bbytxt commited on
Commit
066b794
·
verified ·
1 Parent(s): 28f0d0a

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 sha256:1ad034299d165264b8b41a122c56d71a999010ba87b11d35abc3d2ee85a97b1e
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2d752a02af8402b9dfe36b8cb850ef9275254e5fbd85c32d97aa7ca7fee947
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:756425e312de41936aec7f4180fa852f994da9ce4947fa1da921d364519220dd
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0374069369e8a7217661d09ac8547dd9fdfe8c4e569774331d4eb8f7a7f44627
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2111f77cfa041296a40136fcee994c66ac99a1fb2d045ace1987fa2742bd23e5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e0deb8643bb1a683474955de4e095d8a8dbd40933ca79a7c1191a275e516ab5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d90116c540b4ff0066495fbccc9c914a568905fb44c6564f227952cc4231b00
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ad66011cfc1fc727a51190602a41adc332b48eeef62a5ee87c2ca9f9b90b2b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.1654907464981079,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.04177109440267335,
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": 12.884,
374
  "eval_steps_per_second": 3.221,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.6990316003328e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.15805459022521973,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0835421888053467,
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": 12.884,
374
  "eval_steps_per_second": 3.221,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.042606516290726815,
379
+ "grad_norm": 0.3080545663833618,
380
+ "learning_rate": 2.3816778784387097e-05,
381
+ "loss": 0.1177,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.04344193817878028,
386
+ "grad_norm": 0.40985429286956787,
387
+ "learning_rate": 2.3263454721781537e-05,
388
+ "loss": 0.1433,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.04427736006683375,
393
+ "grad_norm": 0.15664848685264587,
394
+ "learning_rate": 2.2693489161088592e-05,
395
+ "loss": 0.0884,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.045112781954887216,
400
+ "grad_norm": 0.15345360338687897,
401
+ "learning_rate": 2.210802993709498e-05,
402
+ "loss": 0.1044,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.04594820384294068,
407
+ "grad_norm": 0.20342934131622314,
408
+ "learning_rate": 2.1508256086763372e-05,
409
+ "loss": 0.1088,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.04678362573099415,
414
+ "grad_norm": 0.16992981731891632,
415
+ "learning_rate": 2.0895375474808857e-05,
416
+ "loss": 0.1459,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.047619047619047616,
421
+ "grad_norm": 0.17031916975975037,
422
+ "learning_rate": 2.0270622361220143e-05,
423
+ "loss": 0.1282,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.04845446950710108,
428
+ "grad_norm": 0.2852511703968048,
429
+ "learning_rate": 1.963525491562421e-05,
430
+ "loss": 0.1329,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.04928989139515455,
435
+ "grad_norm": 0.4877017140388489,
436
+ "learning_rate": 1.8990552683500128e-05,
437
+ "loss": 0.1365,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.05012531328320802,
442
+ "grad_norm": 0.3902769684791565,
443
+ "learning_rate": 1.8337814009344716e-05,
444
+ "loss": 0.1584,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.050960735171261484,
449
+ "grad_norm": 0.2292199432849884,
450
+ "learning_rate": 1.767835342197955e-05,
451
+ "loss": 0.1402,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.05179615705931495,
456
+ "grad_norm": 0.2017497420310974,
457
+ "learning_rate": 1.7013498987264832e-05,
458
+ "loss": 0.1482,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.05263157894736842,
463
+ "grad_norm": 0.2939629852771759,
464
+ "learning_rate": 1.6344589633551502e-05,
465
+ "loss": 0.1461,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.053467000835421885,
470
+ "grad_norm": 0.1926645189523697,
471
+ "learning_rate": 1.5672972455257726e-05,
472
+ "loss": 0.1044,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.05430242272347535,
477
+ "grad_norm": 0.3081521987915039,
478
+ "learning_rate": 1.5e-05,
479
+ "loss": 0.1596,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.05513784461152882,
484
+ "grad_norm": 0.4025512933731079,
485
+ "learning_rate": 1.4327027544742281e-05,
486
+ "loss": 0.1735,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.055973266499582286,
491
+ "grad_norm": 0.20314837992191315,
492
+ "learning_rate": 1.36554103664485e-05,
493
+ "loss": 0.125,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.05680868838763575,
498
+ "grad_norm": 0.20744721591472626,
499
+ "learning_rate": 1.2986501012735174e-05,
500
+ "loss": 0.1095,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.05764411027568922,
505
+ "grad_norm": 0.2043089121580124,
506
+ "learning_rate": 1.2321646578020452e-05,
507
+ "loss": 0.1544,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.05847953216374269,
512
+ "grad_norm": 0.2829361855983734,
513
+ "learning_rate": 1.1662185990655285e-05,
514
+ "loss": 0.1347,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.059314954051796154,
519
+ "grad_norm": 0.2790044844150543,
520
+ "learning_rate": 1.1009447316499875e-05,
521
+ "loss": 0.1564,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.06015037593984962,
526
