metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_093
results: []
populism_classifier_093
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3474
- Accuracy: 0.95
- 1-f1: 0.6780
- 1-recall: 0.7692
- 1-precision: 0.6061
- Balanced Acc: 0.8663
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 |
|---|---|---|---|---|---|---|---|---|
| 0.175 | 1.0 | 12 | 0.2873 | 0.9289 | 0.6087 | 0.8077 | 0.4884 | 0.8728 |
| 0.3096 | 2.0 | 24 | 0.3289 | 0.9395 | 0.6349 | 0.7692 | 0.5405 | 0.8606 |
| 0.1172 | 3.0 | 36 | 0.3474 | 0.95 | 0.6780 | 0.7692 | 0.6061 | 0.8663 |
Framework versions
- Transformers 4.56.0.dev0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4