bbytxt commited on
Commit
0a32be7
·
verified ·
1 Parent(s): b59ecd4

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 sha256:85c92f4d54752443d0e0f7c9726fe3bbc1a7749fbdda059b86a3348702124181
3
  size 247944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19bb03d1b5ce94804c28924136ef9479989a2ee7e46dfb99bdcbbebf04ceec15
3
  size 247944
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7623f1a80de116d086c576d2dfdb2416fa5ca754db86d2ea7806ae28519e79dc
3
  size 505518
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5330f5f7e34c3fe29f46ea47a9bed677eec5b4e26ef5f7a126fe59aa270fbd
3
  size 505518
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d57df5277b48543db26e485a124f92dd7eef3fb323e6aef28e47e6e9dc22547f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95f6af0370ab9872f137fc9f0c876c812419b55adda3334e3d761f121ee85c66
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
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": 10.9691801071167,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.7736943907156673,
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": 402.965,
374
  "eval_steps_per_second": 103.514,
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": 4191110037504.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.950401306152344,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.551257253384913,
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": 402.965,
374
  "eval_steps_per_second": 103.514,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.7891682785299806,
379
+ "grad_norm": 19.094087600708008,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 87.6992,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.804642166344294,
386
+ "grad_norm": 18.731935501098633,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 87.9922,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.8201160541586073,
393
+ "grad_norm": 18.777690887451172,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 87.9531,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.8355899419729207,
400
+ "grad_norm": 18.983760833740234,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 87.9883,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.851063829787234,
407
+ "grad_norm": 19.079267501831055,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 87.7617,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.8665377176015474,
414
+ "grad_norm": 19.1731014251709,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 87.707,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.8820116054158608,
421
+ "grad_norm": 18.95149803161621,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 88.1133,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.8974854932301741,
428
+ "grad_norm": 19.376663208007812,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 88.168,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.9129593810444874,
435
+ "grad_norm": 18.914901733398438,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 87.8789,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.9284332688588007,
442
+ "grad_norm": 19.372947692871094,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 87.5039,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.9439071566731141,
449
+ "grad_norm": 19.31951904296875,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 87.7539,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.9593810444874274,
456
+ "grad_norm": 18.900074005126953,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 87.9883,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.9748549323017408,
463
+ "grad_norm": 18.852619171142578,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 87.7383,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.9903288201160542,
470
+ "grad_norm": 19.459726333618164,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 87.6445,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.009671179883946,
477
+ "grad_norm": 19.47203826904297,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 87.8477,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.0251450676982592,
484
+ "grad_norm": 19.116628646850586,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 87.9453,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.0406189555125724,
491
+ "grad_norm": 19.162620544433594,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 87.6914,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.056092843326886,
498
+ "grad_norm": 18.91712188720703,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 87.832,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.0715667311411992,
505
+ "grad_norm": 19.34943199157715,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 87.7305,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.0870406189555126,
512
+ "grad_norm": 19.26616668701172,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 87.7969,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.1025145067698259,
519
+ "grad_norm": 19.212594985961914,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 87.9258,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.1179883945841393,
526
+ "grad_norm": 19.052566528320312,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 87.7031,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.1334622823984526,
533
+ "grad_norm": 19.17568588256836,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 87.8242,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.148936170212766,
540
+ "grad_norm": 19.76246452331543,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 87.918,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.1644100580270793,
547
+ "grad_norm": 19.311172485351562,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 87.9023,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.1798839458413926,
554
+ "grad_norm": 19.15486717224121,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 87.7305,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.195357833655706,
561
+ "grad_norm": 19.333757400512695,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 87.5391,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.2108317214700193,
568
+ "grad_norm": 19.257543563842773,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 87.7422,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.2263056092843327,
575
+ "grad_norm": 19.28775978088379,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 87.7383,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.241779497098646,
582
+ "grad_norm": 19.506193161010742,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 87.7227,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.2572533849129595,
589
+ "grad_norm": 19.187644958496094,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 87.8867,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.2727272727272727,
596
+ "grad_norm": 19.333215713500977,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 87.5742,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.2882011605415862,
603
+ "grad_norm": 19.336074829101562,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 87.6484,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.3036750483558994,
610
+ "grad_norm": 19.418418884277344,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 87.8086,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.3191489361702127,
617
+ "grad_norm": 19.10855484008789,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 87.707,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.3346228239845261,
624
+ "grad_norm": 19.175275802612305,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 88.0195,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.3500967117988394,
631
+ "grad_norm": 19.408702850341797,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 88.1445,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.3655705996131529,
638
+ "grad_norm": 20.170278549194336,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 87.6406,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.381044487427466,
645
+ "grad_norm": 19.291183471679688,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 87.7617,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.3965183752417796,
652
+ "grad_norm": 19.194232940673828,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 87.7305,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.4119922630560928,
659
+ "grad_norm": 19.09023666381836,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 87.8633,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.4274661508704063,
666
+ "grad_norm": 19.408191680908203,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 87.6992,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.4429400386847195,
673
+ "grad_norm": 19.612468719482422,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 87.6211,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.4584139264990328,
680
+ "grad_norm": 19.32954978942871,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 87.8281,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.4738878143133463,
687
+ "grad_norm": 19.18812370300293,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 87.8672,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.4893617021276595,
694
+ "grad_norm": 19.7600040435791,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 87.4727,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.504835589941973,
701
+ "grad_norm": 19.480730056762695,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 87.6758,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.5203094777562862,
708
+ "grad_norm": 19.695844650268555,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 88.1094,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.5357833655705995,
715
+ "grad_norm": 19.0916748046875,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 88.0156,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.551257253384913,
722
+ "grad_norm": 19.111989974975586,
723
+ "learning_rate": 0.0,
724
+ "loss": 87.7383,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.551257253384913,
729
+ "eval_loss": 10.950401306152344,
730
+ "eval_runtime": 0.2689,
731
+ "eval_samples_per_second": 405.39,
732
+ "eval_steps_per_second": 104.137,
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": 8361420521472.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null