prxy5604 commited on
Commit
d7f069b
·
verified ·
1 Parent(s): 45a6af8

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 sha256:452e202304b9d1dac6968774ea07cc7aa032a0f2df3754163f29a30ae71cadef
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524a5cc780e0811e6ce6daa76a8cc04b7263ecf4404cbb893ef9db34dc591f3b
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ec376b6c762d2089dd40470cefdbe2e0817f44d5a91bce108620305478b79c4
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb0a1ba6d77bfd1739bf2d3607d30be18686f81007b6f81c75094e652f82f75
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82e3d32f76441821e5c7b9a802980840f9cdabad9d97612eaee56f9fa3e68c5b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427a249c7ab3bb51958537e611ce45aeeae32cd3577a564fc3175b678c64adb0
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": 1.3178330659866333,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.024832381425378695,
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": 14.123,
374
  "eval_steps_per_second": 3.531,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.1094434267136e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1517127752304077,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.04966476285075739,
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": 14.123,
374
  "eval_steps_per_second": 3.531,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.025329029053886266,
379
+ "grad_norm": 0.7699626684188843,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.5083,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.02582567668239384,
386
+ "grad_norm": 0.7138668298721313,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.3867,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.026322324310901417,
393
+ "grad_norm": 0.6291865706443787,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.4705,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.02681897193940899,
400
+ "grad_norm": 0.5630155205726624,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.5699,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.027315619567916564,
407
+ "grad_norm": 0.4821169078350067,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.5039,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.027812267196424136,
414
+ "grad_norm": 0.433138906955719,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.4582,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.02830891482493171,
421
+ "grad_norm": 0.5260890126228333,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.6043,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.028805562453439286,
428
+ "grad_norm": 0.5517573356628418,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.5654,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.029302210081946858,
435
+ "grad_norm": 0.600393533706665,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.4487,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.029798857710454433,
442
+ "grad_norm": 0.7480672597885132,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.4586,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.030295505338962008,
449
+ "grad_norm": 0.6679813861846924,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.433,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.03079215296746958,
456
+ "grad_norm": 0.6178227066993713,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.3339,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.031288800595977155,
463
+ "grad_norm": 0.6035674810409546,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.1944,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.03178544822448473,
470
+ "grad_norm": 0.6234647035598755,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.2268,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0322820958529923,
477
+ "grad_norm": 0.533836305141449,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.9784,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.032778743481499874,
484
+ "grad_norm": 0.5882768034934998,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.1539,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.03327539111000745,
491
+ "grad_norm": 0.5902140140533447,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.0234,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.033772038738515024,
498
+ "grad_norm": 0.6430478096008301,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.0089,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.0342686863670226,
505
+ "grad_norm": 0.5851756930351257,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.924,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.034765333995530175,
512
+ "grad_norm": 0.6246961355209351,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.9896,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.03526198162403774,
519
+ "grad_norm": 0.6118877530097961,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.057,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.03575862925254532,
526
+ "grad_norm": 0.5609412789344788,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.8669,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.03625527688105289,
533
+ "grad_norm": 0.665837824344635,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.8946,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.03675192450956047,
540
+ "grad_norm": 0.5841544270515442,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.8691,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.037248572138068044,
547
+ "grad_norm": 0.5716777443885803,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.8131,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.03774521976657561,
554
+ "grad_norm": 0.6754549145698547,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.7617,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.03824186739508319,
561
+ "grad_norm": 0.6692814826965332,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.7152,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.03873851502359076,
568
+ "grad_norm": 0.6564689874649048,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.731,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.03923516265209834,
575
+ "grad_norm": 0.715313732624054,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.8195,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03973181028060591,
582
+ "grad_norm": 0.7216390371322632,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.8461,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.04022845790911348,
589
+ "grad_norm": 0.6340150833129883,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.7147,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.040725105537621056,
596
+ "grad_norm": 0.7452045679092407,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.7916,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.04122175316612863,
603
+ "grad_norm": 0.7581782937049866,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.7201,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.04171840079463621,
610
+ "grad_norm": 0.6914567947387695,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.7289,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.04221504842314378,
617
+ "grad_norm": 0.6274064183235168,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.8794,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.04271169605165135,
624
+ "grad_norm": 0.699798047542572,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.7242,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.043208343680158925,
631
+ "grad_norm": 0.6357870697975159,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.7442,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.0437049913086665,
638
+ "grad_norm": 0.5206896066665649,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.7311,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.044201638937174076,
645
+ "grad_norm": 0.7244934439659119,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.821,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.04469828656568165,
652
+ "grad_norm": 0.5355032682418823,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.6391,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.04519493419418922,
659
+ "grad_norm": 0.5859981775283813,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.6515,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.045691581822696795,
666
+ "grad_norm": 0.5491009950637817,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.713,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.04618822945120437,
673
+ "grad_norm": 0.6121314764022827,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.6565,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.046684877079711945,
680
+ "grad_norm": 0.5150812268257141,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.6781,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.04718152470821952,
687
+ "grad_norm": 0.7124264240264893,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.7438,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.047678172336727095,
694
+ "grad_norm": 0.6848090291023254,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.611,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.048174819965234664,
701
+ "grad_norm": 0.5835926532745361,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.6222,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.04867146759374224,
708
+ "grad_norm": 0.5525482892990112,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.5364,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.049168115222249814,
715
+ "grad_norm": 0.8804473876953125,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.6927,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.04966476285075739,
722
+ "grad_norm": 0.9884843826293945,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.8015,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.04966476285075739,
729
+ "eval_loss": 1.1517127752304077,
730
+ "eval_runtime": 240.2195,
731
+ "eval_samples_per_second": 14.12,
732
+ "eval_steps_per_second": 3.53,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.42188868534272e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null