nttx commited on
Commit
17d323f
·
verified ·
1 Parent(s): 5a0f81d

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:f97467721aec6e0c2eb65b6c90ed84fa214b6629c96cf4170482dc594e8fb9a4
3
  size 3029024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ab0b0bc8dadef22dde424dee84e4de3b89e33ea481120cdc85febc63b2c95e
3
  size 3029024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b6a6d05d11a53b41ca584412ebda97c2ed909e56189d8d73f9f0cbbc0b311a4
3
  size 1663290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547564943f1e391318007dab5808d6765c7e375c5a963b1980dc1bef44f0e75d
3
  size 1663290
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b4cf84bbe9ec3fab1fc6c408929024432b803fd59844cdcad7453639263843e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6580697246592f87cbea8f8bfebf56e0a57dfbc8e93a56cb2b22420311da14d1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6413aa14aafdcc9641671bfc199ce3eecc99395b74dcb3987f0ba2049861e550
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cdd5e1998f1139b3d2606fc1207245b65164fdf9041e6fa58bd90acc8d38fa5
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.096914291381836,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.003832078327681018,
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": 52.575,
374
  "eval_steps_per_second": 6.572,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 65412268032000.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 9.585326194763184,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.007664156655362036,
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": 52.575,
374
  "eval_steps_per_second": 6.572,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.003908719894234638,
379
+ "grad_norm": 2.9691355228424072,
380
+ "learning_rate": 7.65e-06,
381
+ "loss": 10.012,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.003985361460788259,
386
+ "grad_norm": 3.0408084392547607,
387
+ "learning_rate": 7.8e-06,
388
+ "loss": 10.1541,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0040620030273418786,
393
+ "grad_norm": 2.865037441253662,
394
+ "learning_rate": 7.95e-06,
395
+ "loss": 10.1152,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.004138644593895499,
400
+ "grad_norm": 3.0118324756622314,
401
+ "learning_rate": 8.1e-06,
402
+ "loss": 10.056,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.00421528616044912,
407
+ "grad_norm": 3.0567305088043213,
408
+ "learning_rate": 8.25e-06,
409
+ "loss": 10.1187,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.00429192772700274,
414
+ "grad_norm": 3.090759038925171,
415
+ "learning_rate": 8.400000000000001e-06,
416
+ "loss": 9.9549,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.00436856929355636,
421
+ "grad_norm": 3.094413995742798,
422
+ "learning_rate": 8.55e-06,
423
+ "loss": 10.0912,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.00444521086010998,
428
+ "grad_norm": 2.8803794384002686,
429
+ "learning_rate": 8.7e-06,
430
+ "loss": 10.0612,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.004521852426663601,
435
+ "grad_norm": 3.1622092723846436,
436
+ "learning_rate": 8.85e-06,
437
+ "loss": 10.0883,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0045984939932172215,
442
+ "grad_norm": 3.1270225048065186,
443
+ "learning_rate": 9e-06,
444
+ "loss": 10.0202,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.004675135559770842,
449
+ "grad_norm": 3.1323904991149902,
450
+ "learning_rate": 9.15e-06,
451
+ "loss": 9.9491,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.004751777126324462,
456
+ "grad_norm": 3.130385637283325,
457
+ "learning_rate": 9.3e-06,
458
+ "loss": 9.9419,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.004828418692878082,
463
+ "grad_norm": 2.9450523853302,
464
+ "learning_rate": 9.450000000000001e-06,
465
+ "loss": 9.9549,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.004905060259431703,
470
+ "grad_norm": 2.9594674110412598,
471
+ "learning_rate": 9.600000000000001e-06,
472
+ "loss": 9.9597,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.004981701825985323,
477
+ "grad_norm": 2.946688413619995,
478
+ "learning_rate": 9.75e-06,
479
+ "loss": 10.0721,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.005058343392538944,
484
+ "grad_norm": 3.045152425765991,
485
+ "learning_rate": 9.9e-06,
486
+ "loss": 9.8657,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.005134984959092564,
491
+ "grad_norm": 3.0098981857299805,
492
+ "learning_rate": 1.005e-05,
493
+ "loss": 9.8488,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.005211626525646184,
498
+ "grad_norm": 2.9197866916656494,
499
+ "learning_rate": 1.02e-05,
500
+ "loss": 9.858,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.005288268092199805,
505
+ "grad_norm": 3.026247501373291,
506
+ "learning_rate": 1.035e-05,
507
+ "loss": 9.9475,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.005364909658753425,
512
+ "grad_norm": 2.9125189781188965,
513
+ "learning_rate": 1.05e-05,
514
+ "loss": 9.9352,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.005441551225307045,
519
+ "grad_norm": 2.881605863571167,
520
+ "learning_rate": 1.065e-05,
521
+ "loss": 10.0641,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.0055181927918606655,
