|
--- |
|
license: mit |
|
base_model: neuralmind/bert-base-portuguese-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
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: 1.1957 |
|
- Accuracy: 0.495 |
|
|
|
## 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: 5e-06 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.4561 | 1.0 | 513 | 1.2817 | 0.4547 | |
|
| 1.2173 | 2.0 | 1026 | 1.2062 | 0.4907 | |
|
| 1.1137 | 3.0 | 1539 | 1.1957 | 0.495 | |
|
| 1.028 | 4.0 | 2052 | 1.2423 | 0.4903 | |
|
| 0.9541 | 5.0 | 2565 | 1.2519 | 0.483 | |
|
| 0.8827 | 6.0 | 3078 | 1.2847 | 0.485 | |
|
| 0.8353 | 7.0 | 3591 | 1.3275 | 0.4793 | |
|
| 0.7752 | 8.0 | 4104 | 1.3532 | 0.4893 | |
|
| 0.7351 | 9.0 | 4617 | 1.3674 | 0.483 | |
|
| 0.7373 | 10.0 | 5130 | 1.3706 | 0.486 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
