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_model25
results: []
populism_model25
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: 0.2168
- Accuracy: 0.9534
- 1-f1: 0.4390
- 1-recall: 0.6429
- 1-precision: 0.3333
- Balanced Acc: 0.8027
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| 0.3312 | 1.0 | 31 | 0.2755 | 0.8431 | 0.2654 | 1.0 | 0.1530 | 0.9193 |
| 0.2755 | 2.0 | 62 | 0.1991 | 0.9514 | 0.4286 | 0.6429 | 0.3214 | 0.8016 |
| 0.1684 | 3.0 | 93 | 0.2168 | 0.9534 | 0.4390 | 0.6429 | 0.3333 | 0.8027 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0