nttx commited on
Commit
ceab160
·
verified ·
1 Parent(s): 214db1a

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:b2ae88a6ed891c088b3600347fee2299889647d97b557a376a9f5197e30355a4
3
  size 34456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfed04052524d393fd4b9d3bc71ac911ed4c108652bda583c195b901359cbcc1
3
  size 34456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cacb3e4e8d07d0e37e0fe3d894ea80b1472e9dba3a3077d4affd8beb2198135
3
  size 73222
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b48e2b06c9be9356e34f0963092497eae38a648fca41329561d14d159ed2502
3
  size 73222
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb4d8737d7bc49da86420c732830ab26bc1bfbcad60dc3db56bbd281ed844057
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ad1f94e4390e8ce69664236c9c732498d27ed7a2890f89872eccc93abbab1c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 11.5,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.07209805335255948,
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": 178.358,
374
  "eval_steps_per_second": 44.704,
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": {
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 10974075420672.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
  "best_metric": 11.5,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.14419610670511895,
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": 178.358,
374
  "eval_steps_per_second": 44.704,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07354001441961067,
379
+ "grad_norm": 0.00014630900113843381,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 46.0,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07498197548666186,
386
+ "grad_norm": 0.00016575051995459944,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 46.0,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.07642393655371305,
393
+ "grad_norm": 9.503810724709183e-05,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 46.0,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.07786589762076424,
400
+ "grad_norm": 0.00010648839815985411,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 46.0,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.07930785868781542,
407
+ "grad_norm": 0.00011491494660731405,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 46.0,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.08074981975486661,
414
+ "grad_norm": 0.00013562277308665216,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 46.0,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0821917808219178,
421
+ "grad_norm": 0.00015486359188798815,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 46.0,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.083633741888969,
428
+ "grad_norm": 0.00012581907503772527,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 46.0,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08507570295602018,
435
+ "grad_norm": 0.00029646081384271383,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 46.0,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.08651766402307137,
442
+ "grad_norm": 0.00019654743664432317,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 46.0,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.08795962509012256,
449
+ "grad_norm": 0.0001651565107749775,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 46.0,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.08940158615717375,
456
+ "grad_norm": 0.0001822762133087963,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 46.0,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.09084354722422494,
463
+ "grad_norm": 0.00013959217176306993,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 46.0,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.09228550829127613,
470
+ "grad_norm": 0.00022408162476494908,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 46.0,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.09372746935832732,
477
+ "grad_norm": 0.00035673525417223573,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 46.0,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.09516943042537851,
484
+ "grad_norm": 0.00041785562643781304,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 46.0,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0966113914924297,
491
+ "grad_norm": 0.00033946934854611754,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 46.0,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.09805335255948089,
498
+ "grad_norm": 0.00011334617011016235,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 46.0,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.09949531362653208,
505
+ "grad_norm": 0.00015962774341460317,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 46.0,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.10093727469358327,
512
+ "grad_norm": 0.00016410488751716912,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 46.0,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.10237923576063446,
519
+ "grad_norm": 0.0001240667625097558,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 46.0,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.10382119682768565,
526
+ "grad_norm": 0.00020238997240085155,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 46.0,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.10526315789473684,
533
+ "grad_norm": 0.00023328776296693832,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 46.0,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.10670511896178803,
540
+ "grad_norm": 0.00017381407087668777,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 46.0,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.10814708002883922,
547
+ "grad_norm": 0.0003512923140078783,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 46.0,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.1095890410958904,
554
+ "grad_norm": 0.000159394956426695,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 46.0,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.1110310021629416,
561
+ "grad_norm": 0.0003031495143659413,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 46.0,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.11247296322999278,
568
+ "grad_norm": 0.0002476269437465817,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 46.0,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.11391492429704397,
575
+ "grad_norm": 0.0002291841374244541,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 46.0,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.11535688536409516,
582
+ "grad_norm": 0.0004125789273530245,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 46.0,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.11679884643114635,
589
+ "grad_norm": 0.000245795730734244,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 46.0,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.11824080749819754,
596
+ "grad_norm": 0.00022407225333154202,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 46.0,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.11968276856524873,
603
+ "grad_norm": 0.000303188367979601,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 46.0,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.12112472963229992,
610
+ "grad_norm": 0.00023917999351397157,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 46.0,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.12256669069935111,
617
+ "grad_norm": 0.00031476496951654553,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 46.0,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.1240086517664023,
624
+ "grad_norm": 0.00023287246585823596,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 46.0,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.1254506128334535,
631
+ "grad_norm": 0.0003421494329813868,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 46.0,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.12689257390050468,
638
+ "grad_norm": 0.0002833238977473229,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 46.0,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.12833453496755587,
645
+ "grad_norm": 0.0006084145279601216,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 46.0,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.12977649603460706,
652
+ "grad_norm": 0.00033296371111646295,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 46.0,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.13121845710165825,
659
+ "grad_norm": 0.00019833420810755342,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 46.0,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.13266041816870944,
666
+ "grad_norm": 0.00040156146860681474,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 46.0,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.13410237923576063,
673
+ "grad_norm": 0.00037203371175564826,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 46.0,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.13554434030281182,
680
+ "grad_norm": 0.0004838180320803076,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 46.0,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.136986301369863,
687
+ "grad_norm": 0.0003659892827272415,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 46.0,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.1384282624369142,
694
+ "grad_norm": 0.0003629039856605232,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 46.0,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.13987022350396539,
701
+ "grad_norm": 0.0003685996343847364,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 46.0,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.14131218457101657,
708
+ "grad_norm": 0.0002297442697454244,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 46.0,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.14275414563806776,
715
+ "grad_norm": 0.0004087391134817153,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 46.0,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.14419610670511895,
722
+ "grad_norm": 0.0005655571003444493,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 46.0,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.14419610670511895,
729
+ "eval_loss": 11.5,
730
+ "eval_runtime": 6.6065,
731
+ "eval_samples_per_second": 176.946,
732
+ "eval_steps_per_second": 44.35,
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": {
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 21747160449024.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null