# 24GiB
# It is recommended to use padding_free. For more details, please refer to:
# https://github.com/modelscope/ms-swift/blob/main/examples/train/padding_free/dpo.sh
CUDA_VISIBLE_DEVICES=0 \
swift rlhf \
    --rlhf_type dpo \
    --model Qwen/Qwen2.5-7B-Instruct \
    --tuner_type lora \
    --dataset hjh0119/shareAI-Llama3-DPO-zh-en-emoji \
    --load_from_cache_file true \
    --split_dataset_ratio 0.01 \
    --torch_dtype bfloat16 \
    --num_train_epochs 1 \
    --per_device_train_batch_size 1 \
    --per_device_eval_batch_size 1 \
    --learning_rate 1e-4 \
    --lora_rank 8 \
    --lora_alpha 32 \
    --target_modules all-linear \
    --gradient_accumulation_steps 16 \
    --eval_steps 50 \
    --save_steps 50 \
    --save_total_limit 2 \
    --logging_steps 5 \
    --max_length 2048 \
    --output_dir output \
    --warmup_ratio 0.05 \
    --dataloader_num_workers 4 \
    --rpo_alpha 0.1 \
    --dataset_num_proc 4