Spaces:
Running
Running
Commit History
-
Serve React frontend from FastAPI backend for one-click access Running
havinashpatil62c7e95 -
Fix emoji in README
havinashpatil034343c -
Update README with HF Space metadata
havinashpatilc40cb2b -
Finalizing CodeArena RL Benchmark: frontend improvements, GRPO training scripts, and cleaned environment
havinashpatil03a7eb9
-
fix: clamp reward to [0.01,0.99] so .2f never rounds to 0.00 or 1.00
havinashpatil59fd9d3 -
fix: removed invalid openenv-py package from notebook install cell
havinashpatil82e39c9 -
feat: use m-a-p/Code-Feedback dataset for GRPO training
havinashpatil9204c04 -
chore: update dependencies and include training results for README
havinashpatil8599a81 -
docs: Rewrite README for hackathon submission
havinashpatil3f9399a -
Complete all tasks: Adaptive curriculum, GRPO, React frontend, LLM-as-a-judge
havinashpatila448db8 -
Upload meta
havinashpatil03defc2
-
fix: reset task_id parsing, grader tuple crash fallback, and inference score output
646409d -
fix: exclusive score clamping (0.001, 0.999) for evaluator
2d8d38c -
fix: clamp scores to strict (0.001, 0.999) range
b3485c6 -
Rewrite inference.py for strict OpenEnv parsing + add httpx
eb60bd2 -
fix: openenv.yaml tasks graders + strict score bounds
9967cb5 -
fix: add safe_reward() clamp at every reward return point
f14f8d9 -
Minimal patch: standalone proxy ping + reward clamped to (0,1)
74bfde0 -
Add normalize_reward(); enforce strict (0,1) on all paths
b53855f -
Update grading logic to strict (0,1) ratio fallback
78b7e6b -
fix: use API_BASE_URL/API_KEY for LiteLLM proxy — always make API call (Phase 2)
51fdbe8 -
fix: make inference.py crash-proof when OPENAI_API_KEY is missing (Phase 2)
1fe26af -
fix: OpenEnv multi-mode compliance — add main() entrypoint and uv.lock
e92bfc1 -
Add pyproject.toml for OpenEnv validation compliance
652f070 -
Production-ready: add server/app.py with fallback-safe /reset, fix Dockerfile, add HF metadata, add task JSON files
dcc8fa3 -
Initial commit
54a19c9