prxy5605 commited on
Commit
af2482e
·
verified ·
1 Parent(s): 757e8c1

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:a5fff018d608856dcfcae33ced8e89dae34929c01117c095f9fea358961bc527
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ec199b5c98b48873360b6790b211a33ae3e9fd392389a01b4e6a8bc761109f
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b93f794b3de2cba0f30276b86552f3583035675cde2adb6b39b2501634372e8
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc87b9121428faa450989724a959f52cf5e8dcd5ea46ff647e000bd90e6ac8b
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6d506c968b02b970d15f48bbb1c7e576d4778e8d3f04a673e834d8487b71419
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad7b75e73364c3cd9101bf05d417fd520f6d5501bee44305c4ca9026cb0e7817
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5335737b4b4d079cdec612fe6ee661ed4d29f9e0e55eb4eada44a9677240228
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.4193588197231293,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.031560675398453523,
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": 11.097,
374
  "eval_steps_per_second": 5.548,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.942038949881446e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.40419265627861023,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06312135079690705,
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": 11.097,
374
  "eval_steps_per_second": 5.548,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0321918889064226,
379
+ "grad_norm": 1.4785792827606201,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 0.9662,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03282310241439167,
386
+ "grad_norm": 1.5581904649734497,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 1.4336,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.03345431592236074,
393
+ "grad_norm": 1.3941839933395386,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 1.2795,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03408552943032981,
400
+ "grad_norm": 1.5098243951797485,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 1.5065,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03471674293829888,
407
+ "grad_norm": 1.6207574605941772,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 1.5554,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.03534795644626795,
414
+ "grad_norm": 1.558283805847168,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 1.6396,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03597916995423702,
421
+ "grad_norm": 1.633166790008545,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 1.4533,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.03661038346220609,
428
+ "grad_norm": 1.6480422019958496,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 1.6044,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.037241596970175164,
435
+ "grad_norm": 1.5684033632278442,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 1.6098,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03787281047814423,
442
+ "grad_norm": 1.6380794048309326,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 1.7237,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0385040239861133,
449
+ "grad_norm": 1.626305103302002,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 1.6403,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.039135237494082376,
456
+ "grad_norm": 1.6016772985458374,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 1.6659,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.039766451002051444,
463
+ "grad_norm": 1.6089552640914917,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 1.5893,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.04039766451002051,
470
+ "grad_norm": 1.551110029220581,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 1.5991,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.04102887801798959,
477
+ "grad_norm": 1.6614254713058472,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 1.6066,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.041660091525958655,
484
+ "grad_norm": 1.6592720746994019,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 1.78,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.04229130503392772,
491
+ "grad_norm": 1.694076418876648,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 1.7028,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0429225185418968,
498
+ "grad_norm": 1.687516689300537,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 1.6425,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.043553732049865866,
505
+ "grad_norm": 1.8176817893981934,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 1.7688,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.044184945557834934,
512
+ "grad_norm": 1.764524221420288,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 1.7655,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04481615906580401,
519
+ "grad_norm": 1.7133554220199585,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 1.7212,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04544737257377308,
526
+ "grad_norm": 1.6277440786361694,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 1.5719,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.04607858608174215,
533
+ "grad_norm": 1.6812453269958496,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 1.8084,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04670979958971122,
540
+ "grad_norm": 1.72732412815094,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 1.7182,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04734101309768029,
547
+ "grad_norm": 1.7740263938903809,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 1.7463,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.047972226605649364,
554
+ "grad_norm": 1.6268154382705688,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 1.511,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.04860344011361843,
561
+ "grad_norm": 1.5691125392913818,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 1.7255,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0492346536215875,
568
+ "grad_norm": 1.7060211896896362,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 1.7701,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.049865867129556575,
575
+ "grad_norm": 1.7170287370681763,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 1.8898,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05049708063752564,
582
+ "grad_norm": 1.6707334518432617,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 1.6891,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05112829414549471,
589
+ "grad_norm": 1.708794116973877,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 1.5987,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.051759507653463786,
596
+ "grad_norm": 1.7319235801696777,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 1.5944,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.052390721161432854,
603
+ "grad_norm": 1.7364600896835327,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 1.686,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.05302193466940192,
610
+ "grad_norm": 1.8175327777862549,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 1.6516,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.053653148177371,
617
+ "grad_norm": 1.837198257446289,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 1.6562,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.054284361685340066,
624
+ "grad_norm": 1.8270783424377441,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 1.8419,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.054915575193309134,
631
+ "grad_norm": 1.8131033182144165,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 1.5259,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.05554678870127821,
638
+ "grad_norm": 1.8537405729293823,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 1.8515,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.05617800220924728,
645
+ "grad_norm": 1.7982525825500488,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 1.7434,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.056809215717216345,
652
+ "grad_norm": 1.9493149518966675,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 1.7293,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.05744042922518542,
659
+ "grad_norm": 1.804345726966858,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 1.5746,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.05807164273315449,
666
+ "grad_norm": 1.8308101892471313,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 1.4938,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.05870285624112356,
673
+ "grad_norm": 1.9381098747253418,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 1.662,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.05933406974909263,
680
+ "grad_norm": 1.9891799688339233,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 1.5954,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0599652832570617,
687
+ "grad_norm": 1.9715620279312134,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 1.3628,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.060596496765030775,
694
+ "grad_norm": 2.135878562927246,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 1.658,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.06122771027299984,
701
+ "grad_norm": 1.9819763898849487,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 1.4918,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.06185892378096891,
708
+ "grad_norm": 2.1434459686279297,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 1.614,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.062490137288937986,
715
+ "grad_norm": 2.191251516342163,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 1.4206,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06312135079690705,
722
+ "grad_norm": 2.3877665996551514,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 1.2033,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06312135079690705,
729
+ "eval_loss": 0.40419265627861023,
730
+ "eval_runtime": 240.7348,
731
+ "eval_samples_per_second": 11.083,
732
+ "eval_steps_per_second": 5.541,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5919852849987584e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null