t5-small-finetuned-sql2
This model is a fine-tuned version of FYP19/t5-small-finetuned-spider on the wikisql dataset. It achieves the following results on the evaluation set:
- Loss: 0.1238
- Rouge2 Precision: 0.8201
- Rouge2 Recall: 0.7282
- Rouge2 Fmeasure: 0.7643
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| 0.1923 | 1.0 | 4049 | 0.1548 | 0.7971 | 0.7063 | 0.7419 |
| 0.1623 | 2.0 | 8098 | 0.1362 | 0.8103 | 0.7185 | 0.7546 |
| 0.1495 | 3.0 | 12147 | 0.1290 | 0.816 | 0.7239 | 0.7601 |
| 0.1445 | 4.0 | 16196 | 0.1251 | 0.8181 | 0.7266 | 0.7625 |
| 0.1398 | 5.0 | 20245 | 0.1238 | 0.8201 | 0.7282 | 0.7643 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2