| --- |
| library_name: transformers |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: gpt2_cfg_add_8 |
| 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. --> |
|
|
| # gpt2_cfg_add_8 |
| |
| This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0000 |
| - Accuracy: 1.0 |
| |
| ## 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: 0.001 |
| - train_batch_size: 64 |
| - eval_batch_size: 64 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_ratio: 0.1 |
| - num_epochs: 1 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:------:|:----:|:---------------:|:--------:| |
| | No log | 0 | 0 | 2.7379 | 0.0 | |
| | 1.9725 | 0.0320 | 100 | 1.9286 | 0.0 | |
| | 1.0948 | 0.0641 | 200 | 0.9757 | 0.02 | |
| | 0.6137 | 0.0961 | 300 | 0.6562 | 0.09 | |
| | 0.3684 | 0.1281 | 400 | 0.3644 | 0.35 | |
| | 0.2853 | 0.1602 | 500 | 0.2482 | 0.61 | |
| | 0.0578 | 0.1922 | 600 | 0.0728 | 0.84 | |
| | 0.0081 | 0.2242 | 700 | 0.0669 | 0.88 | |
| | 0.0033 | 0.2562 | 800 | 0.0264 | 0.93 | |
| | 2.4737 | 0.2883 | 900 | 1.5848 | 0.005 | |
| | 0.0482 | 0.3203 | 1000 | 0.0470 | 0.89 | |
| | 0.0009 | 0.3523 | 1100 | 0.0078 | 0.985 | |
| | 0.0125 | 0.3844 | 1200 | 0.0068 | 0.98 | |
| | 0.005 | 0.4164 | 1300 | 0.0116 | 0.975 | |
| | 0.0256 | 0.4484 | 1400 | 0.0035 | 0.995 | |
| | 0.0003 | 0.4805 | 1500 | 0.0005 | 1.0 | |
| | 0.0001 | 0.5125 | 1600 | 0.0001 | 1.0 | |
| | 0.0 | 0.5445 | 1700 | 0.0000 | 1.0 | |
| | 0.0 | 0.5766 | 1800 | 0.0000 | 1.0 | |
| | 0.0001 | 0.6086 | 1900 | 0.0002 | 1.0 | |
| | 0.0 | 0.6406 | 2000 | 0.0000 | 1.0 | |
| | 0.0 | 0.6726 | 2100 | 0.0000 | 1.0 | |
| | 0.0 | 0.7047 | 2200 | 0.0000 | 1.0 | |
| | 0.0 | 0.7367 | 2300 | 0.0000 | 1.0 | |
| | 0.0 | 0.7687 | 2400 | 0.0000 | 1.0 | |
| | 0.0 | 0.8008 | 2500 | 0.0000 | 1.0 | |
| | 0.0 | 0.8328 | 2600 | 0.0000 | 1.0 | |
| | 0.0 | 0.8648 | 2700 | 0.0000 | 1.0 | |
| | 0.0 | 0.8969 | 2800 | 0.0000 | 1.0 | |
| | 0.0 | 0.9289 | 2900 | 0.0000 | 1.0 | |
| | 0.0 | 0.9609 | 3000 | 0.0000 | 1.0 | |
| | 0.0 | 0.9930 | 3100 | 0.0000 | 1.0 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.46.0 |
| - Pytorch 2.5.1 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.1 |
|
|
