Fine-tune your embedding model only when nDCG@10 drops below 0.70 and a reranker hasn't closed the gap

Phil Schmid·high signal

Use a clear decision gate before investing in embedding fine-tuning: measure retrieval with nDCG@10, and only fine-tune when it's below 0.70, a cross-encoder reranker hasn't fixed it, and dense encoding is the proven bottleneck. When you do, contrastive/multiple-negatives-ranking loss on (question, context) pairs with Matryoshka Representation Learning yields ~7% gains from just 6.3K samples in ~3 minutes on a consumer GPU, with 99%+ performance retention at 6× storage reduction.