fsdp + DPO + fullyfintune会报错 about llama-factory HOT 1 OPEN

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 accelerate launch  \
    --config_file ./examples/accelerate/fsdp_config.yaml \
    ./src/train_bash.py \
    --stage dpo \
    --do_train \
    --model_name_or_path my_model \
    --dataset my_dataset \
    --template maritalk \
    --split train \
    --finetuning_type full \
    --dpo_beta=0.1 \
    --cutoff_len 2048 \
    --max_length 2048 \
    --max_new_tokens 2048 \
    --output_dir ~/my_output \
    --overwrite_cache \
    --overwrite_output_dir \
    --per_device_train_batch_size 1 \
    --gradient_accumulation_steps 1 \
    --lr_scheduler_type cosine \
    --logging_steps 10 \
    --save_steps 500 \
    --learning_rate 1e-5 \
    --warmup_ratio=0.1 \
    --num_train_epochs 3.0 \
    --plot_loss \
    --fp16 \
    --use_fast_tokenizer=True