2251821381/jcl

Joint Contrastive Learning for Prompt-Based Few-Shot Language Learners

JCL

<> if you want to run our code ,you should first download all dataset acoording to the download_dataset.sh, and then, run the train.py . The dataset download address is https://nlp.cs.princeton.edu/projects/lm-bff/datasets.tar

• cd data
  bash download_dataset.sh
• python tools/generate_k_shot_data.py
• for seed in 13 21 42 87 100 #### random seeds for different train-test splits
  do for bs in 40 #### batch size do for lr in 1e-5 #### learning rate for MLM loss do for supcon_lr in 1e-5 #### learning rate for SupCon loss do TAG=exp
  TYPE=prompt-demo
  TASK=sst-5
  BS=$bs
  LR=$lr
  SupCon_LR=$supcon_lr
  SEED=$seed
  MODEL=roberta-base
  bash run_experiment.sh done done done done

rm -rf result/

model.png

# observation.png

jcl's Issues

Code missing

Thank you for providing such exquisite code. I found that src was missing files of dataset and processor and other files at runtime. Could you please provide them