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_model001
results: []
populism_model001
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: 0.5837
- Accuracy: 0.9486
- 1-f1: 0.4970
- 1-recall: 0.5373
- 1-precision: 0.4622
- Balanced Acc: 0.7532
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 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| 0.3553 | 1.0 | 452 | 0.3167 | 0.9204 | 0.4484 | 0.6837 | 0.3336 | 0.8080 |
| 0.275 | 2.0 | 904 | 0.2959 | 0.9120 | 0.4547 | 0.7760 | 0.3216 | 0.8474 |
| 0.1906 | 3.0 | 1356 | 0.3891 | 0.9431 | 0.4969 | 0.5944 | 0.4269 | 0.7774 |
| 0.1474 | 4.0 | 1808 | 0.4287 | 0.9374 | 0.5 | 0.6618 | 0.4018 | 0.8064 |
| 0.1065 | 5.0 | 2260 | 0.5837 | 0.9486 | 0.4970 | 0.5373 | 0.4622 | 0.7532 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0