lesso commited on
Commit
745f444
·
verified ·
1 Parent(s): 6b73bdc

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 sha256:7fcd9e6bad6b0d5100e958de60006d40cde40375f40e16bff61f6e2950d22d9c
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb610103a64f11ffddf59071f6e7b48e73e9f4f7b6076bbceb75adebad3bf54c
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7338e43b67d5f7163731880b1705b777ce1f99bec8daecec58b67571683b54b
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31aad0dbac4224bd9e0e5c6a62650086ee40fe2677dd32d46948ef63ec1d3a70
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20fc2b9b5a5d9506299f7be1c884e7adafa18ecae9f416ca1baac4cc66b671f1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:045b75fd050c10a4fe14a1c98e12907f7f4ce5a7257e00e93adf6da74be770bb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1479f554a7a167fd87e9ce99235e9d065370465268e2f8373a74df4bd50982ce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe6f0a2f7a14e66c6816df9a38574183cedfa2cc544d1c8e8e8cea1139c2f76
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4635015726089478,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.05595970900951315,
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": 7.895,
374
  "eval_steps_per_second": 1.989,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.093062590509875e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4105467796325684,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.1119194180190263,
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": 7.895,
374
  "eval_steps_per_second": 1.989,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.05707890318970341,
379
+ "grad_norm": 0.8516172170639038,
380
+ "learning_rate": 7.889157894736843e-05,
381
+ "loss": 1.9615,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.058198097369893675,
386
+ "grad_norm": 0.7036626935005188,
387
+ "learning_rate": 7.83621052631579e-05,
388
+ "loss": 2.1477,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.05931729155008394,
393
+ "grad_norm": 0.7194252014160156,
394
+ "learning_rate": 7.783263157894737e-05,
395
+ "loss": 2.3045,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0604364857302742,
400
+ "grad_norm": 0.7690565586090088,
401
+ "learning_rate": 7.730315789473684e-05,
402
+ "loss": 2.2782,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.06155567991046446,
407
+ "grad_norm": 0.6265071630477905,
408
+ "learning_rate": 7.677368421052632e-05,
409
+ "loss": 1.7766,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.06267487409065473,
414
+ "grad_norm": 0.6072700619697571,
415
+ "learning_rate": 7.624421052631579e-05,
416
+ "loss": 1.8207,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.063794068270845,
421
+ "grad_norm": 0.5296346545219421,
422
+ "learning_rate": 7.571473684210526e-05,
423
+ "loss": 1.2979,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.06491326245103525,
428
+ "grad_norm": 0.6143375635147095,
429
+ "learning_rate": 7.518526315789475e-05,
430
+ "loss": 1.7014,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.06603245663122552,
435
+ "grad_norm": 0.5131465196609497,
436
+ "learning_rate": 7.465578947368422e-05,
437
+ "loss": 1.1046,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.06715165081141578,
442
+ "grad_norm": 0.5977643728256226,
443
+ "learning_rate": 7.412631578947369e-05,
444
+ "loss": 1.6154,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.06827084499160604,
449
+ "grad_norm": 0.5476318001747131,
450
+ "learning_rate": 7.359684210526317e-05,
451
+ "loss": 1.3177,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0693900391717963,
456
+ "grad_norm": 0.6704787611961365,
457
+ "learning_rate": 7.306736842105264e-05,
458
+ "loss": 1.7062,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.07050923335198657,
463
+ "grad_norm": 0.6229788064956665,
464
+ "learning_rate": 7.253789473684211e-05,
465
+ "loss": 1.4367,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.07162842753217684,
470
+ "grad_norm": 0.6314613819122314,
471
+ "learning_rate": 7.200842105263158e-05,
472
+ "loss": 1.5649,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0727476217123671,
477
+ "grad_norm": 0.6403206586837769,
478
+ "learning_rate": 7.147894736842105e-05,
479
+ "loss": 1.8579,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.07386681589255736,
484
+ "grad_norm": 0.5655908584594727,
485
+ "learning_rate": 7.094947368421052e-05,
486
+ "loss": 1.119,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.07498601007274762,
491
+ "grad_norm": 0.502298891544342,
492
+ "learning_rate": 7.042e-05,
493
+ "loss": 0.8837,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.07610520425293789,
498
+ "grad_norm": 0.5558024048805237,
499
+ "learning_rate": 6.989052631578948e-05,
500
+ "loss": 1.1857,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.07722439843312814,
505
+ "grad_norm": 0.5176172852516174,
506
+ "learning_rate": 6.936105263157896e-05,
507
+ "loss": 0.9946,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.07834359261331841,
512
+ "grad_norm": 0.576248824596405,
513
+ "learning_rate": 6.883157894736843e-05,
514
+ "loss": 0.9529,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.07946278679350867,
519
+ "grad_norm": 0.5664923787117004,
520
+ "learning_rate": 6.83021052631579e-05,
521
+ "loss": 1.1525,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.08058198097369894,
526
+ "grad_norm": 0.6141046285629272,
