brixeus commited on
Commit
b1b0b9c
·
verified ·
1 Parent(s): bf1da72

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:fc6e68db57f849e519b75c8eb328cc84268592c60b174f700f4b8d8ca9851515
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35bfa18bdf96d73d0776a4d22831da45517a45fe299a138f453e6fc4fa2b066
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d65c6c62e0f62eaf80f2917b78f5c4c6c1d728aacf6af7abacc48d8ff3faef9
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f233bbdc9db2c456c625b641f36e2e111c2839bf81277fbd465edb35cea937a
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf6705f17cb24d4fd0c5d954a5d525d7657e4e21fdc8727ae67cb37371997ad0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c19603883f401b22c80b09e5759616914515eaed24945964ab2bd875ab59183
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed340328d62f63f2d9d00f6904395875dd09851f050e03ae91b4b798d852ce41
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ca67f9a35cd1c50df3d93bedf5a6642db2c7847c021a0a8d3f44c1bf4993d3
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.82403564453125,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.009961647656522389,
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": 13.916,
374
  "eval_steps_per_second": 3.48,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.1094434267136e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.8152918815612793,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.019923295313044778,
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": 13.916,
374
  "eval_steps_per_second": 3.48,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.010160880609652836,
379
+ "grad_norm": 0.8542794585227966,
380
+ "learning_rate": 9.729774092143627e-05,
381
+ "loss": 1.6775,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.010360113562783284,
386
+ "grad_norm": 0.8750085234642029,
387
+ "learning_rate": 9.716559066288715e-05,
388
+ "loss": 1.4926,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.010559346515913733,
393
+ "grad_norm": 0.875607430934906,
394
+ "learning_rate": 9.703037989675087e-05,
395
+ "loss": 1.8167,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01075857946904418,
400
+ "grad_norm": 0.7322773933410645,
401
+ "learning_rate": 9.689211739666023e-05,
402
+ "loss": 1.4753,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.010957812422174628,
407
+ "grad_norm": 0.648223876953125,
408
+ "learning_rate": 9.675081213427076e-05,
409
+ "loss": 1.3975,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.011157045375305076,
414
+ "grad_norm": 0.6270776391029358,
415
+ "learning_rate": 9.66064732786784e-05,
416
+ "loss": 1.1602,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.011356278328435523,
421
+ "grad_norm": 0.6656715273857117,
422
+ "learning_rate": 9.645911019582467e-05,
423
+ "loss": 1.3633,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.011555511281565971,
428
+ "grad_norm": 0.7466765642166138,
429
+ "learning_rate": 9.630873244788883e-05,
430
+ "loss": 1.4871,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01175474423469642,
435
+ "grad_norm": 0.8152953386306763,
436
+ "learning_rate": 9.615534979266745e-05,
437
+ "loss": 1.4701,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.011953977187826866,
442
+ "grad_norm": 0.8492268919944763,
443
+ "learning_rate": 9.599897218294122e-05,
444
+ "loss": 1.688,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.012153210140957315,
449
+ "grad_norm": 0.7441631555557251,
450
+ "learning_rate": 9.583960976582913e-05,
451
+ "loss": 1.5078,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.012352443094087761,
456
+ "grad_norm": 0.8003615736961365,
457
+ "learning_rate": 9.567727288213005e-05,
458
+ "loss": 1.86,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.01255167604721821,
463
+ "grad_norm": 0.7498038411140442,
464
+ "learning_rate": 9.551197206565173e-05,
465
+ "loss": 1.4841,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.012750909000348658,
470
+ "grad_norm": 0.7930290699005127,
471
+ "learning_rate": 9.534371804252728e-05,
472
+ "loss": 1.6008,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.012950141953479105,
477
+ "grad_norm": 0.7177601456642151,
478
+ "learning_rate": 9.517252173051911e-05,
479
+ "loss": 1.4822,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.013149374906609553,
484
+ "grad_norm": 0.7637808918952942,
485
+ "learning_rate": 9.49983942383106e-05,
486
+ "loss": 1.6999,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.013348607859740002,
491
+ "grad_norm": 0.6996709108352661,
492
+ "learning_rate": 9.482134686478519e-05,
493
+ "loss": 1.5346,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.013547840812870448,
498
+ "grad_norm": 0.8542125821113586,
499
+ "learning_rate": 9.464139109829321e-05,
500
+ "loss": 1.8176,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.013747073766000897,
505
+ "grad_norm": 0.8093202710151672,
506
+ "learning_rate": 9.445853861590647e-05,
507
+ "loss": 1.5795,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.013946306719131345,
512
+ "grad_norm": 0.8053815960884094,
513
+ "learning_rate": 9.42728012826605e-05,
514
+ "loss": 1.7278,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.014145539672261792,
519
+ "grad_norm": 0.823073148727417,
520
+ "learning_rate": 9.408419115078471e-05,
521
+ "loss": 1.6882,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.01434477262539224,
526
+ "grad_norm": 0.9014071822166443,
