nttx commited on
Commit
fd088fc
·
verified ·
1 Parent(s): 619510c

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 sha256:7beae75f0ead682616003306f8d6d1ef69bc3de77397163205b6458da343eb45
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d67d458359b6fbe8a317825a616d0e652a77fe9a6282a5cb8ddb8c147c7bdf
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20b5bd4cca1520a7ee00a477a52d32c60b426f7018fd9f4b63e52e7b91bc7ceb
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de52ca4dafaae173009f4fba54366038ac76c1b47bf73e867abde24cdb57e4d6
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:ef351b9ba7935403e69f10453196f23f50274c55f7fddf7e44a913665987c096
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b0e27818492f7db45cc176cac809c1e4314d3c742a14bfb655212c4c50995a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.872589349746704,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.17316017316017315,
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": 10.966,
374
  "eval_steps_per_second": 1.376,
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": 6.65254329581568e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8903895020484924,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.3463203463203463,
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": 10.966,
374
  "eval_steps_per_second": 1.376,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.17662337662337663,
379
+ "grad_norm": 29.115434646606445,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 7.6859,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.1800865800865801,
386
+ "grad_norm": 23.137310028076172,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 7.0948,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.18354978354978355,
393
+ "grad_norm": 69.08699035644531,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 7.4348,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.18701298701298702,
400
+ "grad_norm": 33.72195053100586,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 7.2166,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.19047619047619047,
407
+ "grad_norm": 24.25813102722168,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 6.1757,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.19393939393939394,
414
+ "grad_norm": 19.192127227783203,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 5.8232,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1974025974025974,
421
+ "grad_norm": 22.991289138793945,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 6.1156,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.20086580086580086,
428
+ "grad_norm": 15.390352249145508,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 4.532,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.20432900432900433,
435
+ "grad_norm": 16.006914138793945,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 5.4136,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2077922077922078,
442
+ "grad_norm": 14.466924667358398,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 5.458,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.21125541125541125,
449
+ "grad_norm": 13.0088529586792,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 5.0082,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.21471861471861473,
456
+ "grad_norm": 15.840579986572266,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 5.3098,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.21818181818181817,
463
+ "grad_norm": 14.281547546386719,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 5.3405,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.22164502164502164,
470
+ "grad_norm": 14.70820426940918,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 4.9791,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.22510822510822512,
477
+ "grad_norm": 13.148139953613281,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 4.6532,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.22857142857142856,
484
+ "grad_norm": 10.900792121887207,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 4.3715,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.23203463203463204,
491
+ "grad_norm": 12.069330215454102,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 4.6059,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2354978354978355,
498
+ "grad_norm": 12.047381401062012,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 4.5906,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.23896103896103896,
505
+ "grad_norm": 12.072599411010742,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 4.6145,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.24242424242424243,
512
+ "grad_norm": 10.38735580444336,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 4.0905,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.24588744588744588,
519
+ "grad_norm": 10.655598640441895,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 4.2857,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.24935064935064935,
526
+ "grad_norm": 10.410820007324219,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 4.1162,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2528138528138528,
533
+ "grad_norm": 13.076409339904785,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 4.0771,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.25627705627705627,
540
+ "grad_norm": 11.476602554321289,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 3.7361,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.2597402597402597,
547
+ "grad_norm": 10.394034385681152,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 3.7557,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.2632034632034632,
554
+ "grad_norm": 10.052972793579102,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 3.7359,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.26666666666666666,
561
+ "grad_norm": 9.783942222595215,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 3.6702,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.2701298701298701,
568
+ "grad_norm": 11.15272045135498,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 3.5763,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.2735930735930736,
575
+ "grad_norm": 10.842543601989746,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 3.6811,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.27705627705627706,
582
+ "grad_norm": 11.585516929626465,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 3.8864,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.2805194805194805,
589
+ "grad_norm": 11.399924278259277,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 3.8351,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.283982683982684,
596
+ "grad_norm": 12.100907325744629,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 3.7107,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.28744588744588745,
603
+ "grad_norm": 18.706764221191406,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 3.6265,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.2909090909090909,
610
+ "grad_norm": 8.809903144836426,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 3.3013,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.2943722943722944,
617
+ "grad_norm": 10.779837608337402,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 3.6764,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.29783549783549784,
624
+ "grad_norm": 10.766345977783203,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 3.4515,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3012987012987013,
631
+ "grad_norm": 9.480976104736328,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 3.0511,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3047619047619048,
638
+ "grad_norm": 9.998576164245605,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 3.4779,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.30822510822510824,
645
+ "grad_norm": 15.594218254089355,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 3.5431,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.3116883116883117,
652
+ "grad_norm": 8.791656494140625,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 3.7535,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.3151515151515151,
659
+ "grad_norm": 12.256552696228027,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 3.6736,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.31861471861471863,
666
+ "grad_norm": 9.614633560180664,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 3.4692,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.3220779220779221,
673
+ "grad_norm": 15.359471321105957,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 3.5086,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3255411255411255,
680
+ "grad_norm": 9.451735496520996,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 3.4297,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.329004329004329,
687
+ "grad_norm": 12.527972221374512,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 3.5274,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.33246753246753247,
694
+ "grad_norm": 10.393943786621094,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 3.3514,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.3359307359307359,
701
+ "grad_norm": 12.969127655029297,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 2.9822,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.3393939393939394,
708
+ "grad_norm": 19.778343200683594,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 3.4786,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.34285714285714286,
715
+ "grad_norm": 14.387062072753906,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 2.9066,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.3463203463203463,
722
+ "grad_norm": 14.423389434814453,
723
+ "learning_rate": 0.0,
724
+ "loss": 3.4718,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.3463203463203463,
729
+ "eval_loss": 0.8903895020484924,
730
+ "eval_runtime": 44.3566,
731
+ "eval_samples_per_second": 10.957,
732
+ "eval_steps_per_second": 1.375,
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": 1.330508659163136e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null