| | --- |
| | license: mit |
| | 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: 1.0626 |
| |
|
| | ## 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 |
| | - mixed_precision_training: Native AMP |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:-----:|:-----:|:---------------:| |
| | | 2.5672 | 0.08 | 5000 | 1.7393 | |
| | | 1.6801 | 0.15 | 10000 | 1.5217 | |
| | | 1.5349 | 0.23 | 15000 | 1.4211 | |
| | | 1.4557 | 0.31 | 20000 | 1.3588 | |
| | | 1.3968 | 0.38 | 25000 | 1.3071 | |
| | | 1.3458 | 0.46 | 30000 | 1.2592 | |
| | | 1.2994 | 0.54 | 35000 | 1.2142 | |
| | | 1.2541 | 0.61 | 40000 | 1.1730 | |
| | | 1.2123 | 0.69 | 45000 | 1.1335 | |
| | | 1.175 | 0.77 | 50000 | 1.1012 | |
| | | 1.1454 | 0.84 | 55000 | 1.0777 | |
| | | 1.1247 | 0.92 | 60000 | 1.0652 | |
| | | 1.1168 | 1.0 | 65000 | 1.0626 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.24.0 |
| | - Pytorch 1.12.1+cu113 |
| | - Datasets 2.7.1 |
| | - Tokenizers 0.13.2 |
| |
|