527
+ "learning_rate": 9.389272045892024e-05,
528
+ "loss": 1.7093,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.014544005578522687,
533
+ "grad_norm": 0.9905192852020264,
534
+ "learning_rate": 9.36984016313259e-05,
535
+ "loss": 1.8529,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.014743238531653135,
540
+ "grad_norm": 0.8374629020690918,
541
+ "learning_rate": 9.350124727707197e-05,
542
+ "loss": 1.7811,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.014942471484783584,
547
+ "grad_norm": 1.0269732475280762,
548
+ "learning_rate": 9.330127018922194e-05,
549
+ "loss": 1.8239,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.01514170443791403,
554
+ "grad_norm": 0.7490584254264832,
555
+ "learning_rate": 9.309848334400246e-05,
556
+ "loss": 1.5871,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.015340937391044479,
561
+ "grad_norm": 0.8312053680419922,
562
+ "learning_rate": 9.289289989996133e-05,
563
+ "loss": 1.6725,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.015540170344174927,
568
+ "grad_norm": 0.7715761661529541,
569
+ "learning_rate": 9.268453319711363e-05,
570
+ "loss": 1.6291,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.015739403297305374,
575
+ "grad_norm": 0.8476051688194275,
576
+ "learning_rate": 9.247339675607605e-05,
577
+ "loss": 1.8967,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.01593863625043582,
582
+ "grad_norm": 0.7571315765380859,
583
+ "learning_rate": 9.225950427718975e-05,
584
+ "loss": 1.6547,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01613786920356627,
589
+ "grad_norm": 0.831329882144928,
590
+ "learning_rate": 9.204286963963111e-05,
591
+ "loss": 1.9368,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.016337102156696717,
596
+ "grad_norm": 0.7381522059440613,
597
+ "learning_rate": 9.182350690051133e-05,
598
+ "loss": 1.8917,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.016536335109827164,
603
+ "grad_norm": 0.9195905923843384,
604
+ "learning_rate": 9.160143029396422e-05,
605
+ "loss": 1.907,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.016735568062957614,
610
+ "grad_norm": 0.7933158874511719,
611
+ "learning_rate": 9.13766542302225e-05,
612
+ "loss": 1.7316,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.01693480101608806,
617
+ "grad_norm": 0.8460677266120911,
618
+ "learning_rate": 9.114919329468282e-05,
619
+ "loss": 2.0394,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.017134033969218507,
624
+ "grad_norm": 0.8626026511192322,
625
+ "learning_rate": 9.091906224695935e-05,
626
+ "loss": 1.7807,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.017333266922348958,
631
+ "grad_norm": 1.0532417297363281,
632
+ "learning_rate": 9.068627601992598e-05,
633
+ "loss": 1.9692,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.017532499875479404,
638
+ "grad_norm": 0.9541111588478088,
639
+ "learning_rate": 9.045084971874738e-05,
640
+ "loss": 2.1123,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.01773173282860985,
645
+ "grad_norm": 0.8808003067970276,
646
+ "learning_rate": 9.021279861989885e-05,
647
+ "loss": 2.1134,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0179309657817403,
652
+ "grad_norm": 0.9053674936294556,
653
+ "learning_rate": 8.997213817017507e-05,
654
+ "loss": 1.8627,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.018130198734870748,
659
+ "grad_norm": 0.9115805625915527,
660
+ "learning_rate": 8.972888398568772e-05,
661
+ "loss": 1.8644,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.018329431688001194,
666
+ "grad_norm": 1.0219849348068237,
667
+ "learning_rate": 8.948305185085225e-05,
668
+ "loss": 2.2721,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.018528664641131645,
673
+ "grad_norm": 0.9994537234306335,
674
+ "learning_rate": 8.92346577173636e-05,
675
+ "loss": 2.1956,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.01872789759426209,
680
+ "grad_norm": 0.881737470626831,
681
+ "learning_rate": 8.898371770316111e-05,
682
+ "loss": 1.9247,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.018927130547392538,
687
+ "grad_norm": 1.0032176971435547,
688
+ "learning_rate": 8.873024809138272e-05,
689
+ "loss": 2.1392,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.019126363500522988,
694
+ "grad_norm": 1.0586591958999634,
695
+ "learning_rate": 8.847426532930831e-05,
696
+ "loss": 2.0194,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.019325596453653435,
701
+ "grad_norm": 1.0651748180389404,
702
+ "learning_rate": 8.821578602729242e-05,
703
+ "loss": 2.0458,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.01952482940678388,
708
+ "grad_norm": 1.0627988576889038,
709
+ "learning_rate": 8.795482695768658e-05,
710
+ "loss": 1.9618,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.01972406235991433,
715
+ "grad_norm": 0.9913427233695984,
716
+ "learning_rate": 8.769140505375085e-05,
717
+ "loss": 1.8278,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.019923295313044778,
722
+ "grad_norm": 1.2119276523590088,
723
+ "learning_rate": 8.742553740855506e-05,
724
+ "loss": 2.1889,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.019923295313044778,
729
+ "eval_loss": 1.8152918815612793,
730
+ "eval_runtime": 607.3335,
731
+ "eval_samples_per_second": 13.92,
732
+ "eval_steps_per_second": 3.481,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.42188868534272e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null