populism_classifier_242
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: 0.6098
- Accuracy: 0.9341
- 1-f1: 0.5818
- 1-recall: 0.5926
- 1-precision: 0.5714
- Balanced Acc: 0.7777
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 |
|---|---|---|---|---|---|---|---|---|
| 0.2926 | 1.0 | 22 | 0.2274 | 0.8739 | 0.5510 | 1.0 | 0.3803 | 0.9317 |
| 0.3213 | 2.0 | 44 | 0.4240 | 0.9284 | 0.6154 | 0.7407 | 0.5263 | 0.8424 |
| 0.0643 | 3.0 | 66 | 0.2893 | 0.8997 | 0.5783 | 0.8889 | 0.4286 | 0.8948 |
| 0.1978 | 4.0 | 88 | 0.6098 | 0.9341 | 0.5818 | 0.5926 | 0.5714 | 0.7777 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- -