lesso commited on
Commit
35f2d85
·
verified ·
1 Parent(s): 7480780

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:ab01e4e12392601aaeac139cda908de1a5a5600dbfc5c53586f7f325205a1490
3
  size 871457448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c2a6d7f68310c78380d6c4ce36dcb947cbef25bc0c7c5dd186573b8f76d40ee
3
  size 871457448
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad2b591994c13c7abf783dd6bee6953d1c323372b3ee1948de94cc6301f17647
3
  size 443280340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba84b182ba6a2ec82a98476274fd79d705d0ba7632cd52cc58490614d378feb7
3
  size 443280340
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6a390f5aa38188edbfecf13ff111eb6f59832ed8d65ccacf0ae6ffb1a4433a1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22cb16048613c4c5759c220f74762a10917ee15e65140948779c5f187b65214d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6da931a425e1a2517e12e4e92e5527637ffeeadbe51a85a949dc53b89acf0af
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ba1abeedc944b50dfc9c3bffbf774b90111e900acad34ff55445cc0c42e5cd9
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2892735004425049,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.008165931732810714,
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": 7.491,
374
  "eval_steps_per_second": 1.874,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.1806176530333696e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.202304482460022,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.01633186346562143,
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": 7.491,
374
  "eval_steps_per_second": 1.874,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008329250367466928,
379
+ "grad_norm": 1.8733032941818237,
380
+ "learning_rate": 7.85778947368421e-05,
381
+ "loss": 0.91,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008492569002123142,
386
+ "grad_norm": 1.351426124572754,
387
+ "learning_rate": 7.805052631578947e-05,
388
+ "loss": 1.0789,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.008655887636779356,
393
+ "grad_norm": 0.9720818400382996,
394
+ "learning_rate": 7.752315789473683e-05,
395
+ "loss": 0.9113,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.008819206271435572,
400
+ "grad_norm": 0.7470458745956421,
401
+ "learning_rate": 7.69957894736842e-05,
402
+ "loss": 0.917,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.008982524906091785,
407
+ "grad_norm": 0.6289156079292297,
408
+ "learning_rate": 7.646842105263158e-05,
409
+ "loss": 0.8513,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009145843540748,
414
+ "grad_norm": 0.6980412006378174,
415
+ "learning_rate": 7.594105263157894e-05,
416
+ "loss": 1.036,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.009309162175404213,
421
+ "grad_norm": 0.6612934470176697,
422
+ "learning_rate": 7.541368421052631e-05,
423
+ "loss": 0.9251,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009472480810060429,
428
+ "grad_norm": 0.6878615021705627,
429
+ "learning_rate": 7.488631578947369e-05,
430
+ "loss": 0.8502,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009635799444716642,
435
+ "grad_norm": 0.7292014360427856,
436
+ "learning_rate": 7.435894736842105e-05,
437
+ "loss": 0.9259,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.009799118079372856,
442
+ "grad_norm": 0.7414498329162598,
443
+ "learning_rate": 7.383157894736842e-05,
444
+ "loss": 0.9209,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.00996243671402907,
449
+ "grad_norm": 0.7968541383743286,
450
+ "learning_rate": 7.33042105263158e-05,
451
+ "loss": 1.006,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.010125755348685286,
456
+ "grad_norm": 0.7785654067993164,
457
+ "learning_rate": 7.277684210526316e-05,
458
+ "loss": 0.998,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0102890739833415,
463
+ "grad_norm": 0.7336849570274353,
464
+ "learning_rate": 7.224947368421053e-05,
465
+ "loss": 0.9043,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010452392617997713,
470
+ "grad_norm": 0.6646738648414612,
471
+ "learning_rate": 7.172210526315789e-05,
472
+ "loss": 0.8958,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010615711252653927,
477
+ "grad_norm": 0.8088564872741699,
478
+ "learning_rate": 7.119473684210526e-05,
479
+ "loss": 1.0874,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.010779029887310143,
484
+ "grad_norm": 0.7672606706619263,
485
+ "learning_rate": 7.066736842105262e-05,
486
+ "loss": 0.9482,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.010942348521966357,
491
+ "grad_norm": 0.9228386878967285,
492
+ "learning_rate": 7.013999999999999e-05,
493
+ "loss": 1.1435,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01110566715662257,
498
+ "grad_norm": 0.8074588179588318,
499
+ "learning_rate": 6.961263157894737e-05,
500
+ "loss": 1.1595,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011268985791278784,
505
+ "grad_norm": 0.7998431324958801,
506
+ "learning_rate": 6.908526315789473e-05,
507
+ "loss": 0.9535,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.011432304425935,
512
+ "grad_norm": 0.8504302501678467,
513
+ "learning_rate": 6.85578947368421e-05,
514
+ "loss": 1.0123,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011595623060591214,
519
+ "grad_norm": 1.089838981628418,
520
+ "learning_rate": 6.803052631578946e-05,
521
+ "loss": 1.0045,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.011758941695247428,
526
