Parameter Efficient Instruction Tuning: An Empirical Study

• URL: http://arxiv.org/abs/2411.16775v1
• Date: Mon, 25 Nov 2024 07:06:09 GMT
• Title: Parameter Efficient Instruction Tuning: An Empirical Study
• Authors: Pengfei He,
• Abstract summary: 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. Our empirical study shows that only LoRA and adapter can get close to full finetuning with ideal training settings.
• Score: 1.5186090363516862
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning [24.03926595342341]
  Low-Rank Adaptation (LoRA) is a tool for parameter-efficient finetuning of large models.<n>It is unclear how the optimal learning rate scales with adapter rank.<n>We introduce Maximal-Update Adaptation ($$A), a theoretical framework that characterizes how the "optimal" learning rate should scale.
  arXiv  Detail & Related papers  (2026-02-05T21:28:59Z)
• Per-parameter Task Arithmetic for Unlearning in Large Language Models [63.240204423180955]
  In large language model (LLM) unlearning, private information is required to be removed.<n> Task arithmetic unlearns by subtracting a specific task vector (TV)
  arXiv  Detail & Related papers  (2026-01-29T17:35:32Z)
• High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning [57.85676271833619]
  Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning.<n>We present textbfSMoA, a high-rank textbfStructured textbfMOdulation textbfAdapter that uses fewer trainable parameters while maintaining a higher rank.
  arXiv  Detail & Related papers  (2026-01-12T13:06:17Z)
• Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs [75.11449420928139]
  Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. Low-Rank Adaptation (LoRA) has emerged as a promising solution, but there exists a gap between the practical performance of low-rank adaptations and its theoretical optimum. We propose eXtreme Gradient Boosting LoRA, a novel framework that bridges this gap by leveraging the power of ensemble learning.
  arXiv  Detail & Related papers  (2024-10-25T17:07:13Z)
• MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning [71.50432879573614]
  Low-rank adaptation (LoRA) is based on the idea that the adaptation process is intrinsically low-dimensional. We present MELoRA, a mini-ensemble low-rank adapters that uses fewer trainable parameters while maintaining a higher rank. Our experimental results show that, compared to LoRA, MELoRA achieves better performance with 8 times fewer trainable parameters on natural language understanding tasks and 36 times fewer trainable parameters on instruction following tasks.
  arXiv  Detail & Related papers  (2024-02-27T07:14:12Z)
• PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation [65.268245109828]
  We introduce PRILoRA, which linearly allocates a different rank for each layer, in an increasing manner, and performs pruning throughout the training process. We validate the effectiveness of PRILoRA through extensive experiments on eight GLUE benchmarks, setting a new state of the art.
  arXiv  Detail & Related papers  (2024-01-20T20:25:17Z)
• Context-PEFT: Efficient Multi-Modal, Multi-Task Fine-Tuning [12.648711621637663]
  This paper introduces a novel. COCO-Efficient Fine-Tuning (PEFT) framework for multi-modal, multi-task transfer learning with pre-trained language models. We propose Context-PEFT, which learns different groups of adaptor parameters based on the token's domain. Our method is evaluated on the captioning task, where it outperforms full fine-tuning under similar data constraints.
  arXiv  Detail & Related papers  (2023-12-14T13:00:24Z)
• TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models [32.83440439290383]
  We introduce TAIL (Task-specific Adapters for Learning), a framework for efficient adaptation to new control tasks. Inspired by recent advancements in parameter-efficient fine-tuning in language domains, we explore efficient fine-tuning techniques. Our experiments in large-scale language-conditioned manipulation tasks suggest that TAIL with LoRA can achieve the best post-adaptation performance.
  arXiv  Detail & Related papers  (2023-10-09T17:49:50Z)
• AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning [143.23123791557245]
  Fine-tuning large pre-trained language models on downstream tasks has become an important paradigm in NLP. We propose AdaLoRA, which adaptively allocates the parameter budget among weight matrices according to their importance score. We conduct extensive experiments with several pre-trained models on natural language processing, question answering, and natural language generation to validate the effectiveness of AdaLoRA.
  arXiv  Detail & Related papers  (2023-03-18T22:36:25Z)
• Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding [40.27182770995891]
  Fine-tuning is widely used as the default algorithm for transfer learning from pre-trained models. We introduce the Speech UndeRstanding Evaluation (SURE) benchmark for parameter-efficient learning for various speech-processing tasks.
  arXiv  Detail & Related papers  (2023-03-02T08:57:33Z)
• Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning [81.3514358542452]
  Few-shot in-context learning (ICL) incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made. parameter-efficient fine-tuning offers an alternative paradigm where a small set of parameters are trained to enable a model to perform the new task. In this paper, we rigorously compare few-shot ICL and parameter-efficient fine-tuning and demonstrate that the latter offers better accuracy as well as dramatically lower computational costs.
  arXiv  Detail & Related papers  (2022-05-11T17:10:41Z)
• LoRA: Low-Rank Adaptation of Large Language Models [71.75808607987281]
  Low-Rank Adaptation, or LoRA, freezes the pre-trained model weights and injects trainable rank decomposition into each layer of the Transformer architecture. For GPT-3, LoRA can reduce the number of trainable parameters by 10,000 times and the computation hardware requirement by 3 times compared to full fine-tuning.
  arXiv  Detail & Related papers  (2021-06-17T17:37:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.