# training

> Browse 3 items tagged with training.

## Items

- [Progressive K-Annealing](https://vectordb.ever.works/items/progressive-k-annealing) — Training technique in CSRv2 that stabilizes sparsity learning by gradually increasing sparsity constraints, reducing dead neurons from >80% to ~20%.
- [Supervised Contrastive Objectives](https://vectordb.ever.works/items/supervised-contrastive-objectives) — Training technique in CSRv2 that enhances representational quality of sparse embeddings by using labeled data to guide the learning process.
- [Sentence Transformers v3.0](https://vectordb.ever.works/items/sentence-transformers-v3-updates) — Major update to the Sentence Transformers library introducing a new SentenceTransformerTrainer for easier fine-tuning, multi-GPU support, improved loss logging, and access to 15,000+ pre-trained models on HuggingFace.

---

_Canonical page: https://vectordb.ever.works/tags/training_