prxy5607 commited on
Commit
bfccd31
·
verified ·
1 Parent(s): 1ad9029

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 sha256:161ba88faab7fe04a167ff5932ac2774116f46b1748a20306ac2d1c6c69e3d1c
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf1ad53752080ca0d0a8739e4688800e9d86ab7eaf05067338cdf7c95c86139
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bf3751429ef60d3a2bb119a2c6bf8c48c197a324fea75334728fe5a303e1f50
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2211e88d866d71e8239f9e8044a6784d36867ddc2772079a2ebb68577b69d88
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c538120bc159af8d1f242385e500f3225dae3b6a9b0fb7d3dd8d99464c4899a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08119a4dd4d7dba27f50d0c7a8a6bc8f4ee214ae40cef4d6d26cf4304b385c00
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": 0.17120130360126495,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.003383636732760371,
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": 12.664,
374
  "eval_steps_per_second": 3.166,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.584289447634534e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.1288403868675232,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.006767273465520742,
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": 12.664,
374
  "eval_steps_per_second": 3.166,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.003451309467415578,
379
+ "grad_norm": 841.7377319335938,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 6.6657,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.003518982202070786,
386
+ "grad_norm": 238.1837615966797,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 7.1571,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.003586654936725993,
393
+ "grad_norm": 23.325450897216797,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 9.6001,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0036543276713812004,
400
+ "grad_norm": 7.813321113586426,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.1321,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.003722000406036408,
407
+ "grad_norm": 2.815350294113159,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.1254,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0037896731406916154,
414
+ "grad_norm": 1.4910508394241333,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.0301,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0038573458753468227,
421
+ "grad_norm": 1.6284786462783813,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.0298,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.00392501861000203,
428
+ "grad_norm": 1.2303739786148071,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.0632,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.003992691344657237,
435
+ "grad_norm": 0.7533950209617615,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.0114,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.004060364079312445,
442
+ "grad_norm": 1.6388555765151978,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.0149,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.004128036813967653,
449
+ "grad_norm": 2.930178165435791,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.0668,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0041957095486228595,
456
+ "grad_norm": 1.2340641021728516,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.0077,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.004263382283278067,
463
+ "grad_norm": 1.9125858545303345,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.0061,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.004331055017933275,
470
+ "grad_norm": 2.1240758895874023,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.0774,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.004398727752588482,
477
+ "grad_norm": 1.073846697807312,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.0085,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0044664004872436896,
484
+ "grad_norm": 2.5742125511169434,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.1324,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.004534073221898897,
491
+ "grad_norm": 1.2932730913162231,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0418,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.004601745956554104,
498
+ "grad_norm": 1.7381422519683838,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.0436,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.004669418691209312,
505
+ "grad_norm": 0.9713917970657349,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.0254,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0047370914258645196,
512
+ "grad_norm": 0.6254978179931641,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.0105,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.004804764160519726,
519
+ "grad_norm": 0.8255944848060608,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.018,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.004872436895174934,
526
+ "grad_norm": 0.11803942173719406,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.0021,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.004940109629830142,
533
+ "grad_norm": 3.658524990081787,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.0798,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.005007782364485349,
540
+ "grad_norm": 1.6816755533218384,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.0782,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.005075455099140556,
547
+ "grad_norm": 1.8367297649383545,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.0444,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.005143127833795763,
554
+ "grad_norm": 0.6377638578414917,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.0111,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.005210800568450971,
561
+ "grad_norm": 1.2953330278396606,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.0086,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.005278473303106179,
568
+ "grad_norm": 2.330518960952759,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.0295,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.005346146037761386,
575
+ "grad_norm": 0.25273895263671875,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0036,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.005413818772416593,
582
+ "grad_norm": 0.12430278211832047,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.0023,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.005481491507071801,
589
+ "grad_norm": 1.8424854278564453,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.0141,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.005549164241727008,
596
+ "grad_norm": 1.7487999200820923,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.0362,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.005616836976382216,
603
+ "grad_norm": 0.9633787274360657,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.0122,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.005684509711037423,
610
+ "grad_norm": 3.59778094291687,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.0905,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.00575218244569263,
617
+ "grad_norm": 2.7662360668182373,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.0614,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.005819855180347838,
624
+ "grad_norm": 0.33430278301239014,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0028,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.005887527915003046,
631
+ "grad_norm": 1.563698172569275,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0476,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.0059552006496582524,
638
+ "grad_norm": 1.9066797494888306,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.0315,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.00602287338431346,
645
+ "grad_norm": 0.4151351749897003,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.0035,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.006090546118968668,
652
+ "grad_norm": 0.6280702948570251,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.0055,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.006158218853623875,
659
+ "grad_norm": 4.358277320861816,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0599,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0062258915882790825,
666
+ "grad_norm": 1.2070956230163574,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.0048,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.00629356432293429,
673
+ "grad_norm": 0.13115110993385315,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.0018,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.006361237057589497,
680
+ "grad_norm": 2.5189132690429688,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0779,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.006428909792244705,
687
+ "grad_norm": 0.9217520952224731,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0134,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.006496582526899912,
694
+ "grad_norm": 0.751133143901825,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0097,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.006564255261555119,
701
+ "grad_norm": 2.118116855621338,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0609,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.006631927996210327,
708
+ "grad_norm": 0.47557875514030457,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0032,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.006699600730865534,
715
+ "grad_norm": 8.165701866149902,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.1346,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.006767273465520742,
722
+ "grad_norm": 42.32011032104492,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.6178,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.006767273465520742,
729
+ "eval_loss": 0.1288403868675232,
730
+ "eval_runtime": 1965.1172,
731
+ "eval_samples_per_second": 12.665,
732
+ "eval_steps_per_second": 3.166,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5275903745943142e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null