Edit model card

Model Description

This model is based on RoBERTa large (Liu, 2019), fine-tuned on a dataset of intent expressions available here and also on 🤗 Transformer datasets hub here.

The model was created as part of the work described in Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy . The model is released under the Community Data License Agreement - Sharing - Version 1.0 (link), If you use this model, please cite our paper.

The official GitHub is here. The script used for training the model is trainer.py.

Training parameters

  1. base_model = 'roberta-large'
  2. learning_rate=5e-6
  3. per_device_train_batch_size=16,
  4. per_device_eval_batch_size=16,
  5. num_train_epochs=15,
  6. load_best_model_at_end=True,
  7. save_total_limit=1,
  8. save_strategy='epoch',
  9. evaluation_strategy='epoch',
  10. metric_for_best_model='accuracy',
  11. seed=123

Data collator

DataCollatorWithPadding

Downloads last month
72
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train ibm/roberta-large-vira-intents