metadata
library_name: transformers
license: apache-2.0
base_model: AnonymousCS/populism_multilingual_bert
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: populism_model28
results: []
populism_model28
This model is a fine-tuned version of AnonymousCS/populism_multilingual_bert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4426
- Accuracy: 0.9204
- F1: 0.4943
- Recall: 0.6337
- Precision: 0.4052
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 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
|---|---|---|---|---|---|---|---|
| 0.5546 | 1.0 | 88 | 0.4400 | 0.8873 | 0.4015 | 0.6163 | 0.2978 |
| 0.3532 | 2.0 | 176 | 0.4000 | 0.9219 | 0.4672 | 0.5581 | 0.4017 |
| 0.2932 | 3.0 | 264 | 0.3958 | 0.9090 | 0.4807 | 0.6860 | 0.3699 |
| 0.224 | 4.0 | 352 | 0.4125 | 0.9144 | 0.4979 | 0.6919 | 0.3889 |
| 0.2034 | 5.0 | 440 | 0.4426 | 0.9204 | 0.4943 | 0.6337 | 0.4052 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0