hyperparameters
Complete guide to SimPO hyperparameter selection and tuning.
- Skills
- AI research
- 0
What it does and how to use it
A skill that teaches Claude Code to do ai research tasks well. It is packaged knowledge the model uses whenever it is relevant.
- Install the skill (command above).
- In Claude Code, describe what you need - the skill turns on by itself when the context fits.
- No commands to memorize: you talk in plain language and the skill does the rest.
Install (Claude Code)
mkdir -p .claude/skills/hyperparameters && curl -fsSL https://doutorai.pt/data/lib/skills__hyperparameters.md -o .claude/skills/hyperparameters/SKILL.mdPaste this command into the terminal, in your project folder, and the component installs automatically.
Content
# Hyperparameters
Complete guide to SimPO hyperparameter selection and tuning.
## Overview
Key hyperparameters in SimPO:
1. **Learning Rate** - Most critical
2. **Beta (β)** - Reward scaling
3. **Gamma-Beta Ratio (γ/β)** - Target margin
4. **SFT Weight** - Regularization strength
## Learning Rate
### Recommended Ranges
**By model size**:
| Model Size | Learning Rate | Notes |
|------------|---------------|-------|
| 1B-3B | 5e-7 to 1e-6 | Higher end safe |
| 7B-8B | 3e-7 to 5e-7 | **Standard** |
| 13B-30B | 1e-7 to 3e-7 | Lower for stability |
| 70B+ | 5e-8 to 1e-7 | Very conservative |
- 🔒 Full content on the Pro plan (€7.99/month) -Need help with Claude Code?
Ask Dr AI - it explains things simply.
Need a tailor-made solution?
Not sure where to start with AI in your business? Get a free assessment and a tailored plan - no commitment.
Save hours every week with AI, no hassle
Doutor AI gives you 1,859 ready-to-copy AI prompts, by industry and in plain English - plus a complete technical library for those who want to go further.