nttx commited on
Commit
034ff2b
·
verified ·
1 Parent(s): 2e2cbc1

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 sha256:3ce5c8e36a19794638ff679c7878d107ac27326a263bf2701fa1e8abdc21981a
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1140af35aec27a849f19d54c27aaa12ea7cd485f6036416ee9005264651fbb10
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2011c8f42a6d807a176eb8a303c7e2e5517fe34df91d77f27b67f4c7e401b42
3
  size 591203178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c6204629a9e364418ebf395ec8e4daeb80c6d1ae7b677c937b93753f7d4cde
3
  size 591203178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51f5b0db9afa3b4f69b3f42d6c81265d315cc75a13c6202709f049c4f618e32c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:426321a1ab650d99edde00799bd7428166ac760641c0b960093cadf470a7a25b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
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": 1.6973111629486084,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.4784688995215311,
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": 30.68,
374
  "eval_steps_per_second": 3.987,
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": 1.387938126495744e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6871801614761353,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.9569377990430622,
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": 30.68,
374
  "eval_steps_per_second": 3.987,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.4880382775119617,
379
+ "grad_norm": 1.9222286939620972,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 2.2571,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.49760765550239233,
386
+ "grad_norm": 4.275127410888672,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 2.4938,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.507177033492823,
393
+ "grad_norm": 0.2680644392967224,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 1.3738,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.5167464114832536,
400
+ "grad_norm": 0.3094908893108368,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 1.6464,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.5263157894736842,
407
+ "grad_norm": 0.31784677505493164,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 1.4569,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.5358851674641149,
414
+ "grad_norm": 0.34948986768722534,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 1.3778,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.5454545454545454,
421
+ "grad_norm": 0.34939584136009216,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 1.4479,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.5550239234449761,
428
+ "grad_norm": 0.36129850149154663,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 1.4858,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.5645933014354066,
435
+ "grad_norm": 0.38175034523010254,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 1.5229,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.5741626794258373,
442
+ "grad_norm": 0.39641234278678894,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 1.5009,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.583732057416268,
449
+ "grad_norm": 0.40825703740119934,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 1.4181,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.5933014354066986,
456
+ "grad_norm": 0.43495655059814453,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 1.4476,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.6028708133971292,
463
+ "grad_norm": 0.4451518952846527,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 1.616,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.6124401913875598,
470
+ "grad_norm": 0.47959691286087036,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 1.5528,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.6220095693779905,
477
+ "grad_norm": 0.48145580291748047,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 1.5756,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.631578947368421,
484
+ "grad_norm": 0.506266176700592,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 1.608,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.6411483253588517,
491
+ "grad_norm": 0.5399481058120728,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 1.686,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.6507177033492823,
498
+ "grad_norm": 0.5846008062362671,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 1.8601,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.6602870813397129,
505
+ "grad_norm": 0.5942398309707642,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 1.6992,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.6698564593301436,
512
+ "grad_norm": 0.6084458231925964,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 1.7457,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.6794258373205742,
519
+ "grad_norm": 0.719818651676178,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 1.7357,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.6889952153110048,
526
+ "grad_norm": 0.7451322674751282,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 1.9377,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.6985645933014354,
533
+ "grad_norm": 0.8885253667831421,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 1.9484,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.7081339712918661,
540
+ "grad_norm": 1.0710029602050781,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 1.9866,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.7177033492822966,
547
+ "grad_norm": 1.0909761190414429,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 2.0548,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.7272727272727273,
554
+ "grad_norm": 1.6213032007217407,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 2.2782,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.7368421052631579,
561
+ "grad_norm": 2.127164125442505,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 2.0789,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.7464114832535885,
568
+ "grad_norm": 3.6304738521575928,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 2.0903,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.7559808612440191,
575
+ "grad_norm": 0.2699255645275116,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 1.4164,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.7655502392344498,
582
+ "grad_norm": 0.29987215995788574,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 1.2793,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.7751196172248804,
589
+ "grad_norm": 0.3141963481903076,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 1.4328,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.784688995215311,
596
+ "grad_norm": 0.336625874042511,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 1.4148,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.7942583732057417,
603
+ "grad_norm": 0.368731290102005,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 1.517,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.8038277511961722,
610
+ "grad_norm": 0.37500929832458496,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 1.5432,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.8133971291866029,
617
+ "grad_norm": 0.38130730390548706,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 1.5176,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.8229665071770335,
624
+ "grad_norm": 0.41141316294670105,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 1.4348,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.8325358851674641,
631
+ "grad_norm": 0.41603273153305054,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 1.5163,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.8421052631578947,
638
+ "grad_norm": 0.44736191630363464,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 1.4274,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.8516746411483254,
645
+ "grad_norm": 0.43399325013160706,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 1.5425,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.861244019138756,
652
+ "grad_norm": 0.47178566455841064,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 1.6099,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.8708133971291866,
659
+ "grad_norm": 0.5100260972976685,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 1.6085,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.8803827751196173,
666
+ "grad_norm": 0.5522103905677795,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 1.7014,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.8899521531100478,
673
+ "grad_norm": 0.5604200959205627,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 1.5571,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.8995215311004785,
680
+ "grad_norm": 0.608319103717804,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 1.7045,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.9090909090909091,
687
+ "grad_norm": 0.645991861820221,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 1.6996,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.9186602870813397,
694
+ "grad_norm": 0.7313124537467957,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 1.8184,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.9282296650717703,
701
+ "grad_norm": 0.7927725315093994,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 1.9343,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.937799043062201,
708
+ "grad_norm": 0.9807630181312561,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 1.8933,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.9473684210526315,
715
+ "grad_norm": 0.920979917049408,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 1.8406,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.9569377990430622,
722
+ "grad_norm": 1.0186470746994019,
723
+ "learning_rate": 0.0,
724
+ "loss": 1.9207,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.9569377990430622,
729
+ "eval_loss": 1.6871801614761353,
730
+ "eval_runtime": 6.0137,
731
+ "eval_samples_per_second": 29.433,
732
+ "eval_steps_per_second": 3.825,
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": 2.78948348952576e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null