nttx commited on
Commit
3c15ea4
·
verified ·
1 Parent(s): 7dd2ac7

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:feb418290d3bfe28b562cd1eb78617933cea391fa3f23eb5ab2a80367a5e4568
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bccbebbed2276fdd30f0dd0aaa072adb38d93ef5d9df6782585351512a7d04cf
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5661f6fad72f73714349ad9e31b58bf2b4c44f655bd7eda711cd10d3e9083af9
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60e5c2cb9d893f964e8d9a851c7bb1d4f2d5dde6d642daee907a4daca79a200b
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b75da9a0774f0ebe7076a1364b6d6166108fa4ab15ec33cdcf8c99ca2a211eeb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c929de6f1c0750de268457e384eaf5abfb27b128a402ca17a328a07b0c21fcb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d90116c540b4ff0066495fbccc9c914a568905fb44c6564f227952cc4231b00
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ad66011cfc1fc727a51190602a41adc332b48eeef62a5ee87c2ca9f9b90b2b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.15802142024040222,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.10570824524312897,
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": 12.341,
374
  "eval_steps_per_second": 3.101,
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": 1.88564197343232e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.15427330136299133,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.21141649048625794,
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": 12.341,
374
  "eval_steps_per_second": 3.101,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.10782241014799154,
379
+ "grad_norm": 0.9042031168937683,
380
+ "learning_rate": 2.3816778784387097e-05,
381
+ "loss": 0.1909,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.10993657505285412,
386
+ "grad_norm": 2.605374574661255,
387
+ "learning_rate": 2.3263454721781537e-05,
388
+ "loss": 0.1462,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.11205073995771671,
393
+ "grad_norm": 0.618105411529541,
394
+ "learning_rate": 2.2693489161088592e-05,
395
+ "loss": 0.2167,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.11416490486257928,
400
+ "grad_norm": 0.24392980337142944,
401
+ "learning_rate": 2.210802993709498e-05,
402
+ "loss": 0.1316,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.11627906976744186,
407
+ "grad_norm": 0.21554243564605713,
408
+ "learning_rate": 2.1508256086763372e-05,
409
+ "loss": 0.126,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.11839323467230443,
414
+ "grad_norm": 0.241543248295784,
415
+ "learning_rate": 2.0895375474808857e-05,
416
+ "loss": 0.1109,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.12050739957716702,
421
+ "grad_norm": 0.3184583783149719,
422
+ "learning_rate": 2.0270622361220143e-05,
423
+ "loss": 0.1138,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.1226215644820296,
428
+ "grad_norm": 0.32614850997924805,
429
+ "learning_rate": 1.963525491562421e-05,
430
+ "loss": 0.1389,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.12473572938689217,
435
+ "grad_norm": 0.3486217260360718,
436
+ "learning_rate": 1.8990552683500128e-05,
437
+ "loss": 0.139,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.12684989429175475,
442
+ "grad_norm": 0.3227207660675049,
443
+ "learning_rate": 1.8337814009344716e-05,
444
+ "loss": 0.1433,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.12896405919661733,
449
+ "grad_norm": 0.4387953579425812,
450
+ "learning_rate": 1.767835342197955e-05,
451
+ "loss": 0.1673,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.13107822410147993,
456
+ "grad_norm": 0.5242079496383667,
457
+ "learning_rate": 1.7013498987264832e-05,
458
+ "loss": 0.1236,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.1331923890063425,
463
+ "grad_norm": 0.4730517864227295,
464
+ "learning_rate": 1.6344589633551502e-05,
465
+ "loss": 0.148,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.13530655391120508,
470
+ "grad_norm": 0.7624608278274536,
471
+ "learning_rate": 1.5672972455257726e-05,
472
+ "loss": 0.1519,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.13742071881606766,
477
+ "grad_norm": 0.43941426277160645,
478
+ "learning_rate": 1.5e-05,
479
+ "loss": 0.1183,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.13953488372093023,
484
+ "grad_norm": 0.6278932094573975,
485
+ "learning_rate": 1.4327027544742281e-05,
486
+ "loss": 0.1535,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.1416490486257928,
491
+ "grad_norm": 0.5535889863967896,
492
+ "learning_rate": 1.36554103664485e-05,
493
+ "loss": 0.1329,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.14376321353065538,
498
+ "grad_norm": 0.6688005328178406,
499
+ "learning_rate": 1.2986501012735174e-05,
500
+ "loss": 0.157,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.14587737843551796,
505
+ "grad_norm": 0.40927010774612427,
506
+ "learning_rate": 1.2321646578020452e-05,
507
+ "loss": 0.1283,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.14799154334038056,
512
+ "grad_norm": 0.5657337307929993,
513
+ "learning_rate": 1.1662185990655285e-05,
514
+ "loss": 0.1415,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.15010570824524314,
519
+ "grad_norm": 0.909653902053833,
520
+ "learning_rate": 1.1009447316499875e-05,
521
+ "loss": 0.2031,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.1522198731501057,
526
