lesso commited on
Commit
a66f01c
·
verified ·
1 Parent(s): f9d1579

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 sha256:85d39358d34033562f001cd4970f06a678cd8c57164fc59ef506d431c2bb9417
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66bfa8ce3bee9a8c57dc049b1e01d18bfadaa583d19c879576c378a54efb11c5
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aff62f3771632ea627d02cbed2e9b0f73ebf0b53feafce8e3e36799eb97719ed
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9f91102a5841c0698324a23ff25752c26935d0aebe16912525cd78fc6e006a6
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09d699b7743f2fb4e87459a00c2a66302d0df8968856f27872b1a9a685e5e36
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbad62572bb8b62aab046919f8707183cb5ad16e2693807a09b0d274e992dbb7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6da931a425e1a2517e12e4e92e5527637ffeeadbe51a85a949dc53b89acf0af
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ba1abeedc944b50dfc9c3bffbf774b90111e900acad34ff55445cc0c42e5cd9
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4861719608306885,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0008418783990840363,
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": 23.226,
374
  "eval_steps_per_second": 5.807,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3435827224903680.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4122529029846191,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0016837567981680727,
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": 23.226,
374
  "eval_steps_per_second": 5.807,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.000858715967065717,
379
+ "grad_norm": 4.5934367179870605,
380
+ "learning_rate": 7.85778947368421e-05,
381
+ "loss": 1.5141,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0008755535350473977,
386
+ "grad_norm": 2.2590882778167725,
387
+ "learning_rate": 7.805052631578947e-05,
388
+ "loss": 1.0027,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0008923911030290785,
393
+ "grad_norm": 2.4307925701141357,
394
+ "learning_rate": 7.752315789473683e-05,
395
+ "loss": 1.0923,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0009092286710107592,
400
+ "grad_norm": 4.569330215454102,
401
+ "learning_rate": 7.69957894736842e-05,
402
+ "loss": 1.2634,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0009260662389924399,
407
+ "grad_norm": 2.3689849376678467,
408
+ "learning_rate": 7.646842105263158e-05,
409
+ "loss": 1.1724,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0009429038069741207,
414
+ "grad_norm": 2.9993743896484375,
415
+ "learning_rate": 7.594105263157894e-05,
416
+ "loss": 1.4869,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0009597413749558014,
421
+ "grad_norm": 2.52467942237854,
422
+ "learning_rate": 7.541368421052631e-05,
423
+ "loss": 1.7681,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.000976578942937482,
428
+ "grad_norm": 2.1674141883850098,
429
+ "learning_rate": 7.488631578947369e-05,
430
+ "loss": 1.265,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0009934165109191629,
435
+ "grad_norm": 2.996170997619629,
436
+ "learning_rate": 7.435894736842105e-05,
437
+ "loss": 1.3146,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0010102540789008435,
442
+ "grad_norm": 2.4902849197387695,
443
+ "learning_rate": 7.383157894736842e-05,
444
+ "loss": 1.3909,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0010270916468825243,
449
+ "grad_norm": 2.4440338611602783,
450
+ "learning_rate": 7.33042105263158e-05,
451
+ "loss": 1.0591,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.001043929214864205,
456
+ "grad_norm": 2.58357834815979,
457
+ "learning_rate": 7.277684210526316e-05,
458
+ "loss": 1.7086,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0010607667828458857,
463
+ "grad_norm": 2.20978045463562,
464
+ "learning_rate": 7.224947368421053e-05,
465
+ "loss": 1.2718,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0010776043508275665,
470
+ "grad_norm": 2.3872764110565186,
471
+ "learning_rate": 7.172210526315789e-05,
472
+ "loss": 1.3063,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0010944419188092473,
477
+ "grad_norm": 2.3353686332702637,
478
+ "learning_rate": 7.119473684210526e-05,
479
+ "loss": 1.394,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0011112794867909278,
484
+ "grad_norm": 4.137941837310791,
485
+ "learning_rate": 7.066736842105262e-05,
486
+ "loss": 1.6868,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0011281170547726086,
491
+ "grad_norm": 2.9827768802642822,
492
+ "learning_rate": 7.013999999999999e-05,
493
+ "loss": 1.7168,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0011449546227542894,
498
+ "grad_norm": 2.142432928085327,
499
+ "learning_rate": 6.961263157894737e-05,
500
+ "loss": 1.3172,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.00116179219073597,
505
+ "grad_norm": 2.022672414779663,
506
+ "learning_rate": 6.908526315789473e-05,
507
+ "loss": 1.2852,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0011786297587176508,
512
+ "grad_norm": 2.539156198501587,
513
+ "learning_rate": 6.85578947368421e-05,
514
+ "loss": 1.5417,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.0011954673266993316,
519
+ "grad_norm": 2.637662887573242,
520
+ "learning_rate": 6.803052631578946e-05,
521
+ "loss": 1.4392,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.0012123048946810122,
526
+ "grad_norm": 2.2341175079345703,
