---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: codeparrot-ds
  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. -->

# codeparrot-ds

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: 1.0590

## 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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 2.569         | 0.08  | 5000  | 1.7450          |
| 1.6804        | 0.15  | 10000 | 1.5230          |
| 1.5318        | 0.23  | 15000 | 1.4228          |
| 1.4512        | 0.31  | 20000 | 1.3543          |
| 1.3933        | 0.38  | 25000 | 1.3017          |
| 1.341         | 0.46  | 30000 | 1.2547          |
| 1.2962        | 0.54  | 35000 | 1.2101          |
| 1.2501        | 0.61  | 40000 | 1.1704          |
| 1.2074        | 0.69  | 45000 | 1.1307          |
| 1.1722        | 0.77  | 50000 | 1.0972          |
| 1.141         | 0.84  | 55000 | 1.0740          |
| 1.1228        | 0.92  | 60000 | 1.0618          |
| 1.1126        | 1.0   | 65000 | 1.0590          |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3