prxy5607 commited on
Commit
6cba81a
·
verified ·
1 Parent(s): 01d085d

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 sha256:1bbb87179eae8e75068d8afba019799bff4041d761daff2980631d2861420ff0
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1c70bdad07b43fb6dec3344717637d7f0ddd84d617f97944d6c30cb9e2f9241
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07d069b638f1763e7ab82497e68c5fbd3a79af554d9b422a07265fb8f64d0acd
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd44742212ad53be6b8dcebad26db16bf23dd27ec3554f0d4065a4acd4a7b6ef
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60ce76a4dff5b26e4ea697b2de51c4f02d22b82d4fbfb71c2c1df5d579d52fa9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c9069734b7dd761ee4bb4476dbceb7c403da329ab8969e19f30fe83e7294a91
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": 0.4881606698036194,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.21482277121374865,
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": 14.17,
374
  "eval_steps_per_second": 3.543,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.65350966345728e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.36948394775390625,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.4296455424274973,
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": 14.17,
374
  "eval_steps_per_second": 3.543,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.21911922663802363,
379
+ "grad_norm": 0.44782543182373047,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.3396,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.22341568206229862,
386
+ "grad_norm": 0.5945596098899841,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.4482,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.22771213748657357,
393
+ "grad_norm": 0.5052401423454285,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.4347,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.23200859291084855,
400
+ "grad_norm": 0.4160156548023224,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.4182,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.23630504833512353,
407
+ "grad_norm": 0.3482251763343811,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.4322,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.24060150375939848,
414
+ "grad_norm": 0.3227390944957733,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.4172,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.24489795918367346,
421
+ "grad_norm": 0.29572582244873047,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.3785,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.24919441460794844,
428
+ "grad_norm": 0.35989752411842346,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.3799,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.2534908700322234,
435
+ "grad_norm": 0.385657399892807,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.3866,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2577873254564984,
442
+ "grad_norm": 0.3310921788215637,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.3486,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.2620837808807734,
449
+ "grad_norm": 0.3422428071498871,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.3028,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.2663802363050483,
456
+ "grad_norm": 0.31822556257247925,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.297,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2706766917293233,
463
+ "grad_norm": 0.3344513177871704,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.3756,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.2749731471535983,
470
+ "grad_norm": 0.2931362986564636,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.4118,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.27926960257787325,
477
+ "grad_norm": 0.3394784927368164,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.3515,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.28356605800214824,
484
+ "grad_norm": 0.317038357257843,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.3846,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.2878625134264232,
491
+ "grad_norm": 0.27550095319747925,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.3494,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2921589688506982,
498
+ "grad_norm": 0.3647957146167755,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.3669,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.2964554242749731,
505
+ "grad_norm": 0.34974852204322815,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.3403,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.3007518796992481,
512
+ "grad_norm": 0.35612866282463074,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.3475,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.3050483351235231,
519
+ "grad_norm": 0.342788428068161,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.3453,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.30934479054779807,
526
+ "grad_norm": 0.3459738492965698,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.3246,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.31364124597207305,
533
+ "grad_norm": 0.4553300440311432,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.4952,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.317937701396348,
540
+ "grad_norm": 0.37579211592674255,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.3655,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.322234156820623,
547
+ "grad_norm": 0.42491230368614197,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.3746,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.32653061224489793,
554
+ "grad_norm": 0.4613445997238159,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.483,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3308270676691729,
561
+ "grad_norm": 0.43322092294692993,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.3813,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3351235230934479,
568
+ "grad_norm": 0.43508535623550415,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.4426,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3394199785177229,
575
+ "grad_norm": 0.3977321982383728,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.3795,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.34371643394199786,
582
+ "grad_norm": 0.36455708742141724,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.3186,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.34801288936627284,
589
+ "grad_norm": 0.3600999116897583,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.3009,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.3523093447905478,
596
+ "grad_norm": 0.3982136845588684,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.3315,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.35660580021482274,
603
+ "grad_norm": 0.3989538550376892,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.3751,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.3609022556390977,
610
+ "grad_norm": 0.5305337905883789,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.4166,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.3651987110633727,
617
+ "grad_norm": 0.5150339007377625,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.3933,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.3694951664876477,
624
+ "grad_norm": 0.6410700678825378,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.5038,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.37379162191192267,
631
+ "grad_norm": 0.45256391167640686,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.3523,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.37808807733619765,
638
+ "grad_norm": 0.5341379046440125,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.3802,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.38238453276047263,
645
+ "grad_norm": 0.48598381876945496,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.4376,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.3866809881847476,
652
+ "grad_norm": 0.7272056341171265,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.4245,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.39097744360902253,
659
+ "grad_norm": 0.5760740041732788,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.3184,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.3952738990332975,
666
+ "grad_norm": 0.7006295323371887,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.4,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.3995703544575725,
673
+ "grad_norm": 0.635381281375885,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.4197,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.4038668098818475,
680
+ "grad_norm": 0.5333322882652283,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.3237,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.40816326530612246,
687
+ "grad_norm": 0.6799944043159485,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.352,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.41245972073039744,
694
+ "grad_norm": 0.6566717028617859,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.3699,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.4167561761546724,
701
+ "grad_norm": 0.7269343733787537,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.3615,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.42105263157894735,
708
+ "grad_norm": 0.982455313205719,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.5638,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.4253490870032223,
715
+ "grad_norm": 1.0673147439956665,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.3045,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.4296455424274973,
722
+ "grad_norm": 0.8240067362785339,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.2006,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.4296455424274973,
729
+ "eval_loss": 0.36948394775390625,
730
+ "eval_runtime": 27.625,
731
+ "eval_samples_per_second": 14.19,
732
+ "eval_steps_per_second": 3.548,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.330701932691456e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null