metadata
language:
- pt
license: apache-2.0
tags:
- toxicity
- portuguese
- hate speech
- offensive language
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
base_model: neuralmind/bert-large-portuguese-cased
model-index:
- name: dougtrajano/toxicity-target-type-identification
results: []
dougtrajano/toxicity-target-type-identification
This model is a fine-tuned version of neuralmind/bert-large-portuguese-cased on the OLID-BR dataset. It achieves the following results on the evaluation set:
- Loss: 1.4281
- Accuracy: 0.8002
- F1: 0.7986
- Precision: 0.7990
- Recall: 0.8002
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: 3.952388499692274e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1993
- optimizer: Adam with betas=(0.9944095815441554,0.8750000522553327) and epsilon=1.8526084265228802e-07
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 355 | 0.7145 | 0.6903 | 0.7052 | 0.7528 | 0.6903 |
| 0.8011 | 2.0 | 710 | 0.9930 | 0.7928 | 0.7840 | 0.7835 | 0.7928 |
| 0.529 | 3.0 | 1065 | 1.4281 | 0.8002 | 0.7986 | 0.7990 | 0.8002 |
| 0.529 | 4.0 | 1420 | 1.6783 | 0.7727 | 0.7753 | 0.7788 | 0.7727 |
| 0.2706 | 5.0 | 1775 | 2.3904 | 0.7727 | 0.7683 | 0.7660 | 0.7727 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.10.2+cu113
- Datasets 2.9.0
- Tokenizers 0.13.2