Nexspear commited on
Commit
420fc07
·
verified ·
1 Parent(s): 78b04cb

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 sha256:4ec27592997c3dc571ae8552c2ff24cfaf81c3bf6ad5b361aabc22131a3f3ed9
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d612c0997bc22e6fcf98b99cfa6238296f13c9f95c1a81f2a1c6b2ce0786d2
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9638207528f9e4e868b0b4bebad0e8a43fa309fac408760e52a403d55305607f
3
  size 79968772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e750bf5be48258f546e038f0163ea693a472e9b5918db1367ea6cdc7e0c5120
3
  size 79968772
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4bffd8813d350fde8708c80ee2ea12b53b6639429972e4ed16deac898a04e31
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5de4a339021b72a3e9bfb340573f3317818a3b68eef13cde099dd4afcb9288
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d027de694a0a716b41fffb32866ba8b6570b1c754bda578c49c1f60b997cbc46
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc864cceb365e111779b7aa13efa5984edec637b413f1c931e43a1b11314c08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9951374530792236,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.4149377593360996,
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": 28.443,
374
  "eval_steps_per_second": 7.146,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.98682972520448e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3937488794326782,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.8298755186721992,
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": 28.443,
374
  "eval_steps_per_second": 7.146,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.42323651452282157,
379
+ "grad_norm": 5.736331462860107,
380
+ "learning_rate": 9.66709978038292e-05,
381
+ "loss": 2.2465,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.4315352697095436,
386
+ "grad_norm": 5.308639049530029,
387
+ "learning_rate": 9.650856666246693e-05,
388
+ "loss": 2.1472,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.43983402489626555,
393
+ "grad_norm": 4.070306301116943,
394
+ "learning_rate": 9.634240975516209e-05,
395
+ "loss": 1.5106,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.44813278008298757,
400
+ "grad_norm": 4.719001293182373,
401
+ "learning_rate": 9.617254039261834e-05,
402
+ "loss": 1.5839,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.45643153526970953,
407
+ "grad_norm": 8.284409523010254,
408
+ "learning_rate": 9.599897218294122e-05,
409
+ "loss": 1.9048,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.46473029045643155,
414
+ "grad_norm": 5.499932765960693,
415
+ "learning_rate": 9.582171903054816e-05,
416
+ "loss": 2.0164,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.4730290456431535,
421
+ "grad_norm": 4.232677936553955,
422
+ "learning_rate": 9.564079513505455e-05,
423
+ "loss": 1.6968,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.48132780082987553,
428
+ "grad_norm": 6.6102776527404785,
429
+ "learning_rate": 9.54562149901362e-05,
430
+ "loss": 2.1707,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.4896265560165975,
435
+ "grad_norm": 5.499170303344727,
436
+ "learning_rate": 9.526799338236827e-05,
437
+ "loss": 2.1749,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.4979253112033195,
442
+ "grad_norm": 6.410165309906006,
443
+ "learning_rate": 9.507614539004082e-05,
444
+ "loss": 2.0269,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.5062240663900415,
449
+ "grad_norm": 4.395339488983154,
450
+ "learning_rate": 9.48806863819507e-05,
451
+ "loss": 1.5799,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.5145228215767634,
456
+ "grad_norm": 5.214993953704834,
457
+ "learning_rate": 9.468163201617062e-05,
458
+ "loss": 1.4865,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.5228215767634855,
463
+ "grad_norm": 7.040699005126953,
464
+ "learning_rate": 9.447899823879456e-05,
465
+ "loss": 2.0153,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.5311203319502075,
470
+ "grad_norm": 5.472765922546387,
471
+ "learning_rate": 9.42728012826605e-05,
472
+ "loss": 1.9123,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.5394190871369294,
477
+ "grad_norm": 5.13813591003418,
478
+ "learning_rate": 9.406305766604995e-05,
479
+ "loss": 1.8829,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.5477178423236515,
484
+ "grad_norm": 5.717247486114502,
485
+ "learning_rate": 9.384978419136468e-05,
486
+ "loss": 2.0948,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.5560165975103735,
491
+ "grad_norm": 5.990386962890625,
492
+ "learning_rate": 9.363299794378073e-05,
493
+ "loss": 1.8932,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.5643153526970954,
498
+ "grad_norm": 7.660478591918945,
499
+ "learning_rate": 9.341271628987968e-05,
500
+ "loss": 2.3816,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.5726141078838174,
505
+ "grad_norm": 4.8774027824401855,
506
+ "learning_rate": 9.318895687625751e-05,
507
+ "loss": 1.6324,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.5809128630705395,
512
+ "grad_norm": 5.0475568771362305,
513
+ "learning_rate": 9.296173762811085e-05,
514
+ "loss": 1.5918,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.5892116182572614,
519
+ "grad_norm": 4.739609718322754,
520
+ "learning_rate": 9.273107674780102e-05,
521
+ "loss": 1.3994,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.5975103734439834,
