metadata
license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: google-play-sentiment-analysis
results: []
google-play-sentiment-analysis
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: 3.3877
- Accuracy: 0.5328
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | Accuracy |
|---|---|---|---|---|
| 1.2365 | 1.0 | 1275 | 1.1915 | 0.5056 |
| 1.0717 | 2.0 | 2550 | 1.2020 | 0.5133 |
| 0.8201 | 3.0 | 3825 | 1.3425 | 0.5017 |
| 0.5824 | 4.0 | 5100 | 1.5890 | 0.5294 |
| 0.4379 | 5.0 | 6375 | 1.9669 | 0.5128 |
| 0.3143 | 6.0 | 7650 | 2.4700 | 0.5361 |
| 0.2556 | 7.0 | 8925 | 2.9751 | 0.5211 |
| 0.1924 | 8.0 | 10200 | 3.2435 | 0.5211 |
| 0.1494 | 9.0 | 11475 | 3.3190 | 0.5278 |
| 0.1293 | 10.0 | 12750 | 3.3877 | 0.5328 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0