bert-base-uncased-Q_and_A-Answer_Prediction_Dataset
This model is a fine-tuned version of bert-base-uncased.
Model description
This is an extractive question answer model.
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Question%26Answer/Answer Prediction Dataset - Question%26Answer with BERT.ipynb
Intended uses & limitations
This model is intended to demonstrate my ability to solve a complex problem using technology.
Training and evaluation data
Dataset Source: https://www.kaggle.com/datasets/a2m2a2n2/question-answer-dataset
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Metric Name | Value |
|---|---|
| exact_match | 65.74 |
| f1 | 79.28 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.12.1