aleegis11 commited on
Commit
b929d93
·
verified ·
1 Parent(s): d078cfb

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 sha256:4af7658ee8c865b1c96f08be7cedc7d11c8b0115f7761454a84ff24f08aaf830
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4606bf6032ab5f4312a7b7c1b39481d6eb457cd8b8b414df88146052dc277973
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b76eac8abf394080d010c31116bce1276b4159ce12df20b5b835f71ebef22ee
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945a35c4c810446646b0b3559f5c6235d7a2140049a9556a1bdb9850d49b44ba
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb5bf7b0c085400a1995bb940ffc37f4cbcbb723466d9e7e4cbea3e1dfc5a5bb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043a860a4d147cf55f314ebad1f8c3d806259ab66f1f29b61a03844a3134bb96
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": 0.5648638010025024,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.08503401360544217,
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": 13.629,
374
  "eval_steps_per_second": 3.414,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.752266054375834e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5157535672187805,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.17006802721088435,
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": 13.629,
374
  "eval_steps_per_second": 3.414,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.08673469387755102,
379
+ "grad_norm": 0.22063733637332916,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.505,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.08843537414965986,
386
+ "grad_norm": 0.2718883454799652,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.5658,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.09013605442176871,
393
+ "grad_norm": 0.23576916754245758,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.5559,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.09183673469387756,
400
+ "grad_norm": 0.2260821908712387,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.5725,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0935374149659864,
407
+ "grad_norm": 0.2174433320760727,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.5552,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.09523809523809523,
414
+ "grad_norm": 0.18729886412620544,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.5591,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.09693877551020408,
421
+ "grad_norm": 0.18305058777332306,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.5186,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.09863945578231292,
428
+ "grad_norm": 0.18157657980918884,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.5212,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.10034013605442177,
435
+ "grad_norm": 0.2037811428308487,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.5548,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.10204081632653061,
442
+ "grad_norm": 0.19771002233028412,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.5718,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.10374149659863946,
449
+ "grad_norm": 0.1701708436012268,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.5323,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.1054421768707483,
456
+ "grad_norm": 0.16258856654167175,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.5529,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.10714285714285714,
463
+ "grad_norm": 0.15664634108543396,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.5361,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.10884353741496598,
470
+ "grad_norm": 0.1598876416683197,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.5361,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.11054421768707483,
477
+ "grad_norm": 0.15704718232154846,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.5496,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.11224489795918367,
484
+ "grad_norm": 0.15310242772102356,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.5342,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.11394557823129252,
491
+ "grad_norm": 0.16328680515289307,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.5541,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.11564625850340136,
498
+ "grad_norm": 0.1636633723974228,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.5231,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.11734693877551021,
505
+ "grad_norm": 0.17201963067054749,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.5296,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.11904761904761904,
512
+ "grad_norm": 0.17560014128684998,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.5538,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.12074829931972789,
519
+ "grad_norm": 0.17567718029022217,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.525,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.12244897959183673,
526
+ "grad_norm": 0.17158040404319763,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.5249,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.12414965986394558,
533
+ "grad_norm": 0.17191287875175476,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.5435,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.12585034013605442,
540
+ "grad_norm": 0.1712241917848587,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.5402,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.12755102040816327,
547
+ "grad_norm": 0.17726421356201172,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.5372,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.1292517006802721,
554
+ "grad_norm": 0.17581725120544434,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.5363,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.13095238095238096,
561
+ "grad_norm": 0.17728029191493988,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.5372,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.1326530612244898,
568
+ "grad_norm": 0.17805948853492737,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.4983,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.13435374149659865,
575
+ "grad_norm": 0.18020778894424438,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.5372,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.1360544217687075,
582
+ "grad_norm": 0.1803048700094223,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.5289,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.1377551020408163,
589
+ "grad_norm": 0.18663981556892395,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.5464,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.13945578231292516,
596
+ "grad_norm": 0.18048711121082306,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.5241,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.141156462585034,
603
+ "grad_norm": 0.1833612471818924,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.5321,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.14285714285714285,
610
+ "grad_norm": 0.18568553030490875,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.5172,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.1445578231292517,
617
+ "grad_norm": 0.18531528115272522,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.4875,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.14625850340136054,
624
+ "grad_norm": 0.19250451028347015,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.5063,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.14795918367346939,
631
+ "grad_norm": 0.20437608659267426,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.5094,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.14965986394557823,
638
+ "grad_norm": 0.2079511433839798,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.5031,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.15136054421768708,
645
+ "grad_norm": 0.2023497223854065,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.4824,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.15306122448979592,
652
+ "grad_norm": 0.2186407893896103,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.4727,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.15476190476190477,
659
+ "grad_norm": 0.2154996246099472,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.4293,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1564625850340136,
666
+ "grad_norm": 0.22082054615020752,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.4432,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.15816326530612246,
673
+ "grad_norm": 0.3104734420776367,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.4886,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.1598639455782313,
680
+ "grad_norm": 0.2640933692455292,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.4422,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.16156462585034015,
687
+ "grad_norm": 0.2691980004310608,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.484,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.16326530612244897,
694
+ "grad_norm": 0.29049983620643616,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.4608,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.1649659863945578,
701
+ "grad_norm": 0.32303106784820557,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.4776,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.16666666666666666,
708
+ "grad_norm": 0.38841065764427185,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.4841,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.1683673469387755,
715
+ "grad_norm": 0.591713011264801,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.4225,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.17006802721088435,
722
+ "grad_norm": 1.1758267879486084,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.245,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.17006802721088435,
729
+ "eval_loss": 0.5157535672187805,
730
+ "eval_runtime": 72.3745,
731
+ "eval_samples_per_second": 13.679,
732
+ "eval_steps_per_second": 3.427,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.3471269714395136e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null