metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_bsample_081
results: []
populism_classifier_bsample_081
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: 0.5385
- Accuracy: 0.8775
- 1-f1: 0.5567
- 1-recall: 0.9
- 1-precision: 0.4030
- Balanced Acc: 0.8877
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| 0.0829 | 1.0 | 11 | 0.4782 | 0.8803 | 0.5625 | 0.9 | 0.4091 | 0.8893 |
| 0.1588 | 2.0 | 22 | 0.4513 | 0.8974 | 0.5610 | 0.7667 | 0.4423 | 0.8382 |
| 0.1521 | 3.0 | 33 | 0.7473 | 0.8348 | 0.5085 | 1.0 | 0.3409 | 0.9097 |
| 0.0496 | 4.0 | 44 | 0.5385 | 0.8775 | 0.5567 | 0.9 | 0.4030 | 0.8877 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3