Final Submission: Aligned ports (8000), synchronized README, and purged workspace logs/caches

README.md

@@ -3,7 +3,7 @@ title: PolicyEvolverEnv
 colorFrom: blue
 colorTo: indigo
 sdk: docker
-app_port: 7860
+app_port: 8000
 base_path: /dashboard/
 ---
 #  PolicyEvolverEnv — Multi-Modal Strategic Governance Sandbox
@@ -140,7 +140,7 @@ pip install -r server/requirements.txt
 ### 2. Run the Environment API
 Start the FastAPI environment server locally:
 ```bash
-uvicorn server.app:app --port 7860
+uvicorn server.app:app --port 8000
 ```
 This boots all core endpoint paths (`/reset`, `/step`, `/state`, `/tasks`, `/grader`, `/health`).
 

run1.json

@@ -1 +0,0 @@
-{"baseline_scores": {"overall_avg": 0.815}, "model": "llama-3.3-70b-versatile", "runtime_seconds": 13.21, "detail": [{"task_id": "task_easy", "reward": 0.745, "steps": 5}, {"task_id": "task_medium", "reward": 0.8, "steps": 5}, {"task_id": "task_hard", "reward": 0.9, "steps": 1}]}

run1_8b.json

@@ -1 +0,0 @@
-{"baseline_scores": {"overall_avg": 0.945}, "model": "llama-3.1-8b-instant", "runtime_seconds": 5.21, "detail": [{"task_id": "task_easy", "reward": 0.935, "steps": 1}, {"task_id": "task_medium", "reward": 1.0, "steps": 1}, {"task_id": "task_hard", "reward": 0.9, "steps": 1}]}

run2.json

@@ -1 +0,0 @@
-{"baseline_scores": {"overall_avg": 0.8983}, "model": "llama-3.3-70b-versatile", "runtime_seconds": 9.94, "detail": [{"task_id": "task_easy", "reward": 0.795, "steps": 5}, {"task_id": "task_medium", "reward": 1.0, "steps": 1}, {"task_id": "task_hard", "reward": 0.9, "steps": 1}]}

run2_8b.json

@@ -1 +0,0 @@
-{"baseline_scores": {"overall_avg": 0.945}, "model": "llama-3.1-8b-instant", "runtime_seconds": 3.86, "detail": [{"task_id": "task_easy", "reward": 0.935, "steps": 1}, {"task_id": "task_medium", "reward": 1.0, "steps": 1}, {"task_id": "task_hard", "reward": 0.9, "steps": 1}]}

run_final_1.json

@@ -1 +0,0 @@
-{"baseline_scores": {"overall_avg": 0.945}, "model": "llama-3.1-8b-instant", "runtime_seconds": 3.81, "detail": [{"task_id": "task_easy", "reward": 0.935, "steps": 1}, {"task_id": "task_medium", "reward": 1.0, "steps": 1}, {"task_id": "task_hard", "reward": 0.9, "steps": 1}]}

run_final_2.json

@@ -1 +0,0 @@
-{"baseline_scores": {"overall_avg": 0.945}, "model": "llama-3.1-8b-instant", "runtime_seconds": 3.78, "detail": [{"task_id": "task_easy", "reward": 0.935, "steps": 1}, {"task_id": "task_medium", "reward": 1.0, "steps": 1}, {"task_id": "task_hard", "reward": 0.9, "steps": 1}]}

test_result.json

@@ -1,31 +0,0 @@
-{
-  "baseline_scores": {
-    "task_easy": 0.85,
-    "task_medium": 0.85,
-    "task_hard": 0.70,
-    "overall_avg": 0.80
-  },
-  "mode": "llm",
-  "model": "meta-llama/Llama-3.3-70B-Instruct",
-  "runtime_seconds": 4.36,
-  "detail": [
-    {
-      "task_id": "task_easy",
-      "reward": 0.85,
-      "mode": "llm",
-      "done": false
-    },
-    {
-      "task_id": "task_medium",
-      "reward": 0.85,
-      "mode": "llm",
-      "done": false
-    },
-    {
-      "task_id": "task_hard",
-      "reward": 0.70,
-      "mode": "llm",
-      "done": false
-    }
-  ]
-}