526
+ "grad_norm": 3.004376173019409,
527
+ "learning_rate": 1.08e-05,
528
+ "loss": 10.0225,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.005594834358414286,
533
+ "grad_norm": 3.101276159286499,
534
+ "learning_rate": 1.095e-05,
535
+ "loss": 9.9834,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.0056714759249679066,
540
+ "grad_norm": 2.9609551429748535,
541
+ "learning_rate": 1.11e-05,
542
+ "loss": 9.942,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.005748117491521527,
547
+ "grad_norm": 2.913710594177246,
548
+ "learning_rate": 1.125e-05,
549
+ "loss": 9.864,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.005824759058075147,
554
+ "grad_norm": 2.971576452255249,
555
+ "learning_rate": 1.1400000000000001e-05,
556
+ "loss": 9.9609,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.005901400624628767,
561
+ "grad_norm": 3.054107904434204,
562
+ "learning_rate": 1.1550000000000001e-05,
563
+ "loss": 10.0123,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.005978042191182388,
568
+ "grad_norm": 2.910504102706909,
569
+ "learning_rate": 1.1700000000000001e-05,
570
+ "loss": 9.8387,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.006054683757736008,
575
+ "grad_norm": 2.9695205688476562,
576
+ "learning_rate": 1.185e-05,
577
+ "loss": 9.8195,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.006131325324289628,
582
+ "grad_norm": 2.9118409156799316,
583
+ "learning_rate": 1.2e-05,
584
+ "loss": 9.7845,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.006207966890843249,
589
+ "grad_norm": 3.0323214530944824,
590
+ "learning_rate": 1.215e-05,
591
+ "loss": 9.8386,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.006284608457396869,
596
+ "grad_norm": 2.9126343727111816,
597
+ "learning_rate": 1.2299999999999999e-05,
598
+ "loss": 9.8635,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.00636125002395049,
603
+ "grad_norm": 3.027489185333252,
604
+ "learning_rate": 1.245e-05,
605
+ "loss": 9.8263,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.00643789159050411,
610
+ "grad_norm": 2.968306064605713,
611
+ "learning_rate": 1.26e-05,
612
+ "loss": 9.7821,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.00651453315705773,
617
+ "grad_norm": 3.212526321411133,
618
+ "learning_rate": 1.275e-05,
619
+ "loss": 9.8742,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0065911747236113505,
624
+ "grad_norm": 3.0750510692596436,
625
+ "learning_rate": 1.29e-05,
626
+ "loss": 9.756,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.006667816290164971,
631
+ "grad_norm": 3.143045425415039,
632
+ "learning_rate": 1.305e-05,
633
+ "loss": 9.733,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.006744457856718592,
638
+ "grad_norm": 3.0339534282684326,
639
+ "learning_rate": 1.32e-05,
640
+ "loss": 9.7565,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.006821099423272211,
645
+ "grad_norm": 2.8683807849884033,
646
+ "learning_rate": 1.3350000000000001e-05,
647
+ "loss": 9.673,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.006897740989825832,
652
+ "grad_norm": 3.0948848724365234,
653
+ "learning_rate": 1.3500000000000001e-05,
654
+ "loss": 9.6999,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.006974382556379452,
659
+ "grad_norm": 3.123711347579956,
660
+ "learning_rate": 1.3650000000000001e-05,
661
+ "loss": 9.868,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.007051024122933073,
666
+ "grad_norm": 3.072702169418335,
667
+ "learning_rate": 1.3800000000000002e-05,
668
+ "loss": 9.6111,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0071276656894866935,
673
+ "grad_norm": 3.133103609085083,
674
+ "learning_rate": 1.395e-05,
675
+ "loss": 9.7074,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.007204307256040313,
680
+ "grad_norm": 3.1256680488586426,
681
+ "learning_rate": 1.4099999999999999e-05,
682
+ "loss": 9.7523,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.007280948822593934,
687
+ "grad_norm": 3.0179288387298584,
688
+ "learning_rate": 1.4249999999999999e-05,
689
+ "loss": 9.6325,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.007357590389147554,
694
+ "grad_norm": 3.047670841217041,
695
+ "learning_rate": 1.44e-05,
696
+ "loss": 9.7347,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.007434231955701175,
701
+ "grad_norm": 3.1137807369232178,
702
+ "learning_rate": 1.455e-05,
703
+ "loss": 9.5914,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0075108735222547945,
708
+ "grad_norm": 2.887342929840088,
709
+ "learning_rate": 1.47e-05,
710
+ "loss": 9.6417,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.007587515088808415,
715
+ "grad_norm": 3.202164888381958,
716
+ "learning_rate": 1.485e-05,
717
+ "loss": 9.4693,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.007664156655362036,
722
+ "grad_norm": 3.069445848464966,
723
+ "learning_rate": 1.5e-05,
724
+ "loss": 9.5667,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.007664156655362036,
729
+ "eval_loss": 9.585326194763184,
730
+ "eval_runtime": 418.1777,
731
+ "eval_samples_per_second": 52.552,
732
+ "eval_steps_per_second": 6.569,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 130824536064000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null