Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
lm-evaluation-harness
Commits
aa44be3f
Commit
aa44be3f
authored
Dec 27, 2023
by
lintangsutawika
Browse files
fixed piqa ov
parent
379bb7eb
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
7 additions
and
36 deletions
+7
-36
lm_eval/tasks/piqa/alternative_worlds/output_variation/_piqa_alt_ov_yaml
...iqa/alternative_worlds/output_variation/_piqa_alt_ov_yaml
+6
-10
lm_eval/tasks/piqa/alternative_worlds/output_variation/styles.py
.../tasks/piqa/alternative_worlds/output_variation/styles.py
+1
-1
lm_eval/tasks/piqa/alternative_worlds/prompt_variation/_piqa_yaml
...tasks/piqa/alternative_worlds/prompt_variation/_piqa_yaml
+0
-25
No files found.
lm_eval/tasks/piqa/alternative_worlds/output_variation/_piqa_alt_ov_yaml
View file @
aa44be3f
group:
- ai2_arc
task: piqa
dataset_path: ai2_arc
dataset_name: ARC-Easy
dataset_path: piqa
output_type: multiple_choice
training_split: train
validation_split: validation
test_split: test
doc_to_text: "Question: {{question}}\nAnswer:"
doc_to_target: "{{choices.label.index(answerKey)}}"
doc_to_choice: "{{choices.text}}"
doc_to_text: "Question: {{goal}}\nAnswer:"
doc_to_target: label
doc_to_choice: "{{[sol1, sol2]}}"
should_decontaminate: true
doc_to_decontamination_query: "Question: {{question}}\nAnswer:"
metric_list:
- metric: acc
aggregation: mean
...
...
@@ -22,3 +16,5 @@ metric_list:
- metric: brier_score
aggregation: brier_score
higher_is_better: false
metadata:
- version: 1.0
lm_eval/tasks/piqa/alternative_worlds/output_variation/styles.py
View file @
aa44be3f
...
...
@@ -27,7 +27,7 @@ def doc_to_text_base(alphabet, style, doc):
# Full continuation
def
choice_A
(
doc
):
return
doc
[
"
choices"
][
"text
"
]
return
[
doc
[
"
sol1"
],
doc
[
"sol2
"
]
]
# Letters only
...
...
lm_eval/tasks/piqa/alternative_worlds/prompt_variation/_piqa_yaml
View file @
aa44be3f
# dataset_path: ai2_arc
# dataset_name: ARC-Easy
# output_type: multiple_choice
# training_split: train
# validation_split: validation
# test_split: test
# doc_to_text: "Question: {{question}}\nAnswer:"
# doc_to_target: "{{choices.label.index(answerKey)}}"
# doc_to_choice: "{{choices.text}}"
# should_decontaminate: true
# doc_to_decontamination_query: "Question: {{question}}\nAnswer:"
# metric_list:
# - metric: acc
# aggregation: mean
# higher_is_better: true
# - metric: acc_norm
# aggregation: mean
# higher_is_better: true
# - metric: brier_score
# aggregation: brier_score
# higher_is_better: false
dataset_path: piqa
dataset_name: null
output_type: multiple_choice
training_split: train
validation_split: validation
test_split: null
doc_to_text: "Question: {{goal}}\nAnswer:"
doc_to_target: label
doc_to_choice: "{{[sol1, sol2]}}"
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment