tcepi
/

prog_integridade_model

@@ -1,199 +1,167 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
+license: mit
+language:
+- pt
 library_name: transformers
+tags:
+- text-classification
+- binary-classification
+- modernbert
+- pytorch
+- transformers
+datasets:
+- tcepi/prog_integridade_dataset
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+- roc_auc
+base_model: answerdotai/ModernBERT-base
+pipeline_tag: text-classification
+model-index:
+- name: prog_integridade_model
+  results:
+  - task:
+      type: text-classification
+      name: Binary Text Classification
+    dataset:
+      name: tcepi/prog_integridade_dataset
+      type: tcepi/prog_integridade_dataset
+      split: test
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9878
+    - name: F1
+      type: f1
+      value: 0.9878
+    - name: Precision
+      type: precision
+      value: 0.9880
+    - name: Recall
+      type: recall
+      value: 0.9878
+    - name: ROC-AUC
+      type: roc_auc
+      value: 0.9970
 ---
+# MBP PAS Classification Model
+Este modelo é um fine-tune do [ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) para classificação binária, treinado no dataset [tcepi/prog_integridade_dataset](https://huggingface.co/datasets/tcepi/prog_integridade_dataset).
+## Descrição do Modelo
+- **Modelo Base:** answerdotai/ModernBERT-base
+- **Tarefa:** Classificação Binária de Texto
+- **Linguagem:** Português (pt)
+- **Framework:** PyTorch + Transformers
+## Métricas de Performance
+### Conjunto de Teste
+| Métrica | Valor |
+|---------|-------|
+| **Accuracy** | 0.9878 |
+| **F1-Score** | 0.9878 |
+| **Precision** | 0.9880 |
+| **Recall** | 0.9878 |
+| **ROC-AUC** | 0.9970 |
+| **Specificity** | 0.9791 |
+### Matriz de Confusão
+|  | Predito Negativo | Predito Positivo |
+|--|-----------------|-----------------|
+| **Real Negativo** | 516 (TN) | 11 (FP) |
+| **Real Positivo** | 2 (FN) | 540 (TP) |
+### Relatório de Classificação
+```
+              precision    recall  f1-score   support
+    Negativo     0.9961    0.9791    0.9876       527
+    Positivo     0.9800    0.9963    0.9881       542
+    accuracy                         0.9878      1069
+   macro avg     0.9881    0.9877    0.9878      1069
+weighted avg     0.9880    0.9878    0.9878      1069
+```
+## Uso
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+# Carregar modelo e tokenizer
+tokenizer = AutoTokenizer.from_pretrained("tcepi/prog_integridade_model")
+model = AutoModelForSequenceClassification.from_pretrained("tcepi/prog_integridade_model")
+# Classificar texto
+text = "Seu texto aqui"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
+with torch.no_grad():
+    outputs = model(**inputs)
+    predictions = torch.softmax(outputs.logits, dim=-1)
+    predicted_class = torch.argmax(predictions, dim=-1).item()
+print(f"Classe predita: {model.config.id2label[predicted_class]}")
+print(f"Probabilidades: {predictions.tolist()}")
+```
+## Treinamento
+### Hiperparâmetros
+- **Épocas:** 10
+- **Learning Rate:** 2e-5
+- **Batch Size:** 8
+- **Weight Decay:** 0.01
+- **Warmup Ratio:** 0.1
+- **Mixed Precision:** FP16
+- **Optimizer:** AdamW
+### Informações de Treinamento
+- **Tempo Total:** 1281.24 segundos
+- **Samples/segundo:** 30.01
+- **Loss Final:** 0.0905
+### Tabela de Métricas por Época
+|   epoch |   eval_loss |   eval_accuracy |   eval_f1 |   eval_roc_auc |   eval_specificity |
+|--------:|------------:|----------------:|----------:|---------------:|-------------------:|
+|       1 |   0.151197  |        0.957944 |  0.957959 |       0.994956 |           0.965686 |
+|       2 |   0.0504656 |        0.985981 |  0.985969 |       0.998654 |           0.970588 |
+|       3 |   0.0681938 |        0.985981 |  0.985969 |       0.998588 |           0.970588 |
+|       4 |   0.0468312 |        0.990654 |  0.990649 |       0.998961 |           0.980392 |
+|       5 |   0.0373923 |        0.990654 |  0.990649 |       0.99907  |           0.980392 |
+|       6 |   0.0413175 |        0.990654 |  0.990649 |       0.999179 |           0.980392 |
+|       7 |   0.0415714 |        0.990654 |  0.990649 |       0.999311 |           0.980392 |
+|       8 |   0.0415429 |        0.988318 |  0.988316 |       0.999442 |           0.985294 |
+|       9 |   0.043584  |        0.990654 |  0.990652 |       0.999486 |           0.985294 |
+|      10 |   0.0377868 |        0.990654 |  0.990652 |       0.999551 |           0.985294 |
+### Curvas de Treinamento
+#### Loss curve
+![Loss Curve](./assets/loss_curve.png)
+#### Métricas por Época
+![Métricas por Época](./assets/metrics_curve.png)
+## Dataset
+O modelo foi treinado usando o dataset [tcepi/prog_integridade_dataset](https://huggingface.co/datasets/tcepi/prog_integridade_dataset).
+## Limitações
+- O modelo foi treinado especificamente para o domínio do dataset Programa de Integridade, e pode não generalizar bem para outros tipos de texto ou domínios.
+- Performance pode variar em textos de outros domínios
+- Recomenda-se avaliar o modelo antes de usar em produção