---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: distilbert-base-future
  results: []
widget:
- text: "We will have a good time."
  example_title: "Positive"
- text: "We had a good time."
  example_title: "Negative"
---

# distilbert-base-future
## Table of Contents

- [Model description](#model_description)
- [Intended uses & limitations](#intended_uses_&_limitations)
- [Training and evaluation data](#training_and_evaluation_data)
- [Training procedure](#training_procedure)

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [future-statements dataset](https://huggingface.co/datasets/fidsinn/future-statements).
It achieves the following results on the evaluation set:
- Train Loss: 0.1142
- Train Sparse Categorical Accuracy: 0.9613
- Validation Loss: 0.1272
- Validation Sparse Categorical Accuracy: 0.9625
- Epoch: 1

## Model description

- The model was created by graduate students [D. Baradari](https://huggingface.co/Dunya), [F. Bartels](https://huggingface.co/fidsinn), A. Dewald, [J. Peters](https://huggingface.co/jpeters92) as part of a data science module of the University of Leipzig.
- Model was created on 11/08/22.
- This is version 1.0
- The model is a text classification model which is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased)
- Questions and comments can be send via the [community tab](https://huggingface.co/fidsinn/distilbert-base-future/discussions)

## Intended uses & limitations

- The primary intended use is the classification of input into a future or non-future sentence/statement.
- The model is primarily intended to be used by researchers to filter or label a large number of sentences according to the grammatical tense of the input.

## Training and evaluation data

- [Distilbert-base-future model](https://huggingface.co/fidsinn/distilbert-base-future) was trained and evaluated on the [future-statements dataset](https://huggingface.co/datasets/fidsinn/future-statements).
- [future-statements](https://huggingface.co/datasets/fidsinn/future-statements) is a dataset collected manually and automatically by graduate students [D. Baradari](https://huggingface.co/Dunya), [F. Bartels](https://huggingface.co/fidsinn), A. Dewald, [J. Peters](https://huggingface.co/jpeters92) of the University of Leipzig.
- We collected 2500 statements, 50% of which relate to future events and 50% of which relate to non-future events.
- The sole purpose of the dataset was the fine-tuning process of this model.
- Additional information on the dataset can be found on Huggingface: [future-statements dataset](https://huggingface.co/datasets/fidsinn/future-statements).

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32

### Training results

| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
| 0.3816     | 0.8594                            | 0.1547          | 0.9475                                 | 0     |
| 0.1142     | 0.9613                            | 0.1272          | 0.9625                                 | 1     |


### Framework versions

- Transformers 4.18.0
- TensorFlow 2.8.0
- Datasets 2.4.0
- Tokenizers 0.12.1