bbytxt commited on
Commit
4ca76e6
·
verified ·
1 Parent(s): b97be44

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:f62b5f2468f1a4794e105e0919ce798a67a1bfe01a19ad62be9eea0837ddea8c
3
  size 26008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cfa960e26e7313f45ed66175129ede040128a91bbe7eefc552edd0291d0afb9
3
  size 26008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca2476b2e9e85fd039e34ab77ba2fc189947c495e1edc8c124467f93ad7f5037
3
  size 68874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1acd47c782af25ea71657f1cd0cd0ead4d496b32e21378acfb48c4ae9d10bf8e
3
  size 68874
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19548bada73dc88e3b9c7d8f5ee2a174119be2d6de8a7d12c7595fb21d905767
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e745240ea492d302e6e50e9ee4c5ad0725ded989d45924a41c0064c4e363c2e0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ad2841b888ce0ae948634757c3fcacf0119c249e0fec8f3ca61ea266369ef92
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d2a6c6aafc669cea03b9634666f204de949a3d45ce2f48a07e7e3eaf18c715
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 11.91733169555664,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.11019283746556474,
5
  "eval_steps": 25,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -381,6 +381,372 @@
381
  "eval_samples_per_second": 189.053,
382
  "eval_steps_per_second": 26.467,
383
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -409,7 +775,7 @@
409
  "attributes": {}
410
  }
411
  },
412
- "total_flos": 79631155200.0,
413
  "train_batch_size": 8,
414
  "trial_name": null,
415
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.898636817932129,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.22038567493112948,
5
  "eval_steps": 25,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
381
  "eval_samples_per_second": 189.053,
382
  "eval_steps_per_second": 26.467,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.11239669421487604,
387
+ "grad_norm": 0.09227705001831055,
388
+ "learning_rate": 0.0002668315918143169,
389
+ "loss": 11.9309,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.11460055096418732,
394
+ "grad_norm": 0.1322363317012787,
395
+ "learning_rate": 0.00026526016662852886,
396
+ "loss": 11.9193,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.11680440771349862,
401
+ "grad_norm": 0.12950630486011505,
402
+ "learning_rate": 0.00026365723046405023,
403
+ "loss": 11.914,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.11900826446280992,
408
+ "grad_norm": 0.14015230536460876,
409
+ "learning_rate": 0.0002620232215476231,
410
+ "loss": 11.9153,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.12121212121212122,
415
+ "grad_norm": 0.14919088780879974,
416
+ "learning_rate": 0.0002603585866009697,
417
+ "loss": 11.9099,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.12341597796143251,
422
+ "grad_norm": 0.11809884756803513,
423
+ "learning_rate": 0.00025866378071866334,
424
+ "loss": 11.9087,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.1256198347107438,
429
+ "grad_norm": 0.13996019959449768,
430
+ "learning_rate": 0.00025693926724370956,
431
+ "loss": 11.9073,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.1278236914600551,
436
+ "grad_norm": 0.13844236731529236,
437
+ "learning_rate": 0.00025518551764087326,
438
+ "loss": 11.9084,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.13002754820936638,
443
+ "grad_norm": 0.1513601541519165,
444
+ "learning_rate": 0.00025340301136778483,
445
+ "loss": 11.9072,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.1322314049586777,
450
+ "grad_norm": 0.15952962636947632,
451
+ "learning_rate": 0.00025159223574386114,
452
+ "loss": 11.9082,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.13443526170798897,
457
+ "grad_norm": 0.11324327439069748,
458
+ "learning_rate": 0.0002497536858170772,
