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
37a46351
Commit
37a46351
authored
Nov 28, 2023
by
lintangsutawika
Browse files
reformat
parent
525afc17
Changes
122
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
20 additions
and
20 deletions
+20
-20
lm_eval/tasks/code_x_glue/code-text/ruby.yaml
lm_eval/tasks/code_x_glue/code-text/ruby.yaml
+1
-1
lm_eval/tasks/coqa/default.yaml
lm_eval/tasks/coqa/default.yaml
+1
-1
lm_eval/tasks/crows_pairs/crows_pairs_english.yaml
lm_eval/tasks/crows_pairs/crows_pairs_english.yaml
+1
-1
lm_eval/tasks/csatqa/_default_csatqa_yaml
lm_eval/tasks/csatqa/_default_csatqa_yaml
+1
-1
lm_eval/tasks/drop/default.yaml
lm_eval/tasks/drop/default.yaml
+1
-1
lm_eval/tasks/glue/cola/default.yaml
lm_eval/tasks/glue/cola/default.yaml
+1
-1
lm_eval/tasks/glue/mnli/default.yaml
lm_eval/tasks/glue/mnli/default.yaml
+1
-1
lm_eval/tasks/glue/mrpc/default.yaml
lm_eval/tasks/glue/mrpc/default.yaml
+1
-1
lm_eval/tasks/glue/qnli/default.yaml
lm_eval/tasks/glue/qnli/default.yaml
+1
-1
lm_eval/tasks/glue/qqp/default.yaml
lm_eval/tasks/glue/qqp/default.yaml
+1
-1
lm_eval/tasks/glue/rte/default.yaml
lm_eval/tasks/glue/rte/default.yaml
+1
-1
lm_eval/tasks/glue/sst/default.yaml
lm_eval/tasks/glue/sst/default.yaml
+1
-1
lm_eval/tasks/glue/wnli/default.yaml
lm_eval/tasks/glue/wnli/default.yaml
+1
-1
lm_eval/tasks/gsm8k/gsm8k-cot-self-consistency.yaml
lm_eval/tasks/gsm8k/gsm8k-cot-self-consistency.yaml
+1
-1
lm_eval/tasks/gsm8k/gsm8k-cot.yaml
lm_eval/tasks/gsm8k/gsm8k-cot.yaml
+1
-1
lm_eval/tasks/gsm8k/gsm8k.yaml
lm_eval/tasks/gsm8k/gsm8k.yaml
+1
-1
lm_eval/tasks/headqa/headqa_en.yaml
lm_eval/tasks/headqa/headqa_en.yaml
+1
-1
lm_eval/tasks/hellaswag/hellaswag.yaml
lm_eval/tasks/hellaswag/hellaswag.yaml
+1
-1
lm_eval/tasks/hendrycks_ethics/commonsense.yaml
lm_eval/tasks/hendrycks_ethics/commonsense.yaml
+1
-1
lm_eval/tasks/hendrycks_ethics/justice.yaml
lm_eval/tasks/hendrycks_ethics/justice.yaml
+1
-1
No files found.
lm_eval/tasks/code_x_glue/code-text/ruby.yaml
View file @
37a46351
...
...
@@ -18,4 +18,4 @@ metric_list:
aggregation
:
mean
higher_is_better
:
True
metadata
:
-
version
:
2.0
\ No newline at end of file
-
version
:
2.0
lm_eval/tasks/coqa/default.yaml
View file @
37a46351
...
...
@@ -19,4 +19,4 @@ metric_list:
aggregation
:
mean
higher_is_better
:
true
metadata
:
-
version
:
2.0
\ No newline at end of file
-
version
:
2.0
lm_eval/tasks/crows_pairs/crows_pairs_english.yaml
View file @
37a46351
...
...
@@ -20,4 +20,4 @@ metric_list:
aggregation
:
mean
higher_is_better
:
false
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/csatqa/_default_csatqa_yaml
View file @
37a46351
...
...
@@ -14,4 +14,4 @@ metric_list:
aggregation: mean
higher_is_better: true
metadata:
- version: 0.0
\ No newline at end of file
- version: 0.0
lm_eval/tasks/drop/default.yaml
View file @
37a46351
...
