lesso commited on
Commit
6342e25
·
verified ·
1 Parent(s): 434ca52

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:bca942a0332d8cdaf6ae591e59a67018da069a0149a60ff832aff0afb22f6663
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac3251736b4749706e795a889907966b5cab5abae1c4647b06151db195237ba
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:565e8c4125d722de048fd741838317c6cd882080ed2b810f977d1a10e609ebab
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dadad7399eae02a7deb08797a7ec823ea4278be855ca3f0675ca00d752211d8
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dc9631693dcdd37ce05c716d305458dab17ae59dfb935b2e02ecf66a56f566c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c6b5340458c9ca6a80b5a49485e7729403a2f924cd9c5295f89ae5a29df02cc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2f1cc7ac96b43e89afbf900f41769c2bbe93e9d76b453a576e60002b6ad5d48
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429ac0058d053852a57e244c528ad2a9ef374afdf80fd23f716aee5119cd57d1
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1576098203659058,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.13440860215053763,
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": 7.838,
374
  "eval_steps_per_second": 1.997,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.66313582395392e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9393484592437744,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.26881720430107525,
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": 7.838,
374
  "eval_steps_per_second": 1.997,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.13709677419354838,
379
+ "grad_norm": 3.6493349075317383,
380
+ "learning_rate": 7.904842105263158e-05,
381
+ "loss": 3.4341,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.13978494623655913,
386
+ "grad_norm": 3.946737051010132,
387
+ "learning_rate": 7.85178947368421e-05,
388
+ "loss": 4.1712,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.1424731182795699,
393
+ "grad_norm": 3.0488572120666504,
394
+ "learning_rate": 7.798736842105263e-05,
395
+ "loss": 2.7678,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.14516129032258066,
400
+ "grad_norm": 2.641152858734131,
401
+ "learning_rate": 7.745684210526315e-05,
402
+ "loss": 3.4299,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.1478494623655914,
407
+ "grad_norm": 2.6064324378967285,
408
+ "learning_rate": 7.692631578947369e-05,
409
+ "loss": 2.8889,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.15053763440860216,
414
+ "grad_norm": 2.853044271469116,
415
+ "learning_rate": 7.639578947368421e-05,
416
+ "loss": 3.9092,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1532258064516129,
421
+ "grad_norm": 3.7264606952667236,
422
+ "learning_rate": 7.586526315789473e-05,
423
+ "loss": 3.1663,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.15591397849462366,
428
+ "grad_norm": 2.3590335845947266,
429
+ "learning_rate": 7.533473684210526e-05,
430
+ "loss": 2.5423,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.1586021505376344,
435
+ "grad_norm": 3.6274800300598145,
436
+ "learning_rate": 7.480421052631578e-05,
437
+ "loss": 2.7857,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.16129032258064516,
442
+ "grad_norm": 3.466926097869873,
443
+ "learning_rate": 7.427368421052632e-05,
444
+ "loss": 2.1407,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.1639784946236559,
449
+ "grad_norm": 2.135305166244507,
450
+ "learning_rate": 7.374315789473685e-05,
451
+ "loss": 2.0501,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.16666666666666666,
456
+ "grad_norm": 2.145434617996216,
457
+ "learning_rate": 7.321263157894737e-05,
458
+ "loss": 1.8671,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.1693548387096774,
463
+ "grad_norm": 2.250318765640259,
464
+ "learning_rate": 7.26821052631579e-05,
465
+ "loss": 2.8158,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.17204301075268819,
470
+ "grad_norm": 2.0222816467285156,
471
+ "learning_rate": 7.215157894736842e-05,
472
+ "loss": 1.9672,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.17473118279569894,
477
+ "grad_norm": 2.0015830993652344,
478
+ "learning_rate": 7.162105263157894e-05,
479
+ "loss": 1.7105,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.1774193548387097,
484
+ "grad_norm": 2.1358511447906494,
485
+ "learning_rate": 7.109052631578947e-05,
486
+ "loss": 2.0722,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.18010752688172044,
491
+ "grad_norm": 2.1164755821228027,
492
+ "learning_rate": 7.055999999999999e-05,
493
+ "loss": 1.3778,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.1827956989247312,
498
+ "grad_norm": 2.6545348167419434,
499
+ "learning_rate": 7.002947368421052e-05,
500
+ "loss": 1.5793,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.18548387096774194,
505
+ "grad_norm": 2.278327703475952,
506
+ "learning_rate": 6.949894736842105e-05,
507
+ "loss": 1.3986,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.1881720430107527,
512
+ "grad_norm": 2.1539969444274902,
513
+ "learning_rate": 6.896842105263158e-05,
514
+ "loss": 0.8514,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.19086021505376344,
519
+ "grad_norm": 2.815715789794922,
520
+ "learning_rate": 6.843789473684211e-05,
521
+ "loss": 1.9194,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.1935483870967742,
526
+ "grad_norm": 1.7789136171340942,
