t5-small-finetuned-sql4
This model is a fine-tuned version of FYP19/t5-small-finetuned-wikisql on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0774
- Rouge2 Precision: 0.8024
- Rouge2 Recall: 0.4538
- Rouge2 Fmeasure: 0.5209
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: 0.001
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| 0.0234 | 1.0 | 916 | 0.0730 | 0.7371 | 0.4098 | 0.4685 |
| 0.0131 | 2.0 | 1832 | 0.0719 | 0.7761 | 0.4279 | 0.4938 |
| 0.0132 | 3.0 | 2748 | 0.0708 | 0.7866 | 0.4427 | 0.5079 |
| 0.0098 | 4.0 | 3664 | 0.0743 | 0.7732 | 0.4353 | 0.4988 |
| 0.0069 | 5.0 | 4580 | 0.0774 | 0.8024 | 0.4538 | 0.5209 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3