nttx commited on
Commit
6eda7f0
·
verified ·
1 Parent(s): 3af151e

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 sha256:9d0d94d54bbce8f8f4cfd098eeeeddaad692e9484a5fde6f146f3633124107c7
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ee0d54d9912f6c96a262924933188436d470932fb0d61d8f49d20ddfb378c11
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b1114e661b1535662811cb317c49d240c128e3a13fe22ff56cc30364bc455f2
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e841863e2a82ad87f0d699e5d3919ede44aa695265f1aae6dd151578e64061ea
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dfc0a2844de759a12be446071908052f89e81d225ea86302a327f7a2d84c45e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab491e1135604465c630102d7aac14773d377a5df648db605285929d38afecc8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
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": 10.375799179077148,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.43149946062567424,
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": 606.113,
374
  "eval_steps_per_second": 76.055,
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": 20920978636800.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.375710487365723,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.8629989212513485,
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": 606.113,
374
  "eval_steps_per_second": 76.055,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.4401294498381877,
379
+ "grad_norm": 0.02763248048722744,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 10.3743,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.4487594390507012,
386
+ "grad_norm": 0.026803849264979362,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 10.3751,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.45738942826321466,
393
+ "grad_norm": 0.032057423144578934,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 10.3756,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.46601941747572817,
400
+ "grad_norm": 0.0315421037375927,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 10.3706,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.4746494066882416,
407
+ "grad_norm": 0.027795402333140373,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 10.3726,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.48327939590075514,
414
+ "grad_norm": 0.0317898653447628,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 10.3707,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.4919093851132686,
421
+ "grad_norm": 0.018849367275834084,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 10.3779,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.5005393743257821,
428
+ "grad_norm": 0.020816050469875336,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 10.3787,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.5091693635382956,
435
+ "grad_norm": 0.021257532760500908,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 10.3775,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.517799352750809,
442
+ "grad_norm": 0.02319033071398735,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 10.3763,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.5264293419633226,
449
+ "grad_norm": 0.02176329866051674,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 10.3773,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.535059331175836,
456
+ "grad_norm": 0.020290648564696312,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 10.3774,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.5436893203883495,
463
+ "grad_norm": 0.022093839943408966,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 10.3777,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.552319309600863,
470
+ "grad_norm": 0.023164978250861168,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 10.3766,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.5609492988133765,
477
+ "grad_norm": 0.022713061422109604,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 10.3777,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.56957928802589,
484
+ "grad_norm": 0.021287312731146812,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 10.3774,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.5782092772384034,
491
+ "grad_norm": 0.025064850226044655,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 10.3765,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.5868392664509169,
498
+ "grad_norm": 0.023417694494128227,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 10.3765,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.5954692556634305,
505
+ "grad_norm": 0.02556951902806759,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 10.3775,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.6040992448759439,
512
+ "grad_norm": 0.02573770470917225,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 10.3777,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.6127292340884574,
519
+ "grad_norm": 0.026057329028844833,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 10.3778,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.6213592233009708,
526
+ "grad_norm": 0.021764149889349937,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 10.378,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.6299892125134844,
533
+ "grad_norm": 0.026920149102807045,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 10.3757,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.6386192017259978,
540
+ "grad_norm": 0.028223862871527672,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 10.3758,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.6472491909385113,
547
+ "grad_norm": 0.02494722604751587,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 10.3752,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.6558791801510249,
554
+ "grad_norm": 0.029117414727807045,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 10.3746,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.6645091693635383,
561
+ "grad_norm": 0.02269524335861206,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 10.3743,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.6731391585760518,
568
+ "grad_norm": 0.030670158565044403,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 10.3743,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.6817691477885652,
575
+ "grad_norm": 0.028203874826431274,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 10.3766,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.6903991370010788,
582
+ "grad_norm": 0.027461817488074303,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 10.3764,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.6990291262135923,
589
+ "grad_norm": 0.028424471616744995,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 10.3726,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.7076591154261057,
596
+ "grad_norm": 0.027228577062487602,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 10.3717,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.7162891046386192,
603
+ "grad_norm": 0.030071238055825233,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 10.3707,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.7249190938511327,
610
+ "grad_norm": 0.03489195927977562,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 10.3703,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.7335490830636462,
617
+ "grad_norm": 0.020027657970786095,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 10.3784,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.7421790722761596,
624
+ "grad_norm": 0.020729346200823784,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 10.3783,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.7508090614886731,
631
+ "grad_norm": 0.022927572950720787,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 10.3768,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.7594390507011867,
638
+ "grad_norm": 0.02265709452331066,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 10.3784,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.7680690399137001,
645
+ "grad_norm": 0.020794713869690895,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 10.3776,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.7766990291262136,
652
+ "grad_norm": 0.020349379628896713,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 10.3767,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.785329018338727,
659
+ "grad_norm": 0.020114626735448837,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 10.3767,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.7939590075512406,
666
+ "grad_norm": 0.02368362620472908,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 10.3771,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.8025889967637541,
673
+ "grad_norm": 0.024577448144555092,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 10.3778,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.8112189859762675,
680
+ "grad_norm": 0.02333916909992695,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 10.3777,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.819848975188781,
687
+ "grad_norm": 0.02276407554745674,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 10.3778,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.8284789644012945,
694
+ "grad_norm": 0.02342147007584572,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 10.3778,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.837108953613808,
701
+ "grad_norm": 0.022775474935770035,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 10.3772,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.8457389428263214,
708
+ "grad_norm": 0.02469836361706257,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 10.3771,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.8543689320388349,
715
+ "grad_norm": 0.02446691133081913,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 10.3775,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.8629989212513485,
722
+ "grad_norm": 0.024237973615527153,
723
+ "learning_rate": 0.0,
724
+ "loss": 10.3771,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.8629989212513485,
729
+ "eval_loss": 10.375710487365723,
730
+ "eval_runtime": 1.2914,
731
+ "eval_samples_per_second": 604.792,
732
+ "eval_steps_per_second": 75.889,
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": 41841957273600.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null