populism_classifier_257
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: 0.4069
- Accuracy: 0.9052
- 1-f1: 0.5373
- 1-recall: 0.6923
- 1-precision: 0.4390
- Balanced Acc: 0.8079
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|---|---|---|---|
| 0.2763 | 1.0 | 21 | 0.3126 | 0.8746 | 0.5060 | 0.8077 | 0.3684 | 0.8440 |
| 0.1755 | 2.0 | 42 | 0.4412 | 0.9083 | 0.5161 | 0.6154 | 0.4444 | 0.7745 |
| 0.1167 | 3.0 | 63 | 0.4087 | 0.9205 | 0.5517 | 0.6154 | 0.5 | 0.7811 |
| 0.0897 | 4.0 | 84 | 0.4069 | 0.9052 | 0.5373 | 0.6923 | 0.4390 | 0.8079 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 10