Advanced self instruct generator with evolution methods

[Yiyi-philosophy]

Description

This PR enhances the mathematical problem generation capability and adds visualization tools. The changes include:

1. Modified examples/dataset/self_instruct_generator.py to examples/dataset/self_instruct_evolution_generator.py:

   • Incorporate evolution-based instruction generation for math problems, based on self_instruct_generator.py
   • Integrate with existing math problem templates and scoring system
   • Evaluate the generated problems with chatgpt o3-mini

2. Added examples/dataset/get_table.py to:

   • Visualize the evolution process of problem generation
   • Display scoring metrics for each generation
   • Present results in a tabular format for better analysis

The new visualization tool helps in understanding and analyzing how the evolution algorithm improves problem generation over iterations.

Checklist

• I have read the CONTRIBUTION guide
• I have linked this PR to an issue using the Development section
• I have checked dependencies in pyproject.toml and uv lock
• I have updated the tests accordingly
• I have updated the documentation
• I have added examples in the code