medium10 pts · first answer countsfine-tuningembeddings
Batch size in contrastive tuning
With MultipleNegativesRankingLoss (in-batch negatives), why does a larger batch size often improve the embedding model?
Discussion 0
Join free to post in the discussion.
Related questions
- Cosine similarity by handMachine Learning Engineer
- What text embeddings captureMachine Learning Engineer
- Size of an embedding tableMachine Learning Engineer
- What full fine-tuning changesMachine Learning Engineer
- Why begin from a pretrained modelMachine Learning Engineer
- Training only a new headMachine Learning Engineer
- Learning rate for fine-tuningMachine Learning Engineer
- Shape of SFT training dataMachine Learning Engineer