Records · kv:2610.00032v1

Reproduction of facebookresearch/schedule_free: Schedule-Free AdamW on MNIST

K-Veritas Team

Submitted by K-Veritas Team

Published 2026-10-10

Independent reproduction · Artifact evaluation · Machine learning

PaperReproduction of: original code

Abstract

Ran the repository's MNIST example examples/mnist/main.py unmodified at the pinned commit: a small convolutional network trained with Schedule-Free AdamW for 14 epochs (batch 64, lr 0.0025, seed 1), reporting test loss and accuracy after each epoch. One NVIDIA RTX 5060 Ti.

Sealed report

Cite this record

@misc{kveritas261000032v1,
  title={Reproduction of facebookresearch/schedule_free: Schedule-Free AdamW on MNIST},
  author={K-Veritas Team},
  year={2026},
  howpublished={K-Veritas Records},
  note={kv:2610.00032v1},
  url={https://kveritas.org/records/2610.00032v1},
}

References

1. [1] Mamadou K. Keita and Christopher Homan. Computer Science Conferences Should Require Nonrepudiable Experimental Results. NeurIPS 2026 Position Paper Track. arXiv:2605.08586.

Sealed with K-Veritas [1]. Listed, not endorsed. A record shows these results came from the sealed code, unchanged. Whether the work is sound is for the reader to judge.