aleegis11 commited on
Commit
c1f9d92
·
verified ·
1 Parent(s): 070411c

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:c3e0acbeb73270926adfc910f8f17e673b2a5312dc16e82021c49acfd2c2cb38
3
  size 54285928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b93d17e7a352c90cb2dba135c2f9aeded2d47ce2c0adfbdfde70cdbf5eeef59f
3
  size 54285928
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42515186dfeed94aa2ec649d62d05ffc07a0487ede521ffba4a4b510f94e9346
3
  size 27753594
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a206df4c1fb3b202814e9a4591fa2be1c89cea6c9e396504cef50019f53b14
3
  size 27753594
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aea3f65396642f52a00c13f761aaded8f2359ecdae407447b32e4ba0808336a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e5baae50274f42dfb92f246aa1f9b40128b9af5eed85ca8330cefdde1f549ea
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": 5.211904048919678,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.003207338390236862,
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": 149.141,
374
  "eval_steps_per_second": 37.285,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1488394911744000.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 5.082364082336426,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.006414676780473724,
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": 149.141,
374
  "eval_steps_per_second": 37.285,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.003271485158041599,
379
+ "grad_norm": 16.199979782104492,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 5.1198,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0033356319258463366,
386
+ "grad_norm": 16.18631362915039,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 5.1413,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0033997786936510736,
393
+ "grad_norm": 15.308594703674316,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 5.1288,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0034639254614558107,
400
+ "grad_norm": 11.432890892028809,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 4.6673,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.003528072229260548,
407
+ "grad_norm": 6.996739864349365,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 4.5088,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0035922189970652853,
414
+ "grad_norm": 2.9491331577301025,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 4.2026,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0036563657648700227,
421
+ "grad_norm": 1.1189446449279785,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 4.3928,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.00372051253267476,
428
+ "grad_norm": 1.140417456626892,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 4.2991,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0037846593004794973,
435
+ "grad_norm": 1.085638403892517,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 4.1921,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0038488060682842344,
442
+ "grad_norm": 1.130789041519165,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 4.3044,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.003912952836088971,
449
+ "grad_norm": 1.2206088304519653,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 4.3771,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.003977099603893709,
456
+ "grad_norm": 1.19307279586792,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 4.2969,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.004041246371698446,
463
+ "grad_norm": 1.1722559928894043,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 4.4744,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.004105393139503183,
470
+ "grad_norm": 1.073339819908142,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 4.439,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0041695399073079205,
477
+ "grad_norm": 0.9737927317619324,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 4.3597,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.004233686675112658,
484
+ "grad_norm": 1.1121063232421875,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 4.4142,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.004297833442917395,
491
+ "grad_norm": 0.9784128665924072,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 4.3532,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.004361980210722132,
498
+ "grad_norm": 0.9304491877555847,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 4.3092,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.00442612697852687,
505
+ "grad_norm": 0.9712762832641602,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 4.1377,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.004490273746331607,
512
+ "grad_norm": 1.0609962940216064,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 4.5251,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.004554420514136344,
519
+ "grad_norm": 1.3250576257705688,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 4.4165,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.004618567281941081,
526
+ "grad_norm": 1.514135479927063,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 4.3032,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.004682714049745819,
533
+ "grad_norm": 1.4466665983200073,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 4.3565,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.004746860817550555,
540
+ "grad_norm": 1.2483808994293213,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 4.4922,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.004811007585355293,
547
+ "grad_norm": 1.1569164991378784,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 4.354,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.00487515435316003,
554
+ "grad_norm": 1.0108411312103271,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 4.3471,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.004939301120964767,
561
+ "grad_norm": 1.0727484226226807,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 4.3835,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0050034478887695044,
568
+ "grad_norm": 1.1690360307693481,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 4.2849,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.005067594656574242,
575
+ "grad_norm": 1.0823379755020142,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 4.3961,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0051317414243789794,
582
+ "grad_norm": 1.2482712268829346,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 4.4605,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.005195888192183716,
589
+ "grad_norm": 1.125679850578308,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 4.5634,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0052600349599884536,
596
+ "grad_norm": 1.0943341255187988,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 4.5166,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.005324181727793191,
603
+ "grad_norm": 1.0785305500030518,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 4.7178,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.005388328495597928,
610
+ "grad_norm": 1.0343631505966187,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 4.4751,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.005452475263402665,
617
+ "grad_norm": 1.005264401435852,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 4.5418,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.005516622031207403,
624
+ "grad_norm": 1.1396501064300537,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 4.4077,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.00558076879901214,
631
+ "grad_norm": 1.1338545083999634,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 4.5811,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.005644915566816877,
638
+ "grad_norm": 1.0844732522964478,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 4.4835,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.005709062334621614,
645
+ "grad_norm": 1.0581928491592407,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 4.3321,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.005773209102426352,
652
+ "grad_norm": 1.4487022161483765,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 4.3464,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.005837355870231088,
659
+ "grad_norm": 1.3548654317855835,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 4.6635,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.005901502638035826,
666
+ "grad_norm": 1.4622880220413208,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 4.7465,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.005965649405840563,
673
+ "grad_norm": 1.5502005815505981,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 4.5915,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.006029796173645301,
680
+ "grad_norm": 1.7211005687713623,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 4.6409,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0060939429414500375,
687
+ "grad_norm": 1.6254551410675049,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 4.8106,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.006158089709254775,
694
+ "grad_norm": 1.7562053203582764,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 4.7768,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0062222364770595125,
701
+ "grad_norm": 1.8948148488998413,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 4.756,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.006286383244864249,
708
+ "grad_norm": 2.0640652179718018,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 5.1927,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.006350530012668987,
715
+ "grad_norm": 2.5090017318725586,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 5.2081,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.006414676780473724,
722
+ "grad_norm": 3.904104709625244,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 5.3744,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.006414676780473724,
729
+ "eval_loss": 5.082364082336426,
730
+ "eval_runtime": 175.9755,
731
+ "eval_samples_per_second": 149.203,
732
+ "eval_steps_per_second": 37.301,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2976789823488000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null