Open ajboloor opened 1 year ago
What pipeline was used to report the finetuned accuracy numbers on fig. 5 of the paper?
Specifically, when is the masking done? Is it done only during pretraining?
Or is it done also during finetuning?
What pipeline was used to report the finetuned accuracy numbers on fig. 5 of the paper?
Specifically, when is the masking done? Is it done only during pretraining?
Or is it done also during finetuning?