aleegis10 commited on
Commit
f98ce0d
·
verified ·
1 Parent(s): 3267c80

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:c201bca7811d1f7f0474b8e2c04497391d4b8924f2ca6d1cd3e4d58f276325e2
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b2513556582afa8b79ca9853a28bf9cb25fd49a888a5aa979732e64f652526
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:116246a96988004a7e19f91b3a10d271b63ad9db54e2b1ad4b8ba6e78e3b045d
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ac04a92114334d8ea5bdf4ca9fb67947f0f94940344760f560f3fac20ce091
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a310466eceedb02f0bdcb08ab26da81c47e290b1ad00a62737818f3bb2803b4f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3f03b46374f712a1b6df3d3dd8a08ace6b544f927ee0a0d4e9bdfc6d3b1262
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": 0.8124762773513794,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.042634832658281815,
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": 33.936,
374
  "eval_steps_per_second": 8.488,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -387,7 +745,7 @@
387
  "early_stopping_threshold": 0.0
388
  },
389
  "attributes": {
390
- "early_stopping_patience_counter": 0
391
  }
392
  },
393
  "TrainerControl": {
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.3607236534272e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
  "best_metric": 0.8124762773513794,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.08526966531656363,
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": 33.936,
374
  "eval_steps_per_second": 8.488,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.043487529311447455,
379
+ "grad_norm": 0.5274108052253723,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.8853,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.04434022596461309,
386
+ "grad_norm": 0.33259961009025574,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.8799,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.04519292261777873,
393
+ "grad_norm": 0.24594545364379883,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.8628,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.04604561927094436,
400
+ "grad_norm": 0.26643481850624084,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.8569,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.04689831592411,
407
+ "grad_norm": 0.2917613089084625,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.8605,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.04775101257727563,
414
+ "grad_norm": 0.2499927282333374,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.8414,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.04860370923044127,
421
+ "grad_norm": 0.28645575046539307,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.8457,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.049456405883606905,
428
+ "grad_norm": 0.21827077865600586,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.8083,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.050309102536772544,
435
+ "grad_norm": 0.2010735720396042,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.8216,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.05116179918993818,
442
+ "grad_norm": 0.1909765750169754,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.8048,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.05201449584310382,
449
+ "grad_norm": 0.24219320714473724,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.7889,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.05286719249626945,
456
+ "grad_norm": 0.17573778331279755,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.814,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.05371988914943509,
463
+ "grad_norm": 0.23709945380687714,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.8261,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.05457258580260072,
470
+ "grad_norm": 0.21676595509052277,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.7994,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.05542528245576636,
477
+ "grad_norm": 0.17138059437274933,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.8102,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.056277979108931994,
484
+ "grad_norm": 0.18411117792129517,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.804,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.057130675762097634,
491
+ "grad_norm": 0.19111822545528412,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.8327,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.05798337241526327,
498
+ "grad_norm": 0.19528895616531372,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.7985,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.058836069068428906,
505
+ "grad_norm": 0.1888338029384613,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.8167,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.059688765721594546,
512
+ "grad_norm": 0.22683273255825043,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.7919,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.06054146237476018,
519
+ "grad_norm": 0.15248703956604004,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.792,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.06139415902792582,
526
+ "grad_norm": 0.18784311413764954,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.7936,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.06224685568109145,
533
+ "grad_norm": 0.17048968374729156,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.7831,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.06309955233425708,
540
+ "grad_norm": 0.23277565836906433,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.7738,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.06395224898742273,
547
+ "grad_norm": 0.20944736897945404,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.7691,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.06480494564058836,
554
+ "grad_norm": 0.2625070810317993,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.767,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.065657642293754,
561
+ "grad_norm": 0.2656240165233612,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.7851,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.06651033894691963,
568
+ "grad_norm": 0.2506884038448334,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.7849,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.06736303560008527,
575
+ "grad_norm": 0.26329290866851807,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.7634,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.06821573225325091,
582
+ "grad_norm": 0.2922832667827606,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.7789,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.06906842890641654,
589
+ "grad_norm": 0.2070065587759018,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.7471,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.06992112555958217,
596
+ "grad_norm": 0.22126182913780212,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.7526,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.07077382221274782,
603
+ "grad_norm": 0.24803754687309265,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.7666,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.07162651886591345,
610
+ "grad_norm": 0.22475339472293854,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.7343,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.07247921551907908,
617
+ "grad_norm": 0.28123778104782104,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.7358,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.07333191217224472,
624
+ "grad_norm": 0.18979664146900177,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.7297,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.07418460882541036,
631
+ "grad_norm": 0.25829166173934937,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.7398,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.075037305478576,
638
+ "grad_norm": 0.26326870918273926,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.7444,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.07589000213174163,
645
+ "grad_norm": 0.3127356767654419,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.7195,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.07674269878490728,
652
+ "grad_norm": 0.2700917720794678,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.7342,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.07759539543807291,
659
+ "grad_norm": 0.27919384837150574,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.7388,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.07844809209123854,
666
+ "grad_norm": 0.3218565285205841,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.765,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.07930078874440417,
673
+ "grad_norm": 0.2563426196575165,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.7267,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.08015348539756982,
680
+ "grad_norm": 0.36784499883651733,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.7639,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.08100618205073545,
687
+ "grad_norm": 0.2592979669570923,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.7315,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.08185887870390109,
694
+ "grad_norm": 0.254527747631073,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.718,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.08271157535706672,
701
+ "grad_norm": 0.2726317346096039,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.7653,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.08356427201023237,
708
+ "grad_norm": 0.2646251320838928,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.7521,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.084416968663398,
715
+ "grad_norm": 0.2835654616355896,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.7306,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.08526966531656363,
722
+ "grad_norm": 0.39553532004356384,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.6667,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.08526966531656363,
729
+ "eval_loss": 0.8160770535469055,
730
+ "eval_runtime": 58.2628,
731
+ "eval_samples_per_second": 33.898,
732
+ "eval_steps_per_second": 8.479,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
745
  "early_stopping_threshold": 0.0
746
  },
747
  "attributes": {
748
+ "early_stopping_patience_counter": 1
749
  }
750
  },
751
  "TrainerControl": {
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.7214473068544e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null