---
license: mit
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-de
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: xtreme
      type: xtreme
      args: PAN-X.de
    metrics:
    - name: F1
      type: f1
      value: 0.8786639400136332
---

<!-- 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. -->

# xlm-roberta-base-finetuned-panx-de

This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2182
- F1: 0.8787

## 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: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1     |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2639        | 1.0   | 525  | 0.1798          | 0.8056 |
| 0.1404        | 2.0   | 1050 | 0.1577          | 0.8370 |
| 0.0994        | 3.0   | 1575 | 0.1451          | 0.8554 |
| 0.0721        | 4.0   | 2100 | 0.1516          | 0.8532 |
| 0.0518        | 5.0   | 2625 | 0.1648          | 0.8630 |
| 0.0341        | 6.0   | 3150 | 0.1926          | 0.8706 |
| 0.024         | 7.0   | 3675 | 0.1911          | 0.8721 |
| 0.0153        | 8.0   | 4200 | 0.2029          | 0.8773 |
| 0.0097        | 9.0   | 4725 | 0.2146          | 0.8773 |
| 0.0075        | 10.0  | 5250 | 0.2182          | 0.8787 |


### Framework versions

- Transformers 4.16.2
- Pytorch 2.8.0+cu126
- Datasets 1.16.1
- Tokenizers 0.22.1