You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
| `--source` | Path to the source code file that will be optimized (e.g., `optimize.py`). | Yes |
192
-
| `--eval-command` | Command to run for evaluating the code in `--source`. This command should print the target `--metric` and its value to the terminal (stdout/stderr). See note below. | Yes |
193
-
| `--metric` | The name of the metric you want to optimize (e.g., 'accuracy', 'speedup', 'loss'). This metric name should match what's printed by your `--eval-command`. | Yes |
192
+
| `--eval-command` | Command to run for evaluating the code in `--source`. This command should print the target `--metric` and its value to the terminal (stdout/stderr). See note below. | Yes |
193
+
| `--metric` | The name of the metric you want to optimize (e.g., 'accuracy', 'speedup', 'loss'). This metric name should match what's printed by your `--eval-command`. | Yes |
194
194
|`--maximize`| Whether to maximize (`true`) or minimize (`false`) the metric. | Yes |
195
195
|`--steps`| Number of optimization steps (LLM iterations) to run. | Yes |
196
-
|`--model`| Model identifier for the LLM to use (e.g., `gpt-4o`, `claude-3.5-sonnet`). Recommended models to try include `o3-mini`, `claude-3-haiku`, and `gemini-2.5-pro-exp-03-25`. | Yes |
197
-
|`--additional-instructions`| (Optional) Natural language description of specific instructions OR path to a file containing detailed instructions to guide the LLM. | No |
196
+
|`--model`| Model identifier for the LLM to use (e.g., `gpt-4o`, `claude-3.5-sonnet`). Recommended models to try include `o3-mini`, `claude-3-haiku`, and `gemini-2.5-pro-exp-03-25`.| Yes |
197
+
|`--additional-instructions`| (Optional) Natural language description of specific instructions OR path to a file containing detailed instructions to guide the LLM. | No |
198
+
|`--log-dir`| (Optional) Path to the directory to log intermediate steps and final optimization result. Defaults to `.runs/`. | No |
0 commit comments