# psyc training container — unsloth + Qwen3.5 QLoRA fine-tuning.
#
# Build:
#   docker build -t psyc-trainer -f Dockerfile.train .
#
# Run (24 GB GPU, mounts host data/ for datasets + adapter output):
#   docker run --gpus all --rm \
#       -v $(pwd)/data:/data \
#       psyc-trainer \
#       --dataset /data/datasets/ioc_extraction-v1.jsonl \
#       --dataset /data/datasets/severity_classification-v1.jsonl \
#       --dataset /data/datasets/routing_decision-v1.jsonl \
#       --dataset /data/datasets/tlp_assignment-v1.jsonl \
#       --output /data/adapters/psyc-v1
#
# Base image already ships Python 3.11 + torch 2.6 + CUDA 12.4 + cuDNN9, so
# there is no apt step and no torch download. Qwen3.5 needs transformers v5 —
# unsloth pulls it automatically.

FROM pytorch/pytorch:2.6.0-cuda12.4-cudnn9-devel

ENV PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    HF_HOME=/data/.hf-cache

RUN pip install --upgrade pip && \
    pip install unsloth unsloth_zoo trl datasets

WORKDIR /workspace
COPY scripts/train_qlora.py /workspace/train_qlora.py

ENTRYPOINT ["python", "/workspace/train_qlora.py"]