| --- |
| library_name: transformers |
| license: mit |
| base_model: microsoft/deberta-v3-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - f1 |
| model-index: |
| - name: deberta_Eau |
| 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. --> |
|
|
| # deberta_Eau |
| |
| This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0898 |
| - Accuracy: 0.9551 |
| - F1: 0.9533 |
| |
| ## 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: 5e-05 |
| - train_batch_size: 32 |
| - eval_batch_size: 32 |
| - 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: linear |
| - num_epochs: 30 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
| | 1.1053 | 1.0 | 67 | 0.4668 | 0.8652 | 0.8481 | |
| | 0.4887 | 2.0 | 134 | 0.2434 | 0.9220 | 0.9225 | |
| | 0.2714 | 3.0 | 201 | 0.2129 | 0.9333 | 0.9341 | |
| | 0.2296 | 4.0 | 268 | 0.1752 | 0.9319 | 0.9341 | |
| | 0.2098 | 5.0 | 335 | 0.1676 | 0.9418 | 0.9402 | |
| | 0.1881 | 6.0 | 402 | 0.1473 | 0.9433 | 0.9443 | |
| | 0.1472 | 7.0 | 469 | 0.0982 | 0.9504 | 0.9515 | |
| | 0.1332 | 8.0 | 536 | 0.0969 | 0.9527 | 0.9517 | |
| | 0.1291 | 9.0 | 603 | 0.0919 | 0.9537 | 0.9517 | |
| | 0.1146 | 10.0 | 670 | 0.0898 | 0.9551 | 0.9533 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.48.3 |
| - Pytorch 2.5.1+cu124 |
| - Datasets 3.3.2 |
| - Tokenizers 0.21.0 |
| |
