aleegis12 commited on
Commit
903384f
·
verified ·
1 Parent(s): c8a6bdc

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 sha256:3fba8889ce19886b853fea6f803e64190bad559245d4085455bc428e415e535f
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a901f9b5a48cb89b5f753d93e9a286ba99a9281a892b9d5e39622dcbf4fae137
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b0b95f94d72a6b6c5b17f0f928dc6c2768a3d85d6c08190b78979f2039ca6e3
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499aaf9ff3577caedfed184d0364e2709fdc20c401ebb31924ce29eaa84671f8
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:238b75d9a3993eb4b3f9720f8df288eb7813094d3ffbbb0bf44bf4b0e703c99c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ab0fc84e4d00f965e90b1cd4c67b2c6f6167c43fe5f0e7e71a710dab3ec396
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": 0.17040474712848663,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.01615639389288311,
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": 14.237,
374
  "eval_steps_per_second": 3.561,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.685741265662771e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.10626650601625443,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.03231278778576622,
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": 14.237,
374
  "eval_steps_per_second": 3.561,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.01647952177074077,
379
+ "grad_norm": 1.1109765768051147,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.2743,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.01680264964859843,
386
+ "grad_norm": 0.7078374028205872,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.1849,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.017125777526456096,
393
+ "grad_norm": 0.6006873846054077,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.1704,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.017448905404313757,
400
+ "grad_norm": 0.46824806928634644,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.1408,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.017772033282171418,
407
+ "grad_norm": 0.607595682144165,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.156,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.018095161160029082,
414
+ "grad_norm": 0.6533870697021484,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.1558,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.018418289037886743,
421
+ "grad_norm": 0.5653566122055054,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.1519,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.018741416915744404,
428
+ "grad_norm": 0.5329752564430237,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.1414,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01906454479360207,
435
+ "grad_norm": 0.4753928482532501,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.1466,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.01938767267145973,
442
+ "grad_norm": 0.41759729385375977,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.1502,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.01971080054931739,
449
+ "grad_norm": 0.4564923942089081,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.1302,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.020033928427175055,
456
+ "grad_norm": 0.5023769736289978,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.1304,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.020357056305032716,
463
+ "grad_norm": 0.4274086654186249,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.11,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.020680184182890377,
470
+ "grad_norm": 0.48943373560905457,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.1195,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.02100331206074804,
477
+ "grad_norm": 1.2140369415283203,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.0953,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.021326439938605703,
484
+ "grad_norm": 0.6015234589576721,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.1819,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.021649567816463364,
491
+ "grad_norm": 1.5427082777023315,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0892,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.021972695694321028,
498
+ "grad_norm": 0.4848945438861847,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.1304,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.02229582357217869,
505
+ "grad_norm": 0.3890538215637207,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.0753,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.02261895145003635,
512
+ "grad_norm": 0.5242356657981873,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.1413,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.022942079327894015,
519
+ "grad_norm": 0.4723387658596039,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.1146,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.023265207205751676,
526
+ "grad_norm": 0.3772827982902527,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.1061,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.023588335083609337,
533
+ "grad_norm": 0.4396408498287201,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.0924,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.023911462961467,
540
+ "grad_norm": 0.4412914216518402,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.0936,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.024234590839324662,
547
+ "grad_norm": 0.4144344925880432,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.0926,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.024557718717182327,
554
+ "grad_norm": 0.4863596260547638,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.1267,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.024880846595039988,
561
+ "grad_norm": 0.5235720276832581,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.1202,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.02520397447289765,
568
+ "grad_norm": 0.3919348120689392,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.0956,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.025527102350755313,
575
+ "grad_norm": 0.2920311987400055,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0746,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.025850230228612974,
582
+ "grad_norm": 0.4613044857978821,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.1015,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.026173358106470635,
589
+ "grad_norm": 0.36731651425361633,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.1003,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0264964859843283,
596
+ "grad_norm": 0.36551782488822937,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.0575,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.02681961386218596,
603
+ "grad_norm": 0.3591379225254059,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.0833,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.02714274174004362,
610
+ "grad_norm": 0.4948481321334839,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.0945,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.027465869617901286,
617
+ "grad_norm": 0.49430689215660095,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.0905,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.027788997495758947,
624
+ "grad_norm": 0.5038220286369324,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0766,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.028112125373616608,
631
+ "grad_norm": 0.46767106652259827,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0918,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.028435253251474273,
638
+ "grad_norm": 0.47734349966049194,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.1032,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.028758381129331934,
645
+ "grad_norm": 0.4050719439983368,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.0775,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.029081509007189595,
652
+ "grad_norm": 0.7349752187728882,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.0959,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.02940463688504726,
659
+ "grad_norm": 0.444937139749527,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0964,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.02972776476290492,
666
+ "grad_norm": 0.5027516484260559,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.0859,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03005089264076258,
673
+ "grad_norm": 0.5471087098121643,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.11,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.030374020518620246,
680
+ "grad_norm": 0.5404782891273499,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.1233,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.030697148396477907,
687
+ "grad_norm": 0.37752440571784973,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0596,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.031020276274335568,
694
+ "grad_norm": 0.4467316269874573,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0649,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03134340415219323,
701
+ "grad_norm": 0.4350702166557312,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0673,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.03166653203005089,
708
+ "grad_norm": 0.34127622842788696,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0622,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03198965990790856,
715
+ "grad_norm": 0.5703495740890503,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.0712,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.03231278778576622,
722
+ "grad_norm": 0.6635679006576538,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0926,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.03231278778576622,
729
+ "eval_loss": 0.10626650601625443,
730
+ "eval_runtime": 366.3307,
731
+ "eval_samples_per_second": 14.23,
732
+ "eval_steps_per_second": 3.56,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.3338220136969011e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null