Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.07490 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917664260096000 |
|---|---|
| author | Kim, Jisu Lee, Juhwan |
| author_facet | Kim, Jisu Lee, Juhwan |
| contents | The rapid advancement of Large Language Models (LLMs) has improved text understanding and generation but poses challenges in computational resources. This study proposes a curriculum learning-inspired, data-centric training strategy that begins with simpler tasks and progresses to more complex ones, using criteria such as prompt length, attention scores, and loss values to structure the training data. Experiments with Mistral-7B (Jiang et al., 2023) and Gemma-7B (Team et al., 2024) models demonstrate that curriculum learning slightly improves performance compared to traditional random data shuffling. Notably, we observed that sorting data based on our proposed attention criteria generally led to better performance. This approach offers a sustainable method to enhance LLM performance without increasing model size or dataset volume, addressing scalability challenges in LLM training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_07490 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learning Kim, Jisu Lee, Juhwan Computation and Language Artificial Intelligence The rapid advancement of Large Language Models (LLMs) has improved text understanding and generation but poses challenges in computational resources. This study proposes a curriculum learning-inspired, data-centric training strategy that begins with simpler tasks and progresses to more complex ones, using criteria such as prompt length, attention scores, and loss values to structure the training data. Experiments with Mistral-7B (Jiang et al., 2023) and Gemma-7B (Team et al., 2024) models demonstrate that curriculum learning slightly improves performance compared to traditional random data shuffling. Notably, we observed that sorting data based on our proposed attention criteria generally led to better performance. This approach offers a sustainable method to enhance LLM performance without increasing model size or dataset volume, addressing scalability challenges in LLM training. |
| title | Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2405.07490 |