metadata
library_name: transformers
license: apache-2.0
base_model: AnonymousCS/populism_english_bert_base_cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_300
results: []
populism_classifier_300
This model is a fine-tuned version of AnonymousCS/populism_english_bert_base_cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2118
- Accuracy: 0.9803
- 1-f1: 0.6723
- 1-recall: 0.7018
- 1-precision: 0.6452
- Balanced Acc: 0.8451
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 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 |
|---|---|---|---|---|---|---|---|---|
| 0.5731 | 1.0 | 62 | 0.3068 | 0.9782 | 0.5981 | 0.5614 | 0.64 | 0.7760 |
| 0.1506 | 2.0 | 124 | 0.1601 | 0.9641 | 0.5697 | 0.8246 | 0.4352 | 0.8964 |
| 0.0665 | 3.0 | 186 | 0.1641 | 0.9494 | 0.5098 | 0.9123 | 0.3537 | 0.9314 |
| 0.1786 | 4.0 | 248 | 0.2118 | 0.9803 | 0.6723 | 0.7018 | 0.6452 | 0.8451 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3