metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_bsample_027
results: []
populism_classifier_bsample_027
This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6278
- Accuracy: 0.8051
- 1-f1: 0.3155
- 1-recall: 0.9414
- 1-precision: 0.1895
- Balanced Acc: 0.8698
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: 32
- eval_batch_size: 32
- 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: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| 0.1822 | 1.0 | 167 | 1.1261 | 0.5216 | 0.1655 | 0.9940 | 0.0903 | 0.7460 |
| 0.0917 | 2.0 | 334 | 0.6039 | 0.7504 | 0.2638 | 0.9368 | 0.1535 | 0.8389 |
| 0.118 | 3.0 | 501 | 0.6889 | 0.7300 | 0.2539 | 0.9624 | 0.1462 | 0.8404 |
| 0.3814 | 4.0 | 668 | 0.4434 | 0.8794 | 0.3885 | 0.8030 | 0.2562 | 0.8431 |
| 0.0625 | 5.0 | 835 | 0.6553 | 0.8022 | 0.3086 | 0.9248 | 0.1852 | 0.8604 |
| 0.0409 | 6.0 | 1002 | 0.6278 | 0.8051 | 0.3155 | 0.9414 | 0.1895 | 0.8698 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3