CITDA:

Fine-tuned bert-base-uncased on the emotions dataset

Demo Notebook: https://colab.research.google.com/drive/10ZCFvlf2UV3FjU4ymf4OoipQvqHbIItG?usp=sharing

Packages

• Install torch
• Also, pip install transformers datasets scikit-learn wandb seaborn python-dotenv

Train

1. Rename .env.example to .env and set an API key from wandb
2. You can adjust model parameters in the explainableai.py file.
3. The model (pytorch_model.bin) is a based on the bert-base-uncased and already trained on the emotions dataset. To re-produce the training run finetune-emotions.py. You can change the base model, or the dataset by changing that file's code.

Example

Run example.py

Train

The model is already trained on bert-base-uncased with the emotions dataset. However, you can change parameters and re-fine-tune the model by running finetune-emotions.py.