Dockerfile.train

FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1

WORKDIR /app

RUN apt-get update && apt-get install -y \
    python3.10 python3.10-dev python3-pip git curl build-essential && \
    rm -rf /var/lib/apt/lists/* && \
    ln -sf python3.10 /usr/bin/python && \
    ln -sf python3.10 /usr/bin/python3

# Training deps (with CUDA support)
RUN pip install --upgrade pip setuptools wheel
RUN pip install --no-cache-dir \
    torch==2.2.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
RUN pip install --no-cache-dir \
    "trl>=0.9.0" \
    "transformers>=4.44.0" \
    "peft>=0.10.0" \
    "accelerate>=0.28.0" \
    "bitsandbytes>=0.42.0" \
    "datasets>=2.18.0" \
    "huggingface-hub>=0.21.0" \
    numpy pandas scipy scikit-learn \
    PyYAML rich python-dotenv wandb
RUN pip install --no-cache-dir \
    "unsloth[cu121-ampere-torch220] @ git+https://github.com/unslothai/unsloth.git" \
    || pip install --no-cache-dir \
    "unsloth @ git+https://github.com/unslothai/unsloth.git"

COPY . .
RUN mkdir -p data results/plots echo_lora_adapter

EXPOSE 7860

CMD ["python", "train_entrypoint.py"]