populism_classifier_bsample_260
This model is a fine-tuned version of AnonymousCS/populism_multilingual_roberta_base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9377
- Accuracy: 0.7895
- 1-f1: 0.3077
- 1-recall: 0.8889
- 1-precision: 0.1860
- Balanced Acc: 0.8364
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 |
|---|---|---|---|---|---|---|---|---|
| 0.0457 | 1.0 | 8 | 0.8925 | 0.7212 | 0.2353 | 0.8148 | 0.1375 | 0.7654 |
| 0.0358 | 2.0 | 16 | 0.8882 | 0.7251 | 0.2618 | 0.9259 | 0.1524 | 0.8200 |
| 0.0077 | 3.0 | 24 | 1.0150 | 0.7466 | 0.2697 | 0.8889 | 0.1589 | 0.8138 |
| 0.0168 | 4.0 | 32 | 0.9377 | 0.7895 | 0.3077 | 0.8889 | 0.1860 | 0.8364 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- -