基于军事题材样本的“实体关系”提取finetune.py脚本执行卡住不动的问题

[szgsuper263]

PaddleNLP-develop\PaddleNLP-develop\applications\information_extraction\text 目录下的finetune.py
i5,16g 笔记本执行以下命令
python finetune.py --device cpu --logging_steps 10 --save_steps 100 --eval_steps 100 --seed 42 --model_name_or_path uie-base --output_dir ./checkpoint/model_best --train_path data/train.txt --dev_path data/dev.txt --max_seq_len 512 --per_device_train_batch_size 4 --per_device_eval_batch_size 4 --num_train_epochs 20 --learning_rate 1e-5 --do_train --do_eval --do_export --export_model_dir ./checkpoint/model_best --overwrite_output_dir --disable_tqdm True --metric_for_best_model eval_f1 --load_best_model_at_end True --save_total_limit 1

执行到下面后就卡住不动了
[2023-04-06 00:06:14,583] [ INFO] - ***** Running training *****
[2023-04-06 00:06:14,583] [ INFO] - Num examples = 1076
[2023-04-06 00:06:14,583] [ INFO] - Num Epochs = 20
[2023-04-06 00:06:14,583] [ INFO] - Instantaneous batch size per device = 16
[2023-04-06 00:06:14,583] [ INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16
[2023-04-06 00:06:14,583] [ INFO] - Gradient Accumulation steps = 1
[2023-04-06 00:06:14,583] [ INFO] - Total optimization steps = 1360.0
[2023-04-06 00:06:14,583] [ INFO] - Total num train samples = 21520.0
[2023-04-06 00:06:14,599] [ INFO] - Number of trainable parameters = 117946370

[w5688414]

请问您的paddle和paddlenlp的版本是多少？请升级一下试试