0x1202 commited on
Commit
880312a
·
verified ·
1 Parent(s): 993f618

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:bcec14500c78912db43f92ea4988a2499175c417ecd13505175636110db4b091
3
  size 985240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:425ba082c9856afd0cd9d29774b2151c22e3a220ccc441e5a801d9a1ea98a89e
3
  size 985240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b9fc49a3d0a84e71ce888d3e72a4bfc24c054849f335bfeec3945d816e0be3b
3
  size 1980078
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c9c5fa5dc2a758ffd24df8413238399ea435ace020171b437d03d54344f5ef
3
  size 1980078
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45d7eafd179fc78f473f0c9cfa0de0165288453578727daedea2c94bf8b0269c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:002018d787452eaa3dee44fbd4c21ec861914789e6a61001902df8148068dc88
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.678608894348145,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.07598784194528875,
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": 472.904,
374
  "eval_steps_per_second": 59.326,
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": 6001709285376.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.644861221313477,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.1519756838905775,
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": 472.904,
374
  "eval_steps_per_second": 59.326,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07750759878419453,
379
+ "grad_norm": 1.7174934148788452,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 42.8151,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0790273556231003,
386
+ "grad_norm": 1.5663914680480957,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 42.7887,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.08054711246200608,
393
+ "grad_norm": 1.557456374168396,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 42.7401,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.08206686930091185,
400
+ "grad_norm": 1.5269972085952759,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 42.7873,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.08358662613981763,
407
+ "grad_norm": 1.5041111707687378,
408
+ "learning_rate": 5e-05,
409
+ "loss": 42.7403,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0851063829787234,
414
+ "grad_norm": 1.5063508749008179,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 42.7848,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.08662613981762918,
421
+ "grad_norm": 1.389691710472107,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 42.7435,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.08814589665653495,
428
+ "grad_norm": 1.4456936120986938,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 42.6884,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08966565349544073,
435
+ "grad_norm": 1.3679536581039429,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 42.6868,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0911854103343465,
442
+ "grad_norm": 1.297853946685791,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 42.7028,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.09270516717325228,
449
+ "grad_norm": 1.2528061866760254,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 42.6757,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.09422492401215805,
456
+ "grad_norm": 1.2463070154190063,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 42.7206,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.09574468085106383,
463
+ "grad_norm": 1.2156941890716553,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 42.6653,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0972644376899696,
470
+ "grad_norm": 1.2177422046661377,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 42.6178,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.09878419452887538,
477
+ "grad_norm": 1.1524884700775146,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 42.6053,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.10030395136778116,
484
+ "grad_norm": 1.1051671504974365,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 42.6853,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.10182370820668693,
491
+ "grad_norm": 1.069922685623169,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 42.6521,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.1033434650455927,
498
+ "grad_norm": 1.0806479454040527,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 42.6595,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.10486322188449848,
505
+ "grad_norm": 1.1521317958831787,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 42.6343,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.10638297872340426,
512
+ "grad_norm": 1.2330914735794067,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 42.6126,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.10790273556231003,
519
+ "grad_norm": 1.2084128856658936,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 42.57,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.1094224924012158,
526
+ "grad_norm": 1.0930789709091187,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 42.609,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.11094224924012158,
533
+ "grad_norm": 1.0117900371551514,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 42.6595,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.11246200607902736,
540
+ "grad_norm": 1.211604118347168,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 42.6429,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.11398176291793313,
547
+ "grad_norm": 1.430601716041565,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 42.5467,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.11550151975683891,
554
+ "grad_norm": 1.2758630514144897,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 42.6039,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.11702127659574468,
561
+ "grad_norm": 1.0489394664764404,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 42.5928,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.11854103343465046,
568
+ "grad_norm": 1.3841549158096313,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 42.5912,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.12006079027355623,
575
+ "grad_norm": 1.5512932538986206,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 42.5429,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.12158054711246201,
582
+ "grad_norm": 1.3741813898086548,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 42.5487,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.12310030395136778,
589
+ "grad_norm": 1.1332428455352783,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 42.6317,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.12462006079027356,
596
+ "grad_norm": 1.4934285879135132,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 42.533,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.12613981762917933,
603
+ "grad_norm": 1.4491100311279297,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 42.5128,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.1276595744680851,
610
+ "grad_norm": 1.6558226346969604,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 42.4972,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.12917933130699089,
617
+ "grad_norm": 1.6108096837997437,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 42.4374,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.13069908814589665,
624
+ "grad_norm": 1.3853203058242798,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 42.5671,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.13221884498480244,
631
+ "grad_norm": 1.7137513160705566,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 42.4684,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.1337386018237082,
638
+ "grad_norm": 1.5326465368270874,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 42.4793,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.135258358662614,
645
+ "grad_norm": 1.5756134986877441,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 42.4665,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.13677811550151975,
652
+ "grad_norm": 1.8401323556900024,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 42.4228,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.13829787234042554,
659
+ "grad_norm": 2.1934590339660645,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 42.5021,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1398176291793313,
666
+ "grad_norm": 4.079236030578613,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 42.6783,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.1413373860182371,
673
+ "grad_norm": 4.929635047912598,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 42.678,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.14285714285714285,
680
+ "grad_norm": 4.8210248947143555,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 42.6223,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.14437689969604864,
687
+ "grad_norm": 4.764625549316406,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 42.6935,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.1458966565349544,
694
+ "grad_norm": 4.984578609466553,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 42.5576,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.1474164133738602,
701
+ "grad_norm": 5.2452263832092285,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 42.6357,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.14893617021276595,
708
+ "grad_norm": 5.212264060974121,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 42.4783,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.15045592705167174,
715
+ "grad_norm": 4.950127601623535,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 42.6065,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.1519756838905775,
722
+ "grad_norm": 6.176753997802734,
723
+ "learning_rate": 0.0,
724
+ "loss": 42.3882,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.1519756838905775,
729
+ "eval_loss": 10.644861221313477,
730
+ "eval_runtime": 2.3512,
731
+ "eval_samples_per_second": 471.254,
732
+ "eval_steps_per_second": 59.119,
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": 12003418570752.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null