aleegis12 commited on
Commit
7a05459
·
verified ·
1 Parent(s): 776b415

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 sha256:4fd5060da99ce47a9753a8dc413537ae0515987f327a05c7ad1847bbef09a67d
3
  size 42487072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551c1da08245846fb77828d0c5090f9c9b83c67dcef0812e045bf6d3be237b12
3
  size 42487072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7ae7c4111feb97e87629da3f92176d3c073d96d03940230990808b1753deca2
3
  size 21735354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a88023cc957a7df7a2df72a0bef2ca0feebbc4baef012ecda99ab0157a73d3f
3
  size 21735354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:733d5b51f6ab36fdc59083e3068b5ff5c713fb540e3a55506c7dfe42304ce2a6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f4df86ea1431cf80b5b92662734debae0bbc728638a37e9173151f6472d8dee
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": 2.4655730724334717,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.2205071664829107,
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": 95.835,
374
  "eval_steps_per_second": 24.084,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1824574282924032.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.3261044025421143,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.4410143329658214,
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": 95.835,
374
  "eval_steps_per_second": 24.084,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.2249173098125689,
379
+ "grad_norm": 7.9255781173706055,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 10.5467,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.22932745314222713,
386
+ "grad_norm": 7.473238468170166,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 10.2634,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.23373759647188533,
393
+ "grad_norm": 5.979231834411621,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 10.4718,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.23814773980154355,
400
+ "grad_norm": 5.469010353088379,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 10.4348,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.24255788313120177,
407
+ "grad_norm": 4.270541667938232,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 10.1428,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.24696802646085997,
414
+ "grad_norm": 4.045993328094482,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 10.0831,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2513781697905182,
421
+ "grad_norm": 3.583444595336914,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 10.324,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2557883131201764,
428
+ "grad_norm": 3.483198404312134,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 10.1282,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.26019845644983464,
435
+ "grad_norm": 3.4700069427490234,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 10.1232,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.26460859977949286,
442
+ "grad_norm": 3.5300607681274414,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 10.1978,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.269018743109151,
449
+ "grad_norm": 3.4217031002044678,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 9.9816,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.27342888643880925,
456
+ "grad_norm": 3.2927191257476807,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 9.9012,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.27783902976846747,
463
+ "grad_norm": 3.17272686958313,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 9.9606,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.2822491730981257,
470
+ "grad_norm": 3.1798388957977295,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 10.2441,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.2866593164277839,
477
+ "grad_norm": 3.097712278366089,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 9.5621,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.29106945975744214,
484
+ "grad_norm": 3.1934633255004883,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 10.0037,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.2954796030871003,
491
+ "grad_norm": 2.925327777862549,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 10.0632,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.29988974641675853,
498
+ "grad_norm": 2.76534366607666,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 9.8498,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.30429988974641675,
505
+ "grad_norm": 2.9064295291900635,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 9.7779,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.308710033076075,
512
+ "grad_norm": 3.097909688949585,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 9.9231,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.3131201764057332,
519
+ "grad_norm": 2.8864567279815674,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 9.5838,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.3175303197353914,
526
+ "grad_norm": 2.7767820358276367,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 9.9516,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.3219404630650496,
533
+ "grad_norm": 2.8595311641693115,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 9.6969,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3263506063947078,
540
+ "grad_norm": 2.894693613052368,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 9.8685,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.33076074972436603,
547
+ "grad_norm": 2.824695587158203,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 9.8168,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.33517089305402425,
554
+ "grad_norm": 2.9962146282196045,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 9.6154,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3395810363836825,
561
+ "grad_norm": 2.707134962081909,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 9.7863,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3439911797133407,
568
+ "grad_norm": 2.5159194469451904,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 9.5093,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3484013230429989,
575
+ "grad_norm": 2.705833911895752,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 9.7085,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.3528114663726571,
582
+ "grad_norm": 2.610684871673584,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 9.7547,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.3572216097023153,
589
+ "grad_norm": 2.7021446228027344,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 9.7201,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.36163175303197354,
596
+ "grad_norm": 2.925966501235962,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 9.6825,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.36604189636163176,
603
+ "grad_norm": 2.917950391769409,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 9.7022,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.37045203969129,
610
+ "grad_norm": 2.6790931224823,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 9.586,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.3748621830209482,
617
+ "grad_norm": 2.8914520740509033,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 9.708,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.37927232635060637,
624
+ "grad_norm": 2.735027313232422,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 9.8346,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3836824696802646,
631
+ "grad_norm": 2.8165762424468994,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 9.9393,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3880926130099228,
638
+ "grad_norm": 3.055398941040039,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 9.9979,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.39250275633958104,
645
+ "grad_norm": 3.5361881256103516,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 9.853,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.39691289966923926,
652
+ "grad_norm": 3.080867290496826,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 9.9319,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.4013230429988975,
659
+ "grad_norm": 3.6121015548706055,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 9.6563,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.40573318632855565,
666
+ "grad_norm": 3.659212112426758,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 9.8984,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.4101433296582139,
673
+ "grad_norm": 3.804407835006714,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 10.0283,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.4145534729878721,
680
+ "grad_norm": 4.0184831619262695,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 9.7105,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.4189636163175303,
687
+ "grad_norm": 3.6824862957000732,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 9.7631,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.42337375964718854,
694
+ "grad_norm": 4.295379638671875,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 9.4494,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.42778390297684676,
701
+ "grad_norm": 4.584733963012695,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 9.5438,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.432194046306505,
708
+ "grad_norm": 4.690437316894531,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 9.2678,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.43660418963616315,
715
+ "grad_norm": 5.595583438873291,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 9.4706,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.4410143329658214,
722
+ "grad_norm": 14.302119255065918,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 9.7156,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.4410143329658214,
729
+ "eval_loss": 2.3261044025421143,
730
+ "eval_runtime": 3.9912,
731
+ "eval_samples_per_second": 95.712,
732
+ "eval_steps_per_second": 24.053,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3635041032732672.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null