459
+ "loss": 11.8976,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.13663911845730028,
464
+ "grad_norm": 0.1319524496793747,
465
+ "learning_rate": 0.00024788786422862526,
466
+ "loss": 11.8988,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.13884297520661157,
471
+ "grad_norm": 0.13562187552452087,
472
+ "learning_rate": 0.00024599528107549745,
473
+ "loss": 11.9001,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.14104683195592285,
478
+ "grad_norm": 0.10524652153253555,
479
+ "learning_rate": 0.00024407645377103054,
480
+ "loss": 11.9006,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.14325068870523416,
485
+ "grad_norm": 0.13076205551624298,
486
+ "learning_rate": 0.00024213190690345018,
487
+ "loss": 11.9137,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.14545454545454545,
492
+ "grad_norm": 0.14588449895381927,
493
+ "learning_rate": 0.00024016217209245374,
494
+ "loss": 11.9071,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.14765840220385676,
499
+ "grad_norm": 0.16398610174655914,
500
+ "learning_rate": 0.00023816778784387094,
501
+ "loss": 11.9,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.14986225895316804,
506
+ "grad_norm": 0.13749021291732788,
507
+ "learning_rate": 0.0002361492994024415,
508
+ "loss": 11.8945,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.15206611570247933,
513
+ "grad_norm": 0.13079959154129028,
514
+ "learning_rate": 0.0002341072586027509,
515
+ "loss": 11.8949,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.15426997245179064,
520
+ "grad_norm": 0.10493382811546326,
521
+ "learning_rate": 0.00023204222371836405,
522
+ "loss": 11.8943,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.15647382920110192,
527
+ "grad_norm": 0.10082471370697021,
528
+ "learning_rate": 0.00022995475930919905,
529
+ "loss": 11.8976,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.15867768595041323,
534
+ "grad_norm": 0.138931542634964,
535
+ "learning_rate": 0.00022784543606718227,
536
+ "loss": 11.9008,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.16088154269972452,
541
+ "grad_norm": 0.16665118932724,
542
+ "learning_rate": 0.00022571483066022657,
543
+ "loss": 11.8992,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 0.1630853994490358,
548
+ "grad_norm": 0.09672952443361282,
549
+ "learning_rate": 0.0002235635255745762,
550
+ "loss": 11.8893,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 0.1652892561983471,
555
+ "grad_norm": 0.0886247456073761,
556
+ "learning_rate": 0.00022139210895556104,
557
+ "loss": 11.8885,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 0.1652892561983471,
562
+ "eval_loss": 11.899949073791504,
563
+ "eval_runtime": 0.2633,
564
+ "eval_samples_per_second": 189.892,
565
+ "eval_steps_per_second": 26.585,
566
+ "step": 75
567
+ },
568
+ {
569
+ "epoch": 0.1674931129476584,
570
+ "grad_norm": 0.09242913126945496,
571
+ "learning_rate": 0.00021920117444680317,
572
+ "loss": 11.8931,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 0.1696969696969697,
577
+ "grad_norm": 0.09106940031051636,
578
+ "learning_rate": 0.00021699132102792097,
579
+ "loss": 11.8972,
580
+ "step": 77
581
+ },
582
+ {
583
+ "epoch": 0.171900826446281,
584
+ "grad_norm": 0.09342004358768463,
585
+ "learning_rate": 0.0002147631528507739,
586
+ "loss": 11.8948,
587
+ "step": 78
588
+ },
589
+ {
590
+ "epoch": 0.17410468319559227,
591
+ "grad_norm": 0.1103108748793602,
592
+ "learning_rate": 0.00021251727907429355,
593
+ "loss": 11.8963,
594
+ "step": 79
595
+ },
596
+ {
597
+ "epoch": 0.1763085399449036,
598
+ "grad_norm": 0.14813131093978882,
599
+ "learning_rate": 0.0002102543136979454,
600
+ "loss": 11.8954,
601
+ "step": 80
602
+ },
603
+ {
604
+ "epoch": 0.17851239669421487,
605
+ "grad_norm": 0.08995470404624939,
606
+ "learning_rate": 0.0002079748753938678,
607
+ "loss": 11.8883,
