---
library_name: transformers
license: apache-2.0
base_model: AnonymousCS/populism_english_bert_large_cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_331
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# populism_classifier_331

This model is a fine-tuned version of [AnonymousCS/populism_english_bert_large_cased](https://huggingface.co/AnonymousCS/populism_english_bert_large_cased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3609
- Accuracy: 0.9703
- 1-f1: 0.6522
- 1-recall: 0.7895
- 1-precision: 0.5556
- Balanced Acc: 0.8832

## 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: 64
- eval_batch_size: 64
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
| 0.3374        | 1.0   | 34   | 0.1473          | 0.9703   | 0.6800 | 0.8947   | 0.5484      | 0.9339       |
| 0.0648        | 2.0   | 68   | 0.3446          | 0.9758   | 0.6061 | 0.5263   | 0.7143      | 0.7593       |
| 0.0041        | 3.0   | 102  | 0.3145          | 0.9703   | 0.6364 | 0.7368   | 0.56        | 0.8578       |
| 0.0003        | 4.0   | 136  | 0.3609          | 0.9703   | 0.6522 | 0.7895   | 0.5556      | 0.8832       |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3