nttx commited on
Commit
11d498d
·
verified ·
1 Parent(s): a3aea85

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 sha256:94402f214edf66039ccd15f87d1601f8d06b95e69dd0a4870a703e17a2527c99
3
  size 93608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c48940155ee91f72110d221efaabbbe3c7f8c5a0c1699f181418a33f05ffa07
3
  size 93608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94dd3cde62f0447454a734da2a8e5e25afe4932ca3fd6d31e900fe5f39624049
3
  size 204106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b1a69ccf46ccbb766979fd00790fdef4e558edc8d151286cab5150f2346662
3
  size 204106
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b107c313cad22cef858053cdf8ec420e319067d8f9f984bbf01d559708c607c0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c188e8f84f90aa80e5ffee5322a9df6bde3c720dba8306ebe6bffd503791b933
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": 11.930001258850098,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.11869436201780416,
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": 115.754,
374
  "eval_steps_per_second": 14.51,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -387,7 +745,7 @@
387
  "early_stopping_threshold": 0.0
388
  },
389
  "attributes": {
390
- "early_stopping_patience_counter": 0
391
  }
392
  },
393
  "TrainerControl": {
@@ -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": 302506967040.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
  "best_metric": 11.930001258850098,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.23738872403560832,
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": 115.754,
374
  "eval_steps_per_second": 14.51,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.12106824925816023,
379
+ "grad_norm": 0.025677772238850594,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 11.9306,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.12344213649851632,
386
+ "grad_norm": 0.02111092023551464,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 11.931,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.1258160237388724,
393
+ "grad_norm": 0.033029962331056595,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 11.9331,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.1281899109792285,
400
+ "grad_norm": 0.037202753126621246,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 11.9304,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.13056379821958458,
407
+ "grad_norm": 0.03716195374727249,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 11.9338,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.13293768545994064,
414
+ "grad_norm": 0.047880083322525024,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 11.9313,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.13531157270029673,
421
+ "grad_norm": 0.05157185345888138,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 11.9336,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.13768545994065282,
428
+ "grad_norm": 0.06601646542549133,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 11.9305,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.1400593471810089,
435
+ "grad_norm": 0.05444641783833504,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 11.9331,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.142433234421365,
442
+ "grad_norm": 0.0777202695608139,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 11.9412,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.14480712166172108,
449
+ "grad_norm": 0.06190499663352966,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 11.941,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.14718100890207717,
456
+ "grad_norm": 0.06600882858037949,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 11.9298,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.14955489614243322,
463
+ "grad_norm": 0.06076720729470253,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 11.936,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.1519287833827893,
470
+ "grad_norm": 0.029090601950883865,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 11.9308,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.1543026706231454,
477
+ "grad_norm": 0.020164206624031067,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 11.9299,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.1566765578635015,
484
+ "grad_norm": 0.03322097659111023,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 11.9281,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.15905044510385757,
491
+ "grad_norm": 0.03079245053231716,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 11.9314,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.16142433234421366,
498
+ "grad_norm": 0.042988039553165436,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 11.929,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.16379821958456972,
505
+ "grad_norm": 0.034079812467098236,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 11.9256,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.1661721068249258,
512
+ "grad_norm": 0.0356653593480587,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 11.9295,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.1685459940652819,
519
+ "grad_norm": 0.034619465470314026,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 11.9278,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.17091988130563798,
526
+ "grad_norm": 0.04170392081141472,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 11.924,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.17329376854599407,
533
+ "grad_norm": 0.03153539076447487,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 11.9275,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.17566765578635016,
540
+ "grad_norm": 0.03831743076443672,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 11.9264,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.17804154302670624,
547
+ "grad_norm": 0.029439780861139297,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 11.9324,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.1804154302670623,
554
+ "grad_norm": 0.03241276368498802,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 11.9285,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.1827893175074184,
561
+ "grad_norm": 0.030664395540952682,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 11.9322,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.18516320474777448,
568
+ "grad_norm": 0.03707865998148918,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 11.9246,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.18753709198813057,
575
+ "grad_norm": 0.032950352877378464,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 11.9287,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.18991097922848665,
582
+ "grad_norm": 0.03910613805055618,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 11.9301,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.19228486646884274,
589
+ "grad_norm": 0.05178769305348396,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 11.9294,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1946587537091988,
596
+ "grad_norm": 0.04277884587645531,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 11.9353,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.1970326409495549,
603
+ "grad_norm": 0.039287272840738297,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 11.9291,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.19940652818991098,
610
+ "grad_norm": 0.029898207634687424,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 11.9305,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.20178041543026706,
617
+ "grad_norm": 0.03671928495168686,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 11.9281,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.20415430267062315,
624
+ "grad_norm": 0.030655406415462494,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 11.9338,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.20652818991097924,
631
+ "grad_norm": 0.03415754809975624,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 11.9266,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.20890207715133532,
638
+ "grad_norm": 0.039449259638786316,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 11.9303,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.21127596439169138,
645
+ "grad_norm": 0.06573513895273209,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 11.9262,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.21364985163204747,
652
+ "grad_norm": 0.03181089460849762,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 11.9253,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.21602373887240356,
659
+ "grad_norm": 0.03856520727276802,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 11.9256,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.21839762611275965,
666
+ "grad_norm": 0.05031546950340271,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 11.918,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.22077151335311573,
673
+ "grad_norm": 0.039829157292842865,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 11.9277,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.22314540059347182,
680
+ "grad_norm": 0.03694596514105797,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 11.9287,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.22551928783382788,
687
+ "grad_norm": 0.0507882721722126,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 11.927,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.22789317507418397,
694
+ "grad_norm": 0.05311484634876251,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 11.9284,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.23026706231454006,
701
+ "grad_norm": 0.04178894683718681,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 11.9322,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.23264094955489614,
708
+ "grad_norm": 0.03615611419081688,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 11.9339,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.23501483679525223,
715
+ "grad_norm": 0.03656531497836113,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 11.9358,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.23738872403560832,
722
+ "grad_norm": 0.048884086310863495,
723
+ "learning_rate": 0.0,
724
+ "loss": 11.9313,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.23738872403560832,
729
+ "eval_loss": 11.930229187011719,
730
+ "eval_runtime": 5.8077,
731
+ "eval_samples_per_second": 122.251,
732
+ "eval_steps_per_second": 15.324,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
745
  "early_stopping_threshold": 0.0
746
  },
747
  "attributes": {
748
+ "early_stopping_patience_counter": 1
749
  }
750
  },
751
  "TrainerControl": {
 
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": 606219141120.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null