ConvLab/mt5-small-nlu-all-crosswoz

mt5-small-nlu-all-crosswoz

This model is a fine-tuned version of mt5-small on CrossWOZ both user and system utterances.

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: 16
• —totaltrainbatch_size: 256
• —optimizer: Adafactor
• —lrschedulertype: linear
• —num_epochs: 10.0

Framework versions

• —Transformers 4.20.1
• —Pytorch 1.11.0+cu102
• —Datasets 2.3.2
• —Tokenizers 0.12.1