aleegis12 commited on
Commit
5475b81
·
verified ·
1 Parent(s): f8782e4

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 sha256:0f6253d3c84bf9f49bccf60ff104ca0cfc1071d8665e99a5d3974461e900b64a
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a060f820c69530408eb26feb7b109cdff742e1091e850dc132f616089aeb58
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e9b8353f498720dad456791a7136961474bbff71fe85a6fd4d281f4c2f6cc59
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020a32595744ac030a3caa968d064c22405deca1e1c91a6b7a3301ffe6daf11a
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:392248293f8f9103c07e22ba8c033ac4eb800fa33494d3431d193ee37a18efab
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e21ece48c62eccc093effa9e0e346993dccddcc589c29a6524cc307f4243ccb0
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": 1.1081956624984741,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.00921574048474795,
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": 13.2,
374
  "eval_steps_per_second": 3.301,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.112815425670349e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.031202793121338,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0184314809694959,
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": 13.2,
374
  "eval_steps_per_second": 3.301,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.009400055294442908,
379
+ "grad_norm": 0.48868894577026367,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.8871,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.009584370104137867,
386
+ "grad_norm": 0.4619584381580353,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.9272,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.009768684913832827,
393
+ "grad_norm": 0.4740832448005676,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.017,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.009952999723527785,
400
+ "grad_norm": 0.36349406838417053,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.0592,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.010137314533222745,
407
+ "grad_norm": 0.3204439878463745,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.9724,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.010321629342917703,
414
+ "grad_norm": 0.2830290198326111,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.9933,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.010505944152612662,
421
+ "grad_norm": 0.2824137806892395,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.0,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.010690258962307622,
428
+ "grad_norm": 0.2988187074661255,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.028,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01087457377200258,
435
+ "grad_norm": 0.25733092427253723,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.0645,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.01105888858169754,
442
+ "grad_norm": 0.29357191920280457,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.0244,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.011243203391392498,
449
+ "grad_norm": 0.28911539912223816,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.0476,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.011427518201087457,
456
+ "grad_norm": 0.307320237159729,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.0962,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.011611833010782417,
463
+ "grad_norm": 0.28484243154525757,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.0024,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.011796147820477375,
470
+ "grad_norm": 0.2947733998298645,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.934,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.011980462630172335,
477
+ "grad_norm": 0.28290286660194397,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.92,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.012164777439867294,
484
+ "grad_norm": 0.29178595542907715,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.035,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.012349092249562252,
491
+ "grad_norm": 0.2829218804836273,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.0749,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.012533407059257212,
498
+ "grad_norm": 0.3027656376361847,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.0472,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.01271772186895217,
505
+ "grad_norm": 0.3055793344974518,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.0366,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.012902036678647128,
512
+ "grad_norm": 0.2900894582271576,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.063,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.013086351488342089,
519
+ "grad_norm": 0.2908357083797455,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.0328,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.013270666298037047,
526
+ "grad_norm": 0.2756956219673157,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.9437,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.013454981107732007,
533
+ "grad_norm": 0.2930951416492462,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.0172,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.013639295917426965,
540
+ "grad_norm": 0.29136356711387634,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.0952,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.013823610727121923,
547
+ "grad_norm": 0.32149508595466614,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.9384,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.014007925536816884,
554
+ "grad_norm": 0.3315494954586029,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.0781,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.014192240346511842,
561
+ "grad_norm": 0.31092604994773865,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.0356,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.014376555156206802,
568
+ "grad_norm": 0.3504660427570343,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.1046,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.01456086996590176,
575
+ "grad_norm": 0.31477150321006775,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.0652,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.014745184775596719,
582
+ "grad_norm": 0.3404114544391632,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.0259,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.014929499585291679,
589
+ "grad_norm": 0.32545822858810425,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.0509,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.015113814394986637,
596
+ "grad_norm": 0.3260136544704437,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.0279,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.015298129204681597,
603
+ "grad_norm": 0.37822264432907104,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.9802,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.015482444014376555,
610
+ "grad_norm": 0.37306562066078186,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.1249,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.015666758824071515,
617
+ "grad_norm": 0.37852713465690613,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.1109,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.015851073633766474,
624
+ "grad_norm": 0.3962250351905823,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.1005,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.016035388443461432,
631
+ "grad_norm": 0.41836705803871155,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.0755,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.01621970325315639,
638
+ "grad_norm": 0.4547691345214844,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.071,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.01640401806285135,
645
+ "grad_norm": 0.4516165256500244,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.089,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.01658833287254631,
652
+ "grad_norm": 0.46264412999153137,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.0303,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.01677264768224127,
659
+ "grad_norm": 0.5163282752037048,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.0642,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.016956962491936227,
666
+ "grad_norm": 0.49469366669654846,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.9772,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.017141277301631185,
673
+ "grad_norm": 0.5242800712585449,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.0933,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.017325592111326144,
680
+ "grad_norm": 0.5365490913391113,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.9827,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.017509906921021105,
687
+ "grad_norm": 0.5569202899932861,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.1377,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.017694221730716064,
694
+ "grad_norm": 0.6217386722564697,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.0177,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.017878536540411022,
701
+ "grad_norm": 0.6114227175712585,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.9871,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.01806285135010598,
708
+ "grad_norm": 0.6836398243904114,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.9991,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.01824716615980094,
715
+ "grad_norm": 0.7496846914291382,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.0059,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0184314809694959,
722
+ "grad_norm": 0.8987806439399719,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.7866,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0184314809694959,
729
+ "eval_loss": 1.031202793121338,
730
+ "eval_runtime": 692.9955,
731
+ "eval_samples_per_second": 13.186,
732
+ "eval_steps_per_second": 3.297,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.4158528819023053e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null