+ "grad_norm": 0.7087647318840027,
527
+ "learning_rate": 1.036474508437579e-05,
528
+ "loss": 0.1479,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.1543340380549683,
533
+ "grad_norm": 0.8850060701370239,
534
+ "learning_rate": 9.729377638779859e-06,
535
+ "loss": 0.166,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.15644820295983086,
540
+ "grad_norm": 0.7543150782585144,
541
+ "learning_rate": 9.104624525191147e-06,
542
+ "loss": 0.1362,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.15856236786469344,
547
+ "grad_norm": 0.83201003074646,
548
+ "learning_rate": 8.491743913236629e-06,
549
+ "loss": 0.1328,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.160676532769556,
554
+ "grad_norm": 2.301429510116577,
555
+ "learning_rate": 7.89197006290502e-06,
556
+ "loss": 0.1032,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.16279069767441862,
561
+ "grad_norm": 0.9384440779685974,
562
+ "learning_rate": 7.30651083891141e-06,
563
+ "loss": 0.1566,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.1649048625792812,
568
+ "grad_norm": 1.3696162700653076,
569
+ "learning_rate": 6.736545278218464e-06,
570
+ "loss": 0.1467,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.16701902748414377,
575
+ "grad_norm": 3.9601619243621826,
576
+ "learning_rate": 6.1832212156129045e-06,
577
+ "loss": 0.3389,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.16913319238900634,
582
+ "grad_norm": 1.9955356121063232,
583
+ "learning_rate": 5.647652972118998e-06,
584
+ "loss": 0.1527,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.17124735729386892,
589
+ "grad_norm": 1.0902405977249146,
590
+ "learning_rate": 5.130919110904311e-06,
591
+ "loss": 0.1259,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1733615221987315,
596
+ "grad_norm": 1.0407441854476929,
597
+ "learning_rate": 4.6340602651970304e-06,
598
+ "loss": 0.1474,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.17547568710359407,
603
+ "grad_norm": 2.1278271675109863,
604
+ "learning_rate": 4.158077042589129e-06,
605
+ "loss": 0.1673,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.17758985200845667,
610
+ "grad_norm": 2.6037819385528564,
611
+ "learning_rate": 3.7039280099458373e-06,
612
+ "loss": 0.1636,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.17970401691331925,
617
+ "grad_norm": 1.4455296993255615,
618
+ "learning_rate": 3.272527762979553e-06,
619
+ "loss": 0.1374,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.18181818181818182,
624
+ "grad_norm": 0.9174126982688904,
625
+ "learning_rate": 2.86474508437579e-06,
626
+ "loss": 0.1216,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.1839323467230444,
631
+ "grad_norm": 1.9632937908172607,
632
+ "learning_rate": 2.4814011941804603e-06,
633
+ "loss": 0.1475,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.18604651162790697,
638
+ "grad_norm": 1.6227281093597412,
639
+ "learning_rate": 2.1232680959720085e-06,
640
+ "loss": 0.141,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.18816067653276955,
645
+ "grad_norm": 1.872657060623169,
646
+ "learning_rate": 1.79106702214893e-06,
647
+ "loss": 0.1461,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.19027484143763213,
652
+ "grad_norm": 1.4686189889907837,
653
+ "learning_rate": 1.4854669814637145e-06,
654
+ "loss": 0.1545,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.19238900634249473,
659
+ "grad_norm": 1.4979490041732788,
660
+ "learning_rate": 1.2070834117282414e-06,
661
+ "loss": 0.1281,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1945031712473573,
666
+ "grad_norm": 1.4667952060699463,
667
+ "learning_rate": 9.56476940403942e-07,
668
+ "loss": 0.1528,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.19661733615221988,
673
+ "grad_norm": 1.0837724208831787,
674
+ "learning_rate": 7.341522555726971e-07,
675
+ "loss": 0.144,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.19873150105708245,
680
+ "grad_norm": 1.2933568954467773,
681
+ "learning_rate": 5.405570895622014e-07,
682
+ "loss": 0.1902,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.20084566596194503,
687
+ "grad_norm": 3.0054140090942383,
688
+ "learning_rate": 3.760813172726457e-07,
689
+ "loss": 0.1994,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.2029598308668076,
694
+ "grad_norm": 2.414536714553833,
695
+ "learning_rate": 2.41056171020555e-07,
696
+ "loss": 0.1413,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.20507399577167018,
701
+ "grad_norm": 2.2516028881073,
702
+ "learning_rate": 1.357535734809795e-07,
703
+ "loss": 0.1668,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.20718816067653276,
708
+ "grad_norm": 1.4251919984817505,
709
+ "learning_rate": 6.038559007141397e-08,
710
+ "loss": 0.1955,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.20930232558139536,
715
+ "grad_norm": 1.7404764890670776,
716
+ "learning_rate": 1.510400188028116e-08,
717
+ "loss": 0.1756,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.21141649048625794,
722
+ "grad_norm": 0.9121055603027344,
723
+ "learning_rate": 0.0,
724
+ "loss": 0.1873,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.21141649048625794,
729
+ "eval_loss": 0.15427330136299133,
730
+ "eval_runtime": 16.1464,
731
+ "eval_samples_per_second": 12.325,
732
+ "eval_steps_per_second": 3.097,
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": 3.77128394686464e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null