Edit model card

T5Training

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

  • Loss: 0.0341
  • Rouge2 Precision: 0.9368
  • Rouge2 Recall: 0.8687
  • Rouge2 Fmeasure: 0.896

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Rouge2 Precision Rouge2 Recall Rouge2 Fmeasure
0.0225 1.0 4049 0.0355 0.9325 0.8665 0.8929
0.0182 2.0 8098 0.0359 0.9364 0.8682 0.8956
0.016 3.0 12147 0.0354 0.9353 0.868 0.895
0.0156 4.0 16196 0.0351 0.9366 0.8684 0.8958
0.0177 5.0 20245 0.0341 0.9368 0.8687 0.896

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.13.1+cu117
  • Datasets 2.8.0
  • Tokenizers 0.13.2
Downloads last month
1

Dataset used to train vjt/T5Training