| --- |
| library_name: transformers |
| license: mit |
| base_model: FacebookAI/xlm-roberta-large |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: populism_classifier_bsample_112 |
| 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. --> |
|
|
| # populism_classifier_bsample_112 |
| |
| This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.9956 |
| - Accuracy: 0.5337 |
| - 1-f1: 0.1942 |
| - 1-recall: 1.0 |
| - 1-precision: 0.1075 |
| - Balanced Acc: 0.7530 |
| |
| ## 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: 3e-05 |
| - train_batch_size: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - optimizer: Use 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: 15 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:| |
| | 0.7261 | 1.0 | 12 | 0.8661 | 0.0562 | 0.1064 | 1.0 | 0.0562 | 0.5 | |
| | 0.6039 | 2.0 | 24 | 0.8458 | 0.0562 | 0.1064 | 1.0 | 0.0562 | 0.5 | |
| | 0.4807 | 3.0 | 36 | 1.3332 | 0.4860 | 0.1794 | 1.0 | 0.0985 | 0.7277 | |
| | 0.8063 | 4.0 | 48 | 0.2922 | 0.8483 | 0.4000 | 0.9 | 0.2571 | 0.8726 | |
| | 0.5137 | 5.0 | 60 | 0.8611 | 0.3567 | 0.1487 | 1.0 | 0.0803 | 0.6592 | |
| | 0.3056 | 6.0 | 72 | 0.9956 | 0.5337 | 0.1942 | 1.0 | 0.1075 | 0.7530 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.46.3 |
| - Pytorch 2.4.1+cu121 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.3 |
| |
