---
license: apache-2.0
base_model: distilgpt2
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 [distilgpt2](https://huggingface.co./distilgpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9628

## 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: 100
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.8291        | 0.09  | 500  | 3.1048          |
| 2.7568        | 0.19  | 1000 | 2.6598          |
| 2.4536        | 0.28  | 1500 | 2.4579          |
| 2.284         | 0.38  | 2000 | 2.3267          |
| 2.1605        | 0.47  | 2500 | 2.2221          |
| 2.0615        | 0.56  | 3000 | 2.1385          |
| 1.9799        | 0.66  | 3500 | 2.0642          |
| 1.9192        | 0.75  | 4000 | 2.0100          |
| 1.8725        | 0.84  | 4500 | 1.9766          |
| 1.8484        | 0.94  | 5000 | 1.9628          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2