license: apache-2.0
tags:
- null
datasets:
- EXIST Dataset
- MeTwo Machismo and Sexism Twitter Identification dataset
metrics:
- accuracy
model-index:
- name: twitter_sexismo-finetuned-exist2021
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: EXIST Dataset
type: EXIST Dataset
args: es
metrics:
- name: Accuracy
type: accuracy
value: 0.94
twitter_sexismo-finetuned-exist2021
This model is a fine-tuned version of pysentimiento/robertuito-hate-speech on the EXIST dataset and + MeTwo: Machismo and Sexism Twitter Identification dataset https://github.com/franciscorodriguez92/MeTwo. It achieves the following results on the evaluation set:
- Loss: 0.24
- Accuracy: 0.94
Model description
Modelo para el Hackaton de Somos NLP para detección de sexismo en twitts en español
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- my_learning_rate = 5E-5
- my_adam_epsilon = 1E-8
- my_number_of_epochs = 8
- my_warmup = 3
- my_mini_batch_size = 32
- optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Epoch Training Loss Validation Loss Accuracy F1 Precision Recall 1 0.246700 0.179020 0.942982 0.944110 0.933673 0.954783
2 0.079300 0.319939 0.928070 0.930976 0.902121 0.961739
3 0.022300 0.425300 0.921053 0.920071 0.940109 0.900870
4 0.000300 0.472090 0.919298 0.918149 0.939891 0.897391
5 0.009000 0.510828 0.918421 0.921783 0.892508 0.953043
6 0.000200 0.496530 0.922807 0.923077 0.927944 0.918261
7 0.000000 0.568268 0.922807 0.925297 0.903814 0.947826
8 0.000000 0.532735 0.927193 0.928139 0.924138 0.932174
9 0.000000 0.545693 0.928070 0.929553 0.918506 0.940870
10 0.000000 0.547560 0.928070 0.929553 0.918506 0.940870303
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Tokenizers 0.11.6