metadata
library_name: transformers
license: apache-2.0
base_model: AnonymousCS/populism_multilingual_bert_uncased_v2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_bsample_167
results: []
populism_classifier_bsample_167
This model is a fine-tuned version of AnonymousCS/populism_multilingual_bert_uncased_v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3828
- Accuracy: 0.9056
- 1-f1: 0.5273
- 1-recall: 0.9062
- 1-precision: 0.3718
- Balanced Acc: 0.9059
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 |
|---|---|---|---|---|---|---|---|---|
| 0.0543 | 1.0 | 6 | 0.4610 | 0.9310 | 0.5581 | 0.75 | 0.4444 | 0.8461 |
| 0.0721 | 2.0 | 12 | 0.4254 | 0.9201 | 0.5217 | 0.75 | 0.4 | 0.8403 |
| 0.0486 | 3.0 | 18 | 0.4625 | 0.8566 | 0.4476 | 1.0 | 0.2883 | 0.9239 |
| 0.0197 | 4.0 | 24 | 0.3800 | 0.8966 | 0.5289 | 1.0 | 0.3596 | 0.9451 |
| 0.0071 | 5.0 | 30 | 0.3595 | 0.9056 | 0.5094 | 0.8438 | 0.3649 | 0.8766 |
| 0.0302 | 6.0 | 36 | 0.3587 | 0.9038 | 0.5225 | 0.9062 | 0.3671 | 0.9050 |
| 0.0069 | 7.0 | 42 | 0.3618 | 0.9056 | 0.5185 | 0.875 | 0.3684 | 0.8913 |
| 0.0029 | 8.0 | 48 | 0.3828 | 0.9056 | 0.5273 | 0.9062 | 0.3718 | 0.9059 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3