t5-small-finetuned-wikisql-sql-nl-nl-sql
This model is a fine-tuned version of t5-small on the wikisql dataset. It achieves the following results on the evaluation set:
- Loss: 0.1931
- Bleu: 42.8504
- Gen Len: 17.1728
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.267 | 1.0 | 8097 | 0.2252 | 40.632 | 17.212 |
| 0.2424 | 2.0 | 16194 | 0.2062 | 41.9468 | 17.2425 |
| 0.2238 | 3.0 | 24291 | 0.1984 | 42.3496 | 17.2079 |
| 0.2217 | 4.0 | 32388 | 0.1943 | 42.7128 | 17.1551 |
| 0.2161 | 5.0 | 40485 | 0.1931 | 42.8504 | 17.1728 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0