I noticed that the prompt Template of the paper contains a line break at the end,

but the actual inference code will remove the line break by default when using the Jinja Template:
# obtain prompt
def get_prompt(data_i):
return Template(system_prompts).render(problem = data_i["question"])
This can make a difference in the reproducibility of the experiment.
So I set keep_trailing_newline=True in the code to prevent this problem:
# obtain prompt
def get_prompt(data_i):
return Template(system_prompts, keep_trailing_newline=True).render(problem = data_i["question"])
Here's my experimental results on the MATH500 dataset (using TraDo-8B-Instruct) :
| Whether to remove the newline character |
ACC |
| No |
75.46666666666667 |
| Yes |
74.86666666667 |
The experimental results with end-of-line breaks (75.46...) are very close to the reported value (75.5) ! I have created a PR to fix it: #39
I noticed that the prompt Template of the paper contains a line break at the end,

but the actual inference code will remove the line break by default when using the Jinja Template:
This can make a difference in the reproducibility of the experiment.
So I set
keep_trailing_newline=Truein the code to prevent this problem:Here's my experimental results on the MATH500 dataset (using TraDo-8B-Instruct) :
The experimental results with end-of-line breaks (75.46...) are very close to the reported value (75.5) ! I have created a PR to fix it: #39