abaddon182 commited on
Commit
e335768
·
verified ·
1 Parent(s): b1defec

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 sha256:75b1e862fc38530a04deac190d0bb06c0f945fb14e4e0f19a0e863f475906f56
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eceda081eedf38618e4698dc7f486f85225e4bc6668dddfc20deca2cc6ea4d6b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:470786156ca87fae7362d01c02b7b6152558066c023a230172f96ac63e7752d1
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e25757156d8e02297fc3e6ecc2b5e8c99339c0d8cbef974121454b0977acd7e6
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": 0.2579116225242615,
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": 13.555,
374
  "eval_steps_per_second": 3.39,
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": 0.24134224653244019,
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": 13.555,
374
  "eval_steps_per_second": 3.39,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008236101578586136,
379
+ "grad_norm": 12.224557876586914,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.1957,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.00839759376640155,
386
+ "grad_norm": 8.004744529724121,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.9128,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.008559085954216965,
393
+ "grad_norm": 5.253309726715088,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.9792,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.008720578142032379,
400
+ "grad_norm": 3.9836456775665283,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.8306,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.008882070329847794,
407
+ "grad_norm": 9.755916595458984,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.2643,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009043562517663207,
414
+ "grad_norm": 3.1687428951263428,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.4911,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.009205054705478622,
421
+ "grad_norm": 4.697276592254639,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.8635,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009366546893294038,
428
+ "grad_norm": 5.923514366149902,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.7305,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009528039081109451,
435
+ "grad_norm": 4.387604236602783,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.8195,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.009689531268924866,
442
+ "grad_norm": 7.801131248474121,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.091,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.00985102345674028,
449
+ "grad_norm": 4.7785964012146,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.7809,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.010012515644555695,
456
+ "grad_norm": 6.387250900268555,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.8659,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.010174007832371108,
463
+ "grad_norm": 7.59951114654541,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.6494,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010335500020186524,
470
+ "grad_norm": 8.04648208618164,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.8663,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010496992208001939,
477
+ "grad_norm": 8.109950065612793,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.0831,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.010658484395817352,
484
+ "grad_norm": 6.599982261657715,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.1722,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.010819976583632767,
491
+ "grad_norm": 5.933468818664551,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.1879,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01098146877144818,
498
+ "grad_norm": 6.831328868865967,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.7366,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011142960959263596,
505
+ "grad_norm": 3.481276273727417,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.6217,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01130445314707901,
512
+ "grad_norm": 5.323179721832275,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.9114,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011465945334894425,
519
+ "grad_norm": 5.245665550231934,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.9737,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.011627437522709838,
526
+ "grad_norm": 5.951338768005371,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.9656,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.011788929710525253,
533
+ "grad_norm": 10.116493225097656,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.49,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.011950421898340668,
540
+ "grad_norm": 4.708444118499756,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.8565,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012111914086156082,
547
+ "grad_norm": 5.650876045227051,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.728,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012273406273971497,
554
+ "grad_norm": 4.68143367767334,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.9765,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.01243489846178691,
561
+ "grad_norm": 5.334131240844727,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.3298,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.012596390649602326,
568
+ "grad_norm": 6.564842700958252,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.0345,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.01275788283741774,
575
+ "grad_norm": 4.808290958404541,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.8163,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.012919375025233154,
582
+ "grad_norm": 3.600611925125122,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.8536,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01308086721304857,
589
+ "grad_norm": 5.961524486541748,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.8228,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.013242359400863983,
596
+ "grad_norm": 6.8201093673706055,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.046,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.013403851588679398,
603
+ "grad_norm": 5.5537028312683105,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.5573,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.013565343776494812,
610
+ "grad_norm": 4.81182336807251,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.8525,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.013726835964310227,
617
+ "grad_norm": 6.7080841064453125,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.3358,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.01388832815212564,
624
+ "grad_norm": 4.635632038116455,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.0484,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.014049820339941056,
631
+ "grad_norm": 5.049192428588867,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.8898,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.014211312527756469,
638
+ "grad_norm": 6.034664154052734,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.0545,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.014372804715571884,
645
+ "grad_norm": 5.578686714172363,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.8689,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0145342969033873,
652
+ "grad_norm": 5.399660110473633,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.9705,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.014695789091202713,
659
+ "grad_norm": 3.986812114715576,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.959,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.014857281279018128,
666
+ "grad_norm": 3.3498876094818115,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.6344,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.015018773466833541,
673
+ "grad_norm": 4.480000972747803,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.675,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015180265654648957,
680
+ "grad_norm": 5.378062725067139,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.9703,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.01534175784246437,
687
+ "grad_norm": 6.625367164611816,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.2045,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.015503250030279785,
694
+ "grad_norm": 7.684246063232422,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.2175,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0156647422180952,
701
+ "grad_norm": 8.043671607971191,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.1995,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.015826234405910616,
708
+ "grad_norm": 6.534055709838867,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.786,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.015987726593726027,
715
+ "grad_norm": 6.658209323883057,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.9529,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.016149218781541443,
722
+ "grad_norm": 6.959057331085205,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.1648,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.016149218781541443,
729
+ "eval_loss": 0.24134224653244019,
730
+ "eval_runtime": 769.3709,
731
+ "eval_samples_per_second": 13.555,
732
+ "eval_steps_per_second": 3.39,
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