prxy5606 commited on
Commit
1e9a6a0
·
verified ·
1 Parent(s): ea51270

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:aa1077d700d4ac674fa1a94f2d0d7cbee1276b38f58db058b7ba0e3501382f1d
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14d7f6d291ae884f920ee39a2201f11ffc7133458447e969504456c2813993b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b6c9c7cfab226961507591fdf59ca9d5be7fcf49a6cbc20f4525939a185a398
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:450ce8009e4e9e6c53512c4679fda9e4293f037c3ec0464b2655e8abc436daac
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c336537008ddb7f56f0e47454add366eecc458d976946ea508a85c76a26a0e5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba636bd0d9934c08088994c025a561ddf3c9cf152024a6c43257589d223c729
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5335737b4b4d079cdec612fe6ee661ed4d29f9e0e55eb4eada44a9677240228
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.070281505584717,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.016764459346186086,
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": 12.092,
374
  "eval_steps_per_second": 6.047,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.54256789372928e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.971840500831604,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.03352891869237217,
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": 12.092,
374
  "eval_steps_per_second": 6.047,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.017099748533109808,
379
+ "grad_norm": 2.837768077850342,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 1.3665,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.01743503772003353,
386
+ "grad_norm": 2.6767208576202393,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 1.97,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.017770326906957252,
393
+ "grad_norm": 1.704293966293335,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 1.6777,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.018105616093880974,
400
+ "grad_norm": 1.6387865543365479,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 1.6942,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.018440905280804692,
407
+ "grad_norm": 1.7911442518234253,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 1.6699,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.018776194467728415,
414
+ "grad_norm": 1.837194800376892,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 2.002,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.019111483654652137,
421
+ "grad_norm": 2.0472233295440674,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 1.9996,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01944677284157586,
428
+ "grad_norm": 1.6679171323776245,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 1.6527,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01978206202849958,
435
+ "grad_norm": 1.514108419418335,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 1.6827,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.020117351215423303,
442
+ "grad_norm": 2.0194151401519775,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 2.168,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.020452640402347025,
449
+ "grad_norm": 1.5403530597686768,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 1.6586,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.020787929589270747,
456
+ "grad_norm": 1.7011923789978027,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 1.7703,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.02112321877619447,
463
+ "grad_norm": 1.5274035930633545,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 1.7972,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.02145850796311819,
470
+ "grad_norm": 1.4921406507492065,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 1.5572,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.02179379715004191,
477
+ "grad_norm": 1.6368732452392578,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 1.8478,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.02212908633696563,
484
+ "grad_norm": 2.0866599082946777,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 2.0398,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.022464375523889354,
491
+ "grad_norm": 1.8268249034881592,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 1.9158,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.022799664710813076,
498
+ "grad_norm": 1.592197060585022,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 1.8296,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.023134953897736798,
505
+ "grad_norm": 1.9506229162216187,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 2.001,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.02347024308466052,
512
+ "grad_norm": 1.7068800926208496,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 1.5299,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.023805532271584242,
519
+ "grad_norm": 1.5702540874481201,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 1.935,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.024140821458507964,
526
+ "grad_norm": 2.0129430294036865,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 2.0506,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.024476110645431686,
533
+ "grad_norm": 1.8408924341201782,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 2.2472,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.024811399832355408,
540
+ "grad_norm": 1.6532615423202515,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 1.7969,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.025146689019279127,
547
+ "grad_norm": 1.6880450248718262,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 1.9276,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.02548197820620285,
554
+ "grad_norm": 1.74911367893219,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 1.9406,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.02581726739312657,
561
+ "grad_norm": 1.6293855905532837,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 1.8643,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.026152556580050293,
568
+ "grad_norm": 1.846153974533081,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 1.9918,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.026487845766974015,
575
+ "grad_norm": 1.8405578136444092,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 2.0667,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.026823134953897737,
582
+ "grad_norm": 1.7012615203857422,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 2.2575,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.02715842414082146,
589
+ "grad_norm": 1.868895173072815,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 2.0323,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.02749371332774518,
596
+ "grad_norm": 1.862149953842163,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 2.1767,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.027829002514668903,
603
+ "grad_norm": 1.9703943729400635,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 2.0881,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.028164291701592625,
610
+ "grad_norm": 1.7949926853179932,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 2.2016,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.028499580888516344,
617
+ "grad_norm": 1.8068915605545044,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 2.2612,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.028834870075440066,
624
+ "grad_norm": 2.0017426013946533,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 2.0378,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.029170159262363788,
631
+ "grad_norm": 1.7997188568115234,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 1.8471,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.02950544844928751,
638
+ "grad_norm": 2.1644763946533203,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 2.0321,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.029840737636211232,
645
+ "grad_norm": 1.910346269607544,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 2.0989,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.030176026823134954,
652
+ "grad_norm": 1.8434735536575317,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 1.9885,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.030511316010058676,
659
+ "grad_norm": 2.194366216659546,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 2.1688,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0308466051969824,
666
+ "grad_norm": 1.953049659729004,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 2.1352,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03118189438390612,
673
+ "grad_norm": 2.183722734451294,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 2.3673,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.03151718357082984,
680
+ "grad_norm": 1.875823736190796,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 2.045,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03185247275775356,
687
+ "grad_norm": 1.9691027402877808,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 2.3289,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03218776194467728,
694
+ "grad_norm": 1.7443435192108154,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 2.033,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.032523051131601005,
701
+ "grad_norm": 1.6460736989974976,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 1.9156,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.03285834031852473,
708
+ "grad_norm": 1.6413999795913696,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 2.1261,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03319362950544845,
715
+ "grad_norm": 1.6792007684707642,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 2.001,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.03352891869237217,
722
+ "grad_norm": 2.3478386402130127,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 2.215,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.03352891869237217,
729
+ "eval_loss": 1.971840500831604,
730
+ "eval_runtime": 415.4443,
731
+ "eval_samples_per_second": 12.091,
732
+ "eval_steps_per_second": 6.047,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null