lesso commited on
Commit
ba92ddb
·
verified ·
1 Parent(s): c173228

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 sha256:6a4eb20df0311e6f6bbacacdd30a50a8605e6d67ea54db4b6b5c88159faf8929
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00789afdf1298113eb5db8f405596c2943b3740715f3a974fba6eb4cb82ffb85
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b189bb37771004e6fda5c8c303fb008775d43cbef06a52fb72472646aaa70e9b
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51de54048560f61b1fffadcce54ac9ca17cf9088f9317cae4b99d07672a1993f
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd4323d146bdd5eca8ff387897d83c707dc98b0b1c889243384b51e24cf7a3c7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd41f0eb63f76991fd9773adcdcd219526a8c1ac4271f5e0f155536249e18f2e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff52bfbef9cf63f1b4a99aeb499cfc330b3f7bf178a825c21249094bbf544e39
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a046f3bc9d619a7e62601f3cf33ff02f6ad189db5b564eab88c1bb00e13b059d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3799381256103516,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0015640396014827095,
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": 9.257,
374
  "eval_steps_per_second": 2.315,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.806637019745485e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3124351501464844,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.003128079202965419,
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": 9.257,
374
  "eval_steps_per_second": 2.315,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0015953203935123637,
379
+ "grad_norm": 3.6396615505218506,
380
+ "learning_rate": 7.944052631578947e-05,
381
+ "loss": 1.8916,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0016266011855420178,
386
+ "grad_norm": 5.276243686676025,
387
+ "learning_rate": 7.890736842105263e-05,
388
+ "loss": 2.152,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0016578819775716722,
393
+ "grad_norm": 3.8016412258148193,
394
+ "learning_rate": 7.837421052631579e-05,
395
+ "loss": 2.4937,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0016891627696013264,
400
+ "grad_norm": 5.2608866691589355,
401
+ "learning_rate": 7.784105263157893e-05,
402
+ "loss": 2.9087,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0017204435616309805,
407
+ "grad_norm": 6.502185821533203,
408
+ "learning_rate": 7.730789473684211e-05,
409
+ "loss": 2.9029,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0017517243536606347,
414
+ "grad_norm": 8.368294715881348,
415
+ "learning_rate": 7.677473684210526e-05,
416
+ "loss": 3.5712,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0017830051456902889,
421
+ "grad_norm": 7.264784336090088,
422
+ "learning_rate": 7.624157894736842e-05,
423
+ "loss": 3.641,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.001814285937719943,
428
+ "grad_norm": 5.740438938140869,
429
+ "learning_rate": 7.570842105263158e-05,
430
+ "loss": 3.4282,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0018455667297495972,
435
+ "grad_norm": 8.016144752502441,
436
+ "learning_rate": 7.517526315789474e-05,
437
+ "loss": 2.8895,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0018768475217792514,
442
+ "grad_norm": 5.884403705596924,
443
+ "learning_rate": 7.464210526315789e-05,
444
+ "loss": 3.003,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0019081283138089055,
449
+ "grad_norm": 4.902200698852539,
450
+ "learning_rate": 7.410894736842106e-05,
451
+ "loss": 2.6912,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.00193940910583856,
456
+ "grad_norm": 5.990637302398682,
457
+ "learning_rate": 7.35757894736842e-05,
458
+ "loss": 3.2658,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.001970689897868214,
463
+ "grad_norm": 6.27999210357666,
464
+ "learning_rate": 7.304263157894737e-05,
465
+ "loss": 2.6262,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.002001970689897868,
470
+ "grad_norm": 6.293524742126465,
471
+ "learning_rate": 7.250947368421053e-05,
472
+ "loss": 2.9332,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0020332514819275224,
477
+ "grad_norm": 5.076088905334473,
478
+ "learning_rate": 7.197631578947368e-05,
479
+ "loss": 2.4266,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0020645322739571764,
484
+ "grad_norm": 8.73829174041748,
485
+ "learning_rate": 7.144315789473684e-05,
486
+ "loss": 2.8764,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0020958130659868308,
491
+ "grad_norm": 6.070854663848877,
492
+ "learning_rate": 7.091e-05,
493
+ "loss": 2.3547,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.002127093858016485,
498
+ "grad_norm": 6.758303642272949,
499
+ "learning_rate": 7.037684210526316e-05,
500
+ "loss": 2.4258,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.002158374650046139,
505
+ "grad_norm": 6.710521221160889,
506
+ "learning_rate": 6.984368421052632e-05,
507
+ "loss": 2.8411,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0021896554420757935,
512
+ "grad_norm": 5.664976119995117,
513
+ "learning_rate": 6.931052631578947e-05,
514
+ "loss": 2.7535,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.0022209362341054474,
519
+ "grad_norm": 5.253357887268066,
520
+ "learning_rate": 6.877736842105263e-05,
521
+ "loss": 2.4245,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.002252217026135102,
526
+ "grad_norm": 7.573156833648682,
