<!-- 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. -->
bert-base-squad-v2-portuguese
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: 2.5445
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: 3e-05
- train_batch_size: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.3221 | 1.0 | 654 | 1.5568 |
1.4383 | 2.0 | 1308 | 1.5087 |
1.1511 | 3.0 | 1962 | 1.6465 |
0.5951 | 4.0 | 2616 | 1.7428 |
0.4432 | 5.0 | 3270 | 2.1401 |
0.3554 | 6.0 | 3924 | 2.3629 |
0.2195 | 7.0 | 4578 | 2.5445 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1