Metraipolis › archive › dc_a60bbb310132

Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss — arXiv:2608.28308

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28308
License (as archived)
CC0-1.0
Archived
2026-10-17T10:48:14.676Z
SHA-256 of the archived text
a0548072e9adc5871dddd06cb2894a94be00ada39d7c2d0becf602c73209318a
Stable URL of this page
https://metraipolis.com/documento/dc_a60bbb310132

How to cite

Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss — arXiv:2608.28308 — arXiv (en), https://arxiv.org/abs/2608.28308 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a60bbb310132 (Metraipolis archive dc_a60bbb310132, sha256 a0548072e9adc5871dddd06cb2894a94be00ada39d7c2d0becf602c73209318a)
BibTeX
@misc{dca60bbb310132,
  title = {Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss — arXiv:2608.28308},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28308},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a60bbb310132; sha256 a0548072e9adc5871dddd06cb2894a94be00ada39d7c2d0becf602c73209318a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28308. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the scaling behavior of learning rate and batch size in pretraining dense large language models on English-prevalent corpora. Beyond scaling jointly optimal learning rates and batch sizes, we investigate their marginal evolution with model capacity and data scale and develop a model that captures these relationships. As we employ a Warmup-Stable-Decay learning rate schedule, we further investigate the gains from learning rate annealing over a broad range of hyperparameters settings, models and data budgets, and whether the optimal learning rate and batch size transfer between the stable and decay phases. Finally, we characterize the dependence of loss on model capacity and dataset size, evaluating recently proposed scaling forms that explicitly model their interaction. We find these approaches particularly effective at capturing both undertraining and overtraining regimes across our experiments. This study establishes a first baseline and scaling procedure for the development of future OpenEuroLLM models. We open-source the complete collection of pretraining runs used in this study.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28308 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T10:33:42.519Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).