prxy5606 commited on
Commit
4bf4abc
·
verified ·
1 Parent(s): b304370

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 sha256:10a562e3b54256e648e8e763db4534fca8ff50159916cb9f3f734b2e9b3a87dc
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972aa9ffe87080f27071031d0e4d226dffe8f3ed6fbff6743ae8a659ec8ab968
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:799e1de59c7fb54c830829de04ad12f2e2e53bc837c474c81657015f76ec40b8
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f24c0296a81f84cf38b6c10994df2d8d2d5bea05eb21e5ea6ae4aeae9b1d22
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd5908c818a08129a979c62e339b8331e05a2b0fe5c4ab8a7ba6f3a3f27e6e99
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e394433f831db42905c4a4dcb8562be06e854e5b31c169d95b91d32afffc57
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": 1.6396291255950928,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.5076142131979695,
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": 21.654,
374
  "eval_steps_per_second": 5.479,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.1132769329414144e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5486623048782349,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.015228426395939,
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": 21.654,
374
  "eval_steps_per_second": 5.479,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5177664974619289,
379
+ "grad_norm": 0.5438342690467834,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.6741,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.5279187817258884,
386
+ "grad_norm": 0.480343222618103,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.6306,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.5380710659898477,
393
+ "grad_norm": 0.4987044036388397,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.6827,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.5482233502538071,
400
+ "grad_norm": 0.5006952881813049,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.7046,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.5583756345177665,
407
+ "grad_norm": 0.5399014949798584,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.6806,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.5685279187817259,
414
+ "grad_norm": 0.5678799152374268,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.7275,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.5786802030456852,
421
+ "grad_norm": 0.5736947059631348,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.8071,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.5888324873096447,
428
+ "grad_norm": 0.5423876047134399,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.6724,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.5989847715736041,
435
+ "grad_norm": 0.6047144532203674,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.7872,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.6091370558375635,
442
+ "grad_norm": 0.5819637179374695,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.7783,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.6192893401015228,
449
+ "grad_norm": 0.6512382626533508,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.6646,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.6294416243654822,
456
+ "grad_norm": 0.6138646602630615,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.7131,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.6395939086294417,
463
+ "grad_norm": 0.6422168016433716,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.6838,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.649746192893401,
470
+ "grad_norm": 0.6840230226516724,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.7402,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.6598984771573604,
477
+ "grad_norm": 0.6549532413482666,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.6616,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.6700507614213198,
484
+ "grad_norm": 0.742430567741394,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.6679,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.6802030456852792,
491
+ "grad_norm": 0.7295668721199036,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.6294,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.6903553299492385,
498
+ "grad_norm": 0.8265715837478638,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.8901,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.700507614213198,
505
+ "grad_norm": 0.7593281269073486,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.5688,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.7106598984771574,
512
+ "grad_norm": 0.8952975869178772,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.7755,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.7208121827411168,
519
+ "grad_norm": 1.0053350925445557,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.5932,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.7309644670050761,
526
+ "grad_norm": 0.9705185294151306,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.5989,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.7411167512690355,
533
+ "grad_norm": 0.4911041557788849,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.708,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.751269035532995,
540
+ "grad_norm": 0.5251993536949158,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.8025,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.7614213197969543,
547
+ "grad_norm": 0.5147970914840698,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.5758,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.7715736040609137,
554
+ "grad_norm": 0.5723939538002014,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.7717,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.7817258883248731,
561
+ "grad_norm": 0.5487803816795349,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.6682,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.7918781725888325,
568
+ "grad_norm": 0.5720694065093994,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.7009,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.8020304568527918,
575
+ "grad_norm": 0.5712814927101135,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.6973,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.8121827411167513,
582
+ "grad_norm": 0.5587448477745056,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.5849,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.8223350253807107,
589
+ "grad_norm": 0.6082424521446228,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.7704,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.8324873096446701,
596
+ "grad_norm": 0.6438080072402954,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.7454,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.8426395939086294,
603
+ "grad_norm": 0.6118745803833008,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.5767,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.8527918781725888,
610
+ "grad_norm": 0.6005804538726807,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.5711,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.8629441624365483,
617
+ "grad_norm": 0.6292843222618103,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.5878,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.8730964467005076,
624
+ "grad_norm": 0.6168345808982849,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.4827,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.883248730964467,
631
+ "grad_norm": 0.6699876189231873,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.6753,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.8934010152284264,
638
+ "grad_norm": 0.7486642003059387,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.5591,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.9035532994923858,
645
+ "grad_norm": 0.716096818447113,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.5256,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.9137055837563451,
652
+ "grad_norm": 0.6980071663856506,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.6128,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.9238578680203046,
659
+ "grad_norm": 0.776879072189331,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.5798,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.934010152284264,
666
+ "grad_norm": 0.8649686574935913,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.6465,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.9441624365482234,
673
+ "grad_norm": 0.8168870210647583,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.7388,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.9543147208121827,
680
+ "grad_norm": 0.836371123790741,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.5316,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.9644670050761421,
687
+ "grad_norm": 0.975714385509491,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.6221,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.9746192893401016,
694
+ "grad_norm": 1.0654964447021484,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.6136,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.9847715736040609,
701
+ "grad_norm": 0.6085041165351868,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.6456,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.9949238578680203,
708
+ "grad_norm": 0.7240885496139526,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.5469,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.0050761421319796,
715
+ "grad_norm": 1.5985159873962402,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.3111,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.015228426395939,
722
+ "grad_norm": 0.5017366409301758,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.5656,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.015228426395939,
729
+ "eval_loss": 1.5486623048782349,
730
+ "eval_runtime": 7.6734,
731
+ "eval_samples_per_second": 21.633,
732
+ "eval_steps_per_second": 5.473,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4.2084252647424e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null