,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.105105105105105,
666
+ "grad_norm": 0.48688921332359314,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.1204,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.117117117117117,
673
+ "grad_norm": 0.48262637853622437,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.095,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.1291291291291292,
680
+ "grad_norm": 0.4971187114715576,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.0891,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.1411411411411412,
687
+ "grad_norm": 0.4802643656730652,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.1336,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.1531531531531531,
694
+ "grad_norm": 0.5007813572883606,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.1243,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.165165165165165,
701
+ "grad_norm": 0.48893651366233826,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.0958,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.1771771771771773,
708
+ "grad_norm": 0.4917381703853607,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.2016,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.1891891891891893,
715
+ "grad_norm": 0.5127087235450745,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.1832,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.2012012012012012,
722
+ "grad_norm": 0.5067014098167419,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.2025,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.2012012012012012,
729
+ "eval_loss": 2.191638946533203,
730
+ "eval_runtime": 5.6281,
731
+ "eval_samples_per_second": 24.875,
732
+ "eval_steps_per_second": 6.219,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.99760643063808e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null