prxy5607 commited on
Commit
50aa4ce
·
verified ·
1 Parent(s): 5a8bba7

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 sha256:1333046d7453be5a40228b4a1d9a97b6e6c75a2270666213cb2ec730ab541405
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b83b241dcdc795ee295c8bede9a2b3d40f4069e944ca6757a04ea8cefe2f4c
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80201f5b8e178e8c312fe0f6721020bb0bc69ca2d1584f1e7ac3e5a2f5044d7c
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa283575feca983fff9f91a37a4fe93584eab3dd4b1ae279c2098a29cb9abf6
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": 2.256721258163452,
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": 22.266,
374
  "eval_steps_per_second": 5.68,
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": 2.149948835372925,
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": 22.266,
374
  "eval_steps_per_second": 5.68,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.8831168831168831,
379
+ "grad_norm": 2.1010754108428955,
380
+ "learning_rate": 8.518457335743926e-05,
381
+ "loss": 2.3307,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.9004329004329005,
386
+ "grad_norm": 2.3242135047912598,
387
+ "learning_rate": 8.449338172278059e-05,
388
+ "loss": 2.4806,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.9177489177489178,
393
+ "grad_norm": 2.3536064624786377,
394
+ "learning_rate": 8.378937720492384e-05,
395
+ "loss": 2.2132,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.935064935064935,
400
+ "grad_norm": 2.595224618911743,
401
+ "learning_rate": 8.307282131280804e-05,
402
+ "loss": 2.2525,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.9523809523809523,
407
+ "grad_norm": 2.8772056102752686,
408
+ "learning_rate": 8.23439802176954e-05,
409
+ "loss": 2.4023,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.9696969696969697,
414
+ "grad_norm": 5.285353660583496,
415
+ "learning_rate": 8.160312465429952e-05,
416
+ "loss": 2.8273,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.987012987012987,
421
+ "grad_norm": 1.2868059873580933,
422
+ "learning_rate": 8.085052982021847e-05,
423
+ "loss": 1.8018,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.0043290043290043,
428
+ "grad_norm": 3.5397348403930664,
429
+ "learning_rate": 8.008647527371023e-05,
430
+ "loss": 2.9306,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.0216450216450217,
435
+ "grad_norm": 0.9906024932861328,
436
+ "learning_rate": 7.931124482984802e-05,
437
+ "loss": 1.6357,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.0389610389610389,
442
+ "grad_norm": 1.0218256711959839,
443
+ "learning_rate": 7.85251264550948e-05,
444
+ "loss": 1.729,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.0562770562770563,
449
+ "grad_norm": 1.1563177108764648,
450
+ "learning_rate": 7.772841216033533e-05,
451
+ "loss": 1.7074,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.0735930735930737,
456
+ "grad_norm": 1.2730008363723755,
457
+ "learning_rate": 7.692139789240611e-05,
458
+ "loss": 1.6385,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.0909090909090908,
463
+ "grad_norm": 1.366668701171875,
464
+ "learning_rate": 7.610438342416319e-05,
465
+ "loss": 1.5181,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.1082251082251082,
470
+ "grad_norm": 1.6161524057388306,
471
+ "learning_rate": 7.527767224312883e-05,
472
+ "loss": 1.8762,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.1255411255411256,
477
+ "grad_norm": 1.4192622900009155,
478
+ "learning_rate": 7.44415714387582e-05,
479
+ "loss": 1.4841,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.1428571428571428,
484
+ "grad_norm": 1.495239496231079,
485
+ "learning_rate": 7.359639158836828e-05,
486
+ "loss": 1.7021,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.1601731601731602,
491
+ "grad_norm": 1.729372262954712,
492
+ "learning_rate": 7.274244664177097e-05,
493
+ "loss": 1.8888,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.1774891774891776,
498
+ "grad_norm": 1.9363900423049927,
499
+ "learning_rate": 7.188005380465364e-05,
500
+ "loss": 1.734,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.1948051948051948,
505
+ "grad_norm": 2.3331375122070312,
506
+ "learning_rate": 7.10095334207501e-05,
507
+ "loss": 1.7476,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.2121212121212122,
512
+ "grad_norm": 2.6032962799072266,
513
+ "learning_rate": 7.013120885284598e-05,
514
+ "loss": 1.9506,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.2294372294372296,
519
+ "grad_norm": 2.9084725379943848,
520
+ "learning_rate": 6.924540636266272e-05,
521
+ "loss": 1.783,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.2467532467532467,
526
+ "grad_norm": 3.581970453262329,
527
+ "learning_rate": 6.835245498966461e-05,
528
+ "loss": 1.8422,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.2640692640692641,
533
+ "grad_norm": 1.1855902671813965,
534
+ "learning_rate": 6.745268642883404e-05,
535
+ "loss": 1.3828,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.2813852813852815,
