bbytxt commited on
Commit
87461ee
·
verified ·
1 Parent(s): 614fc14

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 sha256:44b44bea23136391da795bffb0b54ee8407c205bbf6ee236743d19df2fb9d154
3
  size 26008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae45528f3341936563228a33ed804562ef0575df7cdc5c5711db186ba6ab7d3
3
  size 26008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:142be8efb9f8ff84bcd421869258cfd66703ef9e20d8cbd0c8a2c7dd5813af9b
3
  size 68874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dbb105de7c818c246cfaa11814996aa4cfaffc0ae5e1622d5286fa2bda7e012
3
  size 68874
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ff1ac109557de1d48c609fa29cdbfa6bff52e8b5cf3b144b5284b5baf194877
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ffcfb9336e6489b6865cf033c8678543a127a9139ef4cebf1affb1ad696a14
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": 11.92931842803955,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.04549590536851683,
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": 126.97,
382
  "eval_steps_per_second": 126.97,
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": 11.91674518585205,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.09099181073703366,
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": 126.97,
382
  "eval_steps_per_second": 126.97,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.04640582347588717,
387
+ "grad_norm": 0.15377391874790192,
388
+ "learning_rate": 0.0002668315918143169,
389
+ "loss": 11.9129,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.047315741583257506,
394
+ "grad_norm": 0.16208061575889587,
395
+ "learning_rate": 0.00026526016662852886,
396
+ "loss": 11.9072,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.048225659690627844,
401
+ "grad_norm": 0.1508318930864334,
402
+ "learning_rate": 0.00026365723046405023,
403
+ "loss": 11.9114,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.04913557779799818,
408
+ "grad_norm": 0.1259605437517166,
409
+ "learning_rate": 0.0002620232215476231,
410
+ "loss": 11.9135,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.05004549590536852,
415
+ "grad_norm": 0.13642816245555878,
416
+ "learning_rate": 0.0002603585866009697,
417
+ "loss": 11.9171,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.050955414012738856,
422
+ "grad_norm": 0.1361204981803894,
423
+ "learning_rate": 0.00025866378071866334,
424
+ "loss": 11.9173,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.051865332120109194,
429
+ "grad_norm": 0.11698855459690094,
430
+ "learning_rate": 0.00025693926724370956,
431
+ "loss": 11.9176,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.052775250227479524,
436
+ "grad_norm": 0.08528847247362137,
437
+ "learning_rate": 0.00025518551764087326,
438
+ "loss": 11.9185,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.05368516833484986,
443
+ "grad_norm": 0.05039224773645401,
444
+ "learning_rate": 0.00025340301136778483,
445
+ "loss": 11.9163,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.0545950864422202,
450
+ "grad_norm": 0.07579994201660156,
451
+ "learning_rate": 0.00025159223574386114,
452
+ "loss": 11.9175,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.055505004549590536,
457
+ "grad_norm": 0.05966591835021973,
458
+ "learning_rate": 0.0002497536858170772,
459
+ "loss": 11.9148,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.056414922656960874,
464
+ "grad_norm": 0.0829024538397789,
465
+ "learning_rate": 0.00024788786422862526,
466
+ "loss": 11.917,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.05732484076433121,
471
+ "grad_norm": 0.07866007834672928,
