|
--- |
|
license: mit |
|
base_model: neuralmind/bert-base-portuguese-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- recall |
|
- precision |
|
model-index: |
|
- name: content |
|
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. --> |
|
|
|
# content |
|
|
|
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: 0.4451 |
|
- Accuracy: 0.7772 |
|
- F1-score: 0.7788 |
|
- Recall: 0.8551 |
|
- Precision: 0.7150 |
|
|
|
## 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: 2.5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Recall | Precision | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:------:|:---------:| |
|
| 0.5156 | 0.3814 | 500 | 0.4764 | 0.7687 | 0.7744 | 0.8972 | 0.6812 | |
|
| 0.4498 | 0.7628 | 1000 | 0.4483 | 0.7790 | 0.7755 | 0.8622 | 0.7045 | |
|
| 0.4198 | 1.1442 | 1500 | 0.4574 | 0.7745 | 0.7723 | 0.8642 | 0.6980 | |
|
| 0.3687 | 1.5256 | 2000 | 0.4933 | 0.7696 | 0.7479 | 0.7723 | 0.7250 | |
|
| 0.3591 | 1.9069 | 2500 | 0.4475 | 0.7902 | 0.7828 | 0.8545 | 0.7223 | |
|
| 0.2809 | 2.2883 | 3000 | 0.5172 | 0.7696 | 0.7397 | 0.7400 | 0.7395 | |
|
| 0.2712 | 2.6697 | 3500 | 0.5308 | 0.7799 | 0.7749 | 0.8564 | 0.7076 | |
|
| 0.2482 | 3.0511 | 4000 | 0.6287 | 0.7622 | 0.7224 | 0.6992 | 0.7471 | |
|
| 0.172 | 3.4325 | 4500 | 0.6831 | 0.7725 | 0.7491 | 0.7678 | 0.7314 | |
|
| 0.1802 | 3.8139 | 5000 | 0.7141 | 0.7762 | 0.7570 | 0.7878 | 0.7285 | |
|
| 0.1477 | 4.1953 | 5500 | 0.8481 | 0.7653 | 0.7444 | 0.7723 | 0.7184 | |
|
| 0.121 | 4.5767 | 6000 | 0.9831 | 0.7639 | 0.7461 | 0.7840 | 0.7117 | |
|
| 0.1377 | 4.9580 | 6500 | 0.9748 | 0.7662 | 0.7435 | 0.7658 | 0.7224 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
