t5-text2sql

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

• Loss: 0.1611
• Rouge2 Precision: 0.8631
• Rouge2 Recall: 0.2595
• Rouge2 Fmeasure: 0.3674

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge2 Precision	Rouge2 Recall	Rouge2 Fmeasure
No log	1.0	11	1.8867	0.0	0.0	0.0
No log	2.0	22	0.9658	0.0119	0.0015	0.0027
No log	3.0	33	0.6477	0.0468	0.0078	0.0135
No log	4.0	44	0.4617	0.4251	0.14	0.1943
No log	5.0	55	0.3669	0.6403	0.2091	0.2937
No log	6.0	66	0.3084	0.7085	0.2446	0.3393
No log	7.0	77	0.2788	0.7282	0.2246	0.3175
No log	8.0	88	0.2549	0.7593	0.2346	0.332
No log	9.0	99	0.2368	0.7738	0.2367	0.3348
No log	10.0	110	0.2322	0.7889	0.2388	0.3393
No log	11.0	121	0.2151	0.8056	0.2419	0.3452
No log	12.0	132	0.2067	0.7996	0.2371	0.3382
No log	13.0	143	0.2003	0.7943	0.2365	0.3364
No log	14.0	154	0.1899	0.8204	0.244	0.3477
No log	15.0	165	0.1869	0.8309	0.2454	0.3502
No log	16.0	176	0.1826	0.8309	0.2454	0.3502
No log	17.0	187	0.1797	0.8252	0.245	0.3488
No log	18.0	198	0.1749	0.8353	0.2479	0.3535
No log	19.0	209	0.1726	0.8393	0.2508	0.3566
No log	20.0	220	0.1716	0.8373	0.2475	0.3538
No log	21.0	231	0.1695	0.8472	0.2489	0.3553
No log	22.0	242	0.1693	0.8472	0.2519	0.3589
No log	23.0	253	0.1685	0.877	0.271	0.3808
No log	24.0	264	0.1668	0.8552	0.2598	0.3666
No log	25.0	275	0.1641	0.8552	0.252	0.3591
No log	26.0	286	0.1628	0.8671	0.2598	0.3683
No log	27.0	297	0.1617	0.8631	0.2595	0.3674
No log	28.0	308	0.1611	0.8631	0.2595	0.3674
No log	29.0	319	0.1611	0.8631	0.2595	0.3674
No log	30.0	330	0.1611	0.8631	0.2595	0.3674

Framework versions

• Transformers 4.21.3
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1