---
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: angela_diacritics_shuffle_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_diacritics_shuffle_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: 0.3073
- Precision: 0.4269
- Recall: 0.1883
- F1: 0.2613
- Accuracy: 0.9206

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2305        | 1.0   | 1283 | 0.2759          | 0.3933    | 0.0827 | 0.1367 | 0.9186   |
| 0.2064        | 2.0   | 2566 | 0.2674          | 0.4265    | 0.1068 | 0.1709 | 0.9197   |
| 0.1856        | 3.0   | 3849 | 0.2924          | 0.4325    | 0.1405 | 0.2121 | 0.9201   |
| 0.1688        | 4.0   | 5132 | 0.2899          | 0.4235    | 0.1802 | 0.2528 | 0.9201   |
| 0.1449        | 5.0   | 6415 | 0.3073          | 0.4269    | 0.1883 | 0.2613 | 0.9206   |


### Framework versions

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