nttx commited on
Commit
52ed1c6
·
verified ·
1 Parent(s): 88e82bc

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 sha256:9a638337deb69615536b5dffa161f0c76910e35fdc010e42dd312aef9066f889
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8630fd5328a79e683af20c70a7ef2d99ea5657b0e3e64f081f52c404f15a0f1
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca35c20e92b80a2ee6e38348e4f42ffc06bc398606930476705eeef249e7190a
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083d131494c8cd7e67b1f39a737521663c888b0bdc1193ec94598a2f6b80d0bf
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:738277b1537a199daeed94f3d22f2c8adbc28cf41c932088918fead488cfa96d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74f1aabd19b972fd2d08c49d2f3d2291b3a987231af8cd940c38d736456b0cb4
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": 1.8799346685409546,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.2949852507374631,
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": 8.751,
374
  "eval_steps_per_second": 2.203,
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": 1.2695579394048e+17,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4722347259521484,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.5899705014749262,
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": 8.751,
374
  "eval_steps_per_second": 2.203,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3008849557522124,
379
+ "grad_norm": 14.157112121582031,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 11.7297,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.30678466076696165,
386
+ "grad_norm": 13.268279075622559,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 11.9854,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.31268436578171094,
393
+ "grad_norm": 14.777017593383789,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 11.6982,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3185840707964602,
400
+ "grad_norm": 15.651505470275879,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 12.7209,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.32448377581120946,
407
+ "grad_norm": 16.862051010131836,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 12.7352,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.3303834808259587,
414
+ "grad_norm": 16.122634887695312,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 12.8166,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.336283185840708,
421
+ "grad_norm": 20.204120635986328,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 13.0973,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.3421828908554572,
428
+ "grad_norm": 15.840360641479492,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 13.2673,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.3480825958702065,
435
+ "grad_norm": 27.855974197387695,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 13.2521,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.35398230088495575,
442
+ "grad_norm": 21.352693557739258,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 13.3141,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.35988200589970504,
449
+ "grad_norm": 24.652055740356445,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 13.715,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.36578171091445427,
456
+ "grad_norm": 24.22166633605957,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 12.7998,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.37168141592920356,
463
+ "grad_norm": 22.723926544189453,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 14.2915,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.3775811209439528,
470
+ "grad_norm": 25.48423194885254,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 13.0007,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.3834808259587021,
477
+ "grad_norm": 23.430404663085938,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 14.1499,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3893805309734513,
484
+ "grad_norm": 25.634765625,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 12.2943,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3952802359882006,
491
+ "grad_norm": 29.16959571838379,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 15.9917,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.40117994100294985,
498
+ "grad_norm": 26.52433204650879,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 13.1748,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.40707964601769914,
505
+ "grad_norm": 23.716463088989258,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 13.5076,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.41297935103244837,
512
+ "grad_norm": 25.928203582763672,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 13.0781,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.41887905604719766,
519
+ "grad_norm": 25.973100662231445,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 12.7629,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.4247787610619469,
526
+ "grad_norm": 26.729578018188477,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 13.0884,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.4306784660766962,
533
+ "grad_norm": 28.534502029418945,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 14.8765,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.4365781710914454,
540
+ "grad_norm": 27.88771629333496,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 16.3264,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.4424778761061947,
547
+ "grad_norm": 35.43700408935547,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 13.3003,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.44837758112094395,
554
+ "grad_norm": 31.386333465576172,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 16.0848,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.45427728613569324,
561
+ "grad_norm": 33.588722229003906,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 14.6917,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.46017699115044247,
568
+ "grad_norm": 31.54501724243164,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 12.2341,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.46607669616519176,
575
+ "grad_norm": 39.24992370605469,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 14.9348,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.471976401179941,
582
+ "grad_norm": 38.33148193359375,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 11.4804,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.4778761061946903,
589
+ "grad_norm": 39.474124908447266,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 12.2075,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.4837758112094395,
596
+ "grad_norm": 40.61744689941406,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 15.4732,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.4896755162241888,
603
+ "grad_norm": 43.01291275024414,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 13.508,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.49557522123893805,
610
+ "grad_norm": 53.99359893798828,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 17.6752,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5014749262536873,
617
+ "grad_norm": 4.3658342361450195,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 9.9121,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.5073746312684366,
624
+ "grad_norm": 4.73631477355957,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 12.0327,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.5132743362831859,
631
+ "grad_norm": 5.241606712341309,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 10.5648,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.5191740412979351,
638
+ "grad_norm": 6.079821586608887,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 11.1205,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.5250737463126843,
645
+ "grad_norm": 6.707623481750488,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 9.6277,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.5309734513274337,
652
+ "grad_norm": 7.61404275894165,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 7.6849,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.5368731563421829,
659
+ "grad_norm": 9.975937843322754,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 10.2248,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.5427728613569321,
666
+ "grad_norm": 11.2512845993042,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 9.7481,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.5486725663716814,
673
+ "grad_norm": 12.412166595458984,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 9.6559,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.5545722713864307,
680
+ "grad_norm": 13.59131145477295,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 10.219,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.56047197640118,
687
+ "grad_norm": 12.337257385253906,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 10.9511,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.5663716814159292,
694
+ "grad_norm": 14.506831169128418,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 9.9813,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.5722713864306784,
701
+ "grad_norm": 16.134977340698242,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 10.8139,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.5781710914454278,
708
+ "grad_norm": 16.2382755279541,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 11.4754,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.584070796460177,
715
+ "grad_norm": 16.110279083251953,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 10.8895,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.5899705014749262,
722
+ "grad_norm": 19.847707748413086,
723
+ "learning_rate": 0.0,
724
+ "loss": 11.8983,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.5899705014749262,
729
+ "eval_loss": 1.4722347259521484,
730
+ "eval_runtime": 32.6234,
731
+ "eval_samples_per_second": 8.767,
732
+ "eval_steps_per_second": 2.207,
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": 2.5391158788096e+17,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null