metadata
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: flipped_2e-5_hausa
results: []
flipped_2e-5_hausa
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: 0.1898
- Precision: 0.4205
- Recall: 0.2644
- F1: 0.3247
- Accuracy: 0.9417
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: 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 |
|---|---|---|---|---|---|---|---|
| 0.1886 | 1.0 | 1283 | 0.1796 | 0.3923 | 0.1576 | 0.2248 | 0.9419 |
| 0.1712 | 2.0 | 2566 | 0.1748 | 0.4347 | 0.2002 | 0.2741 | 0.9436 |
| 0.157 | 3.0 | 3849 | 0.1785 | 0.4346 | 0.2393 | 0.3086 | 0.9432 |
| 0.1439 | 4.0 | 5132 | 0.1838 | 0.4246 | 0.2604 | 0.3228 | 0.9422 |
| 0.1323 | 5.0 | 6415 | 0.1898 | 0.4205 | 0.2644 | 0.3247 | 0.9417 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3