bbytxt commited on
Commit
87dc635
·
verified ·
1 Parent(s): 5159f01

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:fe70479fc33479e3710f0bb6d4dc554884081919729a525cbceb345ee6f3f22e
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b459da528d8c7ec740082a94277636aeef431f939ab4081a3d61ff3454f0799b
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54652e285f19d1188006ca4cd407da63e0639d1551f50c110f22ae20780d845d
3
  size 2003253602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a50e34bc0fc4a60bf70430024bdbb1da10d13a05a759be5ac3bb7ac8bfc472
3
  size 2003253602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c174e09731008fd5a78836d5339a613ef26ec0b3e629701660cfeef857fb1b7e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71b322d2a977bd8686468c311cc4bd7836f6ffed0afe65279e2a55b151bf16ac
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": 3.7869925498962402,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.009237021984112323,
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": 9.015,
374
  "eval_steps_per_second": 1.127,
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": 1.2944637324951552e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.204241991043091,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.018474043968224645,
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": 9.015,
374
  "eval_steps_per_second": 1.127,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.009421762423794569,
379
+ "grad_norm": 10.553465843200684,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 12.3464,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.009606502863476815,
386
+ "grad_norm": 9.21324348449707,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 10.9542,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.009791243303159062,
393
+ "grad_norm": 9.639703750610352,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 12.9959,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.009975983742841308,
400
+ "grad_norm": 10.31529426574707,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 13.4257,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.010160724182523555,
407
+ "grad_norm": 10.842665672302246,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 13.3985,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.010345464622205801,
414
+ "grad_norm": 15.412654876708984,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 12.5864,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.010530205061888048,
421
+ "grad_norm": 12.196069717407227,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 12.9136,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.010714945501570294,
428
+ "grad_norm": 10.424600601196289,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 11.7622,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01089968594125254,
435
+ "grad_norm": 9.363513946533203,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 13.2165,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.011084426380934787,
442
+ "grad_norm": 9.543737411499023,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 13.0826,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.011269166820617033,
449
+ "grad_norm": 10.09285831451416,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 12.0315,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.01145390726029928,
456
+ "grad_norm": 12.571577072143555,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 13.6267,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.011638647699981526,
463
+ "grad_norm": 11.248260498046875,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 13.978,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.011823388139663773,
470
+ "grad_norm": 11.726507186889648,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 13.5491,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.012008128579346019,
477
+ "grad_norm": 10.686549186706543,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 11.1128,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.012192869019028265,
484
+ "grad_norm": 11.239615440368652,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 13.6764,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.012377609458710512,
491
+ "grad_norm": 11.39352798461914,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 11.6324,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.012562349898392758,
498
+ "grad_norm": 12.298237800598145,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 12.4812,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.012747090338075005,
505
+ "grad_norm": 11.034797668457031,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 12.8913,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.012931830777757251,
512
+ "grad_norm": 10.423636436462402,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 10.9085,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.013116571217439497,
519
+ "grad_norm": 9.65755558013916,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 10.8279,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.013301311657121744,
526
+ "grad_norm": 11.453106880187988,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 12.9038,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.01348605209680399,
533
+ "grad_norm": 9.885631561279297,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 11.4746,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.013670792536486237,
540
+ "grad_norm": 11.553996086120605,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 11.6637,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.013855532976168483,
547
+ "grad_norm": 12.240235328674316,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 11.4566,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.01404027341585073,
554
+ "grad_norm": 10.19922924041748,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 11.0213,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.014225013855532976,
561
+ "grad_norm": 13.437042236328125,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 11.7195,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.014409754295215222,
568
+ "grad_norm": 10.909409523010254,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 10.9973,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.014594494734897469,
575
+ "grad_norm": 11.503260612487793,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 12.1749,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.014779235174579715,
582
+ "grad_norm": 10.706235885620117,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 12.0294,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.014963975614261962,
589
+ "grad_norm": 12.727118492126465,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 10.4982,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.015148716053944208,
596
+ "grad_norm": 12.55098819732666,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 13.1707,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.015333456493626454,
603
+ "grad_norm": 11.987310409545898,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 13.0754,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.015518196933308701,
610
+ "grad_norm": 10.642148971557617,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 14.0267,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.015702937372990947,
617
+ "grad_norm": 10.866153717041016,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 12.7693,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.015887677812673195,
624
+ "grad_norm": 12.30977725982666,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 13.8829,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.01607241825235544,
631
+ "grad_norm": 13.433856964111328,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 14.4559,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.01625715869203769,
638
+ "grad_norm": 13.631572723388672,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 12.8569,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.016441899131719933,
645
+ "grad_norm": 11.031132698059082,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 15.3341,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.01662663957140218,
652
+ "grad_norm": 15.343162536621094,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 13.857,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.016811380011084426,
659
+ "grad_norm": 12.620141983032227,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 14.4599,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.016996120450766674,
666
+ "grad_norm": 13.098137855529785,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 13.8406,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.01718086089044892,
673
+ "grad_norm": 13.165412902832031,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 13.6391,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.017365601330131167,
680
+ "grad_norm": 14.275860786437988,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 16.2704,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.01755034176981341,
687
+ "grad_norm": 15.78359317779541,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 20.0274,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.01773508220949566,
694
+ "grad_norm": 16.431692123413086,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 17.84,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.017919822649177904,
701
+ "grad_norm": 16.38827896118164,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 16.5615,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.018104563088860152,
708
+ "grad_norm": 34.411861419677734,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 22.2296,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.018289303528542397,
715
+ "grad_norm": 18.320810317993164,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 19.7425,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.018474043968224645,
722
+ "grad_norm": 30.78592872619629,
723
+ "learning_rate": 0.0,
724
+ "loss": 21.2385,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.018474043968224645,
729
+ "eval_loss": 3.204241991043091,
730
+ "eval_runtime": 1011.1857,
731
+ "eval_samples_per_second": 9.016,
732
+ "eval_steps_per_second": 1.127,
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": 2.5889274649903104e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null