527
+ "learning_rate": 6.790736842105263e-05,
528
+ "loss": 1.1168,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.19623655913978494,
533
+ "grad_norm": 2.7908670902252197,
534
+ "learning_rate": 6.737684210526315e-05,
535
+ "loss": 1.6579,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.1989247311827957,
540
+ "grad_norm": 3.0436408519744873,
541
+ "learning_rate": 6.684631578947368e-05,
542
+ "loss": 2.1317,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.20161290322580644,
547
+ "grad_norm": 2.6586692333221436,
548
+ "learning_rate": 6.631578947368421e-05,
549
+ "loss": 1.5078,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.20430107526881722,
554
+ "grad_norm": 2.3957104682922363,
555
+ "learning_rate": 6.578526315789473e-05,
556
+ "loss": 1.4137,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.20698924731182797,
561
+ "grad_norm": 2.467710256576538,
562
+ "learning_rate": 6.525473684210526e-05,
563
+ "loss": 1.5379,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.20967741935483872,
568
+ "grad_norm": 2.3089401721954346,
569
+ "learning_rate": 6.47242105263158e-05,
570
+ "loss": 1.3105,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.21236559139784947,
575
+ "grad_norm": 3.3448803424835205,
576
+ "learning_rate": 6.419368421052632e-05,
577
+ "loss": 2.9907,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.21505376344086022,
582
+ "grad_norm": 1.918912649154663,
583
+ "learning_rate": 6.366315789473684e-05,
584
+ "loss": 1.0538,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.21774193548387097,
589
+ "grad_norm": 2.1565945148468018,
590
+ "learning_rate": 6.313263157894736e-05,
591
+ "loss": 0.8427,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.22043010752688172,
596
+ "grad_norm": 1.9118677377700806,
597
+ "learning_rate": 6.26021052631579e-05,
598
+ "loss": 0.8702,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.22311827956989247,
603
+ "grad_norm": 2.161041498184204,
604
+ "learning_rate": 6.207157894736842e-05,
605
+ "loss": 1.5612,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.22580645161290322,
610
+ "grad_norm": 1.8799899816513062,
611
+ "learning_rate": 6.154105263157894e-05,
612
+ "loss": 1.0472,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.22849462365591397,
617
+ "grad_norm": 3.115447521209717,
618
+ "learning_rate": 6.1010526315789474e-05,
619
+ "loss": 1.3093,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.23118279569892472,
624
+ "grad_norm": 2.5335817337036133,
625
+ "learning_rate": 6.048e-05,
626
+ "loss": 1.5528,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.23387096774193547,
631
+ "grad_norm": 2.8771631717681885,
632
+ "learning_rate": 5.994947368421052e-05,
633
+ "loss": 1.6662,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.23655913978494625,
638
+ "grad_norm": 3.9417519569396973,
639
+ "learning_rate": 5.941894736842104e-05,
640
+ "loss": 1.8012,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.239247311827957,
645
+ "grad_norm": 3.2698731422424316,
646
+ "learning_rate": 5.888842105263158e-05,
647
+ "loss": 2.3075,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.24193548387096775,
652
+ "grad_norm": 2.6435606479644775,
653
+ "learning_rate": 5.835789473684211e-05,
654
+ "loss": 1.3781,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.2446236559139785,
659
+ "grad_norm": 3.099759817123413,
660
+ "learning_rate": 5.782736842105263e-05,
661
+ "loss": 2.1561,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.24731182795698925,
666
+ "grad_norm": 3.145350217819214,
667
+ "learning_rate": 5.7296842105263154e-05,
668
+ "loss": 1.4506,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.25,
673
+ "grad_norm": 4.324268341064453,
674
+ "learning_rate": 5.676631578947368e-05,
675
+ "loss": 0.9423,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.25268817204301075,
680
+ "grad_norm": 2.9348642826080322,
681
+ "learning_rate": 5.623578947368421e-05,
682
+ "loss": 1.7886,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.2553763440860215,
687
+ "grad_norm": 1.738901138305664,
688
+ "learning_rate": 5.570526315789474e-05,
689
+ "loss": 0.676,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.25806451612903225,
694
+ "grad_norm": 2.8710925579071045,
695
+ "learning_rate": 5.5174736842105266e-05,
696
+ "loss": 0.9851,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.260752688172043,
701
+ "grad_norm": 3.99045729637146,
702
+ "learning_rate": 5.464421052631579e-05,
703
+ "loss": 1.8844,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.26344086021505375,
708
+ "grad_norm": 4.602737903594971,
709
+ "learning_rate": 5.411368421052631e-05,
710
+ "loss": 1.3643,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.2661290322580645,
715
+ "grad_norm": 3.7166576385498047,
716
+ "learning_rate": 5.358315789473684e-05,
717
+ "loss": 0.6935,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.26881720430107525,
722
+ "grad_norm": 3.1870436668395996,
723
+ "learning_rate": 5.3052631578947364e-05,
724
+ "loss": 1.2186,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.26881720430107525,
729
+ "eval_loss": 0.9393484592437744,
730
+ "eval_runtime": 20.0614,
731
+ "eval_samples_per_second": 7.826,
732
+ "eval_steps_per_second": 1.994,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.32627164790784e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null