Individual skill
finetuning
This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.
plugins/evo/skills/finetuning/SKILL.md
Source commit c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 3, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,498
- Repository last updated
- Oct 5, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- autonomous-agents Repository topic
- autoresearch Repository topic
- claude-code Repository topic
- code-optimization Repository topic
- codex Repository topic
- evolutionary-algorithms Repository topic
- llm-agents Repository topic
- design Derived category
- legal Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 18,111 bytesSKILL.mdcore · 18,111 bytesSKILL.mdcore · 18,111 bytesSKILL.mdcore · 18,111 bytesSKILL.mdcore · 18,111 bytesSKILL.mdcore · 18,111 bytesreferences/diagnostics.mddoc · 1,685 bytesreferences/false-progress.mddoc · 3,468 bytesreferences/glue.mddoc · 2,909 bytesreferences/observability.mddoc · 4,472 bytesreferences/rl/art.mddoc · 996 bytesreferences/serving/vllm.mddoc · 1,088 bytesreferences/sft/tinker.mddoc · 1,229 bytesreferences/trace-schema.mddoc · 1,996 bytes
Read excerpt
# Finetuning
Priors, not rules. Only firm guardrails: held-out eval you never train on, no leakage, trust evo's recorded numbers over the run's self-report. Override anything else against the gate.
## Pick the technique by reward shape
Decide on the reward first, technique second. Choosing the comfortable technique over the matching one is the most common failure.
| Reward shape | Technique |
|---|---|
| Verifiable (exact match, unit tests, parser-decidable) | **RL** (GRPO / RLOO / PPO) — reward includes format, so the model learns to emit verifier-acceptable shape |
| Preference pairs (chosen vs rejected) | **DPO / KTO / ORPO** — cheaper than full RL, no rollouts |
| Demonstrations only (curated traces, chat data) | **SFT** — install format/tone/capability the base lacks |
| Have a scorer + want SFT stability | **RFT** — sample, filter by reward, SFT on survivors |