bbytxt commited on
Commit
1f754e3
·
verified ·
1 Parent(s): f0a2e36

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 sha256:8c1b45914e5d100c0ae899eb45a2ae2d64f1acc01e5ea7200e3fc902a4a64f1e
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89af14000f59a9a4e7e3dcb0a892e7d4ad55d716d8e154efb465a62705d5bbb1
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20af5895bcb55cac973abcad329a75a6486cc7a696e7533680ed1cf9b5a3f77a
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e3600869dbed83b209ef9d2eda37333c11c4aecbb2378e8cfd1daf2e7e95179
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2998c86ac79ffac27723a13340c25983ae7ddde6c173fd769b5d7ef752e19d4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee1b6ce7ca98a4ed47e849a52d9f1fb305f8ad281416c2f7521263e5525c124
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.5140388607978821,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.007979413114165453,
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": 12.454,
374
  "eval_steps_per_second": 3.114,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.437420017693491e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.18355341255664825,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.015958826228330905,
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": 12.454,
374
  "eval_steps_per_second": 3.114,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008139001376448763,
379
+ "grad_norm": 7.3725104331970215,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 1.0074,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008298589638732071,
386
+ "grad_norm": 7.9290900230407715,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 0.4143,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.008458177901015381,
393
+ "grad_norm": 16.212963104248047,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 0.6425,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.00861776616329869,
400
+ "grad_norm": 7.862034320831299,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 0.3512,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.008777354425581998,
407
+ "grad_norm": 3.113178253173828,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 0.1114,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.008936942687865308,
414
+ "grad_norm": 8.0140380859375,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 0.4566,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.009096530950148616,
421
+ "grad_norm": 11.397700309753418,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 0.6353,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009256119212431926,
428
+ "grad_norm": 0.06368193030357361,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 0.001,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009415707474715235,
435
+ "grad_norm": 4.552347183227539,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 0.2425,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.009575295736998543,
442
+ "grad_norm": 4.318637847900391,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 0.2014,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.009734883999281853,
449
+ "grad_norm": 2.7980666160583496,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 0.1012,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.009894472261565162,
456
+ "grad_norm": 2.5013349056243896,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 0.0972,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.010054060523848472,
463
+ "grad_norm": 2.51824688911438,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 0.1209,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.01021364878613178,
470
+ "grad_norm": 4.979506492614746,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 0.2335,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010373237048415088,
477
+ "grad_norm": 0.3189781904220581,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 0.0033,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.010532825310698398,
484
+ "grad_norm": 13.277030944824219,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 0.3517,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.010692413572981707,
491
+ "grad_norm": 5.3693084716796875,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 0.1901,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.010852001835265017,
498
+ "grad_norm": 0.6272711157798767,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 0.006,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011011590097548325,
505
+ "grad_norm": 9.435708045959473,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 0.2644,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.011171178359831634,
512
+ "grad_norm": 4.341763496398926,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 0.1834,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011330766622114944,
519
+ "grad_norm": 9.02403450012207,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 0.4484,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.011490354884398252,
526
+ "grad_norm": 4.708563327789307,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 0.107,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.011649943146681562,
533
+ "grad_norm": 1.80886709690094,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 0.0173,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.01180953140896487,
540
+ "grad_norm": 1.6764700412750244,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 0.0171,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.011969119671248179,
547
+ "grad_norm": 2.3282880783081055,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 0.0509,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012128707933531489,
554
+ "grad_norm": 3.2590067386627197,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 0.1197,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.012288296195814797,
561
+ "grad_norm": 1.3154736757278442,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 0.0891,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.012447884458098107,
568
+ "grad_norm": 2.3927087783813477,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 0.0256,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.012607472720381416,
575
+ "grad_norm": 1.8653408288955688,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 0.1032,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.012767060982664726,
582
+ "grad_norm": 1.5105987787246704,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 0.0666,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.012926649244948034,
589
+ "grad_norm": 7.518610000610352,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 0.2022,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.013086237507231343,
596
+ "grad_norm": 2.9338836669921875,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 0.0967,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.013245825769514653,
603
+ "grad_norm": 1.571068525314331,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 0.0741,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.013405414031797961,
610
+ "grad_norm": 8.719659805297852,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 0.2685,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.013565002294081271,
617
+ "grad_norm": 2.258552312850952,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 0.051,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.01372459055636458,
624
+ "grad_norm": 1.2262955904006958,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 0.0505,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.013884178818647888,
631
+ "grad_norm": 3.613511323928833,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 0.2141,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.014043767080931198,
638
+ "grad_norm": 6.448750972747803,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 0.3561,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.014203355343214506,
645
+ "grad_norm": 6.130068302154541,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 0.2403,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.014362943605497816,
652
+ "grad_norm": 7.4299211502075195,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 0.3328,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.014522531867781125,
659
+ "grad_norm": 6.2848381996154785,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 0.2196,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.014682120130064433,
666
+ "grad_norm": 5.241060256958008,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 0.2432,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.014841708392347743,
673
+ "grad_norm": 8.220368385314941,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 0.2829,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015001296654631052,
680
+ "grad_norm": 4.223203182220459,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 0.1818,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.015160884916914362,
687
+ "grad_norm": 3.850449562072754,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 0.1388,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.01532047317919767,
694
+ "grad_norm": 5.5809760093688965,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 0.2356,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.015480061441480978,
701
+ "grad_norm": 4.3721795082092285,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 0.0995,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.01563964970376429,
708
+ "grad_norm": 5.354106426239014,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 0.1928,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.015799237966047597,
715
+ "grad_norm": 4.162508010864258,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 0.1439,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.015958826228330905,
722
+ "grad_norm": 5.800200939178467,
723
+ "learning_rate": 0.0,
724
+ "loss": 0.2004,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.015958826228330905,
729
+ "eval_loss": 0.18355341255664825,
730
+ "eval_runtime": 847.1818,
731
+ "eval_samples_per_second": 12.458,
732
+ "eval_steps_per_second": 3.115,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.4874840035386982e+17,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null