<!-- 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-2e-4
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: 0.1942
- Precision: 0.6512
- Recall: 0.4930
- F1: 0.5612
- Accuracy: 0.9599
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 |
---|---|---|---|---|---|---|---|
0.161 | 1.0 | 1312 | 0.1442 | 0.6387 | 0.3751 | 0.4727 | 0.9560 |
0.1238 | 2.0 | 2624 | 0.1386 | 0.6071 | 0.4600 | 0.5234 | 0.9563 |
0.0896 | 3.0 | 3936 | 0.1441 | 0.6555 | 0.4665 | 0.5451 | 0.9593 |
0.0583 | 4.0 | 5248 | 0.1718 | 0.6591 | 0.4788 | 0.5547 | 0.9598 |
0.0349 | 5.0 | 6560 | 0.1942 | 0.6512 | 0.4930 | 0.5612 | 0.9599 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3