populism_classifier_253
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: 0.2440
- Accuracy: 0.9721
- 1-f1: 0.6512
- 1-recall: 0.7368
- 1-precision: 0.5833
- Balanced Acc: 0.8588
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 |
|---|---|---|---|---|---|---|---|---|
| 0.4177 | 1.0 | 34 | 0.1625 | 0.9610 | 0.6038 | 0.8421 | 0.4706 | 0.9037 |
| 0.0548 | 2.0 | 68 | 0.1895 | 0.9740 | 0.6667 | 0.7368 | 0.6087 | 0.8598 |
| 0.0867 | 3.0 | 102 | 0.2083 | 0.9740 | 0.6818 | 0.7895 | 0.6 | 0.8851 |
| 0.0598 | 4.0 | 136 | 0.2440 | 0.9721 | 0.6512 | 0.7368 | 0.5833 | 0.8588 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- -