| { |
| "model": "meta-llama/llama-3.3-70b-instruct:free", |
| "api_base": "https://openrouter.ai/api/v1", |
| "episodes_per_task": 1, |
| "seed_base": 1000, |
| "fast_mode": true, |
| "llm_every": 4, |
| "max_steps": null, |
| "task_averages": { |
| "1": 0.708, |
| "2": 0.6328, |
| "3": 0.5983 |
| }, |
| "overall_average": 0.6463666666666666, |
| "all_results": [ |
| { |
| "task_id": 1, |
| "seed": 1100, |
| "total_reward": 246.42219784256966, |
| "total_steps": 94, |
| "elapsed_sec": 1.5613129138946533, |
| "score": 0.708, |
| "sub_scores": { |
| "cost": 0.7079636116620143 |
| }, |
| "exploit_detected": false |
| }, |
| { |
| "task_id": 2, |
| "seed": 1200, |
| "total_reward": 242.81120610868118, |
| "total_steps": 95, |
| "elapsed_sec": 1.594855785369873, |
| "score": 0.6328, |
| "sub_scores": { |
| "cost": 0.7005224090103834, |
| "temperature": 0.53125 |
| }, |
| "exploit_detected": false |
| }, |
| { |
| "task_id": 3, |
| "seed": 1300, |
| "total_reward": 251.7133773862143, |
| "total_steps": 94, |
| "elapsed_sec": 1.6321852207183838, |
| "score": 0.5983, |
| "sub_scores": { |
| "batch_deadline": 1, |
| "carbon": 0.6563888726735232, |
| "cost": 0.6695079035324871, |
| "grid_response": 0.21428571428571427, |
| "temperature": 0.5833333333333334 |
| }, |
| "exploit_detected": false |
| } |
| ] |
| } |