+ "grad_norm": 0.89869225025177,
527
+ "learning_rate": 6.750315789473684e-05,
528
+ "loss": 0.7452,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.011922260329903641,
533
+ "grad_norm": 0.943939745426178,
534
+ "learning_rate": 6.697578947368421e-05,
535
+ "loss": 0.9891,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.012085578964559857,
540
+ "grad_norm": 0.9160717725753784,
541
+ "learning_rate": 6.644842105263157e-05,
542
+ "loss": 0.9342,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.01224889759921607,
547
+ "grad_norm": 1.082808256149292,
548
+ "learning_rate": 6.592105263157895e-05,
549
+ "loss": 0.8208,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012412216233872285,
554
+ "grad_norm": 1.2106088399887085,
555
+ "learning_rate": 6.539368421052632e-05,
556
+ "loss": 1.2033,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.012575534868528498,
561
+ "grad_norm": 1.1063079833984375,
562
+ "learning_rate": 6.486631578947368e-05,
563
+ "loss": 0.9361,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.012738853503184714,
568
+ "grad_norm": 1.1758522987365723,
569
+ "learning_rate": 6.433894736842105e-05,
570
+ "loss": 0.8596,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.012902172137840928,
575
+ "grad_norm": 1.644689679145813,
576
+ "learning_rate": 6.381157894736842e-05,
577
+ "loss": 0.9575,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.013065490772497142,
582
+ "grad_norm": 1.4819023609161377,
583
+ "learning_rate": 6.328421052631578e-05,
584
+ "loss": 1.0894,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.013228809407153356,
589
+ "grad_norm": 1.3677387237548828,
590
+ "learning_rate": 6.275684210526315e-05,
591
+ "loss": 1.1177,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.013392128041809571,
596
+ "grad_norm": 2.352775812149048,
597
+ "learning_rate": 6.222947368421053e-05,
598
+ "loss": 1.5418,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.013555446676465785,
603
+ "grad_norm": 3.2826321125030518,
604
+ "learning_rate": 6.170210526315789e-05,
605
+ "loss": 1.056,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.013718765311121999,
610
+ "grad_norm": 1.8273366689682007,
611
+ "learning_rate": 6.117473684210526e-05,
612
+ "loss": 1.4655,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.013882083945778213,
617
+ "grad_norm": 3.2411186695098877,
618
+ "learning_rate": 6.064736842105263e-05,
619
+ "loss": 1.4192,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.014045402580434428,
624
+ "grad_norm": 1.9905811548233032,
625
+ "learning_rate": 6.0119999999999994e-05,
626
+ "loss": 1.3103,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.014208721215090642,
631
+ "grad_norm": 1.930762529373169,
632
+ "learning_rate": 5.959263157894736e-05,
633
+ "loss": 0.9912,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.014372039849746856,
638
+ "grad_norm": 2.365586280822754,
639
+ "learning_rate": 5.906526315789473e-05,
640
+ "loss": 1.1073,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.01453535848440307,
645
+ "grad_norm": 2.24143648147583,
646
+ "learning_rate": 5.853789473684211e-05,
647
+ "loss": 1.1891,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.014698677119059285,
652
+ "grad_norm": 2.7449162006378174,
653
+ "learning_rate": 5.8010526315789476e-05,
654
+ "loss": 1.3695,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.014861995753715499,
659
+ "grad_norm": 3.0811843872070312,
660
+ "learning_rate": 5.748315789473684e-05,
661
+ "loss": 0.7728,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.015025314388371713,
666
+ "grad_norm": 2.499147891998291,
667
+ "learning_rate": 5.6955789473684207e-05,
668
+ "loss": 1.2178,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.015188633023027927,
673
+ "grad_norm": 3.266294240951538,
674
+ "learning_rate": 5.642842105263157e-05,
675
+ "loss": 1.3692,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015351951657684142,
680
+ "grad_norm": 3.7990870475769043,
681
+ "learning_rate": 5.5901052631578944e-05,
682
+ "loss": 1.5496,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.015515270292340356,
687
+ "grad_norm": 2.9418234825134277,
688
+ "learning_rate": 5.5373684210526316e-05,
689
+ "loss": 1.4258,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.01567858892699657,
694
+ "grad_norm": 3.900726795196533,
695
+ "learning_rate": 5.484631578947369e-05,
696
+ "loss": 1.4664,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.015841907561652786,
701
+ "grad_norm": 3.98392391204834,
702
+ "learning_rate": 5.4318947368421054e-05,
703
+ "loss": 2.07,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.016005226196308998,
708
+ "grad_norm": 4.655868053436279,
709
+ "learning_rate": 5.379157894736842e-05,
710
+ "loss": 1.5402,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.016168544830965213,
715
+ "grad_norm": 5.109676837921143,
716
+ "learning_rate": 5.3264210526315785e-05,
717
+ "loss": 1.723,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.01633186346562143,
722
+ "grad_norm": 7.739476680755615,
723
+ "learning_rate": 5.273684210526315e-05,
724
+ "loss": 2.4745,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.01633186346562143,
729
+ "eval_loss": 1.202304482460022,
730
+ "eval_runtime": 344.5693,
731
+ "eval_samples_per_second": 7.482,
732
+ "eval_steps_per_second": 1.872,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4.33964503227433e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null