---
library_name: transformers
license: mit
base_model: AnonymousCS/populism_multilingual_roberta_base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_244
  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_244

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: 0.6545
- Accuracy: 0.9599
- 1-f1: 0.32
- 1-recall: 0.2759
- 1-precision: 0.3810
- Balanced Acc: 0.6300

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
| 0.571         | 1.0   | 53   | 0.3298          | 0.9328   | 0.4124 | 0.6897   | 0.2941      | 0.8155       |
| 0.2436        | 2.0   | 106  | 0.3316          | 0.9233   | 0.3564 | 0.6207   | 0.25        | 0.7774       |
| 0.1074        | 3.0   | 159  | 0.4049          | 0.9139   | 0.3540 | 0.6897   | 0.2381      | 0.8058       |
| 0.2472        | 4.0   | 212  | 0.6545          | 0.9599   | 0.32   | 0.2759   | 0.3810      | 0.6300       |


### Framework versions

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