<!-- 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-hausa-5e-5
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: 0.1680
- Precision: 0.7001
- Recall: 0.5395
- F1: 0.6094
- Accuracy: 0.9652
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 |
---|---|---|---|---|---|---|---|
0.1427 | 1.0 | 1312 | 0.1258 | 0.6868 | 0.4660 | 0.5553 | 0.9615 |
0.1042 | 2.0 | 2624 | 0.1183 | 0.6965 | 0.5150 | 0.5921 | 0.9639 |
0.0719 | 3.0 | 3936 | 0.1317 | 0.6943 | 0.5336 | 0.6034 | 0.9646 |
0.048 | 4.0 | 5248 | 0.1490 | 0.7099 | 0.5229 | 0.6022 | 0.9650 |
0.0341 | 5.0 | 6560 | 0.1680 | 0.7001 | 0.5395 | 0.6094 | 0.9652 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3