|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: bert-base-multilingual-cased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: sindhi-bert-ner |
|
|
results: [] |
|
|
datasets: |
|
|
- mirfan899/sindhi-ner |
|
|
language: |
|
|
- sd |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# sindhi-bert-ner |
|
|
|
|
|
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1513 |
|
|
- Precision: 0.7080 |
|
|
- Recall: 0.6443 |
|
|
- F1: 0.6746 |
|
|
- Accuracy: 0.9704 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 0.1578 | 1.0 | 2252 | 0.1457 | 0.7162 | 0.5285 | 0.6082 | 0.9640 | |
|
|
| 0.1162 | 2.0 | 4504 | 0.1280 | 0.7296 | 0.5718 | 0.6411 | 0.9676 | |
|
|
| 0.097 | 3.0 | 6756 | 0.1248 | 0.7040 | 0.6065 | 0.6516 | 0.9678 | |
|
|
| 0.0803 | 4.0 | 9008 | 0.1265 | 0.7442 | 0.6078 | 0.6691 | 0.9707 | |
|
|
| 0.0719 | 5.0 | 11260 | 0.1274 | 0.7459 | 0.6181 | 0.6760 | 0.9707 | |
|
|
| 0.056 | 6.0 | 13512 | 0.1333 | 0.7083 | 0.6383 | 0.6715 | 0.9704 | |
|
|
| 0.0507 | 7.0 | 15764 | 0.1339 | 0.7157 | 0.6378 | 0.6745 | 0.9709 | |
|
|
| 0.0441 | 8.0 | 18016 | 0.1445 | 0.7308 | 0.6284 | 0.6758 | 0.9710 | |
|
|
| 0.0377 | 9.0 | 20268 | 0.1487 | 0.7253 | 0.6307 | 0.6747 | 0.9705 | |
|
|
| 0.0344 | 10.0 | 22520 | 0.1513 | 0.7080 | 0.6443 | 0.6746 | 0.9704 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.0 |
|
|
- Pytorch 2.0.0 |
|
|
- Datasets 2.14.5 |
|
|
- Tokenizers 0.13.3 |
