WavesLi

my_senta.init_model(model_class="ernie_1.0_skep_large_ch", task="sentiment_classify", use_cuda=use_cuda) 采用如上初始化方式

when I run the shell,hava a CUDA error to me. it will runing on a right status if i use cpu.

4

python3 run_classifier_word.py --task_name NEWS --do_train --do_eval --data_dir $GLUE_DIR/ --vocab_file $BERT_BASE_DIR/vocab.txt --bert_config_file $BERT_BASE_DIR/bert_config.json --init_checkpoint $BERT_BASE_DIR/pytorch_model.bin --max_seq_length 256 --train_batch_size 24 --learning_rate 2e-5 --num_train_epochs 50.0 --output_dir ./newsAll_output/ --local_rank 3 04/16/2019 16:33:35 - INFO...