# f1/exact_match = 88.52/81.22 -> 81.5137/88.6696
CUDA_VISIBLE_DEVICES=0 python run_qa.py \
  --model_name_or_path google-bert/bert-base-uncased \
  --dataset_name squad \
  --do_train \
  --do_eval \
  --per_device_train_batch_size 12 \
  --learning_rate 3e-5 \
  --num_train_epochs 2 \
  --max_seq_length 384 \
  --doc_stride 128 \
  --output_dir ./baseline \
  --overwrite_output_dir \
  --apply-trp --trp-depths 1 --trp-p 0.1 --trp-lambdas 0.4 0.2 0.1