<!-- 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-2e-4
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: 0.1932
- Precision: 0.6526
- Recall: 0.4876
- F1: 0.5582
- Accuracy: 0.9598
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: 0.0002
- 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 |
---|---|---|---|---|---|---|---|
0.1621 | 1.0 | 1312 | 0.1475 | 0.6104 | 0.3726 | 0.4628 | 0.9544 |
0.1293 | 2.0 | 2624 | 0.1408 | 0.6209 | 0.4396 | 0.5148 | 0.9568 |
0.0954 | 3.0 | 3936 | 0.1479 | 0.6442 | 0.4594 | 0.5363 | 0.9584 |
0.0621 | 4.0 | 5248 | 0.1717 | 0.6615 | 0.4769 | 0.5542 | 0.9599 |
0.0372 | 5.0 | 6560 | 0.1932 | 0.6526 | 0.4876 | 0.5582 | 0.9598 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3