472
+ "learning_rate": 0.00024599528107549745,
473
+ "loss": 11.9179,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.05823475887170155,
478
+ "grad_norm": 0.06062201410531998,
479
+ "learning_rate": 0.00024407645377103054,
480
+ "loss": 11.919,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.059144676979071886,
485
+ "grad_norm": 0.059842102229595184,
486
+ "learning_rate": 0.00024213190690345018,
487
+ "loss": 11.9171,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.06005459508644222,
492
+ "grad_norm": 0.1073002815246582,
493
+ "learning_rate": 0.00024016217209245374,
494
+ "loss": 11.9169,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.060964513193812554,
499
+ "grad_norm": 0.08621833473443985,
500
+ "learning_rate": 0.00023816778784387094,
501
+ "loss": 11.9157,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.06187443130118289,
506
+ "grad_norm": 0.06708350777626038,
507
+ "learning_rate": 0.0002361492994024415,
508
+ "loss": 11.9198,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.06278434940855324,
513
+ "grad_norm": 0.06917531043291092,
514
+ "learning_rate": 0.0002341072586027509,
515
+ "loss": 11.9187,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.06369426751592357,
520
+ "grad_norm": 0.07202816754579544,
521
+ "learning_rate": 0.00023204222371836405,
522
+ "loss": 11.916,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.0646041856232939,
527
+ "grad_norm": 0.07306147366762161,
528
+ "learning_rate": 0.00022995475930919905,
529
+ "loss": 11.9201,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.06551410373066424,
534
+ "grad_norm": 0.0853971466422081,
535
+ "learning_rate": 0.00022784543606718227,
536
+ "loss": 11.9233,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.06642402183803457,
541
+ "grad_norm": 0.07358640432357788,
542
+ "learning_rate": 0.00022571483066022657,
543
+ "loss": 11.9158,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 0.06733393994540492,
548
+ "grad_norm": 0.0628897175192833,
549
+ "learning_rate": 0.0002235635255745762,
550
+ "loss": 11.9193,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 0.06824385805277525,
555
+ "grad_norm": 0.07899107038974762,
556
+ "learning_rate": 0.00022139210895556104,
557
+ "loss": 11.9145,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 0.06824385805277525,
562
+ "eval_loss": 11.921226501464844,
563
+ "eval_runtime": 0.3951,
564
+ "eval_samples_per_second": 126.559,
565
+ "eval_steps_per_second": 126.559,
566
+ "step": 75
567
+ },
568
+ {
569
+ "epoch": 0.06915377616014559,
570
+ "grad_norm": 0.06351622939109802,
571
+ "learning_rate": 0.00021920117444680317,
572
+ "loss": 11.9147,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 0.07006369426751592,
577
+ "grad_norm": 0.10964340716600418,
578
+ "learning_rate": 0.00021699132102792097,
579
+ "loss": 11.9162,
580
+ "step": 77
581
+ },
582
+ {
583
+ "epoch": 0.07097361237488627,
584
+ "grad_norm": 0.0985313206911087,
585
+ "learning_rate": 0.0002147631528507739,
586
+ "loss": 11.9125,
587
+ "step": 78
588
+ },
589
+ {
590
+ "epoch": 0.0718835304822566,
591
+ "grad_norm": 0.08922101557254791,
592
+ "learning_rate": 0.00021251727907429355,
593
+ "loss": 11.914,
594
+ "step": 79
595
+ },
596
+ {
597
+ "epoch": 0.07279344858962693,
598
+ "grad_norm": 0.08533662557601929,
599
+ "learning_rate": 0.0002102543136979454,
600
+ "loss": 11.9112,
601
+ "step": 80
602
+ },
603
+ {
604
+ "epoch": 0.07370336669699727,
605
+ "grad_norm": 0.07660248875617981,
606
+ "learning_rate": 0.0002079748753938678,
607
+ "loss": 11.9204,
608
+ "step": 81
609
+ },
610
+ {
611
+ "epoch": 0.0746132848043676,
