Merge branch 'big-refactor' of...

Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into num_fewshot_fix

lm_eval/tasks/wikitext/wikitext.yaml

@@ -14,3 +14,5 @@ metric_list:
   - metric: word_perplexity
   - metric: byte_perplexity
   - metric: bits_per_byte
+metadata:
+  - version: 2.0

lm_eval/tasks/winogrande/default.yaml

@@ -13,3 +13,5 @@ metric_list:
   - metric: acc
     aggregation: mean
     higher_is_better: true
+metadata:
+  - version: 1.0

lm_eval/tasks/wmt2016/ro_en-t5_prompt.yaml

@@ -15,3 +15,5 @@ metric_list:
   - metric: !function metrics.bleu
     aggregation: !function metrics.agg_bleu
     higher_is_better: true
+metadata:
+  - version: 0.0

lm_eval/tasks/wsc273/default.yaml

@@ -13,3 +13,5 @@ metric_list:
   - metric: acc
     aggregation: mean
     higher_is_better: true
+metadata:
+  - version: 1.0

lm_eval/tasks/xcopa/default_et.yaml

@@ -10,3 +10,5 @@ doc_to_target: label
 doc_to_choice: !function utils.doc_to_choice
 metric_list:
   - metric: acc
+metadata:
+  - version: 1.0

lm_eval/tasks/xnli/xnli_common_yaml

@@ -15,3 +15,5 @@ metric_list:
   - metric: acc
     aggregation: mean
     higher_is_better: true
+metadata:
+  - version: 1.0

lm_eval/tasks/xstorycloze/default_ar.yaml

@@ -14,3 +14,5 @@ metric_list:
   - metric: acc
     aggregation: mean
     higher_is_better: true
+metadata:
+  - version: 1.0

lm_eval/tasks/xwinograd/xwinograd_common_yaml

@@ -16,3 +16,5 @@ metric_list:
   - metric: acc
     aggregation: mean
     higher_is_better: true
+metadata:
+  - version: 1.0