license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics: - precision
- recall
- f1
- accuracy
model-index: - name: unfiltered_no_delete_hausa
results: []
unfiltered_no_delete_hausa
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: 0.1663
- Precision: 0.4098
- Recall: 0.2849
- F1: 0.3361
- Accuracy: 0.9564
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 |
|---|---|---|---|---|---|---|---|
| 0.142 | 1.0 | 1283 | 0.1349 | 0.4609 | 0.1668 | 0.2450 | 0.9595 |
| 0.1249 | 2.0 | 2566 | 0.1338 | 0.4612 | 0.1821 | 0.2611 | 0.9596 |
| 0.1066 | 3.0 | 3849 | 0.1378 | 0.4548 | 0.2305 | 0.3059 | 0.9594 |
| 0.0852 | 4.0 | 5132 | 0.1511 | 0.4003 | 0.2906 | 0.3368 | 0.9555 |
| 0.0688 | 5.0 | 6415 | 0.1663 | 0.4098 | 0.2849 | 0.3361 | 0.9564 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3