prxy5604 commited on
Commit
255bf1e
·
verified ·
1 Parent(s): 2f39d3a

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:e3c50d80555159f7437daa41a9d8d03845a5d2cb358ef4b283de308e32933e7d
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa88c949b98ad1431afba1e62e4cdd515cb36e99b4d5d92aa0d106f8c3f1fca
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b21e3d606333f0347de6f6117a1efd64e4dc1b97251dbec75fc355c139f34846
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67b490e3109c41f066faa1e0546061b897cff410a8797a0840f2fa3daf38d2cf
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf24f63f0da8e186436dc358d67802b5cc8bf8cfdb65dcf4abcf58205b353cb9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fa119557e709f25237eb7de58a5e0561b78756f065a809e07702d31bbd62f20
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": 1.043031096458435,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.16339869281045752,
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": 41.706,
374
  "eval_steps_per_second": 10.447,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.226560015171584e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0070159435272217,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.32679738562091504,
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": 41.706,
374
  "eval_steps_per_second": 10.447,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.16666666666666666,
379
+ "grad_norm": 0.1735205352306366,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.1695,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.16993464052287582,
386
+ "grad_norm": 0.17092542350292206,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.1097,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.17320261437908496,
393
+ "grad_norm": 0.18938027322292328,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.1351,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.17647058823529413,
400
+ "grad_norm": 0.13851259648799896,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.1063,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.17973856209150327,
407
+ "grad_norm": 0.13026750087738037,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.0843,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.1830065359477124,
414
+ "grad_norm": 0.11888636648654938,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.0522,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.18627450980392157,
421
+ "grad_norm": 0.11656311899423599,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.0453,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.1895424836601307,
428
+ "grad_norm": 0.12335702031850815,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.0676,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.19281045751633988,
435
+ "grad_norm": 0.1326335370540619,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.0474,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.19607843137254902,
442
+ "grad_norm": 0.13129277527332306,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.0032,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.19934640522875818,
449
+ "grad_norm": 0.1514269858598709,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.0552,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.20261437908496732,
456
+ "grad_norm": 0.14056868851184845,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.0481,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.20588235294117646,
463
+ "grad_norm": 0.13416630029678345,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.075,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.20915032679738563,
470
+ "grad_norm": 0.12393052130937576,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.0622,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.21241830065359477,
477
+ "grad_norm": 0.12092893570661545,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.0363,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.21568627450980393,
484
+ "grad_norm": 0.12079605460166931,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.983,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.21895424836601307,
491
+ "grad_norm": 0.12823984026908875,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.0169,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2222222222222222,
498
+ "grad_norm": 0.13442108035087585,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.9858,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.22549019607843138,
505
+ "grad_norm": 0.12223077565431595,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.9908,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.22875816993464052,
512
+ "grad_norm": 0.12562674283981323,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.0032,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.23202614379084968,
519
+ "grad_norm": 0.1272905319929123,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.9899,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.23529411764705882,
526
+ "grad_norm": 0.12599872052669525,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.0017,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.238562091503268,
533
+ "grad_norm": 0.12577585875988007,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.0255,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.24183006535947713,
540
+ "grad_norm": 0.1293269693851471,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.0599,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.24509803921568626,
547
+ "grad_norm": 0.1317208707332611,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.0217,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.24836601307189543,
554
+ "grad_norm": 0.13466817140579224,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.0332,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.25163398692810457,
561
+ "grad_norm": 0.1261163204908371,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.0222,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.2549019607843137,
568
+ "grad_norm": 0.13361579179763794,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.0189,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.2581699346405229,
575
+ "grad_norm": 0.1298186331987381,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.0339,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.26143790849673204,
582
+ "grad_norm": 0.12694045901298523,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.0672,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.2647058823529412,
589
+ "grad_norm": 0.12448877096176147,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.0152,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.2679738562091503,
596
+ "grad_norm": 0.1287432461977005,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.978,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.27124183006535946,
603
+ "grad_norm": 0.13010282814502716,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.0344,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.27450980392156865,
610
+ "grad_norm": 0.135304257273674,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.9755,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.2777777777777778,
617
+ "grad_norm": 0.1396276205778122,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.9595,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.28104575163398693,
624
+ "grad_norm": 0.13439607620239258,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.0071,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.28431372549019607,
631
+ "grad_norm": 0.1342010796070099,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.9888,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.2875816993464052,
638
+ "grad_norm": 0.13898822665214539,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.0095,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.2908496732026144,
645
+ "grad_norm": 0.13906656205654144,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.0027,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.29411764705882354,
652
+ "grad_norm": 0.13596709072589874,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.9514,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.2973856209150327,
659
+ "grad_norm": 0.14506670832633972,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.9667,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.3006535947712418,
666
+ "grad_norm": 0.15467151999473572,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.0348,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.30392156862745096,
673
+ "grad_norm": 0.1493193507194519,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.9577,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.30718954248366015,
680
+ "grad_norm": 0.14980854094028473,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.9604,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.3104575163398693,
687
+ "grad_norm": 0.16146551072597504,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.0109,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.3137254901960784,
694
+ "grad_norm": 0.1532970815896988,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.0249,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.31699346405228757,
701
+ "grad_norm": 0.1485988050699234,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.9954,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.3202614379084967,
708
+ "grad_norm": 0.1484474092721939,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.9798,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.3235294117647059,
715
+ "grad_norm": 0.16410280764102936,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.964,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.32679738562091504,
722
+ "grad_norm": 0.278840571641922,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.8767,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.32679738562091504,
729
+ "eval_loss": 1.0070159435272217,
730
+ "eval_runtime": 12.3082,
731
+ "eval_samples_per_second": 41.842,
732
+ "eval_steps_per_second": 10.481,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.4637857696055296e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null