微调代码,打标签后的文件放在work目录下不会被删除,若放在data下重启环境后会被删掉
python doccano.py \
--doccano_file ./work/admin.jsonl \
--task_type ext \
--save_dir ./data \
--splits 0.8 0.2 0 \
--schema_lang ch
export finetuned_model=./checkpoint/model_best
python finetune.py \
--device gpu \
--logging_steps 10 \
--save_steps 100 \
--eval_steps 100 \
--seed 42 \
--model_name_or_path uie-base \
--output_dir $finetuned_model \
--train_path data/train.txt \
--dev_path data/dev.txt \
--max_seq_length 512 \
--per_device_eval_batch_size 16 \
--per_device_train_batch_size 16 \
--num_train_epochs 20 \
--learning_rate 1e-5 \
--label_names "start_positions" "end_positions" \
--do_train \
--do_eval \
--do_export \
--export_model_dir $finetuned_model \
--overwrite_output_dir \
--disable_tqdm True \
--metric_for_best_model eval_f1 \
--load_best_model_at_end True \
--save_total_limit 1