metadata
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: angela_shuffle_diacritics_regular_eval
results: []
angela_shuffle_diacritics_regular_eval
This model is a fine-tuned version of Davlan/afro-xlmr-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1666
- Precision: 0.4058
- Recall: 0.2753
- F1: 0.3281
- Accuracy: 0.9565
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 |
|---|---|---|---|---|---|---|---|
| 0.1497 | 1.0 | 1283 | 0.1387 | 0.4515 | 0.1507 | 0.2260 | 0.9593 |
| 0.1272 | 2.0 | 2566 | 0.1329 | 0.4710 | 0.2103 | 0.2908 | 0.9600 |
| 0.1092 | 3.0 | 3849 | 0.1442 | 0.4636 | 0.2263 | 0.3041 | 0.9598 |
| 0.0884 | 4.0 | 5132 | 0.1532 | 0.4088 | 0.2785 | 0.3313 | 0.9565 |
| 0.0708 | 5.0 | 6415 | 0.1666 | 0.4058 | 0.2753 | 0.3281 | 0.9565 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3