bbytxt commited on
Commit
86beb99
·
verified ·
1 Parent(s): afa5d20

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 sha256:8b8e6a975d1e19e5e12375912a8f8459325edc41c9aa7a8faa11035a4e9a00ee
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e6ff9a9f06b774d7cc19d978de48377a8515392e09d25814406d1c56f3e8d83
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e772ae2f2331b53f30ff7a4529c92e7e921f4ea5c9f20a201bab26e1073b868f
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2322ea3ab3c96cee3bb96d42983d198b630264ab61f6b73c1d8e3bce52f938a3
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6416e941627e960d72beee9f61a2d80046b139c06e35614d0d925a80298f1054
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6439d2fc98be0e03bf0cef9e6fe9a93a82f69cabcccef40582dfb2f8fcff8249
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": 5.869631767272949,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.2296211251435132,
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": 8.819,
374
  "eval_steps_per_second": 2.211,
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": 1.26956599246848e+17,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 5.363029956817627,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.4592422502870264,
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": 8.819,
374
  "eval_steps_per_second": 2.211,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.23421354764638347,
379
+ "grad_norm": 26.808902740478516,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 47.6216,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.23880597014925373,
386
+ "grad_norm": 26.181222915649414,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 45.5904,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.24339839265212398,
393
+ "grad_norm": 24.47733497619629,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 44.2045,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.24799081515499427,
400
+ "grad_norm": 27.00351905822754,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 46.1095,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.2525832376578645,
407
+ "grad_norm": 25.429462432861328,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 45.1595,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.2571756601607348,
414
+ "grad_norm": 27.074621200561523,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 46.2527,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2617680826636051,
421
+ "grad_norm": 28.328506469726562,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 44.0381,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2663605051664753,
428
+ "grad_norm": 27.414587020874023,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 44.427,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.2709529276693456,
435
+ "grad_norm": 27.592138290405273,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 45.2812,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2755453501722158,
442
+ "grad_norm": 26.86080551147461,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 44.7676,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.2801377726750861,
449
+ "grad_norm": 27.480749130249023,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 44.6694,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.2847301951779564,
456
+ "grad_norm": 27.362363815307617,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 44.9002,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2893226176808266,
463
+ "grad_norm": 28.51040267944336,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 45.6995,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.2939150401836969,
470
+ "grad_norm": 29.854806900024414,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 46.2855,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.29850746268656714,
477
+ "grad_norm": 26.63895606994629,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 42.679,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3030998851894374,
484
+ "grad_norm": 26.914358139038086,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 43.8516,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3076923076923077,
491
+ "grad_norm": 25.817581176757812,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 43.8709,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.31228473019517794,
498
+ "grad_norm": 28.417312622070312,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 44.2127,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.3168771526980482,
505
+ "grad_norm": 27.355661392211914,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 44.3729,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.3214695752009185,
512
+ "grad_norm": 27.43345832824707,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 43.7944,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.32606199770378874,
519
+ "grad_norm": 29.279691696166992,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 44.0171,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.330654420206659,
526
+ "grad_norm": 27.410545349121094,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 43.095,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.33524684270952926,
533
+ "grad_norm": 29.67399024963379,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 45.0487,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.33983926521239954,
540
+ "grad_norm": 30.19101333618164,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 44.676,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.34443168771526983,
547
+ "grad_norm": 27.907899856567383,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 43.2354,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.34902411021814006,
554
+ "grad_norm": 28.882566452026367,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 43.4213,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.35361653272101035,
561
+ "grad_norm": 30.828548431396484,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 45.3045,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3582089552238806,
568
+ "grad_norm": 29.114967346191406,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 43.4449,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.36280137772675086,
575
+ "grad_norm": 29.279699325561523,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 42.7139,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.36739380022962115,
582
+ "grad_norm": 29.65679931640625,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 43.0745,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.3719862227324914,
589
+ "grad_norm": 29.90504264831543,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 44.1824,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.37657864523536166,
596
+ "grad_norm": 30.5111083984375,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 44.0602,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.3811710677382319,
603
+ "grad_norm": 28.713394165039062,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 43.8557,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.3857634902411022,
610
+ "grad_norm": 28.297386169433594,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 42.6137,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.39035591274397247,
617
+ "grad_norm": 28.568580627441406,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 43.4909,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.3949483352468427,
624
+ "grad_norm": 29.288326263427734,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 42.8888,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.399540757749713,
631
+ "grad_norm": 28.4726619720459,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 43.0369,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.4041331802525832,
638
+ "grad_norm": 29.91521644592285,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 41.9991,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.4087256027554535,
645
+ "grad_norm": 30.32415008544922,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 42.7265,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.4133180252583238,
652
+ "grad_norm": 30.52402114868164,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 43.7341,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.417910447761194,
659
+ "grad_norm": 29.194290161132812,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 44.0457,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.4225028702640643,
666
+ "grad_norm": 30.200559616088867,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 44.1988,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.42709529276693453,
673
+ "grad_norm": 30.448226928710938,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 43.5972,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.4316877152698048,
680
+ "grad_norm": 31.17372703552246,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 45.4866,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.4362801377726751,
687
+ "grad_norm": 30.126811981201172,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 43.0588,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.44087256027554533,
694
+ "grad_norm": 31.021615982055664,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 43.662,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.4454649827784156,
701
+ "grad_norm": 31.53817367553711,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 45.2449,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.4500574052812859,
708
+ "grad_norm": 33.527503967285156,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 45.0926,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.45464982778415614,
715
+ "grad_norm": 30.129289627075195,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 44.7906,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.4592422502870264,
722
+ "grad_norm": 31.717391967773438,
723
+ "learning_rate": 0.0,
724
+ "loss": 46.6076,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.4592422502870264,
729
+ "eval_loss": 5.363029956817627,
730
+ "eval_runtime": 41.6293,
731
+ "eval_samples_per_second": 8.816,
732
+ "eval_steps_per_second": 2.21,
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": 2.53913198493696e+17,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null