prxy5604 commited on
Commit
5ef141f
·
verified ·
1 Parent(s): ab7e765

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 sha256:6de9c4b49efa126882f7418359d488e1d7d2a7f20d5a540156d78fc5ba30c21e
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f677dec52b5ba633df03d9768bf0c5683855349e08844e3a5c71d1bb6b0b33
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea5326afbe202c4c9ed1a2c3c3e5667acd72632fbb1b4233cdae2fcaa1a1b810
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9abf9fb5b9154b9601c6835cfda10488f8894a15375d8f3d2fdf0aa7aa715090
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46635f7cfe639e766aa19703243e16042b560bd72d0f1bc1ffded952e4eb1f4a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66fb4c25287efcd562f1cd952fe2acec5050f537751e06ba78f7930e53db878
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": 0.2697645127773285,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.008074609390770721,
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": 13.476,
374
  "eval_steps_per_second": 3.37,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.15499809800192e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.23936980962753296,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.016149218781541443,
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": 13.476,
374
  "eval_steps_per_second": 3.37,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008236101578586136,
379
+ "grad_norm": 20.15778160095215,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.4656,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.00839759376640155,
386
+ "grad_norm": 10.792618751525879,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.0059,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.008559085954216965,
393
+ "grad_norm": 6.110121250152588,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.987,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.008720578142032379,
400
+ "grad_norm": 4.688563346862793,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.8083,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.008882070329847794,
407
+ "grad_norm": 5.73980188369751,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.2474,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009043562517663207,
414
+ "grad_norm": 3.409475088119507,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.5241,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.009205054705478622,
421
+ "grad_norm": 5.96190071105957,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.8567,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009366546893294038,
428
+ "grad_norm": 5.128782749176025,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.6851,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009528039081109451,
435
+ "grad_norm": 4.455477237701416,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.8239,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.009689531268924866,
442
+ "grad_norm": 5.79195499420166,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.0797,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.00985102345674028,
449
+ "grad_norm": 6.7193498611450195,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.7795,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.010012515644555695,
456
+ "grad_norm": 4.534706115722656,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.8244,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.010174007832371108,
463
+ "grad_norm": 5.564373970031738,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.6512,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010335500020186524,
470
+ "grad_norm": 7.308129787445068,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.8395,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010496992208001939,
477
+ "grad_norm": 7.847126007080078,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.0518,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.010658484395817352,
484
+ "grad_norm": 6.746877670288086,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.1552,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.010819976583632767,
491
+ "grad_norm": 5.704141139984131,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.1032,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01098146877144818,
498
+ "grad_norm": 4.532803058624268,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.6292,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011142960959263596,
505
+ "grad_norm": 3.092655897140503,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.5854,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01130445314707901,
512
+ "grad_norm": 12.300941467285156,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.915,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011465945334894425,
519
+ "grad_norm": 5.741693019866943,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.9987,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.011627437522709838,
526
+ "grad_norm": 5.947897911071777,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.9166,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.011788929710525253,
533
+ "grad_norm": 9.199006080627441,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.4229,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.011950421898340668,
540
+ "grad_norm": 4.8748297691345215,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.8394,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012111914086156082,
547
+ "grad_norm": 4.803055286407471,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.7034,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012273406273971497,
554
+ "grad_norm": 4.951623439788818,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.9423,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.01243489846178691,
561
+ "grad_norm": 5.697551727294922,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.3467,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.012596390649602326,
568
+ "grad_norm": 6.667501926422119,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.0246,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.01275788283741774,
575
+ "grad_norm": 5.783114910125732,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.844,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.012919375025233154,
582
+ "grad_norm": 4.069927215576172,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.8796,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01308086721304857,
589
+ "grad_norm": 6.044260501861572,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.8675,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.013242359400863983,
596
+ "grad_norm": 9.066145896911621,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.0933,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.013403851588679398,
603
+ "grad_norm": 6.081099033355713,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.5966,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.013565343776494812,
610
+ "grad_norm": 4.080660820007324,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.8206,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.013726835964310227,
617
+ "grad_norm": 10.46330451965332,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.339,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.01388832815212564,
624
+ "grad_norm": 4.070284366607666,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.9671,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.014049820339941056,
631
+ "grad_norm": 4.478235244750977,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.8915,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.014211312527756469,
638
+ "grad_norm": 5.405301570892334,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.9657,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.014372804715571884,
645
+ "grad_norm": 5.201086044311523,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.8831,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0145342969033873,
652
+ "grad_norm": 5.0022196769714355,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.9536,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.014695789091202713,
659
+ "grad_norm": 3.785090208053589,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.9481,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.014857281279018128,
666
+ "grad_norm": 3.209487199783325,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.623,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.015018773466833541,
673
+ "grad_norm": 3.7691524028778076,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.6287,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015180265654648957,
680
+ "grad_norm": 5.767764091491699,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.0116,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.01534175784246437,
687
+ "grad_norm": 5.574740409851074,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.1322,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.015503250030279785,
694
+ "grad_norm": 6.865067005157471,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.1674,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0156647422180952,
701
+ "grad_norm": 7.697023391723633,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.2146,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.015826234405910616,
708
+ "grad_norm": 6.176741123199463,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.7344,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.015987726593726027,
715
+ "grad_norm": 7.797219276428223,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.9874,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.016149218781541443,
722
+ "grad_norm": 35.21796798706055,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.3663,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.016149218781541443,
729
+ "eval_loss": 0.23936980962753296,
730
+ "eval_runtime": 773.8809,
731
+ "eval_samples_per_second": 13.476,
732
+ "eval_steps_per_second": 3.37,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.430999619600384e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null