| --- |
| 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: 2.5232 |
|
|
| ## 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: 152 |
| - eval_batch_size: 152 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - 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 | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 5.1382 | 0.09 | 100 | 5.0409 | |
| | 4.6763 | 0.18 | 200 | 4.5291 | |
| | 4.1844 | 0.27 | 300 | 4.0911 | |
| | 3.7959 | 0.36 | 400 | 3.7670 | |
| | 3.4769 | 0.45 | 500 | 3.4760 | |
| | 3.2109 | 0.54 | 600 | 3.2396 | |
| | 2.9961 | 0.63 | 700 | 3.0584 | |
| | 2.8295 | 0.73 | 800 | 2.9007 | |
| | 2.6731 | 0.82 | 900 | 2.7664 | |
| | 2.565 | 0.91 | 1000 | 2.6825 | |
| | 2.4186 | 1.0 | 1100 | 2.5232 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.38.1 |
| - Pytorch 2.1.0+cu121 |
| - Datasets 2.18.0 |
| - Tokenizers 0.15.2 |
| |
