Fixes to mmlu_pro_llama (#2816)

* Update generation_kwargs in default template to include additional end tokens

* Update filter_list in MMLU Pro configuration to use strict_match

* Update _default_template_yaml

lm_eval/tasks/llama3/instruct/mmlu_pro/_default_template_yaml

@@ -19,9 +19,10 @@ metric_list:
       - "\\.$"
 generation_kwargs:
   do_sample: false
-  until:
-    - "."
+  temperature: 0
   max_gen_toks: 1024
+  until:
+    - []
 filter_list:
   - name: strict_match
     filter:

lm_eval/tasks/llama3/instruct/mmlu_pro/_mmlu_pro.yaml

@@ -18,6 +18,6 @@ aggregate_metric_list:
   - aggregation: mean
     metric: exact_match
     weight_by_size: true
-    filter_list: custom-extract
+    filter_list: [strict_match]
 metadata:
   version: 1.0