bbytxt commited on
Commit
770b6bd
·
verified ·
1 Parent(s): 037b451

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 sha256:57b2b962b9a3a46b42284b67d433f1049f17ff203fa78425333185079f4a7441
3
  size 78480072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:006f7365dfdc450b6c79243076fa9c2faff8c06f10792c1659cb925ef75415a8
3
  size 78480072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31e82a9b79abdf21bfc097df7976a4b93292c7f2aa033e9b3d3e038c2f017b90
3
  size 157104826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38dd9c3b2423aaaca72c038602b320323d0d6ffb71c9bf42f943016f4569bec2
3
  size 157104826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abc561f1ba62405cdcbd76262602a7f676639f9a6e38795a5467aaf7aa626c4d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628de751c39e070b2637cb9c6f20d0df11cbe56f6aa6898dfb060b339f074696
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": 5.583864212036133,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.6535947712418301,
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": 27.834,
374
  "eval_steps_per_second": 7.12,
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": 1.96755069075456e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.5732855796813965,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.3071895424836601,
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": 27.834,
374
  "eval_steps_per_second": 7.12,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.6666666666666666,
379
+ "grad_norm": 20.410966873168945,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 5.2445,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.6797385620915033,
386
+ "grad_norm": 22.301136016845703,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 6.6047,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.6928104575163399,
393
+ "grad_norm": 26.021312713623047,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 7.225,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.7058823529411765,
400
+ "grad_norm": 25.37548065185547,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 7.1886,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.7189542483660131,
407
+ "grad_norm": 24.194847106933594,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 7.4705,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.7320261437908496,
414
+ "grad_norm": 31.78634262084961,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 7.6195,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.7450980392156863,
421
+ "grad_norm": 33.419776916503906,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 8.226,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.7581699346405228,
428
+ "grad_norm": 5.473607063293457,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 2.4786,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.7712418300653595,
435
+ "grad_norm": 7.471803665161133,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 3.0997,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.7843137254901961,
442
+ "grad_norm": 11.024681091308594,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 3.7581,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.7973856209150327,
449
+ "grad_norm": 16.229074478149414,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 4.2436,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.8104575163398693,
456
+ "grad_norm": 16.74787139892578,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 4.3475,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.8235294117647058,
463
+ "grad_norm": 15.532852172851562,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 4.1585,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.8366013071895425,
470
+ "grad_norm": 17.108413696289062,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 4.5843,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.8496732026143791,
477
+ "grad_norm": 19.03700065612793,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 4.5228,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.8627450980392157,
484
+ "grad_norm": 18.226158142089844,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 4.3519,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.8758169934640523,
491
+ "grad_norm": 17.857391357421875,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 4.3457,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.8888888888888888,
498
+ "grad_norm": 18.92527198791504,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 4.9343,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.9019607843137255,
505
+ "grad_norm": 21.539527893066406,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 4.5055,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.9150326797385621,
512
+ "grad_norm": 18.269908905029297,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 4.9476,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.9281045751633987,
519
+ "grad_norm": 23.49378204345703,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 5.0107,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.9411764705882353,
526
+ "grad_norm": 25.287702560424805,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 5.5347,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.954248366013072,
533
+ "grad_norm": 21.355749130249023,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 5.5062,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.9673202614379085,
540
+ "grad_norm": 25.698564529418945,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 6.4095,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.9803921568627451,
547
+ "grad_norm": 27.62260627746582,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 6.5146,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.9934640522875817,
554
+ "grad_norm": 28.68571662902832,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 6.5249,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.0065359477124183,
561
+ "grad_norm": 18.36124610900879,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 5.1321,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.0196078431372548,
568
+ "grad_norm": 6.567688941955566,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 2.5439,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.0326797385620916,
575
+ "grad_norm": 8.866209983825684,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 3.0478,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.0457516339869282,
582
+ "grad_norm": 13.741599082946777,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 3.9493,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.0588235294117647,
589
+ "grad_norm": 14.087339401245117,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 3.115,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.0718954248366013,
596
+ "grad_norm": 18.528522491455078,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 4.9909,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.0849673202614378,
603
+ "grad_norm": 17.856454849243164,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 4.0747,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.0980392156862746,
610
+ "grad_norm": 19.685808181762695,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 4.2566,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.1111111111111112,
617
+ "grad_norm": 18.7196102142334,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 4.0926,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.1241830065359477,
624
+ "grad_norm": 18.23643684387207,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 4.174,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.1372549019607843,
631
+ "grad_norm": 19.65151596069336,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 4.9878,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.1503267973856208,
638
+ "grad_norm": 20.80632781982422,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 4.5691,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.1633986928104576,
645
+ "grad_norm": 19.64034652709961,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 4.4191,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.1764705882352942,
652
+ "grad_norm": 20.260753631591797,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 4.5841,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.1895424836601307,
659
+ "grad_norm": 23.664470672607422,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 5.0259,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.2026143790849673,
666
+ "grad_norm": 23.812976837158203,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 5.6728,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.215686274509804,
673
+ "grad_norm": 29.3427791595459,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 7.135,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.2287581699346406,
680
+ "grad_norm": 26.24110221862793,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 6.2265,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.2418300653594772,
687
+ "grad_norm": 32.70111846923828,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 6.5576,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.2549019607843137,
694
+ "grad_norm": 19.617277145385742,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 4.6098,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.2679738562091503,
701
+ "grad_norm": 7.279455661773682,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 2.8293,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.2810457516339868,
708
+ "grad_norm": 9.745218276977539,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 3.1096,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.2941176470588236,
715
+ "grad_norm": 16.444101333618164,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 4.1709,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.3071895424836601,
722
+ "grad_norm": 16.58370018005371,
723
+ "learning_rate": 0.0,
724
+ "loss": 4.0866,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.3071895424836601,
729
+ "eval_loss": 4.5732855796813965,
730
+ "eval_runtime": 4.6201,
731
+ "eval_samples_per_second": 27.921,
732
+ "eval_steps_per_second": 7.143,
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": 3.931412223963955e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null