populism_classifier_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: 0.7420
- Accuracy: 0.9087
- 1-f1: 0.4706
- 1-recall: 0.6452
- 1-precision: 0.3704
- Balanced Acc: 0.7858
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 |
|---|---|---|---|---|---|---|---|---|
| 0.4174 | 1.0 | 31 | 0.5382 | 0.9270 | 0.5 | 0.5806 | 0.4390 | 0.7654 |
| 0.1427 | 2.0 | 62 | 0.4422 | 0.8925 | 0.4301 | 0.6452 | 0.3226 | 0.7771 |
| 0.4868 | 3.0 | 93 | 0.5921 | 0.8276 | 0.3511 | 0.7419 | 0.23 | 0.7876 |
| 0.1021 | 4.0 | 124 | 0.5246 | 0.9067 | 0.4773 | 0.6774 | 0.3684 | 0.7997 |
| 0.0746 | 5.0 | 155 | 0.7420 | 0.9087 | 0.4706 | 0.6452 | 0.3704 | 0.7858 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- -