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/prost/corypaik_prost.yaml

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

lm_eval/tasks/pubmedqa/pubmedqa.yaml

@@ -13,4 +13,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/qa4mre/qa4mre_2011.yaml

@@ -19,4 +19,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/qasper/bool.yaml

@@ -11,4 +11,4 @@ doc_to_choice: ["no", "yes"]
 metric_list:
   - metric: f1
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/qasper/freeform.yaml

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

lm_eval/tasks/race/race.yaml

@@ -11,4 +11,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 2.0
+  version: 2.0

lm_eval/tasks/realtoxicityprompts/realtoxicityprompts.yaml

@@ -14,4 +14,4 @@ generation_kwargs:
   do_sample: false
   temperature: 0.0
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/sciq/sciq.yaml

@@ -18,4 +18,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/siqa/default.yml

@@ -13,4 +13,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/storycloze/storycloze_2016.yaml

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

lm_eval/tasks/super_glue/boolq/default.yaml

@@ -14,4 +14,4 @@ doc_to_decontamination_query: passage
 metric_list:
   - metric: acc
 metadata:
-  - version: 2.0
+  version: 2.0

lm_eval/tasks/super_glue/boolq/seq2seq.yaml

@@ -23,4 +23,4 @@ metric_list:
     ignore_case: true
     ignore_punctuation: true
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/super_glue/boolq/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/cb/default.yaml

@@ -14,4 +14,4 @@ metric_list:
   - metric: f1
     aggregation: !function "aggregate.cb_multi_fi"
 metadata:
-  - version: 1.0
+  version: 1.0

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

@@ -22,4 +22,4 @@ metric_list:
     aggregation: !function "t5_utils.agg_mean_3class_f1"
     higher_is_better: true
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/super_glue/copa/default.yaml

@@ -12,4 +12,4 @@ doc_to_choice: !function utils.doc_to_choice
 metric_list:
   - metric: acc
 metadata:
-  - version: 1.0
+  version: 1.0

lm_eval/tasks/super_glue/copa/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/multirc/default.yaml

@@ -12,4 +12,4 @@ doc_to_choice: "['''{{answer}}\\nIs the answer correct? yes''', '''{{answer}}\\n
 metric_list:
   - metric: acc
 metadata:
-  - version: 2.0
+  version: 2.0

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

@@ -20,4 +20,4 @@ metric_list:
     aggregation: !function t5_utils.agg_em
     higher_is_better: true
 metadata:
-  - version: 0.0
+  version: 0.0

lm_eval/tasks/super_glue/record/default.yaml

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