Instruction Fine-Tuning: Does Prompt Loss Matter?

Mathew Huerta-Enochian, Seung Ko


Abstract
We present a novel study analyzing the effects of various prompt loss token weights (PLW) for supervised instruction fine-tuning (SIFT). While prompt-masking (PLW = 0) is common for SIFT, some fine-tuning APIs support fractional PLWs and suggest that using a small non-zero PLW can help stabilize learning when fine-tuning on short-completion data. However, there has never been a study confirming this claim, and OpenAI, a major cloud-based SIFT provider, recently removed this parameter from their fine-tuning API. We found that performance of models fine-tuned on short-completion data had a statistically-significant negative quadratic relationship with PLW. Using small values (0.01 − 0.5) of PLW produced better results on multiple-choice and short-generation benchmarks (outperforming models fine-tuned on long-completion data) while large values (≈ 1.0) of PLW produced better results on long-generation benchmarks. We explained this effect and verified its importance through additional experiments. This research serves as a warning to API providers about the importance of providing a PLW parameter for SIFT.
Anthology ID:
2024.emnlp-main.1267
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22771–22795
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1267
DOI:
Bibkey:
Cite (ACL):
Mathew Huerta-Enochian and Seung Ko. 2024. Instruction Fine-Tuning: Does Prompt Loss Matter?. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 22771–22795, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Instruction Fine-Tuning: Does Prompt Loss Matter? (Huerta-Enochian & Ko, EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1267.pdf