populism_classifier_bsample_330
This model is a fine-tuned version of AnonymousCS/populism_english_bert_large_cased on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8806
- Accuracy: 0.7623
- 1-f1: 0.3310
- 1-recall: 1.0
- 1-precision: 0.1983
- Balanced Acc: 0.8737
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 |
| 0.0399 |
1.0 |
6 |
0.5833 |
0.8015 |
0.3721 |
1.0 |
0.2286 |
0.8945 |
| 0.0832 |
2.0 |
12 |
0.4366 |
0.8505 |
0.4190 |
0.9167 |
0.2716 |
0.8815 |
| 0.0031 |
3.0 |
18 |
0.6716 |
0.8064 |
0.3780 |
1.0 |
0.2330 |
0.8971 |
| 0.0016 |
4.0 |
24 |
0.8806 |
0.7623 |
0.3310 |
1.0 |
0.1983 |
0.8737 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="AnonymousCS/populism_classifier_bsample_330")