612
+ "grad_norm": 0.092041015625,
613
+ "learning_rate": 0.0002056795873377331,
614
+ "loss": 11.9157,
615
+ "step": 82
616
+ },
617
+ {
618
+ "epoch": 0.07552320291173795,
619
+ "grad_norm": 0.06479498744010925,
620
+ "learning_rate": 0.00020336907703837748,
621
+ "loss": 11.92,
622
+ "step": 83
623
+ },
624
+ {
625
+ "epoch": 0.07643312101910828,
626
+ "grad_norm": 0.07256922870874405,
627
+ "learning_rate": 0.00020104397616624645,
628
+ "loss": 11.9126,
629
+ "step": 84
630
+ },
631
+ {
632
+ "epoch": 0.07734303912647862,
633
+ "grad_norm": 0.07706281542778015,
634
+ "learning_rate": 0.00019870492038070252,
635
+ "loss": 11.9111,
636
+ "step": 85
637
+ },
638
+ {
639
+ "epoch": 0.07825295723384895,
640
+ "grad_norm": 0.0908479318022728,
641
+ "learning_rate": 0.0001963525491562421,
642
+ "loss": 11.9176,
643
+ "step": 86
644
+ },
645
+ {
646
+ "epoch": 0.0791628753412193,
647
+ "grad_norm": 0.0594383142888546,
648
+ "learning_rate": 0.0001939875056076697,
649
+ "loss": 11.9157,
650
+ "step": 87
651
+ },
652
+ {
653
+ "epoch": 0.08007279344858963,
654
+ "grad_norm": 0.06577011942863464,
655
+ "learning_rate": 0.00019161043631427666,
656
+ "loss": 11.9193,
657
+ "step": 88
658
+ },
659
+ {
660
+ "epoch": 0.08098271155595996,
661
+ "grad_norm": 0.07253321260213852,
662
+ "learning_rate": 0.00018922199114307294,
663
+ "loss": 11.9117,
664
+ "step": 89
665
+ },
666
+ {
667
+ "epoch": 0.0818926296633303,
668
+ "grad_norm": 0.08957824856042862,
669
+ "learning_rate": 0.00018682282307111987,
670
+ "loss": 11.9163,
671
+ "step": 90
672
+ },
673
+ {
674
+ "epoch": 0.08280254777070063,
675
+ "grad_norm": 0.0847165584564209,
676
+ "learning_rate": 0.00018441358800701273,
677
+ "loss": 11.9122,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 0.08371246587807098,
682
+ "grad_norm": 0.0713360458612442,
683
+ "learning_rate": 0.00018199494461156203,
684
+ "loss": 11.9178,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 0.08462238398544131,
689
+ "grad_norm": 0.08201546221971512,
690
+ "learning_rate": 0.000179567554117722,
691
+ "loss": 11.9134,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 0.08553230209281165,
696
+ "grad_norm": 0.07122859358787537,
697
+ "learning_rate": 0.00017713208014981648,
698
+ "loss": 11.9171,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 0.08644222020018198,
703
+ "grad_norm": 0.08683283627033234,
704
+ "learning_rate": 0.00017468918854211007,
705
+ "loss": 11.9146,
706
+ "step": 95
707
+ },
708
+ {
709
+ "epoch": 0.08735213830755233,
710
+ "grad_norm": 0.09123071283102036,
711
+ "learning_rate": 0.00017223954715677627,
712
+ "loss": 11.9156,
713
+ "step": 96
714
+ },
715
+ {
716
+ "epoch": 0.08826205641492266,
717
+ "grad_norm": 0.0987405776977539,
718
+ "learning_rate": 0.00016978382570131034,
719
+ "loss": 11.9176,
720
+ "step": 97
721
+ },
722
+ {
723
+ "epoch": 0.08917197452229299,
724
+ "grad_norm": 0.06329481303691864,
725
+ "learning_rate": 0.00016732269554543794,
726
+ "loss": 11.9224,
727
+ "step": 98
728
+ },
729
+ {
730
+ "epoch": 0.09008189262966333,
731
+ "grad_norm": 0.11751674115657806,
732
+ "learning_rate": 0.00016485682953756942,
733
+ "loss": 11.9276,
734
+ "step": 99
735
+ },
736
+ {
737
+ "epoch": 0.09099181073703366,
738
+ "grad_norm": 0.11672987043857574,
739
+ "learning_rate": 0.00016238690182084986,
740
+ "loss": 11.9208,
741
+ "step": 100
742
+ },
743
+ {
744
+ "epoch": 0.09099181073703366,
745
+ "eval_loss": 11.91674518585205,
746
+ "eval_runtime": 0.393,
747
+ "eval_samples_per_second": 127.218,
748
+ "eval_steps_per_second": 127.218,
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