Merge branch 'big-refactor' of...

Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into port_master_squadv2

lm_eval/evaluator.py

@@ -559,8 +559,6 @@ def evaluate(
             task_hierarchy, task_order, versions, task_group_alias
         )
 
-        _results_agg = collections.defaultdict(dict)
-        _versions = collections.defaultdict(dict)
         for task in results_agg:
             task_results = results_agg[task]
 
@@ -574,15 +572,10 @@ def evaluate(
 
             if task in task_group_alias:
                 task_alias = task_group_alias[task]
-                _results_agg[tab_string + task_alias] = task_results
-                _versions[tab_string + task_alias] = versions[task]
+                results_agg[task]["alias"] = tab_string + task_alias
             else:
-                _results_agg[tab_string + task] = task_results
-                _versions[tab_string + task] = versions[task]
-        results_agg = _results_agg
-        versions = _versions
+                results_agg[task]["alias"] = tab_string + task
 
-        _groups_agg = collections.defaultdict(dict)
         for group in groups_agg:
             group_results = groups_agg[group]
 
@@ -596,10 +589,9 @@ def evaluate(
 
             if group in task_group_alias:
                 group_alias = task_group_alias[group]
-                _groups_agg[tab_string + group_alias] = group_results
+                groups_agg[group]["alias"] = tab_string + group_alias
             else:
-                _groups_agg[tab_string + group] = group_results
-        groups_agg = _groups_agg
+                groups_agg[group]["alias"] = tab_string + group
 
         results_dict = {
             "results": dict(results_agg.items()),

lm_eval/tasks/mmlu/default/_default_template_yaml

-group: mmlu
 dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
 test_split: test
 fewshot_split: dev

lm_eval/tasks/mmlu/flan_cot_fewshot/_mmlu_flan_cot_fewshot_template_yaml

-group: mmlu_flan_cot_fewshot
 dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
 validation_split: validation
 fewshot_split: dev

lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu_flan_cot_zeroshot_template_yaml

-group: mmlu_flan_cot_zeroshot
 dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
 validation_split: validation
 fewshot_split: dev

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu.yaml

-group: mmlu_flan_n_shot_generative
+group: mmlu_flan_n_shot_loglikelihood
 task:
-  - mmlu_flan_n_shot_generative_stem
-  - mmlu_flan_n_shot_generative_other
-  - mmlu_flan_n_shot_generative_social_sciences
-  - mmlu_flan_n_shot_generative_humanities
+  - mmlu_flan_n_shot_loglikelihood_stem
+  - mmlu_flan_n_shot_loglikelihood_other
+  - mmlu_flan_n_shot_loglikelihood_social_sciences
+  - mmlu_flan_n_shot_loglikelihood_humanities

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu_flan_loglikelihood_template_yaml

-group: mmlu_flan_n_shot_loglikelihood
 dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
 test_split: test
 fewshot_split: dev

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_abstract_algebra.yaml

 "dataset_name": "abstract_algebra"
 "description": "The following are multiple choice questions (with answers) about abstract\
   \ algebra.\n\n"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_abstract_algebra"
+"task": "mmlu_flan_n_shot_loglikelihood_abstract_algebra"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_anatomy.yaml

 "dataset_name": "anatomy"
 "description": "The following are multiple choice questions (with answers) about anatomy.\n\
   \n"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_anatomy"
+"task": "mmlu_flan_n_shot_loglikelihood_anatomy"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_astronomy.yaml

 "dataset_name": "astronomy"
 "description": "The following are multiple choice questions (with answers) about astronomy.\n\
   \n"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_astronomy"
+"task": "mmlu_flan_n_shot_loglikelihood_astronomy"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_business_ethics.yaml

 "dataset_name": "business_ethics"
 "description": "The following are multiple choice questions (with answers) about business\
   \ ethics.\n\n"
-"group": "mmlu_flan_n_shot_generative_other"
+"group": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_business_ethics"
+"task": "mmlu_flan_n_shot_loglikelihood_business_ethics"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_clinical_knowledge.yaml

 "dataset_name": "clinical_knowledge"
 "description": "The following are multiple choice questions (with answers) about clinical\
   \ knowledge.\n\n"
-"group": "mmlu_flan_n_shot_generative_other"
+"group": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_clinical_knowledge"
+"task": "mmlu_flan_n_shot_loglikelihood_clinical_knowledge"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_biology.yaml

 "dataset_name": "college_biology"
 "description": "The following are multiple choice questions (with answers) about college\
   \ biology.\n\n"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_college_biology"
+"task": "mmlu_flan_n_shot_loglikelihood_college_biology"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_chemistry.yaml

 "dataset_name": "college_chemistry"
 "description": "The following are multiple choice questions (with answers) about college\
   \ chemistry.\n\n"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_college_chemistry"
+"task": "mmlu_flan_n_shot_loglikelihood_college_chemistry"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_computer_science.yaml

 "dataset_name": "college_computer_science"
 "description": "The following are multiple choice questions (with answers) about college\
   \ computer science.\n\n"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_college_computer_science"
+"task": "mmlu_flan_n_shot_loglikelihood_college_computer_science"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_mathematics.yaml

 "dataset_name": "college_mathematics"
 "description": "The following are multiple choice questions (with answers) about college\
   \ mathematics.\n\n"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_college_mathematics"
+"task": "mmlu_flan_n_shot_loglikelihood_college_mathematics"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_medicine.yaml

 "dataset_name": "college_medicine"
 "description": "The following are multiple choice questions (with answers) about college\
   \ medicine.\n\n"
-"group": "mmlu_flan_n_shot_generative_other"
+"group": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_college_medicine"
+"task": "mmlu_flan_n_shot_loglikelihood_college_medicine"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_physics.yaml

 "dataset_name": "college_physics"
 "description": "The following are multiple choice questions (with answers) about college\
   \ physics.\n\n"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_college_physics"
+"task": "mmlu_flan_n_shot_loglikelihood_college_physics"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_computer_security.yaml

 "dataset_name": "computer_security"
 "description": "The following are multiple choice questions (with answers) about computer\
   \ security.\n\n"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_computer_security"
+"task": "mmlu_flan_n_shot_loglikelihood_computer_security"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_conceptual_physics.yaml

 "dataset_name": "conceptual_physics"
 "description": "The following are multiple choice questions (with answers) about conceptual\
   \ physics.\n\n"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_conceptual_physics"
+"task": "mmlu_flan_n_shot_loglikelihood_conceptual_physics"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_econometrics.yaml

 "dataset_name": "econometrics"
 "description": "The following are multiple choice questions (with answers) about econometrics.\n\
   \n"
-"group": "mmlu_flan_n_shot_generative_social_sciences"
+"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_econometrics"
+"task": "mmlu_flan_n_shot_loglikelihood_econometrics"