Skip to content

GitLab

Commit 135b41ce authored by lintangsutawika's avatar lintangsutawika
Browse files

format

parent 0436b5d6
Show whitespace changes
Inline Side-by-side
Showing with 23 additions and 21 deletions
lm_eval/tasks/truthfulqa/utils.py
View file @ 135b41ce
...@@ -4,6 +4,7 @@ import numpy as np ...@@ -4,6 +4,7 @@ import numpy as np
from rouge_score import rouge_scorer, scoring from rouge_score import rouge_scorer, scoring
def process_results_mc2(doc, results): def process_results_mc2(doc, results):
lls, is_greedy = zip(*results) lls, is_greedy = zip(*results)
...@@ -24,7 +25,6 @@ def process_docs_gen(dataset: datasets.Dataset) -> datasets.Dataset: ...@@ -24,7 +25,6 @@ def process_docs_gen(dataset: datasets.Dataset) -> datasets.Dataset:
def preprocess_function(examples): def preprocess_function(examples):
def _format_answers(answers): def _format_answers(answers):
formatted_answers = [] formatted_answers = []
for answer in answers: for answer in answers:
...@@ -142,6 +142,7 @@ def bleu(refs, preds): ...@@ -142,6 +142,7 @@ def bleu(refs, preds):
).score ).score
return score return score
def rouge(refs, preds): def rouge(refs, preds):
""" """
Returns `t5` style ROUGE scores. See the related implementation: Returns `t5` style ROUGE scores. See the related implementation:
...@@ -169,6 +170,7 @@ def rouge(refs, preds): ...@@ -169,6 +170,7 @@ def rouge(refs, preds):
result = aggregator.aggregate() result = aggregator.aggregate()
return {type: result[type].mid.fmeasure * 100 for type in rouge_types} return {type: result[type].mid.fmeasure * 100 for type in rouge_types}
# def bleurt_max(predictions, references): # def bleurt_max(predictions, references):
# pass # pass
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment