| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: AnonymousCS/populism_multilingual_bert_cased_v2 |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: populism_classifier_148 |
| 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_148 |
|
|
| This model is a fine-tuned version of [AnonymousCS/populism_multilingual_bert_cased_v2](https://huggingface.co/AnonymousCS/populism_multilingual_bert_cased_v2) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.2107 |
| - Accuracy: 0.9832 |
| - 1-f1: 0.8444 |
| - 1-recall: 0.8636 |
| - 1-precision: 0.8261 |
| - Balanced Acc: 0.9267 |
|
|
| ## 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: 128 |
| - eval_batch_size: 128 |
| - 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 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:| |
| | 0.2092 | 1.0 | 13 | 0.1390 | 0.9159 | 0.5570 | 1.0 | 0.3860 | 0.9556 | |
| | 0.1047 | 2.0 | 26 | 0.1211 | 0.9399 | 0.6377 | 1.0 | 0.4681 | 0.9683 | |
| | 0.035 | 3.0 | 39 | 0.1102 | 0.9688 | 0.7636 | 0.9545 | 0.6364 | 0.9620 | |
| | 0.0368 | 4.0 | 52 | 0.1452 | 0.9784 | 0.8163 | 0.9091 | 0.7407 | 0.9457 | |
| | 0.0269 | 5.0 | 65 | 0.2107 | 0.9832 | 0.8444 | 0.8636 | 0.8261 | 0.9267 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.46.3 |
| - Pytorch 2.4.1+cu121 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.3 |
|
|
