aleegis12 commited on
Commit
aeaef1b
·
verified ·
1 Parent(s): dc35634

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:c3826016bce7f377df1e3456f1537e9f50eef878c7627e51658fd75372445e4c
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f531ec01cce383caffb10e654b3eade8839265a804ac6ea625b0e24db8a6ee
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd63a0ab31ac15fb70f81aaf24465fe7af250e5240c7e7cf7b04f32fd7e61d67
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d10aa52d80f08a4f8c8832ab40ed61fb07eb2dc9ddfc7e3f561b357f9da977d
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ed7fa0287e33b90bc1f8464d1117fbc3c9d414db1d48cbb8f36af023d3f083a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb5f32a452047fe1001f1a1bc9fdc544d2e1c54acdc3ec0e1e04fa31a816c3b
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": 0.14867614209651947,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.2306805074971165,
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": 7.569,
374
  "eval_steps_per_second": 1.908,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.30863552956203e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.13724249601364136,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.461361014994233,
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": 7.569,
374
  "eval_steps_per_second": 1.908,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.23529411764705882,
379
+ "grad_norm": 0.1632201224565506,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.1716,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.23990772779700115,
386
+ "grad_norm": 0.19273817539215088,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.1704,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.24452133794694347,
393
+ "grad_norm": 0.14002658426761627,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.1394,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.2491349480968858,
400
+ "grad_norm": 0.13335628807544708,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.1303,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.2537485582468281,
407
+ "grad_norm": 0.14133335649967194,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.1656,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.25836216839677045,
414
+ "grad_norm": 0.2346196323633194,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.1598,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2629757785467128,
421
+ "grad_norm": 0.17851288616657257,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.1726,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2675893886966551,
428
+ "grad_norm": 0.1496780514717102,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.1431,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.2722029988465975,
435
+ "grad_norm": 0.15850284695625305,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.1457,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2768166089965398,
442
+ "grad_norm": 0.15871545672416687,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.1371,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.28143021914648214,
449
+ "grad_norm": 0.146070197224617,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.118,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.28604382929642447,
456
+ "grad_norm": 0.14819538593292236,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.1166,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2906574394463668,
463
+ "grad_norm": 0.19428430497646332,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.1572,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.2952710495963091,
470
+ "grad_norm": 0.15656042098999023,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.1364,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.29988465974625145,
477
+ "grad_norm": 0.20241779088974,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.1594,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3044982698961938,
484
+ "grad_norm": 0.15743836760520935,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.1345,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3091118800461361,
491
+ "grad_norm": 0.35860782861709595,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.1605,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.3137254901960784,
498
+ "grad_norm": 0.18126502633094788,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.1169,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.31833910034602075,
505
+ "grad_norm": 0.1790701299905777,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.127,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.3229527104959631,
512
+ "grad_norm": 0.16510623693466187,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.1194,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.3275663206459054,
519
+ "grad_norm": 0.16934818029403687,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.1305,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.33217993079584773,
526
+ "grad_norm": 0.23819081485271454,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.1846,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.33679354094579006,
533
+ "grad_norm": 0.18752993643283844,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.1455,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3414071510957324,
540
+ "grad_norm": 0.21817506849765778,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.1476,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.3460207612456747,
547
+ "grad_norm": 0.17927341163158417,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.1292,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.3506343713956171,
554
+ "grad_norm": 0.17165836691856384,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.1188,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3552479815455594,
561
+ "grad_norm": 0.18539024889469147,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.1475,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.35986159169550175,
568
+ "grad_norm": 0.16444933414459229,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.1128,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3644752018454441,
575
+ "grad_norm": 0.15929977595806122,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0969,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.3690888119953864,
582
+ "grad_norm": 0.18575657904148102,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.1059,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.3737024221453287,
589
+ "grad_norm": 0.18567027151584625,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.1247,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.37831603229527105,
596
+ "grad_norm": 0.1998375505208969,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.1476,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.3829296424452134,
603
+ "grad_norm": 0.21210910379886627,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.1332,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.3875432525951557,
610
+ "grad_norm": 0.19910669326782227,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.1241,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.39215686274509803,
617
+ "grad_norm": 0.20645062625408173,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.1255,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.39677047289504036,
624
+ "grad_norm": 0.2057769000530243,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.134,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.4013840830449827,
631
+ "grad_norm": 0.20311889052391052,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.1367,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.405997693194925,
638
+ "grad_norm": 0.2152274250984192,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.1495,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.41061130334486734,
645
+ "grad_norm": 0.19864894449710846,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.1386,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.41522491349480967,
652
+ "grad_norm": 0.19807681441307068,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.1241,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.419838523644752,
659
+ "grad_norm": 0.19944807887077332,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.1215,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.4244521337946944,
666
+ "grad_norm": 0.18852022290229797,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.1025,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.4290657439446367,
673
+ "grad_norm": 0.2149016410112381,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.1276,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.43367935409457903,
680
+ "grad_norm": 0.20780391991138458,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.1063,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.43829296424452135,
687
+ "grad_norm": 0.20517082512378693,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.1052,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.4429065743944637,
694
+ "grad_norm": 0.30427610874176025,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.1841,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.447520184544406,
701
+ "grad_norm": 0.22177459299564362,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.1205,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.45213379469434833,
708
+ "grad_norm": 0.2582891583442688,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.1276,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.45674740484429066,
715
+ "grad_norm": 0.24995219707489014,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.137,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.461361014994233,
722
+ "grad_norm": 0.21583551168441772,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0826,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.461361014994233,
729
+ "eval_loss": 0.13724249601364136,
730
+ "eval_runtime": 48.2111,
731
+ "eval_samples_per_second": 7.571,
732
+ "eval_steps_per_second": 1.908,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.6323561949115187e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null