Skip to content

GitLab

Commit 37a46351 authored by lintangsutawika's avatar lintangsutawika
Browse files

reformat

parent 525afc17
Hide whitespace changes
Inline Side-by-side
Showing with 20 additions and 20 deletions
lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu_flan_generative_template_yaml
View file @ 37a46351
...@@ -13,4 +13,4 @@ metric_list: ...@@ -13,4 +13,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu_flan_loglikelihood_template_yaml
View file @ 37a46351
...@@ -13,4 +13,4 @@ metric_list: ...@@ -13,4 +13,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/model_written_evals/advanced_ai_risk/_template_yaml
View file @ 37a46351
...@@ -11,4 +11,4 @@ doc_to_decontamination_query: "{{sentence_good}} {{sentence_bad}}" ...@@ -11,4 +11,4 @@ doc_to_decontamination_query: "{{sentence_good}} {{sentence_bad}}"
metric_list: metric_list:
- metric: acc - metric: acc
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/model_written_evals/persona/_template_yaml
View file @ 37a46351
...@@ -9,4 +9,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}" ...@@ -9,4 +9,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}"
metric_list: metric_list:
- metric: acc - metric: acc
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_nlp_survey.yaml
View file @ 37a46351
...@@ -11,4 +11,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}" ...@@ -11,4 +11,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}"
metric_list: metric_list:
- metric: acc - metric: acc
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_philpapers2020.yaml
View file @ 37a46351
...@@ -11,4 +11,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}" ...@@ -11,4 +11,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}"
metric_list: metric_list:
- metric: acc - metric: acc
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_political_typology_quiz.yaml
View file @ 37a46351
...@@ -11,4 +11,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}" ...@@ -11,4 +11,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}"
metric_list: metric_list:
- metric: acc - metric: acc
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/model_written_evals/winogenerated/_template_yaml
View file @ 37a46351
...@@ -9,4 +9,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}" ...@@ -9,4 +9,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}"
metric_list: metric_list:
- metric: acc - metric: acc
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/mutual/mutual.yaml
View file @ 37a46351
...@@ -22,4 +22,4 @@ metric_list: ...@@ -22,4 +22,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 2.0 - version: 2.0
\ No newline at end of file
lm_eval/tasks/nq_open/nq_open.yaml
View file @ 37a46351
...@@ -29,4 +29,4 @@ metric_list: ...@@ -29,4 +29,4 @@ metric_list:
regexes_to_ignore: regexes_to_ignore:
- "\ban|a|the\b" - "\ban|a|the\b"
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/openbookqa/openbookqa.yaml
View file @ 37a46351
...@@ -18,4 +18,4 @@ metric_list: ...@@ -18,4 +18,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 1.0 - version: 1.0
\ No newline at end of file
lm_eval/tasks/paws-x/pawsx_template_yaml
View file @ 37a46351
...@@ -17,4 +17,4 @@ metric_list: ...@@ -17,4 +17,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/pile/pile_arxiv.yaml
View file @ 37a46351
...@@ -20,4 +20,4 @@ metric_list: ...@@ -20,4 +20,4 @@ metric_list:
aggregation: bits_per_byte aggregation: bits_per_byte
higher_is_better: false higher_is_better: false
metadata: metadata:
- version: 2.0 - version: 2.0
\ No newline at end of file
lm_eval/tasks/piqa/piqa.yaml
View file @ 37a46351
...@@ -18,4 +18,4 @@ metric_list: ...@@ -18,4 +18,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 1.0 - version: 1.0
\ No newline at end of file
lm_eval/tasks/polemo2/polemo2_in.yaml
View file @ 37a46351
...@@ -42,4 +42,4 @@ metric_list: ...@@ -42,4 +42,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 0.0 - version: 0.0
\ No newline at end of file
lm_eval/tasks/prost/corypaik_prost.yaml
View file @ 37a46351
...@@ -16,4 +16,4 @@ metric_list: ...@@ -16,4 +16,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 1.0 - version: 1.0
\ No newline at end of file
lm_eval/tasks/pubmedqa/pubmedqa.yaml
View file @ 37a46351
...@@ -13,4 +13,4 @@ metric_list: ...@@ -13,4 +13,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 1.0 - version: 1.0
\ No newline at end of file
lm_eval/tasks/qa4mre/qa4mre_2011.yaml
View file @ 37a46351
...@@ -19,4 +19,4 @@ metric_list: ...@@ -19,4 +19,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 1.0 - version: 1.0
\ No newline at end of file
lm_eval/tasks/qasper/bool.yaml
View file @ 37a46351
...@@ -11,4 +11,4 @@ doc_to_choice: ["no", "yes"] ...@@ -11,4 +11,4 @@ doc_to_choice: ["no", "yes"]
metric_list: metric_list:
- metric: f1 - metric: f1
metadata: metadata:
- version: 1.0 - version: 1.0
\ No newline at end of file
lm_eval/tasks/qasper/freeform.yaml
View file @ 37a46351
...@@ -15,4 +15,4 @@ metric_list: ...@@ -15,4 +15,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 1.0 - version: 1.0
\ No newline at end of file
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