metadata
license: apache-2.0
tags:
- generated_from_trainer
- Multiple Choice
metrics:
- accuracy
model-index:
- name: bert-base-uncased-Figurative_Language
results: []
language:
- en
pipeline_tag: question-answering
bert-base-uncased-Figurative_Language
This model is a fine-tuned version of bert-base-uncased.
It achieves the following results on the evaluation set:
- Loss: 0.7629
- Accuracy: 0.8124
Model description
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Multiple%20Choice/Figurative%20Language/Figurative%20Language%20-%20Multiple%20Choice%20Using%20BERT.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://huggingface.co/datasets/nightingal3/fig-qa
Histogram of Input Lengths
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6961 | 1.0 | 539 | 0.6932 | 0.5190 |
| 0.6595 | 2.0 | 1078 | 0.5326 | 0.7214 |
| 0.4647 | 3.0 | 1617 | 0.4604 | 0.7948 |
| 0.2884 | 4.0 | 2156 | 0.6204 | 0.8217 |
| 0.1702 | 5.0 | 2695 | 0.7629 | 0.8124 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3