|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- conll2003 |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xlm-roberta-base-conll2003-en |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: conll2003 |
|
type: conll2003 |
|
config: conll2003 |
|
split: validation |
|
args: conll2003 |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9478680879413725 |
|
- name: Recall |
|
type: recall |
|
value: 0.9588879528222409 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9533461763966831 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9917972098823162 |
|
--- |
|
|
|
<!-- 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-conll2003-en |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the [conll2003](https://huggingface.co/datasets/conll2003) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0534 |
|
- Precision: 0.9479 |
|
- Recall: 0.9589 |
|
- F1: 0.9533 |
|
- Accuracy: 0.9918 |
|
|
|
## 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 | 439 | 0.0535 | 0.9131 | 0.9238 | 0.9184 | 0.9865 | |
|
| 0.1663 | 2.0 | 878 | 0.0461 | 0.9305 | 0.9390 | 0.9348 | 0.9887 | |
|
| 0.0404 | 3.0 | 1317 | 0.0366 | 0.9431 | 0.9501 | 0.9466 | 0.9910 | |
|
| 0.0252 | 4.0 | 1756 | 0.0381 | 0.9395 | 0.9516 | 0.9455 | 0.9908 | |
|
| 0.0172 | 5.0 | 2195 | 0.0398 | 0.9409 | 0.9523 | 0.9466 | 0.9911 | |
|
| 0.0119 | 6.0 | 2634 | 0.0429 | 0.9389 | 0.9560 | 0.9474 | 0.9910 | |
|
| 0.0091 | 7.0 | 3073 | 0.0463 | 0.9451 | 0.9548 | 0.9500 | 0.9913 | |
|
| 0.0063 | 8.0 | 3512 | 0.0446 | 0.9478 | 0.9575 | 0.9526 | 0.9919 | |
|
| 0.0063 | 9.0 | 3951 | 0.0513 | 0.9424 | 0.9569 | 0.9496 | 0.9911 | |
|
| 0.0049 | 10.0 | 4390 | 0.0494 | 0.9470 | 0.9545 | 0.9507 | 0.9915 | |
|
| 0.0036 | 11.0 | 4829 | 0.0506 | 0.9477 | 0.9553 | 0.9515 | 0.9917 | |
|
| 0.0029 | 12.0 | 5268 | 0.0518 | 0.9472 | 0.9586 | 0.9529 | 0.9919 | |
|
| 0.0026 | 13.0 | 5707 | 0.0530 | 0.9451 | 0.9567 | 0.9508 | 0.9916 | |
|
| 0.0021 | 14.0 | 6146 | 0.0526 | 0.9468 | 0.9567 | 0.9517 | 0.9917 | |
|
| 0.0016 | 15.0 | 6585 | 0.0534 | 0.9479 | 0.9589 | 0.9533 | 0.9918 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
### Citation |
|
```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} |
|
} |
|
``` |