527
+ "learning_rate": 6.777263157894737e-05,
528
+ "loss": 1.2382,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0817011751538892,
533
+ "grad_norm": 0.5944051146507263,
534
+ "learning_rate": 6.724315789473684e-05,
535
+ "loss": 1.1227,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.08282036933407946,
540
+ "grad_norm": 0.6328909397125244,
541
+ "learning_rate": 6.671368421052631e-05,
542
+ "loss": 1.1311,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.08393956351426973,
547
+ "grad_norm": 0.5099555850028992,
548
+ "learning_rate": 6.61842105263158e-05,
549
+ "loss": 1.0304,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.08505875769445999,
554
+ "grad_norm": 0.6328510642051697,
555
+ "learning_rate": 6.565473684210527e-05,
556
+ "loss": 0.997,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.08617795187465026,
561
+ "grad_norm": 0.5725546479225159,
562
+ "learning_rate": 6.512526315789474e-05,
563
+ "loss": 0.9623,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.08729714605484051,
568
+ "grad_norm": 0.6395103931427002,
569
+ "learning_rate": 6.459578947368421e-05,
570
+ "loss": 1.5526,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.08841634023503078,
575
+ "grad_norm": 0.6277320981025696,
576
+ "learning_rate": 6.406631578947369e-05,
577
+ "loss": 1.1281,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.08953553441522104,
582
+ "grad_norm": 0.589504063129425,
583
+ "learning_rate": 6.353684210526316e-05,
584
+ "loss": 1.0345,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.09065472859541131,
589
+ "grad_norm": 0.6192626357078552,
590
+ "learning_rate": 6.300736842105263e-05,
591
+ "loss": 0.9688,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.09177392277560156,
596
+ "grad_norm": 0.6085880994796753,
597
+ "learning_rate": 6.247789473684212e-05,
598
+ "loss": 0.8814,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.09289311695579183,
603
+ "grad_norm": 0.6605837345123291,
604
+ "learning_rate": 6.194842105263159e-05,
605
+ "loss": 1.4382,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.09401231113598209,
610
+ "grad_norm": 0.6139897108078003,
611
+ "learning_rate": 6.141894736842106e-05,
612
+ "loss": 1.091,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.09513150531617236,
617
+ "grad_norm": 0.6851410269737244,
618
+ "learning_rate": 6.088947368421053e-05,
619
+ "loss": 1.1183,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.09625069949636261,
624
+ "grad_norm": 0.6170366406440735,
625
+ "learning_rate": 6.036e-05,
626
+ "loss": 1.105,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.09736989367655288,
631
+ "grad_norm": 0.84287029504776,
632
+ "learning_rate": 5.9830526315789475e-05,
633
+ "loss": 1.0071,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.09848908785674315,
638
+ "grad_norm": 0.6654536128044128,
639
+ "learning_rate": 5.9301052631578946e-05,
640
+ "loss": 1.1307,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.09960828203693341,
645
+ "grad_norm": 0.6223897933959961,
646
+ "learning_rate": 5.877157894736843e-05,
647
+ "loss": 0.885,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.10072747621712368,
652
+ "grad_norm": 0.7293018102645874,
653
+ "learning_rate": 5.82421052631579e-05,
654
+ "loss": 1.1569,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.10184667039731393,
659
+ "grad_norm": 0.654303789138794,
660
+ "learning_rate": 5.771263157894737e-05,
661
+ "loss": 0.9901,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1029658645775042,
666
+ "grad_norm": 0.7520757913589478,
667
+ "learning_rate": 5.718315789473685e-05,
668
+ "loss": 1.4022,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.10408505875769446,
673
+ "grad_norm": 0.7011393904685974,
674
+ "learning_rate": 5.665368421052632e-05,
675
+ "loss": 1.18,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.10520425293788473,
680
+ "grad_norm": 0.7474265098571777,
681
+ "learning_rate": 5.612421052631579e-05,
682
+ "loss": 1.3109,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.10632344711807498,
687
+ "grad_norm": 0.8840892910957336,
688
+ "learning_rate": 5.559473684210527e-05,
689
+ "loss": 1.4722,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.10744264129826525,
694
+ "grad_norm": 0.831760048866272,
695
+ "learning_rate": 5.506526315789474e-05,
696
+ "loss": 1.3972,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.1085618354784555,
701
+ "grad_norm": 1.0217140913009644,
702
+ "learning_rate": 5.453578947368421e-05,
703
+ "loss": 1.6376,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.10968102965864578,
708
+ "grad_norm": 2.1897904872894287,
709
+ "learning_rate": 5.400631578947369e-05,
710
+ "loss": 1.3989,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.11080022383883603,
715
+ "grad_norm": 1.0960580110549927,
716
+ "learning_rate": 5.347684210526316e-05,
717
+ "loss": 1.8274,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.1119194180190263,
722
+ "grad_norm": 1.469871163368225,
723
+ "learning_rate": 5.294736842105263e-05,
724
+ "loss": 2.0208,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.1119194180190263,
729
+ "eval_loss": 1.4105467796325684,
730
+ "eval_runtime": 48.5917,
731
+ "eval_samples_per_second": 7.759,
732
+ "eval_steps_per_second": 1.955,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4.167268761285427e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null