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: 0.2426
• Rouge2 Precision: 0.7507
• Rouge2 Recall: 0.2125
• Rouge2 Fmeasure: 0.33

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	68	0.9486	0.583	0.1837	0.2781
No log	2.0	136	0.5544	0.6286	0.1739	0.2718
No log	3.0	204	0.4408	0.6653	0.1854	0.2892
No log	4.0	272	0.3656	0.6999	0.1959	0.3048
No log	5.0	340	0.3403	0.7304	0.2022	0.3157
No log	6.0	408	0.3162	0.7358	0.2044	0.3188
No log	7.0	476	0.2889	0.7331	0.2033	0.317
0.7496	8.0	544	0.2918	0.7219	0.2013	0.3137
0.7496	9.0	612	0.2745	0.73	0.2045	0.3182
0.7496	10.0	680	0.2699	0.7365	0.204	0.3185
0.7496	11.0	748	0.2626	0.7418	0.2071	0.3228
0.7496	12.0	816	0.2623	0.7316	0.2059	0.3204
0.7496	13.0	884	0.2513	0.7476	0.21	0.3269
0.7496	14.0	952	0.2507	0.7417	0.2109	0.3275
0.2318	15.0	1020	0.2457	0.7378	0.2071	0.3224
0.2318	16.0	1088	0.2414	0.7384	0.2077	0.323
0.2318	17.0	1156	0.2420	0.7555	0.2134	0.3316
0.2318	18.0	1224	0.2439	0.7493	0.2104	0.3273
0.2318	19.0	1292	0.2415	0.7514	0.2121	0.3296
0.2318	20.0	1360	0.2426	0.7507	0.2125	0.33

Framework versions

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