<!-- 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-small-finetuned-hausa-2e-4
This model is a fine-tuned version of castorini/afriberta_small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2081
- Precision: 0.6383
- Recall: 0.4793
- F1: 0.5475
- Accuracy: 0.9589
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 |
---|---|---|---|---|---|---|---|
0.1575 | 1.0 | 1312 | 0.1439 | 0.6452 | 0.3971 | 0.4917 | 0.9569 |
0.1201 | 2.0 | 2624 | 0.1371 | 0.6344 | 0.4451 | 0.5231 | 0.9578 |
0.0831 | 3.0 | 3936 | 0.1544 | 0.6444 | 0.4727 | 0.5454 | 0.9591 |
0.0523 | 4.0 | 5248 | 0.1836 | 0.6500 | 0.4683 | 0.5444 | 0.9592 |
0.0318 | 5.0 | 6560 | 0.2081 | 0.6383 | 0.4793 | 0.5475 | 0.9589 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3