---
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: angela_punc_diacritics_eval
  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. -->

# angela_punc_diacritics_eval

This model is a fine-tuned version of [Davlan/afro-xlmr-base](https://huggingface.co./Davlan/afro-xlmr-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4701
- Precision: 0.3989
- Recall: 0.1391
- F1: 0.2063
- Accuracy: 0.8917

## 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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.1546        | 1.0   | 1283 | 0.3076          | 0.3776    | 0.0726 | 0.1217 | 0.8920   |
| 0.1327        | 2.0   | 2566 | 0.3372          | 0.4254    | 0.0843 | 0.1407 | 0.8932   |
| 0.1147        | 3.0   | 3849 | 0.3472          | 0.4208    | 0.1170 | 0.1831 | 0.8932   |
| 0.0934        | 4.0   | 5132 | 0.4240          | 0.4193    | 0.1219 | 0.1889 | 0.8932   |
| 0.0773        | 5.0   | 6415 | 0.4701          | 0.3989    | 0.1391 | 0.2063 | 0.8917   |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3