---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: text_classification_gpt2_1
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# text_classification_gpt2_1

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4571
- Accuracy: 0.792

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.9088        | 0.1   | 625  | 0.6229          | 0.662    |
| 1.0188        | 0.2   | 1250 | 0.5429          | 0.7092   |
| 0.9781        | 0.3   | 1875 | 0.5086          | 0.7556   |
| 0.6919        | 0.4   | 2500 | 0.4571          | 0.792    |
| 0.002         | 0.5   | 3125 | 0.5278          | 0.7892   |
| 1.6834        | 0.6   | 3750 | 0.5348          | 0.8104   |
| 0.0436        | 0.7   | 4375 | 0.4732          | 0.826    |
| 0.0332        | 0.8   | 5000 | 0.4995          | 0.8252   |
| 0.9907        | 0.9   | 5625 | 0.4764          | 0.8344   |
| 0.9651        | 1.0   | 6250 | 0.4809          | 0.8364   |


### Framework versions

- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1