lesso commited on
Commit
c47cc8f
·
verified ·
1 Parent(s): 486bb12

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 sha256:5f5c132cd92d9f959e7893787dab38469aee90ecde18c53f4f621789200e1cef
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d3c368e3744a87120fa02b36def8c35ae56a3e176e906cea85f5b81b3bbe08
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c88840ce32ec50b60bbf729ab3267ffc4ca8301216b8814196aaa6048f9bbc2
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5406c8b7bb921e9147a6706c9b5e19b42cd291e65d4ce13820cc1b514341edd5
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0facd3c71075a0e7ff3447d1fba153ffae8c05df82ae753ec32022b1be6ce921
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0636ac1e1cd9b5ed3b02f674cf2400e6388a98470c99628f3f15decd2b55b27
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": 0.5220252871513367,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.009804882831650161,
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": 8.842,
374
  "eval_steps_per_second": 2.211,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.9139619912155136e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.4575375020503998,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.019609765663300322,
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": 8.842,
374
  "eval_steps_per_second": 2.211,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.010000980488283165,
379
+ "grad_norm": 6.259135723114014,
380
+ "learning_rate": 7.944052631578947e-05,
381
+ "loss": 1.9433,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.010197078144916168,
386
+ "grad_norm": 3.87833833694458,
387
+ "learning_rate": 7.890736842105263e-05,
388
+ "loss": 0.925,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.010393175801549172,
393
+ "grad_norm": 3.702810764312744,
394
+ "learning_rate": 7.837421052631579e-05,
395
+ "loss": 0.8375,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.010589273458182174,
400
+ "grad_norm": 3.9069197177886963,
401
+ "learning_rate": 7.784105263157893e-05,
402
+ "loss": 0.7016,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.010785371114815178,
407
+ "grad_norm": 4.089141845703125,
408
+ "learning_rate": 7.730789473684211e-05,
409
+ "loss": 0.736,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.01098146877144818,
414
+ "grad_norm": 4.299583435058594,
415
+ "learning_rate": 7.677473684210526e-05,
416
+ "loss": 0.9623,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.011177566428081185,
421
+ "grad_norm": 4.404727458953857,
422
+ "learning_rate": 7.624157894736842e-05,
423
+ "loss": 0.9444,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.011373664084714187,
428
+ "grad_norm": 3.662179470062256,
429
+ "learning_rate": 7.570842105263158e-05,
430
+ "loss": 0.7267,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.011569761741347192,
435
+ "grad_norm": 5.034608364105225,
436
+ "learning_rate": 7.517526315789474e-05,
437
+ "loss": 0.8414,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.011765859397980194,
442
+ "grad_norm": 4.015024185180664,
443
+ "learning_rate": 7.464210526315789e-05,
444
+ "loss": 0.7682,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.011961957054613198,
449
+ "grad_norm": 3.8569846153259277,
450
+ "learning_rate": 7.410894736842106e-05,
451
+ "loss": 0.7419,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0121580547112462,
456
+ "grad_norm": 5.50112247467041,
457
+ "learning_rate": 7.35757894736842e-05,
458
+ "loss": 0.789,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.012354152367879203,
463
+ "grad_norm": 4.346161842346191,
464
+ "learning_rate": 7.304263157894737e-05,
465
+ "loss": 0.7292,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.012550250024512207,
470
+ "grad_norm": 12.474294662475586,
471
+ "learning_rate": 7.250947368421053e-05,
472
+ "loss": 0.8405,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.01274634768114521,
477
+ "grad_norm": 6.171235084533691,
478
+ "learning_rate": 7.197631578947368e-05,
479
+ "loss": 0.9972,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.012942445337778214,
484
+ "grad_norm": 10.865174293518066,
485
+ "learning_rate": 7.144315789473684e-05,
486
+ "loss": 0.6531,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.013138542994411216,
491
+ "grad_norm": 5.450807094573975,
492
+ "learning_rate": 7.091e-05,
493
+ "loss": 0.9603,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01333464065104422,
498
+ "grad_norm": 5.7336015701293945,
499
+ "learning_rate": 7.037684210526316e-05,
500
+ "loss": 0.9774,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.013530738307677223,
505
+ "grad_norm": 5.6365156173706055,
506
+ "learning_rate": 6.984368421052632e-05,
507
+ "loss": 0.7666,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.013726835964310227,
512
+ "grad_norm": 7.478610992431641,
513
+ "learning_rate": 6.931052631578947e-05,
514
+ "loss": 0.7726,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.01392293362094323,
519
+ "grad_norm": 5.047933578491211,
520
+ "learning_rate": 6.877736842105263e-05,
521
+ "loss": 0.5822,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.014119031277576233,
526
+ "grad_norm": 6.480734348297119,
527
+ "learning_rate": 6.824421052631579e-05,
528
+ "loss": 0.7629,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.014315128934209236,
