nttx commited on
Commit
e51fb0b
1 Parent(s): d650735

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 sha256:8939a97c8cf69dc2293d9a3d98e2bc84d4314da044570fc97fe63f160614912f
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac0b5f64801ac1fb37f005443129294ef4f50bb96eed9d73f5e838c647f2c67
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da651a30416b2e6cc03c5df9bd45af5ec982e95bc9ea699196a8a0e19925245f
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9578127d0c83a7681d403efee980859388cda9446bd5b9de0721e08bd47a6ea5
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b8d114b7aeb318d673e32c7968e1dc83c5095db1b19036ccb0e75a201d604f1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c65b889e0f8b6457fab65599625eb2180c2a11ed70e5358d050a058c98ebea40
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": 10.366990089416504,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.8791208791208791,
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": 492.002,
374
  "eval_steps_per_second": 123.0,
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": 5230244659200.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.366907119750977,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.7648351648351648,
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": 492.002,
374
  "eval_steps_per_second": 123.0,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.8967032967032967,
379
+ "grad_norm": 0.040907103568315506,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 10.3663,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.9142857142857143,
386
+ "grad_norm": 0.039741672575473785,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 10.3672,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.9318681318681319,
393
+ "grad_norm": 0.04772138595581055,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 10.372,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.9494505494505494,
400
+ "grad_norm": 0.05010518804192543,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 10.3745,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.967032967032967,
407
+ "grad_norm": 0.05096741393208504,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 10.3641,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.9846153846153847,
414
+ "grad_norm": 0.057732198387384415,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 10.3696,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 1.0087912087912088,
421
+ "grad_norm": 0.04998980835080147,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 16.071,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.0263736263736263,
428
+ "grad_norm": 0.036868538707494736,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 10.0527,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.043956043956044,
435
+ "grad_norm": 0.04606516286730766,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 10.5546,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.0615384615384615,
442
+ "grad_norm": 0.038774143904447556,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 9.9698,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.079120879120879,
449
+ "grad_norm": 0.03512636572122574,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 10.5632,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.0967032967032968,
456
+ "grad_norm": 0.04192524775862694,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 10.3435,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.1142857142857143,
463
+ "grad_norm": 0.04670780524611473,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 10.3459,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.1318681318681318,
470
+ "grad_norm": 0.04146342724561691,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 10.5141,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.1494505494505494,
477
+ "grad_norm": 0.04124102741479874,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 10.2299,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.167032967032967,
484
+ "grad_norm": 0.04173829033970833,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 10.39,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.1846153846153846,
491
+ "grad_norm": 0.04246349632740021,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 10.2809,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.2021978021978021,
498
+ "grad_norm": 0.040836114436388016,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 10.43,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.2197802197802199,
505
+ "grad_norm": 0.05367843434214592,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 10.3855,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.2373626373626374,
512
+ "grad_norm": 0.05292685702443123,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 10.9177,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.254945054945055,
519
+ "grad_norm": 0.033866383135318756,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 10.035,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.2725274725274724,
526
+ "grad_norm": 0.03704410046339035,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 9.9829,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.2901098901098902,
533
+ "grad_norm": 0.033814772963523865,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 10.4889,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.3076923076923077,
540
+ "grad_norm": 0.03551120683550835,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 10.3945,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.3252747252747252,
547
+ "grad_norm": 0.03838565945625305,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 10.5222,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.342857142857143,
554
+ "grad_norm": 0.03614303097128868,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 10.1321,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.3604395604395605,
561
+ "grad_norm": 0.0375247560441494,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 10.3162,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.378021978021978,
568
+ "grad_norm": 0.04089844599366188,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 10.7107,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.3956043956043955,
575
+ "grad_norm": 0.040124256163835526,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 10.0535,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.413186813186813,
582
+ "grad_norm": 0.03981036692857742,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 10.6221,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.4307692307692308,
589
+ "grad_norm": 0.04783904552459717,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 10.1964,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.4483516483516483,
596
+ "grad_norm": 0.044217731803655624,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 10.1716,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.465934065934066,
603
+ "grad_norm": 0.05215898156166077,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 10.7019,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.4835164835164836,
610
+ "grad_norm": 0.055684931576251984,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 10.6131,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.501098901098901,
617
+ "grad_norm": 0.041437309235334396,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 10.5622,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.5186813186813186,
624
+ "grad_norm": 0.0326310358941555,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 9.7426,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.5362637362637361,
631
+ "grad_norm": 0.041171569377183914,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 10.4579,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.5538461538461539,
638
+ "grad_norm": 0.03874897211790085,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 10.3767,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.5714285714285714,
645
+ "grad_norm": 0.03308764472603798,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 10.1858,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.5890109890109891,
652
+ "grad_norm": 0.0384545736014843,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 10.4582,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.6065934065934067,
659
+ "grad_norm": 0.043392788618803024,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 10.7153,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.6241758241758242,
666
+ "grad_norm": 0.03623654693365097,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 10.0836,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.6417582417582417,
673
+ "grad_norm": 0.0385335274040699,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 10.1258,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.6593406593406592,
680
+ "grad_norm": 0.04223882779479027,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 10.7705,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.676923076923077,
687
+ "grad_norm": 0.03968479484319687,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 10.4866,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.6945054945054945,
694
+ "grad_norm": 0.05118681862950325,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 10.0814,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.7120879120879122,
701
+ "grad_norm": 0.055021852254867554,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 10.5808,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.7296703296703297,
708
+ "grad_norm": 0.04585081338882446,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 10.5095,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.7472527472527473,
715
+ "grad_norm": 0.03800305351614952,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 10.2719,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.7648351648351648,
722
+ "grad_norm": 0.040729913860559464,
723
+ "learning_rate": 0.0,
724
+ "loss": 10.2925,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.7648351648351648,
729
+ "eval_loss": 10.366907119750977,
730
+ "eval_runtime": 0.1942,
731
+ "eval_samples_per_second": 494.268,
732
+ "eval_steps_per_second": 123.567,
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": 10460489318400.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null