Correctly Print Task Versioning (#1173)

* change version field formatting in metadata * mention versioning in new task guide * add instructions for changelog * run linters

Correctly Print Task Versioning (#1173)
* change version field formatting in metadata * mention versioning in new task guide * add instructions for changelog * run linters
9cd79897 · Hailey Schoelkopf · GitHub · a0cfe3f6 · 9cd79897 · 9cd79897
Unverified Commit 9cd79897 authored Dec 21, 2023 by Hailey Schoelkopf Committed by GitHub Dec 21, 2023
20 changed files
--- a/lm_eval/tasks/mgsm/native_cot/cot_yaml
+++ b/lm_eval/tasks/mgsm/native_cot/cot_yaml
@@ -28,4 +28,4 @@ filter_list:
        regex_pattern: "The answer is (\\-?[0-9\\.\\,]+)"
      - function: "take_first"
 metadata:
-  - version: 1.0
+  version: 1.0
--- a/lm_eval/tasks/minerva_math/minerva_math_algebra.yaml
+++ b/lm_eval/tasks/minerva_math/minerva_math_algebra.yaml
@@ -21,4 +21,4 @@ metric_list:
    higher_is_better: true
 num_fewshot: 0
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/mmlu/default/_default_template_yaml
+++ b/lm_eval/tasks/mmlu/default/_default_template_yaml
@@ -12,4 +12,4 @@ metric_list:
    aggregation: mean
    higher_is_better: true
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/mmlu/flan_cot_fewshot/_mmlu_flan_cot_fewshot_template_yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_fewshot/_mmlu_flan_cot_fewshot_template_yaml
@@ -23,4 +23,4 @@ metric_list:
    ignore_case: true
    ignore_punctuation: true
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu_flan_cot_zeroshot_template_yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu_flan_cot_zeroshot_template_yaml
@@ -23,4 +23,4 @@ metric_list:
    ignore_case: true
    ignore_punctuation: true
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu_flan_generative_template_yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu_flan_generative_template_yaml
@@ -13,4 +13,4 @@ metric_list:
    aggregation: mean
    higher_is_better: true
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu_flan_loglikelihood_template_yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu_flan_loglikelihood_template_yaml
@@ -13,4 +13,4 @@ metric_list:
    aggregation: mean
    higher_is_better: true
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/model_written_evals/advanced_ai_risk/_template_yaml
+++ b/lm_eval/tasks/model_written_evals/advanced_ai_risk/_template_yaml
@@ -11,4 +11,4 @@ doc_to_decontamination_query: "{{sentence_good}} {{sentence_bad}}"
 metric_list:
  - metric: acc
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/model_written_evals/persona/_template_yaml
+++ b/lm_eval/tasks/model_written_evals/persona/_template_yaml
@@ -9,4 +9,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}"
 metric_list:
  - metric: acc
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_nlp_survey.yaml
+++ b/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_nlp_survey.yaml
@@ -11,4 +11,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}"
 metric_list:
  - metric: acc
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_philpapers2020.yaml
+++ b/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_philpapers2020.yaml
@@ -11,4 +11,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}"
 metric_list:
  - metric: acc
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_political_typology_quiz.yaml
+++ b/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_political_typology_quiz.yaml
@@ -11,4 +11,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}"
 metric_list:
  - metric: acc
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/model_written_evals/winogenerated/_template_yaml
+++ b/lm_eval/tasks/model_written_evals/winogenerated/_template_yaml
@@ -9,4 +9,4 @@ doc_to_choice: "{{[answer_matching_behavior, answer_not_matching_behavior]}}"
 metric_list:
  - metric: acc
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/mutual/mutual.yaml
+++ b/lm_eval/tasks/mutual/mutual.yaml
@@ -22,4 +22,4 @@ metric_list:
    aggregation: mean
    higher_is_better: true
 metadata:
-  - version: 2.0
+  version: 2.0
--- a/lm_eval/tasks/nq_open/nq_open.yaml
+++ b/lm_eval/tasks/nq_open/nq_open.yaml
@@ -29,4 +29,4 @@ metric_list:
    regexes_to_ignore:
    - "\ban|a|the\b"
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/openbookqa/openbookqa.yaml
+++ b/lm_eval/tasks/openbookqa/openbookqa.yaml
@@ -18,4 +18,4 @@ metric_list:
    aggregation: mean
    higher_is_better: true
 metadata:
-  - version: 1.0
+  version: 1.0
--- a/lm_eval/tasks/paws-x/pawsx_template_yaml
+++ b/lm_eval/tasks/paws-x/pawsx_template_yaml
@@ -17,4 +17,4 @@ metric_list:
    aggregation: mean
    higher_is_better: true
 metadata:
-  - version: 0.0
+  version: 0.0
--- a/lm_eval/tasks/pile/pile_arxiv.yaml
+++ b/lm_eval/tasks/pile/pile_arxiv.yaml
@@ -20,4 +20,4 @@ metric_list:
    aggregation: bits_per_byte
    higher_is_better: false
 metadata:
-  - version: 2.0
+  version: 2.0
--- a/lm_eval/tasks/piqa/piqa.yaml
+++ b/lm_eval/tasks/piqa/piqa.yaml
@@ -18,4 +18,4 @@ metric_list:
    aggregation: mean
    higher_is_better: true
 metadata:
-  - version: 1.0
+  version: 1.0
--- a/lm_eval/tasks/polemo2/polemo2_in.yaml
+++ b/lm_eval/tasks/polemo2/polemo2_in.yaml
@@ -42,4 +42,4 @@ metric_list:
    aggregation: mean
    higher_is_better: true
 metadata:
-  - version: 0.0
+  version: 0.0