afro-xlmr-mini-finetuned-hausa
This model is a fine-tuned version of Davlan/afro-xlmr-mini on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1501
- Precision: 0.6859
- Recall: 0.4724
- F1: 0.5594
- Accuracy: 0.9527
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: 2e-05
- train_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|
| 0.1925 | 1.0 | 2624 | 0.1785 | 0.5860 | 0.3614 | 0.4470 | 0.9429 |
| 0.1674 | 2.0 | 5248 | 0.1608 | 0.6530 | 0.4409 | 0.5264 | 0.9486 |
| 0.1482 | 3.0 | 7872 | 0.1561 | 0.6909 | 0.4396 | 0.5373 | 0.9513 |
| 0.1439 | 4.0 | 10496 | 0.1493 | 0.6775 | 0.4678 | 0.5534 | 0.9520 |
| 0.1351 | 5.0 | 13120 | 0.1501 | 0.6859 | 0.4724 | 0.5594 | 0.9527 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.