From Checkpoint Variation to Selection Gains in Supervised Fine-Tuning
cs.LG, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/tatsu-lab/stanford_alpaca
Terminology
Sources
- Don't stop me now: How Validation Criteria Affect Checkpoint Selection and Early Stopping
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- The Llama 3 Herd of Models
- Measuring Mathematical Problem Solving With the MATH Dataset
- A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility
- Averaging Weights Leads to Wider Optima and Better Generalization
- Decoupled Weight Decay Regularization
- Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models
- Post-Training Science for Supervised Fine-Tuning
- Qwen2.5 Technical Report
- Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks
- Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking
- Qwen3 Technical Report
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks