prxy5606 commited on
Commit
4f5c701
·
verified ·
1 Parent(s): f4f7f37

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 sha256:6f8491ab3e38c7d8206be32ce0567d9ad12f1b90e49981db8d1feeb4c3f79b13
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43514243f0d1a6bc3b62b96c755bfcd1d607c660851d686763023dc0a6673006
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb78f7c0a1850ea5eb1ed0d692caa044804dde7e3db2dda8b1ed03996b024b2a
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ddc1730b4692a1abb339055142d0589d0682cc7e5ffb43f9ce80e88917dc219
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e91bd06a16b07862657553736cc473f2e18d1747d1792ca02435904d7906f422
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a7e98aac83f3b15bf3ef7368a063caac1bb3f5421854f548e2a5396463408bd
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": 0.29323455691337585,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0042788986114974,
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": 13.105,
374
  "eval_steps_per_second": 3.277,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.54256789372928e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.09263816475868225,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0085577972229948,
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": 13.105,
374
  "eval_steps_per_second": 3.277,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0043644765837273485,
379
+ "grad_norm": 2.4326767921447754,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.4022,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.004450054555957297,
386
+ "grad_norm": 1.9868508577346802,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.2928,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.004535632528187244,
393
+ "grad_norm": 1.331284999847412,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.1449,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.004621210500417193,
400
+ "grad_norm": 0.5776102542877197,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.0617,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.004706788472647141,
407
+ "grad_norm": 2.261007070541382,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.225,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0047923664448770885,
414
+ "grad_norm": 1.6656039953231812,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.1828,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.004877944417107037,
421
+ "grad_norm": 1.5622031688690186,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.1436,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.004963522389336984,
428
+ "grad_norm": 0.4732876718044281,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.0701,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.005049100361566933,
435
+ "grad_norm": 0.6526130437850952,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.0704,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.005134678333796881,
442
+ "grad_norm": 0.9172316193580627,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.081,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.005220256306026828,
449
+ "grad_norm": 0.7165319323539734,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.0599,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.005305834278256777,
456
+ "grad_norm": 1.2434439659118652,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.0907,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.005391412250486725,
463
+ "grad_norm": 1.8290995359420776,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.1152,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0054769902227166725,
470
+ "grad_norm": 0.6257376074790955,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.0532,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.005562568194946621,
477
+ "grad_norm": 1.2729533910751343,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.0639,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.005648146167176568,
484
+ "grad_norm": 0.9542877674102783,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.0606,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.005733724139406517,
491
+ "grad_norm": 0.8180510997772217,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0785,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.005819302111636465,
498
+ "grad_norm": 0.5551479458808899,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.0288,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.0059048800838664125,
505
+ "grad_norm": 0.6363096833229065,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.0407,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.005990458056096361,
512
+ "grad_norm": 0.773931086063385,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.0659,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.006076036028326309,
519
+ "grad_norm": 1.042119026184082,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.0502,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.006161614000556257,
526
+ "grad_norm": 0.7260262966156006,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.0437,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.006247191972786205,
533
+ "grad_norm": 0.5678524374961853,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.0399,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.006332769945016153,
540
+ "grad_norm": 0.7263334393501282,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.0523,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.006418347917246101,
547
+ "grad_norm": 0.3313182294368744,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.0393,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.006503925889476049,
554
+ "grad_norm": 0.3484734892845154,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.0418,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0065895038617059965,
561
+ "grad_norm": 0.47232550382614136,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.0432,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.006675081833935945,
568
+ "grad_norm": 0.8112048506736755,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.0743,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.006760659806165893,
575
+ "grad_norm": 0.51592618227005,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0641,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.006846237778395841,
582
+ "grad_norm": 0.3841154873371124,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.0498,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.006931815750625789,
589
+ "grad_norm": 1.377824068069458,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.0608,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.007017393722855737,
596
+ "grad_norm": 0.7310321927070618,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.0606,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.007102971695085685,
603
+ "grad_norm": 0.6445568203926086,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.0613,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.007188549667315633,
610
+ "grad_norm": 0.586155116558075,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.0583,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.007274127639545581,
617
+ "grad_norm": 0.48145791888237,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.0457,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.007359705611775529,
624
+ "grad_norm": 0.5043821930885315,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0531,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.007445283584005477,
631
+ "grad_norm": 0.42169609665870667,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0581,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.007530861556235425,
638
+ "grad_norm": 0.760418713092804,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.0568,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.007616439528465373,
645
+ "grad_norm": 0.6648797988891602,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.0403,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.007702017500695321,
652
+ "grad_norm": 0.46584442257881165,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.0446,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.007787595472925269,
659
+ "grad_norm": 0.5709188580513,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0643,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.007873173445155217,
666
+ "grad_norm": 0.7237929105758667,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.0586,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.007958751417385165,
673
+ "grad_norm": 0.4494575560092926,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.0617,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.008044329389615114,
680
+ "grad_norm": 2.223395347595215,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0576,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.008129907361845061,
687
+ "grad_norm": 0.8537086844444275,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0348,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.008215485334075009,
694
+ "grad_norm": 0.556140124797821,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0418,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.008301063306304956,
701
+ "grad_norm": 0.4685639441013336,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0378,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.008386641278534905,
708
+ "grad_norm": 0.5281150937080383,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0541,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.008472219250764853,
715
+ "grad_norm": 0.3150881230831146,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.0548,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0085577972229948,
722
+ "grad_norm": 0.96101313829422,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0488,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0085577972229948,
729
+ "eval_loss": 0.09263816475868225,
730
+ "eval_runtime": 1501.1983,
731
+ "eval_samples_per_second": 13.11,
732
+ "eval_steps_per_second": 3.278,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null