<!-- 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. -->
bert-finetuned-hausa
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1505
- Precision: 0.6680
- Recall: 0.4474
- F1: 0.5359
- Accuracy: 0.9557
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1683 | 1.0 | 2624 | 0.1589 | 0.6480 | 0.3641 | 0.4663 | 0.9513 |
| 0.1446 | 2.0 | 5248 | 0.1509 | 0.6658 | 0.4147 | 0.5111 | 0.9543 |
| 0.1163 | 3.0 | 7872 | 0.1505 | 0.6680 | 0.4474 | 0.5359 | 0.9557 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
