prxy5605 commited on
Commit
9c0077f
·
verified ·
1 Parent(s): 8f16088

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 sha256:9546837f121d56e78aceebea07eb5061b7a474c9bbf54340db0e3f3fbef7927e
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d59d739f1b5aaf8d6bde6e3719dcb55926d385da05cd1f26d4c8b42c18ef087
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ddc977cbea4a6c0c1d85d93ac0f0b3ceef9601ba512947a878027e540bfba45
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd0924d11fe8d81f1631cd8e5c2aa63bee79cd1d6251632330b9c42e438b43b
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bae3d8bac295408e1206dc94b11960606832dac0ade4f07f474b80299b36b5bd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765617cfcca38312e6e6a06d5469d4f90799e895741d9cbbd6b75046f8350de2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1315d7eec29cf9168c9f163c958c5df6ae2472b96d8ab0aa2f59aeca18e9936b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70676b886bdad671d073176c81ea76c66ddac446539f48ac64f4e9bef2e2a776
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.257964849472046,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.8658008658008658,
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": 22.329,
374
  "eval_steps_per_second": 5.696,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.07184013033472e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.1507210731506348,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.7316017316017316,
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": 22.329,
374
  "eval_steps_per_second": 5.696,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.8831168831168831,
379
+ "grad_norm": 2.078730344772339,
380
+ "learning_rate": 8.518457335743926e-05,
381
+ "loss": 2.3291,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.9004329004329005,
386
+ "grad_norm": 2.2976505756378174,
387
+ "learning_rate": 8.449338172278059e-05,
388
+ "loss": 2.4847,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.9177489177489178,
393
+ "grad_norm": 2.3204331398010254,
394
+ "learning_rate": 8.378937720492384e-05,
395
+ "loss": 2.2143,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.935064935064935,
400
+ "grad_norm": 2.5574119091033936,
401
+ "learning_rate": 8.307282131280804e-05,
402
+ "loss": 2.2599,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.9523809523809523,
407
+ "grad_norm": 2.842057228088379,
408
+ "learning_rate": 8.23439802176954e-05,
409
+ "loss": 2.398,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.9696969696969697,
414
+ "grad_norm": 5.180115222930908,
415
+ "learning_rate": 8.160312465429952e-05,
416
+ "loss": 2.8077,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.987012987012987,
421
+ "grad_norm": 1.269924521446228,
422
+ "learning_rate": 8.085052982021847e-05,
423
+ "loss": 1.8004,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.0043290043290043,
428
+ "grad_norm": 3.555042266845703,
429
+ "learning_rate": 8.008647527371023e-05,
430
+ "loss": 2.9331,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.0216450216450217,
435
+ "grad_norm": 0.9649820327758789,
436
+ "learning_rate": 7.931124482984802e-05,
437
+ "loss": 1.6347,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.0389610389610389,
442
+ "grad_norm": 1.0270448923110962,
443
+ "learning_rate": 7.85251264550948e-05,
444
+ "loss": 1.7292,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.0562770562770563,
449
+ "grad_norm": 1.1698195934295654,
450
+ "learning_rate": 7.772841216033533e-05,
451
+ "loss": 1.7121,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.0735930735930737,
456
+ "grad_norm": 1.318803071975708,
457
+ "learning_rate": 7.692139789240611e-05,
458
+ "loss": 1.6378,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.0909090909090908,
463
+ "grad_norm": 1.3806180953979492,
464
+ "learning_rate": 7.610438342416319e-05,
465
+ "loss": 1.5165,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.1082251082251082,
470
+ "grad_norm": 1.6144442558288574,
471
+ "learning_rate": 7.527767224312883e-05,
472
+ "loss": 1.8815,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.1255411255411256,
477
+ "grad_norm": 1.3800272941589355,
478
+ "learning_rate": 7.44415714387582e-05,
479
+ "loss": 1.489,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.1428571428571428,
484
+ "grad_norm": 1.5080249309539795,
485
+ "learning_rate": 7.359639158836828e-05,
486
+ "loss": 1.7076,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.1601731601731602,
491
+ "grad_norm": 1.7485432624816895,
492
+ "learning_rate": 7.274244664177097e-05,
493
+ "loss": 1.8926,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.1774891774891776,
498
+ "grad_norm": 1.9501352310180664,
499
+ "learning_rate": 7.188005380465364e-05,
500
+ "loss": 1.7409,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.1948051948051948,
505
+ "grad_norm": 2.2572169303894043,
506
+ "learning_rate": 7.10095334207501e-05,
507
+ "loss": 1.7492,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.2121212121212122,
512
+ "grad_norm": 2.5785837173461914,
513
+ "learning_rate": 7.013120885284598e-05,
514
+ "loss": 1.9541,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.2294372294372296,
519
+ "grad_norm": 2.9430317878723145,
520
+ "learning_rate": 6.924540636266272e-05,
521
+ "loss": 1.7906,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.2467532467532467,
526
+ "grad_norm": 3.6292784214019775,
