揭秘变压器模型学习突变前的隐藏机制
What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers
- 发现训练中存在可解释的部分解与输出重复偏差
- 平台期隐藏状态趋近平行，注意力学习缓慢
- 适用于理解小模型到大模型早期预训练现象
在算法任务上训练浅层Transformer时，常出现性能平台期后突然大幅提升的奇异现象。本文揭示：平台期中模型会形成可解释的部分解，同时输出呈现强烈重复偏差，伴随隐藏状态坍缩（不同词元的隐藏状态趋于平行）。注意力机制的缓慢学习是主要瓶颈，平台期中注意力配置的隐性进展预示快速收敛。直接干预注意力可显著改变平台持续时间、重复偏差和表征坍缩程度。这些现象不仅存在于简化设置中，也在Pythia和OLMo等大语言模型的早期预训练阶段中显现。
原文摘要 · Abstract (English)
Training Transformers on algorithmic tasks frequently demonstrates an intriguing abrupt learning phenomenon: an extended performance plateau followed by a sudden, sharp improvement. This work investigates the underlying mechanisms for such dynamics, primarily in shallow Transformers. We reveal that during the plateau, the model often develops an interpretable partial solution while simultaneously exhibiting a strong repetition bias in their outputs. This output degeneracy is accompanied by internal representation collapse, where hidden states across different tokens become nearly parallel. We further identify the slow learning of optimal attention maps as a key bottleneck. Hidden progress in attention configuration during the plateau precedes the eventual rapid convergence, and directly intervening on attention significantly alters plateau duration and the severity of repetition bias and representational collapse. We validate that these identified phenomena-repetition bias and representation collapse-are not artifacts of toy setups but also manifest in the early pre-training stage of large language models like Pythia and OLMo.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。