| --- |
| library_name: transformers |
| license: mit |
| base_model: AnonymousCS/populism_xlmr_base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: populism_classifier_bsample_195 |
| 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_195 |
| |
| This model is a fine-tuned version of [AnonymousCS/populism_xlmr_base](https://huggingface.co/AnonymousCS/populism_xlmr_base) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.8624 |
| - Accuracy: 0.0534 |
| - 1-f1: 0.1014 |
| - 1-recall: 1.0 |
| - 1-precision: 0.0534 |
| - Balanced Acc: 0.5 |
| |
| ## 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-06 |
| - train_batch_size: 16 |
| - eval_batch_size: 16 |
| - 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 |
| - lr_scheduler_warmup_ratio: 0.06 |
| - num_epochs: 15 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:| |
| | 0.8175 | 1.0 | 13 | 1.0490 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.7624 | 2.0 | 26 | 1.0185 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.8583 | 3.0 | 39 | 0.9908 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.7144 | 4.0 | 52 | 0.9653 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.718 | 5.0 | 65 | 0.9438 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.7514 | 6.0 | 78 | 0.9251 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.6915 | 7.0 | 91 | 0.9108 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.7727 | 8.0 | 104 | 0.8979 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.7329 | 9.0 | 117 | 0.8895 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.7947 | 10.0 | 130 | 0.8810 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.7162 | 11.0 | 143 | 0.8744 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.679 | 12.0 | 156 | 0.8699 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.7156 | 13.0 | 169 | 0.8664 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.7271 | 14.0 | 182 | 0.8633 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
| | 0.7828 | 15.0 | 195 | 0.8624 | 0.0534 | 0.1014 | 1.0 | 0.0534 | 0.5 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.46.3 |
| - Pytorch 2.4.1+cu121 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.3 |
|
|
