t5-text2sql_v1 / README.md
mousaazari's picture
update model card README.md
3c50c5b
|
raw
history blame
4.48 kB
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: 0.1260
  • Rouge2 Precision: 0.7647
  • Rouge2 Recall: 0.1682
  • Rouge2 Fmeasure: 0.2715

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 0.6880 0.5449 0.1342 0.2115
No log 2.0 136 0.3651 0.6371 0.1381 0.2242
No log 3.0 204 0.2780 0.6573 0.143 0.2322
No log 4.0 272 0.2347 0.6729 0.144 0.2342
No log 5.0 340 0.2160 0.7186 0.1544 0.2505
No log 6.0 408 0.1963 0.7025 0.1523 0.2465
No log 7.0 476 0.1797 0.7246 0.1564 0.2536
0.5593 8.0 544 0.1781 0.7285 0.1551 0.2521
0.5593 9.0 612 0.1674 0.7353 0.1583 0.2564
0.5593 10.0 680 0.1622 0.7412 0.1585 0.2572
0.5593 11.0 748 0.1525 0.7274 0.1559 0.2528
0.5593 12.0 816 0.1542 0.7399 0.158 0.2565
0.5593 13.0 884 0.1462 0.7575 0.1642 0.2655
0.5593 14.0 952 0.1453 0.7599 0.1632 0.265
0.1388 15.0 1020 0.1415 0.7601 0.1635 0.2654
0.1388 16.0 1088 0.1404 0.7622 0.1644 0.2663
0.1388 17.0 1156 0.1349 0.7673 0.1646 0.2673
0.1388 18.0 1224 0.1325 0.758 0.1624 0.264
0.1388 19.0 1292 0.1347 0.7713 0.1691 0.2731
0.1388 20.0 1360 0.1343 0.7664 0.1679 0.2711
0.1388 21.0 1428 0.1333 0.7547 0.1631 0.2644
0.1388 22.0 1496 0.1315 0.7649 0.1662 0.2687
0.0973 23.0 1564 0.1297 0.7615 0.1659 0.2683
0.0973 24.0 1632 0.1295 0.7588 0.1657 0.2679
0.0973 25.0 1700 0.1289 0.7636 0.1662 0.2692
0.0973 26.0 1768 0.1282 0.7689 0.1671 0.2705
0.0973 27.0 1836 0.1273 0.7675 0.1684 0.272
0.0973 28.0 1904 0.1270 0.7652 0.1672 0.2703
0.0973 29.0 1972 0.1260 0.7647 0.1682 0.2715
0.0813 30.0 2040 0.1260 0.7647 0.1682 0.2715

Framework versions

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