---
metrics:
- accuracy
model-index:
- name: dgpt-small-sw
  results: []
language:
- en
widget:
- text: "A:The rest of it is just like wild flowers\nB:Wild flowers.\nA:and in the summertime we get the prettiest yellow flowers.\nB:Uh-huh.\nA:They're about, oh, I guess, a third the size of your, palm of your hand\nB:"
  example_title: "SW Example 1"
---

# dgpt-small-sw

This model is a fine-tuned version of [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) on the SwitchBoard dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3895
- Accuracy: 0.4853

## Model description

More details soon.

## Intended uses & limitations

More details soon.

## Training and evaluation data

More details soon.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0

### Training results



### Framework versions

- Transformers 4.26.0
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.0.dev0