metadata
library_name: transformers
license: apache-2.0
base_model: AnonymousCS/populism_multilingual_modernbert_base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_model121
results: []
populism_model121
This model is a fine-tuned version of AnonymousCS/populism_multilingual_modernbert_base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3457
- Accuracy: 0.9135
- 1-f1: 0.4860
- 1-recall: 0.6890
- 1-precision: 0.3754
- Balanced Acc: 0.8083
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 OptimizerNames.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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| 0.388 | 1.0 | 173 | 0.3501 | 0.8175 | 0.3668 | 0.8902 | 0.2310 | 0.8516 |
| 0.2514 | 2.0 | 346 | 0.3263 | 0.8664 | 0.4279 | 0.8415 | 0.2869 | 0.8547 |
| 0.1872 | 3.0 | 519 | 0.3457 | 0.9135 | 0.4860 | 0.6890 | 0.3754 | 0.8083 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0