腾讯混元研究：LLM 强化学习中的临界批量大小理论扩展
⚡️ As LLM reinforcement learning scales to larger GPU clusters and more training data, training efficiency becomes a first-order concern. Our new research revisits classical critical-batch-size theory and extends it to online LLM RL, where the model generates its own training data and rollout generation and training scale differently. Across GRPO and PPO, we find that learning-rate retuning can preserve learning per response over a bounded range of batch sizes. On fixed hardware, scaling up the batch size improves PPO generation-stage throughput by up to 2.29×, while our best measured GRPO configuration reaches the same validation target in 29% less time. 🚀 Read the full research: https://hy.tencent.ai/research/100116
腾讯混元发布新研究，将经典临界批量大小理论扩展至在线 LLM 强化学习场景。在 GRPO 和 PPO 上，学习率重新调优可在有限批量范围内保持每响应学习效果；固定硬件下，增大批量使 PPO 生成阶段吞吐量最高提升 2.29×，最佳 GRPO 配置达到相同验证目标的时间减少 29%。
来源：X：腾讯混元 (@TencentHunyuan) · x.lingyaoai.com