---
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: fedcsis_translated-slot_baseline-xlm_r-pl
  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. -->

# fedcsis_translated-slot_baseline-xlm_r-pl

This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the
[leyzer-fedcsis-translated](https://huggingface.co/datasets/cartesinus/leyzer-fedcsis-translated) dataset.

Results on untranslated test set:
- Precision: 0.5909
- Recall: 0.5766
- F1: 0.5836
- Accuracy: 0.7484

It achieves the following results on the evaluation set:
- Loss: 1.0761
- Precision: 0.7299
- Recall: 0.7427
- F1: 0.7363
- Accuracy: 0.8415

## 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: 16
- eval_batch_size: 16
- 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 | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 1.4842        | 1.0   | 814  | 0.7712          | 0.5858    | 0.6026 | 0.5941 | 0.7918   |
| 0.5128        | 2.0   | 1628 | 0.6435          | 0.6469    | 0.6828 | 0.6644 | 0.8119   |
| 0.3526        | 3.0   | 2442 | 0.7030          | 0.6823    | 0.7045 | 0.6933 | 0.8242   |
| 0.2142        | 4.0   | 3256 | 0.7695          | 0.7112    | 0.7243 | 0.7177 | 0.8381   |
| 0.1422        | 5.0   | 4070 | 0.8550          | 0.7203    | 0.7310 | 0.7256 | 0.8399   |
| 0.1188        | 6.0   | 4884 | 0.9209          | 0.7183    | 0.7333 | 0.7258 | 0.8391   |
| 0.0915        | 7.0   | 5698 | 0.9892          | 0.7238    | 0.7372 | 0.7305 | 0.8404   |
| 0.072         | 8.0   | 6512 | 1.0271          | 0.7230    | 0.7364 | 0.7296 | 0.8417   |
| 0.0626        | 9.0   | 7326 | 1.0608          | 0.7312    | 0.7417 | 0.7364 | 0.8419   |
| 0.0613        | 10.0  | 8140 | 1.0761          | 0.7299    | 0.7427 | 0.7363 | 0.8415   |


### Framework versions

- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2