|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bert-base-parsbert-uncased-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. --> |
|
|
|
# bert-base-parsbert-uncased-ontonotesv5 |
|
|
|
This model is a fine-tuned version of [HooshvareLab/bert-base-parsbert-uncased](https://huggingface.co/HooshvareLab/bert-base-parsbert-uncased) on the [ontonotes5-persian](https://huggingface.co/datasets/Amir13/ontonotes5-persian) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2169 |
|
- Precision: 0.8145 |
|
- Recall: 0.8287 |
|
- F1: 0.8215 |
|
- Accuracy: 0.9741 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1029 | 1.0 | 2310 | 0.1151 | 0.8080 | 0.7559 | 0.7811 | 0.9691 | |
|
| 0.059 | 2.0 | 4620 | 0.1098 | 0.7909 | 0.8068 | 0.7988 | 0.9719 | |
|
| 0.0363 | 3.0 | 6930 | 0.1205 | 0.7981 | 0.8168 | 0.8074 | 0.9728 | |
|
| 0.0202 | 4.0 | 9240 | 0.1406 | 0.8115 | 0.8046 | 0.8080 | 0.9726 | |
|
| 0.0122 | 5.0 | 11550 | 0.1496 | 0.7847 | 0.8225 | 0.8031 | 0.9721 | |
|
| 0.0105 | 6.0 | 13860 | 0.1633 | 0.7962 | 0.8188 | 0.8073 | 0.9724 | |
|
| 0.0057 | 7.0 | 16170 | 0.1842 | 0.8071 | 0.8133 | 0.8102 | 0.9729 | |
|
| 0.0041 | 8.0 | 18480 | 0.1913 | 0.8081 | 0.8093 | 0.8087 | 0.9727 | |
|
| 0.003 | 9.0 | 20790 | 0.1935 | 0.8121 | 0.8130 | 0.8126 | 0.9732 | |
|
| 0.002 | 10.0 | 23100 | 0.1992 | 0.8136 | 0.8214 | 0.8175 | 0.9734 | |
|
| 0.002 | 11.0 | 25410 | 0.2037 | 0.8014 | 0.8280 | 0.8145 | 0.9735 | |
|
| 0.0012 | 12.0 | 27720 | 0.2092 | 0.8133 | 0.8204 | 0.8168 | 0.9737 | |
|
| 0.001 | 13.0 | 30030 | 0.2095 | 0.8125 | 0.8253 | 0.8188 | 0.9739 | |
|
| 0.0006 | 14.0 | 32340 | 0.2143 | 0.8129 | 0.8272 | 0.8200 | 0.9740 | |
|
| 0.0005 | 15.0 | 34650 | 0.2169 | 0.8145 | 0.8287 | 0.8215 | 0.9741 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.0.dev0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.8.0 |
|
- 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} |
|
} |
|
``` |
