prxy5607 commited on
Commit
7e1e859
·
verified ·
1 Parent(s): 1850e42

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:fe1bf50a699176cbc21e37c125da6f4cd11559699159f56a9bbbd6826df6bf8b
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db069093a35bf17fc31561dd8ed082aed6f04017e0d40ca8710bcb074d1a639f
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7eda804c9082bedb822dea5f09f600397f041a53e1d9bf9b705215683fab5627
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33d26f7ffcd17512266ab7866a06232e74f1c54784ce9c41b53062f70887757
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:129253bb2dfa2e043b0f964e3af811ecb380b14734b54e2fab658cb4138dc5a6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de848784cd8f34995e2c4d7dec5de04acc95a57cc9e7dc4af2f8d8221dbc9428
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": 2.6347908973693848,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.09900990099009901,
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": 48.554,
374
  "eval_steps_per_second": 12.153,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.0825725351297024e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.499460458755493,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.19801980198019803,
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": 48.554,
374
  "eval_steps_per_second": 12.153,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.100990099009901,
379
+ "grad_norm": 3.0091025829315186,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.5263,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.10297029702970296,
386
+ "grad_norm": 2.5911030769348145,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.4446,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.10495049504950495,
393
+ "grad_norm": 2.032653570175171,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.5393,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.10693069306930693,
400
+ "grad_norm": 1.3425925970077515,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.4587,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.10891089108910891,
407
+ "grad_norm": 0.7180945873260498,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.4167,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.11089108910891089,
414
+ "grad_norm": 0.4491579234600067,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.4759,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.11287128712871287,
421
+ "grad_norm": 0.4148993194103241,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.358,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.11485148514851486,
428
+ "grad_norm": 0.3795308470726013,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.3737,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.11683168316831684,
435
+ "grad_norm": 0.3720359802246094,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.3098,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.1188118811881188,
442
+ "grad_norm": 0.39235377311706543,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.4268,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.12079207920792079,
449
+ "grad_norm": 0.40234073996543884,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.3345,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.12277227722772277,
456
+ "grad_norm": 0.4109947681427002,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.46,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.12475247524752475,
463
+ "grad_norm": 0.4068487584590912,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.3738,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.12673267326732673,
470
+ "grad_norm": 0.39186495542526245,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.3968,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.12871287128712872,
477
+ "grad_norm": 0.40950897336006165,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.4378,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.1306930693069307,
484
+ "grad_norm": 0.4007221758365631,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.3862,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.13267326732673268,
491
+ "grad_norm": 0.41376572847366333,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.4285,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.13465346534653466,
498
+ "grad_norm": 0.41112542152404785,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.517,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.13663366336633664,
505
+ "grad_norm": 0.4579215943813324,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.3708,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.13861386138613863,
512
+ "grad_norm": 0.431108295917511,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.4168,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.1405940594059406,
519
+ "grad_norm": 0.42973315715789795,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.4979,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.14257425742574256,
526
+ "grad_norm": 0.44449689984321594,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.4562,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.14455445544554454,
533
+ "grad_norm": 0.4433273673057556,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.4481,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.14653465346534653,
540
+ "grad_norm": 0.4581921398639679,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.4801,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.1485148514851485,
547
+ "grad_norm": 0.4564491808414459,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.4362,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.1504950495049505,
554
+ "grad_norm": 0.4512006342411041,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.4825,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.15247524752475247,
561
+ "grad_norm": 0.49259135127067566,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.4237,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.15445544554455445,
568
+ "grad_norm": 0.4646151661872864,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.4271,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.15643564356435644,
575
+ "grad_norm": 0.49332305788993835,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.476,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.15841584158415842,
582
+ "grad_norm": 0.49859699606895447,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.4939,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.1603960396039604,
589
+ "grad_norm": 0.5360106825828552,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.4622,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.16237623762376238,
596
+ "grad_norm": 0.5232015252113342,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.3833,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.16435643564356436,
603
+ "grad_norm": 0.5606503486633301,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.5818,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.16633663366336635,
610
+ "grad_norm": 0.5686036348342896,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.3171,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.16831683168316833,
617
+ "grad_norm": 0.5630202293395996,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.5338,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.1702970297029703,
624
+ "grad_norm": 0.5604642629623413,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.5086,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.17227722772277226,
631
+ "grad_norm": 0.6153882741928101,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.5925,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.17425742574257425,
638
+ "grad_norm": 0.5997647047042847,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.3646,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.17623762376237623,
645
+ "grad_norm": 0.6267396807670593,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.504,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.1782178217821782,
652
+ "grad_norm": 0.6957364678382874,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.4873,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.1801980198019802,
659
+ "grad_norm": 0.6636099219322205,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.6616,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.18217821782178217,
666
+ "grad_norm": 0.6893649101257324,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.558,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.18415841584158416,
673
+ "grad_norm": 0.6587708592414856,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.4511,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.18613861386138614,
680
+ "grad_norm": 0.7910763025283813,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.4364,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.18811881188118812,
687
+ "grad_norm": 0.8297787308692932,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.5862,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.1900990099009901,
694
+ "grad_norm": 0.933093249797821,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.5867,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.19207920792079208,
701
+ "grad_norm": 0.9696834683418274,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.4786,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.19405940594059407,
708
+ "grad_norm": 1.1176578998565674,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.4409,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.19603960396039605,
715
+ "grad_norm": 1.2134913206100464,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.544,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.19801980198019803,
722
+ "grad_norm": 1.9900872707366943,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.8078,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.19801980198019803,
729
+ "eval_loss": 2.499460458755493,
730
+ "eval_runtime": 17.5135,
731
+ "eval_samples_per_second": 48.591,
732
+ "eval_steps_per_second": 12.162,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.165145070259405e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null