Nexspear commited on
Commit
a939c2d
·
verified ·
1 Parent(s): 02ead3e

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 sha256:26e8628a8d7bea74ee851ff66b97cb50b9897f2507a54775053e8e5e3b0c8425
3
  size 147770496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bc786fd137e09b42f1ccfff32915b3bb732495edc3bacbaeda33207762528c7
3
  size 147770496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32881490352b36bdc3f694c997afe2d8466743bcd9aff85fdb4556d2981c7ae7
3
  size 75471860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c899ec00fa2783dcf6cbb846a5ccfa74c560c421e734ad7e72314d67c8815d
3
  size 75471860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8172f37e559a8de245dc068991bed2f9eed8dd993dcff974d4b7d2f03fbe5b72
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e951fbacd8bcfef4738cd1ec0e619c6182c9946d6b1b168b9c160d68fc01ff
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.702011823654175,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.00898593700858157,
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": 25.39,
374
  "eval_steps_per_second": 6.347,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.7945896993947648e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.543463706970215,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.01797187401716314,
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": 25.39,
374
  "eval_steps_per_second": 6.347,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.009165655748753202,
379
+ "grad_norm": 4.447997570037842,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 3.1439,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.009345374488924833,
386
+ "grad_norm": 4.879358291625977,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 3.0015,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.009525093229096464,
393
+ "grad_norm": 3.736008882522583,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 2.9797,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.009704811969268095,
400
+ "grad_norm": 3.3615059852600098,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 3.3752,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.009884530709439726,
407
+ "grad_norm": 2.5511536598205566,
408
+ "learning_rate": 5e-05,
409
+ "loss": 2.8825,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.010064249449611358,
414
+ "grad_norm": 2.8620405197143555,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 2.9289,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.010243968189782989,
421
+ "grad_norm": 2.905618190765381,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 3.1637,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.010423686929954622,
428
+ "grad_norm": 3.0646848678588867,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 3.0125,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.010603405670126253,
435
+ "grad_norm": 3.3001129627227783,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 3.1014,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.010783124410297884,
442
+ "grad_norm": 3.306954860687256,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 3.4818,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.010962843150469515,
449
+ "grad_norm": 3.376537561416626,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 3.5095,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.011142561890641146,
456
+ "grad_norm": 3.216480016708374,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 3.4539,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.011322280630812778,
463
+ "grad_norm": 3.4549150466918945,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 3.3442,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.011501999370984409,
470
+ "grad_norm": 3.040135145187378,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 3.3466,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.011681718111156042,
477
+ "grad_norm": 3.064269542694092,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 3.2623,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.011861436851327673,
484
+ "grad_norm": 3.851158618927002,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 3.8449,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.012041155591499304,
491
+ "grad_norm": 3.46075177192688,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 3.4347,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.012220874331670935,
498
+ "grad_norm": 3.6675915718078613,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 4.0072,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.012400593071842566,
505
+ "grad_norm": 3.480902671813965,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 2.4953,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.012580311812014197,
512
+ "grad_norm": 4.579424858093262,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 2.6752,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.012760030552185829,
519
+ "grad_norm": 3.595804214477539,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 2.4067,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.01293974929235746,
526
+ "grad_norm": 3.2332661151885986,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 2.1416,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.013119468032529093,
533
+ "grad_norm": 3.2234134674072266,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 2.7848,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.013299186772700724,
540
+ "grad_norm": 3.04959774017334,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 2.432,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.013478905512872355,
547
+ "grad_norm": 2.643514633178711,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 2.0934,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.013658624253043986,
554
+ "grad_norm": 3.055098056793213,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 2.3272,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.013838342993215617,
561
+ "grad_norm": 2.4809956550598145,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 2.2483,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.014018061733387249,
568
+ "grad_norm": 2.64147686958313,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 2.3055,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.01419778047355888,
575
+ "grad_norm": 2.2932167053222656,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 2.0433,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.014377499213730511,
582
+ "grad_norm": 2.3609931468963623,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 2.3359,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.014557217953902144,
589
+ "grad_norm": 2.249638080596924,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 2.1387,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.014736936694073775,
596
+ "grad_norm": 2.8411879539489746,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 2.463,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.014916655434245406,
603
+ "grad_norm": 2.662808418273926,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 2.5389,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.015096374174417037,
610
+ "grad_norm": 2.8071436882019043,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 2.1706,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.015276092914588668,
617
+ "grad_norm": 2.656956911087036,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 2.3759,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0154558116547603,
624
+ "grad_norm": 3.031149387359619,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 2.2298,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.015635530394931933,
631
+ "grad_norm": 2.755890369415283,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 2.4255,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.015815249135103564,
638
+ "grad_norm": 2.5731019973754883,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 2.2818,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.015994967875275195,
645
+ "grad_norm": 2.7685189247131348,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 2.3691,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.016174686615446826,
652
+ "grad_norm": 2.6368041038513184,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 2.4944,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.016354405355618457,
659
+ "grad_norm": 2.858224630355835,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 2.2883,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.01653412409579009,
666
+ "grad_norm": 2.793339252471924,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 2.4953,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.01671384283596172,
673
+ "grad_norm": 2.8187801837921143,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 2.2414,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.01689356157613335,
680
+ "grad_norm": 2.9361603260040283,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 2.4021,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.017073280316304982,
687
+ "grad_norm": 2.7744662761688232,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 2.1991,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.017252999056476613,
694
+ "grad_norm": 2.6500556468963623,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 2.2625,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.017432717796648244,
701
+ "grad_norm": 2.4501571655273438,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 2.1335,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.017612436536819875,
708
+ "grad_norm": 2.76723575592041,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 2.0047,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.017792155276991507,
715
+ "grad_norm": 2.838305711746216,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 2.3863,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.01797187401716314,
722
+ "grad_norm": 3.0587007999420166,
723
+ "learning_rate": 0.0,
724
+ "loss": 2.2002,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.01797187401716314,
729
+ "eval_loss": 2.543463706970215,
730
+ "eval_runtime": 368.7,
731
+ "eval_samples_per_second": 25.419,
732
+ "eval_steps_per_second": 6.355,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.609045705424896e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null