cilooor commited on
Commit
e82d9ac
·
verified ·
1 Parent(s): 1b2a818

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 sha256:70e1ec4b6f6902db0e58c3632b9f55aadd914913afa079d9c85514d681d29360
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515948f9892eb56522995af4e7447e14a1ce77ab48040cabb3e69bd864966d61
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1278f66835c673e62d1c58950c57a487cb44334a3c85674f3e8352df685d299b
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c353dec8a42af643633c760a6b4a39c29024ea6e35a17d7000c75db4efd93084
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:825a8fa54ca4102a13edeb7a75c2c5da461eae8b595ce2b2eaadf98696986762
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eabd323f96aa88f0a0c8cc7cb371e7b584d6f9b8cd6ddec15dc9da6604213a40
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f153938c08b62688f6e56c8abc0a37c00fee4d7e364e15e32c7b150f9f5f65c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b0f0591a54513981f9045153a7608f989005ce4fb6ed2c798b085bae23c1094
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.4549524486064911,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0392156862745098,
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": 12.5,
374
  "eval_steps_per_second": 3.125,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.548522993392026e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.423828125,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0784313725490196,
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": 12.5,
374
  "eval_steps_per_second": 3.125,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.04,
379
+ "grad_norm": 14.582710266113281,
380
+ "learning_rate": 8.004947754429507e-05,
381
+ "loss": 4.1472,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0407843137254902,
386
+ "grad_norm": 6.1638922691345215,
387
+ "learning_rate": 7.957804998855866e-05,
388
+ "loss": 2.2978,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.04156862745098039,
393
+ "grad_norm": 3.731342077255249,
394
+ "learning_rate": 7.909716913921508e-05,
395
+ "loss": 1.9173,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.042352941176470586,
400
+ "grad_norm": 3.8371353149414062,
401
+ "learning_rate": 7.860696646428694e-05,
402
+ "loss": 1.4256,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.043137254901960784,
407
+ "grad_norm": 4.627960205078125,
408
+ "learning_rate": 7.810757598029093e-05,
409
+ "loss": 1.6277,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.04392156862745098,
414
+ "grad_norm": 4.3101043701171875,
415
+ "learning_rate": 7.759913421559902e-05,
416
+ "loss": 1.5975,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.04470588235294118,
421
+ "grad_norm": 2.9555671215057373,
422
+ "learning_rate": 7.708178017311287e-05,
423
+ "loss": 1.0289,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.04549019607843137,
428
+ "grad_norm": 3.413313865661621,
429
+ "learning_rate": 7.655565529226198e-05,
430
+ "loss": 1.3867,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.04627450980392157,
435
+ "grad_norm": 3.6849825382232666,
436
+ "learning_rate": 7.602090341033547e-05,
437
+ "loss": 1.2773,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.047058823529411764,
442
+ "grad_norm": 3.837523937225342,
443
+ "learning_rate": 7.547767072315837e-05,
444
+ "loss": 1.4187,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.04784313725490196,
449
+ "grad_norm": 3.476501226425171,
450
+ "learning_rate": 7.492610574512317e-05,
451
+ "loss": 1.2678,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.04862745098039216,
456
+ "grad_norm": 3.9961957931518555,
457
+ "learning_rate": 7.436635926858759e-05,
458
+ "loss": 1.4783,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04941176470588235,
463
+ "grad_norm": 4.245054244995117,
464
+ "learning_rate": 7.379858432264925e-05,
465
+ "loss": 1.5066,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.05019607843137255,
470
+ "grad_norm": 5.134169578552246,
471
+ "learning_rate": 7.322293613130917e-05,
472
+ "loss": 1.4297,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.050980392156862744,
477
+ "grad_norm": 4.725772380828857,
478
+ "learning_rate": 7.263957207103507e-05,
479
+ "loss": 1.6951,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.05176470588235294,
484
+ "grad_norm": 4.962766647338867,
485
+ "learning_rate": 7.204865162773613e-05,
486
+ "loss": 1.5281,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.05254901960784314,
491
+ "grad_norm": 4.3428192138671875,
492
+ "learning_rate": 7.14503363531613e-05,
493
+ "loss": 1.4586,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.05333333333333334,
498
+ "grad_norm": 5.0155029296875,
499
+ "learning_rate": 7.084478982073247e-05,
500
+ "loss": 1.5896,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.05411764705882353,
505
+ "grad_norm": 4.897243976593018,
506
+ "learning_rate": 7.023217758082528e-05,
507
+ "loss": 1.1711,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.054901960784313725,
512
+ "grad_norm": 5.0609612464904785,
513
+ "learning_rate": 6.961266711550922e-05,
514
+ "loss": 1.4897,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.05568627450980392,
519
+ "grad_norm": 4.689002990722656,
520
+ "learning_rate": 6.898642779275972e-05,
521
+ "loss": 0.9881,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.05647058823529412,
526
+ "grad_norm": 6.720233917236328,
