brixeus commited on
Commit
214a4a0
·
verified ·
1 Parent(s): 0640ad9

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 sha256:58d0f964826eb2834161e2b52ced263c1cc933066f4b17e5727ee9143623bc3a
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67abb41e56e78a66688842b966abefe2ae07faf077979342ac8168501b27748f
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aca57125df711506589dfb428f3d2a85fc6d3fe9f0cdb9c4bf415e2b65261016
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c2ef1b33596a23cca0f72b37e834875988cc57936319c329e4850667c3bdd0
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36d302e97ce3d6d13c6d12c84c4cf16a520c1f7a1aada20bb31f08429d9c29e8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16001d5f1e5442ee9e29a6310ea7c7892e9fb70d07faaccf84234f112d26d143
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed340328d62f63f2d9d00f6904395875dd09851f050e03ae91b4b798d852ce41
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ca67f9a35cd1c50df3d93bedf5a6642db2c7847c021a0a8d3f44c1bf4993d3
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 11.74016284942627,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.00821658929378415,
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": 210.911,
374
  "eval_steps_per_second": 52.743,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 20717292748800.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.734024047851562,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0164331785875683,
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": 210.911,
374
  "eval_steps_per_second": 52.743,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008380921079659834,
379
+ "grad_norm": 0.10825006663799286,
380
+ "learning_rate": 9.729774092143627e-05,
381
+ "loss": 11.7462,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008545252865535516,
386
+ "grad_norm": 0.09035345911979675,
387
+ "learning_rate": 9.716559066288715e-05,
388
+ "loss": 11.7452,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.008709584651411199,
393
+ "grad_norm": 0.109395332634449,
394
+ "learning_rate": 9.703037989675087e-05,
395
+ "loss": 11.7461,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.008873916437286883,
400
+ "grad_norm": 0.09128301590681076,
401
+ "learning_rate": 9.689211739666023e-05,
402
+ "loss": 11.7422,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.009038248223162565,
407
+ "grad_norm": 0.09604194760322571,
408
+ "learning_rate": 9.675081213427076e-05,
409
+ "loss": 11.741,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009202580009038248,
414
+ "grad_norm": 0.09056773781776428,
415
+ "learning_rate": 9.66064732786784e-05,
416
+ "loss": 11.7421,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.009366911794913932,
421
+ "grad_norm": 0.08328656107187271,
422
+ "learning_rate": 9.645911019582467e-05,
423
+ "loss": 11.7412,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009531243580789614,
428
+ "grad_norm": 0.09039179235696793,
429
+ "learning_rate": 9.630873244788883e-05,
430
+ "loss": 11.7383,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009695575366665297,
435
+ "grad_norm": 0.07337184250354767,
436
+ "learning_rate": 9.615534979266745e-05,
437
+ "loss": 11.7419,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.009859907152540981,
442
+ "grad_norm": 0.07708930224180222,
443
+ "learning_rate": 9.599897218294122e-05,
444
+ "loss": 11.7387,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.010024238938416663,
449
+ "grad_norm": 0.08723892271518707,
450
+ "learning_rate": 9.583960976582913e-05,
451
+ "loss": 11.7393,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.010188570724292346,
456
+ "grad_norm": 0.08119846135377884,
457
+ "learning_rate": 9.567727288213005e-05,
458
+ "loss": 11.7412,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.01035290251016803,
463
+ "grad_norm": 0.0847805067896843,
464
+ "learning_rate": 9.551197206565173e-05,
465
+ "loss": 11.743,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010517234296043712,
470
+ "grad_norm": 0.07967144250869751,
471
+ "learning_rate": 9.534371804252728e-05,
472
+ "loss": 11.7405,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010681566081919395,
477
+ "grad_norm": 0.046992260962724686,
478
+ "learning_rate": 9.517252173051911e-05,
479
+ "loss": 11.7404,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.010845897867795079,
484
+ "grad_norm": 0.054778508841991425,
485
+ "learning_rate": 9.49983942383106e-05,
486
+ "loss": 11.7398,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.011010229653670761,
491
+ "grad_norm": 0.05465163663029671,
492
+ "learning_rate": 9.482134686478519e-05,
493
+ "loss": 11.7414,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.011174561439546444,
498
+ "grad_norm": 0.06919052451848984,
499
+ "learning_rate": 9.464139109829321e-05,
500
+ "loss": 11.7432,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011338893225422128,
505
+ "grad_norm": 0.04978770390152931,
506
+ "learning_rate": 9.445853861590647e-05,
507
+ "loss": 11.7406,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01150322501129781,
512
+ "grad_norm": 0.05154619738459587,
513
+ "learning_rate": 9.42728012826605e-05,
514
+ "loss": 11.7389,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011667556797173493,
519
+ "grad_norm": 0.058466438204050064,
520
+ "learning_rate": 9.408419115078471e-05,
521
+ "loss": 11.7376,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.011831888583049177,
526
+ "grad_norm": 0.07136223465204239,
