README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: t5-text2sql_v1
    results: []

t5-text2sql_v1

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

• Loss: 0.2037
• Rouge2 Precision: 0.8622
• Rouge2 Recall: 0.3895
• Rouge2 Fmeasure: 0.5158

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	1.0411	0.1107	0.0324	0.0483
No log	2.0	22	0.7306	0.3176	0.132	0.1803
No log	3.0	33	0.5673	0.5279	0.243	0.3215
No log	4.0	44	0.4535	0.7171	0.3205	0.4264
No log	5.0	55	0.3911	0.7334	0.3252	0.4335
No log	6.0	66	0.3657	0.7668	0.3432	0.4565
No log	7.0	77	0.3265	0.7596	0.333	0.4445
No log	8.0	88	0.2986	0.8095	0.3576	0.477
No log	9.0	99	0.2798	0.805	0.3624	0.4818
No log	10.0	110	0.2619	0.8206	0.3663	0.4879
No log	11.0	121	0.2454	0.8194	0.3663	0.4878
No log	12.0	132	0.2379	0.8274	0.3706	0.493
No log	13.0	143	0.2292	0.8359	0.3768	0.5008
No log	14.0	154	0.2241	0.8707	0.3994	0.5261
No log	15.0	165	0.2208	0.8618	0.3882	0.5142
No log	16.0	176	0.2150	0.8618	0.3882	0.5142
No log	17.0	187	0.2099	0.8618	0.3882	0.5142
No log	18.0	198	0.2068	0.8622	0.3895	0.5158
No log	19.0	209	0.2042	0.8622	0.3895	0.5158
No log	20.0	220	0.2037	0.8622	0.3895	0.5158

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1