nttx commited on
Commit
fa91e82
·
verified ·
1 Parent(s): 81e35ee

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 sha256:37db4b5c5859f8f3f1ee09458a3530068602cf34bca3274413ac2a1c3d86eb4c
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d86e193d1e30d861bdabe4afba56d402c0a2de3845ef2098a4c01abdc73a909
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4981f763ea989718f43b36782ff779355555ae547395f430a9a5a089d2fb0adb
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f632b512cc29b2053813c812de19182897a3e5bf64cc46fc11620f49209fea
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:314476803f1494174f81db3c10fd6eb76aa1dad6f3434f1f74552c5f4b48e698
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de0e06e42bcebf883316de8930d271e6249504b354a3aa92c301aa73061972e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d90116c540b4ff0066495fbccc9c914a568905fb44c6564f227952cc4231b00
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ad66011cfc1fc727a51190602a41adc332b48eeef62a5ee87c2ca9f9b90b2b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5323200225830078,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0013505118439888718,
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": 9.008,
374
  "eval_steps_per_second": 2.252,
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": 2.621042343070925e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4810292720794678,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0027010236879777437,
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": 9.008,
374
  "eval_steps_per_second": 2.252,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0013775220808686492,
379
+ "grad_norm": 2.0075578689575195,
380
+ "learning_rate": 2.3816778784387097e-05,
381
+ "loss": 1.6417,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0014045323177484267,
386
+ "grad_norm": 2.1036274433135986,
387
+ "learning_rate": 2.3263454721781537e-05,
388
+ "loss": 1.4913,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.001431542554628204,
393
+ "grad_norm": 2.0413341522216797,
394
+ "learning_rate": 2.2693489161088592e-05,
395
+ "loss": 1.6212,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0014585527915079814,
400
+ "grad_norm": 1.942448616027832,
401
+ "learning_rate": 2.210802993709498e-05,
402
+ "loss": 1.6439,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.001485563028387759,
407
+ "grad_norm": 2.1481826305389404,
408
+ "learning_rate": 2.1508256086763372e-05,
409
+ "loss": 1.7214,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0015125732652675364,
414
+ "grad_norm": 1.8801171779632568,
415
+ "learning_rate": 2.0895375474808857e-05,
416
+ "loss": 1.5555,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.001539583502147314,
421
+ "grad_norm": 2.44754958152771,
422
+ "learning_rate": 2.0270622361220143e-05,
423
+ "loss": 1.8116,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0015665937390270913,
428
+ "grad_norm": 2.611750364303589,
429
+ "learning_rate": 1.963525491562421e-05,
430
+ "loss": 2.0997,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0015936039759068686,
435
+ "grad_norm": 2.4594104290008545,
436
+ "learning_rate": 1.8990552683500128e-05,
437
+ "loss": 1.7715,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0016206142127866462,
442
+ "grad_norm": 2.877983808517456,
443
+ "learning_rate": 1.8337814009344716e-05,
444
+ "loss": 1.7933,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0016476244496664235,
449
+ "grad_norm": 2.124140739440918,
450
+ "learning_rate": 1.767835342197955e-05,
451
+ "loss": 1.4663,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0016746346865462011,
456
+ "grad_norm": 2.2420833110809326,
457
+ "learning_rate": 1.7013498987264832e-05,
458
+ "loss": 1.7904,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0017016449234259785,
463
+ "grad_norm": 2.717524290084839,
464
+ "learning_rate": 1.6344589633551502e-05,
465
+ "loss": 1.7165,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0017286551603057558,
470
+ "grad_norm": 2.5003247261047363,
471
+ "learning_rate": 1.5672972455257726e-05,
472
+ "loss": 1.7485,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0017556653971855334,
477
+ "grad_norm": 2.5034983158111572,
478
+ "learning_rate": 1.5e-05,
479
+ "loss": 1.5087,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0017826756340653107,
484
+ "grad_norm": 3.265855312347412,
485
+ "learning_rate": 1.4327027544742281e-05,
486
+ "loss": 1.8923,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.001809685870945088,
491
+ "grad_norm": 3.260542392730713,
492
+ "learning_rate": 1.36554103664485e-05,
493
+ "loss": 1.5948,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0018366961078248656,
498
+ "grad_norm": 3.1845810413360596,
499
+ "learning_rate": 1.2986501012735174e-05,
500
+ "loss": 1.7641,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.001863706344704643,
505
+ "grad_norm": 2.402411699295044,
506
+ "learning_rate": 1.2321646578020452e-05,
507
+ "loss": 1.485,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0018907165815844206,
512
+ "grad_norm": 3.055525541305542,
513
+ "learning_rate": 1.1662185990655285e-05,
514
+ "loss": 1.4272,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.001917726818464198,
519
+ "grad_norm": 2.2134780883789062,
520
+ "learning_rate": 1.1009447316499875e-05,
521
+ "loss": 1.2956,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.0019447370553439753,
526
+ "grad_norm": 2.314101219177246,
