lesso commited on
Commit
3067c4f
·
verified ·
1 Parent(s): c9134ef

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:a4256d7260da585cb38362625d5c6c6e714abf4c45c670df626b52ddd7d74b7d
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957a4335205b6293dabccea2cc8744e323101fe3128e892012c6398f3141b97e
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8cdfe117c660bcfd09b6659bcb97f09c2056cd54396e7bf0eac94e04133ba46
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e5da87183a0813f8e9b5e9df69cd1747666430fbc5bee02b42d7cba5a82ab8
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1983f721b360ca749bb29929a8141bbaf32429407675fa911781f839e1292ce6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa43bf4d3f1fc37c97372564e0bcfe641d92f3fc335e8df4b873fb1923b99d0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14c7988274ea42082ca98c4badf72b98ef1698024d0fb100dd463f8f4922415a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3388093bd4c4d331382d0016aa94fd7868af3fa4dd50305298d21879ce809e93
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5464621782302856,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.037091988130563795,
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": 23.096,
374
  "eval_steps_per_second": 5.774,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 4136300131123200.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4849724769592285,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.07418397626112759,
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": 23.096,
374
  "eval_steps_per_second": 5.774,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.037833827893175076,
379
+ "grad_norm": 0.4841320216655731,
380
+ "learning_rate": 7.855436842105262e-05,
381
+ "loss": 1.4443,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03857566765578635,
386
+ "grad_norm": 0.46595099568367004,
387
+ "learning_rate": 7.802715789473684e-05,
388
+ "loss": 1.4447,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.039317507418397624,
393
+ "grad_norm": 0.4743313491344452,
394
+ "learning_rate": 7.749994736842104e-05,
395
+ "loss": 1.4073,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.040059347181008904,
400
+ "grad_norm": 0.46219533681869507,
401
+ "learning_rate": 7.697273684210526e-05,
402
+ "loss": 1.4843,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.04080118694362018,
407
+ "grad_norm": 0.4498580992221832,
408
+ "learning_rate": 7.644552631578947e-05,
409
+ "loss": 1.3828,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.04154302670623145,
414
+ "grad_norm": 0.4310692250728607,
415
+ "learning_rate": 7.591831578947369e-05,
416
+ "loss": 1.5251,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.04228486646884273,
421
+ "grad_norm": 0.44536563754081726,
422
+ "learning_rate": 7.539110526315789e-05,
423
+ "loss": 1.5329,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.04302670623145401,
428
+ "grad_norm": 0.4388580620288849,
429
+ "learning_rate": 7.48638947368421e-05,
430
+ "loss": 1.4534,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.04376854599406528,
435
+ "grad_norm": 0.44389694929122925,
436
+ "learning_rate": 7.433668421052632e-05,
437
+ "loss": 1.6085,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.04451038575667656,
442
+ "grad_norm": 0.42019519209861755,
443
+ "learning_rate": 7.380947368421052e-05,
444
+ "loss": 1.3532,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.045252225519287835,
449
+ "grad_norm": 0.4290321469306946,
450
+ "learning_rate": 7.328226315789473e-05,
451
+ "loss": 1.4509,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.04599406528189911,
456
+ "grad_norm": 0.44131532311439514,
457
+ "learning_rate": 7.275505263157895e-05,
458
+ "loss": 1.4341,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04673590504451038,
463
+ "grad_norm": 0.4584609866142273,
464
+ "learning_rate": 7.222784210526316e-05,
465
+ "loss": 1.4711,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.04747774480712166,
470
+ "grad_norm": 0.45380136370658875,
471
+ "learning_rate": 7.170063157894737e-05,
472
+ "loss": 1.5905,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.04821958456973294,
477
+ "grad_norm": 0.44095584750175476,
478
+ "learning_rate": 7.117342105263158e-05,
479
+ "loss": 1.3695,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.04896142433234421,
484
+ "grad_norm": 0.43939009308815,
485
+ "learning_rate": 7.064621052631578e-05,
486
+ "loss": 1.4743,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.04970326409495549,
491
+ "grad_norm": 0.44385743141174316,
492
+ "learning_rate": 7.0119e-05,
493
+ "loss": 1.3362,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.050445103857566766,
498
+ "grad_norm": 0.46653878688812256,
499
+ "learning_rate": 6.959178947368421e-05,
500
+ "loss": 1.353,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.05118694362017804,
505
+ "grad_norm": 0.49922919273376465,
506
+ "learning_rate": 6.906457894736843e-05,
507
+ "loss": 1.5815,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.05192878338278932,
512
+ "grad_norm": 0.48967719078063965,
513
+ "learning_rate": 6.853736842105263e-05,
514
+ "loss": 1.6117,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.052670623145400594,
519
+ "grad_norm": 0.5269822478294373,
520
+ "learning_rate": 6.801015789473684e-05,
521
+ "loss": 1.7096,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.05341246290801187,
526
+ "grad_norm": 0.5190030932426453,
