Nexspear commited on
Commit
d5ebc4e
·
verified ·
1 Parent(s): c5d2868

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:b154b059aa167b1d2a4bc7426f5d1c59d252f431c733125a333e1cef25a900c0
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecd0f190bf1e129f6bd3e655ab0f08c9d2799bee14d0ba46177a16d46bf8331b
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26e7613b809c005346d35cebe07980372f4f9b8429e7d7264b6b822eb883dc26
3
  size 170920084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97bca161f97f5b705dcd774aa5ad533bbcdaffcd9cddd150010c24234199dcfa
3
  size 170920084
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbeef78af7d84bbda3d9792326231e5653251bd0a6da6950a9367d6d20561c15
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02fa73ab0e973006460ca968c7910f4af46e26a0b3fe8a72064f24b91ffe9daf
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": 1.934623122215271,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.022479487467685737,
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": 12.268,
374
  "eval_steps_per_second": 3.068,
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": 7.602970501840896e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.8117440938949585,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.044958974935371473,
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": 12.268,
374
  "eval_steps_per_second": 3.068,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.02292907721703945,
379
+ "grad_norm": 11.476149559020996,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 7.3362,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.023378666966393166,
386
+ "grad_norm": 11.603797912597656,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 7.442,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.02382825671574688,
393
+ "grad_norm": 10.300864219665527,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 7.4202,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.024277846465100596,
400
+ "grad_norm": 8.544779777526855,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 7.0981,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.02472743621445431,
407
+ "grad_norm": 5.459915637969971,
408
+ "learning_rate": 5e-05,
409
+ "loss": 7.3514,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.025177025963808025,
414
+ "grad_norm": 3.0955164432525635,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 7.0576,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.02562661571316174,
421
+ "grad_norm": 3.19674015045166,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 7.23,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.026076205462515455,
428
+ "grad_norm": 2.739734649658203,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 7.0943,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.02652579521186917,
435
+ "grad_norm": 3.8967645168304443,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 7.2636,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.026975384961222884,
442
+ "grad_norm": 3.043419361114502,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 7.3223,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0274249747105766,
449
+ "grad_norm": 3.0673446655273438,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 6.8189,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.027874564459930314,
456
+ "grad_norm": 3.27693510055542,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 7.0324,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.02832415420928403,
463
+ "grad_norm": 3.591726064682007,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 6.9133,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.028773743958637743,
470
+ "grad_norm": 3.230844020843506,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 6.9538,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.029223333707991458,
477
+ "grad_norm": 3.3317620754241943,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 6.9394,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.029672923457345173,
484
+ "grad_norm": 3.195903778076172,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 7.0984,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.030122513206698887,
491
+ "grad_norm": 3.351611614227295,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 7.2142,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.030572102956052602,
498
+ "grad_norm": 3.1880135536193848,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 6.8962,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.031021692705406317,
505
+ "grad_norm": 3.423830270767212,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 7.436,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.03147128245476003,
512
+ "grad_norm": 3.454775094985962,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 7.3572,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.03192087220411375,
519
+ "grad_norm": 3.665876865386963,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 6.9502,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.03237046195346746,
526
+ "grad_norm": 3.3924033641815186,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 7.1721,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.03282005170282118,
533
+ "grad_norm": 3.5606541633605957,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 7.368,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.03326964145217489,
540
+ "grad_norm": 3.614961624145508,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 7.1286,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.03371923120152861,
547
+ "grad_norm": 3.9002952575683594,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 7.6035,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.03416882095088232,
554
+ "grad_norm": 3.7654526233673096,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 6.9176,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.03461841070023604,
561
+ "grad_norm": 3.960015296936035,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 6.8281,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.03506800044958975,
568
+ "grad_norm": 4.176464080810547,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 6.9551,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.03551759019894347,
575
+ "grad_norm": 4.081431865692139,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 7.6075,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03596717994829718,
582
+ "grad_norm": 4.360508441925049,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 7.5639,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.0364167696976509,
589
+ "grad_norm": 4.41530179977417,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 7.417,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.03686635944700461,
596
+ "grad_norm": 4.396665096282959,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 7.2683,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.037315949196358326,
603
+ "grad_norm": 4.680903434753418,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 6.9854,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.03776553894571204,
610
+ "grad_norm": 4.679863452911377,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 7.6362,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.038215128695065756,
617
+ "grad_norm": 4.920777320861816,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 7.4629,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.03866471844441947,
624
+ "grad_norm": 5.3529181480407715,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 7.5006,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.039114308193773185,
631
+ "grad_norm": 5.565374374389648,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 7.5553,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.0395638979431269,
638
+ "grad_norm": 5.736807823181152,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 7.3617,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.040013487692480615,
645
+ "grad_norm": 5.8425703048706055,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 7.2157,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.040463077441834326,
652
+ "grad_norm": 6.148372650146484,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 7.2508,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.040912667191188044,
659
+ "grad_norm": 5.708883285522461,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 7.2955,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.041362256940541756,
666
+ "grad_norm": 6.778091907501221,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 7.0668,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.041811846689895474,
673
+ "grad_norm": 6.998269557952881,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 7.0621,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.042261436439249185,
680
+ "grad_norm": 7.591545581817627,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 7.6306,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0427110261886029,
687
+ "grad_norm": 8.322836875915527,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 6.8658,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.043160615937956615,
694
+ "grad_norm": 7.584608554840088,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 7.9249,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.04361020568731033,
701
+ "grad_norm": 8.986035346984863,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 8.2931,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.044059795436664044,
708
+ "grad_norm": 9.24368667602539,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 7.509,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.04450938518601776,
715
+ "grad_norm": 12.614158630371094,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 7.548,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.044958974935371473,
722
+ "grad_norm": 16.969078063964844,
723
+ "learning_rate": 0.0,
724
+ "loss": 8.8329,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.044958974935371473,
729
+ "eval_loss": 1.8117440938949585,
730
+ "eval_runtime": 305.934,
731
+ "eval_samples_per_second": 12.248,
732
+ "eval_steps_per_second": 3.063,
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": 1.5170578350184858e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null