Open slvcsl opened 4 years ago
Which training data is used for albert in v2? You mention that "In this version, we apply 'no dropout', 'additional training data' and 'long training time' strategies to all models". Thanks
Which training data is used for albert in v2? You mention that "In this version, we apply 'no dropout', 'additional training data' and 'long training time' strategies to all models". Thanks