arcwarden46 commited on
Commit
05d394c
·
verified ·
1 Parent(s): 4dafa48

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 sha256:575f52f36e66e7c4c402b27af399670b604d0b48ef6e11de319df79488c0b6cb
3
  size 224224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a327840041c5e7f13b68febe1404afbdae0a8414835aa8b57e5cb162911778
3
  size 224224
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74108dea98a3f2ae0f32df799657a3fb0ca9112671fbcfece5bd9642cdc545ef
3
  size 458278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14e5a43ce8ddf7cbcd015679d22f3b1b35906ede53546e80360ea858db5c4643
3
  size 458278
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:379eb3425e3f69f62d70ef6a52ed40b8b3281bb802abd6b180e334f77589f502
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0664582359f99320cf3ef366e7c6afff3e12ad91b8e191e816f63cc9e498ed67
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": 10.309220314025879,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.011816838995568686,
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": 507.815,
374
  "eval_steps_per_second": 126.972,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 10847863701504.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.304642677307129,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.023633677991137372,
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": 507.815,
374
  "eval_steps_per_second": 126.972,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.01205317577548006,
379
+ "grad_norm": 0.8177053332328796,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 41.2913,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.012289512555391433,
386
+ "grad_norm": 0.7033486366271973,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 41.2543,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.012525849335302807,
393
+ "grad_norm": 1.0284385681152344,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 41.2326,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01276218611521418,
400
+ "grad_norm": 0.772871732711792,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 41.2613,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.012998522895125554,
407
+ "grad_norm": 0.7103416919708252,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 41.2451,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.013234859675036927,
414
+ "grad_norm": 0.9658076167106628,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 41.228,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0134711964549483,
421
+ "grad_norm": 1.05716872215271,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 41.2597,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.013707533234859674,
428
+ "grad_norm": 0.61740642786026,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 41.235,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01394387001477105,
435
+ "grad_norm": 0.5879736542701721,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 41.2239,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.014180206794682423,
442
+ "grad_norm": 0.7688696384429932,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 41.2473,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.014416543574593797,
449
+ "grad_norm": 0.5945973992347717,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 41.2215,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.01465288035450517,
456
+ "grad_norm": 0.5151475667953491,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 41.208,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.014889217134416544,
463
+ "grad_norm": 0.7458901405334473,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 41.243,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.015125553914327917,
470
+ "grad_norm": 0.6170288324356079,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 41.2167,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.01536189069423929,
477
+ "grad_norm": 0.7434762120246887,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 41.2176,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.015598227474150664,
484
+ "grad_norm": 0.5235951542854309,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 41.2029,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.015834564254062038,
491
+ "grad_norm": 0.8569870591163635,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 41.2486,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.016070901033973413,
498
+ "grad_norm": 0.7099596858024597,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 41.2315,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.016307237813884785,
505
+ "grad_norm": 0.5294151902198792,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 41.2379,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01654357459379616,
512
+ "grad_norm": 0.6385646462440491,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 41.2244,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.01677991137370753,
519
+ "grad_norm": 0.5439596772193909,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 41.19,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.017016248153618907,
526
+ "grad_norm": 0.690276563167572,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 41.1941,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.017252584933530282,
533
+ "grad_norm": 0.7714937329292297,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 41.1957,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.017488921713441654,
540
+ "grad_norm": 0.4136044383049011,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 41.2347,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.01772525849335303,
547
+ "grad_norm": 0.6972559094429016,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 41.2204,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0179615952732644,
554
+ "grad_norm": 0.49755576252937317,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 41.2282,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.018197932053175776,
561
+ "grad_norm": 0.4795960783958435,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 41.2386,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.018434268833087148,
568
+ "grad_norm": 0.856358528137207,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 41.2183,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.018670605612998523,
575
+ "grad_norm": 0.6066249012947083,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 41.1974,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.018906942392909895,
582
+ "grad_norm": 0.4587751030921936,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 41.2179,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01914327917282127,
589
+ "grad_norm": 0.6782584190368652,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 41.2085,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.019379615952732646,
596
+ "grad_norm": 0.43092355132102966,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 41.2086,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.019615952732644017,
603
+ "grad_norm": 0.5649749040603638,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 41.1887,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.019852289512555393,
610
+ "grad_norm": 0.5035609602928162,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 41.2125,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.020088626292466764,
617
+ "grad_norm": 0.5236511826515198,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 41.2211,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.02032496307237814,
624
+ "grad_norm": 0.42666125297546387,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 41.2114,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02056129985228951,
631
+ "grad_norm": 0.5870954990386963,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 41.1914,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.020797636632200887,
638
+ "grad_norm": 0.4540001153945923,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 41.2223,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.02103397341211226,
645
+ "grad_norm": 0.47619494795799255,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 41.2383,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.021270310192023634,
652
+ "grad_norm": 0.4194251596927643,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 41.2252,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.02150664697193501,
659
+ "grad_norm": 0.5211244821548462,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 41.2258,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.02174298375184638,
666
+ "grad_norm": 0.5141422748565674,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 41.2133,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.021979320531757756,
673
+ "grad_norm": 0.4102741479873657,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 41.235,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.022215657311669128,
680
+ "grad_norm": 0.5932872891426086,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 41.2422,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.022451994091580503,
687
+ "grad_norm": 0.7138688564300537,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 41.1864,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.022688330871491875,
694
+ "grad_norm": 0.5744657516479492,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 41.2133,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.02292466765140325,
701
+ "grad_norm": 0.7336076498031616,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 41.2483,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.023161004431314622,
708
+ "grad_norm": 0.6511675715446472,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 41.2562,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.023397341211225997,
715
+ "grad_norm": 0.8956031799316406,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 41.2185,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.023633677991137372,
722
+ "grad_norm": 1.2400425672531128,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 41.1847,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.023633677991137372,
729
+ "eval_loss": 10.304642677307129,
730
+ "eval_runtime": 14.0917,
731
+ "eval_samples_per_second": 505.759,
732
+ "eval_steps_per_second": 126.458,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 21695727403008.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null