---
library_name: transformers
license: apache-2.0
base_model: EuroBERT/EuroBERT-210m
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: EuroBERT-immigration-stance-positive
  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. -->

# EuroBERT-immigration-stance-positive

This model is a fine-tuned version of [EuroBERT/EuroBERT-210m](https://huggingface.co/EuroBERT/EuroBERT-210m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1444
- Accuracy: 0.7389
- F1 Macro: 0.7210
- Accuracy Balanced: 0.7165
- F1 Micro: 0.7389
- Precision Macro: 0.7342
- Recall Macro: 0.7165
- Precision Micro: 0.7389
- Recall Micro: 0.7389

## 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 40
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Accuracy Balanced | F1 Micro | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
| 0.697         | 1.0   | 654  | 0.6768          | 0.5908   | 0.3714   | 0.5               | 0.5908   | 0.2954          | 0.5          | 0.5908          | 0.5908       |
| 0.7267        | 2.0   | 1308 | 0.6543          | 0.5878   | 0.5797   | 0.6340            | 0.5878   | 0.6642          | 0.6340       | 0.5878          | 0.5878       |
| 0.7024        | 3.0   | 1962 | 0.9052          | 0.6779   | 0.6778   | 0.7044            | 0.6779   | 0.7076          | 0.7044       | 0.6779          | 0.6779       |
| 0.675         | 4.0   | 2616 | 1.1944          | 0.7206   | 0.7088   | 0.7073            | 0.7206   | 0.7108          | 0.7073       | 0.7206          | 0.7206       |
| 0.5142        | 5.0   | 3270 | 1.4177          | 0.7160   | 0.7097   | 0.7126            | 0.7160   | 0.7084          | 0.7126       | 0.7160          | 0.7160       |
| 0.3573        | 6.0   | 3924 | 1.6717          | 0.7267   | 0.7159   | 0.7148            | 0.7267   | 0.7172          | 0.7148       | 0.7267          | 0.7267       |
| 0.1643        | 7.0   | 4578 | 1.6307          | 0.7389   | 0.7295   | 0.7292            | 0.7389   | 0.7300          | 0.7292       | 0.7389          | 0.7389       |
| 0.1253        | 8.0   | 5232 | 1.8601          | 0.7374   | 0.7187   | 0.7141            | 0.7374   | 0.7331          | 0.7141       | 0.7374          | 0.7374       |
| 0.0937        | 9.0   | 5886 | 2.0865          | 0.7420   | 0.7209   | 0.7157            | 0.7420   | 0.7412          | 0.7157       | 0.7420          | 0.7420       |
| 0.0562        | 10.0  | 6540 | 2.1444          | 0.7389   | 0.7210   | 0.7165            | 0.7389   | 0.7342          | 0.7165       | 0.7389          | 0.7389       |


### Framework versions

- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1