|
--- |
|
license: mit |
|
base_model: neuralmind/bert-base-portuguese-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: google-play-sentiment-analysis |
|
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. --> |
|
|
|
# google-play-sentiment-analysis |
|
|
|
This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/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 |
|
|
