parser.add_argument("--max_seq_len",type=int,default=512,help="Number of words of the longest seqence.")
parser.add_argument("--max_seq_len",type=int,default=512,help="Number of words of the longest seqence.")
parser.add_argument("--use_gpu",type=ast.literal_eval,default=False,help="Whether use GPU for finetuning, input should be True or False")
parser.add_argument("--use_gpu",type=ast.literal_eval,default=False,help="Whether use GPU for finetuning, input should be True or False")
parser.add_argument("--use_data_parallel",type=ast.literal_eval,default=False,help="Whether use data parallel.")
parser.add_argument("--use_data_parallel",type=ast.literal_eval,default=False,help="Whether use data parallel.")
parser.add_argument("--network",type=str,default='bilstm',help="Pre-defined network which was connected after Transformer model, such as ERNIE, BERT ,RoBERTa and ELECTRA.")