absl-py==2.4.0 accelerate==1.12.0 aiohappyeyeballs==2.6.1 aiohttp==3.13.3 aiosignal==1.4.0 annotated-types==0.7.0 antlr4-python3-runtime==4.9.3 anyio==4.12.1 attrs==25.4.0 bitsandbytes==0.49.1 certifi==2026.1.4 charset-normalizer==3.4.4 click==8.3.1 colorama==0.4.6 datasets==4.5.0 dill==0.4.0 distro==1.9.0 filelock==3.20.3 frozenlist==1.8.0 fsspec==2025.10.0 grpcio==1.76.0 -e git+https://github.com/SonPhatTranDeveloper/grpo-countdown-problem.git@b9f24a8137be56fa8a055ef67fad4f99de30da43#egg=grpo_countdown_problem h11==0.16.0 hf-xet==1.2.0 httpcore==1.0.9 httpx==0.28.1 huggingface_hub==1.3.5 hydra-core==1.3.2 idna==3.11 Jinja2==3.1.6 jiter==0.12.0 joblib==1.5.3 Markdown==3.10.1 MarkupSafe==3.0.3 metrics==0.0.2 mpmath==1.3.0 multidict==6.7.1 multiprocess==0.70.18 networkx==3.6.1 numpy==2.1.2 omegaconf==2.3.0 openai==2.16.0 packaging @ file:///C:/miniconda3/conda-bld/packaging_1761049137378/work pandas==3.0.0 peft==0.18.1 pillow==12.1.0 propcache==0.4.1 protobuf==6.33.4 psutil==7.2.2 pyarrow==23.0.0 pydantic==2.12.5 pydantic_core==2.41.5 python-dateutil==2.9.0.post0 python-dotenv==1.2.1 PyYAML==6.0.3 regex==2026.1.15 requests==2.32.5 safetensors==0.7.0 scikit-learn==1.8.0 scipy==1.17.0 setuptools==80.10.1 shapely==2.0.6 shellingham==1.5.4 six==1.17.0 sniffio==1.3.1 sympy==1.14.0 tensorboard==2.20.0 tensorboard-data-server==0.7.2 threadpoolctl==3.6.0 tokenizers==0.22.2 torch==2.7.1+cu118 torchaudio==2.7.1+cu118 torchvision==0.22.1+cu118 tqdm==4.67.1 transformers==5.0.0 trl==0.27.1 typer-slim==0.21.1 typing-inspection==0.4.2 typing_extensions==4.15.0 tzdata==2025.3 urllib3==2.6.3 Werkzeug==3.1.5 wheel==0.46.3 xxhash==3.6.0 yarl==1.22.0