arXiv:2606. 07597v1 Announce Type: cross Abstract: Pre-training data mixtures are commonly tuned by running small-scale experiments and extrapolating to the target training budget.
arXiv:2608. 14071v1 Announce Type: new Abstract: As large language models scale, their training-token budgets must also increase to maintain an appropriate tokens-per-parameter ratio (\(\mathrm{TPP}\)).
arXiv:2606. 14971v1 Announce Type: cross Abstract: While large and diverse datasets have driven recent advances in large models, identifying the optimal data mixture for pre-training and post-training remains a significant open problem.
arXiv:2607. 01104v1 Announce Type: cross Abstract: In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance.
arXiv:2607. 22769v1 Announce Type: cross Abstract: The training efficacy of large language models (LLMs) is fundamentally constrained by the quality and composition of training data.
Data mixture selection is critical for Large Language Model pretraining. Existing methods such as RegMix select a single static mixture by fitting a regression model on small-scale proxy runs.
arXiv:2606. 01155v1 Announce Type: cross Abstract: Scaling laws for dense LLMs under infinite data are well explored, but how sparsity interacts with limited data is not.
arXiv:2605. 12705v2 Announce Type: replace Abstract: How can we train models whose post-trained capabilities survive subsequent fine-tuning?
arXiv:2508. 12116v2 Announce Type: replace-cross Abstract: As numerous instruction-tuning datasets continue to emerge, dynamically balancing and optimizing their mixtures has become a critical challenge.
arXiv:2607. 25271v1 Announce Type: cross Abstract: Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than the availability of high-quality data.
arXiv:2606. 24998v1 Announce Type: new Abstract: Language models are running out of high-quality training data, and even aggressively deduplicated corpora retain some amount of repetition.
arXiv:2606. 08167v1 Announce Type: cross Abstract: Recent research has established empirical scaling laws to predict model performance on multi-domain data mixtures.
arXiv:2606. 03938v1 Announce Type: cross Abstract: Multi-epoch training is becoming the standard now that compute is growing faster than the supply of high-quality text.