0x1202 commited on
Commit
7d98e45
·
verified ·
1 Parent(s): 83d3572

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 sha256:6c72c7020b4c8ec437329aecf2acf3f865d93ea02310629c574e37a5957ffc7f
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031366e2dcddd98a0d6a30b349ef6ab8e5769312122ed9ce32dde45a1986e71f
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df7430003808cfd55293f4aa97f80fdd545d43a9f6f13da595cd9f63f659f5ef
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcb2a54d8ec4ecda1bad9c2fc6bc14133a0f1f5876fc745f54ca17df9fdff0b9
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a5f1f99ef350703e7b225875ce45c2c4be505d4a46404d8d22899e51a510475
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2cf9324f5ca73826e5c9f2c45cac176b672eaa8f31f38db597f7560005f726
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": 0.3110412061214447,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.015844094113919037,
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": 13.59,
374
  "eval_steps_per_second": 3.398,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.719068728773837e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2861791253089905,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.031688188227838074,
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": 13.59,
374
  "eval_steps_per_second": 3.398,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.016160975996197417,
379
+ "grad_norm": 0.09471043199300766,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.1704,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.016477857878475798,
386
+ "grad_norm": 0.10490579158067703,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.1973,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.016794739760754178,
393
+ "grad_norm": 0.11275085806846619,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.2089,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.017111621643032558,
400
+ "grad_norm": 0.09714960306882858,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.1874,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.017428503525310942,
407
+ "grad_norm": 0.10512809455394745,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.1858,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.017745385407589322,
414
+ "grad_norm": 0.10947681963443756,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.2236,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.018062267289867703,
421
+ "grad_norm": 0.10696465522050858,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.2353,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.018379149172146083,
428
+ "grad_norm": 0.12559695541858673,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.251,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.018696031054424463,
435
+ "grad_norm": 0.1162128821015358,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.2488,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.019012912936702844,
442
+ "grad_norm": 0.1090744361281395,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.2398,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.019329794818981224,
449
+ "grad_norm": 0.11116234958171844,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.2555,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.019646676701259604,
456
+ "grad_norm": 0.11902529746294022,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.2682,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.019963558583537985,
463
+ "grad_norm": 0.10772904753684998,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.2352,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.02028044046581637,
470
+ "grad_norm": 0.10973820835351944,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.2369,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.02059732234809475,
477
+ "grad_norm": 0.11814217269420624,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.2524,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.02091420423037313,
484
+ "grad_norm": 0.12398887425661087,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.2532,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.02123108611265151,
491
+ "grad_norm": 0.12989726662635803,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.2718,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.02154796799492989,
498
+ "grad_norm": 0.11946962773799896,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.242,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.02186484987720827,
505
+ "grad_norm": 0.1271256059408188,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.2929,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.02218173175948665,
512
+ "grad_norm": 0.13123860955238342,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.2413,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.02249861364176503,
519
+ "grad_norm": 0.13517530262470245,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.2833,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.022815495524043414,
526
+ "grad_norm": 0.14057579636573792,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.2952,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.023132377406321795,
533
+ "grad_norm": 0.1402745395898819,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.3068,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.023449259288600175,
540
+ "grad_norm": 0.1463419497013092,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.3047,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.023766141170878555,
547
+ "grad_norm": 0.15095284581184387,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.3107,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.024083023053156936,
554
+ "grad_norm": 0.1348758339881897,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.3007,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.024399904935435316,
561
+ "grad_norm": 0.1441372185945511,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.2894,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.024716786817713696,
568
+ "grad_norm": 0.14854104816913605,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.3202,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.025033668699992077,
575
+ "grad_norm": 0.1389545202255249,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.3043,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.025350550582270457,
582
+ "grad_norm": 0.15648682415485382,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.337,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.02566743246454884,
589
+ "grad_norm": 0.14272603392601013,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.3011,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.02598431434682722,
596
+ "grad_norm": 0.15423764288425446,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.3214,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0263011962291056,
603
+ "grad_norm": 0.15417426824569702,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.296,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.026618078111383982,
610
+ "grad_norm": 0.15329402685165405,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.2983,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.026934959993662362,
617
+ "grad_norm": 0.15941715240478516,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.3016,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.027251841875940742,
624
+ "grad_norm": 0.15860851109027863,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.272,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.027568723758219123,
631
+ "grad_norm": 0.16991178691387177,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.3448,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.027885605640497503,
638
+ "grad_norm": 0.1755577027797699,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.3156,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.028202487522775887,
645
+ "grad_norm": 0.1622546762228012,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.3063,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.028519369405054267,
652
+ "grad_norm": 0.17945386469364166,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.3276,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.028836251287332648,
659
+ "grad_norm": 0.18708471953868866,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.325,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.029153133169611028,
666
+ "grad_norm": 0.1904095858335495,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.3476,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.029470015051889408,
673
+ "grad_norm": 0.1793287843465805,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.3423,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.02978689693416779,
680
+ "grad_norm": 0.18426981568336487,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.321,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03010377881644617,
687
+ "grad_norm": 0.20930606126785278,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.3844,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03042066069872455,
694
+ "grad_norm": 0.19688951969146729,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.3542,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03073754258100293,
701
+ "grad_norm": 0.21573825180530548,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.3764,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.031054424463281313,
708
+ "grad_norm": 0.22527675330638885,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.4116,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.031371306345559694,
715
+ "grad_norm": 0.2153525948524475,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.3692,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.031688188227838074,
722
+ "grad_norm": 0.27288129925727844,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.4117,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.031688188227838074,
729
+ "eval_loss": 0.2861791253089905,
730
+ "eval_runtime": 390.5684,
731
+ "eval_samples_per_second": 13.608,
732
+ "eval_steps_per_second": 3.403,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.3438137457547674e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null