data-constrained

Tag

Cards List
#data-constrained

Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining

Hugging Face Daily Papers · 2026-06-19 Cached

This paper investigates training-time data augmentation techniques to mitigate overfitting in autoregressive language model pretraining under data-constrained, compute-abundant regimes, finding that combining token-level noise, sequence permutations, and target offset prediction improves validation loss.

0 favorites 0 likes
#data-constrained

Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws

arXiv cs.LG · 2026-06-08 Cached

This paper studies data-constrained language model pretraining, proposing masked-input regularization (MIR) to improve validation loss and downstream performance, and SoftQ, a scaling law that better captures model-data interaction under repeated data.

0 favorites 0 likes
← Back to home

Submit Feedback