metadata
license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
- generated_from_trainer
metrics:
- f1
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: 3.6324
- F1: 0.5277
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: 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.7056 | 1.0 | 1125 | 1.5127 | 0.4766 |
| 0.7472 | 2.0 | 2250 | 1.4296 | 0.5148 |
| 0.5266 | 3.0 | 3375 | 1.6938 | 0.5262 |
| 0.3887 | 4.0 | 4500 | 2.1185 | 0.5176 |
| 0.3078 | 5.0 | 5625 | 2.5383 | 0.5229 |
| 0.2286 | 6.0 | 6750 | 3.0566 | 0.5107 |
| 0.1718 | 7.0 | 7875 | 3.3369 | 0.5248 |
| 0.1324 | 8.0 | 9000 | 3.4615 | 0.5255 |
| 0.1372 | 9.0 | 10125 | 3.5526 | 0.5221 |
| 0.1095 | 10.0 | 11250 | 3.6324 | 0.5277 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0