nttx commited on
Commit
6a969f9
·
verified ·
1 Parent(s): a485197

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:e8ce77a9b98108411242edcbee89dfeb01b7a17340f33d35d9a5bc5dec9eb4d8
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c8d17f163130c52ec5d5488dbd3d24b50f512fa4517ab7eb24e3cb5f74a556c
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca191d92498a6ca3d310eb94d81a258f3e0dca1e37d0175d489146b227bbf5a0
3
  size 46346
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592a29b7e69a2afe4f592e7a044f01ce3f84273a52c2dca828a6796ec1f077f0
3
  size 46346
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43b24777cd92f98dea51da13762fbd49091865241148ed41824a6e24f0fcb18b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f1c80b0aab9b05abc5abd62c141ed5d5b8afb25a6bee8be17337c37469d7df
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 11.930991172790527,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0023053160588316656,
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": 47.837,
374
  "eval_steps_per_second": 5.982,
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": 12052463616.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.93097972869873,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.004610632117663331,
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": 47.837,
374
  "eval_steps_per_second": 5.982,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0023514223800082993,
379
+ "grad_norm": 0.010148766450583935,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 11.9311,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0023975287011849325,
386
+ "grad_norm": 0.011732972227036953,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 11.93,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0024436350223615657,
393
+ "grad_norm": 0.008542712777853012,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 11.9327,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.002489741343538199,
400
+ "grad_norm": 0.009703322313725948,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 11.9283,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0025358476647148326,
407
+ "grad_norm": 0.013916654512286186,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 11.9337,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.002581953985891466,
414
+ "grad_norm": 0.012623277492821217,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 11.9281,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.002628060307068099,
421
+ "grad_norm": 0.013886111788451672,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 11.9325,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0026741666282447322,
428
+ "grad_norm": 0.010405468754470348,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 11.9322,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.002720272949421366,
435
+ "grad_norm": 0.010533565655350685,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 11.9338,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.002766379270597999,
442
+ "grad_norm": 0.015023970045149326,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 11.9285,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0028124855917746323,
449
+ "grad_norm": 0.01545638870447874,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 11.93,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0028585919129512655,
456
+ "grad_norm": 0.015377589501440525,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 11.9311,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0029046982341278988,
463
+ "grad_norm": 0.01387741044163704,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 11.9288,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0029508045553045324,
470
+ "grad_norm": 0.014318383298814297,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 11.9313,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0029969108764811656,
477
+ "grad_norm": 0.019190404564142227,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 11.9256,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.003043017197657799,
484
+ "grad_norm": 0.01856730319559574,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 11.9317,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.003089123518834432,
491
+ "grad_norm": 0.01225450448691845,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 11.9345,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0031352298400110657,
498
+ "grad_norm": 0.01742597296833992,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 11.9302,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.003181336161187699,
505
+ "grad_norm": 0.01626632548868656,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 11.9344,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.003227442482364332,
512
+ "grad_norm": 0.01698143593966961,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 11.9246,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.0032735488035409654,
519
+ "grad_norm": 0.013797706924378872,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 11.9347,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.0033196551247175986,
526
+ "grad_norm": 0.015473989769816399,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 11.9309,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0033657614458942322,
533
+ "grad_norm": 0.017822301015257835,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 11.9317,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.0034118677670708654,
540
+ "grad_norm": 0.017122985795140266,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 11.9321,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0034579740882474987,
547
+ "grad_norm": 0.02036653459072113,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 11.9375,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.003504080409424132,
554
+ "grad_norm": 0.017380934208631516,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 11.939,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0035501867306007655,
561
+ "grad_norm": 0.0208874624222517,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 11.926,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0035962930517773987,
568
+ "grad_norm": 0.02793768234550953,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 11.9347,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.003642399372954032,
575
+ "grad_norm": 0.017211785539984703,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 11.9357,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.003688505694130665,
582
+ "grad_norm": 0.022742517292499542,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 11.9328,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.003734612015307299,
589
+ "grad_norm": 0.02240605652332306,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 11.9287,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.003780718336483932,
596
+ "grad_norm": 0.01831667870283127,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 11.936,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0038268246576605653,
603
+ "grad_norm": 0.021101830527186394,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 11.9253,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0038729309788371985,
610
+ "grad_norm": 0.02482517622411251,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 11.9261,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.003919037300013832,
617
+ "grad_norm": 0.02878445014357567,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 11.9309,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.003965143621190465,
624
+ "grad_norm": 0.034189388155937195,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 11.9306,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.004011249942367098,
631
+ "grad_norm": 0.02674616314470768,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 11.9353,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.004057356263543732,
638
+ "grad_norm": 0.02872542478144169,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 11.9199,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0041034625847203654,
645
+ "grad_norm": 0.03754565492272377,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 11.9285,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.004149568905896998,
652
+ "grad_norm": 0.043331414461135864,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 11.9281,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.004195675227073632,
659
+ "grad_norm": 0.033205412328243256,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 11.93,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0042417815482502655,
666
+ "grad_norm": 0.03685666620731354,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 11.9276,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.004287887869426898,
673
+ "grad_norm": 0.04748856648802757,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 11.935,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.004333994190603532,
680
+ "grad_norm": 0.03603879362344742,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 11.9439,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.004380100511780165,
687
+ "grad_norm": 0.042884595692157745,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 11.9186,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.004426206832956798,
694
+ "grad_norm": 0.05015327408909798,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 11.933,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.004472313154133432,
701
+ "grad_norm": 0.04760831966996193,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 11.9286,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.004518419475310065,
708
+ "grad_norm": 0.06750523298978806,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 11.9305,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0045645257964866985,
715
+ "grad_norm": 0.07084526866674423,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 11.912,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.004610632117663331,
722
+ "grad_norm": 0.10393932461738586,
723
+ "learning_rate": 0.0,
724
+ "loss": 11.9212,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.004610632117663331,
729
+ "eval_loss": 11.93097972869873,
730
+ "eval_runtime": 190.9735,
731
+ "eval_samples_per_second": 47.818,
732
+ "eval_steps_per_second": 5.98,
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": 23868604416.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null