---
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_bsample_119
  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_bsample_119

This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8715
- Accuracy: 0.6158
- 1-f1: 0.3105
- 1-recall: 1.0
- 1-precision: 0.1838
- Balanced Acc: 0.7897

## 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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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: 15
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1   | 1-recall | 1-precision | Balanced Acc |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
| 0.6817        | 1.0   | 11   | 0.8455          | 0.0865   | 0.1593 | 1.0      | 0.0865      | 0.5          |
| 0.6879        | 2.0   | 22   | 0.7567          | 0.3410   | 0.2080 | 1.0      | 0.1160      | 0.6393       |
| 0.6883        | 3.0   | 33   | 0.4163          | 0.8499   | 0.4587 | 0.7353   | 0.3333      | 0.7980       |
| 0.197         | 4.0   | 44   | 0.3296          | 0.8753   | 0.5505 | 0.8824   | 0.4         | 0.8785       |
| 0.329         | 5.0   | 55   | 0.7855          | 0.7863   | 0.44   | 0.9706   | 0.2845      | 0.8697       |
| 0.3333        | 6.0   | 66   | 1.8715          | 0.6158   | 0.3105 | 1.0      | 0.1838      | 0.7897       |


### Framework versions

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