aleegis09 commited on
Commit
3550a0b
·
verified ·
1 Parent(s): 9af132f

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:a1131c69a73edae9faf30fd006f30c2f580633bd8f25934ececf756021c68c5a
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cdb938f94d59810542bfbd9c77671ae4ca0dc2450991fe2f478234eaa9649aa
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f240625a022d35302e089e0c270189142c1f41cb41133539a8efdff0d8734f91
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c879b46379c9eb4001f789c1f8421cf6e3aff373bf9e82a5ea0f5af3cb23c6
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06aadbcb2a2c1b9b2a5d7a43a8f700ffce3a138db2855fe5382d6565f9087a4d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a63b2e6cfa8e7c53a6078d8f283572bcc328e7348f57fcb91b3a529da9fcee4
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": 0.8684490919113159,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.56657223796034,
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": 13.038,
374
  "eval_steps_per_second": 3.325,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.617993572666573e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8006256818771362,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.13314447592068,
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": 13.038,
374
  "eval_steps_per_second": 3.325,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5779036827195467,
379
+ "grad_norm": 0.2893388867378235,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.844,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.5892351274787535,
386
+ "grad_norm": 0.2875760495662689,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.903,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.6005665722379604,
393
+ "grad_norm": 0.27715393900871277,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.9204,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.6118980169971672,
400
+ "grad_norm": 0.26955386996269226,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.8777,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.623229461756374,
407
+ "grad_norm": 0.2984619736671448,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.8642,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.6345609065155807,
414
+ "grad_norm": 0.2795373797416687,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.8738,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.6458923512747875,
421
+ "grad_norm": 0.28245463967323303,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.869,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.6572237960339944,
428
+ "grad_norm": 0.2853794991970062,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.8579,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.6685552407932012,
435
+ "grad_norm": 0.28548476099967957,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.8918,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.6798866855524079,
442
+ "grad_norm": 0.29240891337394714,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.8751,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.6912181303116147,
449
+ "grad_norm": 0.2984645962715149,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.9003,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.7025495750708215,
456
+ "grad_norm": 0.3319612443447113,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.9274,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.7138810198300283,
463
+ "grad_norm": 0.355567991733551,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.8746,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.7252124645892352,
470
+ "grad_norm": 0.32513099908828735,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.8737,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.7365439093484419,
477
+ "grad_norm": 0.3675692677497864,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.88,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.7478753541076487,
484
+ "grad_norm": 0.7361142635345459,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.9353,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.7592067988668555,
491
+ "grad_norm": 0.3202268183231354,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.8416,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.7705382436260623,
498
+ "grad_norm": 0.3057731091976166,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.8207,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.7818696883852692,
505
+ "grad_norm": 0.29968634247779846,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.8556,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.7932011331444759,
512
+ "grad_norm": 0.2880346477031708,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.8181,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.8045325779036827,
519
+ "grad_norm": 0.29776275157928467,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.8898,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.8158640226628895,
526
+ "grad_norm": 0.2974025011062622,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.8094,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.8271954674220963,
533
+ "grad_norm": 0.2973535358905792,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.8292,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.8385269121813032,
540
+ "grad_norm": 0.2857825756072998,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.8457,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.8498583569405099,
547
+ "grad_norm": 0.2873602509498596,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.8835,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.8611898016997167,
554
+ "grad_norm": 0.2918296456336975,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.8375,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.8725212464589235,
561
+ "grad_norm": 0.2822003662586212,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.8625,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.8838526912181303,
568
+ "grad_norm": 0.2973242998123169,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.8737,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.8951841359773371,
575
+ "grad_norm": 0.29444533586502075,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.8341,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.9065155807365439,
582
+ "grad_norm": 0.29816219210624695,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.8417,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.9178470254957507,
589
+ "grad_norm": 0.29705649614334106,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.8601,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.9291784702549575,
596
+ "grad_norm": 0.3126617968082428,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.8669,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.9405099150141643,
603
+ "grad_norm": 0.32415011525154114,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.8647,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.9518413597733711,
610
+ "grad_norm": 0.317557692527771,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.8415,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.9631728045325779,
617
+ "grad_norm": 0.36104077100753784,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.7996,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.9745042492917847,
624
+ "grad_norm": 0.3510071635246277,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.8511,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.9858356940509915,
631
+ "grad_norm": 0.3717744052410126,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.7375,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.9971671388101983,
638
+ "grad_norm": 0.735817551612854,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.6304,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.0084985835694051,
645
+ "grad_norm": 0.6571866273880005,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.3475,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.019830028328612,
652
+ "grad_norm": 0.2599029242992401,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.7176,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.0311614730878187,
659
+ "grad_norm": 0.2709405720233917,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.7737,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.0424929178470255,
666
+ "grad_norm": 0.2753128409385681,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.7402,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.0538243626062322,
673
+ "grad_norm": 0.2703261375427246,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.7564,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.065155807365439,
680
+ "grad_norm": 0.29065266251564026,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.7662,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.0764872521246458,
687
+ "grad_norm": 0.3075530230998993,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.7171,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.0878186968838528,
694
+ "grad_norm": 0.28683334589004517,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.7185,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.0991501416430596,
701
+ "grad_norm": 0.2910711467266083,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.7349,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.1104815864022664,
708
+ "grad_norm": 0.2993939220905304,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.6895,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.1218130311614731,
715
+ "grad_norm": 0.31023624539375305,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.7225,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.13314447592068,
722
+ "grad_norm": 0.32338133454322815,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.7458,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.13314447592068,
729
+ "eval_loss": 0.8006256818771362,
730
+ "eval_runtime": 11.4274,
731
+ "eval_samples_per_second": 13.039,
732
+ "eval_steps_per_second": 3.325,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.519356020093092e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null