Update README.md

README.md

@@ -16,38 +16,80 @@ metrics:
 model-index:
 - name: dougtrajano/toxicity-type-detection
   results: []
+datasets:
+- dougtrajano/olid-br
+library_name: transformers
 ---
 
-<!-- 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. -->
-
 # dougtrajano/toxicity-type-detection
 
-This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the OLID-BR dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.2337
-- Accuracy: 0.4214
-- F1: 0.7645
-- Precision: 0.8180
-- Recall: 0.7230
+Toxicity Type Detection is a model that predicts the type(s) of toxicity(s) in a given text.
+
+Toxicity Labels: `health`, `ideology`, `insult`, `lgbtqphobia`, `other_lifestyle`, `physical_aspects`, `profanity_obscene`, `racism`, `sexism`, `xenophobia`
+
+This BERT model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the [OLID-BR dataset](https://huggingface.co/datasets/dougtrajano/olid-br).
+
+## Overview
+
+**Input:** Text in Brazilian Portuguese
+
+**Output:** Multilabel classification (toxicity types)
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("dougtrajano/toxicity-type-detection")
+
+model = AutoModelForSequenceClassification.from_pretrained("dougtrajano/toxicity-type-detection")
+```
+
+## Limitations and bias
+
+The following factors may degrade the model’s performance.
 
-## Model description
+**Text Language**:  The model was trained on Brazilian Portuguese texts, so it may not work well with Portuguese dialects.
 
-More information needed
+**Text Origin**: The model was trained on texts from social media and a few texts from other sources, so it may not work well on other types of texts.
 
-## Intended uses & limitations
+## Trade-offs
 
-More information needed
+Sometimes models exhibit performance issues under particular circumstances. In this section, we'll discuss situations in which you might discover that the model performs less than optimally, and should plan accordingly.
 
-## Training and evaluation data
+**Text Length**: The model was fine-tuned on texts with a word count between 1 and 178 words (average of 18 words). It may give poor results on texts with a word count outside this range.
 
-More information needed
+## Performance
+
+The model was evaluated on the test set of the [OLID-BR](https://dougtrajano.github.io/olid-br/) dataset.
+
+**Accuracy:** 0.4214
+
+**Precision:** 0.8180
+
+**Recall:** 0.7230
+
+**F1-Score:** 0.7645
+
+| Label | Precision | Recall | F1-Score | Support |
+| :---: | :-------: | :----: | :------: | :-----: |
+| `health` | 0.3182 | 0.1795 | 0.2295 | 39 |
+| `ideology` | 0.6820 | 0.6842 | 0.6831 | 304 |
+| `insult` | 0.9689 | 0.8068 | 0.8805 | 1351 |
+| `lgbtqphobia` | 0.8182 | 0.5870 | 0.6835 | 92 |
+| `other_lifestyle` | 0.4242 | 0.4118 | 0.4179 | 34 |
+| `physical_aspects` | 0.4324 | 0.5783 | 0.4948 | 83 |
+| `profanity_obscene` | 0.7482 | 0.7509 | 0.7496 | 562 |
+| `racism` | 0.4737 | 0.3913 | 0.4286 | 23 |
+| `sexism` | 0.5132 | 0.3391 | 0.4084 | 115 |
+| `xenophobia` | 0.3333 | 0.4375 | 0.3784 | 32 |
 
 ## Training procedure
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
+
 - learning_rate: 7.044186985160909e-05
 - train_batch_size: 8
 - eval_batch_size: 8
@@ -56,24 +98,13 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 30
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 1.1107        | 1.0   | 534  | 0.9282          | 0.2823   | 0.6762 | 0.7419    | 0.6630 |
-| 0.8974        | 2.0   | 1068 | 0.8605          | 0.2754   | 0.6324 | 0.7759    | 0.5913 |
-| 0.7436        | 3.0   | 1602 | 1.0151          | 0.3150   | 0.6870 | 0.7828    | 0.6512 |
-| 0.644         | 4.0   | 2136 | 1.1455          | 0.3519   | 0.7114 | 0.7857    | 0.6865 |
-| 0.4704        | 5.0   | 2670 | 1.4827          | 0.3387   | 0.7109 | 0.7814    | 0.6843 |
-| 0.3316        | 6.0   | 3204 | 1.6275          | 0.3602   | 0.7217 | 0.8020    | 0.6816 |
-| 0.2717        | 7.0   | 3738 | 2.2337          | 0.4214   | 0.7645 | 0.8180    | 0.7230 |
-| 0.231         | 8.0   | 4272 | 2.0275          | 0.3651   | 0.7194 | 0.8271    | 0.6528 |
-| 0.197         | 9.0   | 4806 | 1.9878          | 0.4033   | 0.7409 | 0.8240    | 0.6812 |
-
-
 ### Framework versions
 
 - Transformers 4.26.0
 - Pytorch 1.10.2+cu113
 - Datasets 2.9.0
 - Tokenizers 0.13.2
+
+## Provide Feedback
+
+If you have any feedback on this model, please [open an issue](https://github.com/DougTrajano/ToChiquinho/issues/new) on GitHub.