527
+ "learning_rate": 6.750315789473684e-05,
528
+ "loss": 1.4049,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.001229142462662693,
533
+ "grad_norm": 2.2582802772521973,
534
+ "learning_rate": 6.697578947368421e-05,
535
+ "loss": 1.3465,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.0012459800306443738,
540
+ "grad_norm": 2.781930923461914,
541
+ "learning_rate": 6.644842105263157e-05,
542
+ "loss": 1.4692,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0012628175986260544,
547
+ "grad_norm": 2.596421957015991,
548
+ "learning_rate": 6.592105263157895e-05,
549
+ "loss": 1.7602,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0012796551666077352,
554
+ "grad_norm": 2.116238594055176,
555
+ "learning_rate": 6.539368421052632e-05,
556
+ "loss": 1.2029,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.001296492734589416,
561
+ "grad_norm": 3.9173460006713867,
562
+ "learning_rate": 6.486631578947368e-05,
563
+ "loss": 1.6201,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0013133303025710966,
568
+ "grad_norm": 2.327167272567749,
569
+ "learning_rate": 6.433894736842105e-05,
570
+ "loss": 1.4733,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0013301678705527774,
575
+ "grad_norm": 2.6510813236236572,
576
+ "learning_rate": 6.381157894736842e-05,
577
+ "loss": 1.4754,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0013470054385344582,
582
+ "grad_norm": 3.711254119873047,
583
+ "learning_rate": 6.328421052631578e-05,
584
+ "loss": 2.1011,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.0013638430065161388,
589
+ "grad_norm": 2.670668840408325,
590
+ "learning_rate": 6.275684210526315e-05,
591
+ "loss": 1.0381,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0013806805744978196,
596
+ "grad_norm": 2.776033401489258,
597
+ "learning_rate": 6.222947368421053e-05,
598
+ "loss": 1.496,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0013975181424795004,
603
+ "grad_norm": 3.6561427116394043,
604
+ "learning_rate": 6.170210526315789e-05,
605
+ "loss": 1.6738,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.001414355710461181,
610
+ "grad_norm": 2.9641172885894775,
611
+ "learning_rate": 6.117473684210526e-05,
612
+ "loss": 0.9949,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.0014311932784428617,
617
+ "grad_norm": 2.4028921127319336,
618
+ "learning_rate": 6.064736842105263e-05,
619
+ "loss": 1.1722,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0014480308464245425,
624
+ "grad_norm": 3.3796043395996094,
625
+ "learning_rate": 6.0119999999999994e-05,
626
+ "loss": 1.5237,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.0014648684144062231,
631
+ "grad_norm": 3.0940074920654297,
632
+ "learning_rate": 5.959263157894736e-05,
633
+ "loss": 1.5104,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.001481705982387904,
638
+ "grad_norm": 3.486140251159668,
639
+ "learning_rate": 5.906526315789473e-05,
640
+ "loss": 1.2832,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0014985435503695845,
645
+ "grad_norm": 3.9877243041992188,
646
+ "learning_rate": 5.853789473684211e-05,
647
+ "loss": 1.4576,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0015153811183512653,
652
+ "grad_norm": 2.9244778156280518,
653
+ "learning_rate": 5.8010526315789476e-05,
654
+ "loss": 1.6941,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.0015322186863329461,
659
+ "grad_norm": 4.34598970413208,
660
+ "learning_rate": 5.748315789473684e-05,
661
+ "loss": 2.0928,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0015490562543146267,
666
+ "grad_norm": 3.355473756790161,
667
+ "learning_rate": 5.6955789473684207e-05,
668
+ "loss": 1.3159,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0015658938222963075,
673
+ "grad_norm": 3.85603928565979,
674
+ "learning_rate": 5.642842105263157e-05,
675
+ "loss": 1.846,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0015827313902779883,
680
+ "grad_norm": 3.5386862754821777,
681
+ "learning_rate": 5.5901052631578944e-05,
682
+ "loss": 1.5301,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0015995689582596689,
687
+ "grad_norm": 4.031479835510254,
688
+ "learning_rate": 5.5373684210526316e-05,
689
+ "loss": 2.0078,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.0016164065262413497,
694
+ "grad_norm": 3.196629524230957,
695
+ "learning_rate": 5.484631578947369e-05,
696
+ "loss": 1.7842,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0016332440942230305,
701
+ "grad_norm": 2.8968214988708496,
702
+ "learning_rate": 5.4318947368421054e-05,
703
+ "loss": 1.1119,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.001650081662204711,
708
+ "grad_norm": 4.223515510559082,
709
+ "learning_rate": 5.379157894736842e-05,
710
+ "loss": 1.8077,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0016669192301863919,
715
+ "grad_norm": 3.419590711593628,
716
+ "learning_rate": 5.3264210526315785e-05,
717
+ "loss": 1.158,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0016837567981680727,
722
+ "grad_norm": 5.4764628410339355,
723
+ "learning_rate": 5.273684210526315e-05,
724
+ "loss": 1.3783,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0016837567981680727,
729
+ "eval_loss": 1.4122529029846191,
730
+ "eval_runtime": 1076.0209,
731
+ "eval_samples_per_second": 23.24,
732
+ "eval_steps_per_second": 5.81,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6871654449807360.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null