---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: gpt2-finetuned-wikitext2
  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. -->

# gpt2-finetuned-wikitext2

**THE GITHUB REPO OF THIS MODEL [HERE](https://github.com/lengoctuong/Research-Transformer-and-fine_tune-GPT2).**

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.

It achieves the following results on the evaluation set:
- Loss: 3.3943
- Perplexity: 29.7930

## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- optimizer: AdamW
- lr_scheduler_type: linear
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.9315        | 1.0   | 49   | 3.6200          |
| 3.8128        | 1.0   | 112  | 3.4878          |
| 3.5448        | 2.0   | 195  | 3.4476          |
| 3.4743        | 2.0   | 258  | 3.4325          |
| 3.5040        | 3.0   | 391  | 3.4216          |
| 3.4371        | 3.0   | 404  | 3.4142          |


### Framework versions

- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3