Parameter Efficient Instruction Tuning: An Empirical Study
Instruction tuning has become an important step for finetuning pretrained language models to better follow human instructions and generalize on various tasks. Nowadays, pretrained language models become increasingly larger, and full parameter finetuning is overwhelmingly costly. Therefore, Parameter Efficient Finetuning (PEFT) has arisen as a cost-effective practice for instruction tuning because of significantly smaller computational, memory, and storage cost compared to full finetuning. Despite their widespread adaptations, the vast hyperparameter spaces, the number of PEFT methods, the different focus of instruction tuning capabilities make disentangling the impact of each aspect difficult. This study systematically investigates several representative PEFT methods, surveying the effect of hyperparameter choices including training hyperparameters and PEFT-specific hyperparameters, how different models sizes and the number of instruction tasks affect the performance, in-task-distribution memorization and open instruction following capability. Our empirical study shows that only LoRA and adapter can get close to full finetuning with ideal training settings. The ideal training setting includes an appropriate learning rate, largest LoRA rank or adapter size allowed and diverse training tasks. On the other hand, LoRA and adapter suffer from training instability if such an ideal training condition is not met. Additionally, LoRA requires a greater number of tasks for effective unseen task generalization, exhibit slower learning speed. Moreover, LoRA has weaker task-level memorization. Lastly, LoRA and adapter fall short in complex reasoning, coding and long-form generation compared to finetuning in open instruction tuning settings but it shows stronger capabilities compared to adapter.
Code (1)
Tasks
Instruction FollowingMemorizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An Empirical Study of Instruction-tuning Large Language Models in Chinese
The success of ChatGPT validates the potential of large language models (LLMs) in artificial general intelligence (AGI). Subsequently, the release of LLMs has sparked the open-source community's interest in instruction-t…
An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
Visual instruction tuning has recently shown encouraging progress with open-source large multimodal models (LMM) such as LLaVA and MiniGPT-4. However, most existing studies of open-source LMM are performed using models w…
Visual Question AnsweringMonolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca
Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language,…
Instruction FollowingLarge Language ModelMultilingual NLPOpen-Domain Question Answering+2An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge for achieving a satisfactory performance in downstream tasks.…
DecoderReading ComprehensionAn Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models
Multimodal large language models (MLLMs) fine-tuned with multimodal instruction datasets have demonstrated remarkable capabilities in multimodal tasks. However, fine-tuning all parameters of MLLMs has become challenging …
Hallucinationparameter-efficient fine-tuning