prxy5604 commited on
Commit
b339db7
·
verified ·
1 Parent(s): 46ef8e1

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 sha256:14435f92f4b874d219bd167b2b274896b84cc981523ac1fc3fe239d8d8e78e6e
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936c1b8bc0bdaae8f4d526d2713f0d9f1455592e31863a3f95d931e5c8ae076e
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ed17b343b382ac1f254f263318b2c78437b5a44fbc70c161f9e1e2e3c45d638
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512548d909c01161977d33749de906d270283b8671a35bcc9711e71e977b6ab3
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a71bb679158daddfa4109f94e905ee08d88cf2d754468b220047f563ed7d0af
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2282d3b55291d9e7d0729a73f1123803802e8d9f90fc14744e7d8232ec1fdb
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": 0.45007362961769104,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.08305647840531562,
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": 7.531,
374
  "eval_steps_per_second": 1.886,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.2280129388544e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.409039705991745,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.16611295681063123,
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": 7.531,
374
  "eval_steps_per_second": 1.886,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.08471760797342193,
379
+ "grad_norm": 0.18804551661014557,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.3224,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.08637873754152824,
386
+ "grad_norm": 0.16869483888149261,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.3237,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.08803986710963455,
393
+ "grad_norm": 0.16511651873588562,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.353,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.08970099667774087,
400
+ "grad_norm": 0.1492200344800949,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.3538,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.09136212624584718,
407
+ "grad_norm": 0.13702312111854553,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.3423,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.09302325581395349,
414
+ "grad_norm": 0.14534348249435425,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.331,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0946843853820598,
421
+ "grad_norm": 0.1291942298412323,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.3115,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.09634551495016612,
428
+ "grad_norm": 0.13093352317810059,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.3066,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.09800664451827243,
435
+ "grad_norm": 0.1452917754650116,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.3485,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.09966777408637874,
442
+ "grad_norm": 0.13886800408363342,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.3127,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.10132890365448505,
449
+ "grad_norm": 0.14664413034915924,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.3349,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.10299003322259136,
456
+ "grad_norm": 0.13130126893520355,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.3031,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.10465116279069768,
463
+ "grad_norm": 0.13619501888751984,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.3359,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.10631229235880399,
470
+ "grad_norm": 0.14423972368240356,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.3169,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.1079734219269103,
477
+ "grad_norm": 0.13670726120471954,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.3358,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.10963455149501661,
484
+ "grad_norm": 0.13185586035251617,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.3096,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.11129568106312292,
491
+ "grad_norm": 0.13396374881267548,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.3091,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.11295681063122924,
498
+ "grad_norm": 0.1417226344347,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.3102,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.11461794019933555,
505
+ "grad_norm": 0.1466892659664154,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.3403,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.11627906976744186,
512
+ "grad_norm": 0.1433144360780716,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.324,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.11794019933554817,
519
+ "grad_norm": 0.1436891257762909,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.3434,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.11960132890365449,
526
+ "grad_norm": 0.15285548567771912,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.3344,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.1212624584717608,
533
+ "grad_norm": 0.14362435042858124,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.3191,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.12292358803986711,
540
+ "grad_norm": 0.15305458009243011,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.3776,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.12458471760797342,
547
+ "grad_norm": 0.1848021298646927,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.4502,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.12624584717607973,
554
+ "grad_norm": 0.18864738941192627,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.5257,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.12790697674418605,
561
+ "grad_norm": 0.16458578407764435,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.526,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.12956810631229235,
568
+ "grad_norm": 0.14648108184337616,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.5084,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.13122923588039867,
575
+ "grad_norm": 0.13501055538654327,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.4777,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.132890365448505,
582
+ "grad_norm": 0.15276943147182465,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.5236,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.1345514950166113,
589
+ "grad_norm": 0.1511184722185135,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.5364,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1362126245847176,
596
+ "grad_norm": 0.14624027907848358,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.5027,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.1378737541528239,
603
+ "grad_norm": 0.13957354426383972,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.4793,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.13953488372093023,
610
+ "grad_norm": 0.13981389999389648,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.4919,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.14119601328903655,
617
+ "grad_norm": 0.15372055768966675,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.5226,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.14285714285714285,
624
+ "grad_norm": 0.1438971310853958,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.5232,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.14451827242524917,
631
+ "grad_norm": 0.1383737474679947,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.5007,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.1461794019933555,
638
+ "grad_norm": 0.14018723368644714,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.5328,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.1478405315614618,
645
+ "grad_norm": 0.1336921900510788,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.5123,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.14950166112956811,
652
+ "grad_norm": 0.14490532875061035,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.4996,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.1511627906976744,
659
+ "grad_norm": 0.14218592643737793,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.5103,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.15282392026578073,
666
+ "grad_norm": 0.13371700048446655,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.4695,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.15448504983388706,
673
+ "grad_norm": 0.14268216490745544,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.4996,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.15614617940199335,
680
+ "grad_norm": 0.15761351585388184,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.5142,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.15780730897009967,
687
+ "grad_norm": 0.14862477779388428,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.4953,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.15946843853820597,
694
+ "grad_norm": 0.15104886889457703,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.5656,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.1611295681063123,
701
+ "grad_norm": 0.1583997756242752,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.538,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.16279069767441862,
708
+ "grad_norm": 0.16727805137634277,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.5618,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.1644518272425249,
715
+ "grad_norm": 0.18140842020511627,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.5916,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.16611295681063123,
722
+ "grad_norm": 0.2026122659444809,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.677,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.16611295681063123,
729
+ "eval_loss": 0.409039705991745,
730
+ "eval_runtime": 134.7555,
731
+ "eval_samples_per_second": 7.525,
732
+ "eval_steps_per_second": 1.885,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.46948355375104e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null