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_173
results: []
populism_classifier_bsample_173
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: 0.9122
- Accuracy: 0.8059
- 1-f1: 0.2774
- 1-recall: 0.8636
- 1-precision: 0.1652
- Balanced Acc: 0.8335
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 |
|---|---|---|---|---|---|---|---|---|
| 0.1673 | 1.0 | 7 | 1.0145 | 0.7412 | 0.2326 | 0.9091 | 0.1333 | 0.8213 |
| 0.0216 | 2.0 | 14 | 0.9962 | 0.7549 | 0.2424 | 0.9091 | 0.1399 | 0.8285 |
| 0.029 | 3.0 | 21 | 0.7441 | 0.8314 | 0.2951 | 0.8182 | 0.18 | 0.8251 |
| 0.0125 | 4.0 | 28 | 0.8679 | 0.7980 | 0.2695 | 0.8636 | 0.1597 | 0.8294 |
| 0.0192 | 5.0 | 35 | 0.9122 | 0.8059 | 0.2774 | 0.8636 | 0.1652 | 0.8335 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3