global_ep5_bertsqv1pptbased_ctxpar_punct_sqv2
This model is a fine-tuned version of pierreguillou/bert-base-cased-squad-v1.1-portuguese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1198
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: 30
- eval_batch_size: 180
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 90
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.99 | 37 | 1.0977 |
| No log | 1.99 | 74 | 0.1261 |
| No log | 2.99 | 111 | 0.1167 |
| No log | 3.99 | 148 | 0.1200 |
| No log | 4.99 | 185 | 0.1198 |
Framework versions
- Transformers 4.24.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3