---
library_name: transformers
license: mit
datasets:
- mteb/tweet_sentiment_extraction
language:
- en
metrics:
- accuracy
base_model:
- openai-community/gpt2
pipeline_tag: text-classification
---

# Model Card for Model ID

This is a fine-tuned GPT-2 model for tweet sentiment classification. It categorizes tweets into positive, neutral, or negative sentiment based on their content.

### Model Description

<!-- Provide a longer summary of what this model is. -->

- **Model type:**  GPT-2 (with sequence classification head)
- **Language(s) (NLP):** English
- **License:** MIT
- **Finetuned from model [optional]:** gpt2


#### Metrics

The model was evaluated using the following metrics:

- Training Loss: Measures how well the model fits the training data. A lower value indicates better learning.

- Validation Loss: Measures how well the model generalizes to unseen data. It is used to detect overfitting.

- Accuracy: Percentage of correctly classified samples in the validation dataset. It is the primary performance metric for this sentiment classification task.

### Results

- The model was trained for 3 epochs. Below are the results per epoch:
- 
| Epoch | Training Loss | Validation Loss | Accuracy |
| ----- | ------------- | --------------- | -------- |
| 1     | 0.832400      | 0.871651        | 62.7%    |
| 2     | 0.512700      | 0.794255        | 69.3%    |
| 3     | 0.517500      | 0.819540        | 71.8%    |