Results establish ELR as a common coordinate linking LR scheduling, norm control, and loss dynamics, and Controlled interventions further show that weight decay and Hyperball shape loss dynamics primarily through the ELR schedules they induce.
Abstract
We uncover ELR collapse in language model pretraining: learning rate (LR) and parameter norm govern loss dynamics primarily through their ratio, the effective learning rate (ELR). When ELR is matched across runs, their loss trajectories collapse throughout training despite substantially different LRs and parameter norms. Across optimizers, architectures, datasets, and model scales, mean collapse errors are typically a few x 10^-3, below the seed-to-seed variation measured in a representative configuration. Systematic ablations identify normalization design and the timescale of LR-norm variation as key determinants of collapse precision. Controlled interventions further show that weight decay and Hyperball shape loss dynamics primarily through the ELR schedules they induce. Replacing LR with ELR enables a fitted functional scaling law (FSL) to transfer across norm-control methods. The resulting ELR-based FSL also explains delayed acceleration, a recurring effect of norm control. Together, these results establish ELR as a common coordinate linking LR scheduling, norm control, and loss dynamics.
The results suggest that continual learning is not a single capability: different patterns of environmental change require fundamentally different update behaviors, determining when adaptation must be learned inside model weights and when it can be achieved through external scaffolding.
A. Harrington, Nayan Saxena, Michael Murphy et al.· 2 citations· ⚡1
This study establishes a first baseline and scaling procedure for the development of future OpenEuroLLM models, and characterize the dependence of loss on model capacity and dataset size, evaluating recently proposed scaling forms that explicitly model their interaction.
Niccolò Ajroldi, Diana-Alexandra Onutu, Haider Al-Tahan et al.· 1 citation
Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard approach for improving complex reasoning in Large Language Models (LLMs). However, entropy collapse remains a critical bottleneck, often leading to performance degradation. While typically attributed to reduced exploration, we identify a more severe failure mode: update deadlock. We show that policy entropy bounds both the policy gradient and probability update norms; consequently, entropy collapse effectively stops reward signal backpropagation, preventing further policy learning regardless of data quality. To analyze this, we develop a micro-dynamics framework based on single-step logit updates. Our results indicate that entropy evolution depends on the interaction between advantage signals and the log-probability residual relative to its expectation, offering a unified perspective on existing interventions. Based on these findings, we propose ANCHOR, an algorithm designed to resolve deadlocks and maintain stability. ANCHOR uses a dual mechanism: it dynamically anchors the entropy decay of positive samples to prevent premature saturation, and uses entropy variations to stabilize updates for negative samples. Extensive experiments on reasoning benchmarks show that ANCHOR significantly outperforms strong baselines. Unlike heuristic methods that induce verbosity to mitigate collapse, ANCHOR promotes concise reasoning paths, improving both stability and efficiency.
Cong Qin, Jiaye Lin, Xiaoliang Fu et al.· Proceedings of the 32nd ACM...· 0 citations
A systematic literature review on how RL are adapted and scaled as a fundamental post-training tools and how innovations in the RL pipeline enhance the domain-specific LLMs is conducted.
Qianyue Hao, Lin Chen, Xiao-Qian Qi et al.· ACM Computing Surveys· 1 citation
A capacity-headroom hypothesis is proposed, which states that PPO performance at the SLM scale depends on both a fluent supervised model and a discriminative reward signal, rather than on the number of model parameters.
Behavior manifold analysis is introduced, which isolates behavior-specific geometry by selecting sparse behavior-associated coordinates and lifting them into low-dimensional local charts, and provides a unified framework for understanding the mechanistic distinction between the two objectives.
Jun-Tong Wang, Shengkun Yang, Xiyuan Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
