populism_classifier_258
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: 0.7785
- Accuracy: 0.9467
- 1-f1: 0.5357
- 1-recall: 0.5172
- 1-precision: 0.5556
- Balanced Acc: 0.7455
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 |
|---|---|---|---|---|---|---|---|---|
| 0.9108 | 1.0 | 31 | 0.4081 | 0.9447 | 0.6087 | 0.7241 | 0.525 | 0.8414 |
| 0.1323 | 2.0 | 62 | 0.3606 | 0.9406 | 0.6133 | 0.7931 | 0.5 | 0.8715 |
| 0.0631 | 3.0 | 93 | 0.6827 | 0.9447 | 0.5263 | 0.5172 | 0.5357 | 0.7445 |
| 0.0314 | 4.0 | 124 | 0.6555 | 0.9467 | 0.5517 | 0.5517 | 0.5517 | 0.7617 |
| 0.0312 | 5.0 | 155 | 0.7785 | 0.9467 | 0.5357 | 0.5172 | 0.5556 | 0.7455 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- -