| --- |
| library_name: transformers |
| license: mit |
| base_model: FacebookAI/roberta-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: roberta-base-cpp |
| 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. --> |
|
|
| # roberta-base-cpp |
|
|
| This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.1043 |
| - Accuracy: 0.9419 |
|
|
| ## 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: 2e-05 |
| - train_batch_size: 2 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - gradient_accumulation_steps: 2 |
| - total_train_batch_size: 4 |
| - 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: linear |
| - num_epochs: 1 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | 0.1244 | 0.125 | 1000 | 0.0842 | 0.931 | |
| | 0.0851 | 0.25 | 2000 | 0.2041 | 0.7715 | |
| | 0.0632 | 0.375 | 3000 | 0.1610 | 0.9123 | |
| | 0.0521 | 0.5 | 4000 | 0.0907 | 0.9224 | |
| | 0.0426 | 0.625 | 5000 | 0.2447 | 0.8784 | |
| | 0.0341 | 0.75 | 6000 | 0.0667 | 0.9641 | |
| | 0.0252 | 0.875 | 7000 | 0.0872 | 0.957 | |
| | 0.0184 | 1.0 | 8000 | 0.1043 | 0.9419 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.57.1 |
| - Pytorch 2.8.0+cu126 |
| - Datasets 4.4.1 |
| - Tokenizers 0.22.1 |
| |
