a question about run_classifier.py

pmichel31415 / are-16-heads-really-better-than-1

Code for the paper "Are Sixteen Heads Really Better than One?"

MIT License

165 stars 14 forks source link

a question about run_classifier.py #5

Closed Ixuanzhang closed 4 years ago

Ixuanzhang commented 4 years ago

1、 (1)I do this and get a pruned model: model.bert.prune_heads(to_prune) (2) I set n_retrain_steps_after_pruning a value greater than 0 next： aaa then:

bbb

  to retrain my pruned model, that is ok?

2、I don't understand the difference between above method and retrain_pruned_heads（the following method）

cccc

THANK YOU !

pmichel31415 commented 4 years ago

Sorry for the late reply, did you figure this out?