bbytxt commited on
Commit
201fb78
·
verified ·
1 Parent(s): 37b984e

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 sha256:9d13f91581e6c0113535614fd83d5478b864440320f3a1ede11fd41a90055f8d
3
  size 628216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d679d225ca5e07bc96074f009eb38d0586a5368763bbb78f1c8bfae0e14a8bb
3
  size 628216
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:642475beb62f24b9c5d2beb8f3e4ba24ba1ef669c5507ef1ed018b2ccee6ed59
3
  size 1273162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e09ac261eeddadc9997bc627fd1ed1e786842110bc5ca577418ab8940db125
3
  size 1273162
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5457bb750bdf63b3180d04d62516b10f9c9e2cad261ef8019b6fd6a2526be36
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e46fccc4be1a8d61042b97c95ce2311a6460b315d5f85e0f154f1defc5f482
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79f5b4ba066d00b62be68b9f9ec9376def1ffea9a45f98d620f3198033186a6a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.766061782836914,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.010803802938634399,
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": 286.089,
374
  "eval_steps_per_second": 143.063,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 35008932741120.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.751439094543457,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.021607605877268798,
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": 286.089,
374
  "eval_steps_per_second": 143.063,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.011019878997407088,
379
+ "grad_norm": 0.31955963373184204,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 10.7833,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.011235955056179775,
386
+ "grad_norm": 0.2600715458393097,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 10.7863,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.011452031114952464,
393
+ "grad_norm": 0.25826898217201233,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 10.7734,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.011668107173725151,
400
+ "grad_norm": 0.33920153975486755,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 10.7821,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.01188418323249784,
407
+ "grad_norm": 0.2760711908340454,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 10.7771,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.012100259291270527,
414
+ "grad_norm": 0.2651015818119049,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 10.7812,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.012316335350043216,
421
+ "grad_norm": 0.3452089726924896,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 10.7577,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.012532411408815903,
428
+ "grad_norm": 0.24794746935367584,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 10.7618,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01274848746758859,
435
+ "grad_norm": 0.26710182428359985,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 10.7622,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.01296456352636128,
442
+ "grad_norm": 0.2514508068561554,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 10.7781,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.013180639585133967,
449
+ "grad_norm": 0.2650161385536194,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 10.7779,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.013396715643906655,
456
+ "grad_norm": 0.2767448127269745,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 10.7757,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.013612791702679343,
463
+ "grad_norm": 0.29482796788215637,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 10.771,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.013828867761452032,
470
+ "grad_norm": 0.274749755859375,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 10.7587,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.014044943820224719,
477
+ "grad_norm": 0.21438376605510712,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 10.773,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.014261019878997408,
484
+ "grad_norm": 0.2738189995288849,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 10.7707,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.014477095937770095,
491
+ "grad_norm": 0.2180059552192688,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 10.7649,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.014693171996542784,
498
+ "grad_norm": 0.2755647301673889,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 10.7556,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.014909248055315471,
505
+ "grad_norm": 0.2628243863582611,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 10.7485,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01512532411408816,
512
+ "grad_norm": 0.27653780579566956,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 10.7742,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.015341400172860847,
519
+ "grad_norm": 0.292253315448761,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 10.7542,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.015557476231633534,
526
+ "grad_norm": 0.21869610249996185,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 10.7724,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.015773552290406223,
533
+ "grad_norm": 0.20132863521575928,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 10.7621,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.01598962834917891,
540
+ "grad_norm": 0.2435745745897293,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 10.7661,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.016205704407951597,
547
+ "grad_norm": 0.23909196257591248,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 10.7694,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.016421780466724288,
554
+ "grad_norm": 0.22482334077358246,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 10.7642,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.016637856525496975,
561
+ "grad_norm": 0.2314310371875763,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 10.7584,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.016853932584269662,
568
+ "grad_norm": 0.23524075746536255,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 10.7632,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.01707000864304235,
575
+ "grad_norm": 0.20763476192951202,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 10.7533,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.01728608470181504,
582
+ "grad_norm": 0.1953965127468109,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 10.7633,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.017502160760587727,
589
+ "grad_norm": 0.1644563525915146,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 10.764,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.017718236819360415,
596
+ "grad_norm": 0.2148687094449997,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 10.7566,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.017934312878133102,
603
+ "grad_norm": 0.2654571831226349,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 10.7444,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.018150388936905792,
610
+ "grad_norm": 0.231702521443367,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 10.753,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.01836646499567848,
617
+ "grad_norm": 0.26304373145103455,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 10.7559,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.018582541054451167,
624
+ "grad_norm": 0.19173169136047363,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 10.7675,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.018798617113223854,
631
+ "grad_norm": 0.2556131184101105,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 10.7589,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.01901469317199654,
638
+ "grad_norm": 0.22893981635570526,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 10.7599,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.019230769230769232,
645
+ "grad_norm": 0.21988166868686676,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 10.7564,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.01944684528954192,
652
+ "grad_norm": 0.24298734962940216,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 10.7532,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.019662921348314606,
659
+ "grad_norm": 0.21422868967056274,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 10.7588,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.019878997407087293,
666
+ "grad_norm": 0.18029530346393585,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 10.7508,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.020095073465859984,
673
+ "grad_norm": 0.29323095083236694,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 10.7534,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.02031114952463267,
680
+ "grad_norm": 0.24313682317733765,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 10.753,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.02052722558340536,
687
+ "grad_norm": 0.30919376015663147,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 10.7502,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.020743301642178046,
694
+ "grad_norm": 0.3091332018375397,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 10.7492,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.020959377700950736,
701
+ "grad_norm": 0.31597936153411865,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 10.7353,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.021175453759723423,
708
+ "grad_norm": 0.41740843653678894,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 10.753,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.02139152981849611,
715
+ "grad_norm": 0.3725014328956604,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 10.72,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.021607605877268798,
722
+ "grad_norm": 0.6240119934082031,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 10.7379,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.021607605877268798,
729
+ "eval_loss": 10.751439094543457,
730
+ "eval_runtime": 27.1534,
731
+ "eval_samples_per_second": 287.073,
732
+ "eval_steps_per_second": 143.555,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 69847090200576.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null