|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: Amir13/ontonotes5-persian |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xlm-roberta-base-ontonotesv5 |
|
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-ontonotesv5 |
|
|
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the [ontonotes5-persian](https://huggingface.co/datasets/Amir13/ontonotes5-persian) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1693 |
|
- Precision: 0.8336 |
|
- Recall: 0.8360 |
|
- F1: 0.8348 |
|
- Accuracy: 0.9753 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1145 | 1.0 | 2310 | 0.1174 | 0.7717 | 0.7950 | 0.7832 | 0.9697 | |
|
| 0.0793 | 2.0 | 4620 | 0.1084 | 0.8129 | 0.8108 | 0.8118 | 0.9729 | |
|
| 0.0627 | 3.0 | 6930 | 0.1078 | 0.8227 | 0.8102 | 0.8164 | 0.9735 | |
|
| 0.047 | 4.0 | 9240 | 0.1132 | 0.8105 | 0.8223 | 0.8164 | 0.9731 | |
|
| 0.0347 | 5.0 | 11550 | 0.1190 | 0.8185 | 0.8315 | 0.8250 | 0.9742 | |
|
| 0.0274 | 6.0 | 13860 | 0.1282 | 0.8088 | 0.8387 | 0.8235 | 0.9734 | |
|
| 0.0202 | 7.0 | 16170 | 0.1329 | 0.8219 | 0.8354 | 0.8286 | 0.9745 | |
|
| 0.0167 | 8.0 | 18480 | 0.1423 | 0.8147 | 0.8376 | 0.8260 | 0.9742 | |
|
| 0.0134 | 9.0 | 20790 | 0.1520 | 0.8259 | 0.8308 | 0.8284 | 0.9745 | |
|
| 0.0097 | 10.0 | 23100 | 0.1627 | 0.8226 | 0.8377 | 0.8300 | 0.9745 | |
|
| 0.0084 | 11.0 | 25410 | 0.1693 | 0.8336 | 0.8360 | 0.8348 | 0.9753 | |
|
| 0.0066 | 12.0 | 27720 | 0.1744 | 0.8317 | 0.8359 | 0.8338 | 0.9751 | |
|
| 0.0053 | 13.0 | 30030 | 0.1764 | 0.8247 | 0.8409 | 0.8327 | 0.9750 | |
|
| 0.004 | 14.0 | 32340 | 0.1797 | 0.8280 | 0.8378 | 0.8328 | 0.9751 | |
|
| 0.004 | 15.0 | 34650 | 0.1809 | 0.8310 | 0.8382 | 0.8346 | 0.9754 | |
|
|
|
|
|
### 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} |
|
} |
|
``` |
