0x1202 commited on
Commit
73e2956
·
verified ·
1 Parent(s): 8aa1fb6

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:b03783bdeb3f3eedb3b94da16e0f320f06a7b03b76ffbf664acf71ec6f343899
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd3287dc8a3fb34188027efd0f4cecac89657b44e9fa52cbd714cc9310ec4464
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2482c07aea4eae4ce4b18ffb0a0ad95c54e84a7dbf300167acd1bb412fcd7b4
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8c34cb71ac568e8dca9b10b09758f9412ae5ea1763ec85db7f38dc5eb31f9c4
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ab7382f5873fa24e6c9ff82d2ec53dd84b08047d2db4caa49fa3db1c6544c5e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac797189e053209446e4a93c56757be96e09b957b763c47c2baaa24d47710714
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": 1.066644549369812,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.35650623885918004,
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": 9.862,
374
  "eval_steps_per_second": 1.248,
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": 6.719068728773837e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.985734760761261,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.7130124777183601,
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": 9.862,
374
  "eval_steps_per_second": 1.248,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.36363636363636365,
379
+ "grad_norm": 1.4158107042312622,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 4.6554,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.37076648841354726,
386
+ "grad_norm": 1.3614400625228882,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 4.3879,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.3778966131907308,
393
+ "grad_norm": 1.2782399654388428,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 4.2737,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3850267379679144,
400
+ "grad_norm": 1.2635055780410767,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 4.0312,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.39215686274509803,
407
+ "grad_norm": 1.2960742712020874,
408
+ "learning_rate": 5e-05,
409
+ "loss": 4.4185,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.39928698752228164,
414
+ "grad_norm": 1.373910903930664,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 3.8564,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.40641711229946526,
421
+ "grad_norm": 1.3597720861434937,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 3.9357,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.41354723707664887,
428
+ "grad_norm": 1.4076162576675415,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 3.5085,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.4206773618538324,
435
+ "grad_norm": 1.3893558979034424,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 3.2469,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.42780748663101603,
442
+ "grad_norm": 1.395827054977417,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 3.2323,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.43493761140819964,
449
+ "grad_norm": 1.3438602685928345,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 2.8626,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.44206773618538325,
456
+ "grad_norm": 1.4302135705947876,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 3.0505,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.44919786096256686,
463
+ "grad_norm": 1.4719938039779663,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 3.0484,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.4563279857397504,
470
+ "grad_norm": 1.6130385398864746,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 3.185,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.46345811051693403,
477
+ "grad_norm": 1.8266406059265137,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 3.2009,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.47058823529411764,
484
+ "grad_norm": 1.9313302040100098,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 3.1525,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.47771836007130125,
491
+ "grad_norm": 2.423699378967285,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 3.1436,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.48484848484848486,
498
+ "grad_norm": 2.443610668182373,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 3.4362,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.4919786096256685,
505
+ "grad_norm": 2.610008955001831,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 3.2321,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.49910873440285203,
512
+ "grad_norm": 3.1767327785491943,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 3.209,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.5062388591800356,
519
+ "grad_norm": 2.1577703952789307,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 5.3338,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.5133689839572193,
526
+ "grad_norm": 2.098604679107666,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 5.2837,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.5204991087344029,
533
+ "grad_norm": 2.168285608291626,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 5.5498,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.5276292335115864,
540
+ "grad_norm": 2.237492322921753,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 5.3952,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.5347593582887701,
547
+ "grad_norm": 2.1015090942382812,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 5.1172,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.5418894830659536,
554
+ "grad_norm": 1.8349698781967163,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 4.8605,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.5490196078431373,
561
+ "grad_norm": 1.669671654701233,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 4.7191,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5561497326203209,
568
+ "grad_norm": 1.5524064302444458,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 4.0673,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5632798573975044,
575
+ "grad_norm": 1.3542040586471558,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 4.3932,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.5704099821746881,
582
+ "grad_norm": 1.2547845840454102,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 4.0502,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.5775401069518716,
589
+ "grad_norm": 1.199395775794983,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 4.3932,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.5846702317290553,
596
+ "grad_norm": 1.1699484586715698,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 3.8516,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.5918003565062389,
603
+ "grad_norm": 1.2436898946762085,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 3.9816,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.5989304812834224,
610
+ "grad_norm": 1.2301483154296875,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 4.2743,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.6060606060606061,
617
+ "grad_norm": 1.1662721633911133,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 4.3479,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.6131907308377896,
624
+ "grad_norm": 1.154500961303711,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 3.7961,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.6203208556149733,
631
+ "grad_norm": 1.2171392440795898,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 3.9442,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.6274509803921569,
638
+ "grad_norm": 1.3039647340774536,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 3.8009,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.6345811051693404,
645
+ "grad_norm": 1.2364025115966797,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 3.8085,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.6417112299465241,
652
+ "grad_norm": 1.339046835899353,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 3.8189,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.6488413547237076,
659
+ "grad_norm": 1.3669147491455078,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 3.636,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.6559714795008913,
666
+ "grad_norm": 1.4621479511260986,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 3.6006,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.6631016042780749,
673
+ "grad_norm": 1.3589284420013428,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 3.5506,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.6702317290552585,
680
+ "grad_norm": 1.483871340751648,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 3.4198,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.6773618538324421,
687
+ "grad_norm": 1.504876732826233,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 3.2703,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.6844919786096256,
694
+ "grad_norm": 1.50764000415802,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 3.1094,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.6916221033868093,
701
+ "grad_norm": 1.628373384475708,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 2.9344,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.6987522281639929,
708
+ "grad_norm": 1.6594825983047485,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 2.9435,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.7058823529411765,
715
+ "grad_norm": 1.6344276666641235,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 2.7318,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.7130124777183601,
722
+ "grad_norm": 1.735816240310669,
723
+ "learning_rate": 0.0,
724
+ "loss": 2.843,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.7130124777183601,
729
+ "eval_loss": 0.985734760761261,
730
+ "eval_runtime": 24.0148,
731
+ "eval_samples_per_second": 9.869,
732
+ "eval_steps_per_second": 1.249,
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": 1.3404874741068595e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null