---
license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
- f1
model-index:
- name: oracle_class_bin
  results: []
---

<!-- 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. -->

# oracle_class_bin

This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1283
- Precision: 0.7996
- Recall: 0.8499
- Accuracy: 0.9627
- F1: 0.8240

## 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: 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: 2000
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | Accuracy | F1     |
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:--------:|:------:|
| 0.1359        | 0.5606 | 1800 | 0.1183          | 0.7706    | 0.7945 | 0.9546   | 0.7824 |
| 0.1129        | 1.1211 | 3600 | 0.1203          | 0.7550    | 0.8529 | 0.9565   | 0.8010 |
| 0.0919        | 1.6817 | 5400 | 0.1111          | 0.8016    | 0.8180 | 0.9605   | 0.8098 |
| 0.0658        | 2.2423 | 7200 | 0.1142          | 0.8059    | 0.8249 | 0.9616   | 0.8153 |
| 0.0731        | 2.8029 | 9000 | 0.1283          | 0.7996    | 0.8499 | 0.9627   | 0.8240 |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.1.0
- Datasets 2.19.2
- Tokenizers 0.19.1