metadata
license: mit
base_model: unicamp-dl/ptt5-base-portuguese-vocab
tags:
- generated_from_trainer
datasets:
- tiagoblima/du-qg-squadv1_pt
model-index:
- name: t5_base-qg-ap-oficial
results: []
t5_base-qg-ap-oficial
This model is a fine-tuned version of unicamp-dl/ptt5-base-portuguese-vocab on the tiagoblima/du-qg-squadv1_pt dataset. It achieves the following results on the evaluation set:
- Loss: 1.9945
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1593 | 1.0 | 2366 | 2.0509 |
| 1.9907 | 2.0 | 4733 | 2.0158 |
| 1.9408 | 3.0 | 7099 | 2.0011 |
| 1.8321 | 4.0 | 9466 | 1.9945 |
| 1.7928 | 5.0 | 11830 | 1.9992 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.0