nttx commited on
Commit
55696ce
·
verified ·
1 Parent(s): b82883b

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:bc22097f64b58cc8d61e094d947c2e8a384fd71749d0599f9016fe2f399b772d
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c8e9c80e3a58ec565b40042dd32592c721f5e49119981c561c0f3c6bc22d3b
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ca221551ec7beec46854130f38c2f50f10d9a5a520a157d5a0ff9e7c15b7c76
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccbbc593b64a50a6637b97abc65a045545ea263d210fb6e1f0574517584dd747
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81e60c48516eba6572e9994448babb4d9ea221f86133bbacdba9b63551550470
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61448e1e5439eee4cfab31ba2cf9bb45016fbb1f9dc92dbfd8f3198803c5b9f
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": 0.44972315430641174,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.003544528134692069,
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": 13.343,
374
  "eval_steps_per_second": 3.336,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.8634147815424e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3743059039115906,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.007089056269384138,
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": 13.343,
374
  "eval_steps_per_second": 3.336,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0036154186973859103,
379
+ "grad_norm": 2.26267409324646,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.5829,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.003686309260079752,
386
+ "grad_norm": 1.55825674533844,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.3442,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0037571998227735933,
393
+ "grad_norm": 0.7894648909568787,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.3763,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0038280903854674346,
400
+ "grad_norm": 0.49781158566474915,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.3286,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.003898980948161276,
407
+ "grad_norm": 4.833137035369873,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.5205,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.003969871510855118,
414
+ "grad_norm": 0.6314643025398254,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.4451,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.004040762073548958,
421
+ "grad_norm": 0.5179358720779419,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.3937,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0041116526362428,
428
+ "grad_norm": 0.5772222876548767,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.3653,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.004182543198936642,
435
+ "grad_norm": 0.5230809450149536,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.3794,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.004253433761630483,
442
+ "grad_norm": 0.5087058544158936,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.3957,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.004324324324324324,
449
+ "grad_norm": 0.4886504113674164,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.3961,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.004395214887018166,
456
+ "grad_norm": 0.47368374466896057,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.373,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.004466105449712007,
463
+ "grad_norm": 0.6237163543701172,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.3751,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.004536996012405849,
470
+ "grad_norm": 0.5442241430282593,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.4068,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0046078865750996895,
477
+ "grad_norm": 0.6219522953033447,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.508,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.004678777137793531,
484
+ "grad_norm": 0.5011370778083801,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.2985,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.004749667700487373,
491
+ "grad_norm": 0.5422576069831848,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.3871,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.004820558263181214,
498
+ "grad_norm": 0.5588858127593994,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.4035,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.0048914488258750555,
505
+ "grad_norm": 0.5312881469726562,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.3745,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.004962339388568897,
512
+ "grad_norm": 0.7475187182426453,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.5522,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.005033229951262738,
519
+ "grad_norm": 0.47773832082748413,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.3167,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.00510412051395658,
526
+ "grad_norm": 0.6200078129768372,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.4522,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.005175011076650421,
533
+ "grad_norm": 0.5681312680244446,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.3945,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.005245901639344262,
540
+ "grad_norm": 0.6025010943412781,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.3965,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.005316792202038104,
547
+ "grad_norm": 0.5036550760269165,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.3446,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.005387682764731945,
554
+ "grad_norm": 0.5747814774513245,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.3936,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0054585733274257866,
561
+ "grad_norm": 0.6142371892929077,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.4408,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.005529463890119627,
568
+ "grad_norm": 0.5577287673950195,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.3285,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.005600354452813469,
575
+ "grad_norm": 0.5796722173690796,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.3367,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.005671245015507311,
582
+ "grad_norm": 0.5557568073272705,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.3138,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.005742135578201152,
589
+ "grad_norm": 0.5195022821426392,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.2951,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.005813026140894993,
596
+ "grad_norm": 0.565771222114563,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.3469,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.005883916703588835,
603
+ "grad_norm": 0.707554817199707,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.3922,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.005954807266282676,
610
+ "grad_norm": 0.6795750856399536,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.4394,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.006025697828976518,
617
+ "grad_norm": 0.6365452408790588,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.4404,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0060965883916703585,
624
+ "grad_norm": 0.6396660208702087,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.3951,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.0061674789543642,
631
+ "grad_norm": 0.5342606902122498,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.3531,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.006238369517058042,
638
+ "grad_norm": 0.604596734046936,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.4086,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.006309260079751883,
645
+ "grad_norm": 0.5136443972587585,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.3438,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0063801506424457245,
652
+ "grad_norm": 0.5856671929359436,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.3713,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.006451041205139566,
659
+ "grad_norm": 0.5504666566848755,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.3081,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.006521931767833407,
666
+ "grad_norm": 0.5364263653755188,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.3002,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.006592822330527249,
673
+ "grad_norm": 0.5979559421539307,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.4272,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0066637128932210896,
680
+ "grad_norm": 0.5369541645050049,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.371,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.006734603455914931,
687
+ "grad_norm": 0.7055835723876953,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.4687,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.006805494018608773,
694
+ "grad_norm": 0.6241551637649536,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.4236,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.006876384581302614,
701
+ "grad_norm": 0.6014761924743652,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.3931,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0069472751439964555,
708
+ "grad_norm": 0.5446456670761108,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.376,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.007018165706690297,
715
+ "grad_norm": 0.5127068758010864,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.289,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.007089056269384138,
722
+ "grad_norm": 0.6141975522041321,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.4337,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.007089056269384138,
729
+ "eval_loss": 0.3743059039115906,
730
+ "eval_runtime": 1778.6043,
731
+ "eval_samples_per_second": 13.358,
732
+ "eval_steps_per_second": 3.34,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.37604737531904e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null