---
library_name: transformers
license: mit
base_model: AnonymousCS/populism_multilingual_roberta_base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_236
  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_236

This model is a fine-tuned version of [AnonymousCS/populism_multilingual_roberta_base](https://huggingface.co/AnonymousCS/populism_multilingual_roberta_base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7136
- Accuracy: 0.7639
- 1-f1: 0.1220
- 1-recall: 0.4167
- 1-precision: 0.0714
- Balanced Acc: 0.5974

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
| 0.4056        | 1.0   | 20   | 0.5048          | 0.9607   | 0.0    | 0.0      | 0.0         | 0.5          |
| 0.4879        | 2.0   | 40   | 0.5256          | 0.9508   | 0.0    | 0.0      | 0.0         | 0.4949       |
| 0.3654        | 3.0   | 60   | 0.4942          | 0.9607   | 0.0    | 0.0      | 0.0         | 0.5          |
| 0.3067        | 4.0   | 80   | 0.5256          | 0.9475   | 0.2727 | 0.25     | 0.3         | 0.6131       |
| 0.4163        | 5.0   | 100  | 0.4695          | 0.7869   | 0.1558 | 0.5      | 0.0923      | 0.6493       |
| 0.1399        | 6.0   | 120  | 0.7171          | 0.9344   | 0.0909 | 0.0833   | 0.1         | 0.5263       |
| 0.4091        | 7.0   | 140  | 0.6109          | 0.8590   | 0.1887 | 0.4167   | 0.1220      | 0.6469       |
| 0.2123        | 8.0   | 160  | 0.7136          | 0.7639   | 0.1220 | 0.4167   | 0.0714      | 0.5974       |


### Framework versions

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