Skip to content

Updated parallel iterations #120

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
Jul 7, 2025
Merged

Updated parallel iterations #120

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
8312b0f
init
MashAliK Jun 9, 2025
37afa09
Merge latest main into parallel-iterations fork
SuhailB Jul 2, 2025
16e7dc9
Fixed large artifact store/load issue
SuhailB Jul 3, 2025
d18123a
Added iteration increment
SuhailB Jul 3, 2025
321fb32
fixed error in iteration log message
SuhailB Jul 3, 2025
c5a2efe
Reverted database and config mods
SuhailB Jul 4, 2025
38a6568
Updated dependencies in pyproject.toml
SuhailB Jul 5, 2025
11da33c
Updated utils init and added a new line in code_utils
SuhailB Jul 5, 2025
ab4d044
Update config.py
codelion Jul 7, 2025
470a271
Refactor to threaded parallel evolution and remove file locks
codelion Jul 7, 2025
7dcfda8
Bump version to 0.0.12
codelion Jul 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions openevolve/cli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,6 +126,7 @@ async def main_async() -> int:
best_program = await openevolve.run(
iterations=args.iterations,
target_score=args.target_score,
checkpoint_path=args.checkpoint,
)

# Get the checkpoint path
Expand Down
10 changes: 7 additions & 3 deletions openevolve/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,10 @@ class LLMConfig(LLMModelConfig):
retry_delay: int = 5

# n-model configuration for evolution LLM ensemble
models: List[LLMModelConfig] = field(default_factory=lambda: [LLMModelConfig()])
models: List[LLMModelConfig] = field(default_factory=lambda: [
LLMModelConfig(name="gpt-4o-mini", weight=0.8),
LLMModelConfig(name="gpt-4o", weight=0.2)
])

# n-model configuration for evaluator LLM ensemble
evaluator_models: List[LLMModelConfig] = field(default_factory=lambda: [])
Expand Down Expand Up @@ -195,7 +198,7 @@ class EvaluatorConfig:
cascade_thresholds: List[float] = field(default_factory=lambda: [0.5, 0.75, 0.9])

# Parallel evaluation
parallel_evaluations: int = 4
parallel_evaluations: int = 1
distributed: bool = False

# LLM-based feedback
Expand All @@ -217,6 +220,7 @@ class Config:
log_level: str = "INFO"
log_dir: Optional[str] = None
random_seed: Optional[int] = 42
language: str = None

# Component configurations
llm: LLMConfig = field(default_factory=LLMConfig)
Expand Down Expand Up @@ -361,4 +365,4 @@ def load_config(config_path: Optional[Union[str, Path]] = None) -> Config:
# Make the system message available to the individual models, in case it is not provided from the prompt sampler
config.llm.update_model_params({"system_message": config.prompt.system_message})

return config
return config
Loading