README.md

metadata

base_model: TeeA/T5-Text2SQL-Bilingual
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: Text2SQL-Bilingual
    results: []

Text2SQL-Bilingual

This model is a fine-tuned version of TeeA/T5-Text2SQL-Bilingual on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6352
• Rouge1: 0.8954
• Rouge2: 0.8464
• Rougel: 0.8923
• Rougelsum: 0.8922

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.8096	1.0	4389	0.6355	0.8975	0.8473	0.8940	0.8941
0.7862	2.0	8778	0.6368	0.8972	0.8489	0.8938	0.8939
0.7791	3.0	13167	0.6368	0.8963	0.8469	0.8927	0.8925
0.7792	4.0	17556	0.6369	0.8954	0.8464	0.8919	0.8917
0.7859	5.0	21945	0.6356	0.8949	0.8448	0.8914	0.8912
0.7812	6.0	26334	0.6354	0.8962	0.8468	0.8928	0.8928
0.7813	7.0	30723	0.6359	0.8950	0.8451	0.8916	0.8913
0.7695	8.0	35112	0.6356	0.8947	0.8458	0.8916	0.8915
0.7842	9.0	39501	0.6350	0.8950	0.8463	0.8920	0.8918
0.7724	10.0	43890	0.6352	0.8954	0.8464	0.8923	0.8922

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2