uv run accelerate launch --config-file ./accelerate_config/fsdp2.yaml \
    main.py \
    --teacher_name_or_path 'swiss-ai/Apertus-8B-Instruct-2509' \
    --student_name_or_path 'HuggingFaceTB/SmolLM2-135M-Instruct' \
    --output_dir ./Apertus-8B-distill \
    --max_length 2048 \
    --per_device_train_batch_size 4 \
    --per_device_eval_batch_size 8 \
    --max_steps 200 \
    --logging_steps 5