metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
model-index:
- name: populism_model14
results: []
populism_model14
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4686
- Accuracy: 0.8846
- F1: 0.4935
- Recall: 0.7037
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 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 11 | 0.3736 | 0.8609 | 0.4946 | 0.8519 |
| No log | 2.0 | 22 | 0.3838 | 0.8491 | 0.4632 | 0.8148 |
| No log | 3.0 | 33 | 0.3863 | 0.8521 | 0.4681 | 0.8148 |
| No log | 4.0 | 44 | 0.4882 | 0.8964 | 0.5070 | 0.6667 |
| 0.2997 | 5.0 | 55 | 0.4686 | 0.8846 | 0.4935 | 0.7037 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0