ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation

• URL: http://arxiv.org/abs/2406.14088v2
• Date: Thu, 24 Apr 2025 13:24:42 GMT
• Title: ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation
• Authors: Zhiyu Mei, Wei Fu, Kaiwei Li, Guangju Wang, Huanchen Zhang, Yi Wu,
• Abstract summary: Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for empowering large language model (LLM) applications.<n>We introduce ReaL, a pioneering system for efficient RLHF training.<n>We evaluate ReaL on the LLaMA models with up to 70 billion parameters and 128 GPUs.
• Score: 12.321332446941378
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for empowering large language model (LLM) applications. Compared with the supervised training process of LLMs, the RLHF training process is much more sophisticated, requiring a diverse range of computation workloads with intricate dependencies between multiple LLM instances. Therefore, simply adopting the fixed parallelization strategies from supervised training for LLMs can be insufficient for RLHF and result in low training efficiency. To overcome this limitation, we propose a novel technique named parameter ReaLlocation, which dynamically adapts the parallelization strategies for different workloads during training by redistributing LLM parameters across the training cluster. Building upon this idea, we introduce ReaL, a pioneering system for efficient RLHF training. ReaL introduces the concept of an execution plan, which defines a fine-grained resource allocation and parallelization strategy particularly designed for RLHF training. Based on this concept, ReaL employs a tailored search algorithm with a lightweight run-time estimator to automatically discover an efficient execution plan for an instance of RLHF experiment. Subsequently, the runtime engine deploys the selected plan by effectively parallelizing computations and redistributing parameters. We evaluate ReaL on the LLaMA models with up to 70 billion parameters and 128 GPUs. The experimental results demonstrate that ReaL achieves speedups of up to $3.58\times$ compared to baseline methods. Furthermore, the execution plans generated by ReaL exhibit an average of $81\%$ performance improvement over heuristic approaches based on Megatron-LM in the long-context scenario. The source code of ReaL is publicly available at https://github.com/openpsi-project/ReaLHF .

Related papers

• SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks [110.20297293596005]
  Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. Existing multi-turn RL algorithms for optimizing LLM agents fail to perform effective credit assignment over multiple turns while leveraging the generalization capabilities of LLMs. We propose a novel RL algorithm, SWEET-RL, that uses a carefully designed optimization objective to train a critic model with access to additional training-time information. Our experiments demonstrate that SWEET-RL achieves a 6% absolute improvement in success and win rates on ColBench compared to other state-of-the-art multi-turn RL algorithms.
  arXiv  Detail & Related papers  (2025-03-19T17:55:08Z)
• 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)
• Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models [11.624678008637623]
  We propose separating generation and learning in RLHF. Asynchronous training relies on an underexplored regime, online but off-policy RLHF. We study further compute optimizations for asynchronous RLHF but find that they come at a performance cost.
  arXiv  Detail & Related papers  (2024-10-23T19:59:50Z)
• In-the-loop Hyper-Parameter Optimization for LLM-Based Automated Design of Heuristics [0.020482269513546456]
  Large Language Models (LLMs) have shown great potential in automatically generating and optimizing (meta)heuristics. This paper presents a novel hybrid approach, LLaMEA-HPO, which integrates an open source LLaMEA framework with a Hyper- Evolutionary Optimization (HPO) procedure in the loop.
  arXiv  Detail & Related papers  (2024-10-07T14:04:31Z)
• VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment [66.80143024475635]
  We propose VinePPO, a straightforward approach to compute unbiased Monte Carlo-based estimates. We show that VinePPO consistently outperforms PPO and other RL-free baselines across MATH and GSM8K datasets.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning [67.95280175998792]
  A novel adversarial imitation learning (GAIL)-powered policy learning approach is proposed for optimizing beamforming, spectrum allocation, and remote user equipment (RUE) association ins. We employ inverse RL (IRL) to automatically learn reward functions without manual tuning. We show that the proposed MA-AL method outperforms traditional RL approaches, achieving a $14.6%$ improvement in convergence and reward value.
  arXiv  Detail & Related papers  (2024-09-27T13:05:02Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• Teaching Large Language Models to Reason with Reinforcement Learning [38.17625148525193]
  Reinforcement Learning from Human Feedback (textbfRLHF) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from feedback.
  arXiv  Detail & Related papers  (2024-03-07T16:36:29Z)
• Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy [47.327200425168314]
  Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values. We introduce Proxy-RLHF, which decouples the generation and alignment processes of LLMs. Our method achieves a comparable level of alignment with only 1% of the training parameters of other methods.
  arXiv  Detail & Related papers  (2024-03-07T07:31:00Z)
• ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL [80.10358123795946]
  We develop a framework for building multi-turn RL algorithms for fine-tuning large language models. Our framework adopts a hierarchical RL approach and runs two RL algorithms in parallel. Empirically, we find that ArCHer significantly improves efficiency and performance on agent tasks.
  arXiv  Detail & Related papers  (2024-02-29T18:45:56Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Run LoRA Run: Faster and Lighter LoRA Implementations [50.347242693025336]
  LoRA is a technique that reduces the number of trainable parameters in a neural network by introducing low-rank adapters to linear layers. This paper presents the RunLoRA framework for efficient implementations of LoRA. Experiments show up to 28% speedup on language modeling networks.
  arXiv  Detail & Related papers  (2023-12-06T10:54:34Z)
• vTrain: A Simulation Framework for Evaluating Cost-effective and Compute-optimal Large Language Model Training [3.0051215935332505]
  This paper presents our profiling-driven simulator called vTrain to determine an efficient and cost-effective training system configuration. We demonstrate vTrain's practicality through several case studies, e.g., effectively evaluating optimal training parallelization strategies.
  arXiv  Detail & Related papers  (2023-11-27T13:35:15Z)
• Language Reward Modulation for Pretraining Reinforcement Learning [61.76572261146311]
  We propose leveraging the capabilities of LRFs as a pretraining signal for reinforcement learning. Our VLM pretraining approach, which is a departure from previous attempts to use LRFs, can warmstart sample-efficient learning on robot manipulation tasks.
  arXiv  Detail & Related papers  (2023-08-23T17:37:51Z)

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.