|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
base_model: neuralmind/bert-base-portuguese-cased |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: hate_BERTimbau_v1 |
|
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. --> |
|
|
|
# hate_BERTimbau_v1 |
|
|
|
This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1389 |
|
- Precision: 0.7715 |
|
- Recall: 0.7690 |
|
- F1: 0.7700 |
|
- Accuracy: 0.7690 |
|
|
|
## 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 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.5196 | 1.0 | 284 | 0.4981 | 0.7509 | 0.7566 | 0.7482 | 0.7566 | |
|
| 0.4019 | 2.0 | 568 | 0.4680 | 0.7923 | 0.7813 | 0.7843 | 0.7813 | |
|
| 0.2706 | 3.0 | 852 | 0.6745 | 0.7525 | 0.7531 | 0.7355 | 0.7531 | |
|
| 0.1601 | 4.0 | 1136 | 0.9990 | 0.7632 | 0.7672 | 0.7573 | 0.7672 | |
|
| 0.0975 | 5.0 | 1420 | 1.1389 | 0.7715 | 0.7690 | 0.7700 | 0.7690 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
