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: 3.5035
- Accuracy: 0.5107
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.18 | 1.0 | 1125 | 1.2287 | 0.4957 |
| 0.9342 | 2.0 | 2250 | 1.3080 | 0.5223 |
| 0.6743 | 3.0 | 3375 | 1.4724 | 0.5147 |
| 0.493 | 4.0 | 4500 | 1.8871 | 0.5113 |
| 0.3701 | 5.0 | 5625 | 2.4745 | 0.5183 |
| 0.275 | 6.0 | 6750 | 2.7261 | 0.5183 |
| 0.2115 | 7.0 | 7875 | 3.1310 | 0.5183 |
| 0.1521 | 8.0 | 9000 | 3.3735 | 0.5077 |
| 0.1442 | 9.0 | 10125 | 3.4553 | 0.5137 |
| 0.1189 | 10.0 | 11250 | 3.5035 | 0.5107 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0