527
+ "learning_rate": 6.835363082015469e-05,
528
+ "loss": 1.5692,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.05725490196078432,
533
+ "grad_norm": 5.96003532409668,
534
+ "learning_rate": 6.771444919806798e-05,
535
+ "loss": 1.3238,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.05803921568627451,
540
+ "grad_norm": 6.871821880340576,
541
+ "learning_rate": 6.706905767237288e-05,
542
+ "loss": 1.4878,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.058823529411764705,
547
+ "grad_norm": 6.003084182739258,
548
+ "learning_rate": 6.641763268666833e-05,
549
+ "loss": 1.5651,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0596078431372549,
554
+ "grad_norm": 6.855623245239258,
555
+ "learning_rate": 6.576035233404096e-05,
556
+ "loss": 1.5011,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0603921568627451,
561
+ "grad_norm": 6.763059616088867,
562
+ "learning_rate": 6.509739630837631e-05,
563
+ "loss": 1.6047,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0611764705882353,
568
+ "grad_norm": 6.753271579742432,
569
+ "learning_rate": 6.442894585523218e-05,
570
+ "loss": 1.5268,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.06196078431372549,
575
+ "grad_norm": 5.556756973266602,
576
+ "learning_rate": 6.375518372228808e-05,
577
+ "loss": 1.0404,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.06274509803921569,
582
+ "grad_norm": 6.503464221954346,
583
+ "learning_rate": 6.307629410938363e-05,
584
+ "loss": 1.0106,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.06352941176470588,
589
+ "grad_norm": 4.450430870056152,
590
+ "learning_rate": 6.239246261816035e-05,
591
+ "loss": 0.6093,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.06431372549019608,
596
+ "grad_norm": 6.413719177246094,
597
+ "learning_rate": 6.170387620131993e-05,
598
+ "loss": 1.238,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.06509803921568627,
603
+ "grad_norm": 5.047544956207275,
604
+ "learning_rate": 6.101072311151325e-05,
605
+ "loss": 0.8442,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.06588235294117648,
610
+ "grad_norm": 7.372629165649414,
611
+ "learning_rate": 6.0313192849873945e-05,
612
+ "loss": 1.4398,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.06666666666666667,
617
+ "grad_norm": 9.576523780822754,
618
+ "learning_rate": 5.961147611421077e-05,
619
+ "loss": 1.4834,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.06745098039215686,
624
+ "grad_norm": 6.8355207443237305,
625
+ "learning_rate": 5.890576474687264e-05,
626
+ "loss": 1.6157,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.06823529411764706,
631
+ "grad_norm": 7.017658233642578,
632
+ "learning_rate": 5.8196251682300926e-05,
633
+ "loss": 1.6794,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.06901960784313725,
638
+ "grad_norm": 8.371786117553711,
639
+ "learning_rate": 5.748313089428301e-05,
640
+ "loss": 1.5957,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.06980392156862746,
645
+ "grad_norm": 10.280915260314941,
646
+ "learning_rate": 5.676659734292189e-05,
647
+ "loss": 2.2618,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.07058823529411765,
652
+ "grad_norm": 8.091904640197754,
653
+ "learning_rate": 5.604684692133597e-05,
654
+ "loss": 1.3325,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.07137254901960784,
659
+ "grad_norm": 8.49736499786377,
660
+ "learning_rate": 5.532407640210383e-05,
661
+ "loss": 1.4017,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.07215686274509804,
666
+ "grad_norm": 7.801628112792969,
667
+ "learning_rate": 5.4598483383468616e-05,
668
+ "loss": 1.3546,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.07294117647058823,
673
+ "grad_norm": 9.922377586364746,
674
+ "learning_rate": 5.3870266235316614e-05,
675
+ "loss": 1.8899,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.07372549019607844,
680
+ "grad_norm": 12.533098220825195,
681
+ "learning_rate": 5.313962404494496e-05,
682
+ "loss": 1.8032,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.07450980392156863,
687
+ "grad_norm": 13.20348072052002,
688
+ "learning_rate": 5.240675656263303e-05,
689
+ "loss": 1.8548,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.07529411764705882,
694
+ "grad_norm": 22.03706932067871,
695
+ "learning_rate": 5.167186414703289e-05,
696
+ "loss": 2.4985,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.07607843137254902,
701
+ "grad_norm": 18.293331146240234,
702
+ "learning_rate": 5.093514771039311e-05,
703
+ "loss": 1.9427,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.07686274509803921,
708
+ "grad_norm": 19.484935760498047,
709
+ "learning_rate": 5.019680866363139e-05,
710
+ "loss": 2.3599,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.07764705882352942,
715
+ "grad_norm": 19.723976135253906,
716
+ "learning_rate": 4.9457048861270835e-05,
717
+ "loss": 2.401,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0784313725490196,
722
+ "grad_norm": 19.807950973510742,
723
+ "learning_rate": 4.871607054625497e-05,
724
+ "loss": 1.9219,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0784313725490196,
729
+ "eval_loss": 0.423828125,
730
+ "eval_runtime": 172.1475,
731
+ "eval_samples_per_second": 12.478,
732
+ "eval_steps_per_second": 3.119,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.513282097727406e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null