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: 0.2541
• Rouge2 Precision: 0.8524
• Rouge2 Recall: 0.3329
• Rouge2 Fmeasure: 0.462

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	3.1289	0.0456	0.0134	0.0207
No log	2.0	22	2.0536	0.0472	0.0134	0.0208
No log	3.0	33	1.4151	0.0519	0.0149	0.0231
No log	4.0	44	0.9640	0.0484	0.0134	0.0209
No log	5.0	55	0.7020	0.4762	0.1867	0.2605
No log	6.0	66	0.5500	0.6708	0.2613	0.3658
No log	7.0	77	0.4783	0.7633	0.2985	0.415
No log	8.0	88	0.3953	0.8121	0.3085	0.4324
No log	9.0	99	0.3533	0.8308	0.3189	0.4461
No log	10.0	110	0.3330	0.8068	0.2979	0.4262
No log	11.0	121	0.3071	0.8378	0.323	0.4534
No log	12.0	132	0.2937	0.8218	0.3121	0.4404
No log	13.0	143	0.2794	0.8414	0.3305	0.4577
No log	14.0	154	0.2741	0.8671	0.336	0.4669
No log	15.0	165	0.2690	0.8635	0.337	0.4678
No log	16.0	176	0.2627	0.8446	0.3341	0.462
No log	17.0	187	0.2583	0.8379	0.3322	0.4589
No log	18.0	198	0.2563	0.8527	0.339	0.4684
No log	19.0	209	0.2544	0.8524	0.3329	0.462
No log	20.0	220	0.2541	0.8524	0.3329	0.462

Framework versions

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