|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: Amir13/ncbi-persian |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xlm-roberta-base-ncbi_disease |
|
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. --> |
|
|
|
# xlm-roberta-base-ncbi_disease |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the [ncbi-persian](https://huggingface.co/datasets/Amir13/ncbi-persian) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0915 |
|
- Precision: 0.8273 |
|
- Recall: 0.8763 |
|
- F1: 0.8511 |
|
- Accuracy: 0.9866 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 169 | 0.0682 | 0.7049 | 0.7763 | 0.7389 | 0.9784 | |
|
| No log | 2.0 | 338 | 0.0575 | 0.7558 | 0.8592 | 0.8042 | 0.9832 | |
|
| 0.0889 | 3.0 | 507 | 0.0558 | 0.8092 | 0.8592 | 0.8334 | 0.9859 | |
|
| 0.0889 | 4.0 | 676 | 0.0595 | 0.8316 | 0.8579 | 0.8446 | 0.9858 | |
|
| 0.0889 | 5.0 | 845 | 0.0665 | 0.7998 | 0.8566 | 0.8272 | 0.9850 | |
|
| 0.0191 | 6.0 | 1014 | 0.0796 | 0.8229 | 0.85 | 0.8362 | 0.9862 | |
|
| 0.0191 | 7.0 | 1183 | 0.0783 | 0.8193 | 0.8474 | 0.8331 | 0.9860 | |
|
| 0.0191 | 8.0 | 1352 | 0.0792 | 0.8257 | 0.8539 | 0.8396 | 0.9864 | |
|
| 0.0079 | 9.0 | 1521 | 0.0847 | 0.8154 | 0.8658 | 0.8398 | 0.9851 | |
|
| 0.0079 | 10.0 | 1690 | 0.0855 | 0.8160 | 0.875 | 0.8444 | 0.9857 | |
|
| 0.0079 | 11.0 | 1859 | 0.0868 | 0.8081 | 0.8645 | 0.8353 | 0.9864 | |
|
| 0.0037 | 12.0 | 2028 | 0.0912 | 0.8036 | 0.8776 | 0.8390 | 0.9853 | |
|
| 0.0037 | 13.0 | 2197 | 0.0907 | 0.8323 | 0.8684 | 0.8500 | 0.9868 | |
|
| 0.0037 | 14.0 | 2366 | 0.0899 | 0.8192 | 0.8763 | 0.8468 | 0.9865 | |
|
| 0.0023 | 15.0 | 2535 | 0.0915 | 0.8273 | 0.8763 | 0.8511 | 0.9866 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
### Citation |
|
If you used the datasets and models in this repository, please cite it. |
|
|
|
```bibtex |
|
@misc{https://doi.org/10.48550/arxiv.2302.09611, |
|
doi = {10.48550/ARXIV.2302.09611}, |
|
url = {https://arxiv.org/abs/2302.09611}, |
|
author = {Sartipi, Amir and Fatemi, Afsaneh}, |
|
keywords = {Computation and Language (cs.CL), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences}, |
|
title = {Exploring the Potential of Machine Translation for Generating Named Entity Datasets: A Case Study between Persian and English}, |
|
publisher = {arXiv}, |
|
year = {2023}, |
|
copyright = {arXiv.org perpetual, non-exclusive license} |
|
} |
|
``` |
|
|
