google-research / albert

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Apache License 2.0
3.23k stars 570 forks source link

Albert-base-v2 training data #225

Open slvcsl opened 4 years ago

slvcsl commented 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