面向预训练代码模型的高效微调：实验研究及其发展方向（英文版）

英文标题：Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond中文摘要：该研究通过分层预训练表示的实验研究发现了不同层数与源代码信息的关系，从而提出了 Telly 技术，通过层冻结来有效地微调预训练代码模型，从而降低了学习参数和时间成本。英文摘要：Recently, fine-tuning pre-trained code models such as CodeBERT on downstreamtasks has achieved great success in many software testing and analysis tasks.While effective and prevalent, fine-tuning the pre-trained parameters incurs alarge computational cost. In this paper, we conduct an extensive experimentalstu