metadata
library_name: transformers
license: apache-2.0
base_model: AnonymousCS/populism_english_bert_base_uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_bsample_357
results: []
populism_classifier_bsample_357
This model is a fine-tuned version of AnonymousCS/populism_english_bert_base_uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4739
- Accuracy: 0.7972
- 1-f1: 0.2695
- 1-recall: 0.95
- 1-precision: 0.1570
- Balanced Acc: 0.8705
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 |
|---|---|---|---|---|---|---|---|---|
| 0.139 | 1.0 | 6 | 0.4716 | 0.8091 | 0.2920 | 1.0 | 0.1709 | 0.9006 |
| 0.0907 | 2.0 | 12 | 0.7459 | 0.7126 | 0.2151 | 1.0 | 0.1205 | 0.8504 |
| 0.0751 | 3.0 | 18 | 0.4739 | 0.7972 | 0.2695 | 0.95 | 0.1570 | 0.8705 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3