auxyus commited on
Commit
7d8e9b8
·
verified ·
1 Parent(s): b166c58

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 sha256:58f4fae483dcf8f4e4f5d86b14ad362dc091685d2cf968c1139182aee027053e
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:400c4b91687b8312187d094dc9019ee5fe643ec96ee0247cb2ae0aa320ba4fde
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91363b0da2861decdb4c1c96979139f1f214a2e4a015fcdbc8606b620c3dd728
3
  size 162933396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372dbd0dccb840394bd2297197e472ea9333926d64ca61bc22f9249dc22a8c31
3
  size 162933396
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e7b44bcd1c62eb2cd5aa4629c2eb9f7782bca4c695b2c4d82cec1a62bda031d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae74b89a782002529a8d6b196e29bf77599aee309927180f5c7243a32b8ae49
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": 0.2953316271305084,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.012046741356463078,
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": 13.656,
374
  "eval_steps_per_second": 3.415,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.731079410201395e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.26430198550224304,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.024093482712926155,
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": 13.656,
374
  "eval_steps_per_second": 3.415,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.012287676183592338,
379
+ "grad_norm": 1.0552361011505127,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.7515,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0125286110107216,
386
+ "grad_norm": 0.5925299525260925,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.2375,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.012769545837850862,
393
+ "grad_norm": 0.611186146736145,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.2472,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.013010480664980123,
400
+ "grad_norm": 0.613996684551239,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.2734,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.013251415492109385,
407
+ "grad_norm": 0.6335679292678833,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.2563,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.013492350319238646,
414
+ "grad_norm": 0.3528399169445038,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.1847,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.013733285146367907,
421
+ "grad_norm": 0.971021831035614,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.3174,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01397421997349717,
428
+ "grad_norm": 0.7653561234474182,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.2841,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01421515480062643,
435
+ "grad_norm": 0.5496749877929688,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.2655,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.014456089627755691,
442
+ "grad_norm": 0.5923565030097961,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.2768,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.014697024454884954,
449
+ "grad_norm": 0.6262228488922119,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.2214,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.014937959282014215,
456
+ "grad_norm": 0.45588913559913635,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.2558,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.015178894109143477,
463
+ "grad_norm": 0.2943878173828125,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.2471,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.015419828936272738,
470
+ "grad_norm": 0.39070063829421997,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.2447,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.015660763763402,
477
+ "grad_norm": 0.5298280119895935,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.2571,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.01590169859053126,
484
+ "grad_norm": 0.6332111954689026,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.2839,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.016142633417660524,
491
+ "grad_norm": 0.3768083453178406,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.2159,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.016383568244789783,
498
+ "grad_norm": 0.4113668203353882,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.231,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.016624503071919046,
505
+ "grad_norm": 0.596541702747345,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.2575,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01686543789904831,
512
+ "grad_norm": 0.6093540787696838,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.2782,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.017106372726177568,
519
+ "grad_norm": 0.3764282763004303,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.2746,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.01734730755330683,
526
+ "grad_norm": 0.4304805397987366,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.221,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.017588242380436093,
533
+ "grad_norm": 0.4044836163520813,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.2574,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.017829177207565352,
540
+ "grad_norm": 0.5122354030609131,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.2165,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.018070112034694615,
547
+ "grad_norm": 0.5512914657592773,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.2753,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.018311046861823877,
554
+ "grad_norm": 0.30249151587486267,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.2452,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.01855198168895314,
561
+ "grad_norm": 0.4858316481113434,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.24,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0187929165160824,
568
+ "grad_norm": 0.5286673307418823,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.2612,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.01903385134321166,
575
+ "grad_norm": 0.45666831731796265,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.2665,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.019274786170340924,
582
+ "grad_norm": 0.3813072741031647,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.2395,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.019515720997470183,
589
+ "grad_norm": 0.48633506894111633,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.2829,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.019756655824599446,
596
+ "grad_norm": 0.5978692770004272,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.2392,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.01999759065172871,
603
+ "grad_norm": 0.3837064206600189,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.2315,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.020238525478857967,
610
+ "grad_norm": 0.5809662938117981,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.2415,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.02047946030598723,
617
+ "grad_norm": 0.5919232964515686,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.2374,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.020720395133116493,
624
+ "grad_norm": 0.47563308477401733,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.2224,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.020961329960245755,
631
+ "grad_norm": 0.3658895790576935,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.2474,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.021202264787375014,
638
+ "grad_norm": 0.5233673453330994,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.2577,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.021443199614504277,
645
+ "grad_norm": 0.7580683827400208,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.3074,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.02168413444163354,
652
+ "grad_norm": 0.3404545783996582,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.2327,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.0219250692687628,
659
+ "grad_norm": 0.42800337076187134,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.2559,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.02216600409589206,
666
+ "grad_norm": 0.4471622407436371,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.2464,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.022406938923021324,
673
+ "grad_norm": 0.5359969735145569,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.2855,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.022647873750150583,
680
+ "grad_norm": 0.43152597546577454,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.2572,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.022888808577279846,
687
+ "grad_norm": 0.5459998846054077,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.2744,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.023129743404409108,
694
+ "grad_norm": 0.7160676121711731,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.3009,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.023370678231538367,
701
+ "grad_norm": 0.4426705241203308,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.2747,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.02361161305866763,
708
+ "grad_norm": 0.45476841926574707,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.2913,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.023852547885796892,
715
+ "grad_norm": 0.669862687587738,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.2896,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.024093482712926155,
722
+ "grad_norm": 0.21566569805145264,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.2563,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.024093482712926155,
729
+ "eval_loss": 0.26430198550224304,
730
+ "eval_runtime": 510.5793,
731
+ "eval_samples_per_second": 13.69,
732
+ "eval_steps_per_second": 3.424,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.3429000793751552e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null