| | --- |
| | library_name: transformers |
| | license: mit |
| | base_model: AnonymousCS/populism_multilingual_roberta_base |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - accuracy |
| | model-index: |
| | - name: populism_classifier_248 |
| | 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_248 |
| |
|
| | 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: 0.2247 |
| | - Accuracy: 0.9833 |
| | - 1-f1: 0.7481 |
| | - 1-recall: 0.8596 |
| | - 1-precision: 0.6622 |
| | - Balanced Acc: 0.9233 |
| |
|
| | ## 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: 64 |
| | - eval_batch_size: 64 |
| | - 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 | |
| | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:| |
| | | 0.4461 | 1.0 | 124 | 0.3656 | 0.9737 | 0.3953 | 0.2982 | 0.5862 | 0.6460 | |
| | | 0.1764 | 2.0 | 248 | 0.3212 | 0.9722 | 0.4211 | 0.3509 | 0.5263 | 0.6707 | |
| | | 0.1825 | 3.0 | 372 | 0.2600 | 0.9615 | 0.4722 | 0.5965 | 0.3908 | 0.7844 | |
| | | 0.0418 | 4.0 | 496 | 0.3632 | 0.9787 | 0.5532 | 0.4561 | 0.7027 | 0.7252 | |
| | | 0.0178 | 5.0 | 620 | 0.1983 | 0.9803 | 0.6929 | 0.7719 | 0.6286 | 0.8792 | |
| | | 0.0888 | 6.0 | 744 | 0.1902 | 0.9747 | 0.6622 | 0.8596 | 0.5385 | 0.9189 | |
| | | 0.001 | 7.0 | 868 | 0.2618 | 0.9863 | 0.7429 | 0.6842 | 0.8125 | 0.8398 | |
| | | 0.0388 | 8.0 | 992 | 0.1879 | 0.9838 | 0.7576 | 0.8772 | 0.6667 | 0.9321 | |
| | | 0.0127 | 9.0 | 1116 | 0.2108 | 0.9904 | 0.8319 | 0.8246 | 0.8393 | 0.9099 | |
| | | 0.0557 | 10.0 | 1240 | 0.2210 | 0.9894 | 0.8235 | 0.8596 | 0.7903 | 0.9264 | |
| | | 0.0004 | 11.0 | 1364 | 0.2247 | 0.9833 | 0.7481 | 0.8596 | 0.6622 | 0.9233 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.46.3 |
| | - Pytorch 2.4.1+cu121 |
| | - Datasets 3.1.0 |
| | - Tokenizers 0.20.3 |
| |
|
