| --- |
| library_name: transformers |
| license: mit |
| base_model: AnonymousCS/populism_multilingual_roberta_base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: populism_classifier_bsample_240 |
| 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_240 |
| |
| 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: 0.9436 |
| - Accuracy: 0.7955 |
| - 1-f1: 0.3415 |
| - 1-recall: 0.8485 |
| - 1-precision: 0.2137 |
| - Balanced Acc: 0.8202 |
| |
| ## 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 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:| |
| | 0.0519 | 1.0 | 8 | 0.8375 | 0.7765 | 0.3218 | 0.8485 | 0.1986 | 0.8101 | |
| | 0.015 | 2.0 | 16 | 1.0175 | 0.7008 | 0.2818 | 0.9394 | 0.1658 | 0.8121 | |
| | 0.0228 | 3.0 | 24 | 0.6612 | 0.8371 | 0.3944 | 0.8485 | 0.2569 | 0.8424 | |
| | 0.0207 | 4.0 | 32 | 0.8965 | 0.7576 | 0.3191 | 0.9091 | 0.1935 | 0.8283 | |
| | 0.0083 | 5.0 | 40 | 0.9436 | 0.7955 | 0.3415 | 0.8485 | 0.2137 | 0.8202 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.46.3 |
| - Pytorch 2.4.1+cu121 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.3 |
| |
