Nexspear commited on
Commit
d6104d7
·
verified ·
1 Parent(s): 02b3d5b

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 sha256:8cc88cb0bfe35bb4d47cdc3987c01c6db045cfb3cdcb388c7d0d35b2c846a076
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a270c51baf8dcedc5809e9246b83c9124c6a6b9a80bf5d4cc15e1e6646663b76
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7954a3f84b4dd50fe3297561a83cd1d14313fb57763bbb1aeba3a2b949f86360
3
  size 170920084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca586d556ebb7bde74c288867f7c843f0d06bbde6a5a014b7b4e7aa54de2f784
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:dab7858131204e7fa779cc8da68e7b7264ac24671644c279ec8a99b9d7b67372
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957344c806b6a64c57f59542b010043e5ef9d36f7d40155addb18de783573d8a
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": 3.633587121963501,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.06791171477079797,
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": 13.088,
374
  "eval_steps_per_second": 3.272,
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": 7.49740504425431e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.150726318359375,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.13582342954159593,
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": 13.088,
374
  "eval_steps_per_second": 3.272,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.06926994906621392,
379
+ "grad_norm": 3.272021770477295,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 3.2556,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07062818336162988,
386
+ "grad_norm": 3.229267120361328,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 3.4505,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.07198641765704585,
393
+ "grad_norm": 2.744947671890259,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 3.4129,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0733446519524618,
400
+ "grad_norm": 2.082028388977051,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 3.2264,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.07470288624787776,
407
+ "grad_norm": 1.7917437553405762,
408
+ "learning_rate": 5e-05,
409
+ "loss": 3.0597,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.07606112054329371,
414
+ "grad_norm": 1.5164369344711304,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 2.9627,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.07741935483870968,
421
+ "grad_norm": 1.220090627670288,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 3.031,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.07877758913412564,
428
+ "grad_norm": 1.1720942258834839,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 2.8598,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08013582342954159,
435
+ "grad_norm": 1.0795058012008667,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 2.9687,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.08149405772495756,
442
+ "grad_norm": 1.1166324615478516,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 2.9217,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.08285229202037352,
449
+ "grad_norm": 1.0355231761932373,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 2.9804,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.08421052631578947,
456
+ "grad_norm": 1.0210473537445068,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 2.9672,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.08556876061120543,
463
+ "grad_norm": 1.0804847478866577,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 2.9076,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0869269949066214,
470
+ "grad_norm": 1.092564582824707,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 3.0434,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.08828522920203735,
477
+ "grad_norm": 1.035814881324768,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 2.8399,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.08964346349745331,
484
+ "grad_norm": 1.1453022956848145,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 3.0329,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.09100169779286928,
491
+ "grad_norm": 1.2078114748001099,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 3.0805,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.09235993208828523,
498
+ "grad_norm": 1.1674644947052002,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 2.9356,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.09371816638370119,
505
+ "grad_norm": 1.27103590965271,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 3.0431,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.09507640067911714,
512
+ "grad_norm": 1.3005256652832031,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 2.9927,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.09643463497453311,
519
+ "grad_norm": 1.3241961002349854,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 2.9704,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.09779286926994907,
526
+ "grad_norm": 1.2523479461669922,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 2.9684,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.09915110356536502,
533
+ "grad_norm": 1.3486278057098389,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 3.0913,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.10050933786078098,
540
+ "grad_norm": 1.3774032592773438,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 2.9827,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.10186757215619695,
547
+ "grad_norm": 1.4519808292388916,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 3.09,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.1032258064516129,
554
+ "grad_norm": 1.27621591091156,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 2.8098,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.10458404074702886,
561
+ "grad_norm": 1.4423140287399292,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 3.0745,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.10594227504244483,
568
+ "grad_norm": 1.4936318397521973,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 3.032,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.10730050933786078,
575
+ "grad_norm": 1.448979139328003,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 3.0732,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.10865874363327674,
582
+ "grad_norm": 1.5673203468322754,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 2.9532,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.1100169779286927,
589
+ "grad_norm": 1.7247906923294067,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 3.1121,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.11137521222410866,
596
+ "grad_norm": 1.7172918319702148,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 3.063,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.11273344651952462,
603
+ "grad_norm": 1.903825283050537,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 3.0997,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.11409168081494057,
610
+ "grad_norm": 1.8186181783676147,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 3.013,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.11544991511035653,
617
+ "grad_norm": 1.949047565460205,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 3.0805,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.1168081494057725,
624
+ "grad_norm": 1.848542332649231,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 2.9419,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.11816638370118845,
631
+ "grad_norm": 2.18829083442688,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 3.2824,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.11952461799660441,
638
+ "grad_norm": 2.0119502544403076,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 3.06,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.12088285229202038,
645
+ "grad_norm": 2.2902331352233887,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 3.2513,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.12224108658743633,
652
+ "grad_norm": 2.4380276203155518,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 3.2012,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.12359932088285229,
659
+ "grad_norm": 4.407219886779785,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 3.2539,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.12495755517826825,
666
+ "grad_norm": 2.8006558418273926,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 3.4096,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.12631578947368421,
673
+ "grad_norm": 3.0161592960357666,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 3.3603,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.12767402376910017,
680
+ "grad_norm": 3.3037898540496826,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 3.3665,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.12903225806451613,
687
+ "grad_norm": 3.8923280239105225,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 3.6658,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.13039049235993208,
694
+ "grad_norm": 4.091800212860107,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 3.5337,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.13174872665534804,
701
+ "grad_norm": 5.110889434814453,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 4.1419,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.13310696095076402,
708
+ "grad_norm": 5.706676483154297,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 4.1927,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.13446519524617997,
715
+ "grad_norm": 7.825375080108643,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 4.7749,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.13582342954159593,
722
+ "grad_norm": 10.896963119506836,
723
+ "learning_rate": 0.0,
724
+ "loss": 5.1337,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.13582342954159593,
729
+ "eval_loss": 3.150726318359375,
730
+ "eval_runtime": 94.8667,
731
+ "eval_samples_per_second": 13.071,
732
+ "eval_steps_per_second": 3.268,
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": 1.499481008850862e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null