aleegis09 commited on
Commit
f8c1a01
·
verified ·
1 Parent(s): f239c6a

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 sha256:5d427aa073f23096e2ae777695de70a29c7b3aa3d903a8da5a829057a78202f5
3
  size 478211024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2aab14d48ce7ba29df570a487b42580a2b415061dac3f055b99f99707463d71
3
  size 478211024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22b91b66dafcbe3bb97144f091901e59fa7064633876ae7b7888f76c7a998175
3
  size 243337876
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f2b9388a6c6b74a2b99d7028db098712e21d33b704a3cde61fc28ec4aaa809c
3
  size 243337876
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31191e5b7f31dd442343c300a714f2e9674bdc72110d9db36f75536aaf04a922
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780705b58eb3883ec8bc8ba0e22bebdc50e0113d6f02b577b5f5e6755ca35203
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1202869415283203,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.008104056080068074,
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": 16.654,
374
  "eval_steps_per_second": 4.163,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 4.494575629290701e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0881792306900024,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.016208112160136148,
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": 16.654,
374
  "eval_steps_per_second": 4.163,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008266137201669436,
379
+ "grad_norm": 1.0332852602005005,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 4.6871,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008428218323270797,
386
+ "grad_norm": 0.747059166431427,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 4.6101,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.008590299444872159,
393
+ "grad_norm": 0.7617971897125244,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 4.3059,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.00875238056647352,
400
+ "grad_norm": 0.6986435055732727,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 4.1676,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.008914461688074882,
407
+ "grad_norm": 0.6283707618713379,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 4.0447,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009076542809676243,
414
+ "grad_norm": 0.5435439944267273,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 3.9407,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.009238623931277605,
421
+ "grad_norm": 0.6282440423965454,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 4.2496,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009400705052878966,
428
+ "grad_norm": 0.5533632636070251,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 3.908,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009562786174480328,
435
+ "grad_norm": 0.5285382270812988,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 3.8597,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.009724867296081689,
442
+ "grad_norm": 0.5500264763832092,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 3.9084,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.009886948417683051,
449
+ "grad_norm": 0.5860369801521301,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 4.3225,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.010049029539284412,
456
+ "grad_norm": 0.549226701259613,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 4.1944,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.010211110660885774,
463
+ "grad_norm": 0.5468707084655762,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 4.1808,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010373191782487134,
470
+ "grad_norm": 0.5705710649490356,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 4.3865,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010535272904088497,
477
+ "grad_norm": 0.5604478120803833,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 4.0285,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.010697354025689857,
484
+ "grad_norm": 0.5283072590827942,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 3.7654,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.01085943514729122,
491
+ "grad_norm": 0.6135756373405457,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 3.9427,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01102151626889258,
498
+ "grad_norm": 0.5224963426589966,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 4.1028,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011183597390493943,
505
+ "grad_norm": 0.5102367997169495,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 3.752,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.011345678512095303,
512
+ "grad_norm": 0.6364815831184387,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 4.2697,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011507759633696666,
519
+ "grad_norm": 0.5517566800117493,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 4.3871,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.011669840755298026,
526
+ "grad_norm": 0.5636042952537537,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 4.1798,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.011831921876899389,
533
+ "grad_norm": 0.5331016778945923,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 4.1414,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.01199400299850075,
540
+ "grad_norm": 0.5853242874145508,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 4.2212,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012156084120102112,
547
+ "grad_norm": 0.5571672320365906,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 3.9346,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012318165241703472,
554
+ "grad_norm": 0.5618833303451538,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 4.046,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.012480246363304835,
561
+ "grad_norm": 0.590742290019989,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 4.191,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.012642327484906195,
568
+ "grad_norm": 0.6346542835235596,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 4.1737,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.012804408606507557,
575
+ "grad_norm": 0.6081542372703552,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 4.2878,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.012966489728108918,
582
+ "grad_norm": 0.5877219438552856,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 3.9882,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01312857084971028,
589
+ "grad_norm": 0.6087138652801514,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 3.9351,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.013290651971311641,
596
+ "grad_norm": 0.6984849572181702,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 4.0993,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.013452733092913003,
603
+ "grad_norm": 0.7047072649002075,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 4.4722,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.013614814214514364,
610
+ "grad_norm": 0.6677774786949158,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 4.1163,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.013776895336115726,
617
+ "grad_norm": 0.7007635831832886,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 4.5499,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.013938976457717087,
624
+ "grad_norm": 0.7800924181938171,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 4.535,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.01410105757931845,
631
+ "grad_norm": 0.7068495154380798,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 4.5603,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.01426313870091981,
638
+ "grad_norm": 0.7155495285987854,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 4.2512,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.014425219822521172,
645
+ "grad_norm": 0.7719190716743469,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 4.9387,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.014587300944122533,
652
+ "grad_norm": 0.7631606459617615,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 4.6449,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.014749382065723895,
659
+ "grad_norm": 0.8474345803260803,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 4.7862,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.014911463187325256,
666
+ "grad_norm": 0.922042727470398,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 4.9097,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.015073544308926618,
673
+ "grad_norm": 0.9074467420578003,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 4.6718,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015235625430527979,
680
+ "grad_norm": 0.9892921447753906,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 4.8383,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.015397706552129341,
687
+ "grad_norm": 1.0625590085983276,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 4.9755,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.015559787673730702,
694
+ "grad_norm": 1.2702600955963135,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 5.1954,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.015721868795332064,
701
+ "grad_norm": 1.2826322317123413,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 5.0106,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.015883949916933426,
708
+ "grad_norm": 1.510257363319397,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 5.2868,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.016046031038534785,
715
+ "grad_norm": 1.7453159093856812,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 5.1547,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.016208112160136148,
722
+ "grad_norm": 2.375579357147217,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 5.0376,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.016208112160136148,
729
+ "eval_loss": 1.0881792306900024,
730
+ "eval_runtime": 624.3364,
731
+ "eval_samples_per_second": 16.645,
732
+ "eval_steps_per_second": 4.161,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 9.064690344787968e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null