aleegis09 commited on
Commit
f735dc8
·
verified ·
1 Parent(s): 8f3d617

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:c93f07aca7bf2140ec6c3c5cb555d40409f51cd7770a440a65bf7465429713da
3
  size 479005064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543cabfc6d5bc954b47dcdde6571ec3d5ce0243b46b60f1fe4a8ea9865e952f5
3
  size 479005064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca60a3add9a31f5771746ca5b6e9abc2b99c33a83239b637c24a470ed184b5ab
3
  size 958299770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ee2148d3d1fa3fa092d0f526567ff9407d7e80527157565c20ac7e4b8758c26
3
  size 958299770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:691b4382dbadb396f8019ae2d3c3d4476c6c538ae3756cfcf376d2b55207af47
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c624552f1c961b604c5438d23262731c2c34ed397e3dcfcfd955324544844da
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5335737b4b4d079cdec612fe6ee661ed4d29f9e0e55eb4eada44a9677240228
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.2094399482011795,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.021659085986571368,
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": 19.004,
374
  "eval_steps_per_second": 9.502,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.8596442616561664e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.08056939393281937,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.043318171973142736,
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": 19.004,
374
  "eval_steps_per_second": 9.502,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.022092267706302793,
379
+ "grad_norm": 2.441636323928833,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 0.2969,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.02252544942603422,
386
+ "grad_norm": 3.2028415203094482,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 0.2594,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.02295863114576565,
393
+ "grad_norm": 1.429338812828064,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 0.21,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.023391812865497075,
400
+ "grad_norm": 0.7525247931480408,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 0.1651,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.023824994585228503,
407
+ "grad_norm": 2.9362690448760986,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 0.2147,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.02425817630495993,
414
+ "grad_norm": 2.608370780944824,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 0.2761,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.024691358024691357,
421
+ "grad_norm": 2.0152244567871094,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 0.1976,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.025124539744422785,
428
+ "grad_norm": 0.9376019835472107,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 0.1674,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.025557721464154214,
435
+ "grad_norm": 0.7567312121391296,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 0.1707,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.02599090318388564,
442
+ "grad_norm": 0.4066583812236786,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 0.1036,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.026424084903617067,
449
+ "grad_norm": 0.9996243119239807,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 0.1479,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.026857266623348496,
456
+ "grad_norm": 1.146002173423767,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 0.1592,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.02729044834307992,
463
+ "grad_norm": 0.6335452198982239,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 0.1147,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.02772363006281135,
470
+ "grad_norm": 0.46830275654792786,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 0.1149,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.028156811782542777,
477
+ "grad_norm": 0.5706634521484375,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 0.1181,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.028589993502274202,
484
+ "grad_norm": 0.4780918061733246,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 0.0775,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.02902317522200563,
491
+ "grad_norm": 0.45546865463256836,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 0.0855,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.02945635694173706,
498
+ "grad_norm": 0.8334485292434692,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 0.0958,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.029889538661468484,
505
+ "grad_norm": 0.6183558702468872,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 0.0958,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.030322720381199913,
512
+ "grad_norm": 0.7801946997642517,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 0.1081,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.03075590210093134,
519
+ "grad_norm": 0.5213829278945923,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 0.0898,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.031189083820662766,
526
+ "grad_norm": 0.6553680300712585,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 0.1158,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0316222655403942,
533
+ "grad_norm": 0.6341337561607361,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 0.0805,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.03205544726012562,
540
+ "grad_norm": 0.47776395082473755,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 0.0671,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.03248862897985705,
547
+ "grad_norm": 0.6857931017875671,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 0.0757,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.03292181069958848,
554
+ "grad_norm": 0.7055604457855225,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 0.0995,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.033354992419319905,
561
+ "grad_norm": 0.8226217031478882,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 0.0734,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.03378817413905133,
568
+ "grad_norm": 0.6480997204780579,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 0.0708,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.03422135585878276,
575
+ "grad_norm": 0.5634680390357971,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 0.06,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03465453757851419,
582
+ "grad_norm": 0.5001603364944458,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 0.0499,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.03508771929824561,
589
+ "grad_norm": 0.3587808609008789,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 0.0339,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.035520901017977044,
596
+ "grad_norm": 0.5878409147262573,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 0.0634,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.03595408273770847,
603
+ "grad_norm": 0.5627532005310059,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 0.0498,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.036387264457439894,
610
+ "grad_norm": 0.522148847579956,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 0.0239,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.036820446177171326,
617
+ "grad_norm": 0.6190194487571716,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 0.0461,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.03725362789690275,
624
+ "grad_norm": 0.5469635128974915,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 0.0413,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.037686809616634176,
631
+ "grad_norm": 0.3395079970359802,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 0.0338,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.03811999133636561,
638
+ "grad_norm": 0.8697502017021179,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 0.0772,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.03855317305609703,
645
+ "grad_norm": 0.6907822489738464,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 0.0291,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.03898635477582846,
652
+ "grad_norm": 0.47123125195503235,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 0.0268,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03941953649555989,
659
+ "grad_norm": 0.2734449803829193,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 0.012,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.039852718215291315,
666
+ "grad_norm": 0.27939316630363464,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 0.0145,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.04028589993502274,
673
+ "grad_norm": 0.2553471028804779,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 0.0174,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.04071908165475417,
680
+ "grad_norm": 0.15355971455574036,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 0.006,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0411522633744856,
687
+ "grad_norm": 0.2645378112792969,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 0.0155,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.04158544509421702,
694
+ "grad_norm": 0.36685898900032043,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 0.0247,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.042018626813948454,
701
+ "grad_norm": 0.24984949827194214,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 0.0127,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.04245180853367988,
708
+ "grad_norm": 0.42770883440971375,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 0.0153,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.042884990253411304,
715
+ "grad_norm": 0.01884501427412033,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 0.0004,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.043318171973142736,
722
+ "grad_norm": 0.1676054745912552,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 0.0012,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.043318171973142736,
729
+ "eval_loss": 0.08056939393281937,
730
+ "eval_runtime": 205.2456,
731
+ "eval_samples_per_second": 18.943,
732
+ "eval_steps_per_second": 9.472,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 5.719288523312333e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null