prxy5605 commited on
Commit
5b196fc
·
verified ·
1 Parent(s): 8d0d70f

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 sha256:263ab552c533cd67b0b267a268e7a2f1c986037d315198e34972fcd5bc018833
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049dbea609070280cf454ceb76803a70be8cd747b965377d942b7a02d01e2a47
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed5aebbc4a6149130eae1cda8ac3e88c5494e8b866091eec15d6e2e6d4325384
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85950f08dd7b1ef54bc09315daa841822d3613bd9e9fac611b752f0ccd048b89
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4c978271bc337b9c3efe273e9dac7c6660a3a2100898e3f930187ac11cb3bd4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba69f4e2d66a42dbdfdbf3816dc82ae6c726a7187dae1cbbac71c03486c13dd
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": 1.6608927249908447,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.3952569169960474,
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": 44.249,
374
  "eval_steps_per_second": 11.218,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 5197404435382272.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.644432544708252,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.7905138339920948,
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": 44.249,
374
  "eval_steps_per_second": 11.218,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.4031620553359684,
379
+ "grad_norm": 0.8258354067802429,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.7065,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.41106719367588934,
386
+ "grad_norm": 0.7727131843566895,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.7414,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.4189723320158103,
393
+ "grad_norm": 0.767753541469574,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.6911,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.4268774703557312,
400
+ "grad_norm": 0.896858274936676,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.8343,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.43478260869565216,
407
+ "grad_norm": 0.8155654072761536,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.7718,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.4426877470355731,
414
+ "grad_norm": 0.8962050080299377,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.7042,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.4505928853754941,
421
+ "grad_norm": 0.8581175208091736,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.7504,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.45849802371541504,
428
+ "grad_norm": 0.948732852935791,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.8929,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.466403162055336,
435
+ "grad_norm": 0.9872562289237976,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.7411,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.4743083003952569,
442
+ "grad_norm": 1.1096147298812866,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.7791,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.48221343873517786,
449
+ "grad_norm": 1.0001335144042969,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.7769,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.4901185770750988,
456
+ "grad_norm": 1.14747953414917,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.8926,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.4980237154150198,
463
+ "grad_norm": 0.8204768300056458,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.4519,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.5059288537549407,
470
+ "grad_norm": 0.7378841042518616,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.5685,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.5138339920948617,
477
+ "grad_norm": 0.7584918141365051,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.6277,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.5217391304347826,
484
+ "grad_norm": 0.6478469967842102,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.6634,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.5296442687747036,
491
+ "grad_norm": 0.621213436126709,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.7036,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.5375494071146245,
498
+ "grad_norm": 0.6001406311988831,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.7276,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.5454545454545454,
505
+ "grad_norm": 0.6318312287330627,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.7278,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.5533596837944664,
512
+ "grad_norm": 0.6229626536369324,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.6364,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.5612648221343873,
519
+ "grad_norm": 0.6349075436592102,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.6318,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.5691699604743083,
526
+ "grad_norm": 0.6748497486114502,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.5987,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.5770750988142292,
533
+ "grad_norm": 0.7020136117935181,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.7664,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.5849802371541502,
540
+ "grad_norm": 0.6632049083709717,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.6788,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.5928853754940712,
547
+ "grad_norm": 0.6933974623680115,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.7321,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.6007905138339921,
554
+ "grad_norm": 0.6252143979072571,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.6356,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.6086956521739131,
561
+ "grad_norm": 0.6765616536140442,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.6761,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.616600790513834,
568
+ "grad_norm": 0.6760627627372742,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.7556,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.6245059288537549,
575
+ "grad_norm": 0.7049459218978882,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.7011,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.6324110671936759,
582
+ "grad_norm": 0.7250329852104187,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.8144,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.6403162055335968,
589
+ "grad_norm": 0.7103596329689026,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.6611,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.6482213438735178,
596
+ "grad_norm": 0.7164954543113708,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.6305,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.6561264822134387,
603
+ "grad_norm": 0.7123523950576782,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.6529,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.6640316205533597,
610
+ "grad_norm": 0.7113423943519592,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.6658,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.6719367588932806,
617
+ "grad_norm": 0.7906448841094971,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.7731,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.6798418972332015,
624
+ "grad_norm": 0.8516830801963806,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.755,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.6877470355731226,
631
+ "grad_norm": 0.8049620985984802,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.7237,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.6956521739130435,
638
+ "grad_norm": 0.8168877363204956,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.7243,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.7035573122529645,
645
+ "grad_norm": 0.8963014483451843,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.6904,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.7114624505928854,
652
+ "grad_norm": 0.9513223171234131,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.7241,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.7193675889328063,
659
+ "grad_norm": 0.8429911136627197,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.7412,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.7272727272727273,
666
+ "grad_norm": 0.9856913089752197,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.7932,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.7351778656126482,
673
+ "grad_norm": 1.2035722732543945,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.7209,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.7430830039525692,
680
+ "grad_norm": 0.7656598091125488,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.6114,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.7509881422924901,
687
+ "grad_norm": 0.7776647806167603,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.5802,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.758893280632411,
694
+ "grad_norm": 0.6927933096885681,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.6236,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.766798418972332,
701
+ "grad_norm": 0.6408959031105042,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.6836,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.7747035573122529,
708
+ "grad_norm": 0.6113343834877014,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.5781,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.782608695652174,
715
+ "grad_norm": 0.6380818486213684,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.648,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.7905138339920948,
722
+ "grad_norm": 0.6411934494972229,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.6435,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.7905138339920948,
729
+ "eval_loss": 1.644432544708252,
730
+ "eval_runtime": 4.8149,
731
+ "eval_samples_per_second": 44.238,
732
+ "eval_steps_per_second": 11.215,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.0298202840367104e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null