Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Zheng Yuan, Hongyi Yuan, Chengpeng Li, Guanting Dong, Keming Lu, Chuanqi Tan, Chang Zhou, Jingren Zhou

Primary Area: representation learning for computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Mathematical Reasoning, Scaling Relationship, Large Language Model

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract:

Mathematical reasoning is a challenging task for large language models (LLMs), while the scaling relationship of it with respect to LLM capacity is under-explored.
In this paper, we investigate how the pre-training loss, supervised data amount, and augmented data amount influence the reasoning performances of a supervised LLM.
We find that pre-training loss is a better indicator of the model's performance than the model's parameter count.
We apply supervised fine-tuning (SFT) with different amounts of supervised data and empirically find a log-linear relation between data amount and model performance, and we find better models improve less with enlarged supervised datasets.
To augment more data samples for improving model performances without any human effort, we propose to apply Rejection sampling Fine-Tuning (RFT).
RFT uses supervised models to generate and collect correct reasoning paths as augmented fine-tuning datasets.
We find with augmented samples containing more distinct reasoning paths, RFT improves mathematical reasoning performance more for LLMs.
We also find RFT brings more improvement for less performant LLMs.
Furthermore, we combine rejection samples from multiple models which push LLaMA-7B to an accuracy of 49.3\% on GSM8K which outperforms the supervised fine-tuning (SFT) accuracy of 35.9\% significantly.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1254