527
+ "learning_rate": 6.835245498966461e-05,
528
+ "loss": 1.8423,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.2640692640692641,
533
+ "grad_norm": 1.190421462059021,
534
+ "learning_rate": 6.745268642883404e-05,
535
+ "loss": 1.3868,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.2813852813852815,
540
+ "grad_norm": 1.5110549926757812,
541
+ "learning_rate": 6.654643490746042e-05,
542
+ "loss": 1.8033,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.2987012987012987,
547
+ "grad_norm": 1.511256217956543,
548
+ "learning_rate": 6.563403706098833e-05,
549
+ "loss": 1.911,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.316017316017316,
554
+ "grad_norm": 1.329278588294983,
555
+ "learning_rate": 6.471583180797121e-05,
556
+ "loss": 1.3092,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.3333333333333333,
561
+ "grad_norm": 1.5857261419296265,
562
+ "learning_rate": 6.379216022417696e-05,
563
+ "loss": 1.7496,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.3506493506493507,
568
+ "grad_norm": 1.6332991123199463,
569
+ "learning_rate": 6.286336541589224e-05,
570
+ "loss": 1.6607,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.3679653679653678,
575
+ "grad_norm": 1.6632938385009766,
576
+ "learning_rate": 6.192979239247243e-05,
577
+ "loss": 1.5656,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.3852813852813852,
582
+ "grad_norm": 1.711585521697998,
583
+ "learning_rate": 6.0991787938184784e-05,
584
+ "loss": 1.7717,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.4025974025974026,
589
+ "grad_norm": 1.7672886848449707,
590
+ "learning_rate": 6.004970048339226e-05,
591
+ "loss": 1.5959,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.4199134199134198,
596
+ "grad_norm": 1.8584389686584473,
597
+ "learning_rate": 5.910387997512573e-05,
598
+ "loss": 1.7643,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.4372294372294372,
603
+ "grad_norm": 2.1086313724517822,
604
+ "learning_rate": 5.8154677747093134e-05,
605
+ "loss": 1.6635,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.4545454545454546,
610
+ "grad_norm": 2.3654050827026367,
611
+ "learning_rate": 5.7202446389173223e-05,
612
+ "loss": 1.9113,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.4718614718614718,
617
+ "grad_norm": 2.853776693344116,
618
+ "learning_rate": 5.624753961644281e-05,
619
+ "loss": 1.6637,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.4891774891774892,
624
+ "grad_norm": 3.0281548500061035,
625
+ "learning_rate": 5.5290312137786146e-05,
626
+ "loss": 1.5317,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.5064935064935066,
631
+ "grad_norm": 0.9081037044525146,
632
+ "learning_rate": 5.433111952413495e-05,
633
+ "loss": 1.4504,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.5238095238095237,
638
+ "grad_norm": 1.2145230770111084,
639
+ "learning_rate": 5.33703180763884e-05,
640
+ "loss": 1.8371,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.5411255411255411,
645
+ "grad_norm": 1.255497932434082,
646
+ "learning_rate": 5.240826469306187e-05,
647
+ "loss": 1.6484,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.5584415584415585,
652
+ "grad_norm": 1.4401757717132568,
653
+ "learning_rate": 5.144531673771363e-05,
654
+ "loss": 1.4698,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.5757575757575757,
659
+ "grad_norm": 1.397579550743103,
660
+ "learning_rate": 5.048183190619904e-05,
661
+ "loss": 1.5281,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.593073593073593,
666
+ "grad_norm": 1.5913752317428589,
667
+ "learning_rate": 4.951816809380097e-05,
668
+ "loss": 1.5165,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.6103896103896105,
673
+ "grad_norm": 1.7253613471984863,
674
+ "learning_rate": 4.855468326228638e-05,
675
+ "loss": 1.5576,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.6277056277056277,
680
+ "grad_norm": 1.8811947107315063,
681
+ "learning_rate": 4.759173530693814e-05,
682
+ "loss": 1.6702,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.645021645021645,
687
+ "grad_norm": 1.9672281742095947,
688
+ "learning_rate": 4.6629681923611603e-05,
689
+ "loss": 1.7017,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.6623376623376624,
694
+ "grad_norm": 2.2291691303253174,
695
+ "learning_rate": 4.566888047586507e-05,
696
+ "loss": 1.8685,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.6796536796536796,
701
+ "grad_norm": 2.2788848876953125,
702
+ "learning_rate": 4.4709687862213866e-05,
703
+ "loss": 1.6978,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.696969696969697,
708
+ "grad_norm": 2.3256399631500244,
709
+ "learning_rate": 4.3752460383557195e-05,
710
+ "loss": 1.7429,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.7142857142857144,
715
+ "grad_norm": 3.4185853004455566,
716
+ "learning_rate": 4.27975536108268e-05,
717
+ "loss": 1.8859,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.7316017316017316,
722
+ "grad_norm": 3.066596031188965,
723
+ "learning_rate": 4.1845322252906864e-05,
724
+ "loss": 1.4093,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.7316017316017316,
729
+ "eval_loss": 2.1507210731506348,
730
+ "eval_runtime": 4.391,
731
+ "eval_samples_per_second": 22.318,
732
+ "eval_steps_per_second": 5.693,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4.137205760262144e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null