nttx commited on
Commit
f837bac
1 Parent(s): 72594f9

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 sha256:5c969c484006c89a5cf20932f39326ab018ac0005ac16edf6957f6937fae77f5
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc8e899d779f09caf4f76dbfd0ef7eefaf758d787188edf5272f623ac84ed9c8
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d3682cdd156a72fc3f9c5c5cde99103a3b331eeb806d817eff2e4c9a2219aab
3
  size 90365754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6464ef6b0be4273696df02676b28a6daf846b622f7d4387376f80bd2c1e6d7f4
3
  size 90365754
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99acd6e02f1825cc0d849a9ee3b6a2e22a5777e7dea501eae9c029451a56b58a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207879ca5b423a359080126c222fbed6fdd13ca0f79b861bf94ba0cd4a874d3b
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": 1.2643074989318848,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.4429678848283499,
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": 45.836,
374
  "eval_steps_per_second": 11.58,
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": 9677225695641600.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1487233638763428,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.8859357696566998,
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": 45.836,
374
  "eval_steps_per_second": 11.58,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.45182724252491696,
379
+ "grad_norm": 3.724428176879883,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 1.7979,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.46068660022148394,
386
+ "grad_norm": 3.677011489868164,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 1.776,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.4695459579180509,
393
+ "grad_norm": 4.029702186584473,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 1.9899,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.47840531561461797,
400
+ "grad_norm": 5.193387031555176,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 2.527,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.48726467331118495,
407
+ "grad_norm": 6.274040222167969,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 3.3244,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.49612403100775193,
414
+ "grad_norm": 8.404130935668945,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 4.9856,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.5049833887043189,
421
+ "grad_norm": 1.3020391464233398,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 0.5332,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.5138427464008859,
428
+ "grad_norm": 1.1718058586120605,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 0.5553,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.5227021040974529,
435
+ "grad_norm": 1.183056354522705,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 0.5742,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.53156146179402,
442
+ "grad_norm": 1.2540595531463623,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 0.5917,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.540420819490587,
449
+ "grad_norm": 1.1747428178787231,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 0.639,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.5492801771871539,
456
+ "grad_norm": 1.4563751220703125,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 0.6741,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.5581395348837209,
463
+ "grad_norm": 1.4563407897949219,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 0.7447,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.5669988925802879,
470
+ "grad_norm": 1.3163275718688965,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 0.6955,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.5758582502768549,
477
+ "grad_norm": 1.5846550464630127,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 0.7429,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.584717607973422,
484
+ "grad_norm": 1.705263614654541,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 0.7714,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.593576965669989,
491
+ "grad_norm": 1.5806174278259277,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 0.8223,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.602436323366556,
498
+ "grad_norm": 1.8107914924621582,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 0.8763,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.6112956810631229,
505
+ "grad_norm": 1.9689290523529053,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 0.8702,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.6201550387596899,
512
+ "grad_norm": 2.174515962600708,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 0.9745,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.6290143964562569,
519
+ "grad_norm": 2.0214343070983887,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 0.9701,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.6378737541528239,
526
+ "grad_norm": 2.1900439262390137,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 1.0289,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.646733111849391,
533
+ "grad_norm": 2.4474709033966064,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 1.089,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.655592469545958,
540
+ "grad_norm": 2.823962688446045,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 1.1816,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.6644518272425249,
547
+ "grad_norm": 2.5962817668914795,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 1.1133,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.6733111849390919,
554
+ "grad_norm": 2.841041088104248,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 1.283,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.6821705426356589,
561
+ "grad_norm": 3.0042049884796143,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 1.3755,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.6910299003322259,
568
+ "grad_norm": 2.9517288208007812,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 1.3274,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.6998892580287929,
575
+ "grad_norm": 3.294313907623291,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 1.425,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.70874861572536,
582
+ "grad_norm": 3.9566781520843506,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 1.7255,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.717607973421927,
589
+ "grad_norm": 4.484854221343994,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 2.0507,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.7264673311184939,
596
+ "grad_norm": 5.30416202545166,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 2.4313,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.7353266888150609,
603
+ "grad_norm": 6.225465297698975,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 2.9252,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.7441860465116279,
610
+ "grad_norm": 8.09953498840332,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 4.476,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.7530454042081949,
617
+ "grad_norm": 0.983315646648407,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 0.4917,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.7619047619047619,
624
+ "grad_norm": 1.218385100364685,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 0.5298,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.770764119601329,
631
+ "grad_norm": 1.2609528303146362,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 0.619,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.7796234772978959,
638
+ "grad_norm": 1.2983731031417847,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 0.6307,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.7884828349944629,
645
+ "grad_norm": 1.3116830587387085,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 0.6177,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.7973421926910299,
652
+ "grad_norm": 1.4940251111984253,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 0.6654,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.8062015503875969,
659
+ "grad_norm": 1.5201992988586426,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 0.7048,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.8150609080841639,
666
+ "grad_norm": 1.5003371238708496,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 0.7234,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.8239202657807309,
673
+ "grad_norm": 1.7071876525878906,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 0.8071,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.832779623477298,
680
+ "grad_norm": 1.8066092729568481,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 0.8,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.8416389811738649,
687
+ "grad_norm": 1.8863574266433716,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 0.7962,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.8504983388704319,
694
+ "grad_norm": 1.6819432973861694,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 0.8041,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.8593576965669989,
701
+ "grad_norm": 1.8421244621276855,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 0.8698,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.8682170542635659,
708
+ "grad_norm": 1.914803385734558,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 0.9064,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.8770764119601329,
715
+ "grad_norm": 2.1939234733581543,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 0.9801,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.8859357696566998,
722
+ "grad_norm": 1.958722472190857,
723
+ "learning_rate": 0.0,
724
+ "loss": 0.9593,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.8859357696566998,
729
+ "eval_loss": 1.1487233638763428,
730
+ "eval_runtime": 4.1469,
731
+ "eval_samples_per_second": 45.817,
732
+ "eval_steps_per_second": 11.575,
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": 1.93544513912832e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null