|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: punjabi-roberta-ner |
|
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. --> |
|
|
|
# punjabi-roberta-ner |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an [punjabi-ner](https://huggingface.co/datasets/mirfan899/punjabi-ner) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0638 |
|
- Precision: 0.7625 |
|
- Recall: 0.7844 |
|
- F1: 0.7733 |
|
- Accuracy: 0.9830 |
|
|
|
## 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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1017 | 1.0 | 1613 | 0.0739 | 0.7020 | 0.6731 | 0.6872 | 0.9775 | |
|
| 0.0693 | 2.0 | 3226 | 0.0623 | 0.7695 | 0.7433 | 0.7562 | 0.9824 | |
|
| 0.046 | 3.0 | 4839 | 0.0638 | 0.7625 | 0.7844 | 0.7733 | 0.9830 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
