prxy5607 commited on
Commit
2ea8d47
·
verified ·
1 Parent(s): 083f696

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 sha256:68e8fb6a223902ab8bd39603ccdccb06b592646ae755ad8a66def63727fff011
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb404dadbdfe6ad7082f9459cd32fcb29655bfd666e26fc879662a78334ec795
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6e85f34fab23ff882cac3b941d35b80427d41310cda6bf90c3e74302880ee7a
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d9287851e1b25f932c475f3f5b8126e44c079c10b6f699967eb4dc8471439b0
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7aa195a5f60fbc71f123718762b2f68153bc944cf1d14c7470ad8b78242b07e7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4cafdc776d03552717c6b1dd570dccb608fbcadcb39d520da2da15a595399cb
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": 0.28004929423332214,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.17921146953405018,
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": 9.411,
374
  "eval_steps_per_second": 2.363,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.0236057862589645e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.25865477323532104,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.35842293906810035,
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": 9.411,
374
  "eval_steps_per_second": 2.363,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.1827956989247312,
379
+ "grad_norm": 9.191633224487305,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.8294,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.1863799283154122,
386
+ "grad_norm": 7.976558208465576,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.0961,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.18996415770609318,
393
+ "grad_norm": 6.3274946212768555,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.3197,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.1935483870967742,
400
+ "grad_norm": 6.010959148406982,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.0092,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.1971326164874552,
407
+ "grad_norm": 5.882427215576172,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.8697,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.2007168458781362,
414
+ "grad_norm": 6.208774089813232,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.6801,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.20430107526881722,
421
+ "grad_norm": 5.348367214202881,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.6368,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2078853046594982,
428
+ "grad_norm": 5.442905902862549,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.3868,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.2114695340501792,
435
+ "grad_norm": 5.595448970794678,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.2856,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.21505376344086022,
442
+ "grad_norm": 10.32099723815918,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.5686,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.21863799283154123,
449
+ "grad_norm": 8.23583698272705,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.416,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.2222222222222222,
456
+ "grad_norm": 12.7261962890625,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.6503,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.22580645161290322,
463
+ "grad_norm": 5.927293300628662,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.8517,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.22939068100358423,
470
+ "grad_norm": 6.635047435760498,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.9006,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.23297491039426524,
477
+ "grad_norm": 8.029170989990234,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.799,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.23655913978494625,
484
+ "grad_norm": 9.035547256469727,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.4406,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.24014336917562723,
491
+ "grad_norm": 9.572111129760742,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.968,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.24372759856630824,
498
+ "grad_norm": 7.323725700378418,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.7307,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.24731182795698925,
505
+ "grad_norm": 8.532878875732422,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.921,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.25089605734767023,
512
+ "grad_norm": 12.004900932312012,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.9137,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.25448028673835127,
519
+ "grad_norm": 9.63646125793457,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.9467,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.25806451612903225,
526
+ "grad_norm": 7.666362285614014,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.2921,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2616487455197133,
533
+ "grad_norm": 7.735444068908691,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.4973,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.26523297491039427,
540
+ "grad_norm": 14.301405906677246,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.2532,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.26881720430107525,
547
+ "grad_norm": 5.494683265686035,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.1198,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.2724014336917563,
554
+ "grad_norm": 5.784592151641846,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.8771,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.27598566308243727,
561
+ "grad_norm": 6.8970770835876465,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.2429,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.27956989247311825,
568
+ "grad_norm": 5.237691402435303,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.9329,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.2831541218637993,
575
+ "grad_norm": 8.241721153259277,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.3392,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.2867383512544803,
582
+ "grad_norm": 5.223793029785156,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.9224,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.2903225806451613,
589
+ "grad_norm": 7.292931079864502,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.2648,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.2939068100358423,
596
+ "grad_norm": 6.255661964416504,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.1487,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.2974910394265233,
603
+ "grad_norm": 5.561267375946045,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.1417,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.3010752688172043,
610
+ "grad_norm": 5.368224620819092,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.8612,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.3046594982078853,
617
+ "grad_norm": 6.687611103057861,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.0543,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.30824372759856633,
624
+ "grad_norm": 6.311729431152344,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.0505,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3118279569892473,
631
+ "grad_norm": 5.3506598472595215,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.0001,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3154121863799283,
638
+ "grad_norm": 6.4501543045043945,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.1149,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.31899641577060933,
645
+ "grad_norm": 7.826871395111084,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.0674,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.3225806451612903,
652
+ "grad_norm": 6.225786209106445,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.8601,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.32616487455197135,
659
+ "grad_norm": 4.410377025604248,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.6826,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.32974910394265233,
666
+ "grad_norm": 5.833151817321777,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.6293,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.3333333333333333,
673
+ "grad_norm": 6.048341751098633,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.775,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.33691756272401435,
680
+ "grad_norm": 5.176039695739746,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.7012,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.34050179211469533,
687
+ "grad_norm": 6.657656669616699,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.9241,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.34408602150537637,
694
+ "grad_norm": 5.278158187866211,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.6386,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.34767025089605735,
701
+ "grad_norm": 8.443243026733398,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.8443,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.35125448028673834,
708
+ "grad_norm": 6.784634113311768,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.542,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.3548387096774194,
715
+ "grad_norm": 7.89312744140625,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.0249,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.35842293906810035,
722
+ "grad_norm": 9.279082298278809,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.953,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.35842293906810035,
729
+ "eval_loss": 0.25865477323532104,
730
+ "eval_runtime": 49.9482,
731
+ "eval_samples_per_second": 9.41,
732
+ "eval_steps_per_second": 2.362,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.047211572517929e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null