populism_classifier_259
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: 0.6682
- Accuracy: 0.9445
- 1-f1: 0.5316
- 1-recall: 0.6
- 1-precision: 0.4773
- Balanced Acc: 0.7818
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 |
|---|---|---|---|---|---|---|---|---|
| 0.3455 | 1.0 | 42 | 0.2947 | 0.9310 | 0.5 | 0.6571 | 0.4035 | 0.8017 |
| 0.2899 | 2.0 | 84 | 0.2864 | 0.8966 | 0.448 | 0.8 | 0.3111 | 0.8509 |
| 0.087 | 3.0 | 126 | 0.3834 | 0.9025 | 0.4348 | 0.7143 | 0.3125 | 0.8136 |
| 0.0262 | 4.0 | 168 | 0.6384 | 0.9415 | 0.5063 | 0.5714 | 0.4545 | 0.7667 |
| 0.0966 | 5.0 | 210 | 0.6682 | 0.9445 | 0.5316 | 0.6 | 0.4773 | 0.7818 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- -