bbytxt commited on
Commit
1a2018a
·
verified ·
1 Parent(s): 46b140b

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 sha256:8765c8ffce2b138facbd64b99490f37e337a33fa7f340a4914d80089c4ed7a92
3
  size 200068512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcab7be35d83f382c63b5b22f8d11c4a73380674be6b6103c99f110a1fe26970
3
  size 200068512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:200f223188ce87124498ed28424f1b5ae0d2ff4bd251e043a3c11a13fc8c0e17
3
  size 400361770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab2ba2076d1e533206f3c9d680f837222729ef30a5ba7f75e6cf640b4d4911b2
3
  size 400361770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38ece10712c5b6c3d44f563e926820822b655e68e1bc2d1dd4df6150d1b268ac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f6934adc0da90164ad951437872c7506a968dadbca79677c43e66525efc2bae
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": 1.0674021244049072,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.013531341970839958,
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": 10.705,
374
  "eval_steps_per_second": 2.676,
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": 7.688115974465126e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0187755823135376,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.027062683941679915,
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": 10.705,
374
  "eval_steps_per_second": 2.676,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.013801968810256757,
379
+ "grad_norm": 0.5559863448143005,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 0.7655,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.014072595649673557,
386
+ "grad_norm": 0.678560197353363,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 0.803,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.014343222489090356,
393
+ "grad_norm": 0.6894142627716064,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 0.8397,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.014613849328507155,
400
+ "grad_norm": 0.7735072374343872,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 0.8653,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.014884476167923953,
407
+ "grad_norm": 0.7143723964691162,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 0.8341,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.015155103007340753,
414
+ "grad_norm": 0.7415910959243774,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 0.8152,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.015425729846757552,
421
+ "grad_norm": 0.8374602794647217,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 0.8897,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01569635668617435,
428
+ "grad_norm": 0.8707734942436218,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 0.9219,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01596698352559115,
435
+ "grad_norm": 0.815484881401062,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 0.8614,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.01623761036500795,
442
+ "grad_norm": 0.7766671776771545,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 0.8877,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.01650823720442475,
449
+ "grad_norm": 0.8103740215301514,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 0.9241,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.01677886404384155,
456
+ "grad_norm": 0.9171229004859924,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 0.9715,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.017049490883258345,
463
+ "grad_norm": 0.823610246181488,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 0.9178,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.017320117722675145,
470
+ "grad_norm": 0.8297237157821655,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 0.9384,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.017590744562091944,
477
+ "grad_norm": 0.8308224678039551,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 0.91,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.017861371401508744,
484
+ "grad_norm": 0.8265281319618225,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 0.8696,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.018131998240925543,
491
+ "grad_norm": 0.8544564843177795,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 0.9598,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.018402625080342343,
498
+ "grad_norm": 0.9564810991287231,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 0.9123,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.018673251919759142,
505
+ "grad_norm": 0.9041321873664856,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 0.9157,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01894387875917594,
512
+ "grad_norm": 0.9885373711585999,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 0.9612,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.01921450559859274,
519
+ "grad_norm": 0.9514999389648438,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 0.969,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.01948513243800954,
526
+ "grad_norm": 0.9459763169288635,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 0.9962,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.01975575927742634,
533
+ "grad_norm": 0.9458332657814026,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 0.9358,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.02002638611684314,
540
+ "grad_norm": 0.9821689128875732,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 1.0361,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.020297012956259936,
547
+ "grad_norm": 0.951698362827301,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 1.0104,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.020567639795676735,
554
+ "grad_norm": 1.0073827505111694,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 0.9367,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.020838266635093534,
561
+ "grad_norm": 1.1683809757232666,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 1.0249,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.021108893474510334,
568
+ "grad_norm": 1.0686205625534058,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 1.0685,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.021379520313927133,
575
+ "grad_norm": 0.9999198317527771,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 0.9795,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.021650147153343933,
582
+ "grad_norm": 1.199865460395813,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 1.1232,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.021920773992760732,
589
+ "grad_norm": 1.196691870689392,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 1.0305,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.022191400832177532,
596
+ "grad_norm": 1.3286807537078857,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 1.0715,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.02246202767159433,
603
+ "grad_norm": 1.3111743927001953,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 1.053,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.02273265451101113,
610
+ "grad_norm": 1.197509527206421,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 1.1335,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.02300328135042793,
617
+ "grad_norm": 1.2589415311813354,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 1.0684,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.023273908189844726,
624
+ "grad_norm": 1.5249485969543457,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 1.1123,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.023544535029261526,
631
+ "grad_norm": 1.3184010982513428,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 1.0367,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.023815161868678325,
638
+ "grad_norm": 1.3574773073196411,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 1.1233,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.024085788708095125,
645
+ "grad_norm": 1.364808440208435,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 1.0077,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.024356415547511924,
652
+ "grad_norm": 1.426081657409668,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 1.0295,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.024627042386928723,
659
+ "grad_norm": 1.6618572473526,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 0.9982,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.024897669226345523,
666
+ "grad_norm": 1.6236708164215088,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 1.058,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.025168296065762322,
673
+ "grad_norm": 1.7425477504730225,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 1.0255,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.025438922905179122,
680
+ "grad_norm": 1.9277325868606567,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 1.2349,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.02570954974459592,
687
+ "grad_norm": 1.8921107053756714,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 1.1955,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.02598017658401272,
694
+ "grad_norm": 2.8468291759490967,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 1.4125,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.02625080342342952,
701
+ "grad_norm": 3.475755453109741,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 1.3095,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.026521430262846316,
708
+ "grad_norm": 4.424863815307617,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 1.3732,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.026792057102263116,
715
+ "grad_norm": 5.109591960906982,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 1.2857,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.027062683941679915,
722
+ "grad_norm": 6.888213157653809,
723
+ "learning_rate": 0.0,
724
+ "loss": 1.4212,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.027062683941679915,
729
+ "eval_loss": 1.0187755823135376,
730
+ "eval_runtime": 580.4087,
731
+ "eval_samples_per_second": 10.723,
732
+ "eval_steps_per_second": 2.681,
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": 1.539540430796882e+17,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null