+ "grad_norm": 2.54337739944458,
527
+ "learning_rate": 1.036474508437579e-05,
528
+ "loss": 0.1629,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.06098579782790309,
533
+ "grad_norm": 0.279619425535202,
534
+ "learning_rate": 9.729377638779859e-06,
535
+ "loss": 0.1506,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.061821219715956555,
540
+ "grad_norm": 0.2148342877626419,
541
+ "learning_rate": 9.104624525191147e-06,
542
+ "loss": 0.1222,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.06265664160401002,
547
+ "grad_norm": 3.0420451164245605,
548
+ "learning_rate": 8.491743913236629e-06,
549
+ "loss": 0.1404,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.06349206349206349,
554
+ "grad_norm": 0.2432384490966797,
555
+ "learning_rate": 7.89197006290502e-06,
556
+ "loss": 0.1076,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.06432748538011696,
561
+ "grad_norm": 3.1877377033233643,
562
+ "learning_rate": 7.30651083891141e-06,
563
+ "loss": 0.152,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.06516290726817042,
568
+ "grad_norm": 0.4180755019187927,
569
+ "learning_rate": 6.736545278218464e-06,
570
+ "loss": 0.1127,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.06599832915622389,
575
+ "grad_norm": 0.25477147102355957,
576
+ "learning_rate": 6.1832212156129045e-06,
577
+ "loss": 0.1277,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.06683375104427736,
582
+ "grad_norm": 0.399618536233902,
583
+ "learning_rate": 5.647652972118998e-06,
584
+ "loss": 0.1418,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.06766917293233082,
589
+ "grad_norm": 0.27185890078544617,
590
+ "learning_rate": 5.130919110904311e-06,
591
+ "loss": 0.155,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.06850459482038429,
596
+ "grad_norm": 1.3203309774398804,
597
+ "learning_rate": 4.6340602651970304e-06,
598
+ "loss": 0.3033,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.06934001670843776,
603
+ "grad_norm": 0.3346821367740631,
604
+ "learning_rate": 4.158077042589129e-06,
605
+ "loss": 0.1639,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.07017543859649122,
610
+ "grad_norm": 0.3132845163345337,
611
+ "learning_rate": 3.7039280099458373e-06,
612
+ "loss": 0.1417,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.07101086048454469,
617
+ "grad_norm": 0.30599430203437805,
618
+ "learning_rate": 3.272527762979553e-06,
619
+ "loss": 0.1666,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.07184628237259816,
624
+ "grad_norm": 0.5425288677215576,
625
+ "learning_rate": 2.86474508437579e-06,
626
+ "loss": 0.1837,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.07268170426065163,
631
+ "grad_norm": 0.2609088122844696,
632
+ "learning_rate": 2.4814011941804603e-06,
633
+ "loss": 0.1981,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.07351712614870509,
638
+ "grad_norm": 0.2561860680580139,
639
+ "learning_rate": 2.1232680959720085e-06,
640
+ "loss": 0.1169,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.07435254803675856,
645
+ "grad_norm": 0.26870644092559814,
646
+ "learning_rate": 1.79106702214893e-06,
647
+ "loss": 0.162,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.07518796992481203,
652
+ "grad_norm": 0.35758742690086365,
653
+ "learning_rate": 1.4854669814637145e-06,
654
+ "loss": 0.1946,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.07602339181286549,
659
+ "grad_norm": 0.40720826387405396,
660
+ "learning_rate": 1.2070834117282414e-06,
661
+ "loss": 0.1676,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.07685881370091896,
666
+ "grad_norm": 0.2641846835613251,
667
+ "learning_rate": 9.56476940403942e-07,
668
+ "loss": 0.1419,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.07769423558897243,
673
+ "grad_norm": 0.32390695810317993,
674
+ "learning_rate": 7.341522555726971e-07,
675
+ "loss": 0.1727,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0785296574770259,
680
+ "grad_norm": 0.17990685999393463,
681
+ "learning_rate": 5.405570895622014e-07,
682
+ "loss": 0.1278,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.07936507936507936,
687
+ "grad_norm": 0.5421126484870911,
688
+ "learning_rate": 3.760813172726457e-07,
689
+ "loss": 0.1988,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.08020050125313283,
694
+ "grad_norm": 0.22047364711761475,
695
+ "learning_rate": 2.41056171020555e-07,
696
+ "loss": 0.1636,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0810359231411863,
701
+ "grad_norm": 0.2979952096939087,
702
+ "learning_rate": 1.357535734809795e-07,
703
+ "loss": 0.1766,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.08187134502923976,
708
+ "grad_norm": 0.4420830309391022,
709
+ "learning_rate": 6.038559007141397e-08,
710
+ "loss": 0.2073,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.08270676691729323,
715
+ "grad_norm": 0.8136470913887024,
716
+ "learning_rate": 1.510400188028116e-08,
717
+ "loss": 0.2351,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0835421888053467,
722
+ "grad_norm": 0.37833961844444275,
723
+ "learning_rate": 0.0,
724
+ "loss": 0.1832,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0835421888053467,
729
+ "eval_loss": 0.15805459022521973,
730
+ "eval_runtime": 39.1836,
731
+ "eval_samples_per_second": 12.863,
732
+ "eval_steps_per_second": 3.216,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.3812411056128e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null