prxy5605 commited on
Commit
5dbec1f
·
verified ·
1 Parent(s): f4e5f41

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:f4d716f3ed59f2f8365c5a83288c44f2c6a3497247e0d210db211da8e3457ea6
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f265d20d146f4e7fa4c6f76f80c9c73b1f36dc7254474f156ce6ff3d91b9d486
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43f5f3e41db37e163d460049e7842b891a73ddcbcd37501643f24a7fba868bea
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24182bdb9dd2b3d82b2ed9df6d90296d1464ebb2f1bda4c8022639f4e152b661
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69c32ff4b1846dda8adb32bac70ee2d25a8c5b5a521a5ab02ac03902d636cd53
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23497d4d502105d9b958588fefb577aec8f2e43ebd8ab4f9c721b0a4560d33f0
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": 0.012402563355863094,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.005599260897561522,
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": 13.93,
374
  "eval_steps_per_second": 3.482,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.685806012294758e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.008957763202488422,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.011198521795123043,
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": 13.93,
374
  "eval_steps_per_second": 3.482,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.005711246115512753,
379
+ "grad_norm": 0.08151597529649734,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.0191,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.005823231333463983,
386
+ "grad_norm": 0.043629955500364304,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.0075,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.005935216551415213,
393
+ "grad_norm": 0.07190629094839096,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.008,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.006047201769366443,
400
+ "grad_norm": 0.04685960337519646,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.0116,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.006159186987317674,
407
+ "grad_norm": 0.03496837243437767,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.0115,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0062711722052689045,
414
+ "grad_norm": 0.07295988500118256,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.0077,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.006383157423220135,
421
+ "grad_norm": 0.028815751895308495,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.0068,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.006495142641171366,
428
+ "grad_norm": 0.07860519737005234,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.0067,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.006607127859122596,
435
+ "grad_norm": 0.03098691627383232,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.0046,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.006719113077073826,
442
+ "grad_norm": 0.04155720770359039,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.0056,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.006831098295025056,
449
+ "grad_norm": 0.04726318642497063,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.0063,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.006943083512976287,
456
+ "grad_norm": 0.14553825557231903,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.0127,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.007055068730927518,
463
+ "grad_norm": 0.08409129083156586,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.0119,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.007167053948878748,
470
+ "grad_norm": 0.0558687187731266,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.0062,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.007279039166829979,
477
+ "grad_norm": 0.03517032787203789,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.0069,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.007391024384781209,
484
+ "grad_norm": 0.03434384986758232,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.0029,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.007503009602732439,
491
+ "grad_norm": 0.07082964479923248,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0097,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.007614994820683669,
498
+ "grad_norm": 0.06074490025639534,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.0049,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.0077269800386349004,
505
+ "grad_norm": 0.07937470078468323,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.0132,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.00783896525658613,
512
+ "grad_norm": 0.04968696087598801,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.0064,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.00795095047453736,
519
+ "grad_norm": 0.05936945974826813,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.0067,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.008062935692488591,
526
+ "grad_norm": 0.07118445634841919,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.0124,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.008174920910439821,
533
+ "grad_norm": 0.048843711614608765,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.0106,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.008286906128391053,
540
+ "grad_norm": 0.05531323701143265,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.006,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.008398891346342283,
547
+ "grad_norm": 0.07174713909626007,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.0176,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.008510876564293514,
554
+ "grad_norm": 0.09108234196901321,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.0071,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.008622861782244744,
561
+ "grad_norm": 0.07062532752752304,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.0058,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.008734847000195974,
568
+ "grad_norm": 0.05787373706698418,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.008,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.008846832218147204,
575
+ "grad_norm": 0.07510489225387573,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0067,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.008958817436098434,
582
+ "grad_norm": 0.09543178230524063,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.0126,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.009070802654049666,
589
+ "grad_norm": 0.08685528486967087,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.0086,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.009182787872000896,
596
+ "grad_norm": 0.049802061170339584,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.009,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.009294773089952127,
603
+ "grad_norm": 0.03666006773710251,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.0083,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.009406758307903357,
610
+ "grad_norm": 0.06713581085205078,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.0053,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.009518743525854587,
617
+ "grad_norm": 0.12403149157762527,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.0145,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.009630728743805817,
624
+ "grad_norm": 0.1675027757883072,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0113,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.009742713961757047,
631
+ "grad_norm": 0.10205962508916855,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0108,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.00985469917970828,
638
+ "grad_norm": 0.09269709140062332,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.0051,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.00996668439765951,
645
+ "grad_norm": 0.17211325466632843,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.0277,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.01007866961561074,
652
+ "grad_norm": 0.4585292935371399,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.0204,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.01019065483356197,
659
+ "grad_norm": 0.23112568259239197,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0084,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0103026400515132,
666
+ "grad_norm": 0.09548697620630264,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.0113,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.01041462526946443,
673
+ "grad_norm": 0.10480192303657532,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.0196,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.01052661048741566,
680
+ "grad_norm": 0.053521186113357544,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0035,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.010638595705366892,
687
+ "grad_norm": 0.12508662045001984,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0046,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.010750580923318123,
694
+ "grad_norm": 0.07000123709440231,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0089,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.010862566141269353,
701
+ "grad_norm": 0.13927717506885529,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0225,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.010974551359220583,
708
+ "grad_norm": 0.36776211857795715,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0061,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.011086536577171813,
715
+ "grad_norm": 0.11161035299301147,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.0117,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.011198521795123043,
722
+ "grad_norm": 0.10862310975790024,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0104,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.011198521795123043,
729
+ "eval_loss": 0.008957763202488422,
730
+ "eval_runtime": 1080.5124,
731
+ "eval_samples_per_second": 13.919,
732
+ "eval_steps_per_second": 3.48,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.3371612024589517e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null