...
@@ -21,4 +21,4 @@ metric_list:
aggregation
:
mean
higher_is_better
:
true
metadata
:
-
version
:
2.0
\ No newline at end of file
-
version
:
2.0
lm_eval/tasks/glue/cola/default.yaml
View file @
37a46351
...
...
@@ -13,4 +13,4 @@ doc_to_decontamination_query: sentence
metric_list
:
-
metric
:
mcc
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/glue/mnli/default.yaml
View file @
37a46351
...
...
@@ -11,4 +11,4 @@ doc_to_choice: ["True", "Neither", "False"]
metric_list
:
-
metric
:
acc
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/glue/mrpc/default.yaml
View file @
37a46351
...
...
@@ -12,4 +12,4 @@ metric_list:
-
metric
:
acc
-
metric
:
f1
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/glue/qnli/default.yaml
View file @
37a46351
...
...
@@ -11,4 +11,4 @@ doc_to_choice: ["yes", "no"]
metric_list
:
-
metric
:
acc
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/glue/qqp/default.yaml
View file @
37a46351
...
...
@@ -13,4 +13,4 @@ metric_list:
-
metric
:
acc
-
metric
:
f1
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/glue/rte/default.yaml
View file @
37a46351
...
...
@@ -11,4 +11,4 @@ doc_to_choice: ["True", "False"]
metric_list
:
-
metric
:
acc
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/glue/sst/default.yaml
View file @
37a46351
...
...
@@ -11,4 +11,4 @@ doc_to_choice: ["negative", "positive"]
metric_list
:
-
metric
:
acc
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/glue/wnli/default.yaml
View file @
37a46351
...
...
@@ -11,4 +11,4 @@ doc_to_choice: ["False", "True"]
metric_list
:
-
metric
:
acc
metadata
:
-
version
:
2.0
\ No newline at end of file
-
version
:
2.0
lm_eval/tasks/gsm8k/gsm8k-cot-self-consistency.yaml
View file @
37a46351
...
...
@@ -31,4 +31,4 @@ filter_list:
-
function
:
"
majority_vote"
-
function
:
"
take_first"
metadata
:
-
version
:
0.0
\ No newline at end of file
-
version
:
0.0
lm_eval/tasks/gsm8k/gsm8k-cot.yaml
View file @
37a46351
...
...
@@ -41,4 +41,4 @@ filter_list:
regex_pattern
:
"
The
answer
is
(
\\
-?[0-9
\\
.
\\
,]+)."
-
function
:
"
take_first"
metadata
:
-
version
:
0.0
\ No newline at end of file
-
version
:
0.0
lm_eval/tasks/gsm8k/gsm8k.yaml
View file @
37a46351
...
...
@@ -34,4 +34,4 @@ filter_list:
regex_pattern
:
"
####
(
\\
-?[0-9
\\
.
\\
,]+)"
-
function
:
"
take_first"
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/headqa/headqa_en.yaml
View file @
37a46351
...
...
@@ -20,4 +20,4 @@ metric_list:
aggregation
:
mean
higher_is_better
:
true
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/hellaswag/hellaswag.yaml
View file @
37a46351
...
...
@@ -19,4 +19,4 @@ metric_list:
aggregation
:
mean
higher_is_better
:
true
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/hendrycks_ethics/commonsense.yaml
View file @
37a46351
...
...
@@ -12,4 +12,4 @@ doc_to_choice: ['no', 'yes']
metric_list
:
-
metric
:
acc
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
lm_eval/tasks/hendrycks_ethics/justice.yaml
View file @
37a46351
...
...
@@ -6,4 +6,4 @@ dataset_name: justice
doc_to_text
:
"
Question:
Would
most
people
believe
this
reasonable
or
unreasonable
to
say?
\"
{{scenario}}
\"\n
Answer:"
# TODO: impl. exact match for this and deontology
metadata
:
-
version
:
1.0
\ No newline at end of file
-
version
:
1.0
Prev
1
2
3
4
5
6
7
Next
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