metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_model0
results: []
populism_model0
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: 0.4208
- Accuracy: 0.8688
- 1-f1: 0.3284
- 1-recall: 0.6588
- 1-precision: 0.2188
- Balanced Acc: 0.7692
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 | 1-f1 | 1-recall | 1-precision | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| 0.4957 | 1.0 | 55 | 0.5050 | 0.8682 | 0.2722 | 0.5059 | 0.1861 | 0.6963 |
| 0.4629 | 2.0 | 110 | 0.4640 | 0.7788 | 0.2548 | 0.7765 | 0.1524 | 0.7777 |
| 0.3876 | 3.0 | 165 | 0.4342 | 0.7851 | 0.2802 | 0.8588 | 0.1674 | 0.8201 |
| 0.3452 | 4.0 | 220 | 0.4179 | 0.8911 | 0.3493 | 0.6 | 0.2464 | 0.7530 |
| 0.3012 | 5.0 | 275 | 0.4208 | 0.8688 | 0.3284 | 0.6588 | 0.2188 | 0.7692 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0