#load model
vocab_path="ernie_gen_large/vocab.txt"
config_path="ernie_gen_large/ernie_config.json"
init_model="ernie_gen_large/params"

#for multi-turn dialog/qa
task_type="dialog"
role_type_size=3
turn_type_size=16

#input
max_src_len=480
max_tgt_len=32
tokenized_input="true"
continuous_position="true"
batch_size=4
in_tokens="false"
#tgt_type_id=1

#decode
do_decode="true"
max_dec_len=30
beam_size=3
length_penalty=0.0
use_multi_gpu_test="true"

#train
epoch=10
weight_decay=0.01
label_smooth=0.1
hidden_dropout_prob=0.1
save_and_valid_by_epoch="true"
#lr
warmup_proportion=0.1
lr_scheduler="linear_warmup_decay"
learning_rate=1e-5
#noise
random_noise="false"
noise_prob=0.5

#dataset
data_path="./datasets/coqa/"
train_set="train.tsv"
dev_set="dev.tsv"
do_train="true"
do_val="true"
do_test="false"
do_pred="false"

#evaluate
eval_script="sh ./eval/tasks/coqa/eval.sh"
eval_mertrics="f1"