embedding-training

A guide for fine-tuning SentenceTransformers bi-encoders, which turn text into vectors so similar documents can be found. It covers training, model selection, dataset formats, and retrieval testing.

In plain words
What is it for?
Use it to train embedding models from paired or triplet examples, choose adapter modes, run local training, and measure recall, MRR, nDCG, or MAP.
Why use it?
It provides a repeatable command-line process for training and evaluating text-retrieval models without writing one-off Python scripts.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/profsynapse/synaptic-tuner/embedding-training
Any agent
npx skills add ProfSynapse/Synaptic-Tuner --skill embedding-training
Clone the repo
git clone --depth 1 https://github.com/ProfSynapse/Synaptic-Tuner

Made for: Claude Code, Codex.

Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00143 $0.02506
Opus 5 $0.00072 $0.01253
Sonnet 5 $0.00029 $0.00501
Haiku 4.5 $0.00014 $0.00251

Measured 2d ago against content hash baa1104ee76d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

embedding-training scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/embedding-training/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Embedding Training Pipeline

Fine-tune SentenceTransformer bi-encoders for retrieval with the embedding training method. This skill covers the end-to-end loop: obtain triplets → train (pick a base + adapter mode) → evaluate retrieval against a labeled corpus → read metrics → refine. Every step is a copy-pasteable CLI command or a YAML edit; there is no ad hoc Python.

The embedding method is a sibling to sft/kto/grpo/dpo — it is wired into the same method registry (shared/utilities/paths.py TRAINING_METHODS), the same recipe/local-run path (tuner.py local-run), and the same output layout (embedding_output/<timestamp>/...). What differs is the model family (encoder, not causal-LM), the loss (contrastive, not next-token), and the evaluation axis (corpus-level retrieval metrics, not per-completion correctness).

Quick Reference

Task Command
Local Docker embedding smoke python tuner.py local-run --job-config Trainers/recipes/embedding_bge_base_smoke.yaml --yes
List registered models inspect Trainers/embedding/configs/model_registry.yaml
Validate a triplet dataset shape run the smoke recipe --dry-run (loader validates the JSONL)
Retrieval eval (untrained base) python -m Evaluator.cli --scenario embedding_retrieval_smoke.yaml (see reference/retrieval-eval.md)
Retrieval eval (trained adapter) swap model.registry_name for model.path in the scenario

The exact local-run / eval flags follow the same surface as the SFT path — verify against tuner/cli/parser.py or --help before scripting; do not guess flags from memory.

Method at a Glance

Aspect Embedding method
Model family encoder bi-encoder (BERT / XLM-RoBERTa / decoder-as-embedder)
Loss multiple_negatives_ranking (MNRL), optionally Matryoshka-wrapped
Dataset triplets {query, positive, negatives} or pairs {query, positive}
Adapter modes full · lora · frozen_head (no qlora in v1)
Evaluation corpus-level retrieval: recall@k / MRR / nDCG@k / MAP against qrels
Output embedding_output/<timestamp>/ (adapter or merged encoder)

Read the full file on GitHub · 182 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 182 lines · 143 tokens per session scan A baa1104ee76d

Subscribe to this mod's changes

embedding-training is a skill published in the GitHub repository ProfSynapse/Synaptic-Tuner (27 stars, last pushed 2d ago), licensed MIT. It adds 143 tokens to every session and 2,506 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens