<!-- 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-hausa-5e-5
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: 0.1657
- Precision: 0.6982
- Recall: 0.5348
- F1: 0.6056
- Accuracy: 0.9648
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: 5e-05
- 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 |
---|---|---|---|---|---|---|---|
0.1444 | 1.0 | 1312 | 0.1255 | 0.6832 | 0.4535 | 0.5452 | 0.9612 |
0.1065 | 2.0 | 2624 | 0.1204 | 0.6788 | 0.5101 | 0.5824 | 0.9631 |
0.0752 | 3.0 | 3936 | 0.1303 | 0.6818 | 0.5248 | 0.5931 | 0.9635 |
0.0529 | 4.0 | 5248 | 0.1461 | 0.6963 | 0.5307 | 0.6023 | 0.9648 |
0.0386 | 5.0 | 6560 | 0.1657 | 0.6982 | 0.5348 | 0.6056 | 0.9648 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3