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/super_glue/record/t5-prompt.yaml

@@ -19,4 +19,4 @@ metric_list:
     aggregation: !function t5_utils.squad_f1_agg
     higher_is_better: true
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/super_glue/rte/default.yaml

@@ -12,4 +12,4 @@ doc_to_choice: ['True', 'False']
 metric_list:
   - metric: acc
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/super_glue/rte/t5-prompt.yaml

@@ -19,4 +19,4 @@ metric_list:
     ignore_case: true
     ignore_punctuation: true
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/super_glue/wic/default.yaml

@@ -12,4 +12,4 @@ doc_to_choice: ['no', 'yes']
 metric_list:
   - metric: acc
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/super_glue/wic/t5-prompt.yaml

@@ -19,4 +19,4 @@ metric_list:
     ignore_case: true
     ignore_punctuation: true
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/super_glue/wsc/default.yaml

@@ -12,4 +12,4 @@ doc_to_choice: ['no', 'yes']
 metric_list:
   - metric: acc
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/super_glue/wsc/t5-prompt.yaml

@@ -20,4 +20,4 @@ filter_list:
     filter:
       - function: !function t5_utils.WSCPostprocess
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/swag/swag.yaml

@@ -16,4 +16,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/toxigen/toxigen.yaml

@@ -15,4 +15,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/translation/wmt_common_yaml

@@ -14,4 +14,4 @@ generation_kwargs:
   temperature: 0.0
 repeats: 1
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/triviaqa/default.yaml

@@ -28,4 +28,4 @@ metric_list:
     ignore_case: true
     ignore_punctuation: true
 metadata:
-  - version: 2.0
+  version: 2.0

lm_eval/tasks/truthfulqa/truthfulqa_gen.yaml

@@ -76,4 +76,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 2.0
+  version: 2.0

lm_eval/tasks/truthfulqa/truthfulqa_mc1.yaml

@@ -33,4 +33,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 2.0
+  version: 2.0

lm_eval/tasks/truthfulqa/truthfulqa_mc2.yaml

@@ -10,4 +10,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 2.0
+  version: 2.0

lm_eval/tasks/unscramble/anagrams1.yaml

@@ -17,4 +17,4 @@ metric_list:
     ignore_case: false
     ignore_punctuation: false
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/unscramble/anagrams2.yaml

@@ -17,4 +17,4 @@ metric_list:
     ignore_case: false
     ignore_punctuation: false
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/unscramble/cycle_letters.yaml

@@ -17,4 +17,4 @@ metric_list:
     ignore_case: false
     ignore_punctuation: false
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/unscramble/random_insertion.yaml

@@ -17,4 +17,4 @@ metric_list:
     ignore_case: false
     ignore_punctuation: false
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/unscramble/reversed_words.yaml

@@ -17,4 +17,4 @@ metric_list:
     ignore_case: false
     ignore_punctuation: false
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/webqs/webqs.yaml

@@ -17,4 +17,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 1.0
+  version: 1.0