t5-small-finetuned-wikisql

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1482
• Model Preparation Time: 0.0044
• Exact Match: 0.2483
• Prediction Sample: SELECT Nationality FROM table WHERE Name = terrence ross
• Reference Sample: SELECT Nationality FROM table WHERE Player = Terrence Ross

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_FUSED 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	Model Preparation Time	Exact Match	Prediction Sample	Reference Sample
0.2286	1.0	3523	0.1864	0.0044	0.212	SELECT Nationality FROM table WHERE Country = terrence ross	SELECT Nationality FROM table WHERE Player = Terrence Ross
0.1925	2.0	7046	0.1636	0.0044	0.2329	SELECT Nationality FROM table WHERE Name = terrence ross	SELECT Nationality FROM table WHERE Player = Terrence Ross
0.1798	3.0	10569	0.1540	0.0044	0.2426	SELECT Nationality FROM table WHERE Name = terrence ross	SELECT Nationality FROM table WHERE Player = Terrence Ross
0.171	4.0	14092	0.1496	0.0044	0.2473	SELECT Nationality FROM table WHERE Name = terrence ross	SELECT Nationality FROM table WHERE Player = Terrence Ross
0.1672	5.0	17615	0.1482	0.0044	0.2483	SELECT Nationality FROM table WHERE Name = terrence ross	SELECT Nationality FROM table WHERE Player = Terrence Ross

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu126
• Datasets 4.2.0
• Tokenizers 0.22.1