Recent studies have showcased remarkable capabilities of decoder-only models in many NLP tasks, including translation. Yet, the machine translation field has been largely dominated by encoder-decoder models based on the Transformer architecture. As a consequence, scaling laws of encoder-decoder models for neural machine translation have already been well studied, but decoder-only models have received less attention. This work explores the scaling laws of decoder-only models on the multilingual and multidomain translation task. We trained a collection of six decoder-only models, ranging from 70M to 7B parameters, on a sentence-level, multilingual and multidomain dataset. We conducted a series of experiments showing that the loss of decoder-only models can be estimated using a scaling law similar to the one discovered for large language models, but we also show that this scaling law has difficulties to generalize to too large models or to a different data distribution. We also study different scaling methods and show that scaling the depth and the width of a model lead to similar test loss improvements, but with different impact on the model's efficiency.
@article{arxiv.2409.15051,
title = {Scaling Laws of Decoder-Only Models on the Multilingual Machine Translation Task},
author = {Gaëtan Caillaut and Raheel Qader and Mariam Nakhlé and Jingshu Liu and Jean-Gabriel Barthélemy},
journal= {arXiv preprint arXiv:2409.15051},
year = {2024}
}