nttx commited on
Commit
09bc45f
·
verified ·
1 Parent(s): 98ddaf6

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:f41d648d53e4e3a004320167d618c8fc3d29c4e83dc513d8ee9a0bee862bbe05
3
  size 100697728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e4d76d3aec679cbdbb115cf5f66ad0fa5e865ad425027f824b44e3318265e4
3
  size 100697728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b9721936755af58ffc7eb46fcea71efa7f42410a631d432235d699ec98e9790
3
  size 201541754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d00ca038ecec690b4d2814f8c93b5fc27bb4703caf232883dcd89ce3e014f2
3
  size 201541754
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af5fe02eb619cd1f919f8c2b57554e2e5ef50a4b9aefb79971d73bac6d175722
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b9e632ae3d38c765d8e1bc9e4876e7b7c0e531ecee7f8e29d5240fd12c41f5
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": 2.0947766304016113,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.3629764065335753,
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": 13.621,
374
  "eval_steps_per_second": 3.405,
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": 3.748656219527578e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7874782085418701,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.7259528130671506,
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": 13.621,
374
  "eval_steps_per_second": 3.405,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3702359346642468,
379
+ "grad_norm": 27.389202117919922,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 17.0387,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.37749546279491836,
386
+ "grad_norm": 27.716867446899414,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 18.4511,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.38475499092558985,
393
+ "grad_norm": 29.619388580322266,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 17.47,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.39201451905626133,
400
+ "grad_norm": 31.908462524414062,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 18.4963,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.3992740471869328,
407
+ "grad_norm": 36.90242004394531,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 18.7586,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.40653357531760437,
414
+ "grad_norm": 37.4904670715332,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 19.8906,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.41379310344827586,
421
+ "grad_norm": 41.82046127319336,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 17.6513,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.42105263157894735,
428
+ "grad_norm": 36.44230651855469,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 19.9673,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.4283121597096189,
435
+ "grad_norm": 43.02734375,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 17.6983,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.4355716878402904,
442
+ "grad_norm": 37.226016998291016,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 18.3587,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.44283121597096187,
449
+ "grad_norm": 42.38252639770508,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 20.4464,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.4500907441016334,
456
+ "grad_norm": 41.940921783447266,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 17.4957,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.4573502722323049,
463
+ "grad_norm": 46.13038635253906,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 19.7075,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.4646098003629764,
470
+ "grad_norm": 44.92179489135742,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 21.3875,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.47186932849364793,
477
+ "grad_norm": 44.2301139831543,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 21.2556,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.4791288566243194,
484
+ "grad_norm": 46.1361198425293,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 21.0062,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4863883847549909,
491
+ "grad_norm": 43.51995849609375,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 22.3918,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.49364791288566245,
498
+ "grad_norm": 51.73350524902344,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 21.1049,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.5009074410163339,
505
+ "grad_norm": 3.369800329208374,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 12.9291,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.5081669691470054,
512
+ "grad_norm": 3.5551090240478516,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 11.0554,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.515426497277677,
519
+ "grad_norm": 3.8818531036376953,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 11.6997,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.5226860254083484,
526
+ "grad_norm": 4.654056072235107,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 11.2339,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.52994555353902,
533
+ "grad_norm": 6.711645126342773,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 12.0514,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.5372050816696915,
540
+ "grad_norm": 8.446243286132812,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 11.2013,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.5444646098003629,
547
+ "grad_norm": 10.63932991027832,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 12.1054,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.5517241379310345,
554
+ "grad_norm": 12.101577758789062,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 10.123,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.558983666061706,
561
+ "grad_norm": 11.52901840209961,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 10.222,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5662431941923775,
568
+ "grad_norm": 15.732647895812988,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 12.0639,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.573502722323049,
575
+ "grad_norm": 16.677928924560547,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 11.0684,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.5807622504537205,
582
+ "grad_norm": 18.44302749633789,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 12.4404,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.588021778584392,
589
+ "grad_norm": 19.314517974853516,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 12.3501,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.5952813067150635,
596
+ "grad_norm": 20.21866798400879,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 14.039,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.6025408348457351,
603
+ "grad_norm": 22.13374137878418,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 14.3035,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.6098003629764065,
610
+ "grad_norm": 25.172279357910156,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 15.6511,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.617059891107078,
617
+ "grad_norm": 26.78219223022461,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 13.3722,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.6243194192377496,
624
+ "grad_norm": 32.689048767089844,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 17.8477,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.631578947368421,
631
+ "grad_norm": 30.472444534301758,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 15.272,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.6388384754990926,
638
+ "grad_norm": 34.43206024169922,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 16.787,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.6460980036297641,
645
+ "grad_norm": 32.31828689575195,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 16.542,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.6533575317604355,
652
+ "grad_norm": 32.913631439208984,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 17.1815,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.6606170598911071,
659
+ "grad_norm": 34.70173263549805,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 14.765,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.6678765880217786,
666
+ "grad_norm": 35.73689270019531,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 18.3037,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.6751361161524501,
673
+ "grad_norm": 37.242130279541016,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 15.7251,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.6823956442831216,
680
+ "grad_norm": 40.024654388427734,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 17.6311,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.6896551724137931,
687
+ "grad_norm": 36.8790168762207,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 15.6619,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.6969147005444646,
694
+ "grad_norm": 43.34751510620117,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 17.6543,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.7041742286751361,
701
+ "grad_norm": 39.92681884765625,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 17.7566,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.7114337568058077,
708
+ "grad_norm": 43.69413375854492,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 18.9589,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.7186932849364791,
715
+ "grad_norm": 42.85605239868164,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 17.9384,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.7259528130671506,
722
+ "grad_norm": 49.98722839355469,
723
+ "learning_rate": 0.0,
724
+ "loss": 19.4431,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.7259528130671506,
729
+ "eval_loss": 1.7874782085418701,
730
+ "eval_runtime": 17.0271,
731
+ "eval_samples_per_second": 13.625,
732
+ "eval_steps_per_second": 3.406,
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": 7.460470608887808e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null