---
library_name: transformers
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
model-index:
- name: gpt2-finetuned-python-purpose
  results: []
datasets:
- flytech/python-codes-25k
language:
- en
---

<!-- 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-python-purpose

This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on [flytech/python-codes-25k](https://huggingface.co/flytech/python-codes-25k).
It achieves the following results on the evaluation set:
- Loss: 0.4763

## 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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.0083        | 1.0   | 8233  | 0.9360          |
| 0.6853        | 2.0   | 16466 | 0.7537          |
| 0.4557        | 3.0   | 24699 | 0.6140          |
| 0.271         | 4.0   | 32932 | 0.5133          |
| 0.1585        | 5.0   | 41165 | 0.4763          |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.4.1+cu121
- Datasets 4.4.1
- Tokenizers 0.22.1