526
+ "grad_norm": 6.396079063415527,
527
+ "learning_rate": 9.249699271339593e-05,
528
+ "loss": 1.8884,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.6058091286307054,
533
+ "grad_norm": 6.702268600463867,
534
+ "learning_rate": 9.225950427718975e-05,
535
+ "loss": 2.0607,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.6141078838174274,
540
+ "grad_norm": 4.683436393737793,
541
+ "learning_rate": 9.201863046420065e-05,
542
+ "loss": 1.458,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.6224066390041494,
547
+ "grad_norm": 5.798123359680176,
548
+ "learning_rate": 9.177439057064683e-05,
549
+ "loss": 1.9928,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.6307053941908713,
554
+ "grad_norm": 6.20752477645874,
555
+ "learning_rate": 9.152680416240059e-05,
556
+ "loss": 2.0453,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.6390041493775933,
561
+ "grad_norm": 4.803196430206299,
562
+ "learning_rate": 9.1275891073421e-05,
563
+ "loss": 1.6836,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.6473029045643154,
568
+ "grad_norm": 5.217916011810303,
569
+ "learning_rate": 9.102167140416503e-05,
570
+ "loss": 1.5624,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.6556016597510373,
575
+ "grad_norm": 5.689030170440674,
576
+ "learning_rate": 9.076416551997721e-05,
577
+ "loss": 1.2365,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.6639004149377593,
582
+ "grad_norm": 5.20029878616333,
583
+ "learning_rate": 9.050339404945833e-05,
584
+ "loss": 1.5095,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.6721991701244814,
589
+ "grad_norm": 7.432442665100098,
590
+ "learning_rate": 9.023937788281278e-05,
591
+ "loss": 2.1264,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.6804979253112033,
596
+ "grad_norm": 5.681693077087402,
597
+ "learning_rate": 8.997213817017507e-05,
598
+ "loss": 1.5059,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.6887966804979253,
603
+ "grad_norm": 6.367238521575928,
604
+ "learning_rate": 8.970169631991556e-05,
605
+ "loss": 1.5183,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.6970954356846473,
610
+ "grad_norm": 7.021786212921143,
611
+ "learning_rate": 8.942807399692543e-05,
612
+ "loss": 1.8657,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.7053941908713693,
617
+ "grad_norm": 6.1124587059021,
618
+ "learning_rate": 8.915129312088112e-05,
619
+ "loss": 1.7342,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.7136929460580913,
624
+ "grad_norm": 6.746445655822754,
625
+ "learning_rate": 8.88713758644883e-05,
626
+ "loss": 1.7254,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.7219917012448133,
631
+ "grad_norm": 5.889866828918457,
632
+ "learning_rate": 8.858834465170576e-05,
633
+ "loss": 1.6482,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.7302904564315352,
638
+ "grad_norm": 6.273972511291504,
639
+ "learning_rate": 8.83022221559489e-05,
640
+ "loss": 1.5594,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.7385892116182573,
645
+ "grad_norm": 8.849343299865723,
646
+ "learning_rate": 8.801303129827352e-05,
647
+ "loss": 1.4801,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.7468879668049793,
652
+ "grad_norm": 6.7875566482543945,
653
+ "learning_rate": 8.772079524553951e-05,
654
+ "loss": 1.6455,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.7551867219917012,
659
+ "grad_norm": 5.853145599365234,
660
+ "learning_rate": 8.742553740855506e-05,
661
+ "loss": 1.3349,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.7634854771784232,
666
+ "grad_norm": 7.308794021606445,
667
+ "learning_rate": 8.712728144020118e-05,
668
+ "loss": 1.8087,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.7717842323651453,
673
+ "grad_norm": 7.031892776489258,
674
+ "learning_rate": 8.682605123353685e-05,
675
+ "loss": 1.3419,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.7800829875518672,
680
+ "grad_norm": 6.652479648590088,
681
+ "learning_rate": 8.652187091988517e-05,
682
+ "loss": 1.645,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.7883817427385892,
687
+ "grad_norm": 8.24259090423584,
688
+ "learning_rate": 8.621476486689992e-05,
689
+ "loss": 1.6243,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.7966804979253111,
694
+ "grad_norm": 5.5381975173950195,
695
+ "learning_rate": 8.59047576766137e-05,
696
+ "loss": 1.282,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.8049792531120332,
701
+ "grad_norm": 6.3423309326171875,
702
+ "learning_rate": 8.559187418346703e-05,
703
+ "loss": 1.3701,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.8132780082987552,
708
+ "grad_norm": 6.963042736053467,
709
+ "learning_rate": 8.527613945231885e-05,
710
+ "loss": 1.1813,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.8215767634854771,
715
+ "grad_norm": 8.486031532287598,
716
+ "learning_rate": 8.495757877643858e-05,
717
+ "loss": 1.5802,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.8298755186721992,
722
+ "grad_norm": 8.076821327209473,
723
+ "learning_rate": 8.463621767547998e-05,
724
+ "loss": 1.6718,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.8298755186721992,
729
+ "eval_loss": 1.3937488794326782,
730
+ "eval_runtime": 7.2083,
731
+ "eval_samples_per_second": 28.162,
732
+ "eval_steps_per_second": 7.075,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.97365945040896e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null