527
+ "learning_rate": 6.824421052631579e-05,
528
+ "loss": 2.8877,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0022834978181647558,
533
+ "grad_norm": 7.890182971954346,
534
+ "learning_rate": 6.771105263157895e-05,
535
+ "loss": 2.8596,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.00231477861019441,
540
+ "grad_norm": 6.137823104858398,
541
+ "learning_rate": 6.71778947368421e-05,
542
+ "loss": 2.5406,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.002346059402224064,
547
+ "grad_norm": 6.550741195678711,
548
+ "learning_rate": 6.664473684210527e-05,
549
+ "loss": 2.3237,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0023773401942537185,
554
+ "grad_norm": 7.004899978637695,
555
+ "learning_rate": 6.611157894736842e-05,
556
+ "loss": 2.1531,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.002408620986283373,
561
+ "grad_norm": 6.756047248840332,
562
+ "learning_rate": 6.557842105263158e-05,
563
+ "loss": 2.5744,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.002439901778313027,
568
+ "grad_norm": 8.45261287689209,
569
+ "learning_rate": 6.504526315789474e-05,
570
+ "loss": 2.2788,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0024711825703426812,
575
+ "grad_norm": 7.253743648529053,
576
+ "learning_rate": 6.451210526315789e-05,
577
+ "loss": 2.7263,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.002502463362372335,
582
+ "grad_norm": 7.247540473937988,
583
+ "learning_rate": 6.397894736842105e-05,
584
+ "loss": 2.0866,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.0025337441544019896,
589
+ "grad_norm": 6.436933994293213,
590
+ "learning_rate": 6.344578947368421e-05,
591
+ "loss": 2.6969,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0025650249464316435,
596
+ "grad_norm": 6.152482509613037,
597
+ "learning_rate": 6.291263157894737e-05,
598
+ "loss": 2.7461,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.002596305738461298,
603
+ "grad_norm": 7.333639621734619,
604
+ "learning_rate": 6.237947368421053e-05,
605
+ "loss": 2.6492,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.002627586530490952,
610
+ "grad_norm": 5.620179176330566,
611
+ "learning_rate": 6.184631578947368e-05,
612
+ "loss": 2.432,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.0026588673225206062,
617
+ "grad_norm": 6.900599479675293,
618
+ "learning_rate": 6.131315789473684e-05,
619
+ "loss": 2.4198,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0026901481145502606,
624
+ "grad_norm": 7.6465559005737305,
625
+ "learning_rate": 6.078e-05,
626
+ "loss": 2.1368,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.0027214289065799146,
631
+ "grad_norm": 7.627400875091553,
632
+ "learning_rate": 6.024684210526315e-05,
633
+ "loss": 2.3818,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.002752709698609569,
638
+ "grad_norm": 7.236347198486328,
639
+ "learning_rate": 5.9713684210526305e-05,
640
+ "loss": 2.2773,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.002783990490639223,
645
+ "grad_norm": 9.498893737792969,
646
+ "learning_rate": 5.918052631578947e-05,
647
+ "loss": 2.6348,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0028152712826688773,
652
+ "grad_norm": 6.960134983062744,
653
+ "learning_rate": 5.8647368421052634e-05,
654
+ "loss": 2.4035,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.0028465520746985312,
659
+ "grad_norm": 7.996723651885986,
660
+ "learning_rate": 5.811421052631579e-05,
661
+ "loss": 2.4397,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0028778328667281856,
666
+ "grad_norm": 8.388598442077637,
667
+ "learning_rate": 5.758105263157894e-05,
668
+ "loss": 2.3052,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0029091136587578396,
673
+ "grad_norm": 9.838214874267578,
674
+ "learning_rate": 5.70478947368421e-05,
675
+ "loss": 2.1201,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.002940394450787494,
680
+ "grad_norm": 7.014636039733887,
681
+ "learning_rate": 5.6514736842105256e-05,
682
+ "loss": 1.9283,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0029716752428171483,
687
+ "grad_norm": 6.765852928161621,
688
+ "learning_rate": 5.5981578947368424e-05,
689
+ "loss": 2.1875,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.0030029560348468023,
694
+ "grad_norm": 7.371057033538818,
695
+ "learning_rate": 5.544842105263158e-05,
696
+ "loss": 2.3463,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0030342368268764567,
701
+ "grad_norm": 9.242403030395508,
702
+ "learning_rate": 5.491526315789474e-05,
703
+ "loss": 2.9248,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0030655176189061106,
708
+ "grad_norm": 7.47991943359375,
709
+ "learning_rate": 5.438210526315789e-05,
710
+ "loss": 2.5732,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.003096798410935765,
715
+ "grad_norm": 10.116243362426758,
716
+ "learning_rate": 5.384894736842105e-05,
717
+ "loss": 3.2258,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.003128079202965419,
722
+ "grad_norm": 10.563674926757812,
723
+ "learning_rate": 5.331578947368421e-05,
724
+ "loss": 2.8873,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.003128079202965419,
729
+ "eval_loss": 1.3124351501464844,
730
+ "eval_runtime": 1453.2201,
731
+ "eval_samples_per_second": 9.263,
732
+ "eval_steps_per_second": 2.316,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.61327403949097e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null