Post-Training Science for Supervised Fine-Tuning
cs.LG, cs.CL
Submitted: 2026-09-01
Updated: 2026-09-01
Code: https://github.com/modelscope/ms-swift
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Old Optimizer, New Norm: An Anthology
- Chinchilla Scaling: A replication attempt
- A Hitchhiker's Guide to Scaling Law Estimation
- Understanding Emergent Abilities of Language Models from the Loss Perspective
- Practical Efficiency of Muon for Pretraining
- Language models scale reliably with over-training and on downstream tasks
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- Flatness is a False Friend
- Training Compute-Optimal Large Language Models
- Scaling Laws for Downstream Task Performance of Large Language Models
- A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
- Scaling Laws for Neural Language Models
- Muon is Scalable for LLM Training
- An Empirical Model of Large-Batch Training
- How predictable is language model benchmark performance?
- SOAP: Improving and Stabilizing Shampoo using Adam
- Instruction-Following Evaluation for Large Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks