sort set to False by default, fix predict_only arg

lm_eval/evaluator.py

@@ -22,7 +22,7 @@ from lm_eval.evaluator_utils import (
     print_writeout,
     run_task_tests,
 )
-from lm_eval.logging_utils import add_env_info, get_git_commit_hash
+from lm_eval.logging.utils import add_env_info, get_git_commit_hash
 from lm_eval.tasks import (
     ConfigurableGroup,
     ConfigurableTask,
@@ -224,7 +224,7 @@ def simple_evaluate(
             if isinstance(task_obj, dict):
                 adjusted_task_dict = {
                     **adjusted_task_dict,
-                    **{task_name: _adjust_config(task_obj)},
+                    **{task_name: _adjust_config(task_obj, predict_only)},
                 }
 
             else:

lm_eval/utils.py

@@ -242,7 +242,7 @@ class Reorderer:
         return res
 
 
-def make_table(result_dict, column: str = "results", sort_results: bool = True):
+def make_table(result_dict, column: str = "results", sort_results: bool = False):
     """Generate table of results."""
     from pytablewriter import LatexTableWriter, MarkdownTableWriter
 
@@ -276,7 +276,10 @@ def make_table(result_dict, column: str = "results", sort_results: bool = True):
     for k in keys:
         dic = result_dict[column][k]
         version = result_dict["versions"].get(k, "    N/A")
-        n = str(result_dict["n-shot"][k])
+        if k in result_dict["n-shot"]:
+            n = str(result_dict["n-shot"][k])
+        else:
+            n = " "
 
         if "alias" in dic:
             k = dic.pop("alias")