|
--- |
|
license: apache-2.0 |
|
language: "es" |
|
tags: |
|
- generated_from_trainer |
|
- es |
|
- text-classification |
|
- acoso |
|
- twitter |
|
- cyberbullying |
|
datasets: |
|
- hackathon-pln-es/Dataset-Acoso-Twitter-Es |
|
widget: |
|
- text: "Que horrible como la farándula chilena siempre se encargaba de dejar mal a las mujeres. Un asco" |
|
- text: "Hay que ser bien menestra para amenazar a una mujer con una llave de ruedas. Viendo como se viste no me queda ninguna duda" |
|
- text: "más centrados en tener una sociedad reprimida y sumisa que en estudiar y elaborar políticas de protección hacia las personas de mayor riesgo ante el virus." |
|
|
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Detección de acoso en Twitter |
|
results: [] |
|
--- |
|
|
|
# Detección de acoso en Twitter Español |
|
|
|
This model is a fine-tuned version of [mrm8488/distilroberta-finetuned-tweets-hate-speech](https://huggingface.co/mrm8488/distilroberta-finetuned-tweets-hate-speech) on [hackathon-pln-es/Dataset-Acoso-Twitter-Es](https://huggingface.co/datasets/hackathon-pln-es/Dataset-Acoso-Twitter-Es). |
|
|
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1628 |
|
- Accuracy: 0.9167 |
|
|
|
# UNL: Universidad Nacional de Loja |
|
|
|
## Miembros del equipo: |
|
- Anderson Quizhpe <br> |
|
- Luis Negrón <br> |
|
- David Pacheco <br> |
|
- Bryan Requenes <br> |
|
- Paul Pasaca |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.6732 | 1.0 | 27 | 0.3797 | 0.875 | |
|
| 0.5537 | 2.0 | 54 | 0.3242 | 0.9167 | |
|
| 0.5218 | 3.0 | 81 | 0.2879 | 0.9167 | |
|
| 0.509 | 4.0 | 108 | 0.2606 | 0.9167 | |
|
| 0.4196 | 5.0 | 135 | 0.1628 | 0.9167 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0 |
|
- Pytorch 1.10.0+cu111 |
|
- Datasets 2.0.0 |
|
- Tokenizers 0.11.6 |
|
|
