bbytxt commited on
Commit
1884ca3
·
verified ·
1 Parent(s): 9eec24b

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:faba036e91248b2cce80b7ea70b8ec8ff876fd85373eed100e3d0d03d1824baa
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614964fabe82285d67a51a3d40e562e051392eccbb748842a3cbc17bf63569f7
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22aa3de46d21802c916055442529dac6a95f2c51fd429005d807d1bc774d0511
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c008826cde0d895c1c4107fd9f3e5767bb2bda3ae633c3b917ef18cb6f7b587
3
  size 27273018
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fbdfebe7d519c456ce3866535d28c2b7cb1a1804711d82e33d7a5856bcf7b47
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5523777bc41848d4797ac61c85e11d1b21d16faae2065e567f3f00076a1372d8
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": 1.4491695165634155,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0427715996578272,
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": 133.755,
374
  "eval_steps_per_second": 33.541,
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": 770548602765312.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.874006450176239,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0855431993156544,
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": 133.755,
374
  "eval_steps_per_second": 33.541,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.04362703165098375,
379
+ "grad_norm": 43.02643966674805,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 9.5889,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.04448246364414029,
386
+ "grad_norm": 44.06403350830078,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 9.5999,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.045337895637296836,
393
+ "grad_norm": 31.32398223876953,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 7.1508,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.046193327630453376,
400
+ "grad_norm": 17.837383270263672,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 2.9384,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.04704875962360992,
407
+ "grad_norm": 7.213578701019287,
408
+ "learning_rate": 5e-05,
409
+ "loss": 0.9618,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.04790419161676647,
414
+ "grad_norm": 5.207120418548584,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 0.7529,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.04875962360992301,
421
+ "grad_norm": 4.69100284576416,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 0.6933,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.04961505560307956,
428
+ "grad_norm": 2.485616683959961,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 0.4986,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0504704875962361,
435
+ "grad_norm": 1.7521893978118896,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 0.382,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.05132591958939264,
442
+ "grad_norm": 1.4033925533294678,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 0.343,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.05218135158254919,
449
+ "grad_norm": 1.392710566520691,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 0.3722,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.05303678357570573,
456
+ "grad_norm": 1.1755892038345337,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 0.3236,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.05389221556886228,
463
+ "grad_norm": 0.8601241707801819,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 0.2427,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.05474764756201882,
470
+ "grad_norm": 0.9155849814414978,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 0.3333,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.055603079555175364,
477
+ "grad_norm": 0.8021154403686523,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 0.2494,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.05645851154833191,
484
+ "grad_norm": 0.8067910075187683,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 0.2427,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.05731394354148845,
491
+ "grad_norm": 0.6124118566513062,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 0.2362,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.058169375534645,
498
+ "grad_norm": 0.7200761437416077,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 0.2506,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.05902480752780154,
505
+ "grad_norm": 0.6140468120574951,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 0.242,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.059880239520958084,
512
+ "grad_norm": 0.8597086071968079,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 0.3553,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.06073567151411463,
519
+ "grad_norm": 0.8153907656669617,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 0.2191,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.06159110350727117,
526
+ "grad_norm": 0.5583605766296387,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 0.2033,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.06244653550042772,
533
+ "grad_norm": 0.5807018876075745,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 0.2504,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.06330196749358426,
540
+ "grad_norm": 0.563032865524292,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 0.2386,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0641573994867408,
547
+ "grad_norm": 0.4548931121826172,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 0.2231,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.06501283147989735,
554
+ "grad_norm": 0.545421838760376,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 0.2811,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0658682634730539,
561
+ "grad_norm": 0.8195017576217651,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 0.2811,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.06672369546621043,
568
+ "grad_norm": 0.7224476337432861,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 0.3034,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.06757912745936698,
575
+ "grad_norm": 0.738802433013916,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 0.3257,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.06843455945252352,
582
+ "grad_norm": 0.7129746079444885,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 0.3329,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.06928999144568007,
589
+ "grad_norm": 0.7020834684371948,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 0.307,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.07014542343883662,
596
+ "grad_norm": 0.5662789940834045,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 0.3007,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.07100085543199315,
603
+ "grad_norm": 0.6873999238014221,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 0.34,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0718562874251497,
610
+ "grad_norm": 0.7224177718162537,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 0.3833,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.07271171941830624,
617
+ "grad_norm": 1.1468607187271118,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 0.3873,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.07356715141146279,
624
+ "grad_norm": 0.7172346115112305,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 0.3333,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.07442258340461934,
631
+ "grad_norm": 0.7859193086624146,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 0.4443,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.07527801539777587,
638
+ "grad_norm": 0.7493287324905396,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 0.3925,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.07613344739093242,
645
+ "grad_norm": 1.187333106994629,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 0.5375,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.07698887938408897,
652
+ "grad_norm": 1.1516120433807373,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 0.5597,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.07784431137724551,
659
+ "grad_norm": 1.370631217956543,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 0.6242,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.07869974337040206,
666
+ "grad_norm": 1.2987772226333618,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 0.6291,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.07955517536355859,
673
+ "grad_norm": 1.182003378868103,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 0.7286,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.08041060735671514,
680
+ "grad_norm": 2.1859383583068848,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 0.7186,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.08126603934987169,
687
+ "grad_norm": 2.0418176651000977,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 0.7344,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.08212147134302823,
694
+ "grad_norm": 1.459978461265564,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 0.7504,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.08297690333618478,
701
+ "grad_norm": 2.8905394077301025,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 0.9282,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.08383233532934131,
708
+ "grad_norm": 2.008319854736328,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 1.0452,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.08468776732249786,
715
+ "grad_norm": 2.0289366245269775,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 1.0555,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0855431993156544,
722
+ "grad_norm": 5.0649800300598145,
723
+ "learning_rate": 0.0,
724
+ "loss": 1.9191,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0855431993156544,
729
+ "eval_loss": 0.874006450176239,
730
+ "eval_runtime": 7.3781,
731
+ "eval_samples_per_second": 133.503,
732
+ "eval_steps_per_second": 33.477,
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": 1537626265878528.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null