transformers
torch
numpy
pandas
datasets
wandb
sklearn
huggingface_hub
wandb login
higgungface-cli login
!python run.py \
--model_path "vinai/phobert-base"\
--data_path "truongpdd/vietnamese_clf_10classes_all_tokenized"\
--n_last-hidden 2\
--is_freeze False\
--epochs 5\
--n-folds 10\
--batch_size 64\
--max_length 512
KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media: https://aclanthology.org/2020.semeval-1.271.pdf