nttx commited on
Commit
7d4dd17
·
verified ·
1 Parent(s): 56dbc4d

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 sha256:7f00a359f23f841c35bc7f2c05b50f88fa4ffbafde6529bb8f0f7e934f0d0015
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd3af65a1a21661d230da092c1951623375451bc9baa538f5596df6bfd31a35
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9da25129dd0c067e7e717a6476a567ca1ccd55d4f78cc432d2665932ac0b9445
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6ee579cd2527284739dd4c51f9da3ee7749d73c40497777b11422e9214323e
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04abeca279b226a6a380f6f6ebf9f5fc6a39afdf329aa2fca2946deb1fed163a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:171c613a15ea21d0246cef4d9e299db55469335aca7c6fa2134b058abf79ccb5
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": 0.9812448024749756,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 1.3986013986013985,
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": 12.971,
374
  "eval_steps_per_second": 3.402,
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": 7.026908475477197e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9307088255882263,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 2.797202797202797,
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": 12.971,
374
  "eval_steps_per_second": 3.402,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.4265734265734267,
379
+ "grad_norm": 19.437496185302734,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 7.9052,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 1.4545454545454546,
386
+ "grad_norm": 26.167152404785156,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 9.7995,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 1.4825174825174825,
393
+ "grad_norm": 13.2216157913208,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 7.3562,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 1.5104895104895104,
400
+ "grad_norm": 15.14995002746582,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 7.6083,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 1.5384615384615383,
407
+ "grad_norm": 14.735421180725098,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 7.493,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 1.5664335664335665,
414
+ "grad_norm": 16.057226181030273,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 7.7143,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 1.5944055944055944,
421
+ "grad_norm": 17.881492614746094,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 7.9213,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.6223776223776225,
428
+ "grad_norm": 18.69293785095215,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 8.0768,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.6503496503496504,
435
+ "grad_norm": 20.132923126220703,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 8.4112,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.6783216783216783,
442
+ "grad_norm": 22.801490783691406,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 8.7676,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.7062937062937062,
449
+ "grad_norm": 12.906396865844727,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 7.2744,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.7342657342657342,
456
+ "grad_norm": 14.026016235351562,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 7.0761,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.762237762237762,
463
+ "grad_norm": 13.737709999084473,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 7.4639,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.7902097902097902,
470
+ "grad_norm": 15.159075736999512,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 7.1799,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.8181818181818183,
477
+ "grad_norm": 16.306058883666992,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 7.3868,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.8461538461538463,
484
+ "grad_norm": 16.63066291809082,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 7.9422,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.8741258741258742,
491
+ "grad_norm": 19.77796173095703,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 8.3306,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.902097902097902,
498
+ "grad_norm": 23.449113845825195,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 8.1032,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.93006993006993,
505
+ "grad_norm": 13.089604377746582,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 6.8976,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.958041958041958,
512
+ "grad_norm": 15.323660850524902,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 7.1423,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.986013986013986,
519
+ "grad_norm": 17.456003189086914,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 8.0554,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 2.013986013986014,
526
+ "grad_norm": 17.351194381713867,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 7.5417,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 2.041958041958042,
533
+ "grad_norm": 12.989124298095703,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 6.9213,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 2.06993006993007,
540
+ "grad_norm": 13.786518096923828,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 6.993,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 2.097902097902098,
547
+ "grad_norm": 14.11694622039795,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 7.277,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 2.125874125874126,
554
+ "grad_norm": 15.72767162322998,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 7.5282,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 2.1538461538461537,
561
+ "grad_norm": 17.46666717529297,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 7.2148,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 2.1818181818181817,
568
+ "grad_norm": 17.60526466369629,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 7.6238,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 2.20979020979021,
575
+ "grad_norm": 18.603511810302734,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 8.0623,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 2.237762237762238,
582
+ "grad_norm": 18.113256454467773,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 7.6123,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 2.265734265734266,
589
+ "grad_norm": 12.54310417175293,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 7.2639,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 2.2937062937062938,
596
+ "grad_norm": 14.775126457214355,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 6.9113,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 2.3216783216783217,
603
+ "grad_norm": 13.778559684753418,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 7.214,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 2.3496503496503496,
610
+ "grad_norm": 15.231853485107422,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 7.3562,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 2.3776223776223775,
617
+ "grad_norm": 16.52434539794922,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 7.6841,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 2.4055944055944054,
624
+ "grad_norm": 16.546457290649414,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 7.2925,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 2.4335664335664333,
631
+ "grad_norm": 20.887779235839844,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 8.0049,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 2.4615384615384617,
638
+ "grad_norm": 24.01591682434082,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 8.0908,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 2.4895104895104896,
645
+ "grad_norm": 13.272303581237793,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 6.8586,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 2.5174825174825175,
652
+ "grad_norm": 13.375730514526367,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 6.9535,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 2.5454545454545454,
659
+ "grad_norm": 15.659381866455078,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 7.2084,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 2.5734265734265733,
666
+ "grad_norm": 15.646546363830566,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 6.8886,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 2.6013986013986012,
673
+ "grad_norm": 17.0341796875,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 7.3088,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 2.629370629370629,
680
+ "grad_norm": 17.291650772094727,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 7.3454,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 2.6573426573426575,
687
+ "grad_norm": 18.05946922302246,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 7.7567,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 2.6853146853146854,
694
+ "grad_norm": 16.397621154785156,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 7.8379,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 2.7132867132867133,
701
+ "grad_norm": 14.185662269592285,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 6.869,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 2.7412587412587412,
708
+ "grad_norm": 13.866539001464844,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 6.8378,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 2.769230769230769,
715
+ "grad_norm": 15.03514575958252,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 7.0574,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 2.797202797202797,
722
+ "grad_norm": 15.289778709411621,
723
+ "learning_rate": 0.0,
724
+ "loss": 7.0866,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 2.797202797202797,
729
+ "eval_loss": 0.9307088255882263,
730
+ "eval_runtime": 4.6988,
731
+ "eval_samples_per_second": 12.982,
732
+ "eval_steps_per_second": 3.405,
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": 1.4053816950954394e+17,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null