The paper investigates how the timing of introducing mid‑training (MT) data and the decay of the learning rate (LR) interact in large‑language‑model training. It shows that when the LR decays, mixing MT data earlier with pretraining (PT) data reduces final MT loss, whereas with a constant LR the opposite holds. The authors conduct ablation studies and propose a theoretical model explaining why the optimal data schedule depends on the LR schedule.
Mid-training (MT) is a training phase in LLM training pipelines that continues pretraining (PT) on smaller datasets of higher value. Taking the PT and MT phases as a whole, training usually starts wit...
The paper proposes a theoretical framework for scheduling high‑quality data in large language model training by extending functional scaling laws to account for time‑varying data quality. It identifies two regimes—noise‑limited and signal‑limited—where high‑quality data should be used differently, and introduces a Drop‑Stable‑Rampup training schedule that adjusts batch size at the quality transition. Experiments on 15B MoE and 600M dense models show significant accuracy gains over conventional decay schedules across multiple benchmarks.
arXiv:2609.13922v1 Announce Type: new Abstract: Minibatch persistency reuses data instead of reading it: rather than drawing a fresh minibatch at every optimizer step, it takes K consecutive steps on...
The paper introduces OP‑Mix, an on‑policy data mixing algorithm that operates continuously across pretraining, mid‑training, and instruction tuning. By simulating candidate mixtures through low‑rank adapters trained on the current model, OP‑Mix avoids separate proxy models and remains grounded in the model’s learning dynamics. Experiments show OP‑Mix consistently finds near‑optimal mixtures, improving pretraining perplexity by 6.3% and reducing compute for continual learning by 66–95% compared to baselines.
The paper investigates training-time data augmentation as a regularizer for autoregressive language model pretraining in data‑constrained, compute‑abundant settings. It introduces three orthogonal augmentation categories—token‑level noise, sequence permutations, and target offset prediction—and shows through systematic ablations that each category delays overfitting and reduces validation loss, with random token replacement performing best individually. Combining augmentation categories further lowers the minimum validation loss, demonstrating that such augmentations mitigate data inefficiency in autoregressive pretraining.
The paper introduces LARE, a method that adjusts domain weights during large language model pretraining by reweighting losses based on running loss statistics, rather than altering data exposure. Experiments on a 1.5B model trained with 240B tokens show that LARE improves performance across five benchmarks, achieving significant gains on GSM8K (+17.06 pp) and MATH (+9.00 pp). The approach demonstrates that balancing loss scales can enhance joint capabilities without increasing domain exposure.
arXiv:2602.06797v3 Announce Type: replace-cross Abstract: We study optimal learning rate (LR) schedules under the functional scaling law (FSL) framework (Li et al., 2025), which decomposes training d...
The paper studies how long‑context continual pre‑training (LCCP) scales with token budget and model size. An empirical additive power law is derived that predicts LCCP performance across five model scales and over a hundred budget configurations, and a new Constant‑Last4 protocol is introduced for stable monitoring. Experiments show that performance continues to improve without clear saturation, even after 128K context extension and fine‑tuning, indicating that scaling LCCP yields transferable gains for downstream tasks.
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.
Long-context continual pre-training (LCCP) is widely used to improve long-context capability, but how its benefits scale with the number of tokens used for LCCP remains unclear. We investigate this qu...
arXiv:2607. 04969v1 Announce Type: new Abstract: The training paradigm of large language models has shifted from traditional one-pass training to multi-epoch training, as reasonable reuse of limited high-quality data can improve both model performance and sample efficiency.
arXiv:2606. 16246v1 Announce Type: cross Abstract: As AI labs approach a data ceiling where compute capacity outpaces the rate of new high-quality text generation, language model pretraining is shifting toward a data-constrained, compute-abundant regime that demands productive multi-epoch training on fixed corpora.