527
+ "learning_rate": 9.389272045892024e-05,
528
+ "loss": 11.738,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.01199622036892486,
533
+ "grad_norm": 0.0563649944961071,
534
+ "learning_rate": 9.36984016313259e-05,
535
+ "loss": 11.738,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.012160552154800542,
540
+ "grad_norm": 0.062396273016929626,
541
+ "learning_rate": 9.350124727707197e-05,
542
+ "loss": 11.7354,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012324883940676224,
547
+ "grad_norm": 0.05039061978459358,
548
+ "learning_rate": 9.330127018922194e-05,
549
+ "loss": 11.7388,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012489215726551909,
554
+ "grad_norm": 0.058604415506124496,
555
+ "learning_rate": 9.309848334400246e-05,
556
+ "loss": 11.7386,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.012653547512427591,
561
+ "grad_norm": 0.08999053388834,
562
+ "learning_rate": 9.289289989996133e-05,
563
+ "loss": 11.7338,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.012817879298303273,
568
+ "grad_norm": 0.05026502162218094,
569
+ "learning_rate": 9.268453319711363e-05,
570
+ "loss": 11.7371,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.012982211084178958,
575
+ "grad_norm": 0.06558049470186234,
576
+ "learning_rate": 9.247339675607605e-05,
577
+ "loss": 11.7358,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.01314654287005464,
582
+ "grad_norm": 0.06828798353672028,
583
+ "learning_rate": 9.225950427718975e-05,
584
+ "loss": 11.7333,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.013310874655930323,
589
+ "grad_norm": 0.05039716139435768,
590
+ "learning_rate": 9.204286963963111e-05,
591
+ "loss": 11.7367,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.013475206441806007,
596
+ "grad_norm": 0.09033340215682983,
597
+ "learning_rate": 9.182350690051133e-05,
598
+ "loss": 11.737,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.01363953822768169,
603
+ "grad_norm": 0.04329407215118408,
604
+ "learning_rate": 9.160143029396422e-05,
605
+ "loss": 11.7365,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.013803870013557372,
610
+ "grad_norm": 0.05856756493449211,
611
+ "learning_rate": 9.13766542302225e-05,
612
+ "loss": 11.7351,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.013968201799433056,
617
+ "grad_norm": 0.06545337289571762,
618
+ "learning_rate": 9.114919329468282e-05,
619
+ "loss": 11.7321,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.014132533585308738,
624
+ "grad_norm": 0.06385994702577591,
625
+ "learning_rate": 9.091906224695935e-05,
626
+ "loss": 11.734,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.01429686537118442,
631
+ "grad_norm": 0.0672338604927063,
632
+ "learning_rate": 9.068627601992598e-05,
633
+ "loss": 11.7357,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.014461197157060105,
638
+ "grad_norm": 0.06891307979822159,
639
+ "learning_rate": 9.045084971874738e-05,
640
+ "loss": 11.7329,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.014625528942935787,
645
+ "grad_norm": 0.05319250375032425,
646
+ "learning_rate": 9.021279861989885e-05,
647
+ "loss": 11.7367,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.01478986072881147,
652
+ "grad_norm": 0.07806988060474396,
653
+ "learning_rate": 8.997213817017507e-05,
654
+ "loss": 11.7364,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.014954192514687154,
659
+ "grad_norm": 0.07189088314771652,
660
+ "learning_rate": 8.972888398568772e-05,
661
+ "loss": 11.7356,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.015118524300562836,
666
+ "grad_norm": 0.07356931269168854,
667
+ "learning_rate": 8.948305185085225e-05,
668
+ "loss": 11.7331,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.015282856086438519,
673
+ "grad_norm": 0.07599375396966934,
674
+ "learning_rate": 8.92346577173636e-05,
675
+ "loss": 11.7298,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015447187872314203,
680
+ "grad_norm": 0.08366679400205612,
681
+ "learning_rate": 8.898371770316111e-05,
682
+ "loss": 11.728,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.015611519658189885,
687
+ "grad_norm": 0.08361729979515076,
688
+ "learning_rate": 8.873024809138272e-05,
689
+ "loss": 11.7304,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.01577585144406557,
694
+ "grad_norm": 0.07593885809183121,
695
+ "learning_rate": 8.847426532930831e-05,
696
+ "loss": 11.7272,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.01594018322994125,
701
+ "grad_norm": 0.09948297590017319,
702
+ "learning_rate": 8.821578602729242e-05,
703
+ "loss": 11.7321,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.016104515015816934,
708
+ "grad_norm": 0.13416649401187897,
709
+ "learning_rate": 8.795482695768658e-05,
710
+ "loss": 11.7273,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.01626884680169262,
715
+ "grad_norm": 0.12499107420444489,
716
+ "learning_rate": 8.769140505375085e-05,
717
+ "loss": 11.7205,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0164331785875683,
722
+ "grad_norm": 0.2499997466802597,
723
+ "learning_rate": 8.742553740855506e-05,
724
+ "loss": 11.7202,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0164331785875683,
729
+ "eval_loss": 11.734024047851562,
730
+ "eval_runtime": 48.7146,
731
+ "eval_samples_per_second": 210.389,
732
+ "eval_steps_per_second": 52.613,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 41434585497600.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null