soarsmu / attack-pretrain-models-of-code Goto Github PK

# fine-tuing
python run.py \
    --output_dir=./adv_saved_models \
    --model_type=roberta \
    --tokenizer_name=microsoft/codebert-base \
    --model_name_or_path=microsoft/codebert-base \
    --do_train \
    --train_data_file=../preprocess/dataset/train.jsonl \
    --eval_data_file=../preprocess/dataset/valid.jsonl \
    --test_data_file=../preprocess/dataset/test.jsonl \
    --epoch 5 \
    --block_size 512 \
    --train_batch_size 24 \
    --eval_batch_size 64 \
    --learning_rate 2e-5 \
    --max_grad_norm 1.0 \
    --evaluate_during_training \
    --seed 123456  2>&1 | tee train.log

# attack
python gi_attack.py \
    --output_dir=./saved_models \
    --model_type=roberta \
    --tokenizer_name=microsoft/codebert-base-mlm \
    --model_name_or_path=microsoft/codebert-base-mlm \
    --csv_store_path ./attack_genetic_400_800.csv \
    --base_model=microsoft/codebert-base-mlm \
    --use_ga \
    --train_data_file=../preprocess/dataset/train_subs.jsonl \
    --eval_data_file=../preprocess/dataset/test_subs_400_800.jsonl \
    --test_data_file=../preprocess/dataset/test_subs.jsonl \
    --block_size 512 \
    --eval_batch_size 64 \
    --seed 123456  > attack_gi_400_800.log 2>&1 &

    for index, pos in enumerate(replace_pos[line]):

        code[line] = code[line][:pos[3]+diff] + pos[1] + code[line][pos[4]+diff:]

        diff += pos[2]

    for index, pos in enumerate(list(sorted(replace_pos[line], key=lambda x:x[3]))):

        code[line] = code[line][:pos[3]+diff] + pos[1] + code[line][pos[4]+diff:]

        diff += pos[2]