prxy5607 commited on
Commit
820982d
·
verified ·
1 Parent(s): c62c701

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:b8074ec43d15f505271628c8c5959ffee92306b0cab459557d7c399afab6a6e5
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c0656d97aeb0442ad6c5bd748c47a50a63181bc6989c31c5eaa06f5ad0e6be
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a254fa26144db046ba8c8662e10e70f02c1aa3c0e380a03b0e38aac49d45346c
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7556aa98a428afacf4373ea90404728f761509f991fa94d62db4d2cac57257a
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8aca31a0a500420a6d71d4320be83d2c042ee0de868f32bdb3a5bc4baed4ee3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ad1a8d0ce331913f56703e57ec5ff6cbcbbc8675d04d183d9f8ddecab98e436
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": 0.7394875884056091,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.028105677346824058,
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": 19.638,
374
  "eval_steps_per_second": 4.914,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.3812663934976e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7103737592697144,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.056211354693648116,
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": 19.638,
374
  "eval_steps_per_second": 4.914,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.02866779089376054,
379
+ "grad_norm": 0.328805536031723,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.7461,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.02922990444069702,
386
+ "grad_norm": 0.33998236060142517,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.868,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.029792017987633503,
393
+ "grad_norm": 0.2628476917743683,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.7035,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03035413153456998,
400
+ "grad_norm": 0.2293473780155182,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.7382,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.030916245081506463,
407
+ "grad_norm": 0.22472500801086426,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.7453,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.03147835862844295,
414
+ "grad_norm": 0.20862101018428802,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.6398,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03204047217537943,
421
+ "grad_norm": 0.21950207650661469,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.7376,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.032602585722315905,
428
+ "grad_norm": 0.22642666101455688,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.6904,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03316469926925239,
435
+ "grad_norm": 0.2184956967830658,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.6677,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03372681281618887,
442
+ "grad_norm": 0.2059151977300644,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.6943,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.034288926363125354,
449
+ "grad_norm": 0.20753073692321777,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.7104,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.03485103991006183,
456
+ "grad_norm": 0.20797058939933777,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.7273,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.03541315345699832,
463
+ "grad_norm": 0.2004324048757553,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.621,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.035975267003934795,
470
+ "grad_norm": 0.2056368589401245,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.6748,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.03653738055087127,
477
+ "grad_norm": 0.20332691073417664,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.7194,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.03709949409780776,
484
+ "grad_norm": 0.21475742757320404,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.7574,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.03766160764474424,
491
+ "grad_norm": 0.21810247004032135,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.736,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.03822372119168072,
498
+ "grad_norm": 0.2109690010547638,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.735,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.0387858347386172,
505
+ "grad_norm": 0.21837064623832703,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.7252,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.03934794828555368,
512
+ "grad_norm": 0.20757514238357544,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.728,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.039910061832490164,
519
+ "grad_norm": 0.21207264065742493,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.7625,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04047217537942664,
526
+ "grad_norm": 0.20816613733768463,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.7204,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.04103428892636313,
533
+ "grad_norm": 0.21276846528053284,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.7226,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.041596402473299605,
540
+ "grad_norm": 0.21693867444992065,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.7129,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04215851602023609,
547
+ "grad_norm": 0.21719211339950562,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.731,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.04272062956717257,
554
+ "grad_norm": 0.2159098982810974,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.695,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.04328274311410905,
561
+ "grad_norm": 0.21332460641860962,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.7161,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.04384485666104553,
568
+ "grad_norm": 0.22994939982891083,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.754,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.04440697020798201,
575
+ "grad_norm": 0.22945700585842133,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.7042,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.044969083754918496,
582
+ "grad_norm": 0.23664583265781403,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.7297,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.045531197301854974,
589
+ "grad_norm": 0.23979917168617249,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.7108,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.04609331084879146,
596
+ "grad_norm": 0.23731853067874908,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.7092,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.04665542439572794,
603
+ "grad_norm": 0.23034045100212097,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.6778,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.047217537942664416,
610
+ "grad_norm": 0.23124980926513672,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.7142,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.0477796514896009,
617
+ "grad_norm": 0.22591619193553925,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.6442,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.04834176503653738,
624
+ "grad_norm": 0.2527121901512146,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.811,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.048903878583473864,
631
+ "grad_norm": 0.2379622459411621,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.6786,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.04946599213041034,
638
+ "grad_norm": 0.2407558411359787,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.7249,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.05002810567734682,
645
+ "grad_norm": 0.25664445757865906,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.6669,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.050590219224283306,
652
+ "grad_norm": 0.2580859959125519,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.6994,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.051152332771219784,
659
+ "grad_norm": 0.25966179370880127,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.7234,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.05171444631815627,
666
+ "grad_norm": 0.27060139179229736,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.613,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.05227655986509275,
673
+ "grad_norm": 0.26522526144981384,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.6309,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.05283867341202923,
680
+ "grad_norm": 0.2706226408481598,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.6742,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.05340078695896571,
687
+ "grad_norm": 0.30376970767974854,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.7692,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.05396290050590219,
694
+ "grad_norm": 0.31754347681999207,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.646,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.054525014052838675,
701
+ "grad_norm": 0.3306269943714142,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.7368,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.05508712759977515,
708
+ "grad_norm": 0.34835872054100037,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.6777,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.05564924114671164,
715
+ "grad_norm": 0.3743361234664917,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.6904,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.056211354693648116,
722
+ "grad_norm": 0.5413866639137268,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.8674,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.056211354693648116,
729
+ "eval_loss": 0.7103737592697144,
730
+ "eval_runtime": 152.8241,
731
+ "eval_samples_per_second": 19.611,
732
+ "eval_steps_per_second": 4.908,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4.769336405262336e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null