prxy5607 commited on
Commit
e30c6ee
·
verified ·
1 Parent(s): 9769ff3

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 sha256:5964a1f5fb8dc5a0fe712e286e3b0461316f9d7b7511372c72b6a3a2d61be579
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc08e731f7be8fb0a51942d71927f0f9afe4bd4be004d18c7ff4bdc8eb3b2da
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee6b0f548ebea8e0381b839b6dee7f6967ad8883f59fbd928704b4581448740b
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c79c43ebea80e4f155d13dc4e4d89adcef57d533bf13c66636dc7a11c64c2763
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c1dba1944f5f2daa14a5c787a69dbda12a26200754d971a7aee05b01a1673c1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e668f1a45cea6b9c0567125f2d00b18fa782739da61b22880fec33e22c4b37
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": 1.9373520612716675,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.010051766597979595,
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": 48.586,
374
  "eval_steps_per_second": 12.149,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.0825725351297024e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.814341425895691,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.02010353319595919,
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": 48.586,
374
  "eval_steps_per_second": 12.149,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.010252801929939187,
379
+ "grad_norm": 1.9833588600158691,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.8957,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.01045383726189878,
386
+ "grad_norm": 1.938567876815796,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.9646,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.010654872593858371,
393
+ "grad_norm": 0.9525935649871826,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.67,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.010855907925817962,
400
+ "grad_norm": 1.0226001739501953,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.8589,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.011056943257777554,
407
+ "grad_norm": 0.9939088821411133,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.7025,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.011257978589737146,
414
+ "grad_norm": 0.672572135925293,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.7452,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.011459013921696739,
421
+ "grad_norm": 0.7350982427597046,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.7313,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01166004925365633,
428
+ "grad_norm": 0.6969625949859619,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.7895,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.011861084585615921,
435
+ "grad_norm": 0.813930094242096,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.7949,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.012062119917575513,
442
+ "grad_norm": 0.6331385374069214,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.6823,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.012263155249535106,
449
+ "grad_norm": 0.6768167018890381,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.5996,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.012464190581494698,
456
+ "grad_norm": 0.7389916181564331,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.724,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.01266522591345429,
463
+ "grad_norm": 0.7186094522476196,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.7208,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.012866261245413882,
470
+ "grad_norm": 0.6613526344299316,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.7751,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.013067296577373473,
477
+ "grad_norm": 0.7740375399589539,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.7576,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.013268331909333065,
484
+ "grad_norm": 0.6247599124908447,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.7399,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.013469367241292657,
491
+ "grad_norm": 0.7394496202468872,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.7569,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01367040257325225,
498
+ "grad_norm": 0.7518988847732544,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.8087,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.013871437905211842,
505
+ "grad_norm": 0.768896222114563,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.7186,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.014072473237171432,
512
+ "grad_norm": 0.6294169425964355,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.6522,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.014273508569131024,
519
+ "grad_norm": 0.6437097787857056,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.7515,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.014474543901090616,
526
+ "grad_norm": 0.7687767744064331,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.922,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.014675579233050209,
533
+ "grad_norm": 0.8429214954376221,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.8244,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.014876614565009801,
540
+ "grad_norm": 0.7580492496490479,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.7377,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.015077649896969393,
547
+ "grad_norm": 0.7352554798126221,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.6991,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.015278685228928984,
554
+ "grad_norm": 0.7524585723876953,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.6867,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.015479720560888576,
561
+ "grad_norm": 0.870159387588501,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.684,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.015680755892848168,
568
+ "grad_norm": 0.7836048603057861,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.7913,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.01588179122480776,
575
+ "grad_norm": 0.7694597840309143,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.8434,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.016082826556767352,
582
+ "grad_norm": 0.8581750392913818,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.7675,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.016283861888726943,
589
+ "grad_norm": 0.8228153586387634,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.9144,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.016484897220686537,
596
+ "grad_norm": 0.9851665496826172,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.7136,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.016685932552646127,
603
+ "grad_norm": 1.0223902463912964,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.8572,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.016886967884605718,
610
+ "grad_norm": 0.8929843902587891,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.6725,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.017088003216565312,
617
+ "grad_norm": 0.8399107456207275,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.6636,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.017289038548524902,
624
+ "grad_norm": 0.7982478737831116,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.7159,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.017490073880484496,
631
+ "grad_norm": 0.9400783181190491,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.8073,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.017691109212444087,
638
+ "grad_norm": 0.9305055141448975,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.7618,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.01789214454440368,
645
+ "grad_norm": 0.8941248059272766,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.7527,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.01809317987636327,
652
+ "grad_norm": 1.0266920328140259,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.6766,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.01829421520832286,
659
+ "grad_norm": 1.0415492057800293,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.818,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.018495250540282455,
666
+ "grad_norm": 1.000577449798584,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.8711,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.018696285872242046,
673
+ "grad_norm": 1.1230899095535278,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.9138,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.01889732120420164,
680
+ "grad_norm": 1.0591013431549072,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.7242,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.01909835653616123,
687
+ "grad_norm": 1.121505618095398,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.7318,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.01929939186812082,
694
+ "grad_norm": 1.2818670272827148,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.8267,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.019500427200080415,
701
+ "grad_norm": 1.2918139696121216,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.0023,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.019701462532040005,
708
+ "grad_norm": 1.3619199991226196,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.6922,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0199024978639996,
715
+ "grad_norm": 1.9346954822540283,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.7747,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.02010353319595919,
722
+ "grad_norm": 2.650932550430298,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.7894,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.02010353319595919,
729
+ "eval_loss": 1.814341425895691,
730
+ "eval_runtime": 172.5177,
731
+ "eval_samples_per_second": 48.563,
732
+ "eval_steps_per_second": 12.144,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.159812200628224e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null