Crystal: Illuminating LLM Abilities on Language and Code

Tianhua Tao, Junbo Li, Bowen Tan, Hongyi Wang, William Marshall, Bhargav M Kanakiya, Joel Hestness, Natalia Vassilieva, Zhiqiang Shen, Eric P. Xing, Zhengzhong Liu

Research Area: LMs on diverse modalities and novel applications

Keywords: LM Pretraining, Language and Code, Transparency and Reproducibility, Multi-stage Pretraining, Open Science

TL;DR: The paper presents **Crystal**, a Large Language Model pretrained on 1.4T tokens that excels in both natural language and coding, featuring a multi-phase pretraining approach and openly sharing all resources to advance research.

Abstract: Large Language Models (LLMs) specializing in code generation (which are also often referred to as code LLMs), e.g., StarCoder and Code Llama, play increasingly critical roles in various software development scenarios. It is also crucial for code LLMs to possess both code generation and natural language abilities for many specific applications, such as code snippet retrieval using natural language or code explanations. The intricate interaction between acquiring language and coding skills complicates the development of strong code LLMs. Furthermore, there is a lack of thorough prior studies on the LLM pretraining strategy that mixes code and natural language. In this work, we propose a pretraining strategy to enhance the integration of natural language and coding capabilities within a single LLM. Specifically, it includes two phases of training with appropriately adjusted code/language ratio. The resulting model, CRYSTAL, demonstrates remarkable capabilities in both domains. Specifically, it has natural language and coding performance comparable to that of Llama 2 and Code Llama, respectively. CRYSTAL exhibits better data efficiency, using 1.4 trillion tokens compared to the more than 2 trillion tokens used by Llama 2 and Code Llama. We verify our pretraining strategy by analyzing the training process and observe consistent improvements in most benchmarks. We also adopted a typical application adaption phase with a code-centric data mixture, only to find out that it did not lead to enhanced performance or training efficiency, underlining the importance of a carefully designed data recipe. To foster research within the community, we commit to open-sourcing every detail of the pretraining, including our training datasets, code, loggings and 136 checkpoints throughout the training.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 1005