prxy5604 commited on
Commit
7137b7a
·
verified ·
1 Parent(s): 1f67f09

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 sha256:8fe0feb48fe62aa6e2b3ec2a3cd8038b05b8c2c7f128f280a7537a7872c0395b
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddab7c69343af5caaf93f4dd233507d377a61423c08eed952aaf6eb143e3c4a
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1320a1521ee7c96880f98edae75a32ac79ae13dfea4dd7f8fffb1c3ca3496fcb
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03927b2315418b9b1552330c82fc7339cac8b8bada3c102c9d809c63c84c705d
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22c18bfde3fe27dc64c0d13b7808a68aaf2a8325d24aaa41a51a7f7a419b8cdf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1112b86ea2ccf53bf6fa78c0004230219252ce4c3cbcafa985b4b3e0cd872dfb
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": 0.8853886127471924,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.23228803716608595,
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": 10.318,
374
  "eval_steps_per_second": 2.587,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 9.7754847117312e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.871712327003479,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.4645760743321719,
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": 10.318,
374
  "eval_steps_per_second": 2.587,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.23693379790940766,
379
+ "grad_norm": 0.14753635227680206,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.958,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.2415795586527294,
386
+ "grad_norm": 0.13887369632720947,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.653,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.2462253193960511,
393
+ "grad_norm": 0.1636919528245926,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.8807,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.2508710801393728,
400
+ "grad_norm": 0.14415013790130615,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.846,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.25551684088269455,
407
+ "grad_norm": 0.1366504728794098,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.6806,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.2601626016260163,
414
+ "grad_norm": 0.11705049127340317,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.7397,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.26480836236933797,
421
+ "grad_norm": 0.12336675822734833,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.7548,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2694541231126597,
428
+ "grad_norm": 0.12091846764087677,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.9128,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.27409988385598144,
435
+ "grad_norm": 0.11321322619915009,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.8901,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2787456445993031,
442
+ "grad_norm": 0.11016193777322769,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.9241,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.28339140534262486,
449
+ "grad_norm": 0.10698598623275757,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.8907,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.2880371660859466,
456
+ "grad_norm": 0.10707106441259384,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.8498,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2926829268292683,
463
+ "grad_norm": 0.11155840009450912,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.7976,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.29732868757259,
470
+ "grad_norm": 0.10202828049659729,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.8585,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.30197444831591175,
477
+ "grad_norm": 0.11714151501655579,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.817,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.30662020905923343,
484
+ "grad_norm": 0.10279451310634613,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.7803,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.31126596980255516,
491
+ "grad_norm": 0.10880623757839203,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.8819,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.3159117305458769,
498
+ "grad_norm": 0.10310228914022446,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.7834,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.3205574912891986,
505
+ "grad_norm": 0.1109737902879715,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.7166,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.3252032520325203,
512
+ "grad_norm": 0.11841745674610138,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.7829,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.32984901277584205,
519
+ "grad_norm": 0.1297767162322998,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.7764,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.3344947735191638,
526
+ "grad_norm": 0.1227758377790451,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.707,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.33914053426248547,
533
+ "grad_norm": 0.13544820249080658,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.8454,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3437862950058072,
540
+ "grad_norm": 0.1268458068370819,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.7319,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.34843205574912894,
547
+ "grad_norm": 0.13013871014118195,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.7981,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.3530778164924506,
554
+ "grad_norm": 0.1546456515789032,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.7556,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.35772357723577236,
561
+ "grad_norm": 0.14676199853420258,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.7872,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3623693379790941,
568
+ "grad_norm": 0.14500990509986877,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.9039,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3670150987224158,
575
+ "grad_norm": 0.1635589599609375,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.7036,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.3716608594657375,
582
+ "grad_norm": 0.16299131512641907,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.8043,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.37630662020905925,
589
+ "grad_norm": 0.1477063000202179,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.7513,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.38095238095238093,
596
+ "grad_norm": 0.17232096195220947,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.7715,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.38559814169570267,
603
+ "grad_norm": 0.17469638586044312,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.9285,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.3902439024390244,
610
+ "grad_norm": 0.16923201084136963,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.7327,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.3948896631823461,
617
+ "grad_norm": 0.1980726420879364,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.7601,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.3995354239256678,
624
+ "grad_norm": 0.20499838888645172,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.9292,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.40418118466898956,
631
+ "grad_norm": 0.2034449428319931,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.9332,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.4088269454123113,
638
+ "grad_norm": 0.22591711580753326,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.0875,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.413472706155633,
645
+ "grad_norm": 0.2202339917421341,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.8283,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.4181184668989547,
652
+ "grad_norm": 0.2351447194814682,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.8803,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.42276422764227645,
659
+ "grad_norm": 0.22027833759784698,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.9161,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.4274099883855981,
666
+ "grad_norm": 0.2328965663909912,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.8979,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.43205574912891986,
673
+ "grad_norm": 0.26121312379837036,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.9793,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.4367015098722416,
680
+ "grad_norm": 0.28046953678131104,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.0957,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.4413472706155633,
687
+ "grad_norm": 0.285359650850296,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.0233,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.445993031358885,
694
+ "grad_norm": 0.28869330883026123,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.0457,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.45063879210220675,
701
+ "grad_norm": 0.3298930823802948,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.1204,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.45528455284552843,
708
+ "grad_norm": 0.3415940999984741,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.0313,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.45993031358885017,
715
+ "grad_norm": 0.6324352025985718,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.2237,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.4645760743321719,
722
+ "grad_norm": 0.7398970723152161,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.2192,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.4645760743321719,
729
+ "eval_loss": 0.871712327003479,
730
+ "eval_runtime": 35.4234,
731
+ "eval_samples_per_second": 10.247,
732
+ "eval_steps_per_second": 2.569,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.937323333779456e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null