metadata
license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: newsdata-bertimbal
results: []
newsdata-bertimbal
This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3387
- Accuracy: 0.9045
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5125 | 0.2749 | 2000 | 0.4810 | 0.8749 |
| 0.3874 | 0.5498 | 4000 | 0.3903 | 0.8938 |
| 0.3425 | 0.8247 | 6000 | 0.3387 | 0.9045 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1