prxy5604 commited on
Commit
2ee727c
·
verified ·
1 Parent(s): a3c180c

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 sha256:1d5e1d9b54a0d5d0b7ae8c63c19ce3f807c1f554a53ba4430778967421de7c1a
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8d8ca7b23a1c428af793a87a537ac9d3f23b95daa686a75a7c00f0500ff079d
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:924e94debb2db2c61711c60aa873bf6f22077c47c881b7028657b9a2af34d951
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7edafa7c43ad59f03c50520d727154931ffd64527eadafa202a7e11508f1313e
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61a1b580ba639beebafd8fffa0dc7cb727f86689732f14f59b9d2e8a590d3e9b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e31e37afd19c26fe63a4fe0cf95fe7e01d072d7e4539409bdd070401a42711
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": 1.6694526672363281,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.07122507122507123,
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": 22.414,
374
  "eval_steps_per_second": 5.613,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.0821993309863936e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5963640213012695,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.14245014245014245,
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": 22.414,
374
  "eval_steps_per_second": 5.613,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07264957264957266,
379
+ "grad_norm": 1.8794810771942139,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.2168,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07407407407407407,
386
+ "grad_norm": 2.151414632797241,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.4221,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0754985754985755,
393
+ "grad_norm": 1.6555006504058838,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.3112,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.07692307692307693,
400
+ "grad_norm": 1.2223625183105469,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.1976,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.07834757834757834,
407
+ "grad_norm": 1.0195894241333008,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.2126,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.07977207977207977,
414
+ "grad_norm": 0.7386775612831116,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.1169,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0811965811965812,
421
+ "grad_norm": 0.6235164403915405,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.0829,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.08262108262108261,
428
+ "grad_norm": 0.6764860153198242,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.1481,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08404558404558404,
435
+ "grad_norm": 0.7909321188926697,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.1837,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.08547008547008547,
442
+ "grad_norm": 0.843760073184967,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.2104,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0868945868945869,
449
+ "grad_norm": 0.8562942147254944,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.1524,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.08831908831908832,
456
+ "grad_norm": 0.843786895275116,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.1703,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.08974358974358974,
463
+ "grad_norm": 0.7898869514465332,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.1328,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.09116809116809117,
470
+ "grad_norm": 0.768024742603302,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.1505,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.09259259259259259,
477
+ "grad_norm": 0.7674038410186768,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.1166,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.09401709401709402,
484
+ "grad_norm": 0.7880211472511292,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.0265,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.09544159544159544,
491
+ "grad_norm": 0.8146145939826965,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.0635,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.09686609686609686,
498
+ "grad_norm": 0.8939031958580017,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.0924,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.09829059829059829,
505
+ "grad_norm": 0.9344921112060547,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.1032,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.09971509971509972,
512
+ "grad_norm": 1.0251350402832031,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.0943,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.10113960113960115,
519
+ "grad_norm": 1.0262216329574585,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.0996,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.10256410256410256,
526
+ "grad_norm": 1.050524115562439,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.03,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.10398860398860399,
533
+ "grad_norm": 1.1450400352478027,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.0246,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.10541310541310542,
540
+ "grad_norm": 1.1916637420654297,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.9999,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.10683760683760683,
547
+ "grad_norm": 1.4077075719833374,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.1149,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.10826210826210826,
554
+ "grad_norm": 1.5274344682693481,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.9944,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.10968660968660969,
561
+ "grad_norm": 2.256171464920044,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.2873,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.1111111111111111,
568
+ "grad_norm": 2.207008123397827,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.0648,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.11253561253561253,
575
+ "grad_norm": 3.2979633808135986,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.3021,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.11396011396011396,
582
+ "grad_norm": 2.376344919204712,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.0125,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.11538461538461539,
589
+ "grad_norm": 2.4043941497802734,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.9742,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1168091168091168,
596
+ "grad_norm": 2.793799877166748,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.1254,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.11823361823361823,
603
+ "grad_norm": 2.7024142742156982,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.2951,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.11965811965811966,
610
+ "grad_norm": 3.5849368572235107,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.5779,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.12108262108262108,
617
+ "grad_norm": 3.006340265274048,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.3645,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.1225071225071225,
624
+ "grad_norm": 2.277855157852173,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.0624,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.12393162393162394,
631
+ "grad_norm": 2.4271788597106934,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.5051,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.12535612535612536,
638
+ "grad_norm": 2.7788116931915283,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.7977,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.1267806267806268,
645
+ "grad_norm": 3.2901506423950195,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.9937,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.1282051282051282,
652
+ "grad_norm": 3.284877061843872,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.0343,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.12962962962962962,
659
+ "grad_norm": 3.519197702407837,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.2603,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.13105413105413105,
666
+ "grad_norm": 3.5070576667785645,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.1193,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.13247863247863248,
673
+ "grad_norm": 3.874929904937744,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.1551,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.1339031339031339,
680
+ "grad_norm": 4.789926052093506,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.4054,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.13532763532763534,
687
+ "grad_norm": 5.195937633514404,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.6756,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.13675213675213677,
694
+ "grad_norm": 4.467799663543701,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.3472,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.13817663817663817,
701
+ "grad_norm": 4.928045272827148,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.9974,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.1396011396011396,
708
+ "grad_norm": 5.623568058013916,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.399,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.14102564102564102,
715
+ "grad_norm": 5.925526142120361,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.9024,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.14245014245014245,
722
+ "grad_norm": 7.447940826416016,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.841,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.14245014245014245,
729
+ "eval_loss": 1.5963640213012695,
730
+ "eval_runtime": 52.7393,
731
+ "eval_samples_per_second": 22.412,
732
+ "eval_steps_per_second": 5.613,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4.154039461321114e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null