CoolFace
Modelpublic

ConvLab/mt5-small-dst-crosswoz

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
3likes11downloads
Model Card

mt5-small-dst-crosswoz

This model is a fine-tuned version of mt5-small on CrossWOZ.

Refer to ConvLab-3 for model description and usage.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.001
  • trainbatchsize: 16
  • evalbatchsize: 16
  • seed: 42
  • gradientaccumulationsteps: 4
  • totaltrainbatch_size: 64
  • optimizer: Adafactor
  • lrschedulertype: linear
  • num_epochs: 10.0

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.11.0+cu113
  • Datasets 2.3.2
  • Tokenizers 0.12.1