t5_large-qg-aas
This model is a fine-tuned version of unicamp-dl/ptt5-large-t5-vocab on the tiagoblima/qg_squad_v1_pt dataset. It achieves the following results on the evaluation set:
- Loss: 4.9208
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: 0.005
- train_batch_size: 64
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.0267 | 1.0 | 808 | 6.6599 |
| 5.1565 | 2.0 | 1616 | 5.7159 |
| 4.7181 | 3.0 | 2424 | 5.2321 |
| 4.4869 | 4.0 | 3232 | 4.9931 |
| 4.4539 | 5.0 | 4040 | 4.9208 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.0