540
+ "grad_norm": 1.5189799070358276,
541
+ "learning_rate": 6.654643490746042e-05,
542
+ "loss": 1.8042,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.2987012987012987,
547
+ "grad_norm": 1.53164541721344,
548
+ "learning_rate": 6.563403706098833e-05,
549
+ "loss": 1.9113,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.316017316017316,
554
+ "grad_norm": 1.3554658889770508,
555
+ "learning_rate": 6.471583180797121e-05,
556
+ "loss": 1.3116,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.3333333333333333,
561
+ "grad_norm": 1.5969181060791016,
562
+ "learning_rate": 6.379216022417696e-05,
563
+ "loss": 1.7443,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.3506493506493507,
568
+ "grad_norm": 1.6001543998718262,
569
+ "learning_rate": 6.286336541589224e-05,
570
+ "loss": 1.6611,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.3679653679653678,
575
+ "grad_norm": 1.6653358936309814,
576
+ "learning_rate": 6.192979239247243e-05,
577
+ "loss": 1.5659,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.3852813852813852,
582
+ "grad_norm": 1.736785888671875,
583
+ "learning_rate": 6.0991787938184784e-05,
584
+ "loss": 1.773,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.4025974025974026,
589
+ "grad_norm": 1.7712799310684204,
590
+ "learning_rate": 6.004970048339226e-05,
591
+ "loss": 1.5936,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.4199134199134198,
596
+ "grad_norm": 1.8556205034255981,
597
+ "learning_rate": 5.910387997512573e-05,
598
+ "loss": 1.7578,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.4372294372294372,
603
+ "grad_norm": 2.0250351428985596,
604
+ "learning_rate": 5.8154677747093134e-05,
605
+ "loss": 1.6592,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.4545454545454546,
610
+ "grad_norm": 2.347397565841675,
611
+ "learning_rate": 5.7202446389173223e-05,
612
+ "loss": 1.8997,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.4718614718614718,
617
+ "grad_norm": 2.838571786880493,
618
+ "learning_rate": 5.624753961644281e-05,
619
+ "loss": 1.6595,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.4891774891774892,
624
+ "grad_norm": 2.8864710330963135,
625
+ "learning_rate": 5.5290312137786146e-05,
626
+ "loss": 1.5153,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.5064935064935066,
631
+ "grad_norm": 0.9010306000709534,
632
+ "learning_rate": 5.433111952413495e-05,
633
+ "loss": 1.4468,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.5238095238095237,
638
+ "grad_norm": 1.2178982496261597,
639
+ "learning_rate": 5.33703180763884e-05,
640
+ "loss": 1.8386,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.5411255411255411,
645
+ "grad_norm": 1.256874918937683,
646
+ "learning_rate": 5.240826469306187e-05,
647
+ "loss": 1.6508,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.5584415584415585,
652
+ "grad_norm": 1.3813403844833374,
653
+ "learning_rate": 5.144531673771363e-05,
654
+ "loss": 1.4675,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.5757575757575757,
659
+ "grad_norm": 1.4501692056655884,
660
+ "learning_rate": 5.048183190619904e-05,
661
+ "loss": 1.5286,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.593073593073593,
666
+ "grad_norm": 1.596665382385254,
667
+ "learning_rate": 4.951816809380097e-05,
668
+ "loss": 1.5156,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.6103896103896105,
673
+ "grad_norm": 1.736958384513855,
674
+ "learning_rate": 4.855468326228638e-05,
675
+ "loss": 1.554,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.6277056277056277,
680
+ "grad_norm": 1.8774197101593018,
681
+ "learning_rate": 4.759173530693814e-05,
682
+ "loss": 1.6657,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.645021645021645,
687
+ "grad_norm": 2.086031675338745,
688
+ "learning_rate": 4.6629681923611603e-05,
689
+ "loss": 1.7142,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.6623376623376624,
694
+ "grad_norm": 2.1625614166259766,
695
+ "learning_rate": 4.566888047586507e-05,
696
+ "loss": 1.8664,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.6796536796536796,
701
+ "grad_norm": 2.298473358154297,
702
+ "learning_rate": 4.4709687862213866e-05,
703
+ "loss": 1.6924,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.696969696969697,
708
+ "grad_norm": 2.3079867362976074,
709
+ "learning_rate": 4.3752460383557195e-05,
710
+ "loss": 1.7353,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.7142857142857144,
715
+ "grad_norm": 3.372159004211426,
716
+ "learning_rate": 4.27975536108268e-05,
717
+ "loss": 1.8684,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.7316017316017316,
722
+ "grad_norm": 3.0336737632751465,
723
+ "learning_rate": 4.1845322252906864e-05,
724
+ "loss": 1.4009,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.7316017316017316,
729
+ "eval_loss": 2.149948835372925,
730
+ "eval_runtime": 4.3993,
731
+ "eval_samples_per_second": 22.276,
732
+ "eval_steps_per_second": 5.683,
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