<!-- 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-base-finetuned-hausa
This model is a fine-tuned version of castorini/afriberta_base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1401
- Precision: 0.7156
- Recall: 0.5251
- F1: 0.6057
- Accuracy: 0.9655
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 |
|---|---|---|---|---|---|---|---|
| 0.1381 | 1.0 | 2624 | 0.1277 | 0.6804 | 0.4403 | 0.5346 | 0.9607 |
| 0.1113 | 2.0 | 5248 | 0.1198 | 0.6803 | 0.4994 | 0.5760 | 0.9628 |
| 0.0861 | 3.0 | 7872 | 0.1270 | 0.7102 | 0.5052 | 0.5904 | 0.9645 |
| 0.0723 | 4.0 | 10496 | 0.1322 | 0.7188 | 0.5134 | 0.5990 | 0.9654 |
| 0.0602 | 5.0 | 13120 | 0.1401 | 0.7156 | 0.5251 | 0.6057 | 0.9655 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
