---
license: apache-2.0
tags:
- generated_from_trainer
- Multiple Choice
datasets:
- tasksource/winowhy
metrics:
- accuracy
pipeline_tag: question-answering
base_model: bert-base-uncased
model-index:
- name: bert-base-uncased-Winowhy
  results: []
---

# bert-base-uncased-Winowhy

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased).

It achieves the following results on the evaluation set:
- Loss: 0.8005
- Accuracy: 0.7118

## 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/Winowhy/Winowhy%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/tasksource/bigbench/viewer/winowhy/train

**Histogram of Input Lengths**

![Histogram of Input Lengths](https://raw.githubusercontent.com/DunnBC22/NLP_Projects/main/Multiple%20Choice/Winowhy/Images/Histogram%20of%20Input%20Lengths.png)

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7028        | 1.0   | 115  | 0.6916          | 0.5371   |
| 0.6119        | 2.0   | 230  | 0.5572          | 0.7031   |
| 0.4959        | 3.0   | 345  | 0.5328          | 0.7118   |
| 0.4537        | 4.0   | 460  | 0.5829          | 0.7118   |
| 0.2275        | 5.0   | 575  | 0.8005          | 0.7118   |

### Framework versions

- Transformers 4.26.1
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3