arXiv (All)
open access
Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack
Language-model checkpoints are commonly selected by pretraining loss or benchmark scores, assuming that the highest-scoring checkpoint will remain the best starting point for subsequent training. We show that this assumption can fail in a full 30B mixture-of-experts training pipeline. The checkpoint
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization#1160986
- Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization#1155493
- Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models#332492
- Prompt-Robust Language Models: Which Training Strategies Work?#821176
- An Efficient Sparse Fine-Tuning with Low Quantization Error via Neural Network Pruning#793414
Record · ID 986585
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive