0x1202 commited on
Commit
183012f
·
verified ·
1 Parent(s): 150827b

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 sha256:697d162fa2dbe32097fb5b80d3847f2ea26a478491fd8368a542ea905b293250
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12544515ccd7d317af38345a7943b500761ef9e7214296d471ae9f8c8f58a122
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27acbf30ecc16678f201b1b72b4bc4791656be678bd58c2e1a085153248ffc00
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f0c1daccf22b58f4a83e254562ad68fae8724ad207344d1d50cc88d0055654
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:498c17de409a3b9deb8302be29a53fc9e16b2c8ca43f274792b3a5966771b400
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:184a0e99461028aa661e839c7448c1fd95e3c978211b4ff9fc646517dc2ed9ce
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": 0.5612907409667969,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0648508430609598,
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": 7.345,
374
  "eval_steps_per_second": 1.853,
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": 1.66313582395392e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.10878434032201767,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.1297016861219196,
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": 7.345,
374
  "eval_steps_per_second": 1.853,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.06614785992217899,
379
+ "grad_norm": 20.423954010009766,
380
+ "learning_rate": 2.3816778784387097e-05,
381
+ "loss": 2.997,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.06744487678339818,
386
+ "grad_norm": 17.79172134399414,
387
+ "learning_rate": 2.3263454721781537e-05,
388
+ "loss": 1.577,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.06874189364461739,
393
+ "grad_norm": 6.911210060119629,
394
+ "learning_rate": 2.2693489161088592e-05,
395
+ "loss": 0.398,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.07003891050583658,
400
+ "grad_norm": 12.149227142333984,
401
+ "learning_rate": 2.210802993709498e-05,
402
+ "loss": 0.9617,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.07133592736705577,
407
+ "grad_norm": 8.559869766235352,
408
+ "learning_rate": 2.1508256086763372e-05,
409
+ "loss": 0.432,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.07263294422827497,
414
+ "grad_norm": 5.802802562713623,
415
+ "learning_rate": 2.0895375474808857e-05,
416
+ "loss": 0.3059,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.07392996108949416,
421
+ "grad_norm": 5.68005895614624,
422
+ "learning_rate": 2.0270622361220143e-05,
423
+ "loss": 0.2853,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.07522697795071336,
428
+ "grad_norm": 2.1309173107147217,
429
+ "learning_rate": 1.963525491562421e-05,
430
+ "loss": 0.1154,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.07652399481193256,
435
+ "grad_norm": 12.48730182647705,
436
+ "learning_rate": 1.8990552683500128e-05,
437
+ "loss": 0.3949,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.07782101167315175,
442
+ "grad_norm": 13.918665885925293,
443
+ "learning_rate": 1.8337814009344716e-05,
444
+ "loss": 0.5255,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.07911802853437094,
449
+ "grad_norm": 10.23596477508545,
450
+ "learning_rate": 1.767835342197955e-05,
451
+ "loss": 0.4977,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.08041504539559015,
456
+ "grad_norm": 6.709722518920898,
457
+ "learning_rate": 1.7013498987264832e-05,
458
+ "loss": 0.1514,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.08171206225680934,
463
+ "grad_norm": 5.081240177154541,
464
+ "learning_rate": 1.6344589633551502e-05,
465
+ "loss": 0.165,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.08300907911802853,
470
+ "grad_norm": 26.20868492126465,
471
+ "learning_rate": 1.5672972455257726e-05,
472
+ "loss": 1.1272,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.08430609597924774,
477
+ "grad_norm": 22.001665115356445,
478
+ "learning_rate": 1.5e-05,
479
+ "loss": 0.71,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.08560311284046693,
484
+ "grad_norm": 8.501405715942383,
485
+ "learning_rate": 1.4327027544742281e-05,
486
+ "loss": 0.2905,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.08690012970168612,
491
+ "grad_norm": 7.549007892608643,
492
+ "learning_rate": 1.36554103664485e-05,
493
+ "loss": 0.2497,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.08819714656290532,
498
+ "grad_norm": 16.637163162231445,
499
+ "learning_rate": 1.2986501012735174e-05,
500
+ "loss": 0.3425,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.08949416342412451,
505
+ "grad_norm": 45.87193298339844,
506
+ "learning_rate": 1.2321646578020452e-05,
507
+ "loss": 0.4744,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0907911802853437,
512
+ "grad_norm": 11.191590309143066,
513
+ "learning_rate": 1.1662185990655285e-05,
514
+ "loss": 0.3808,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.09208819714656291,
519
+ "grad_norm": 11.546527862548828,
520
+ "learning_rate": 1.1009447316499875e-05,
521
+ "loss": 0.5787,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.0933852140077821,
526
+ "grad_norm": 4.363774299621582,
527
+ "learning_rate": 1.036474508437579e-05,
528
+ "loss": 0.0979,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0946822308690013,
533
+ "grad_norm": 27.667964935302734,
534
+ "learning_rate": 9.729377638779859e-06,
535
+ "loss": 0.1371,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.0959792477302205,
540
+ "grad_norm": 6.752371788024902,
541
+ "learning_rate": 9.104624525191147e-06,
542
+ "loss": 0.1615,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.09727626459143969,
547
+ "grad_norm": 5.200261116027832,
548
+ "learning_rate": 8.491743913236629e-06,
549
+ "loss": 0.1498,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.09857328145265888,
554
+ "grad_norm": 11.683087348937988,
555
+ "learning_rate": 7.89197006290502e-06,
556
+ "loss": 0.1882,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.09987029831387809,
561
+ "grad_norm": 10.970105171203613,
562
+ "learning_rate": 7.30651083891141e-06,
563
+ "loss": 0.3211,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.10116731517509728,
568
+ "grad_norm": 9.882152557373047,
569
+ "learning_rate": 6.736545278218464e-06,
570
+ "loss": 0.2548,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.10246433203631647,
575
+ "grad_norm": 7.567006587982178,
576
+ "learning_rate": 6.1832212156129045e-06,
577
+ "loss": 0.2546,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.10376134889753567,
582
+ "grad_norm": 8.493035316467285,
583
+ "learning_rate": 5.647652972118998e-06,
584
+ "loss": 0.2932,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.10505836575875487,
589
+ "grad_norm": 5.506453990936279,
590
+ "learning_rate": 5.130919110904311e-06,
591
+ "loss": 0.1486,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.10635538261997406,
596
+ "grad_norm": 0.8174970149993896,
597
+ "learning_rate": 4.6340602651970304e-06,
598
+ "loss": 0.017,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.10765239948119326,
603
+ "grad_norm": 3.514220714569092,
604
+ "learning_rate": 4.158077042589129e-06,
605
+ "loss": 0.0581,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.10894941634241245,
610
+ "grad_norm": 0.8819956183433533,
611
+ "learning_rate": 3.7039280099458373e-06,
612
+ "loss": 0.0219,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.11024643320363164,
617
+ "grad_norm": 17.65021514892578,
618
+ "learning_rate": 3.272527762979553e-06,
619
+ "loss": 1.1424,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.11154345006485085,
624
+ "grad_norm": 2.7677478790283203,
625
+ "learning_rate": 2.86474508437579e-06,
626
+ "loss": 0.0682,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.11284046692607004,
631
+ "grad_norm": 9.2994966506958,
632
+ "learning_rate": 2.4814011941804603e-06,
633
+ "loss": 0.3074,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.11413748378728923,
638
+ "grad_norm": 5.88765811920166,
639
+ "learning_rate": 2.1232680959720085e-06,
640
+ "loss": 0.2075,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.11543450064850844,
645
+ "grad_norm": 8.574594497680664,
646
+ "learning_rate": 1.79106702214893e-06,
647
+ "loss": 0.247,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.11673151750972763,
652
+ "grad_norm": 3.277462959289551,
653
+ "learning_rate": 1.4854669814637145e-06,
654
+ "loss": 0.0624,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.11802853437094682,
659
+ "grad_norm": 12.124244689941406,
660
+ "learning_rate": 1.2070834117282414e-06,
661
+ "loss": 0.3679,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.11932555123216602,
666
+ "grad_norm": 2.1732170581817627,
667
+ "learning_rate": 9.56476940403942e-07,
668
+ "loss": 0.0485,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.12062256809338522,
673
+ "grad_norm": 4.28770112991333,
674
+ "learning_rate": 7.341522555726971e-07,
675
+ "loss": 0.1238,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.1219195849546044,
680
+ "grad_norm": 2.6389272212982178,
681
+ "learning_rate": 5.405570895622014e-07,
682
+ "loss": 0.0633,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.12321660181582361,
687
+ "grad_norm": 7.191143989562988,
688
+ "learning_rate": 3.760813172726457e-07,
689
+ "loss": 0.1797,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.1245136186770428,
694
+ "grad_norm": 10.877296447753906,
695
+ "learning_rate": 2.41056171020555e-07,
696
+ "loss": 0.2109,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.125810635538262,
701
+ "grad_norm": 21.885887145996094,
702
+ "learning_rate": 1.357535734809795e-07,
703
+ "loss": 0.8667,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.12710765239948119,
708
+ "grad_norm": 1.5145925283432007,
709
+ "learning_rate": 6.038559007141397e-08,
710
+ "loss": 0.0464,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.12840466926070038,
715
+ "grad_norm": 22.95406723022461,
716
+ "learning_rate": 1.510400188028116e-08,
717
+ "loss": 0.2276,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.1297016861219196,
722
+ "grad_norm": 10.279451370239258,
723
+ "learning_rate": 0.0,
724
+ "loss": 0.1799,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.1297016861219196,
729
+ "eval_loss": 0.10878434032201767,
730
+ "eval_runtime": 44.3192,
731
+ "eval_samples_per_second": 7.333,
732
+ "eval_steps_per_second": 1.85,
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": 3.32627164790784e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null