merged latest and added altworld files

lm_eval/tasks/blimp/tough_vs_raising_2.yaml

 # Generated by utils.py
 dataset_name: tough_vs_raising_2
-include: template_yaml
+include: _template_yaml
 task: blimp_tough_vs_raising_2

lm_eval/tasks/blimp/transitive.yaml

 # Generated by utils.py
 dataset_name: transitive
-include: template_yaml
+include: _template_yaml
 task: blimp_transitive

lm_eval/tasks/blimp/wh_island.yaml

 # Generated by utils.py
 dataset_name: wh_island
-include: template_yaml
+include: _template_yaml
 task: blimp_wh_island

lm_eval/tasks/blimp/wh_questions_object_gap.yaml

 # Generated by utils.py
 dataset_name: wh_questions_object_gap
-include: template_yaml
+include: _template_yaml
 task: blimp_wh_questions_object_gap

lm_eval/tasks/blimp/wh_questions_subject_gap.yaml

 # Generated by utils.py
 dataset_name: wh_questions_subject_gap
-include: template_yaml
+include: _template_yaml
 task: blimp_wh_questions_subject_gap

lm_eval/tasks/blimp/wh_questions_subject_gap_long_distance.yaml

 # Generated by utils.py
 dataset_name: wh_questions_subject_gap_long_distance
-include: template_yaml
+include: _template_yaml
 task: blimp_wh_questions_subject_gap_long_distance

lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml

 # Generated by utils.py
 dataset_name: wh_vs_that_no_gap
-include: template_yaml
+include: _template_yaml
 task: blimp_wh_vs_that_no_gap

lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml

 # Generated by utils.py
 dataset_name: wh_vs_that_no_gap_long_distance
-include: template_yaml
+include: _template_yaml
 task: blimp_wh_vs_that_no_gap_long_distance

lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml

 # Generated by utils.py
 dataset_name: wh_vs_that_with_gap
-include: template_yaml
+include: _template_yaml
 task: blimp_wh_vs_that_with_gap

lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml

 # Generated by utils.py
 dataset_name: wh_vs_that_with_gap_long_distance
-include: template_yaml
+include: _template_yaml
 task: blimp_wh_vs_that_with_gap_long_distance

lm_eval/tasks/ceval/_default_ceval_yaml

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

lm_eval/tasks/cmmlu/_default_template_yaml

@@ -15,3 +15,5 @@ metric_list:
   - metric: acc_norm
     aggregation: mean
     higher_is_better: true
+metadata:
+  - version: 0.0

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

@@ -17,3 +17,5 @@ metric_list:
   - metric: !function bleu.smoothed_bleu_4
     aggregation: mean
     higher_is_better: True
+metadata:
+  - version: 0.0

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

@@ -17,3 +17,5 @@ metric_list:
   - metric: !function bleu.smoothed_bleu_4
     aggregation: mean
     higher_is_better: True
+metadata:
+  - version: 0.0

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

@@ -17,3 +17,5 @@ metric_list:
   - metric: !function bleu.smoothed_bleu_4
     aggregation: mean
     higher_is_better: True
+metadata:
+  - version: 0.0

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

@@ -17,3 +17,5 @@ metric_list:
   - metric: !function bleu.smoothed_bleu_4
     aggregation: mean
     higher_is_better: True
+metadata:
+  - version: 0.0

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

@@ -17,3 +17,5 @@ metric_list:
   - metric: !function bleu.smoothed_bleu_4
     aggregation: mean
     higher_is_better: True
+metadata:
+  - version: 0.0

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

@@ -17,3 +17,5 @@ metric_list:
   - metric: !function bleu.smoothed_bleu_4
     aggregation: mean
     higher_is_better: True
+metadata:
+  - version: 2.0

lm_eval/tasks/coqa/default.yaml

@@ -18,3 +18,5 @@ metric_list:
   - metric: f1
     aggregation: mean
     higher_is_better: true
+metadata:
+  - version: 2.0

lm_eval/tasks/crows_pairs/crows_pairs_english.yaml

@@ -19,3 +19,5 @@ metric_list:
   - metric: pct_stereotype
     aggregation: mean
     higher_is_better: false
+metadata:
+  - version: 1.0