prxy5608 commited on
Commit
9cf30ff
·
verified ·
1 Parent(s): ae8f804

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:cd4544005ba9af2512e5e33b0215f95de4a19c41e46e6604cdf19eac8db0a9a8
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f434c58c47621bd05e9f910274c111977fde022648675ed0c9fba17f39b1b44f
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:326e5666281ba529f2da74465415ff06e2283e83ebc57ead7e857c2d5733387d
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b7b98b811f2a024b2fa9e457f86637d06c54905a4fed1538698e92f58beaa3d
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b18cfbf249eaf5efacc990ff51b4ec711411ae2f0ccb1660bc7e93cc429338e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976a489fc15f58294d879d44ac4f7737be8fcb89ac3c7231f0e3d8123b0ed9ce
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": 2.6282694339752197,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.024387269845140835,
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": 13.594,
374
  "eval_steps_per_second": 3.401,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.28717951238144e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.1385467052459717,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.04877453969028167,
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": 13.594,
374
  "eval_steps_per_second": 3.401,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.024875015242043653,
379
+ "grad_norm": 2.525137424468994,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 3.3201,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.02536276063894647,
386
+ "grad_norm": 1.9298559427261353,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.8963,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.025850506035849288,
393
+ "grad_norm": 1.562819480895996,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.8588,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.026338251432752105,
400
+ "grad_norm": 1.0883809328079224,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.6198,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.02682599682965492,
407
+ "grad_norm": 1.0330435037612915,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.5798,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.027313742226557736,
414
+ "grad_norm": 1.270867109298706,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.6996,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.027801487623460554,
421
+ "grad_norm": 1.1742101907730103,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.6916,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.02828923302036337,
428
+ "grad_norm": 1.0894042253494263,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.5709,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.02877697841726619,
435
+ "grad_norm": 1.244813084602356,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.6457,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.029264723814169002,
442
+ "grad_norm": 1.0746277570724487,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.2518,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.02975246921107182,
449
+ "grad_norm": 1.1548517942428589,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.3314,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.030240214607974637,
456
+ "grad_norm": 1.1649878025054932,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.4831,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.030727960004877455,
463
+ "grad_norm": 1.2175664901733398,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.0127,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.031215705401780272,
470
+ "grad_norm": 1.2224698066711426,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.3575,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.031703450798683086,
477
+ "grad_norm": 1.2590465545654297,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.2152,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.03219119619558591,
484
+ "grad_norm": 1.3008689880371094,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.2786,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.03267894159248872,
491
+ "grad_norm": 1.5196938514709473,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.2248,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.033166686989391535,
498
+ "grad_norm": 1.4997824430465698,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.3649,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.033654432386294356,
505
+ "grad_norm": 1.448543906211853,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.0617,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.03414217778319717,
512
+ "grad_norm": 1.5949437618255615,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.1539,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.03462992318009999,
519
+ "grad_norm": 1.6336168050765991,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.128,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.035117668577002804,
526
+ "grad_norm": 1.8401151895523071,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.2938,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.03560541397390562,
533
+ "grad_norm": 1.8767706155776978,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.2114,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.03609315937080844,
540
+ "grad_norm": 1.8363771438598633,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.0475,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.03658090476771125,
547
+ "grad_norm": 2.051151990890503,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.4243,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.037068650164614074,
554
+ "grad_norm": 2.10811185836792,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.0605,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.03755639556151689,
561
+ "grad_norm": 2.5270118713378906,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.4051,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0380441409584197,
568
+ "grad_norm": 2.524273633956909,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.5405,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.03853188635532252,
575
+ "grad_norm": 2.4887049198150635,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.4866,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03901963175222534,
582
+ "grad_norm": 2.3588764667510986,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.0816,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.03950737714912816,
589
+ "grad_norm": 2.476278781890869,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.1117,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.03999512254603097,
596
+ "grad_norm": 2.739741325378418,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.1998,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.040482867942933785,
603
+ "grad_norm": 2.7698280811309814,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.9936,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.040970613339836606,
610
+ "grad_norm": 2.5614287853240967,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.0132,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.04145835873673942,
617
+ "grad_norm": 3.0431385040283203,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.0992,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.04194610413364224,
624
+ "grad_norm": 3.1751694679260254,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.512,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.042433849530545055,
631
+ "grad_norm": 2.9213707447052,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.0407,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.04292159492744787,
638
+ "grad_norm": 2.7673933506011963,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.0313,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.04340934032435069,
645
+ "grad_norm": 3.18284010887146,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.1928,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.043897085721253504,
652
+ "grad_norm": 3.1404869556427,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.0266,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.044384831118156325,
659
+ "grad_norm": 3.900766372680664,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.2138,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.04487257651505914,
666
+ "grad_norm": 3.2854883670806885,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.0153,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.04536032191196195,
673
+ "grad_norm": 3.054872989654541,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.7195,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.04584806730886477,
680
+ "grad_norm": 3.2677552700042725,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.8897,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.04633581270576759,
687
+ "grad_norm": 3.4859201908111572,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.8254,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.04682355810267041,
694
+ "grad_norm": 3.594351053237915,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.9488,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.04731130349957322,
701
+ "grad_norm": 4.0036163330078125,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.01,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.04779904889647604,
708
+ "grad_norm": 4.132566452026367,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.0372,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.04828679429337886,
715
+ "grad_norm": 4.630672454833984,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.1507,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.04877453969028167,
722
+ "grad_norm": 6.598683834075928,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.1817,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.04877453969028167,
729
+ "eval_loss": 2.1385467052459717,
730
+ "eval_runtime": 254.8774,
731
+ "eval_samples_per_second": 13.548,
732
+ "eval_steps_per_second": 3.39,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.4609906241896448e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null