527
+ "learning_rate": 1.036474508437579e-05,
528
+ "loss": 1.4229,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.001971747292223753,
533
+ "grad_norm": 2.550278425216675,
534
+ "learning_rate": 9.729377638779859e-06,
535
+ "loss": 1.5253,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.0019987575291035304,
540
+ "grad_norm": 1.8057441711425781,
541
+ "learning_rate": 9.104624525191147e-06,
542
+ "loss": 1.1277,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0020257677659833075,
547
+ "grad_norm": 2.356515884399414,
548
+ "learning_rate": 8.491743913236629e-06,
549
+ "loss": 1.5744,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.002052778002863085,
554
+ "grad_norm": 1.8322139978408813,
555
+ "learning_rate": 7.89197006290502e-06,
556
+ "loss": 1.22,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0020797882397428627,
561
+ "grad_norm": 2.382089853286743,
562
+ "learning_rate": 7.30651083891141e-06,
563
+ "loss": 1.3513,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.00210679847662264,
568
+ "grad_norm": 2.511622667312622,
569
+ "learning_rate": 6.736545278218464e-06,
570
+ "loss": 1.4673,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0021338087135024174,
575
+ "grad_norm": 2.1049392223358154,
576
+ "learning_rate": 6.1832212156129045e-06,
577
+ "loss": 1.3462,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.002160818950382195,
582
+ "grad_norm": 1.8335689306259155,
583
+ "learning_rate": 5.647652972118998e-06,
584
+ "loss": 1.2784,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.0021878291872619725,
589
+ "grad_norm": 2.07208251953125,
590
+ "learning_rate": 5.130919110904311e-06,
591
+ "loss": 1.3297,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0022148394241417496,
596
+ "grad_norm": 2.2498092651367188,
597
+ "learning_rate": 4.6340602651970304e-06,
598
+ "loss": 1.385,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.002241849661021527,
603
+ "grad_norm": 2.364032030105591,
604
+ "learning_rate": 4.158077042589129e-06,
605
+ "loss": 1.2464,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0022688598979013048,
610
+ "grad_norm": 1.9826806783676147,
611
+ "learning_rate": 3.7039280099458373e-06,
612
+ "loss": 1.5284,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.002295870134781082,
617
+ "grad_norm": 2.1717441082000732,
618
+ "learning_rate": 3.272527762979553e-06,
619
+ "loss": 1.4557,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0023228803716608595,
624
+ "grad_norm": 2.2217328548431396,
625
+ "learning_rate": 2.86474508437579e-06,
626
+ "loss": 1.4088,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.002349890608540637,
631
+ "grad_norm": 2.221723794937134,
632
+ "learning_rate": 2.4814011941804603e-06,
633
+ "loss": 1.3783,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.002376900845420414,
638
+ "grad_norm": 1.8951011896133423,
639
+ "learning_rate": 2.1232680959720085e-06,
640
+ "loss": 1.3405,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0024039110823001917,
645
+ "grad_norm": 2.2864327430725098,
646
+ "learning_rate": 1.79106702214893e-06,
647
+ "loss": 1.3055,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0024309213191799693,
652
+ "grad_norm": 2.2295827865600586,
653
+ "learning_rate": 1.4854669814637145e-06,
654
+ "loss": 1.4331,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.0024579315560597464,
659
+ "grad_norm": 2.1161422729492188,
660
+ "learning_rate": 1.2070834117282414e-06,
661
+ "loss": 1.6016,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.002484941792939524,
666
+ "grad_norm": 2.2798967361450195,
667
+ "learning_rate": 9.56476940403942e-07,
668
+ "loss": 1.34,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0025119520298193016,
673
+ "grad_norm": 1.9478846788406372,
674
+ "learning_rate": 7.341522555726971e-07,
675
+ "loss": 1.1043,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.002538962266699079,
680
+ "grad_norm": 2.527766227722168,
681
+ "learning_rate": 5.405570895622014e-07,
682
+ "loss": 1.507,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0025659725035788563,
687
+ "grad_norm": 2.620147228240967,
688
+ "learning_rate": 3.760813172726457e-07,
689
+ "loss": 1.5329,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.002592982740458634,
694
+ "grad_norm": 2.2767059803009033,
695
+ "learning_rate": 2.41056171020555e-07,
696
+ "loss": 1.438,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0026199929773384114,
701
+ "grad_norm": 1.911629319190979,
702
+ "learning_rate": 1.357535734809795e-07,
703
+ "loss": 1.0212,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0026470032142181885,
708
+ "grad_norm": 2.204927682876587,
709
+ "learning_rate": 6.038559007141397e-08,
710
+ "loss": 1.1526,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.002674013451097966,
715
+ "grad_norm": 2.275649309158325,
716
+ "learning_rate": 1.510400188028116e-08,
717
+ "loss": 1.3758,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0027010236879777437,
722
+ "grad_norm": 3.0716145038604736,
723
+ "learning_rate": 0.0,
724
+ "loss": 1.7359,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0027010236879777437,
729
+ "eval_loss": 1.4810292720794678,
730
+ "eval_runtime": 1731.0852,
731
+ "eval_samples_per_second": 9.005,
732
+ "eval_steps_per_second": 2.252,
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": 5.204371846673203e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null