533
+ "grad_norm": 7.191463470458984,
534
+ "learning_rate": 6.771105263157895e-05,
535
+ "loss": 0.6803,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.01451122659084224,
540
+ "grad_norm": 4.883853435516357,
541
+ "learning_rate": 6.71778947368421e-05,
542
+ "loss": 0.6785,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.014707324247475242,
547
+ "grad_norm": 6.941567420959473,
548
+ "learning_rate": 6.664473684210527e-05,
549
+ "loss": 0.8324,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.014903421904108247,
554
+ "grad_norm": 6.098438739776611,
555
+ "learning_rate": 6.611157894736842e-05,
556
+ "loss": 0.8325,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.015099519560741249,
561
+ "grad_norm": 8.49299144744873,
562
+ "learning_rate": 6.557842105263158e-05,
563
+ "loss": 1.1349,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.015295617217374253,
568
+ "grad_norm": 4.6161627769470215,
569
+ "learning_rate": 6.504526315789474e-05,
570
+ "loss": 0.3797,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.015491714874007256,
575
+ "grad_norm": 5.683040142059326,
576
+ "learning_rate": 6.451210526315789e-05,
577
+ "loss": 0.4784,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.01568781253064026,
582
+ "grad_norm": 7.138983249664307,
583
+ "learning_rate": 6.397894736842105e-05,
584
+ "loss": 0.6783,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01588391018727326,
589
+ "grad_norm": 5.301764488220215,
590
+ "learning_rate": 6.344578947368421e-05,
591
+ "loss": 0.4013,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.016080007843906265,
596
+ "grad_norm": 5.394726753234863,
597
+ "learning_rate": 6.291263157894737e-05,
598
+ "loss": 0.472,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.01627610550053927,
603
+ "grad_norm": 7.571673393249512,
604
+ "learning_rate": 6.237947368421053e-05,
605
+ "loss": 0.6222,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.016472203157172273,
610
+ "grad_norm": 13.990236282348633,
611
+ "learning_rate": 6.184631578947368e-05,
612
+ "loss": 1.5111,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.016668300813805274,
617
+ "grad_norm": 9.939437866210938,
618
+ "learning_rate": 6.131315789473684e-05,
619
+ "loss": 1.2702,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.016864398470438278,
624
+ "grad_norm": 11.926310539245605,
625
+ "learning_rate": 6.078e-05,
626
+ "loss": 0.997,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.017060496127071282,
631
+ "grad_norm": 7.9521379470825195,
632
+ "learning_rate": 6.024684210526315e-05,
633
+ "loss": 0.8637,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.017256593783704286,
638
+ "grad_norm": 11.58044147491455,
639
+ "learning_rate": 5.9713684210526305e-05,
640
+ "loss": 1.3852,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.017452691440337287,
645
+ "grad_norm": 9.782970428466797,
646
+ "learning_rate": 5.918052631578947e-05,
647
+ "loss": 0.8799,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.01764878909697029,
652
+ "grad_norm": 10.114582061767578,
653
+ "learning_rate": 5.8647368421052634e-05,
654
+ "loss": 1.1961,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.017844886753603295,
659
+ "grad_norm": 12.574527740478516,
660
+ "learning_rate": 5.811421052631579e-05,
661
+ "loss": 1.0894,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0180409844102363,
666
+ "grad_norm": 14.899230003356934,
667
+ "learning_rate": 5.758105263157894e-05,
668
+ "loss": 1.2862,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0182370820668693,
673
+ "grad_norm": 8.636293411254883,
674
+ "learning_rate": 5.70478947368421e-05,
675
+ "loss": 0.854,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.018433179723502304,
680
+ "grad_norm": 11.84518814086914,
681
+ "learning_rate": 5.6514736842105256e-05,
682
+ "loss": 0.6895,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.01862927738013531,
687
+ "grad_norm": 28.145517349243164,
688
+ "learning_rate": 5.5981578947368424e-05,
689
+ "loss": 1.5005,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.01882537503676831,
694
+ "grad_norm": 13.958025932312012,
695
+ "learning_rate": 5.544842105263158e-05,
696
+ "loss": 0.4707,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.019021472693401313,
701
+ "grad_norm": 14.421865463256836,
702
+ "learning_rate": 5.491526315789474e-05,
703
+ "loss": 1.3302,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.019217570350034317,
708
+ "grad_norm": 19.330612182617188,
709
+ "learning_rate": 5.438210526315789e-05,
710
+ "loss": 1.0502,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.01941366800666732,
715
+ "grad_norm": 16.62639045715332,
716
+ "learning_rate": 5.384894736842105e-05,
717
+ "loss": 1.2102,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.019609765663300322,
722
+ "grad_norm": 26.352754592895508,
723
+ "learning_rate": 5.331578947368421e-05,
724
+ "loss": 1.9532,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.019609765663300322,
729
+ "eval_loss": 0.4575375020503998,
730
+ "eval_runtime": 243.2626,
731
+ "eval_samples_per_second": 8.83,
732
+ "eval_steps_per_second": 2.207,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.774261496696013e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null