t5-text2sql_v1 / README.md
mousaazari's picture
update model card README.md
0651066
|
raw
history blame
4.42 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: t5-text2sql_v1
    results: []

t5-text2sql_v1

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1192
  • Rouge2 Precision: 0.7957
  • Rouge2 Recall: 0.1732
  • Rouge2 Fmeasure: 0.2797

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 68 0.4893 0.5045 0.1277 0.2011
No log 2.0 136 0.3149 0.6629 0.1483 0.2391
No log 3.0 204 0.2463 0.7023 0.1501 0.2438
No log 4.0 272 0.2131 0.7077 0.1542 0.2491
No log 5.0 340 0.1964 0.7246 0.1572 0.254
No log 6.0 408 0.1819 0.7362 0.1582 0.2563
No log 7.0 476 0.1662 0.729 0.1588 0.2565
0.4062 8.0 544 0.1628 0.7666 0.166 0.2683
0.4062 9.0 612 0.1565 0.7486 0.1625 0.2625
0.4062 10.0 680 0.1522 0.756 0.1652 0.2667
0.4062 11.0 748 0.1436 0.741 0.1584 0.2574
0.4062 12.0 816 0.1450 0.7478 0.1624 0.2627
0.4062 13.0 884 0.1369 0.7563 0.1672 0.2696
0.4062 14.0 952 0.1356 0.7508 0.163 0.2638
0.128 15.0 1020 0.1318 0.7606 0.1645 0.2669
0.128 16.0 1088 0.1325 0.7805 0.1715 0.2768
0.128 17.0 1156 0.1273 0.7742 0.1688 0.2727
0.128 18.0 1224 0.1265 0.7842 0.1716 0.2771
0.128 19.0 1292 0.1264 0.7787 0.1696 0.2741
0.128 20.0 1360 0.1247 0.7856 0.172 0.2776
0.128 21.0 1428 0.1237 0.7754 0.1688 0.2734
0.128 22.0 1496 0.1226 0.7835 0.1697 0.2747
0.0903 23.0 1564 0.1225 0.78 0.1683 0.2725
0.0903 24.0 1632 0.1207 0.7824 0.17 0.2753
0.0903 25.0 1700 0.1208 0.7864 0.1702 0.2756
0.0903 26.0 1768 0.1206 0.7885 0.1722 0.2783
0.0903 27.0 1836 0.1189 0.788 0.1719 0.2778
0.0903 28.0 1904 0.1199 0.8001 0.1742 0.2814
0.0903 29.0 1972 0.1195 0.7957 0.1732 0.2797
0.0753 30.0 2040 0.1192 0.7957 0.1732 0.2797

Framework versions

  • Transformers 4.21.2
  • Pytorch 1.12.1+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1