CUDA_VISIBLE_DEVICES=0 python run_squad.py \
  --model_name_or_path /path/to/xdoc-pretrain-roberta-1M \
  --dataset_name squad \
  --do_train \
  --do_eval \
  --per_device_train_batch_size 16 \
  --learning_rate 3e-5 \
  --num_train_epochs 2 \
  --max_seq_length 384 \
  --doc_stride 128 \
  --output_dir ./squadv1.1_result \
  --overwrite_output_dir