|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: afriberta-small-hausa-5e-5 |
|
results: [] |
|
--- |
|
|
|
<!-- 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-hausa-5e-5 |
|
|
|
This model is a fine-tuned version of [castorini/afriberta_small](https://huggingface.co/castorini/afriberta_small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1600 |
|
- Precision: 0.6808 |
|
- Recall: 0.4937 |
|
- F1: 0.5724 |
|
- Accuracy: 0.9623 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1523 | 1.0 | 1312 | 0.1338 | 0.6526 | 0.4261 | 0.5156 | 0.9583 | |
|
| 0.1162 | 2.0 | 2624 | 0.1300 | 0.6862 | 0.4603 | 0.5510 | 0.9614 | |
|
| 0.089 | 3.0 | 3936 | 0.1375 | 0.6953 | 0.4630 | 0.5559 | 0.9619 | |
|
| 0.0698 | 4.0 | 5248 | 0.1507 | 0.6860 | 0.4888 | 0.5708 | 0.9623 | |
|
| 0.0559 | 5.0 | 6560 | 0.1600 | 0.6808 | 0.4937 | 0.5724 | 0.9623 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|