bbytxt commited on
Commit
9dbec18
·
verified ·
1 Parent(s): bc2326f

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 sha256:6df2b154c6a19a6794eef3837db35b24527fb7a02125e86b8433e46955064a30
3
  size 479005064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d6aaf5fe2f885e1dd87c5c85f452f882073fa92d77d61df34d438911007cf1
3
  size 479005064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4874658278500ef3956eea973816131e3c4a6a76eb5c293034edc730fcda2f0c
3
  size 958299770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57b874d0a26bf230afffe5fb8721ab76e2a8c0d209f577f12a1a939fa091be7e
3
  size 958299770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d3e43d86992023f54063dbdd33e4e2f2002ad19ba7b6783b71d7f1d764554c3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a925690ecfa455097a4a06b3b6d2b5be08004f370902f55438664ebbd924cc40
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.8435356616973877,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.704225352112676,
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": 21.62,
374
  "eval_steps_per_second": 2.702,
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": 2.8596442616561664e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.689497470855713,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.408450704225352,
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": 21.62,
374
  "eval_steps_per_second": 2.702,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.7183098591549296,
379
+ "grad_norm": 2.7816450595855713,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 2.3131,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.7323943661971831,
386
+ "grad_norm": 1.5190588235855103,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 1.6635,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.7464788732394366,
393
+ "grad_norm": 1.3857049942016602,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 1.5654,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.7605633802816901,
400
+ "grad_norm": 1.2096006870269775,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 1.7222,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.7746478873239436,
407
+ "grad_norm": 1.2725486755371094,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 1.7869,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.7887323943661971,
414
+ "grad_norm": 1.3458586931228638,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 1.8483,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.8028169014084507,
421
+ "grad_norm": 1.5015977621078491,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 1.5314,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.8169014084507042,
428
+ "grad_norm": 1.5502326488494873,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 1.63,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.8309859154929577,
435
+ "grad_norm": 1.6416538953781128,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 1.5956,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.8450704225352113,
442
+ "grad_norm": 1.6144381761550903,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 1.6909,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.8591549295774648,
449
+ "grad_norm": 1.3809669017791748,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 1.801,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.8732394366197183,
456
+ "grad_norm": 1.4957369565963745,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 1.8188,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.8873239436619719,
463
+ "grad_norm": 1.5907005071640015,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 1.7431,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.9014084507042254,
470
+ "grad_norm": 1.412441372871399,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 1.8455,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.9154929577464789,
477
+ "grad_norm": 1.4778364896774292,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 1.824,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.9295774647887324,
484
+ "grad_norm": 1.4273475408554077,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 1.8471,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.9436619718309859,
491
+ "grad_norm": 2.055863380432129,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 2.0734,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.9577464788732394,
498
+ "grad_norm": 2.6091489791870117,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 2.1574,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.971830985915493,
505
+ "grad_norm": 0.8804201483726501,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 1.6816,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.9859154929577465,
512
+ "grad_norm": 1.1886156797409058,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 1.587,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.0,
519
+ "grad_norm": 1.3310304880142212,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 1.8521,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.0140845070422535,
526
+ "grad_norm": 1.2212010622024536,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 1.5759,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.028169014084507,
533
+ "grad_norm": 1.4360296726226807,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 1.558,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.0422535211267605,
540
+ "grad_norm": 1.3856598138809204,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 1.6417,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.056338028169014,
547
+ "grad_norm": 1.0938535928726196,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 1.6678,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.0704225352112675,
554
+ "grad_norm": 1.2646450996398926,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 1.7071,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.084507042253521,
561
+ "grad_norm": 1.1934901475906372,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 1.7286,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.0985915492957747,
568
+ "grad_norm": 1.6086108684539795,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 1.5267,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.1126760563380282,
575
+ "grad_norm": 1.856623649597168,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 1.5899,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.1267605633802817,
582
+ "grad_norm": 1.3756409883499146,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 1.5355,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.1408450704225352,
589
+ "grad_norm": 1.3555829524993896,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 1.6508,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.1549295774647887,
596
+ "grad_norm": 1.3804004192352295,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 1.6912,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.1690140845070423,
603
+ "grad_norm": 1.4337102174758911,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 1.7094,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.1830985915492958,
610
+ "grad_norm": 1.4616302251815796,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 1.7183,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.1971830985915493,
617
+ "grad_norm": 1.3623261451721191,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 1.6798,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.2112676056338028,
624
+ "grad_norm": 1.4235385656356812,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 1.7621,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.2253521126760563,
631
+ "grad_norm": 1.6084195375442505,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 1.8549,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.2394366197183098,
638
+ "grad_norm": 2.6670219898223877,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 2.1107,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.2535211267605635,
645
+ "grad_norm": 1.3784013986587524,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 1.5806,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.267605633802817,
652
+ "grad_norm": 1.3833378553390503,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 1.5403,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.2816901408450705,
659
+ "grad_norm": 1.3122845888137817,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 1.5813,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.295774647887324,
666
+ "grad_norm": 1.1090465784072876,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 1.6799,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.3098591549295775,
673
+ "grad_norm": 1.3463518619537354,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 1.7081,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.323943661971831,
680
+ "grad_norm": 1.2838189601898193,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 1.7572,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.3380281690140845,
687
+ "grad_norm": 1.5930005311965942,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 1.4535,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.352112676056338,
694
+ "grad_norm": 1.4882570505142212,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 1.5066,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.3661971830985915,
701
+ "grad_norm": 1.4822651147842407,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 1.4942,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.380281690140845,
708
+ "grad_norm": 1.6636682748794556,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 1.6294,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.3943661971830985,
715
+ "grad_norm": 1.2824631929397583,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 1.6908,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.408450704225352,
722
+ "grad_norm": 1.4730621576309204,
723
+ "learning_rate": 0.0,
724
+ "loss": 1.6844,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.408450704225352,
729
+ "eval_loss": 1.689497470855713,
730
+ "eval_runtime": 5.5773,
731
+ "eval_samples_per_second": 21.516,
732
+ "eval_steps_per_second": 2.689,
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": 5.719288523312333e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null