Skip to content

Add benchmark runner script with retry functionality#8

Open
AlexCuadron wants to merge 25 commits intomainfrom
benchmark-runner-script
Open

Add benchmark runner script with retry functionality#8
AlexCuadron wants to merge 25 commits intomainfrom
benchmark-runner-script

Conversation

@AlexCuadron
Copy link
Owner

This PR adds a script to run the polyglot_benchmark and aider_bench benchmarks with retry functionality.

The script will:

  1. Run the polyglot_benchmark with the specified parameters
  2. Retry the benchmark if it fails, up to a maximum number of attempts
  3. Run the aider_bench with the specified parameters
  4. Retry the aider_bench if it fails, up to a maximum number of attempts
  5. Provide a summary of the benchmark runs

The script is configurable with parameters for the model, agent, evaluation limit, number of workers, maximum retry attempts, and retry delay.

openhands-agent and others added 25 commits February 25, 2025 04:45
- Added update_llm_config_for_completions_logging to imports
- Modified get_config to accept instance parameter
- Updated llm_config to enable completions logging
- Updated process_instance to pass instance to get_config

This change makes aider_bench save llm_completions in the same way as swe_bench,
with completions being saved in {eval_output_dir}/llm_completions/{instance_id}/
…tions-fork

feat: Enable llm_completions logging in aider_bench
Add polyglot benchmark implementation
@github-actions
Copy link

This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants