t5-small-finetuned-wikisql

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

• Loss: 0.2640
• Rouge2 Precision: 0.8471
• Rouge2 Recall: 0.3841
• Rouge2 Fmeasure: 0.5064

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge2 Precision	Rouge2 Recall	Rouge2 Fmeasure
No log	1.0	11	2.7587	0.098	0.0305	0.045
No log	2.0	22	2.0056	0.0969	0.0284	0.0422
No log	3.0	33	1.4456	0.1046	0.0349	0.0503
No log	4.0	44	1.0317	0.1054	0.0337	0.0482
No log	5.0	55	0.7603	0.2749	0.1299	0.1724
No log	6.0	66	0.5722	0.7115	0.352	0.4552
No log	7.0	77	0.4751	0.6872	0.337	0.436
No log	8.0	88	0.4253	0.7256	0.3439	0.4462
No log	9.0	99	0.3805	0.7335	0.3204	0.4308
No log	10.0	110	0.3562	0.7342	0.3239	0.433
No log	11.0	121	0.3275	0.7906	0.355	0.471
No log	12.0	132	0.3133	0.8382	0.3838	0.5061
No log	13.0	143	0.2996	0.8409	0.3841	0.5062
No log	14.0	154	0.2903	0.8304	0.3763	0.4978
No log	15.0	165	0.2867	0.8409	0.3841	0.5062
No log	16.0	176	0.2786	0.8409	0.3841	0.5062
No log	17.0	187	0.2711	0.8409	0.3841	0.5062
No log	18.0	198	0.2673	0.8409	0.3841	0.5062
No log	19.0	209	0.2643	0.8471	0.3841	0.5064
No log	20.0	220	0.2640	0.8471	0.3841	0.5064

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1