Merge pull request algorithmicsuperintelligence#5 from codelion/merged

Merged

Author: codelion

README.md

@@ -61,6 +61,36 @@ OpenEvolve can also be run from the command line:
 python openevolve-run.py path/to/initial_program.py path/to/evaluator.py --config path/to/config.yaml --iterations 1000
 ```
 
+### Resuming from Checkpoints
+
+OpenEvolve automatically saves checkpoints at intervals specified by the `checkpoint_interval` config parameter (default is 10 iterations). You can resume an evolution run from a saved checkpoint:
+
+```bash
+python openevolve-run.py path/to/initial_program.py path/to/evaluator.py \
+  --config path/to/config.yaml \
+  --checkpoint path/to/checkpoint_directory \
+  --iterations 50
+```
+
+When resuming from a checkpoint:
+- The system loads all previously evolved programs and their metrics
+- Checkpoint numbering continues from where it left off (e.g., if loaded from checkpoint_50, the next checkpoint will be checkpoint_60)
+- All evolution state is preserved (best programs, feature maps, archives, etc.)
+
+Example workflow with checkpoints:
+
+```bash
+# Run for 50 iterations (creates checkpoints at iterations 10, 20, 30, 40, 50)
+python openevolve-run.py examples/function_minimization/initial_program.py \
+  examples/function_minimization/evaluator.py \
+  --iterations 50
+
+# Resume from checkpoint 50 for another 50 iterations (creates checkpoints at 60, 70, 80, 90, 100)
+python openevolve-run.py examples/function_minimization/initial_program.py \
+  examples/function_minimization/evaluator.py \
+  --checkpoint examples/function_minimization/openevolve_output/checkpoints/checkpoint_50 \
+  --iterations 50
+```
 ### Docker
 
 You can also install and execute via Docker:

openevolve/cli.py

@@ -45,6 +45,12 @@ def parse_args() -> argparse.Namespace:
         default="INFO",
     )
 
+    parser.add_argument(
+        "--checkpoint",
+        help="Path to checkpoint directory to resume from (e.g., openevolve_output/checkpoints/checkpoint_50)",
+        default=None,
+    )
+
     parser.add_argument("--api-base", help="Base URL for the LLM API", default=None)
 
     parser.add_argument("--primary-model", help="Primary LLM model name", default=None)
@@ -101,6 +107,17 @@ async def main_async() -> int:
             output_dir=args.output,
         )
 
+        # Load from checkpoint if specified
+        if args.checkpoint:
+            if not os.path.exists(args.checkpoint):
+                print(f"Error: Checkpoint directory '{args.checkpoint}' not found")
+                return 1
+            print(f"Loading checkpoint from {args.checkpoint}")
+            openevolve.database.load(args.checkpoint)
+            print(
+                f"Checkpoint loaded successfully (iteration {openevolve.database.last_iteration})"
+            )
+
         # Override log level if specified
         if args.log_level:
             logging.getLogger().setLevel(getattr(logging, args.log_level))
@@ -111,11 +128,29 @@ async def main_async() -> int:
             target_score=args.target_score,
         )
 
+        # Get the checkpoint path
+        checkpoint_dir = os.path.join(openevolve.output_dir, "checkpoints")
+        latest_checkpoint = None
+        if os.path.exists(checkpoint_dir):
+            checkpoints = [
+                os.path.join(checkpoint_dir, d)
+                for d in os.listdir(checkpoint_dir)
+                if os.path.isdir(os.path.join(checkpoint_dir, d))
+            ]
+            if checkpoints:
+                latest_checkpoint = sorted(
+                    checkpoints, key=lambda x: int(x.split("_")[-1]) if "_" in x else 0
+                )[-1]
+
         print(f"\nEvolution complete!")
         print(f"Best program metrics:")
         for name, value in best_program.metrics.items():
             print(f"  {name}: {value:.4f}")
 
+        if latest_checkpoint:
+            print(f"\nLatest checkpoint saved at: {latest_checkpoint}")
+            print(f"To resume, use: --checkpoint {latest_checkpoint}")
+
         return 0
 
     except Exception as e:

openevolve/controller.py

@@ -154,7 +154,14 @@ async def run(
         self.database.add(initial_program)
 
         # Main evolution loop
-        for i in range(max_iterations):
+        start_iteration = self.database.last_iteration
+        total_iterations = start_iteration + max_iterations
+
+        logger.info(
+            f"Starting evolution from iteration {start_iteration} for {max_iterations} iterations (total: {total_iterations})"
+        )
+
+        for i in range(start_iteration, total_iterations):
             iteration_start = time.time()
 
             # Sample parent and inspirations
@@ -348,7 +355,7 @@ def _save_checkpoint(self, iteration: int) -> None:
 
         # Save the database
         checkpoint_path = os.path.join(checkpoint_dir, f"checkpoint_{iteration}")
-        self.database.save(checkpoint_path)
+        self.database.save(checkpoint_path, iteration)
 
         logger.info(f"Saved checkpoint at iteration {iteration} to {checkpoint_path}")
 

openevolve/database.py

@@ -81,6 +81,9 @@ def __init__(self, config: DatabaseConfig):
         # Track the absolute best program separately
         self.best_program_id: Optional[str] = None
 
+        # Track the last iteration number (for resuming)
+        self.last_iteration: int = 0
+
         # Load database from disk if path is provided
         if config.db_path and os.path.exists(config.db_path):
             self.load(config.db_path)
@@ -253,12 +256,13 @@ def get_top_programs(self, n: int = 10, metric: Optional[str] = None) -> List[Pr
 
         return sorted_programs[:n]
 
-    def save(self, path: Optional[str] = None) -> None:
+    def save(self, path: Optional[str] = None, iteration: int = 0) -> None:
         """
         Save the database to disk
 
         Args:
             path: Path to save to (uses config.db_path if None)
+            iteration: Current iteration number
         """
         save_path = path or self.config.db_path
         if not save_path:
@@ -278,6 +282,7 @@ def save(self, path: Optional[str] = None) -> None:
             "islands": [list(island) for island in self.islands],
             "archive": list(self.archive),
             "best_program_id": self.best_program_id,
+            "last_iteration": iteration or self.last_iteration,
         }
 
         with open(os.path.join(save_path, "metadata.json"), "w") as f:
@@ -306,6 +311,9 @@ def load(self, path: str) -> None:
             self.islands = [set(island) for island in metadata.get("islands", [])]
             self.archive = set(metadata.get("archive", []))
             self.best_program_id = metadata.get("best_program_id")
+            self.last_iteration = metadata.get("last_iteration", 0)
+
+            logger.info(f"Loaded database metadata with last_iteration={self.last_iteration}")
 
         # Load programs
         programs_dir = os.path.join(path, "programs")