Tag:model-training

All the articles with the tag "model-training".

• Mine the Way Your Model Scores: MaxSim Hard-Negative Mining for a Late-Interaction Student

  Updated:7 Jun, 2026

  The standard way to mine hard negatives for a late-interaction model uses a single-vector cosine teacher, even though the model itself scores with multi-vector MaxSim. So I rebuilt my miner to score the way my model does. Matched mining clearly beat training with no mined negatives, while the cosine approach was barely doing anything at all.

• Diminishing Returns and the Art of Knowing When to Stop

  15 Mar, 2026

  I trained three generations of ColQwen3.5, each with more sophisticated optimization than the last. The most optimized version barely beat the previous one on the primary benchmark (+0.0011 nDCG@5). Individual tasks reshuffled substantially, with per-task swings an order of magnitude larger than the aggregate gain.