nttx commited on
Commit
26f61fa
·
verified ·
1 Parent(s): 3b3594a

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 sha256:8fbc2e0e8c532b12d5ae650b860aefcac977a026f98d5a9b9b1cf5c5be586dfd
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3295d5976673808dc24412a5de970a12ab80bc3ec255d16ba914323ffdfbbc05
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:617b22e00f0a497b70b1e137fbc558a04fde83dfeaa0028a2e95c7eab0f50acc
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f15ab6e7f6095924d67fdd8c458002ee64af3b93e3b0bdfcdb987b2b11d3cd0
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a34422589ed8b4e08d8507d1a22598d0cd3ce93e9659881ad0b41146a6489cc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41b31be3551324932df2292a91940e599744f3599d34ee30fe8772305928cbeb
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": 2.710475206375122,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.38113387327298714,
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": 12.918,
374
  "eval_steps_per_second": 1.622,
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": 2.9750196755339674e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.6097841262817383,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.7622677465459743,
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": 12.918,
374
  "eval_steps_per_second": 1.622,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3887565507384469,
379
+ "grad_norm": 1.2314931154251099,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 2.6059,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.39637922820390664,
386
+ "grad_norm": 1.3346525430679321,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 2.7265,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.4040019056693664,
393
+ "grad_norm": 1.3276231288909912,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 2.7018,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.4116245831348261,
400
+ "grad_norm": 1.3935623168945312,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 2.7656,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.41924726060028583,
407
+ "grad_norm": 1.392889380455017,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 2.7419,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.4268699380657456,
414
+ "grad_norm": 1.4677642583847046,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 2.8227,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.43449261553120533,
421
+ "grad_norm": 1.4074047803878784,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 2.7652,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.4421152929966651,
428
+ "grad_norm": 1.4082292318344116,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 2.7916,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.4497379704621248,
435
+ "grad_norm": 1.5705230236053467,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 2.8949,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.4573606479275846,
442
+ "grad_norm": 1.4800447225570679,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 2.8763,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.4649833253930443,
449
+ "grad_norm": 1.7153626680374146,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 2.9525,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.47260600285850407,
456
+ "grad_norm": 1.6682062149047852,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 2.9583,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.4802286803239638,
463
+ "grad_norm": 2.1147046089172363,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 3.2925,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.4878513577894235,
470
+ "grad_norm": 2.6401166915893555,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 4.3026,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.49547403525488326,
477
+ "grad_norm": 0.7430612444877625,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 2.0217,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.5030967127203431,
484
+ "grad_norm": 0.7868032455444336,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 2.1813,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.5107193901858028,
491
+ "grad_norm": 0.8234112858772278,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 2.2301,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.5183420676512626,
498
+ "grad_norm": 0.8945828676223755,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 2.2984,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.5259647451167222,
505
+ "grad_norm": 0.8570656776428223,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 2.2342,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.533587422582182,
512
+ "grad_norm": 0.8565142154693604,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 2.3728,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.5412101000476417,
519
+ "grad_norm": 0.9122400879859924,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 2.3101,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.5488327775131014,
526
+ "grad_norm": 0.9057995676994324,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 2.3959,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.5564554549785612,
533
+ "grad_norm": 0.9446002244949341,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 2.3936,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.5640781324440209,
540
+ "grad_norm": 0.977627694606781,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 2.4138,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.5717008099094807,
547
+ "grad_norm": 0.9783718585968018,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 2.4278,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.5793234873749404,
554
+ "grad_norm": 0.9705466628074646,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 2.4498,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.5869461648404002,
561
+ "grad_norm": 1.0789556503295898,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 2.4888,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5945688423058599,
568
+ "grad_norm": 1.047377347946167,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 2.4992,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.6021915197713197,
575
+ "grad_norm": 1.069031000137329,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 2.5096,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.6098141972367794,
582
+ "grad_norm": 1.0925695896148682,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 2.5255,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.6174368747022392,
589
+ "grad_norm": 1.0890165567398071,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 2.5195,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.6250595521676989,
596
+ "grad_norm": 1.142870306968689,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 2.526,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.6326822296331587,
603
+ "grad_norm": 1.1425656080245972,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 2.5021,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.6403049070986184,
610
+ "grad_norm": 1.1594488620758057,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 2.6243,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.6479275845640782,
617
+ "grad_norm": 1.2081568241119385,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 2.6227,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.6555502620295379,
624
+ "grad_norm": 1.2804358005523682,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 2.6482,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.6631729394949977,
631
+ "grad_norm": 1.2887688875198364,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 2.5992,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.6707956169604573,
638
+ "grad_norm": 1.2514843940734863,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 2.735,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.6784182944259171,
645
+ "grad_norm": 1.3292714357376099,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 2.6533,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.6860409718913768,
652
+ "grad_norm": 1.38014554977417,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 2.7992,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.6936636493568366,
659
+ "grad_norm": 1.4328645467758179,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 2.764,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.7012863268222963,
666
+ "grad_norm": 1.6062235832214355,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 2.8302,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.708909004287756,
673
+ "grad_norm": 1.6477878093719482,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 2.925,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.7165316817532158,
680
+ "grad_norm": 1.810110330581665,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 2.922,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.7241543592186755,
687
+ "grad_norm": 2.1606154441833496,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 3.3003,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.7317770366841353,
694
+ "grad_norm": 2.8912160396575928,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 4.0696,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.739399714149595,
701
+ "grad_norm": 0.7114972472190857,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 2.0816,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.7470223916150548,
708
+ "grad_norm": 0.7526923418045044,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 2.15,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.7546450690805145,
715
+ "grad_norm": 0.7823670506477356,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 2.1743,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.7622677465459743,
722
+ "grad_norm": 0.8256052136421204,
723
+ "learning_rate": 0.0,
724
+ "loss": 2.2702,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.7622677465459743,
729
+ "eval_loss": 2.6097841262817383,
730
+ "eval_runtime": 68.4212,
731
+ "eval_samples_per_second": 12.92,
732
+ "eval_steps_per_second": 1.622,
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": 5.946329850225623e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null