527
+ "learning_rate": 6.748294736842105e-05,
528
+ "loss": 1.5746,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.05415430267062315,
533
+ "grad_norm": 0.5140092372894287,
534
+ "learning_rate": 6.695573684210526e-05,
535
+ "loss": 1.5915,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.05489614243323442,
540
+ "grad_norm": 0.5112202167510986,
541
+ "learning_rate": 6.642852631578946e-05,
542
+ "loss": 1.5368,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.055637982195845696,
547
+ "grad_norm": 0.45904073119163513,
548
+ "learning_rate": 6.590131578947369e-05,
549
+ "loss": 1.3563,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.05637982195845697,
554
+ "grad_norm": 0.4861205816268921,
555
+ "learning_rate": 6.537410526315789e-05,
556
+ "loss": 1.4552,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.05712166172106825,
561
+ "grad_norm": 0.5068615674972534,
562
+ "learning_rate": 6.484689473684211e-05,
563
+ "loss": 1.4687,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.057863501483679525,
568
+ "grad_norm": 0.49406206607818604,
569
+ "learning_rate": 6.431968421052631e-05,
570
+ "loss": 1.4759,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0586053412462908,
575
+ "grad_norm": 0.4920863211154938,
576
+ "learning_rate": 6.379247368421052e-05,
577
+ "loss": 1.4521,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05934718100890208,
582
+ "grad_norm": 0.5270341038703918,
583
+ "learning_rate": 6.326526315789474e-05,
584
+ "loss": 1.6008,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.06008902077151335,
589
+ "grad_norm": 0.5248571038246155,
590
+ "learning_rate": 6.273805263157894e-05,
591
+ "loss": 1.6934,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.06083086053412463,
596
+ "grad_norm": 0.519171416759491,
597
+ "learning_rate": 6.221084210526315e-05,
598
+ "loss": 1.5087,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.06157270029673591,
603
+ "grad_norm": 0.4932954013347626,
604
+ "learning_rate": 6.168363157894737e-05,
605
+ "loss": 1.3543,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.06231454005934718,
610
+ "grad_norm": 0.5216118097305298,
611
+ "learning_rate": 6.115642105263159e-05,
612
+ "loss": 1.4453,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.06305637982195846,
617
+ "grad_norm": 0.5293753147125244,
618
+ "learning_rate": 6.0629210526315787e-05,
619
+ "loss": 1.4051,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.06379821958456973,
624
+ "grad_norm": 0.5512006878852844,
625
+ "learning_rate": 6.0101999999999995e-05,
626
+ "loss": 1.4588,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.064540059347181,
631
+ "grad_norm": 0.5609034895896912,
632
+ "learning_rate": 5.95747894736842e-05,
633
+ "loss": 1.5523,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.06528189910979229,
638
+ "grad_norm": 0.6228796243667603,
639
+ "learning_rate": 5.904757894736841e-05,
640
+ "loss": 1.563,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.06602373887240356,
645
+ "grad_norm": 0.6174453496932983,
646
+ "learning_rate": 5.852036842105263e-05,
647
+ "loss": 1.6785,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.06676557863501484,
652
+ "grad_norm": 0.560930609703064,
653
+ "learning_rate": 5.799315789473684e-05,
654
+ "loss": 1.5602,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.06750741839762611,
659
+ "grad_norm": 0.5620979070663452,
660
+ "learning_rate": 5.746594736842105e-05,
661
+ "loss": 1.4652,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.06824925816023739,
666
+ "grad_norm": 0.5614945888519287,
667
+ "learning_rate": 5.693873684210526e-05,
668
+ "loss": 1.4533,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06899109792284866,
673
+ "grad_norm": 0.6170912384986877,
674
+ "learning_rate": 5.641152631578947e-05,
675
+ "loss": 1.5405,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.06973293768545995,
680
+ "grad_norm": 0.6051465272903442,
681
+ "learning_rate": 5.588431578947368e-05,
682
+ "loss": 1.3788,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.07047477744807122,
687
+ "grad_norm": 0.612392008304596,
688
+ "learning_rate": 5.5357105263157896e-05,
689
+ "loss": 1.513,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.0712166172106825,
694
+ "grad_norm": 0.5922538638114929,
695
+ "learning_rate": 5.482989473684211e-05,
696
+ "loss": 1.6693,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.07195845697329377,
701
+ "grad_norm": 0.6305238604545593,
702
+ "learning_rate": 5.430268421052632e-05,
703
+ "loss": 1.5546,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.07270029673590504,
708
+ "grad_norm": 0.6214465498924255,
709
+ "learning_rate": 5.377547368421053e-05,
710
+ "loss": 1.4541,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.07344213649851632,
715
+ "grad_norm": 0.6209021806716919,
716
+ "learning_rate": 5.3248263157894736e-05,
717
+ "loss": 1.4974,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.07418397626112759,
722
+ "grad_norm": 0.7504584193229675,
723
+ "learning_rate": 5.2721052631578944e-05,
724
+ "loss": 1.7205,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.07418397626112759,
729
+ "eval_loss": 1.4849724769592285,
730
+ "eval_runtime": 24.627,
731
+ "eval_samples_per_second": 23.064,
732
+ "eval_steps_per_second": 5.766,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 8272600262246400.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null