<!-- 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. -->
afriberta-large-finetuned-hausa
This model is a fine-tuned version of castorini/afriberta_large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1448
- Precision: 0.7114
- Recall: 0.5238
- F1: 0.6034
- Accuracy: 0.9652
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: 8
- 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 |
|---|---|---|---|---|---|---|---|
| 0.1373 | 1.0 | 2624 | 0.1267 | 0.6804 | 0.4519 | 0.5431 | 0.9612 |
| 0.1102 | 2.0 | 5248 | 0.1186 | 0.6927 | 0.5020 | 0.5821 | 0.9635 |
| 0.0849 | 3.0 | 7872 | 0.1269 | 0.7114 | 0.5036 | 0.5897 | 0.9645 |
| 0.0683 | 4.0 | 10496 | 0.1341 | 0.7159 | 0.5078 | 0.5941 | 0.9650 |
| 0.0567 | 5.0 | 13120 | 0.1448 | 0.7114 | 0.5238 | 0.6034 | 0.9652 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
