prxy5605 commited on
Commit
c609a1d
·
verified ·
1 Parent(s): bac33f2

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 sha256:216d0dbb3a51e60455a16d025dabd37c10c8e6597d776930fd9b461984e783ff
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d6d025c38202d7987ee426151328b7612425c438c05ca9732083d682444a78d
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6708ab003f628a58d33e24c4be5418abd73c432afb09c3f00631546f93f7df8
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bce81c1d83fa2e10d0a288ac0ce4a34d1786db0c43d6da813d17aa3d07319346
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b71fd13ede0e0aaa635e96cd7c7ae24eb934dcfc999271d7d3352406f87a70d6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:095a5dbc60995a1f237ab3f197cce7aef4d06809ef2d17a6c3188fde144e0eb9
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": 1.4198116064071655,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.22650056625141562,
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": 13.254,
374
  "eval_steps_per_second": 3.314,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.54256789372928e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2719783782958984,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.45300113250283125,
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": 13.254,
374
  "eval_steps_per_second": 3.314,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.23103057757644394,
379
+ "grad_norm": 3.488363742828369,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.9693,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.23556058890147225,
386
+ "grad_norm": 2.687886953353882,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.1449,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.24009060022650056,
393
+ "grad_norm": 2.1666171550750732,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.3024,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.24462061155152887,
400
+ "grad_norm": 1.742993712425232,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.1097,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.2491506228765572,
407
+ "grad_norm": 1.1420605182647705,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.9356,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.2536806342015855,
414
+ "grad_norm": 1.286728024482727,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.8034,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2582106455266138,
421
+ "grad_norm": 1.2109533548355103,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.982,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2627406568516421,
428
+ "grad_norm": 1.1387308835983276,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.8655,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.26727066817667045,
435
+ "grad_norm": 1.2849539518356323,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.1622,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2718006795016987,
442
+ "grad_norm": 1.1417158842086792,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.125,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.27633069082672707,
449
+ "grad_norm": 1.0794636011123657,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.9444,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.2808607021517554,
456
+ "grad_norm": 1.2429821491241455,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.9038,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2853907134767837,
463
+ "grad_norm": 1.1989555358886719,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.0491,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.289920724801812,
470
+ "grad_norm": 1.1882569789886475,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.0463,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.2944507361268403,
477
+ "grad_norm": 1.1703907251358032,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.0251,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.29898074745186864,
484
+ "grad_norm": 1.2039575576782227,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.0778,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3035107587768969,
491
+ "grad_norm": 1.465887427330017,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.2316,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.30804077010192527,
498
+ "grad_norm": 1.305050015449524,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.0009,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.31257078142695355,
505
+ "grad_norm": 1.4737871885299683,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.0594,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.3171007927519819,
512
+ "grad_norm": 1.253055214881897,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.9838,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.32163080407701017,
519
+ "grad_norm": 1.260217547416687,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.0468,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.3261608154020385,
526
+ "grad_norm": 1.305269718170166,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.1493,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.33069082672706684,
533
+ "grad_norm": 1.295682668685913,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.1228,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3352208380520951,
540
+ "grad_norm": 1.2946406602859497,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.0911,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.33975084937712347,
547
+ "grad_norm": 1.3201980590820312,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.9902,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.34428086070215175,
554
+ "grad_norm": 1.3449866771697998,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.7981,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3488108720271801,
561
+ "grad_norm": 1.356520652770996,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.1687,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.35334088335220837,
568
+ "grad_norm": 1.3135828971862793,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.9721,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3578708946772367,
575
+ "grad_norm": 1.6086395978927612,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.3614,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.362400906002265,
582
+ "grad_norm": 1.6636041402816772,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.3424,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.3669309173272933,
589
+ "grad_norm": 1.725728988647461,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.3588,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.3714609286523216,
596
+ "grad_norm": 1.5616434812545776,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.0019,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.37599093997734995,
603
+ "grad_norm": 1.633862853050232,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.2381,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.38052095130237823,
610
+ "grad_norm": 1.6802394390106201,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.451,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.38505096262740657,
617
+ "grad_norm": 1.623841643333435,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.1578,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.3895809739524349,
624
+ "grad_norm": 1.532440185546875,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.2683,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3941109852774632,
631
+ "grad_norm": 1.7631417512893677,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.2269,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3986409966024915,
638
+ "grad_norm": 1.90073561668396,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.2522,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.4031710079275198,
645
+ "grad_norm": 1.7768625020980835,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.2126,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.40770101925254815,
652
+ "grad_norm": 1.7604447603225708,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.0491,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.41223103057757643,
659
+ "grad_norm": 1.8100131750106812,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.1563,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.41676104190260477,
666
+ "grad_norm": 1.7785227298736572,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.2355,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.42129105322763305,
673
+ "grad_norm": 2.1177375316619873,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.3305,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.4258210645526614,
680
+ "grad_norm": 2.3690457344055176,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.5447,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.43035107587768967,
687
+ "grad_norm": 1.9034374952316284,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.1644,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.434881087202718,
694
+ "grad_norm": 2.056325912475586,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.3085,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.43941109852774635,
701
+ "grad_norm": 2.021763324737549,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.3537,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.44394110985277463,
708
+ "grad_norm": 2.4095985889434814,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.4288,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.44847112117780297,
715
+ "grad_norm": 2.138651132583618,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.2902,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.45300113250283125,
722
+ "grad_norm": 2.890157461166382,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.3736,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.45300113250283125,
729
+ "eval_loss": 1.2719783782958984,
730
+ "eval_runtime": 28.1062,
731
+ "eval_samples_per_second": 13.235,
732
+ "eval_steps_per_second": 3.309,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null