prxy5607 commited on
Commit
5c8f555
·
verified ·
1 Parent(s): b2a67b8

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 sha256:1181105d75a9a8d6a7037dd0987ae1a3535beafd7d3b5cb10cb4586801a74ca8
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4afe94a99101c0ef1e8328a92221d48c4dd1f4b9e05d13bd9a0fa0e7133706d
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:278263a9978d491d71c115dac72e2f8e70822836bdc3c3f396bffc380f7bb5bf
3
  size 463916180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b789cbf94346c0f934bb43bda36fe8c3c9e2aff8ef075eeb90551542b2bc7e4
3
  size 463916180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1172561353f385bb1e51804996ea8c44517ce2ac62ca4cd0b22e3b77d0c30ca1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95bf27e4c54eae74106423ad909d78cd68ecd3141cff730f14635eff50f0d401
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": 1.0742619037628174,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.32051282051282054,
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": 9.312,
374
  "eval_steps_per_second": 2.337,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.16045503266816e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9980463981628418,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.6410256410256411,
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": 9.312,
374
  "eval_steps_per_second": 2.337,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3269230769230769,
379
+ "grad_norm": 3.3093056678771973,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 3.9733,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.3333333333333333,
386
+ "grad_norm": 3.6032257080078125,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 4.1736,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.33974358974358976,
393
+ "grad_norm": 3.5169215202331543,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 4.7065,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.34615384615384615,
400
+ "grad_norm": 3.892195463180542,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 3.6555,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.3525641025641026,
407
+ "grad_norm": 3.566694736480713,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.4694,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.358974358974359,
414
+ "grad_norm": 3.5258185863494873,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 4.0258,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.36538461538461536,
421
+ "grad_norm": 3.711472988128662,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 3.9599,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.3717948717948718,
428
+ "grad_norm": 3.8064444065093994,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 4.0288,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.3782051282051282,
435
+ "grad_norm": 4.256228446960449,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 4.2489,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.38461538461538464,
442
+ "grad_norm": 3.41007924079895,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 3.6778,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.391025641025641,
449
+ "grad_norm": 4.161782264709473,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 3.8408,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.3974358974358974,
456
+ "grad_norm": 4.120133876800537,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 3.8373,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.40384615384615385,
463
+ "grad_norm": 3.7649734020233154,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 3.8083,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.41025641025641024,
470
+ "grad_norm": 3.989408016204834,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 3.7964,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.4166666666666667,
477
+ "grad_norm": 4.099987030029297,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 3.8704,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.4230769230769231,
484
+ "grad_norm": 4.085524082183838,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 3.7143,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.42948717948717946,
491
+ "grad_norm": 5.65880823135376,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 3.625,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.4358974358974359,
498
+ "grad_norm": 4.0476393699646,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 3.6684,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.4423076923076923,
505
+ "grad_norm": 4.744653224945068,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 3.4566,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.44871794871794873,
512
+ "grad_norm": 4.958125114440918,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 4.0852,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.4551282051282051,
519
+ "grad_norm": 6.67598819732666,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 3.5015,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.46153846153846156,
526
+ "grad_norm": 5.2367706298828125,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 3.952,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.46794871794871795,
533
+ "grad_norm": 4.691414833068848,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 3.2776,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.47435897435897434,
540
+ "grad_norm": 5.058370113372803,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 3.6019,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.4807692307692308,
547
+ "grad_norm": 5.959715843200684,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 3.5346,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.48717948717948717,
554
+ "grad_norm": 10.346742630004883,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 4.6809,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.4935897435897436,
561
+ "grad_norm": 11.073515892028809,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 6.4677,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5,
568
+ "grad_norm": 9.660663604736328,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 5.9138,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5064102564102564,
575
+ "grad_norm": 7.799278259277344,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 5.3653,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.5128205128205128,
582
+ "grad_norm": 7.223135471343994,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 5.1873,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.5192307692307693,
589
+ "grad_norm": 5.180141925811768,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 4.6571,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.5256410256410257,
596
+ "grad_norm": 3.5540072917938232,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 4.1324,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.532051282051282,
603
+ "grad_norm": 2.854039430618286,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 4.1329,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.5384615384615384,
610
+ "grad_norm": 3.3957605361938477,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 4.7686,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5448717948717948,
617
+ "grad_norm": 3.0800118446350098,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 4.3467,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.5512820512820513,
624
+ "grad_norm": 3.383251428604126,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 4.4548,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.5576923076923077,
631
+ "grad_norm": 3.3952181339263916,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 4.0999,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.5641025641025641,
638
+ "grad_norm": 3.5181736946105957,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 4.7229,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.5705128205128205,
645
+ "grad_norm": 3.4152626991271973,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 3.8945,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.5769230769230769,
652
+ "grad_norm": 3.2614777088165283,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 3.7917,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.5833333333333334,
659
+ "grad_norm": 3.2620959281921387,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 3.7493,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.5897435897435898,
666
+ "grad_norm": 3.280299186706543,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 3.8057,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.5961538461538461,
673
+ "grad_norm": 3.3490095138549805,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 4.0438,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.6025641025641025,
680
+ "grad_norm": 3.555368423461914,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 3.5393,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.6089743589743589,
687
+ "grad_norm": 3.605402946472168,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 3.8683,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.6153846153846154,
694
+ "grad_norm": 3.5116748809814453,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 3.9831,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.6217948717948718,
701
+ "grad_norm": 3.322603702545166,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 3.9772,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.6282051282051282,
708
+ "grad_norm": 3.720085620880127,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 3.6853,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.6346153846153846,
715
+ "grad_norm": 3.5957906246185303,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 3.8104,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.6410256410256411,
722
+ "grad_norm": 3.5254197120666504,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 3.6103,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.6410256410256411,
729
+ "eval_loss": 0.9980463981628418,
730
+ "eval_runtime": 28.245,
731
+ "eval_samples_per_second": 9.311,
732
+ "eval_steps_per_second": 2.337,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.32091006533632e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null