Saved in:
Bibliographic Details
Main Authors: Caillaut, Gaëtan, Qader, Raheel, Nakhlé, Mariam, Liu, Jingshu, Barthélemy, Jean-Gabriel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.15051
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913513498214400
author Caillaut, Gaëtan
Qader, Raheel
Nakhlé, Mariam
Liu, Jingshu
Barthélemy, Jean-Gabriel
author_facet Caillaut, Gaëtan
Qader, Raheel
Nakhlé, Mariam
Liu, Jingshu
Barthélemy, Jean-Gabriel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15051
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scaling Laws of Decoder-Only Models on the Multilingual Machine Translation Task
Caillaut, Gaëtan
Qader, Raheel
Nakhlé, Mariam
Liu, Jingshu
Barthélemy, Jean-Gabriel
Computation and Language
Artificial Intelligence
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.
title Scaling Laws of Decoder-Only Models on the Multilingual Machine Translation Task
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2409.15051