prxy5606 commited on
Commit
d930fba
·
verified ·
1 Parent(s): c23a0c7

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 sha256:3f01d94bbe55576c28e61a378465e7d6b5c42f872880f8eb49f92fad1b8388de
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:436bc40987fea02b0e5787c947c758810e1bb2f9ea90bc3f5775267069413696
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5532e8a8e2b5d61a1556f24ad5ca71e5018f41c0c9666a22ee55fe9b085c1c3c
3
  size 463916180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd6903a576f9d812ace772073519c99679e024334fd425f88bb3eb97ea0f5b4
3
  size 463916180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f718d514232b5744742f92c7332037765ca9a9e7de363ebe5e130a92740a1db2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e63b9c3956df80ec528cc467810e3135c069e80c68b8bc041d3c90d9b4f4d2b4
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": 1.5564213991165161,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.5194805194805194,
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": 9.164,
374
  "eval_steps_per_second": 2.319,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.16045503266816e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4060604572296143,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.0389610389610389,
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": 9.164,
374
  "eval_steps_per_second": 2.319,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5298701298701298,
379
+ "grad_norm": 9.15640926361084,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.5358,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.5402597402597402,
386
+ "grad_norm": 7.217840194702148,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.8447,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.5506493506493506,
393
+ "grad_norm": 7.621275424957275,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 4.0846,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.561038961038961,
400
+ "grad_norm": 6.927586078643799,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.7463,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.5714285714285714,
407
+ "grad_norm": 7.786722660064697,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.0062,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.5818181818181818,
414
+ "grad_norm": 7.90624475479126,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 3.631,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.5922077922077922,
421
+ "grad_norm": 22.610877990722656,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 4.3947,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.6025974025974026,
428
+ "grad_norm": 8.461299896240234,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 8.2739,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.612987012987013,
435
+ "grad_norm": 8.185771942138672,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 8.7998,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.6233766233766234,
442
+ "grad_norm": 7.691197395324707,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 8.1865,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.6337662337662338,
449
+ "grad_norm": 8.699455261230469,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 8.2093,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.6441558441558441,
456
+ "grad_norm": 8.309798240661621,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 7.5779,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.6545454545454545,
463
+ "grad_norm": 8.643186569213867,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 6.7183,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.6649350649350649,
470
+ "grad_norm": 8.525787353515625,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 5.9121,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.6753246753246753,
477
+ "grad_norm": 9.759805679321289,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 6.8276,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.6857142857142857,
484
+ "grad_norm": 10.294455528259277,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 6.1688,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.6961038961038961,
491
+ "grad_norm": 10.0902681350708,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 7.0199,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.7064935064935065,
498
+ "grad_norm": 14.20248031616211,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 6.6244,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.7168831168831169,
505
+ "grad_norm": 12.053751945495605,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 7.9556,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.7272727272727273,
512
+ "grad_norm": 10.587654113769531,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 6.6079,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.7376623376623377,
519
+ "grad_norm": 13.080458641052246,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 6.8979,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.7480519480519481,
526
+ "grad_norm": 20.203798294067383,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 7.6002,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.7584415584415585,
533
+ "grad_norm": 10.804618835449219,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 4.3275,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.7688311688311689,
540
+ "grad_norm": 12.095099449157715,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 3.1685,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.7792207792207793,
547
+ "grad_norm": 5.91151762008667,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.4299,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.7896103896103897,
554
+ "grad_norm": 6.148896217346191,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.697,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.8,
561
+ "grad_norm": 6.840137481689453,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.8022,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.8103896103896104,
568
+ "grad_norm": 7.766355991363525,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.9416,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.8207792207792208,
575
+ "grad_norm": 5.920592784881592,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.6363,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.8311688311688312,
582
+ "grad_norm": 6.974241733551025,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 3.4222,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.8415584415584415,
589
+ "grad_norm": 6.821755886077881,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.7414,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.8519480519480519,
596
+ "grad_norm": 9.252930641174316,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 6.7547,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.8623376623376623,
603
+ "grad_norm": 7.803735733032227,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 8.0916,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.8727272727272727,
610
+ "grad_norm": 6.56402587890625,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 7.0716,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.8831168831168831,
617
+ "grad_norm": 7.134830951690674,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 7.6986,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.8935064935064935,
624
+ "grad_norm": 7.818478584289551,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 7.4413,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.9038961038961039,
631
+ "grad_norm": 7.542208671569824,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 6.4206,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.9142857142857143,
638
+ "grad_norm": 7.44448709487915,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 6.1373,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.9246753246753247,
645
+ "grad_norm": 10.097084999084473,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 6.8287,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.935064935064935,
652
+ "grad_norm": 12.01990795135498,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 6.7226,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.9454545454545454,
659
+ "grad_norm": 9.571053504943848,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 5.2302,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.9558441558441558,
666
+ "grad_norm": 11.317047119140625,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 6.8719,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.9662337662337662,
673
+ "grad_norm": 10.105382919311523,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 6.5456,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.9766233766233766,
680
+ "grad_norm": 10.427618980407715,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 6.4078,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.987012987012987,
687
+ "grad_norm": 10.727428436279297,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 6.5427,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.9974025974025974,
694
+ "grad_norm": 14.104158401489258,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 7.616,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.0077922077922077,
701
+ "grad_norm": 8.729491233825684,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 3.2676,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.018181818181818,
708
+ "grad_norm": 14.363706588745117,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 3.5505,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.0285714285714285,
715
+ "grad_norm": 9.730070114135742,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.8847,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.0389610389610389,
722
+ "grad_norm": 6.3668060302734375,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.1662,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.0389610389610389,
729
+ "eval_loss": 1.4060604572296143,
730
+ "eval_runtime": 17.6741,
731
+ "eval_samples_per_second": 9.166,
732
+ "eval_steps_per_second": 2.32,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.3180089277546496e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null