arXiv Machine Learning
Effective Learning Rate Governs Loss Dynamics in Language Model Pretraining
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
3d ago
How Does Local Landscape Geometry Evolve in Language Model Pre-Training?
The paper investigates how the local landscape geometry of language model pre‑training evolves, identifying two distinct phases. In Phase I, the landscape starts sharp, causing instability and loss plateaus at high learning rates, which explains the need for learning‑rate warmup and suggests longer warmups for larger peak rates. In Phase II, the geometry is governed by gradient noise scale, revealing a depth‑flatness trade‑off that motivates a dynamic batch‑size scheduler that starts small and grows later in training.
arXiv Machine Learning
Aug 31
Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss
The paper investigates how learning rate and batch size scale when pretraining dense large language models on English‑prevalent corpora, examining both jointly optimal and marginal evolutions across model capacity and data size. It explores the benefits of a Warmup‑Stable‑Decay learning‑rate schedule, assessing whether optimal hyperparameters transfer between stable and decay phases, and evaluates loss scaling forms that capture interactions between model capacity and dataset size. The study provides a baseline scaling procedure and releases the full set of pretraining runs for future OpenEuroLLM development.
arXiv Machine Learning
Jun 5
Neural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm Threshold
arXiv:2604. 00230v2 Announce Type: replace Abstract: Neural collapse (NC) -- the convergence of penultimate-layer features to a simplex equiangular tight frame -- is well understood at equilibrium, but the dynamics governing its onset remain poorly characterised.
arXiv Machine Learning
Aug 4
(How) Learning Rates Regulate Catastrophic Overtraining
arXiv:2604. 13627v2 Announce Type: replace Abstract: Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant.
arXiv Machine Learning
Aug 31
Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models
The paper investigates the often-overlooked scale vectors in large language models, showing that despite their tiny size they are crucial for pre‑training performance. The authors provide theoretical insights that scale vectors mainly aid optimization rather than expressivity, and they analyze how weight decay affects different normalization layers. Building on these findings, they propose lightweight improvements—branch‑specific heterogeneity, better placement, and magnitude‑direction reparameterization—that consistently reduce loss across a range of model sizes and training settings.
arXiv Machine Learning
Jul 24
Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay
arXiv:2607. 21005v1 Announce Type: new Abstract: Most explanations of training instability focus on \emph{learning-rate criticality}, typically characterized by the Edge of Stability, beyond which optimization becomes unstable.