nttx commited on
Commit
73a9e23
·
verified ·
1 Parent(s): 610ed18

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 sha256:7c58da1217f71b44d4c9d2caac92916f34ad8a07f6bc657650f8fd0a0073862d
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f59c03e0db6e28e6264baf54723e9200176bf6aae719a51b41d81b573893054
3
  size 83115256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee3af30333a689ba6e38b0db905197e59fa2103e4b7f22c82a95cfb57a1c47a6
3
  size 166439638
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05362f8e708da0f6fab3dbb2851ab26a2d238c5907f7c83df3a5463cc6e3638
3
  size 166439638
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5c5bb441bbc6d262df4ef0f6f28cec35031fef61c4955cb20d2972dc177b7e4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6f7cbd62dd1dd1abad27b2e9bc108a1841e8f3477190f33f916fadcc76e787
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.19923071563243866,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.05980861244019139,
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": 19.888,
374
  "eval_steps_per_second": 4.972,
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": 1.0103247819767808e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.15960238873958588,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.11961722488038277,
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": 19.888,
374
  "eval_steps_per_second": 4.972,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.061004784688995214,
379
+ "grad_norm": 0.7308669090270996,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 0.1903,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.06220095693779904,
386
+ "grad_norm": 0.8045475482940674,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 0.2067,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.06339712918660287,
393
+ "grad_norm": 0.8171185851097107,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 0.2032,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0645933014354067,
400
+ "grad_norm": 0.6744611859321594,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 0.1581,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.06578947368421052,
407
+ "grad_norm": 0.7448108792304993,
408
+ "learning_rate": 5e-05,
409
+ "loss": 0.1815,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.06698564593301436,
414
+ "grad_norm": 0.7760705351829529,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 0.1738,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.06818181818181818,
421
+ "grad_norm": 0.8528043031692505,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 0.1841,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.06937799043062201,
428
+ "grad_norm": 0.905849277973175,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 0.1738,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.07057416267942583,
435
+ "grad_norm": 0.8059756755828857,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 0.1722,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.07177033492822966,
442
+ "grad_norm": 0.8063069581985474,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 0.1927,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0729665071770335,
449
+ "grad_norm": 0.825333833694458,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 0.1445,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.07416267942583732,
456
+ "grad_norm": 0.8422712087631226,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 0.1558,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.07535885167464115,
463
+ "grad_norm": 0.9840994477272034,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 0.1733,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.07655502392344497,
470
+ "grad_norm": 0.8723501563072205,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 0.1491,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.07775119617224881,
477
+ "grad_norm": 0.8056702017784119,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 0.1573,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.07894736842105263,
484
+ "grad_norm": 0.8925252556800842,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 0.1795,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.08014354066985646,
491
+ "grad_norm": 0.9729580283164978,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 0.1791,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.08133971291866028,
498
+ "grad_norm": 1.0415399074554443,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 0.177,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.08253588516746412,
505
+ "grad_norm": 0.8020843863487244,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 0.1268,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.08373205741626795,
512
+ "grad_norm": 0.8391036987304688,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 0.1344,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.08492822966507177,
519
+ "grad_norm": 1.1039748191833496,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 0.1954,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.0861244019138756,
526
+ "grad_norm": 0.9647433757781982,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 0.1759,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.08732057416267942,
533
+ "grad_norm": 0.9805471301078796,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 0.1625,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.08851674641148326,
540
+ "grad_norm": 0.9431953430175781,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 0.1464,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.08971291866028708,
547
+ "grad_norm": 0.9271813631057739,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 0.1374,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.09090909090909091,
554
+ "grad_norm": 1.0403175354003906,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 0.1637,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.09210526315789473,
561
+ "grad_norm": 0.9993944764137268,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 0.1522,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.09330143540669857,
568
+ "grad_norm": 1.0364563465118408,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 0.1471,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.09449760765550239,
575
+ "grad_norm": 0.8725647926330566,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 0.1113,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.09569377990430622,
582
+ "grad_norm": 0.9386890530586243,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 0.1104,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.09688995215311005,
589
+ "grad_norm": 1.0741575956344604,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 0.1286,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.09808612440191387,
596
+ "grad_norm": 1.2276641130447388,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 0.1517,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.09928229665071771,
603
+ "grad_norm": 1.12937593460083,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 0.1482,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.10047846889952153,
610
+ "grad_norm": 1.1188244819641113,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 0.1201,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.10167464114832536,
617
+ "grad_norm": 1.406683325767517,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 0.2082,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.10287081339712918,
624
+ "grad_norm": 1.214578628540039,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 0.186,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.10406698564593302,
631
+ "grad_norm": 1.270246148109436,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 0.1308,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.10526315789473684,
638
+ "grad_norm": 1.2750657796859741,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 0.1296,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.10645933014354067,
645
+ "grad_norm": 1.4091739654541016,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 0.1985,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.1076555023923445,
652
+ "grad_norm": 1.3769253492355347,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 0.1777,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.10885167464114832,
659
+ "grad_norm": 1.5859569311141968,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 0.1514,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.11004784688995216,
666
+ "grad_norm": 1.3966237306594849,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 0.1825,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.11124401913875598,
673
+ "grad_norm": 1.6977550983428955,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 0.1799,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.11244019138755981,
680
+ "grad_norm": 1.6813634634017944,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 0.1539,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.11363636363636363,
687
+ "grad_norm": 2.3753628730773926,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 0.2349,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.11483253588516747,
694
+ "grad_norm": 2.1884944438934326,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 0.2109,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.11602870813397129,
701
+ "grad_norm": 1.6471924781799316,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 0.1618,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.11722488038277512,
708
+ "grad_norm": 1.5181317329406738,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 0.102,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.11842105263157894,
715
+ "grad_norm": 5.536009788513184,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 0.5176,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.11961722488038277,
722
+ "grad_norm": 5.12874174118042,
723
+ "learning_rate": 0.0,
724
+ "loss": 0.2482,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.11961722488038277,
729
+ "eval_loss": 0.15960238873958588,
730
+ "eval_runtime": 35.4137,
731
+ "eval_samples_per_second": 19.879,
732
+ "eval_steps_per_second": 4.97,
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": 2.015623072500941e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null