---
license: mit
tags:
- text-classification
- generated_from_trainer
datasets:
- paws-x
metrics:
- accuracy
model-index:
- name: paws_x_xlm_r_only_de
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: paws-x
      type: paws-x
      config: de
      split: train
      args: de
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.87
---

<!-- 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. -->

# paws_x_xlm_r_only_de

This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the paws-x dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5602
- Accuracy: 0.87

## 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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4751        | 1.0   | 386  | 0.4272          | 0.826    |
| 0.2308        | 2.0   | 772  | 0.3728          | 0.8575   |
| 0.1753        | 3.0   | 1158 | 0.4369          | 0.845    |
| 0.1387        | 4.0   | 1544 | 0.3616          | 0.8645   |
| 0.1169        | 5.0   | 1930 | 0.4507          | 0.8635   |
| 0.0975        | 6.0   | 2316 | 0.4476          | 0.8595   |
| 0.0829        | 7.0   | 2702 | 0.5073          | 0.8675   |
| 0.072         | 8.0   | 3088 | 0.5038          | 0.8655   |
| 0.0626        | 9.0   | 3474 | 0.5009          | 0.868    |
| 0.0562        | 10.0  | 3860 | 0.5602          | 0.87     |


### Framework versions

- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1