---
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_315
  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_315

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: 1.2852
- Accuracy: 0.9527
- 1-f1: 0.5556
- 1-recall: 0.4
- 1-precision: 0.9091
- Balanced Acc: 0.6984

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
| 0.1878        | 1.0   | 22   | 0.4096          | 0.7485   | 0.3609 | 0.96     | 0.2222      | 0.8458       |
| 0.7696        | 2.0   | 44   | 0.3752          | 0.8846   | 0.5063 | 0.8      | 0.3704      | 0.8457       |
| 0.1811        | 3.0   | 66   | 0.5636          | 0.9201   | 0.5263 | 0.6      | 0.4688      | 0.7728       |
| 0.0429        | 4.0   | 88   | 0.9458          | 0.9556   | 0.6154 | 0.48     | 0.8571      | 0.7368       |
| 0.5734        | 5.0   | 110  | 1.2852          | 0.9527   | 0.5556 | 0.4      | 0.9091      | 0.6984       |


### Framework versions

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