nttx commited on
Commit
4eebbbb
·
verified ·
1 Parent(s): 71609e4

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 sha256:0bbeece09223dfdcbc7ac9e30ec1f6461a087e83eb310134e93dfa29db5ae41b
3
  size 25192496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020d54c9c3de4c639e5a985ef1698ad3b9701716887d31a208743f1c58f94dff
3
  size 25192496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aef97598ff11ecd09e77d933c4ed7d0f432db53fedaa95a0c2bd7f18eb57d30
3
  size 50493050
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46ae36a21a5e5a5e77705251fbc638d024a495c827f35e0baa50939ab2000ea
3
  size 50493050
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5995c4ff303a6f39ae658f87ca1c977b5e816079b1edba3b71a575b5e47250a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e8b49a7cee2ab1d48ffed61619fa44411c55a1180b64f37d7d3bc20dc8fd2d
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": 2.273921012878418,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.00639467962655071,
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": 23.293,
374
  "eval_steps_per_second": 2.915,
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": 2985723691008000.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.227423667907715,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.01278935925310142,
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": 23.293,
374
  "eval_steps_per_second": 2.915,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.006522573219081724,
379
+ "grad_norm": 0.824315071105957,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 1.7344,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.006650466811612738,
386
+ "grad_norm": 0.8575537204742432,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 1.6085,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.006778360404143752,
393
+ "grad_norm": 1.030655860900879,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 1.6915,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.006906253996674766,
400
+ "grad_norm": 0.9780040979385376,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 1.8391,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.007034147589205781,
407
+ "grad_norm": 1.075355887413025,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 1.7932,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.007162041181736795,
414
+ "grad_norm": 1.0918196439743042,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 1.7666,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.007289934774267809,
421
+ "grad_norm": 1.0339546203613281,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 1.8442,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0074178283667988235,
428
+ "grad_norm": 1.178619384765625,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 1.9234,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.007545721959329838,
435
+ "grad_norm": 1.1075314283370972,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 1.9327,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.007673615551860852,
442
+ "grad_norm": 1.2657276391983032,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 1.8388,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.007801509144391866,
449
+ "grad_norm": 1.1688446998596191,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 1.7806,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.00792940273692288,
456
+ "grad_norm": 1.1615688800811768,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 1.9443,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.008057296329453895,
463
+ "grad_norm": 1.2162307500839233,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 1.7797,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.00818518992198491,
470
+ "grad_norm": 1.4072235822677612,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 1.7035,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.008313083514515924,
477
+ "grad_norm": 1.484116792678833,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 2.0504,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.008440977107046936,
484
+ "grad_norm": 1.3416109085083008,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 1.9764,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.00856887069957795,
491
+ "grad_norm": 1.3301259279251099,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 1.951,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.008696764292108965,
498
+ "grad_norm": 1.3805782794952393,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 2.0396,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.008824657884639979,
505
+ "grad_norm": 1.2760380506515503,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 1.9385,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.008952551477170993,
512
+ "grad_norm": 1.4715478420257568,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 2.2723,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.009080445069702008,
519
+ "grad_norm": 1.3770544528961182,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 1.888,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.009208338662233022,
526
+ "grad_norm": 1.2823768854141235,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 2.0006,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.009336232254764036,
533
+ "grad_norm": 1.366890788078308,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 1.8851,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.00946412584729505,
540
+ "grad_norm": 1.4455935955047607,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 2.0491,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.009592019439826065,
547
+ "grad_norm": 1.420132040977478,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 1.9303,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.009719913032357079,
554
+ "grad_norm": 1.3549017906188965,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 1.97,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.009847806624888093,
561
+ "grad_norm": 1.558439016342163,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 2.4078,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.009975700217419108,
568
+ "grad_norm": 1.561328649520874,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 2.0117,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.010103593809950122,
575
+ "grad_norm": 1.3918482065200806,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 2.0692,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.010231487402481136,
582
+ "grad_norm": 1.4925870895385742,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 2.1758,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01035938099501215,
589
+ "grad_norm": 1.8017629384994507,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 2.1219,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.010487274587543165,
596
+ "grad_norm": 1.533422827720642,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 2.0952,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.010615168180074179,
603
+ "grad_norm": 1.8227595090866089,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 2.258,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.010743061772605193,
610
+ "grad_norm": 1.8445152044296265,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 2.3289,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.010870955365136206,
617
+ "grad_norm": 1.7444809675216675,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 2.2124,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.01099884895766722,
624
+ "grad_norm": 1.7502052783966064,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 2.2203,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.011126742550198234,
631
+ "grad_norm": 1.734458327293396,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 2.5345,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.011254636142729249,
638
+ "grad_norm": 2.3257081508636475,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 2.403,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.011382529735260263,
645
+ "grad_norm": 1.9918384552001953,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 2.5831,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.011510423327791277,
652
+ "grad_norm": 2.127302885055542,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 2.9882,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.011638316920322292,
659
+ "grad_norm": 2.2728164196014404,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 2.6982,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.011766210512853306,
666
+ "grad_norm": 2.0041537284851074,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 2.5671,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.01189410410538432,
673
+ "grad_norm": 2.0824832916259766,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 2.5581,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.012021997697915334,
680
+ "grad_norm": 2.170213460922241,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 2.4461,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.012149891290446349,
687
+ "grad_norm": 2.363558769226074,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 2.8194,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.012277784882977363,
694
+ "grad_norm": 2.4575698375701904,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 3.1582,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.012405678475508377,
701
+ "grad_norm": 2.772186517715454,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 3.2808,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.012533572068039392,
708
+ "grad_norm": 3.1454925537109375,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 3.2904,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.012661465660570406,
715
+ "grad_norm": 2.797976493835449,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 3.0262,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.01278935925310142,
722
+ "grad_norm": 3.6094884872436523,
723
+ "learning_rate": 0.0,
724
+ "loss": 4.3375,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.01278935925310142,
729
+ "eval_loss": 2.227423667907715,
730
+ "eval_runtime": 141.3088,
731
+ "eval_samples_per_second": 23.296,
732
+ "eval_steps_per_second": 2.916,
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": 5971447382016000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null