aleegis12 commited on
Commit
7eb033f
·
verified ·
1 Parent(s): 00f44a1

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 sha256:3d21a9530841d39ff310ecdd70d886a2201d4dde653d7c720a30d968a9eccd5e
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ef4549e4aec297dd7f2c2a33b953b288178cfe5696724059ccac292ec00b178
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e93cb98d72fba2525cb2b0feb7efe62554a95138761fd60dd2a6fab029cc271a
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56236b001fec6f6fe36996f9604de97abc40b2b18d506842e3a2d811096fbe81
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9b22770a3309ed65df5a1866c29e5edaf89d9b51efc9be6239e9bea663eae7e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8066681b3d0c293501d378f7a598a067c188b166fec80ddfc9caa3dd5141287
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": 0.8842460513114929,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.03139224611520954,
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": 31.786,
374
  "eval_steps_per_second": 7.949,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.421956217831424e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8422326445579529,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06278449223041908,
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": 31.786,
374
  "eval_steps_per_second": 7.949,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.032020091037513736,
379
+ "grad_norm": 0.3064557909965515,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.5255,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03264793595981792,
386
+ "grad_norm": 0.5814394354820251,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.5061,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.033275780882122116,
393
+ "grad_norm": 0.3637872338294983,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.6412,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03390362580442631,
400
+ "grad_norm": 0.4275180399417877,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.7904,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0345314707267305,
407
+ "grad_norm": 0.3474939167499542,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.7238,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.03515931564903469,
414
+ "grad_norm": 0.3170601427555084,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.7328,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03578716057133888,
421
+ "grad_norm": 0.3025910556316376,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.7229,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.03641500549364307,
428
+ "grad_norm": 0.33307960629463196,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.7689,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03704285041594726,
435
+ "grad_norm": 0.3866959810256958,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.7089,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03767069533825145,
442
+ "grad_norm": 0.3711072504520416,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.711,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.038298540260555645,
449
+ "grad_norm": 0.3593451976776123,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.7486,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.03892638518285983,
456
+ "grad_norm": 0.34750768542289734,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.8219,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.039554230105164026,
463
+ "grad_norm": 0.32483235001564026,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.7605,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.04018207502746821,
470
+ "grad_norm": 0.3605320155620575,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.9071,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.04080991994977241,
477
+ "grad_norm": 0.3330734968185425,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.767,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0414377648720766,
484
+ "grad_norm": 0.3530653119087219,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.811,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.04206560979438079,
491
+ "grad_norm": 0.37905681133270264,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.8761,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.04269345471668498,
498
+ "grad_norm": 0.38746708631515503,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.8722,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.04332129963898917,
505
+ "grad_norm": 0.40445587038993835,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.8652,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.04394914456129336,
512
+ "grad_norm": 0.3931260406970978,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.8637,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04457698948359755,
519
+ "grad_norm": 0.38505905866622925,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.778,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04520483440590174,
526
+ "grad_norm": 0.41518208384513855,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.7828,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.045832679328205936,
533
+ "grad_norm": 0.4309608042240143,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.9456,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04646052425051012,
540
+ "grad_norm": 0.4033466577529907,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.8607,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.047088369172814316,
547
+ "grad_norm": 0.4080653488636017,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.8547,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0477162140951185,
554
+ "grad_norm": 0.45925450325012207,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.7668,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0483440590174227,
561
+ "grad_norm": 0.4721239507198334,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.7897,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.04897190393972689,
568
+ "grad_norm": 0.4305371046066284,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.8035,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.04959974886203108,
575
+ "grad_norm": 0.4776322841644287,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.8277,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05022759378433527,
582
+ "grad_norm": 0.4314558804035187,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.7437,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05085543870663946,
589
+ "grad_norm": 0.49073314666748047,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.789,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.05148328362894365,
596
+ "grad_norm": 0.46452414989471436,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.7861,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.05211112855124784,
603
+ "grad_norm": 0.46071621775627136,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.841,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.05273897347355203,
610
+ "grad_norm": 0.5624316930770874,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.8978,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.053366818395856226,
617
+ "grad_norm": 0.5588775277137756,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.9293,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.05399466331816041,
624
+ "grad_norm": 0.5270624160766602,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.7834,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.05462250824046461,
631
+ "grad_norm": 0.49282562732696533,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.8024,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.055250353162768794,
638
+ "grad_norm": 0.6458669304847717,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.9619,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.05587819808507299,
645
+ "grad_norm": 0.6261863708496094,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.8275,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.05650604300737718,
652
+ "grad_norm": 0.6104888319969177,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.8617,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.05713388792968137,
659
+ "grad_norm": 0.6412619352340698,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.7762,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.05776173285198556,
666
+ "grad_norm": 0.6976544857025146,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.9369,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.05838957777428975,
673
+ "grad_norm": 0.8839225172996521,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.8236,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.05901742269659394,
680
+ "grad_norm": 0.7913328409194946,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.0054,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.05964526761889813,
687
+ "grad_norm": 0.9896240830421448,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.159,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.06027311254120232,
694
+ "grad_norm": 1.0347424745559692,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.9988,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.060900957463506517,
701
+ "grad_norm": 0.9619345664978027,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.0012,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0615288023858107,
708
+ "grad_norm": 1.298412561416626,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.9692,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0621566473081149,
715
+ "grad_norm": 1.2043523788452148,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.0544,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06278449223041908,
722
+ "grad_norm": 1.8621759414672852,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.8761,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06278449223041908,
729
+ "eval_loss": 0.8422326445579529,
730
+ "eval_runtime": 84.22,
731
+ "eval_samples_per_second": 31.857,
732
+ "eval_steps_per_second": 7.967,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.85751967219712e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null