t5-base-wikisql

This model is a fine-tuned version of t5-base on the wikisql dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0822
  • Rouge2 Precision: 0.8552
  • Rouge2 Recall: 0.7632
  • Rouge2 Fmeasure: 0.7994

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: 100
  • eval_batch_size: 100
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge2 Precision Rouge2 Recall Rouge2 Fmeasure
0.3772 1.0 648 0.1194 0.8164 0.7266 0.7619
0.1367 2.0 1296 0.1029 0.8322 0.7413 0.777
0.1184 3.0 1944 0.0960 0.839 0.7477 0.7837
0.0999 4.0 2592 0.0920 0.8447 0.7527 0.789
0.0943 5.0 3240 0.0884 0.8473 0.7549 0.7913
0.0886 6.0 3888 0.0868 0.8494 0.7568 0.7933
0.0821 7.0 4536 0.0852 0.8516 0.7588 0.7954
0.0792 8.0 5184 0.0845 0.8534 0.7605 0.7971
0.0765 9.0 5832 0.0836 0.8539 0.7622 0.7983
0.0741 10.0 6480 0.0825 0.8536 0.7616 0.7978
0.0708 11.0 7128 0.0827 0.8548 0.7625 0.7989
0.0693 12.0 7776 0.0822 0.8547 0.7629 0.799
0.0686 13.0 8424 0.0822 0.855 0.7631 0.7993
0.0672 14.0 9072 0.0823 0.8553 0.7633 0.7995
0.0664 15.0 9720 0.0822 0.8552 0.7632 0.7994

Framework versions

  • Transformers 4.26.1
  • Pytorch 2.0.1
  • Datasets 2.14.7
  • Tokenizers 0.13.3
Downloads last month
11
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train e22vvb/t5-base-wikisql