t5-text2sql_v1 / README.md
mousaazari's picture
update model card README.md
52e03ef
|
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: 0.1245
  • Rouge2 Precision: 0.7634
  • Rouge2 Recall: 0.1643
  • Rouge2 Fmeasure: 0.2668

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 0.7074 0.5932 0.1448 0.2296
No log 2.0 136 0.3721 0.6346 0.1387 0.225
No log 3.0 204 0.2772 0.6492 0.1436 0.2322
No log 4.0 272 0.2343 0.6778 0.1452 0.2358
No log 5.0 340 0.2119 0.7235 0.1533 0.2495
No log 6.0 408 0.1922 0.7267 0.1583 0.2556
No log 7.0 476 0.1807 0.7299 0.1575 0.2551
0.5699 8.0 544 0.1772 0.7163 0.1541 0.25
0.5699 9.0 612 0.1612 0.729 0.156 0.2533
0.5699 10.0 680 0.1610 0.7354 0.1563 0.2541
0.5699 11.0 748 0.1534 0.7397 0.158 0.2566
0.5699 12.0 816 0.1483 0.7497 0.1602 0.2601
0.5699 13.0 884 0.1456 0.7579 0.1664 0.2684
0.5699 14.0 952 0.1430 0.7528 0.161 0.2615
0.1382 15.0 1020 0.1383 0.7492 0.1624 0.2632
0.1382 16.0 1088 0.1386 0.7525 0.1623 0.263
0.1382 17.0 1156 0.1357 0.7644 0.1649 0.2674
0.1382 18.0 1224 0.1337 0.7396 0.1602 0.2599
0.1382 19.0 1292 0.1336 0.7498 0.1606 0.2609
0.1382 20.0 1360 0.1300 0.7529 0.1617 0.2626
0.1382 21.0 1428 0.1299 0.7522 0.1631 0.2645
0.1382 22.0 1496 0.1280 0.7585 0.1635 0.2654
0.0969 23.0 1564 0.1263 0.7601 0.1648 0.2669
0.0969 24.0 1632 0.1265 0.7683 0.1649 0.268
0.0969 25.0 1700 0.1263 0.7755 0.1677 0.2717
0.0969 26.0 1768 0.1251 0.7675 0.1653 0.2684
0.0969 27.0 1836 0.1243 0.7743 0.1684 0.2728
0.0969 28.0 1904 0.1247 0.7673 0.1656 0.2689
0.0969 29.0 1972 0.1245 0.7634 0.1643 0.2668
0.0807 30.0 2040 0.1245 0.7634 0.1643 0.2668

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.12.1+cu113
  • Datasets 2.7.1
  • Tokenizers 0.13.2