Text2SQL-StudentProject-domain

This model is a fine-tuned version of cssupport/t5-small-awesome-text-to-sql on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.0454
• Rouge1: 0.3934
• Rouge2: 0.2246
• Rougel: 0.3769
• Rougelsum: 0.3750

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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	21	2.6820	0.3744	0.1996	0.3567	0.3541
No log	2.0	42	2.3569	0.3835	0.2191	0.3667	0.3651
No log	3.0	63	2.1723	0.3904	0.2216	0.3746	0.3725
No log	4.0	84	2.0758	0.3899	0.2214	0.3728	0.3708
No log	5.0	105	2.0454	0.3934	0.2246	0.3769	0.3750

Framework versions

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