| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: AnonymousCS/populism_multilingual_bert_uncased_v2 |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: populism_classifier_bsample_180 |
| 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_180 |
| |
| This model is a fine-tuned version of [AnonymousCS/populism_multilingual_bert_uncased_v2](https://huggingface.co/AnonymousCS/populism_multilingual_bert_uncased_v2) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.6209 |
| - Accuracy: 0.8519 |
| - 1-f1: 0.4375 |
| - 1-recall: 1.0 |
| - 1-precision: 0.28 |
| - Balanced Acc: 0.9214 |
| |
| ## 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 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:| |
| | 0.0568 | 1.0 | 7 | 0.5297 | 0.8333 | 0.4088 | 1.0 | 0.2569 | 0.9116 | |
| | 0.0433 | 2.0 | 14 | 0.5274 | 0.8436 | 0.4242 | 1.0 | 0.2692 | 0.9170 | |
| | 0.0254 | 3.0 | 21 | 0.5235 | 0.8580 | 0.448 | 1.0 | 0.2887 | 0.9247 | |
| | 0.0028 | 4.0 | 28 | 0.6784 | 0.8272 | 0.4 | 1.0 | 0.25 | 0.9083 | |
| | 0.0289 | 5.0 | 35 | 0.5078 | 0.8642 | 0.45 | 0.9643 | 0.2935 | 0.9112 | |
| | 0.0283 | 6.0 | 42 | 0.4661 | 0.8868 | 0.4860 | 0.9286 | 0.3291 | 0.9064 | |
| | 0.0022 | 7.0 | 49 | 0.6075 | 0.8498 | 0.4341 | 1.0 | 0.2772 | 0.9203 | |
| | 0.0016 | 8.0 | 56 | 0.6209 | 0.8519 | 0.4375 | 1.0 | 0.28 | 0.9214 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.46.3 |
| - Pytorch 2.4.1+cu121 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.3 |
| |