608
+ "step": 81
609
+ },
610
+ {
611
+ "epoch": 0.18071625344352618,
612
+ "grad_norm": 0.08261939138174057,
613
+ "learning_rate": 0.0002056795873377331,
614
+ "loss": 11.8938,
615
+ "step": 82
616
+ },
617
+ {
618
+ "epoch": 0.18292011019283747,
619
+ "grad_norm": 0.08036128431558609,
620
+ "learning_rate": 0.00020336907703837748,
621
+ "loss": 11.8852,
622
+ "step": 83
623
+ },
624
+ {
625
+ "epoch": 0.18512396694214875,
626
+ "grad_norm": 0.122383251786232,
627
+ "learning_rate": 0.00020104397616624645,
628
+ "loss": 11.8976,
629
+ "step": 84
630
+ },
631
+ {
632
+ "epoch": 0.18732782369146006,
633
+ "grad_norm": 0.06162508204579353,
634
+ "learning_rate": 0.00019870492038070252,
635
+ "loss": 11.8828,
636
+ "step": 85
637
+ },
638
+ {
639
+ "epoch": 0.18953168044077134,
640
+ "grad_norm": 0.05778353661298752,
641
+ "learning_rate": 0.0001963525491562421,
642
+ "loss": 11.8874,
643
+ "step": 86
644
+ },
645
+ {
646
+ "epoch": 0.19173553719008266,
647
+ "grad_norm": 0.0797528401017189,
648
+ "learning_rate": 0.0001939875056076697,
649
+ "loss": 11.8865,
650
+ "step": 87
651
+ },
652
+ {
653
+ "epoch": 0.19393939393939394,
654
+ "grad_norm": 0.0552869513630867,
655
+ "learning_rate": 0.00019161043631427666,
656
+ "loss": 11.8921,
657
+ "step": 88
658
+ },
659
+ {
660
+ "epoch": 0.19614325068870522,
661
+ "grad_norm": 0.07009490579366684,
662
+ "learning_rate": 0.00018922199114307294,
663
+ "loss": 11.8908,
664
+ "step": 89
665
+ },
666
+ {
667
+ "epoch": 0.19834710743801653,
668
+ "grad_norm": 0.11296062171459198,
669
+ "learning_rate": 0.00018682282307111987,
670
+ "loss": 11.8894,
671
+ "step": 90
672
+ },
673
+ {
674
+ "epoch": 0.20055096418732782,
675
+ "grad_norm": 0.046599071472883224,
676
+ "learning_rate": 0.00018441358800701273,
677
+ "loss": 11.879,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 0.20275482093663913,
682
+ "grad_norm": 0.06188511103391647,
683
+ "learning_rate": 0.00018199494461156203,
684
+ "loss": 11.8923,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 0.2049586776859504,
689
+ "grad_norm": 0.08621121942996979,
690
+ "learning_rate": 0.000179567554117722,
691
+ "loss": 11.8869,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 0.2071625344352617,
696
+ "grad_norm": 0.11004097014665604,
697
+ "learning_rate": 0.00017713208014981648,
698
+ "loss": 11.8952,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 0.209366391184573,
703
+ "grad_norm": 0.07841908186674118,
704
+ "learning_rate": 0.00017468918854211007,
705
+ "loss": 11.8892,
706
+ "step": 95
707
+ },
708
+ {
709
+ "epoch": 0.2115702479338843,
710
+ "grad_norm": 0.11397922039031982,
711
+ "learning_rate": 0.00017223954715677627,
712
+ "loss": 11.8855,
713
+ "step": 96
714
+ },
715
+ {
716
+ "epoch": 0.2137741046831956,
717
+ "grad_norm": 0.1289277821779251,
718
+ "learning_rate": 0.00016978382570131034,
719
+ "loss": 11.8875,
720
+ "step": 97
721
+ },
722
+ {
723
+ "epoch": 0.2159779614325069,
724
+ "grad_norm": 0.08124374598264694,
725
+ "learning_rate": 0.00016732269554543794,
726
+ "loss": 11.8823,
727
+ "step": 98
728
+ },
729
+ {
730
+ "epoch": 0.21818181818181817,
731
+ "grad_norm": 0.09473321586847305,
732
+ "learning_rate": 0.00016485682953756942,
733
+ "loss": 11.8845,
734
+ "step": 99
735
+ },
736
+ {
737
+ "epoch": 0.22038567493112948,
738
+ "grad_norm": 0.34638768434524536,
739
+ "learning_rate": 0.00016238690182084986,
740
+ "loss": 11.8753,
741
+ "step": 100
742
+ },
743
+ {
744
+ "epoch": 0.22038567493112948,
745
+ "eval_loss": 11.898636817932129,
746
+ "eval_runtime": 0.2629,
747
+ "eval_samples_per_second": 190.203,
748
+ "eval_steps_per_second": 26.628,
749
+ "step": 100
750
  }
751
  ],
752
  "logging_steps": 1,
 
775
  "attributes": {}
776
  }
777
  },
778
+ "total_flos": 159262310400.0,
779
  "train_batch_size": 8,
780
  "trial_name": null,
781
  "trial_params": null