nttx commited on
Commit
dae9dfc
·
verified ·
1 Parent(s): cc3db59

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:cf1e8b7eb8b1242a37bd640155dbf3cfb10360b7ae45c350918146b99fb31df3
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7e2ee3246cb67502507b8554e933704583d8a9f573d0be11398fd4b3eaa4372
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:288d71c49bf2c5f1b499981a91d9302a2f6b4d5da39d6bf7d4382052b1d90a5f
3
  size 130762746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1838f0e085e931d288f28bb5412ff6db3cc5add46580d8f87cdcfd8e4d7242d
3
  size 130762746
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b9df5f207efd9a770d6dae3c348692fb7790a350910d88568a4e140dcad775c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2c751fd059375b38fa8325fd007d0d9297fc0920f7525fe56c91d048914175
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": 1.6653131246566772,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.01804402742692169,
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": 14.386,
374
  "eval_steps_per_second": 7.199,
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": 1.63247803072512e+16,
405
  "train_batch_size": 2,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1221874952316284,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.03608805485384338,
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": 14.386,
374
  "eval_steps_per_second": 7.199,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.018404907975460124,
379
+ "grad_norm": 33.91326141357422,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 8.6254,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.018765788523998555,
386
+ "grad_norm": 32.49760437011719,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 8.327,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.01912666907253699,
393
+ "grad_norm": 28.867843627929688,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 7.541,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.019487549621075424,
400
+ "grad_norm": 20.9218692779541,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 7.1236,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.019848430169613858,
407
+ "grad_norm": 15.627690315246582,
408
+ "learning_rate": 5e-05,
409
+ "loss": 6.3454,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.020209310718152292,
414
+ "grad_norm": 10.86724853515625,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 6.0616,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.020570191266690727,
421
+ "grad_norm": 8.642108917236328,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 5.842,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.020931071815229157,
428
+ "grad_norm": 6.51857328414917,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 6.1749,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.021291952363767592,
435
+ "grad_norm": 5.3840837478637695,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 5.3718,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.021652832912306026,
442
+ "grad_norm": 4.127508640289307,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 5.1566,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.02201371346084446,
449
+ "grad_norm": 4.8461689949035645,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 5.8174,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.022374594009382895,
456
+ "grad_norm": 3.6144542694091797,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 5.1848,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.02273547455792133,
463
+ "grad_norm": 3.756178855895996,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 5.1231,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.02309635510645976,
470
+ "grad_norm": 3.632399320602417,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 5.8659,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.023457235654998194,
477
+ "grad_norm": 3.7913990020751953,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 5.1113,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.02381811620353663,
484
+ "grad_norm": 3.783937692642212,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 4.8848,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.024178996752075063,
491
+ "grad_norm": 3.555427074432373,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 5.0399,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.024539877300613498,
498
+ "grad_norm": 4.134983062744141,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 4.9774,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.024900757849151932,
505
+ "grad_norm": 3.7418508529663086,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 4.8787,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.025261638397690366,
512
+ "grad_norm": 4.393967628479004,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 5.3012,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.025622518946228797,
519
+ "grad_norm": 3.980875015258789,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 4.769,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.02598339949476723,
526
+ "grad_norm": 4.168369293212891,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 4.659,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.026344280043305666,
533
+ "grad_norm": 4.086007118225098,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 4.5202,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.0267051605918441,
540
+ "grad_norm": 4.269333839416504,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 5.4667,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.027066041140382534,
547
+ "grad_norm": 4.5333967208862305,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 5.6192,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.02742692168892097,
554
+ "grad_norm": 4.340392112731934,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 5.003,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0277878022374594,
561
+ "grad_norm": 4.1651716232299805,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 4.6308,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.028148682785997834,
568
+ "grad_norm": 4.309195041656494,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 4.806,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.02850956333453627,
575
+ "grad_norm": 4.466158866882324,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 4.8006,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.028870443883074703,
582
+ "grad_norm": 4.160628795623779,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 4.6954,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.029231324431613137,
589
+ "grad_norm": 4.586925506591797,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 4.6823,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.02959220498015157,
596
+ "grad_norm": 4.5009541511535645,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 4.3726,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.029953085528690002,
603
+ "grad_norm": 4.383872032165527,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 4.3119,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.030313966077228437,
610
+ "grad_norm": 6.453273296356201,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 5.5564,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.03067484662576687,
617
+ "grad_norm": 4.931399345397949,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 4.5286,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.031035727174305305,
624
+ "grad_norm": 4.450496196746826,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 4.2613,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.031396607722843736,
631
+ "grad_norm": 4.452889919281006,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 4.1908,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.031757488271382174,
638
+ "grad_norm": 4.126706600189209,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 4.2074,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.032118368819920605,
645
+ "grad_norm": 5.554738521575928,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 4.2712,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.03247924936845904,
652
+ "grad_norm": 4.914494514465332,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 3.96,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.032840129916997474,
659
+ "grad_norm": 6.710911750793457,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 4.0386,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.033201010465535905,
666
+ "grad_norm": 7.206127166748047,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 4.2879,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03356189101407434,
673
+ "grad_norm": 6.181286811828613,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 4.0742,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.03392277156261277,
680
+ "grad_norm": 5.3509955406188965,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 3.8129,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03428365211115121,
687
+ "grad_norm": 7.3788323402404785,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 4.8281,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03464453265968964,
694
+ "grad_norm": 7.814950466156006,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 3.8794,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03500541320822808,
701
+ "grad_norm": 7.361276626586914,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 3.4146,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.03536629375676651,
708
+ "grad_norm": 7.151997089385986,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 3.7909,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03572717430530494,
715
+ "grad_norm": 7.618679046630859,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 3.623,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.03608805485384338,
722
+ "grad_norm": 12.368490219116211,
723
+ "learning_rate": 0.0,
724
+ "loss": 3.9289,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.03608805485384338,
729
+ "eval_loss": 1.1221874952316284,
730
+ "eval_runtime": 81.1645,
731
+ "eval_samples_per_second": 14.378,
732
+ "eval_steps_per_second": 7.195,
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": 3.26495606145024e+16,
763
  "train_batch_size": 2,
764
  "trial_name": null,
765
  "trial_params": null