Skip to content

Latest commit

 

History

History
24 lines (21 loc) · 725 Bytes

README.md

File metadata and controls

24 lines (21 loc) · 725 Bytes

Fine-tuning CPT for NER

Requirement

To run NER code, please install the newest version of fastNLP on github.

pip install git+https://github.com/fastnlp/fastNLP

Dataset

  • CLUENER can be found HERE.
  • MSRA can be downloaded by fastNLP automatically.
  • OntoNotes can be downloaded HERE.

Train and Evaluate

The example running scripts for training CPT on MSRA dataset are as follows.

python -m torch.distributed.launch --nproc_per_node 1 --nnodes 1 \
    train_msra.py \
    --ptm_name fnlp/cpt-base \
    --dataset '' \
    --use_decoder 0 \
    --batch_size 16 \
    --update_every 1