bbytxt commited on
Commit
edff761
·
verified ·
1 Parent(s): 8376eda

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:bcfbea5fbc6c2082c800c2a31619115d24e5f8e6c38dc00a6369805dc95d7344
3
  size 411094576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee61387ae938122ecaf275bf9884cefefafd6dbc0adf8d80802af54937ad9fb3
3
  size 411094576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:013cfc76875c9c538225a0106df7f54fd00fe4a18ebdc3c8e8634bf2391c6284
3
  size 209193332
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a288d2e7907611253e095658ec5b4b0d11bd3c33f62c9b52bc64803fb29777
3
  size 209193332
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e9cee4caf33aba1b2e26075f7f822390845422302c824966564d74ca0e1a5ce
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cce9ade4c3f92c6eb28d476379147a3afe884120b10d385ff03f2a1335b835f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3668920993804932,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.040666937779585195,
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": 19.327,
374
  "eval_steps_per_second": 4.834,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3.13171868909568e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3060370683670044,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.08133387555917039,
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": 19.327,
374
  "eval_steps_per_second": 4.834,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0414802765351769,
379
+ "grad_norm": 2.5964858531951904,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.327,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0422936152907686,
386
+ "grad_norm": 1.9609887599945068,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.3133,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.04310695404636031,
393
+ "grad_norm": 1.1775012016296387,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.204,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.04392029280195201,
400
+ "grad_norm": 1.0460187196731567,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.2136,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.044733631557543715,
407
+ "grad_norm": 0.9313177466392517,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.1933,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.04554697031313542,
414
+ "grad_norm": 1.049389362335205,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.2795,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.046360309068727124,
421
+ "grad_norm": 1.006925344467163,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.1701,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.04717364782431883,
428
+ "grad_norm": 0.9446033239364624,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.1624,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.04798698657991053,
435
+ "grad_norm": 0.8426344990730286,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.1467,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.048800325335502236,
442
+ "grad_norm": 0.8230246901512146,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.1479,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.04961366409109394,
449
+ "grad_norm": 0.8439881801605225,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.1607,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.050427002846685644,
456
+ "grad_norm": 0.9041538238525391,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.1217,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.05124034160227735,
463
+ "grad_norm": 0.9187133312225342,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.2933,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.05205368035786905,
470
+ "grad_norm": 0.9471145868301392,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.2492,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.052867019113460756,
477
+ "grad_norm": 1.015170931816101,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.2066,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.05368035786905246,
484
+ "grad_norm": 0.9947161078453064,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.2231,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.054493696624644164,
491
+ "grad_norm": 0.9911460280418396,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.2152,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.05530703538023587,
498
+ "grad_norm": 1.1157715320587158,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.1715,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.05612037413582757,
505
+ "grad_norm": 1.0330973863601685,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.1573,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.056933712891419276,
512
+ "grad_norm": 1.1242437362670898,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.2355,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.05774705164701098,
519
+ "grad_norm": 1.18375563621521,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.1546,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.058560390402602684,
526
+ "grad_norm": 1.1902270317077637,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.1947,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.05937372915819439,
533
+ "grad_norm": 1.186957597732544,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.2263,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.06018706791378609,
540
+ "grad_norm": 1.2676359415054321,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.2803,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.061000406669377796,
547
+ "grad_norm": 1.3717691898345947,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.2326,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0618137454249695,
554
+ "grad_norm": 1.4836101531982422,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.2476,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0626270841805612,
561
+ "grad_norm": 1.612488031387329,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.1825,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0634404229361529,
568
+ "grad_norm": 1.594044804573059,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.3276,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.06425376169174461,
575
+ "grad_norm": 1.643832802772522,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.1981,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.06506710044733631,
582
+ "grad_norm": 1.9011435508728027,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.2833,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.06588043920292802,
589
+ "grad_norm": 1.8688122034072876,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.3166,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.06669377795851972,
596
+ "grad_norm": 2.2397377490997314,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.2734,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.06750711671411143,
603
+ "grad_norm": 2.2626216411590576,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.2673,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.06832045546970313,
610
+ "grad_norm": 2.330335855484009,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.1307,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.06913379422529484,
617
+ "grad_norm": 2.426630973815918,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.1187,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.06994713298088653,
624
+ "grad_norm": 2.255751609802246,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.19,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.07076047173647824,
631
+ "grad_norm": 2.8092153072357178,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.2152,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.07157381049206994,
638
+ "grad_norm": 2.3413901329040527,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.0266,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.07238714924766165,
645
+ "grad_norm": 2.6290576457977295,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.0065,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.07320048800325335,
652
+ "grad_norm": 2.9226067066192627,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.0783,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.07401382675884506,
659
+ "grad_norm": 2.9445765018463135,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.9754,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.07482716551443676,
666
+ "grad_norm": 2.7714364528656006,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.8755,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.07564050427002847,
673
+ "grad_norm": 3.633474349975586,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.224,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.07645384302562017,
680
+ "grad_norm": 4.1051154136657715,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.0751,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.07726718178121188,
687
+ "grad_norm": 3.6421470642089844,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.0392,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.07808052053680357,
694
+ "grad_norm": 3.6323955059051514,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.0279,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.07889385929239529,
701
+ "grad_norm": 4.387916088104248,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.9259,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.07970719804798698,
708
+ "grad_norm": 3.2340691089630127,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.7949,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0805205368035787,
715
+ "grad_norm": 4.503349304199219,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.0153,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.08133387555917039,
722
+ "grad_norm": 6.987500190734863,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.2214,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.08133387555917039,
729
+ "eval_loss": 1.3060370683670044,
730
+ "eval_runtime": 107.5359,
731
+ "eval_samples_per_second": 19.259,
732
+ "eval_steps_per_second": 4.817,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6.26343737819136e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null