bbytxt commited on
Commit
fa3194a
·
verified ·
1 Parent(s): 0b144c4

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:e33ea43f9beb2291bf71df807ff47d3a72df49f4c4c7a14c248564945689fbab
3
  size 30322120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cfbe704ce4276472f1f20979a6ea0043f95207eac2138f2d66cab213105345f
3
  size 30322120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f356c448a2f7dbaa0068d81e6808e9d0f1590d6837289593aed4c0c642f3a9e
3
  size 60837186
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2876946d36e7a06fa92ac4d7fe33adc6e244c5e621bbe68dcdbde5d691b7cb4d
3
  size 60837186
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4341bcfa5b25340682a457b6fcbb20cc8c5b2e7d8edaf7fad67bc2dc77fd767d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af6a4b820f4231a631cf38cad86ec74ec053a4da9eb416b7574c925fb8aa6ddc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 4.675076484680176,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.01897083234526915,
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": 63.413,
374
  "eval_steps_per_second": 15.857,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3106157258342400.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.415204048156738,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0379416646905383,
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": 63.413,
374
  "eval_steps_per_second": 15.857,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.01935024899217453,
379
+ "grad_norm": 3.7669692039489746,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 4.0896,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.019729665639079914,
386
+ "grad_norm": 4.779418468475342,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 3.8922,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0201090822859853,
393
+ "grad_norm": 5.031223297119141,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 4.1811,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.020488498932890682,
400
+ "grad_norm": 4.953243255615234,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 3.7881,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.020867915579796063,
407
+ "grad_norm": 5.7064208984375,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 4.0777,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.021247332226701447,
414
+ "grad_norm": 5.718916893005371,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 4.1119,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.02162674887360683,
421
+ "grad_norm": 6.402388572692871,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 4.0965,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.02200616552051221,
428
+ "grad_norm": 6.114238739013672,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 4.1586,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.022385582167417595,
435
+ "grad_norm": 5.461117267608643,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 3.6969,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.02276499881432298,
442
+ "grad_norm": 6.01952600479126,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 4.0374,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.023144415461228363,
449
+ "grad_norm": 6.108837604522705,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 4.3124,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.023523832108133743,
456
+ "grad_norm": 6.704663276672363,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 3.8151,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.023903248755039127,
463
+ "grad_norm": 6.462284088134766,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 4.3228,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.02428266540194451,
470
+ "grad_norm": 7.066595554351807,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 4.1603,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.024662082048849895,
477
+ "grad_norm": 6.231473922729492,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 4.3381,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.025041498695755275,
484
+ "grad_norm": 6.865777492523193,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 3.7183,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.02542091534266066,
491
+ "grad_norm": 6.609790802001953,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 4.5205,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.025800331989566043,
498
+ "grad_norm": 6.334497928619385,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 4.3837,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.026179748636471427,
505
+ "grad_norm": 7.466740608215332,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 4.3184,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.026559165283376807,
512
+ "grad_norm": 7.18544340133667,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 4.3352,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.02693858193028219,
519
+ "grad_norm": 6.762673377990723,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 4.504,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.027317998577187575,
526
+ "grad_norm": 5.527563095092773,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 4.1255,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.027697415224092956,
533
+ "grad_norm": 6.735006332397461,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 4.3378,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.02807683187099834,
540
+ "grad_norm": 6.313520431518555,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 3.8856,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.028456248517903723,
547
+ "grad_norm": 6.748076915740967,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 4.1941,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.028835665164809107,
554
+ "grad_norm": 7.661444187164307,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 4.2481,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.029215081811714488,
561
+ "grad_norm": 7.217004299163818,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 4.3925,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.02959449845861987,
568
+ "grad_norm": 7.152622222900391,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 3.8941,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.029973915105525255,
575
+ "grad_norm": 6.765809059143066,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 4.5282,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03035333175243064,
582
+ "grad_norm": 6.723090171813965,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 4.3739,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.03073274839933602,
589
+ "grad_norm": 7.00840950012207,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 4.2958,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.031112165046241404,
596
+ "grad_norm": 6.291935443878174,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 3.9951,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.03149158169314679,
603
+ "grad_norm": 6.735934734344482,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 4.4475,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.03187099834005217,
610
+ "grad_norm": 7.057698726654053,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 4.248,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.032250414986957555,
617
+ "grad_norm": 7.530543804168701,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 4.8054,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.03262983163386293,
624
+ "grad_norm": 11.086931228637695,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 4.5513,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.033009248280768316,
631
+ "grad_norm": 6.664738655090332,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 4.3811,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.0333886649276737,
638
+ "grad_norm": 7.505542278289795,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 4.5977,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.033768081574579084,
645
+ "grad_norm": 7.716992378234863,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 4.8648,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.03414749822148447,
652
+ "grad_norm": 9.030020713806152,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 4.5738,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03452691486838985,
659
+ "grad_norm": 7.875784873962402,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 4.5702,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.034906331515295236,
666
+ "grad_norm": 6.821437358856201,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 4.7577,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03528574816220062,
673
+ "grad_norm": 7.495672225952148,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 4.5927,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.035665164809106,
680
+ "grad_norm": 8.056374549865723,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 4.8237,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03604458145601138,
687
+ "grad_norm": 8.059727668762207,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 5.0902,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.036423998102916764,
694
+ "grad_norm": 8.202387809753418,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 4.8697,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03680341474982215,
701
+ "grad_norm": 8.158020973205566,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 4.7059,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.03718283139672753,
708
+ "grad_norm": 8.748244285583496,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 4.7764,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.037562248043632916,
715
+ "grad_norm": 8.805473327636719,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 5.3301,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0379416646905383,
722
+ "grad_norm": 8.97905158996582,
723
+ "learning_rate": 0.0,
724
+ "loss": 5.5488,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0379416646905383,
729
+ "eval_loss": 4.415204048156738,
730
+ "eval_runtime": 70.0282,
731
+ "eval_samples_per_second": 63.389,
732
+ "eval_steps_per_second": 15.851,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6212314516684800.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null