5.0 KiB
Fine-Tuning Practical Examples Collection
A collection of specific code examples and markdown templates used for LangGraph application fine-tuning.
📋 Table of Contents
This guide is divided by Phase:
Phase 1: Preparation and Analysis Examples
Templates and code examples used in the optimization preparation phase:
- Example 1.1: fine-tune.md structure example
- Example 1.2: Optimization target list example
- Example 1.3: Code search example with Serena MCP
Estimated Time: 30 minutes - 1 hour
Phase 2: Baseline Evaluation Examples
Scripts and report examples used for current performance measurement:
- Example 2.1: Evaluation script (evaluator.py)
- Example 2.2: Baseline measurement script (baseline_evaluation.sh)
- Example 2.3: Baseline results report
Estimated Time: 1-2 hours
Phase 3: Iterative Improvement Examples
Practical examples of prompt optimization and result comparison:
- Example 3.1: Before/After prompt comparison
- Example 3.2: Prioritization matrix
- Example 3.3: Iteration results report
Estimated Time: 1-2 hours per iteration × number of iterations
Phase 4: Completion and Documentation Examples
Examples of recording final results and version control:
- Example 4.1: Final evaluation report (complete version)
- Example 4.2: Git commit message examples
Estimated Time: 30 minutes - 1 hour
🎯 How to Use
For First-Time Implementation
- Start with Phase 1 examples - Copy and use templates
- Set up Phase 2 evaluation scripts - Customize for your environment
- Iterate using Phase 3 comparison examples - Record Before/After
- Document with Phase 4 report - Summarize final results
Copy & Paste Ready
Each example includes complete code and templates:
- Python scripts → Ready to execute as-is
- Bash scripts → Set environment variables and run
- Markdown templates → Fill in content and use
- JSON structures → Templates for test cases and reports
📊 Types of Examples
Code Scripts
- Evaluation scripts (Phase 2): evaluator.py, aggregate_results.py
- Measurement scripts (Phase 2): baseline_evaluation.sh
- Analysis scripts (Phase 1): Serena MCP search examples
Markdown Templates
- fine-tune.md (Phase 1): Goal setting
- Optimization target list (Phase 1): Organizing improvement targets
- Baseline results report (Phase 2): Current state analysis
- Iteration results report (Phase 3): Improvement effect measurement
- Final evaluation report (Phase 4): Overall summary
Comparison Examples
- Before/After prompts (Phase 3): Specific improvement examples
- Prioritization matrix (Phase 3): Decision-making records
🔍 Finding Examples
By Purpose
| Purpose | Phase | Example |
|---|---|---|
| Set goals | Phase 1 | Example 1.1 |
| Find optimization targets | Phase 1 | Example 1.3 |
| Create evaluation scripts | Phase 2 | Example 2.1 |
| Measure baseline | Phase 2 | Example 2.2 |
| Improve prompts | Phase 3 | Example 3.1 |
| Determine priorities | Phase 3 | Example 3.2 |
| Write final report | Phase 4 | Example 4.1 |
| Git commit | Phase 4 | Example 4.2 |
🔗 Related Documentation
- Workflow - Detailed procedures for each Phase
- Evaluation Methods - Evaluation metrics and statistical analysis
- Prompt Optimization - Detailed optimization techniques
- SKILL.md - Overview of the Fine-tune skill
💡 Tips
Customization Points
- Number of test cases: Examples use 20 cases, but adjust according to your project
- Number of runs: 3-5 runs recommended for baseline measurement, but adjust based on time constraints
- Target values: Set Accuracy, Latency, and Cost targets according to project requirements
- Model: Adjust pricing if using models other than Claude 3.5 Sonnet
Frequently Asked Questions
Q: Can I use the example code as-is? A: Yes, it's executable once you set environment variables (API keys, etc.).
Q: Can I edit the templates? A: Yes, please customize freely according to your project.
Q: Can I skip phases? A: We recommend executing all phases on the first run. From the second run onward, you can start from Phase 2.
💡 Tip: For detailed procedures of each Phase, refer to the Workflow.