| --- |
| library_name: transformers |
| license: mit |
| base_model: AnonymousCS/populism_multilingual_roberta_base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: populism_classifier_bsample_235 |
| 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_235 |
| |
| This model is a fine-tuned version of [AnonymousCS/populism_multilingual_roberta_base](https://huggingface.co/AnonymousCS/populism_multilingual_roberta_base) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.9723 |
| - Accuracy: 0.6953 |
| - 1-f1: 0.2263 |
| - 1-recall: 0.9338 |
| - 1-precision: 0.1288 |
| - Balanced Acc: 0.8086 |
| |
| ## 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: 1e-05 |
| - train_batch_size: 32 |
| - eval_batch_size: 32 |
| - 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: 20 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:| |
| | 0.2215 | 1.0 | 167 | 1.2513 | 0.2303 | 0.1102 | 0.9985 | 0.0583 | 0.5951 | |
| | 0.2192 | 2.0 | 334 | 0.9871 | 0.4950 | 0.1555 | 0.9744 | 0.0845 | 0.7227 | |
| | 0.2565 | 3.0 | 501 | 0.9863 | 0.6052 | 0.1847 | 0.9368 | 0.1024 | 0.7627 | |
| | 0.1831 | 4.0 | 668 | 1.0533 | 0.6338 | 0.1945 | 0.9263 | 0.1086 | 0.7727 | |
| | 0.0799 | 5.0 | 835 | 0.7577 | 0.7237 | 0.2352 | 0.8902 | 0.1355 | 0.8028 | |
| | 0.0769 | 6.0 | 1002 | 0.9875 | 0.6611 | 0.2088 | 0.9368 | 0.1175 | 0.7921 | |
| | 0.0708 | 7.0 | 1169 | 0.7383 | 0.7561 | 0.2613 | 0.9038 | 0.1527 | 0.8262 | |
| | 0.0419 | 8.0 | 1336 | 0.8412 | 0.7274 | 0.2437 | 0.9203 | 0.1405 | 0.8190 | |
| | 0.1823 | 9.0 | 1503 | 0.9723 | 0.6953 | 0.2263 | 0.9338 | 0.1288 | 0.8086 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.46.3 |
| - Pytorch 2.4.1+cu121 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.3 |
| |
