|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- lg-ner |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: luganda-ner-v2 |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: lg-ner |
|
type: lg-ner |
|
config: lug |
|
split: test |
|
args: lug |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.79182156133829 |
|
- name: Recall |
|
type: recall |
|
value: 0.7842415316642121 |
|
- name: F1 |
|
type: f1 |
|
value: 0.788013318534961 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9559346774929295 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# luganda-ner-v2 |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the lg-ner dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3199 |
|
- Precision: 0.7918 |
|
- Recall: 0.7842 |
|
- F1: 0.7880 |
|
- Accuracy: 0.9559 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 261 | 0.2380 | 0.7942 | 0.7106 | 0.7501 | 0.9526 | |
|
| 0.0954 | 2.0 | 522 | 0.2345 | 0.7954 | 0.7872 | 0.7913 | 0.9558 | |
|
| 0.0954 | 3.0 | 783 | 0.2560 | 0.8168 | 0.7518 | 0.7830 | 0.9555 | |
|
| 0.0562 | 4.0 | 1044 | 0.2815 | 0.7261 | 0.7791 | 0.7517 | 0.9477 | |
|
| 0.0562 | 5.0 | 1305 | 0.2738 | 0.7744 | 0.8012 | 0.7875 | 0.9566 | |
|
| 0.0345 | 6.0 | 1566 | 0.2951 | 0.8083 | 0.7732 | 0.7904 | 0.9556 | |
|
| 0.0345 | 7.0 | 1827 | 0.3026 | 0.7741 | 0.7872 | 0.7806 | 0.9547 | |
|
| 0.0215 | 8.0 | 2088 | 0.3062 | 0.8159 | 0.7636 | 0.7889 | 0.9563 | |
|
| 0.0215 | 9.0 | 2349 | 0.3157 | 0.7959 | 0.7813 | 0.7886 | 0.9563 | |
|
| 0.017 | 10.0 | 2610 | 0.3199 | 0.7918 | 0.7842 | 0.7880 | 0.9559 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
