prxy5608 commited on
Commit
f2e01e0
·
verified ·
1 Parent(s): 1c99dfe

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 sha256:5689abb29e65a63394e18ab37644fe76031405c1e66d1b708a204d8058313e11
3
  size 478211024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f43b1541bee994a2dc43194abc4e0bfb7a869a0d33acf268d62cc27efa1b12a
3
  size 478211024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efaac8fb8eaa260db40b8ba20c797572204471f0b259c1b8528ef405e39fc105
3
  size 243337876
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52882a297977b9f0e7dc4155aa6e0c54ca61c8e0839fcdf90bb642b16fd56e96
3
  size 243337876
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0480bd3e3d2c4a833e31c1df97212cbb3dea83ff156e02488d4bce02a4c926f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92552aa2b952ee70b5474b2df21ebc30d3237b84140f0dc67a661759c4f7d604
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": 0.5834899544715881,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.008429215661482699,
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": 19.829,
374
  "eval_steps_per_second": 4.958,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3.833608624983245e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5253283381462097,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.016858431322965398,
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": 19.829,
374
  "eval_steps_per_second": 4.958,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008597799974712352,
379
+ "grad_norm": 1.5893906354904175,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.225,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008766384287942007,
386
+ "grad_norm": 1.3943727016448975,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.1335,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.00893496860117166,
393
+ "grad_norm": 1.213746190071106,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.1279,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.009103552914401314,
400
+ "grad_norm": 0.8661502003669739,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.0464,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.00927213722763097,
407
+ "grad_norm": 0.627927839756012,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.9024,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009440721540860623,
414
+ "grad_norm": 0.5861731767654419,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.9038,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.009609305854090276,
421
+ "grad_norm": 0.6599506735801697,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.0148,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009777890167319931,
428
+ "grad_norm": 0.6939547061920166,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.0994,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009946474480549585,
435
+ "grad_norm": 0.7301190495491028,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.9956,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.010115058793779238,
442
+ "grad_norm": 0.7114450335502625,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.9967,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.010283643107008893,
449
+ "grad_norm": 0.6240396499633789,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.8873,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.010452227420238547,
456
+ "grad_norm": 0.6104307770729065,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.0076,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0106208117334682,
463
+ "grad_norm": 0.5649477243423462,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.9833,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010789396046697855,
470
+ "grad_norm": 0.5459277629852295,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.1804,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010957980359927509,
477
+ "grad_norm": 0.5765476822853088,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.037,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.011126564673157162,
484
+ "grad_norm": 0.5954334139823914,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.1889,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.011295148986386817,
491
+ "grad_norm": 0.5802199840545654,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.1004,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01146373329961647,
498
+ "grad_norm": 0.5583539605140686,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.9828,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011632317612846124,
505
+ "grad_norm": 0.5685673356056213,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.001,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01180090192607578,
512
+ "grad_norm": 0.5391646027565002,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.99,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011969486239305433,
519
+ "grad_norm": 0.5730313062667847,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.9903,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.012138070552535086,
526
+ "grad_norm": 0.5506834387779236,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.9428,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.012306654865764741,
533
+ "grad_norm": 0.5586628317832947,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.087,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.012475239178994395,
540
+ "grad_norm": 0.5688629150390625,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.044,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012643823492224048,
547
+ "grad_norm": 0.5850514769554138,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.1281,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012812407805453703,
554
+ "grad_norm": 0.9722267389297485,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.9546,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.012980992118683357,
561
+ "grad_norm": 0.5938723087310791,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.9647,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.01314957643191301,
568
+ "grad_norm": 0.5510969161987305,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.9415,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.013318160745142664,
575
+ "grad_norm": 0.6177936792373657,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.057,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.013486745058372319,
582
+ "grad_norm": 0.5951735973358154,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.1511,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.013655329371601972,
589
+ "grad_norm": 0.5899169445037842,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.1427,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.013823913684831626,
596
+ "grad_norm": 0.6052743196487427,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.0984,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.01399249799806128,
603
+ "grad_norm": 0.5954638719558716,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.8308,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.014161082311290934,
610
+ "grad_norm": 0.6279288530349731,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.0456,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.014329666624520588,
617
+ "grad_norm": 0.6560235619544983,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.1687,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.014498250937750243,
624
+ "grad_norm": 0.6726033687591553,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.0138,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.014666835250979896,
631
+ "grad_norm": 0.6857135891914368,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.112,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.01483541956420955,
638
+ "grad_norm": 0.6859216094017029,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.9114,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.015004003877439205,
645
+ "grad_norm": 0.707784116268158,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.1385,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.015172588190668858,
652
+ "grad_norm": 0.7206366062164307,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.0489,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.015341172503898512,
659
+ "grad_norm": 0.7995542287826538,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.1788,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.015509756817128167,
666
+ "grad_norm": 0.789454996585846,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.0025,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.01567834113035782,
673
+ "grad_norm": 0.9014174342155457,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.2109,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015846925443587474,
680
+ "grad_norm": 0.890470027923584,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.189,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.016015509756817127,
687
+ "grad_norm": 0.9573277831077576,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.0214,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.01618409407004678,
694
+ "grad_norm": 1.0161410570144653,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.0902,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.016352678383276437,
701
+ "grad_norm": 1.1503360271453857,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.0676,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.01652126269650609,
708
+ "grad_norm": 1.0322849750518799,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.8626,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.016689847009735744,
715
+ "grad_norm": 1.092878818511963,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.6393,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.016858431322965398,
722
+ "grad_norm": 1.5688586235046387,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.1295,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.016858431322965398,
729
+ "eval_loss": 0.5253283381462097,
730
+ "eval_runtime": 504.2844,
731
+ "eval_samples_per_second": 19.81,
732
+ "eval_steps_per_second": 4.954,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 7.66721724996649e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null