bbau-semeval25_fold1
This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4537
- Precision Samples: 1.0
- Recall Samples: 0.0
- F1 Samples: 0.0
- Precision Macro: 1.0
- Recall Macro: 0.3939
- F1 Macro: 0.3939
- Precision Micro: 1.0
- Recall Micro: 0.0
- F1 Micro: 0.0
- Precision Weighted: 1.0
- Recall Weighted: 0.0
- F1 Weighted: 0.0
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision Samples | Recall Samples | F1 Samples | Precision Macro | Recall Macro | F1 Macro | Precision Micro | Recall Micro | F1 Micro | Precision Weighted | Recall Weighted | F1 Weighted |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 5 | 0.6318 | 0.0483 | 0.2944 | 0.0758 | 0.5723 | 0.5505 | 0.2182 | 0.0462 | 0.2525 | 0.0781 | 0.6003 | 0.2525 | 0.0437 |
| 0.6419 | 2.0 | 10 | 0.5807 | 0.0523 | 0.2259 | 0.0771 | 0.8251 | 0.4798 | 0.3760 | 0.0525 | 0.1717 | 0.0804 | 0.7656 | 0.1717 | 0.0321 |
| 0.6419 | 3.0 | 15 | 0.5453 | 0.0705 | 0.2280 | 0.0983 | 0.8718 | 0.4621 | 0.3778 | 0.0721 | 0.1616 | 0.0997 | 0.8203 | 0.1616 | 0.0385 |
| 0.5558 | 4.0 | 20 | 0.5173 | 0.0604 | 0.1301 | 0.0697 | 0.9280 | 0.4394 | 0.3705 | 0.06 | 0.0909 | 0.0723 | 0.9184 | 0.0909 | 0.0167 |
| 0.5558 | 5.0 | 25 | 0.4962 | 0.0667 | 0.1051 | 0.0701 | 0.9460 | 0.4356 | 0.3896 | 0.0702 | 0.0808 | 0.0751 | 0.9259 | 0.0808 | 0.0273 |
| 0.5084 | 6.0 | 30 | 0.4806 | 0.15 | 0.0 | 0.0 | 0.9545 | 0.3939 | 0.3788 | 0.0 | 0.0 | 0.0 | 0.9495 | 0.0 | 0.0 |
| 0.5084 | 7.0 | 35 | 0.4688 | 0.65 | 0.0 | 0.0 | 0.9848 | 0.3939 | 0.3788 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.4795 | 8.0 | 40 | 0.4605 | 1.0 | 0.0 | 0.0 | 1.0 | 0.3939 | 0.3939 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.4795 | 9.0 | 45 | 0.4555 | 1.0 | 0.0 | 0.0 | 1.0 | 0.3939 | 0.3939 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.4666 | 10.0 | 50 | 0.4537 | 1.0 | 0.0 | 0.0 | 1.0 | 0.3939 | 0.3939 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.3.1
- Datasets 2.21.0
- Tokenizers 0.20.1
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for g-assismoraes/bbau-semeval25_fold1
Base model
neuralmind/bert-base-portuguese-cased