prxy5606 commited on
Commit
2c4e396
·
verified ·
1 Parent(s): b82db66

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 sha256:9bb71dec7e9a81bebfe9a5bc616ddd9fb59e1985d222dbe4e163678f5084518f
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21412951cd72e6fd19b3444890979058085dbd36e25bc541914ee500e18256b2
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b2969221e019e9dfa08267bb771ddae370ac416de2fc689522fe7f1c823cf3b
3
  size 278249554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b75179ebc04cea309056b57e383f0872b70aa175f89efeb6eec80734c30e015
3
  size 278249554
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68f63439457281969b27d6e236ec293dbab9291037f1a0c477508be4fb9aec52
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c0ed57d004d68592d1591b7e8adc3d02bdce29c643e16159cede5771dba770
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5335737b4b4d079cdec612fe6ee661ed4d29f9e0e55eb4eada44a9677240228
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.9957740902900696,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.08598452278589853,
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": 37.543,
374
  "eval_steps_per_second": 18.772,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3571817360916480.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9143250584602356,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.17196904557179707,
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": 37.543,
374
  "eval_steps_per_second": 18.772,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.08770421324161651,
379
+ "grad_norm": 0.15448810160160065,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 0.6494,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.08942390369733448,
386
+ "grad_norm": 0.19541579484939575,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 0.6789,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.09114359415305245,
393
+ "grad_norm": 0.22956673800945282,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 0.6399,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.09286328460877043,
400
+ "grad_norm": 0.20343832671642303,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 0.7056,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.09458297506448839,
407
+ "grad_norm": 0.20558185875415802,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 0.695,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.09630266552020636,
414
+ "grad_norm": 0.20323364436626434,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 0.7068,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.09802235597592433,
421
+ "grad_norm": 0.18025411665439606,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 0.6984,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0997420464316423,
428
+ "grad_norm": 0.15938173234462738,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 0.6744,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.10146173688736028,
435
+ "grad_norm": 0.1582622081041336,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 0.7612,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.10318142734307825,
442
+ "grad_norm": 0.12570132315158844,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 0.7241,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.10490111779879621,
449
+ "grad_norm": 0.10931485146284103,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 0.7559,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.10662080825451418,
456
+ "grad_norm": 0.09841756522655487,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 0.6782,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.10834049871023216,
463
+ "grad_norm": 0.09882379323244095,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 0.7601,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.11006018916595013,
470
+ "grad_norm": 0.10225917398929596,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 0.7911,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.1117798796216681,
477
+ "grad_norm": 0.10474953055381775,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 0.7669,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.11349957007738606,
484
+ "grad_norm": 0.10357484966516495,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 0.7644,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.11521926053310404,
491
+ "grad_norm": 0.11238912492990494,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 0.8878,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.11693895098882201,
498
+ "grad_norm": 0.11020366847515106,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 0.8643,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.11865864144453998,
505
+ "grad_norm": 0.10074474662542343,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 0.8067,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.12037833190025796,
512
+ "grad_norm": 0.09557520598173141,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 0.7716,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.12209802235597593,
519
+ "grad_norm": 0.10227945446968079,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 0.923,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.12381771281169389,
526
+ "grad_norm": 0.10992958396673203,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 0.8756,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.12553740326741186,
533
+ "grad_norm": 0.10675280541181564,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 0.7982,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.12725709372312985,
540
+ "grad_norm": 0.1144600510597229,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 0.7169,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.1289767841788478,
547
+ "grad_norm": 0.10181998461484909,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 0.736,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.13069647463456577,
554
+ "grad_norm": 0.10681930184364319,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 0.8836,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.13241616509028376,
561
+ "grad_norm": 0.11621927469968796,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 0.8581,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.13413585554600171,
568
+ "grad_norm": 0.09889838099479675,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 0.7897,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.1358555460017197,
575
+ "grad_norm": 0.09543070942163467,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 0.8192,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.13757523645743766,
582
+ "grad_norm": 0.11200384050607681,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 0.7359,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.13929492691315562,
589
+ "grad_norm": 0.10140563547611237,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 0.824,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1410146173688736,
596
+ "grad_norm": 0.102725550532341,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 0.8458,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.14273430782459157,
603
+ "grad_norm": 0.10617943853139877,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 0.7649,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.14445399828030955,
610
+ "grad_norm": 0.10800634324550629,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 0.7318,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.1461736887360275,
617
+ "grad_norm": 0.1077365055680275,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 0.8679,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.14789337919174547,
624
+ "grad_norm": 0.11147390305995941,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 0.8635,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.14961306964746346,
631
+ "grad_norm": 0.13498784601688385,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 0.9565,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.15133276010318142,
638
+ "grad_norm": 0.1289157271385193,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 1.041,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.1530524505588994,
645
+ "grad_norm": 0.1310902088880539,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 0.8777,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.15477214101461736,
652
+ "grad_norm": 0.160873144865036,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 1.1091,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.15649183147033535,
659
+ "grad_norm": 0.15653099119663239,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 1.1321,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1582115219260533,
666
+ "grad_norm": 0.19784240424633026,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 1.1846,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.15993121238177127,
673
+ "grad_norm": 0.19561642408370972,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 1.3051,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.16165090283748926,
680
+ "grad_norm": 0.19523312151432037,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 1.3682,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.16337059329320722,
687
+ "grad_norm": 0.21068979799747467,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 1.2489,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.1650902837489252,
694
+ "grad_norm": 0.20077933371067047,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 1.3355,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.16680997420464316,
701
+ "grad_norm": 0.21723942458629608,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 1.6464,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.16852966466036112,
708
+ "grad_norm": 0.28459852933883667,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 1.7727,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.1702493551160791,
715
+ "grad_norm": 0.37411239743232727,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 2.0809,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.17196904557179707,
722
+ "grad_norm": 0.6213313937187195,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 2.2677,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.17196904557179707,
729
+ "eval_loss": 0.9143250584602356,
730
+ "eval_runtime": 26.1292,
731
+ "eval_samples_per_second": 37.506,
732
+ "eval_steps_per_second": 18.753,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 7109290324131840.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null