Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sickn33/train-sentence-transformers
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair...
Passed 22 of 23 test cases with the skill, and 12 of 23 without it.
and 11 more in the full report
10 fixed12 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
What exact directory and filename pattern should be used for teeing script logs during execution?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies teeing execution logs to logs/{RUN_NAME}.log. | Missed | Passed |
The instructions your model reads when the skill loads.
Use this skill when you need train or fine-tune sentence-transformers models across SentenceTransformer (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), CrossEncoder (reranker; pair scoring for two-stage retrieval / pair...
This SKILL.md is a router, not a manual. It tells you which references and example scripts to load for your task. The actual content — recommended losses, evaluators, training-script structure, model selection, training-arg knobs, troubleshooting — lives in references/ and scripts/.
Do not synthesize a training script from this file alone. Open the per-type production template (scripts/train_<type>_example.py) and copy it as your starting point. The templates contain load-bearing scaffolding (autocast helper, model-card class, logger silencing list, force=True, seed, TF32, version-compatible imports, named-evaluator metric handling) that prior agent runs have repeatedly missed when rolling their own from a synthesized snippet.
| Tag | Class | What it does | When to pick |
|---|---|---|---|
| [SentenceTransformer] | SentenceTransformer (bi-encoder) | Maps each input to a fixed-dim dense vector | Retrieval, similarity, clustering, classification, paraphrase mining, dedup |
| [CrossEncoder] | CrossEncoder (reranker) | Scores (query, passage) pairs jointly | Two-stage retrieval (rerank top-100 from bi-encoder), pair classification |
| [SparseEncoder] | SparseEncoder (SPLADE) | Sparse vectors over the vocabulary | Learned-sparse retrieval, inverted-index backends (Elasticsearch / OpenSearch / Lucene) |
Tiebreakers when the request is ambiguous: "embedding model" / "vector search" / "similarity" → [SentenceTransformer]. "rerank" / "ranker" / "two-stage" → [CrossEncoder]. "SPLADE" / "sparse" / "inverted index" → [SparseEncoder]. If still unclear, ask.
Read these in full before writing any code. Do not triage by perceived relevance.
[SentenceTransformer]
references/losses_sentence_transformer.md — loss-to-data-shape mapping; BatchSamplers.NO_DUPLICATES requirement for MNRL-family; Cached* ↔ gradient_checkpointing incompatibility.references/evaluators_sentence_transformer.md — evaluator-to-task mapping; metric_for_best_model key construction (named vs unnamed); per-evaluator primary_metric values.references/model_architectures.md — encoder vs decoder vs static vs Router pipelines; pooling rules (mean / cls / lasttoken); auto-mean-pooling behavior for fresh-start MLM bases.scripts/train_sentence_transformer_example.py — production template; copy this as your starting point.[CrossEncoder]
references/losses_cross_encoder.md — pointwise / pairwise / listwise / distillation; pos_weight derivation; activation_fn=Identity() mandatory for non-BCE losses (silent eval-rank collapse otherwise).references/evaluators_cross_encoder.md — CrossEncoderRerankingEvaluator recipe; named-evaluator key format eval_{name}_{primary_metric}.scripts/train_cross_encoder_example.py — production template; copy this as your starting point.[SparseEncoder]
references/losses_sparse_encoder.md — SpladeLoss wrapper requirement; FLOPS regularizer weights; smoke-test active-dim ramp behavior.references/evaluators_sparse_encoder.md — SparseNanoBEIREvaluator (English-only) and the in-domain alternative; eval_{name}_{primary_metric} key format.test cases passed, vs 12 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.