Correctly Print Task Versioning (#1173)

* change version field formatting in metadata

* mention versioning in new task guide

* add instructions for changelog

* run linters

lm_eval/tasks/code_x_glue/code-text/php.yaml

@@ -18,4 +18,4 @@ metric_list:
     aggregation: mean
     higher_is_better: True
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/code_x_glue/code-text/python.yaml

@@ -18,4 +18,4 @@ metric_list:
     aggregation: mean
     higher_is_better: True
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/code_x_glue/code-text/ruby.yaml

@@ -18,4 +18,4 @@ metric_list:
     aggregation: mean
     higher_is_better: True
 metadata:
-  - version: 2.0
+  version: 2.0

lm_eval/tasks/coqa/default.yaml

@@ -19,4 +19,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 2.0
+  version: 2.0

lm_eval/tasks/crows_pairs/crows_pairs_english.yaml

@@ -20,4 +20,4 @@ metric_list:
     aggregation: mean
     higher_is_better: false
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/csatqa/_default_csatqa_yaml

@@ -14,4 +14,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/drop/default.yaml

@@ -21,4 +21,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 2.0
+  version: 2.0

lm_eval/tasks/fld/fld_default.yaml

@@ -12,3 +12,5 @@ metric_list:
   - metric: exact_match
     aggregation: mean
     higher_is_better: true
+metadata:
+  version: 0.0

lm_eval/tasks/glue/cola/default.yaml

@@ -13,4 +13,4 @@ doc_to_decontamination_query: sentence
 metric_list:
   - metric: mcc
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/glue/mnli/default.yaml

@@ -11,4 +11,4 @@ doc_to_choice: ["True", "Neither", "False"]
 metric_list:
   - metric: acc
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/glue/mrpc/default.yaml

@@ -12,4 +12,4 @@ metric_list:
   - metric: acc
   - metric: f1
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/glue/qnli/default.yaml

@@ -11,4 +11,4 @@ doc_to_choice: ["yes", "no"]
 metric_list:
   - metric: acc
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/glue/qqp/default.yaml

@@ -12,4 +12,4 @@ metric_list:
   - metric: acc
   - metric: f1
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/glue/rte/default.yaml

@@ -11,4 +11,4 @@ doc_to_choice: ["True", "False"]
 metric_list:
   - metric: acc
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/glue/sst2/default.yaml

@@ -11,4 +11,4 @@ doc_to_choice: ["negative", "positive"]
 metric_list:
   - metric: acc
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/glue/wnli/default.yaml

@@ -11,4 +11,4 @@ doc_to_choice: ["False", "True"]
 metric_list:
   - metric: acc
 metadata:
-  - version: 2.0
+  version: 2.0

lm_eval/tasks/gsm8k/gsm8k-cot-self-consistency.yaml

@@ -31,4 +31,4 @@ filter_list:
       - function: "majority_vote"
       - function: "take_first"
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/gsm8k/gsm8k-cot.yaml

@@ -41,4 +41,4 @@ filter_list:
         regex_pattern: "The answer is (\\-?[0-9\\.\\,]+)."
       - function: "take_first"
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/gsm8k/gsm8k.yaml

@@ -34,4 +34,4 @@ filter_list:
         regex_pattern: "#### (\\-?[0-9\\.\\,]+)"
       - function: "take_first"
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/headqa/headqa_en.yaml

@@ -20,4 +20,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 1.0
+  version: 1.0