Closed xguo7 closed 1 year ago
Hi, we have released the training hyper-parameters in the run_exp.py. From your results, the BLEU score is much lower than expected and is problematic. To reproduce the results, please use our released finetuned checkpoints here.
Hello,
I tried to follow the instructions to fine-tune the code generation task in Concode dataset, but failed to get the similar results as shown in the paper. What I got is: Bleu: 26.88, EM: 21.30.
Could you provide all the hyper-parameters regarding the fine-tuning on Concorde datasets? Thank you!