---
library_name: transformers
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: 1.0836

## 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: 96
- eval_batch_size: 96
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 768
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 2.2179        | 0.2299 | 5000  | 1.4381          |
| 1.4035        | 0.4598 | 10000 | 1.2469          |
| 1.2543        | 0.6897 | 15000 | 1.1352          |
| 1.1667        | 0.9196 | 20000 | 1.0836          |


### Framework versions

- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.2
- Tokenizers 0.22.1