metadata
library_name: transformers
license: apache-2.0
base_model: AnonymousCS/populism_english_bert_large_uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_bsample_373
results: []
populism_classifier_bsample_373
This model is a fine-tuned version of AnonymousCS/populism_english_bert_large_uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8096
- Accuracy: 0.8241
- 1-f1: 0.3281
- 1-recall: 0.7778
- 1-precision: 0.2079
- Balanced Acc: 0.8023
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 |
|---|---|---|---|---|---|---|---|---|
| 0.053 | 1.0 | 7 | 0.7568 | 0.8078 | 0.3188 | 0.8148 | 0.1982 | 0.8111 |
| 0.0089 | 2.0 | 14 | 1.4364 | 0.5951 | 0.2016 | 0.9259 | 0.1131 | 0.7508 |
| 0.123 | 3.0 | 21 | 0.8096 | 0.8241 | 0.3281 | 0.7778 | 0.2079 | 0.8023 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3