fix: revert to torch 2.1.0 cu121 with trl 0.7.4 - versions that worked before

Dockerfile

@@ -7,16 +7,29 @@ ENV TORCHINDUCTOR_CACHE_DIR=/tmp/torch_cache
 
 RUN apt-get update && apt-get install -y git build-essential && rm -rf /var/lib/apt/lists/*
 
+RUN useradd -m -u 1000 trainer
+USER trainer
+ENV HOME=/home/trainer
+ENV HF_HOME=/home/trainer/.cache/huggingface
+ENV TORCHINDUCTOR_CACHE_DIR=/home/trainer/.cache/torch
+
 WORKDIR /app
 
-RUN pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cu124
+RUN pip install --no-cache-dir torch==2.1.0 --index-url https://download.pytorch.org/whl/cu121
 
-RUN pip install --no-cache-dir transformers accelerate peft trl bitsandbytes wandb datasets huggingface_hub matplotlib Pillow
+RUN pip install --no-cache-dir \
+    transformers==4.36.0 \
+    accelerate==0.25.0 \
+    peft==0.7.1 \
+    trl==0.7.4 \
+    bitsandbytes==0.41.3 \
+    wandb datasets huggingface_hub matplotlib Pillow
 
-RUN pip install --no-cache-dir git+https://github.com/Jayant-kernel/DECEIT-the-ai-truth-environment-.git
+RUN pip install --no-cache-dir \
+    git+https://github.com/Jayant-kernel/DECEIT-the-ai-truth-environment-.git
 
-RUN mkdir -p /usr/local/lib/python3.10/site-packages/deceit_env/data/
-COPY data/ /usr/local/lib/python3.10/site-packages/deceit_env/data/
+RUN mkdir -p /home/trainer/.local/lib/python3.10/site-packages/deceit_env/data/
+COPY data/ /home/trainer/.local/lib/python3.10/site-packages/deceit_env/data/
 COPY data/ /app/data/
 COPY train.py .
 COPY evaluate.py .