<!-- 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. -->
afro-xlmr-base-hausa-seed-20
This model is a fine-tuned version of Davlan/afro-xlmr-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1634
- Precision: 0.7249
- Recall: 0.5600
- F1: 0.6319
- Accuracy: 0.9590
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 |
|---|---|---|---|---|---|---|---|
| 0.1613 | 1.0 | 1312 | 0.1389 | 0.6893 | 0.4698 | 0.5588 | 0.9526 |
| 0.1226 | 2.0 | 2624 | 0.1359 | 0.7030 | 0.5383 | 0.6098 | 0.9565 |
| 0.0938 | 3.0 | 3936 | 0.1434 | 0.7376 | 0.5205 | 0.6103 | 0.9577 |
| 0.0725 | 4.0 | 5248 | 0.1498 | 0.7322 | 0.5491 | 0.6276 | 0.9590 |
| 0.0589 | 5.0 | 6560 | 0.1634 | 0.7249 | 0.5600 | 0.6319 | 0.9590 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
